fix(backend/copilot): prevent double upload in timeout handling

Previous fix created NEW task after timeout, causing double upload:
- Original shielded task still running
- New task also uploading same transcript

Correct fix: Create task FIRST, then shield it. If timeout occurs,
track the SAME task (no double upload).

Fixes double-upload bug in b8c65e3d2

.agents/skills

@@ -1 +0,0 @@
-../.claude/skills

.claude/settings.json

@@ -1,10 +0,0 @@
-{
-  "permissions": {
-    "allowedTools": [
-      "Read", "Grep", "Glob",
-      "Bash(ls:*)", "Bash(cat:*)", "Bash(grep:*)", "Bash(find:*)",
-      "Bash(git status:*)", "Bash(git diff:*)", "Bash(git log:*)", "Bash(git worktree:*)",
-      "Bash(tmux:*)", "Bash(sleep:*)", "Bash(branchlet:*)"
-    ]
-  }
-}

.claude/skills/open-pr/SKILL.md

@@ -1,106 +0,0 @@
----
-name: open-pr
-description: Open a pull request with proper PR template, test coverage, and review workflow. Guides agents through creating a PR that follows repo conventions, ensures existing behaviors aren't broken, covers new behaviors with tests, and handles review via bot when local testing isn't possible. TRIGGER when user asks to "open a PR", "create a PR", "make a PR", "submit a PR", "open pull request", "push and create PR", or any variation of opening/submitting a pull request.
-user-invocable: true
-args: "[base-branch] — optional target branch (defaults to dev)."
-metadata:
-  author: autogpt-team
-  version: "1.0.0"
----
-
-# Open a Pull Request
-
-## Step 1: Pre-flight checks
-
-Before opening the PR:
-
-1. Ensure all changes are committed
-2. Ensure the branch is pushed to the remote (`git push -u origin <branch>`)
-3. Run linters/formatters across the whole repo (not just changed files) and commit any fixes
-
-## Step 2: Test coverage
-
-**This is critical.** Before opening the PR, verify:
-
-### Existing behavior is not broken
-- Identify which modules/components your changes touch
-- Run the existing test suites for those areas
-- If tests fail, fix them before opening the PR — do not open a PR with known regressions
-
-### New behavior has test coverage
-- Every new feature, endpoint, or behavior change needs tests
-- If you added a new block, add tests for that block
-- If you changed API behavior, add or update API tests
-- If you changed frontend behavior, verify it doesn't break existing flows
-
-If you cannot run the full test suite locally, note which tests you ran and which you couldn't in the test plan.
-
-## Step 3: Create the PR using the repo template
-
-Read the canonical PR template at `.github/PULL_REQUEST_TEMPLATE.md` and use it **verbatim** as your PR body:
-
-1. Read the template: `cat .github/PULL_REQUEST_TEMPLATE.md`
-2. Preserve the exact section titles and formatting, including:
-   - `### Why / What / How`
-   - `### Changes 🏗️`
-   - `### Checklist 📋`
-3. Replace HTML comment prompts (`<!-- ... -->`) with actual content; do not leave them in
-4. **Do not pre-check boxes** — leave all checkboxes as `- [ ]` until each step is actually completed
-5. Do not alter the template structure, rename sections, or remove any checklist items
-
-**PR title must use conventional commit format** (e.g., `feat(backend): add new block`, `fix(frontend): resolve routing bug`, `dx(skills): update PR workflow`). See CLAUDE.md for the full list of scopes.
-
-Use `gh pr create` with the base branch (defaults to `dev` if no `[base-branch]` was provided). Use `--body-file` to avoid shell interpretation of backticks and special characters:
-
-```bash
-BASE_BRANCH="${BASE_BRANCH:-dev}"
-PR_BODY=$(mktemp)
-cat > "$PR_BODY" << 'PREOF'
-<filled-in template from .github/PULL_REQUEST_TEMPLATE.md>
-PREOF
-gh pr create --base "$BASE_BRANCH" --title "<type>(scope): short description" --body-file "$PR_BODY"
-rm "$PR_BODY"
-```
-
-## Step 4: Review workflow
-
-### If you have a workspace that allows testing (docker, running backend, etc.)
-- Run `/pr-test` to do E2E manual testing of the PR using docker compose, agent-browser, and API calls. This is the most thorough way to validate your changes before review.
-- After testing, run `/pr-review` to self-review the PR for correctness, security, code quality, and testing gaps before requesting human review.
-
-### If you do NOT have a workspace that allows testing
-This is common for agents running in worktrees without a full stack. In this case:
-
-1. Run `/pr-review` locally to catch obvious issues before pushing
-2. **Comment `/review` on the PR** after creating it to trigger the review bot
-3. **Poll for the review** rather than blindly waiting — check for new review comments every 30 seconds using `gh api repos/Significant-Gravitas/AutoGPT/pulls/{N}/reviews --paginate` and the GraphQL inline threads query. The bot typically responds within 30 minutes, but polling lets the agent react as soon as it arrives.
-4. Do NOT proceed or merge until the bot review comes back
-5. Address any issues the bot raises — use `/pr-address` which has a full polling loop with CI + comment tracking
-
-```bash
-# After creating the PR:
-PR_NUMBER=$(gh pr view --json number -q .number)
-gh pr comment "$PR_NUMBER" --body "/review"
-# Then use /pr-address to poll for and address the review when it arrives
-```
-
-## Step 5: Address review feedback
-
-Once the review bot or human reviewers leave comments:
-- Run `/pr-address` to address review comments. It will loop until CI is green and all comments are resolved.
-- Do not merge without human approval.
-
-## Related skills
-
-| Skill | When to use |
-|---|---|
-| `/pr-test` | E2E testing with docker compose, agent-browser, API calls — use when you have a running workspace |
-| `/pr-review` | Review for correctness, security, code quality — use before requesting human review |
-| `/pr-address` | Address reviewer comments and loop until CI green — use after reviews come in |
-
-## Step 6: Post-creation
-
-After the PR is created and review is triggered:
-- Share the PR URL with the user
-- If waiting on the review bot, let the user know the expected wait time (~30 min)
-- Do not merge without human approval

.claude/skills/orchestrate/SKILL.md

@@ -1,545 +0,0 @@
----
-name: orchestrate
-description: "Meta-agent supervisor that manages a fleet of Claude Code agents running in tmux windows. Auto-discovers spare worktrees, spawns agents, monitors state, kicks idle agents, approves safe confirmations, and recycles worktrees when done. TRIGGER when user asks to supervise agents, run parallel tasks, manage worktrees, check agent status, or orchestrate parallel work."
-user-invocable: true
-argument-hint: "any free text — e.g. 'start 3 agents on X Y Z', 'show status', 'add task: implement feature A', 'stop', 'how many are free?'"
-metadata:
-  author: autogpt-team
-  version: "6.0.0"
----
-
-# Orchestrate — Agent Fleet Supervisor
-
-One tmux session, N windows — each window is one agent working in its own worktree. Speak naturally; Claude maps your intent to the right scripts.
-
-## Scripts
-
-```bash
-SKILLS_DIR=$(git rev-parse --show-toplevel)/.claude/skills/orchestrate/scripts
-STATE_FILE=~/.claude/orchestrator-state.json
-```
-
-| Script | Purpose |
-|---|---|
-| `find-spare.sh [REPO_ROOT]` | List free worktrees — one `PATH BRANCH` per line |
-| `spawn-agent.sh SESSION PATH SPARE NEW_BRANCH OBJECTIVE [PR_NUMBER] [STEPS...]` | Create window + checkout branch + launch claude + send task. **Stdout: `SESSION:WIN` only** |
-| `recycle-agent.sh WINDOW PATH SPARE_BRANCH` | Kill window + restore spare branch |
-| `run-loop.sh` | **Mechanical babysitter** — idle restart + dialog approval + recycle on ORCHESTRATOR:DONE + supervisor health check + all-done notification |
-| `verify-complete.sh WINDOW` | Verify PR is done: checkpoints ✓ + 0 unresolved threads + CI green + no fresh CHANGES_REQUESTED. Repo auto-derived from state file `.repo` or git remote. |
-| `notify.sh MESSAGE` | Send notification via Discord webhook (env `DISCORD_WEBHOOK_URL` or state `.discord_webhook`), macOS notification center, and stdout |
-| `capacity.sh [REPO_ROOT]` | Print available + in-use worktrees |
-| `status.sh` | Print fleet status + live pane commands |
-| `poll-cycle.sh` | One monitoring cycle — classifies panes, tracks checkpoints, returns JSON action array |
-| `classify-pane.sh WINDOW` | Classify one pane state |
-
-## Supervision model
-
-```
-Orchestrating Claude (this Claude session — IS the supervisor)
-  └── Reads pane output, checks CI, intervenes with targeted guidance
-        run-loop.sh (separate tmux window, every 30s)
-          └── Mechanical only: idle restart, dialog approval, recycle on ORCHESTRATOR:DONE
-```
-
-**You (the orchestrating Claude)** are the supervisor. After spawning agents, stay in this conversation and actively monitor: poll each agent's pane every 2-3 minutes, check CI, nudge stalled agents, and verify completions. Do not spawn a separate supervisor Claude window — it loses context, is hard to observe, and compounds context compression problems.
-
-**run-loop.sh** is the mechanical layer — zero tokens, handles things that need no judgment: restart crashed agents, press Enter on dialogs, recycle completed worktrees (only after `verify-complete.sh` passes).
-
-## Checkpoint protocol
-
-Agents output checkpoints as they complete each required step:
-
-```
-CHECKPOINT:<step-name>
-```
-
-Required steps are passed as args to `spawn-agent.sh` (e.g. `pr-address pr-test`). `run-loop.sh` will not recycle a window until all required checkpoints are found in the pane output. If `verify-complete.sh` fails, the agent is re-briefed automatically.
-
-## Worktree lifecycle
-
-```text
-spare/N branch  →  spawn-agent.sh (--session-id UUID)  →  window + feat/branch + claude running
-                                                                 ↓
-                                               CHECKPOINT:<step> (as steps complete)
-                                                                 ↓
-                                                        ORCHESTRATOR:DONE
-                                                                 ↓
-                                    verify-complete.sh: checkpoints ✓ + 0 threads + CI green + no fresh CHANGES_REQUESTED
-                                                                 ↓
-                                              state → "done", notify, window KEPT OPEN
-                                                                 ↓
-                              user/orchestrator explicitly requests recycle
-                                                                 ↓
-                                         recycle-agent.sh → spare/N (free again)
-```
-
-**Windows are never auto-killed.** The worktree stays on its branch, the session stays alive. The agent is done working but the window, git state, and Claude session are all preserved until you choose to recycle.
-
-**To resume a done or crashed session:**
-```bash
-# Resume by stored session ID (preferred — exact session, full context)
-claude --resume SESSION_ID --permission-mode bypassPermissions
-
-# Or resume most recent session in that worktree directory
-cd /path/to/worktree && claude --continue --permission-mode bypassPermissions
-```
-
-**To manually recycle when ready:**
-```bash
-bash ~/.claude/orchestrator/scripts/recycle-agent.sh SESSION:WIN WORKTREE_PATH spare/N
-# Then update state:
-jq --arg w "SESSION:WIN" '.agents |= map(if .window == $w then .state = "recycled" else . end)' \
-  ~/.claude/orchestrator-state.json > /tmp/orch.tmp && mv /tmp/orch.tmp ~/.claude/orchestrator-state.json
-```
-
-## State file (`~/.claude/orchestrator-state.json`)
-
-Never committed to git. You maintain this file directly using `jq` + atomic writes (`.tmp` → `mv`).
-
-```json
-{
-  "active": true,
-  "tmux_session": "autogpt1",
-  "idle_threshold_seconds": 300,
-  "loop_window": "autogpt1:5",
-  "repo": "Significant-Gravitas/AutoGPT",
-  "discord_webhook": "https://discord.com/api/webhooks/...",
-  "last_poll_at": 0,
-  "agents": [
-    {
-      "window": "autogpt1:3",
-      "worktree": "AutoGPT6",
-      "worktree_path": "/path/to/AutoGPT6",
-      "spare_branch": "spare/6",
-      "branch": "feat/my-feature",
-      "objective": "Implement X and open a PR",
-      "pr_number": "12345",
-      "session_id": "550e8400-e29b-41d4-a716-446655440000",
-      "steps": ["pr-address", "pr-test"],
-      "checkpoints": ["pr-address"],
-      "state": "running",
-      "last_output_hash": "",
-      "last_seen_at": 0,
-      "spawned_at": 0,
-      "idle_since": 0,
-      "revision_count": 0,
-      "last_rebriefed_at": 0
-    }
-  ]
-}
-```
-
-Top-level optional fields:
-- `repo` — GitHub `owner/repo` for CI/thread checks. Auto-derived from git remote if omitted.
-- `discord_webhook` — Discord webhook URL for completion notifications. Also reads `DISCORD_WEBHOOK_URL` env var.
-
-Per-agent fields:
-- `session_id` — UUID passed to `claude --session-id` at spawn; use with `claude --resume UUID` to restore exact session context after a crash or window close.
-- `last_rebriefed_at` — Unix timestamp of last re-brief; enforces 5-min cooldown to prevent spam.
-
-Agent states: `running` | `idle` | `stuck` | `waiting_approval` | `complete` | `done` | `escalated`
-
-`done` means verified complete — window is still open, session still alive, worktree still on task branch. Not recycled yet.
-
-## Serial /pr-test rule
-
-`/pr-test` and `/pr-test --fix` run local Docker + integration tests that use shared ports, a shared database, and shared build caches. **Running two `/pr-test` jobs simultaneously will cause port conflicts and database corruption.**
-
-**Rule: only one `/pr-test` runs at a time. The orchestrator serializes them.**
-
-You (the orchestrating Claude) own the test queue:
-1. Agents do `pr-review` and `pr-address` in parallel — that's safe (they only push code and reply to GitHub).
-2. When a PR needs local testing, add it to your mental queue — don't give agents a `pr-test` step.
-3. Run `/pr-test https://github.com/OWNER/REPO/pull/PR_NUMBER --fix` yourself, sequentially.
-4. Feed results back to the relevant agent via `tmux send-keys`:
-   ```bash
-   tmux send-keys -t SESSION:WIN "Local tests for PR #N: <paste failure output or 'all passed'>. Fix any failures and push, then output ORCHESTRATOR:DONE."
-   sleep 0.3
-   tmux send-keys -t SESSION:WIN Enter
-   ```
-5. Wait for CI to confirm green before marking the agent done.
-
-If multiple PRs need testing at the same time, pick the one furthest along (fewest pending CI checks) and test it first. Only start the next test after the previous one completes.
-
-## Session restore (tested and confirmed)
-
-Agent sessions are saved to disk. To restore a closed or crashed session:
-
-```bash
-# If session_id is in state (preferred):
-NEW_WIN=$(tmux new-window -t SESSION -n WORKTREE_NAME -P -F '#{window_index}')
-tmux send-keys -t "SESSION:${NEW_WIN}" "cd /path/to/worktree && claude --resume SESSION_ID --permission-mode bypassPermissions" Enter
-
-# If no session_id (use --continue for most recent session in that directory):
-tmux send-keys -t "SESSION:${NEW_WIN}" "cd /path/to/worktree && claude --continue --permission-mode bypassPermissions" Enter
-```
-
-`--continue` restores the full conversation history including all tool calls, file edits, and context. The agent resumes exactly where it left off. After restoring, update the window address in the state file:
-
-```bash
-jq --arg old "SESSION:OLD_WIN" --arg new "SESSION:NEW_WIN" \
-  '(.agents[] | select(.window == $old)).window = $new' \
-  ~/.claude/orchestrator-state.json > /tmp/orch.tmp && mv /tmp/orch.tmp ~/.claude/orchestrator-state.json
-```
-
-## Intent → action mapping
-
-Match the user's message to one of these intents:
-
-| The user says something like… | What to do |
-|---|---|
-| "status", "what's running", "show agents" | Run `status.sh` + `capacity.sh`, show output |
-| "how many free", "capacity", "available worktrees" | Run `capacity.sh`, show output |
-| "start N agents on X, Y, Z" or "run these tasks: …" | See **Spawning agents** below |
-| "add task: …", "add one more agent for …" | See **Adding an agent** below |
-| "stop", "shut down", "pause the fleet" | See **Stopping** below |
-| "poll", "check now", "run a cycle" | Run `poll-cycle.sh`, process actions |
-| "recycle window X", "free up autogpt3" | Run `recycle-agent.sh` directly |
-
-When the intent is ambiguous, show capacity first and ask what tasks to run.
-
-## Spawning agents
-
-### 1. Resolve tmux session
-
-```bash
-tmux list-sessions -F "#{session_name}: #{session_windows} windows" 2>/dev/null
-```
-
-Use an existing session. **Never create a tmux session from within Claude** — it becomes a child of Claude's process and dies when the session ends. If no session exists, tell the user to run `tmux new-session -d -s autogpt1` in their terminal first, then re-invoke `/orchestrate`.
-
-### 2. Show available capacity
-
-```bash
-bash $SKILLS_DIR/capacity.sh $(git rev-parse --show-toplevel)
-```
-
-### 3. Collect tasks from the user
-
-For each task, gather:
-- **objective** — what to do (e.g. "implement feature X and open a PR")
-- **branch name** — e.g. `feat/my-feature` (derive from objective if not given)
-- **pr_number** — GitHub PR number if working on an existing PR (for verification)
-- **steps** — required checkpoint names in order (e.g. `pr-address pr-test`) — derive from objective
-
-Ask for `idle_threshold_seconds` only if the user mentions it (default: 300).
-
-Never ask the user to specify a worktree — auto-assign from `find-spare.sh`.
-
-### 4. Spawn one agent per task
-
-```bash
-# Get ordered list of spare worktrees
-SPARE_LIST=$(bash $SKILLS_DIR/find-spare.sh $(git rev-parse --show-toplevel))
-
-# For each task, take the next spare line:
-WORKTREE_PATH=$(echo "$SPARE_LINE" | awk '{print $1}')
-SPARE_BRANCH=$(echo "$SPARE_LINE" | awk '{print $2}')
-
-# With PR number and required steps:
-WINDOW=$(bash $SKILLS_DIR/spawn-agent.sh "$SESSION" "$WORKTREE_PATH" "$SPARE_BRANCH" "$NEW_BRANCH" "$OBJECTIVE" "$PR_NUMBER" "pr-address" "pr-test")
-
-# Without PR (new work):
-WINDOW=$(bash $SKILLS_DIR/spawn-agent.sh "$SESSION" "$WORKTREE_PATH" "$SPARE_BRANCH" "$NEW_BRANCH" "$OBJECTIVE")
-```
-
-Build an agent record and append it to the state file. If the state file doesn't exist yet, initialize it:
-
-```bash
-# Derive repo from git remote (used by verify-complete.sh + supervisor)
-REPO=$(git remote get-url origin 2>/dev/null | sed 's|.*github\.com[:/]||; s|\.git$||' || echo "")
-
-jq -n \
-  --arg session "$SESSION" \
-  --arg repo "$REPO" \
-  --argjson threshold 300 \
-  '{active:true, tmux_session:$session, idle_threshold_seconds:$threshold,
-    repo:$repo, loop_window:null, supervisor_window:null, last_poll_at:0, agents:[]}' \
-  > ~/.claude/orchestrator-state.json
-```
-
-Optionally add a Discord webhook for completion notifications:
-```bash
-jq --arg hook "$DISCORD_WEBHOOK_URL" '.discord_webhook = $hook' ~/.claude/orchestrator-state.json \
-  > /tmp/orch.tmp && mv /tmp/orch.tmp ~/.claude/orchestrator-state.json
-```
-
-`spawn-agent.sh` writes the initial agent record (window, worktree_path, branch, objective, state, etc.) to the state file automatically — **do not append the record again after calling it.** The record already exists and `pr_number`/`steps` are patched in by the script itself.
-
-### 5. Start the mechanical babysitter
-
-```bash
-LOOP_WIN=$(tmux new-window -t "$SESSION" -n "orchestrator" -P -F '#{window_index}')
-LOOP_WINDOW="${SESSION}:${LOOP_WIN}"
-tmux send-keys -t "$LOOP_WINDOW" "bash $SKILLS_DIR/run-loop.sh" Enter
-
-jq --arg w "$LOOP_WINDOW" '.loop_window = $w' ~/.claude/orchestrator-state.json \
-  > /tmp/orch.tmp && mv /tmp/orch.tmp ~/.claude/orchestrator-state.json
-```
-
-### 6. Begin supervising directly in this conversation
-
-You are the supervisor. After spawning, immediately start your first poll loop (see **Supervisor duties** below) and continue every 2-3 minutes. Do NOT spawn a separate supervisor Claude window.
-
-## Adding an agent
-
-Find the next spare worktree, then spawn and append to state — same as steps 2–4 above but for a single task. If no spare worktrees are available, tell the user.
-
-## Supervisor duties (YOUR job, every 2-3 min in this conversation)
-
-You are the supervisor. Run this poll loop directly in your Claude session — not in a separate window.
-
-### Poll loop mechanism
-
-You are reactive — you only act when a tool completes or the user sends a message. To create a self-sustaining poll loop without user involvement:
-
-1. Start each poll with `run_in_background: true` + a sleep before the work:
-   ```bash
-   sleep 120 && tmux capture-pane -t autogpt1:0 -p -S -200 | tail -40
-   # + similar for each active window
-   ```
-2. When the background job notifies you, read the pane output and take action.
-3. Immediately schedule the next background poll — this keeps the loop alive.
-4. Stop scheduling when all agents are done/escalated.
-
-**Never tell the user "I'll poll every 2-3 minutes"** — that does nothing without a trigger. Start the background job instead.
-
-### Each poll: what to check
-
-```bash
-# 1. Read state
-cat ~/.claude/orchestrator-state.json | jq '.agents[] | {window, worktree, branch, state, pr_number, checkpoints}'
-
-# 2. For each running/stuck/idle agent, capture pane
-tmux capture-pane -t SESSION:WIN -p -S -200 | tail -60
-```
-
-For each agent, decide:
-
-| What you see | Action |
-|---|---|
-| Spinner / tools running | Do nothing — agent is working |
-| Idle `❯` prompt, no `ORCHESTRATOR:DONE` | Stalled — send specific nudge with objective from state |
-| Stuck in error loop | Send targeted fix with exact error + solution |
-| Waiting for input / question | Answer and unblock via `tmux send-keys` |
-| CI red | `gh pr checks PR_NUMBER --repo REPO` → tell agent exactly what's failing |
-| Context compacted / agent lost | Send recovery: `cat ~/.claude/orchestrator-state.json | jq '.agents[] | select(.window=="WIN")'` + `gh pr view PR_NUMBER --json title,body` |
-| `ORCHESTRATOR:DONE` in output | Run `verify-complete.sh` — if it fails, re-brief with specific reason |
-
-### Strict ORCHESTRATOR:DONE gate
-
-`verify-complete.sh` handles the main checks automatically (checkpoints, threads, CI green, spawned_at, and CHANGES_REQUESTED). Run it:
-
-**CHANGES_REQUESTED staleness rule**: a `CHANGES_REQUESTED` review only blocks if it was submitted *after* the latest commit. If the latest commit postdates the review, the review is considered stale (feedback already addressed) and does not block. This avoids false negatives when a bot reviewer hasn't re-reviewed after the agent's fixing commits.
-
-```bash
-SKILLS_DIR=~/.claude/orchestrator/scripts
-bash $SKILLS_DIR/verify-complete.sh SESSION:WIN
-```
-
-If it passes → run-loop.sh will recycle the window automatically. No manual action needed.
-If it fails → re-brief the agent with the failure reason. Never manually mark state `done` to bypass this.
-
-### Re-brief a stalled agent
-
-```bash
-OBJ=$(jq -r --arg w SESSION:WIN '.agents[] | select(.window==$w) | .objective' ~/.claude/orchestrator-state.json)
-PR=$(jq -r --arg w SESSION:WIN '.agents[] | select(.window==$w) | .pr_number' ~/.claude/orchestrator-state.json)
-tmux send-keys -t SESSION:WIN "You appear stalled. Your objective: $OBJ. Check: gh pr view $PR --json title,body,headRefName to reorient."
-sleep 0.3
-tmux send-keys -t SESSION:WIN Enter
-```
-
-If `image_path` is set on the agent record, include: "Re-read context at IMAGE_PATH with the Read tool."
-
-## Self-recovery protocol (agents)
-
-spawn-agent.sh automatically includes this instruction in every objective:
-
-> If your context compacts and you lose track of what to do, run:
-> `cat ~/.claude/orchestrator-state.json | jq '.agents[] | select(.window=="SESSION:WIN")'`
-> and `gh pr view PR_NUMBER --json title,body,headRefName` to reorient.
-> Output each completed step as `CHECKPOINT:<step-name>` on its own line.
-
-## Passing images and screenshots to agents
-
-`tmux send-keys` is text-only — you cannot paste a raw image into a pane. To give an agent visual context (screenshots, diagrams, mockups):
-
-1. **Save the image to a temp file** with a stable path:
-   ```bash
-   # If the user drags in a screenshot or you receive a file path:
-   IMAGE_PATH="/tmp/orchestrator-context-$(date +%s).png"
-   cp "$USER_PROVIDED_PATH" "$IMAGE_PATH"
-   ```
-
-2. **Reference the path in the objective string**:
-   ```bash
-   OBJECTIVE="Implement the layout shown in /tmp/orchestrator-context-1234567890.png. Read that image first with the Read tool to understand the design."
-   ```
-
-3. The agent uses its `Read` tool to view the image at startup — Claude Code agents are multimodal and can read image files directly.
-
-**Rule**: always use `/tmp/orchestrator-context-<timestamp>.png` as the naming convention so the supervisor knows what to look for if it needs to re-brief an agent with the same image.
-
----
-
-## Orchestrator final evaluation (YOU decide, not the script)
-
-`verify-complete.sh` is a gate — it blocks premature marking. But it cannot tell you if the work is actually good. That is YOUR job.
-
-When run-loop marks an agent `pending_evaluation` and you're notified, do all of these before marking done:
-
-### 1. Run /pr-test (required, serialized, use TodoWrite to queue)
-
-`/pr-test` is the only reliable confirmation that the objective is actually met. Run it yourself, not the agent.
-
-**When multiple PRs reach `pending_evaluation` at the same time, use TodoWrite to queue them:**
-```
-- [ ] /pr-test PR #12636 — fix copilot retry logic
-- [ ] /pr-test PR #12699 — builder chat panel
-```
-Run one at a time. Check off as you go.
-
-```
-/pr-test https://github.com/Significant-Gravitas/AutoGPT/pull/PR_NUMBER
-```
-
-**/pr-test can be lazy** — if it gives vague output, re-run with full context:
-
-```
-/pr-test https://github.com/OWNER/REPO/pull/PR_NUMBER
-Context: This PR implements <objective from state file>. Key files: <list>.
-Please verify: <specific behaviors to check>.
-```
-
-Only one `/pr-test` at a time — they share ports and DB.
-
-### /pr-test result evaluation
-
-**PARTIAL on any headline feature scenario is an immediate blocker.** Do not approve, do not mark done, do not let the agent output `ORCHESTRATOR:DONE`.
-
-| `/pr-test` result | Action |
-|---|---|
-| All headline scenarios **PASS** | Proceed to evaluation step 2 |
-| Any headline scenario **PARTIAL** | Re-brief the agent immediately — see below |
-| Any headline scenario **FAIL** | Re-brief the agent immediately |
-
-**What PARTIAL means**: the feature is only partly working. Example: the Apply button never appeared, or the AI returned no action blocks. The agent addressed part of the objective but not all of it.
-
-**When any headline scenario is PARTIAL or FAIL:**
-
-1. Do NOT mark the agent done or accept `ORCHESTRATOR:DONE`
-2. Re-brief the agent with the specific scenario that failed and what was missing:
-   ```bash
-   tmux send-keys -t SESSION:WIN "PARTIAL result on /pr-test — S5 (Apply button) never appeared. The AI must output JSON action blocks for the Apply button to render. Fix this before re-running /pr-test."
-   sleep 0.3
-   tmux send-keys -t SESSION:WIN Enter
-   ```
-3. Set state back to `running`:
-   ```bash
-   jq --arg w "SESSION:WIN" '(.agents[] | select(.window == $w)).state = "running"' \
-     ~/.claude/orchestrator-state.json > /tmp/orch.tmp && mv /tmp/orch.tmp ~/.claude/orchestrator-state.json
-   ```
-4. Wait for new `ORCHESTRATOR:DONE`, then re-run `/pr-test` from scratch
-
-**Rule: only ALL-PASS qualifies for approval.** A mix of PASS + PARTIAL is a failure.
-
-> **Why this matters**: PR #12699 was wrongly approved with S5 PARTIAL — the AI never output JSON action blocks so the Apply button never appeared. The fix was already in the agent's reach but slipped through because PARTIAL was not treated as blocking.
-
-### 2. Do your own evaluation
-
-1. **Read the PR diff and objective** — does the code actually implement what was asked? Is anything obviously missing or half-done?
-2. **Read the resolved threads** — were comments addressed with real fixes, or just dismissed/resolved without changes?
-3. **Check CI run names** — any suspicious retries that shouldn't have passed?
-4. **Check the PR description** — title, summary, test plan complete?
-
-### 3. Decide
-
-- `/pr-test` all scenarios PASS + evaluation looks good → mark `done` in state, tell the user the PR is ready, ask if window should be closed
-- `/pr-test` any scenario PARTIAL or FAIL → re-brief the agent with the specific failing scenario, set state back to `running` (see `/pr-test result evaluation` above)
-- Evaluation finds gaps even with all PASS → re-brief the agent with specific gaps, set state back to `running`
-
-**Never mark done based purely on script output.** You hold the full objective context; the script does not.
-
-```bash
-# Mark done after your positive evaluation:
-jq --arg w "SESSION:WIN" '(.agents[] | select(.window == $w)).state = "done"' \
-  ~/.claude/orchestrator-state.json > /tmp/orch.tmp && mv /tmp/orch.tmp ~/.claude/orchestrator-state.json
-```
-
-## When to stop the fleet
-
-Stop the fleet (`active = false`) when **all** of the following are true:
-
-| Check | How to verify |
-|---|---|
-| All agents are `done` or `escalated` | `jq '[.agents[] | select(.state | test("running\|stuck\|idle\|waiting_approval"))] | length' ~/.claude/orchestrator-state.json` == 0 |
-| All PRs have 0 unresolved review threads | GraphQL `isResolved` check per PR |
-| All PRs have green CI **on a run triggered after the agent's last push** | `gh run list --branch BRANCH --limit 1` timestamp > `spawned_at` in state |
-| No fresh CHANGES_REQUESTED (after latest commit) | `verify-complete.sh` checks this — stale pre-commit reviews are ignored |
-| No agents are `escalated` without human review | If any are escalated, surface to user first |
-
-**Do NOT stop just because agents output `ORCHESTRATOR:DONE`.** That is a signal to verify, not a signal to stop.
-
-**Do stop** if the user explicitly says "stop", "shut down", or "kill everything", even with agents still running.
-
-```bash
-# Graceful stop
-jq '.active = false' ~/.claude/orchestrator-state.json > /tmp/orch.tmp \
-  && mv /tmp/orch.tmp ~/.claude/orchestrator-state.json
-
-LOOP_WINDOW=$(jq -r '.loop_window // ""' ~/.claude/orchestrator-state.json)
-[ -n "$LOOP_WINDOW" ] && tmux kill-window -t "$LOOP_WINDOW" 2>/dev/null || true
-```
-
-Does **not** recycle running worktrees — agents may still be mid-task. Run `capacity.sh` to see what's still in progress.
-
-## tmux send-keys pattern
-
-**Always split long messages into text + Enter as two separate calls with a sleep between them.** If sent as one call (`"text" Enter`), Enter can fire before the full string is buffered into Claude's input — leaving the message stuck as `[Pasted text +N lines]` unsent.
-
-```bash
-# CORRECT — text then Enter separately
-tmux send-keys -t "$WINDOW" "your long message here"
-sleep 0.3
-tmux send-keys -t "$WINDOW" Enter
-
-# WRONG — Enter may fire before text is buffered
-tmux send-keys -t "$WINDOW" "your long message here" Enter
-```
-
-Short single-character sends (`y`, `Down`, empty Enter for dialog approval) are safe to combine since they have no buffering lag.
-
----
-
-## Protected worktrees
-
-Some worktrees must **never** be used as spare worktrees for agent tasks because they host files critical to the orchestrator itself:
-
-| Worktree | Protected branch | Why |
-|---|---|---|
-| `AutoGPT1` | `dx/orchestrate-skill` | Hosts the orchestrate skill scripts. `recycle-agent.sh` would check out `spare/1`, wiping `.claude/skills/` and breaking all subsequent `spawn-agent.sh` calls. |
-
-**Rule**: when selecting spare worktrees via `find-spare.sh`, skip any worktree whose CURRENT branch matches a protected branch. If you accidentally spawn an agent in a protected worktree, do not let `recycle-agent.sh` run on it — manually restore the branch after the agent finishes.
-
-When `dx/orchestrate-skill` is merged into `dev`, `AutoGPT1` becomes a normal spare again.
-
----
-
-## Key rules
-
-1. **Scripts do all the heavy lifting** — don't reimplement their logic inline in this file
-2. **Never ask the user to pick a worktree** — auto-assign from `find-spare.sh` output
-3. **Never restart a running agent** — only restart on `idle` kicks (foreground is a shell)
-4. **Auto-dismiss settings dialogs** — if "Enter to confirm" appears, send Down+Enter
-5. **Always `--permission-mode bypassPermissions`** on every spawn
-6. **Escalate after 3 kicks** — mark `escalated`, surface to user
-7. **Atomic state writes** — always write to `.tmp` then `mv`
-8. **Never approve destructive commands** outside the worktree scope — when in doubt, escalate
-9. **Never recycle without verification** — `verify-complete.sh` must pass before recycling
-10. **No TASK.md files** — commit risk; use state file + `gh pr view` for agent context persistence
-11. **Re-brief stalled agents** — read objective from state file + `gh pr view`, send via tmux
-12. **ORCHESTRATOR:DONE is a signal to verify, not to accept** — always run `verify-complete.sh` and check CI run timestamp before recycling
-13. **Protected worktrees** — never use the worktree hosting the skill scripts as a spare
-14. **Images via file path** — save screenshots to `/tmp/orchestrator-context-<ts>.png`, pass path in objective; agents read with the `Read` tool
-15. **Split send-keys** — always separate text and Enter with `sleep 0.3` between calls for long strings

.claude/skills/orchestrate/scripts/capacity.sh

@@ -1,43 +0,0 @@
-#!/usr/bin/env bash
-# capacity.sh — show fleet capacity: available spare worktrees + in-use agents
-#
-# Usage: capacity.sh [REPO_ROOT]
-#   REPO_ROOT defaults to the root worktree of the current git repo.
-#
-# Reads: ~/.claude/orchestrator-state.json (skipped if missing or corrupt)
-
-set -euo pipefail
-
-SCRIPTS_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-STATE_FILE="${ORCHESTRATOR_STATE_FILE:-$HOME/.claude/orchestrator-state.json}"
-REPO_ROOT="${1:-$(git rev-parse --show-toplevel 2>/dev/null || echo "")}"
-
-echo "=== Available (spare) worktrees ==="
-if [ -n "$REPO_ROOT" ]; then
-  SPARE=$("$SCRIPTS_DIR/find-spare.sh" "$REPO_ROOT" 2>/dev/null || echo "")
-else
-  SPARE=$("$SCRIPTS_DIR/find-spare.sh" 2>/dev/null || echo "")
-fi
-
-if [ -z "$SPARE" ]; then
-  echo "  (none)"
-else
-  while IFS= read -r line; do
-    [ -z "$line" ] && continue
-    echo "  ✓ $line"
-  done <<< "$SPARE"
-fi
-
-echo ""
-echo "=== In-use worktrees ==="
-if [ -f "$STATE_FILE" ] && jq -e '.' "$STATE_FILE" >/dev/null 2>&1; then
-  IN_USE=$(jq -r '.agents[] | select(.state != "done") | "  [\(.state)] \(.worktree_path) → \(.branch)"' \
-    "$STATE_FILE" 2>/dev/null || echo "")
-  if [ -n "$IN_USE" ]; then
-    echo "$IN_USE"
-  else
-    echo "  (none)"
-  fi
-else
-  echo "  (no active state file)"
-fi

.claude/skills/orchestrate/scripts/classify-pane.sh

@@ -1,85 +0,0 @@
-#!/usr/bin/env bash
-# classify-pane.sh — Classify the current state of a tmux pane
-#
-# Usage: classify-pane.sh <tmux-target>
-#   tmux-target: e.g. "work:0", "work:1.0"
-#
-# Output (stdout): JSON object:
-#   { "state": "running|idle|waiting_approval|complete", "reason": "...", "pane_cmd": "..." }
-#
-# Exit codes: 0=ok, 1=error (invalid target or tmux window not found)
-
-set -euo pipefail
-
-TARGET="${1:-}"
-
-if [ -z "$TARGET" ]; then
-  echo '{"state":"error","reason":"no target provided","pane_cmd":""}'
-  exit 1
-fi
-
-# Validate tmux target format: session:window or session:window.pane
-if ! [[ "$TARGET" =~ ^[a-zA-Z0-9_.-]+:[a-zA-Z0-9_.-]+(\.[0-9]+)?$ ]]; then
-  echo '{"state":"error","reason":"invalid tmux target format","pane_cmd":""}'
-  exit 1
-fi
-
-# Check session exists (use %%:* to extract session name from session:window)
-if ! tmux list-windows -t "${TARGET%%:*}" &>/dev/null 2>&1; then
-  echo '{"state":"error","reason":"tmux target not found","pane_cmd":""}'
-  exit 1
-fi
-
-# Get the current foreground command in the pane
-PANE_CMD=$(tmux display-message -t "$TARGET" -p '#{pane_current_command}' 2>/dev/null || echo "unknown")
-
-# Capture and strip ANSI codes (use perl for cross-platform compatibility — BSD sed lacks \x1b support)
-RAW=$(tmux capture-pane -t "$TARGET" -p -S -50 2>/dev/null || echo "")
-CLEAN=$(echo "$RAW" | perl -pe 's/\x1b\[[0-9;]*[a-zA-Z]//g; s/\x1b\(B//g; s/\x1b\[\?[0-9]*[hl]//g; s/\r//g' \
-  | grep -v '^[[:space:]]*$' || true)
-
-# --- Check: explicit completion marker ---
-# Must be on its own line (not buried in the objective text sent at spawn time).
-if echo "$CLEAN" | grep -qE "^[[:space:]]*ORCHESTRATOR:DONE[[:space:]]*$"; then
-  jq -n --arg cmd "$PANE_CMD" '{"state":"complete","reason":"ORCHESTRATOR:DONE marker found","pane_cmd":$cmd}'
-  exit 0
-fi
-
-# --- Check: Claude Code approval prompt patterns ---
-LAST_40=$(echo "$CLEAN" | tail -40)
-APPROVAL_PATTERNS=(
-  "Do you want to proceed"
-  "Do you want to make this"
-  "\\[y/n\\]"
-  "\\[Y/n\\]"
-  "\\[n/Y\\]"
-  "Proceed\\?"
-  "Allow this command"
-  "Run bash command"
-  "Allow bash"
-  "Would you like"
-  "Press enter to continue"
-  "Esc to cancel"
-)
-for pattern in "${APPROVAL_PATTERNS[@]}"; do
-  if echo "$LAST_40" | grep -qiE "$pattern"; then
-    jq -n --arg pattern "$pattern" --arg cmd "$PANE_CMD" \
-      '{"state":"waiting_approval","reason":"approval pattern: \($pattern)","pane_cmd":$cmd}'
-    exit 0
-  fi
-done
-
-# --- Check: shell prompt (claude has exited) ---
-# If the foreground process is a shell (not claude/node), the agent has exited
-case "$PANE_CMD" in
-  zsh|bash|fish|sh|dash|tcsh|ksh)
-    jq -n --arg cmd "$PANE_CMD" \
-      '{"state":"idle","reason":"agent exited — shell prompt active","pane_cmd":$cmd}'
-    exit 0
-    ;;
-esac
-
-# Agent is still running (claude/node/python is the foreground process)
-jq -n --arg cmd "$PANE_CMD" \
-  '{"state":"running","reason":"foreground process: \($cmd)","pane_cmd":$cmd}'
-exit 0

.claude/skills/orchestrate/scripts/find-spare.sh

@@ -1,24 +0,0 @@
-#!/usr/bin/env bash
-# find-spare.sh — list worktrees on spare/N branches (free to use)
-#
-# Usage: find-spare.sh [REPO_ROOT]
-#   REPO_ROOT defaults to the root worktree containing the current git repo.
-#
-# Output (stdout): one line per available worktree: "PATH BRANCH"
-#   e.g.: /Users/me/Code/AutoGPT3 spare/3
-
-set -euo pipefail
-
-REPO_ROOT="${1:-$(git rev-parse --show-toplevel 2>/dev/null || echo "")}"
-if [ -z "$REPO_ROOT" ]; then
-  echo "Error: not inside a git repo and no REPO_ROOT provided" >&2
-  exit 1
-fi
-
-git -C "$REPO_ROOT" worktree list --porcelain \
-  | awk '
-      /^worktree / { path = substr($0, 10) }
-      /^branch /   { branch = substr($0, 8); print path " " branch }
-    ' \
-  | { grep -E " refs/heads/spare/[0-9]+$" || true; } \
-  | sed 's|refs/heads/||'

.claude/skills/orchestrate/scripts/notify.sh

@@ -1,40 +0,0 @@
-#!/usr/bin/env bash
-# notify.sh — send a fleet notification message
-#
-# Delivery order (first available wins):
-#   1. Discord webhook — DISCORD_WEBHOOK_URL env var OR state file .discord_webhook
-#   2. macOS notification center — osascript (silent fail if unavailable)
-#   3. Stdout only
-#
-# Usage: notify.sh MESSAGE
-# Exit: always 0 (notification failure must not abort the caller)
-
-MESSAGE="${1:-}"
-[ -z "$MESSAGE" ] && exit 0
-
-STATE_FILE="${ORCHESTRATOR_STATE_FILE:-$HOME/.claude/orchestrator-state.json}"
-
-# --- Resolve Discord webhook ---
-WEBHOOK="${DISCORD_WEBHOOK_URL:-}"
-if [ -z "$WEBHOOK" ] && [ -f "$STATE_FILE" ]; then
-  WEBHOOK=$(jq -r '.discord_webhook // ""' "$STATE_FILE" 2>/dev/null || echo "")
-fi
-
-# --- Discord delivery ---
-if [ -n "$WEBHOOK" ]; then
-  PAYLOAD=$(jq -n --arg msg "$MESSAGE" '{"content": $msg}')
-  curl -s -X POST "$WEBHOOK" \
-    -H "Content-Type: application/json" \
-    -d "$PAYLOAD" > /dev/null 2>&1 || true
-fi
-
-# --- macOS notification center (silent if not macOS or osascript missing) ---
-if command -v osascript &>/dev/null 2>&1; then
-  # Escape single quotes for AppleScript
-  SAFE_MSG=$(echo "$MESSAGE" | sed "s/'/\\\\'/g")
-  osascript -e "display notification \"${SAFE_MSG}\" with title \"Orchestrator\"" 2>/dev/null || true
-fi
-
-# Always print to stdout so run-loop.sh logs it
-echo "$MESSAGE"
-exit 0

.claude/skills/orchestrate/scripts/poll-cycle.sh

@@ -1,257 +0,0 @@
-#!/usr/bin/env bash
-# poll-cycle.sh — Single orchestrator poll cycle
-#
-# Reads ~/.claude/orchestrator-state.json, classifies each agent, updates state,
-# and outputs a JSON array of actions for Claude to take.
-#
-# Usage: poll-cycle.sh
-# Output (stdout): JSON array of action objects
-#   [{ "window": "work:0", "action": "kick|approve|none", "state": "...",
-#      "worktree": "...", "objective": "...", "reason": "..." }]
-#
-# The state file is updated in-place (atomic write via .tmp).
-
-set -euo pipefail
-
-STATE_FILE="${ORCHESTRATOR_STATE_FILE:-$HOME/.claude/orchestrator-state.json}"
-SCRIPTS_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-CLASSIFY="$SCRIPTS_DIR/classify-pane.sh"
-
-# Cross-platform md5: always outputs just the hex digest
-md5_hash() {
-  if command -v md5sum &>/dev/null; then
-    md5sum | awk '{print $1}'
-  else
-    md5 | awk '{print $NF}'
-  fi
-}
-
-# Clean up temp file on any exit (avoids stale .tmp if jq write fails)
-trap 'rm -f "${STATE_FILE}.tmp"' EXIT
-
-# Ensure state file exists
-if [ ! -f "$STATE_FILE" ]; then
-  echo '{"active":false,"agents":[]}' > "$STATE_FILE"
-fi
-
-# Validate JSON upfront before any jq reads that run under set -e.
-# A truncated/corrupt file (e.g. from a SIGKILL mid-write) would otherwise
-# abort the script at the ACTIVE read below without emitting any JSON output.
-if ! jq -e '.' "$STATE_FILE" >/dev/null 2>&1; then
-  echo "State file parse error — check $STATE_FILE" >&2
-  echo "[]"
-  exit 0
-fi
-
-ACTIVE=$(jq -r '.active // false' "$STATE_FILE")
-if [ "$ACTIVE" != "true" ]; then
-  echo "[]"
-  exit 0
-fi
-
-NOW=$(date +%s)
-IDLE_THRESHOLD=$(jq -r '.idle_threshold_seconds // 300' "$STATE_FILE")
-
-ACTIONS="[]"
-UPDATED_AGENTS="[]"
-
-# Read agents as newline-delimited JSON objects.
-# jq exits non-zero when .agents[] has no matches on an empty array, which is valid —
-# so we suppress that exit code and separately validate the file is well-formed JSON.
-if ! AGENTS_JSON=$(jq -e -c '.agents // empty | .[]' "$STATE_FILE" 2>/dev/null); then
-  if ! jq -e '.' "$STATE_FILE" > /dev/null 2>&1; then
-    echo "State file parse error — check $STATE_FILE" >&2
-  fi
-  echo "[]"
-  exit 0
-fi
-
-if [ -z "$AGENTS_JSON" ]; then
-  echo "[]"
-  exit 0
-fi
-
-while IFS= read -r agent; do
-  [ -z "$agent" ] && continue
-
-  # Use // "" defaults so a single malformed field doesn't abort the whole cycle
-  WINDOW=$(echo "$agent"   | jq -r '.window // ""')
-  WORKTREE=$(echo "$agent" | jq -r '.worktree // ""')
-  OBJECTIVE=$(echo "$agent"| jq -r '.objective // ""')
-  STATE=$(echo "$agent"    | jq -r '.state // "running"')
-  LAST_HASH=$(echo "$agent"| jq -r '.last_output_hash // ""')
-  IDLE_SINCE=$(echo "$agent"| jq -r '.idle_since // 0')
-  REVISION_COUNT=$(echo "$agent"| jq -r '.revision_count // 0')
-
-  # Validate window format to prevent tmux target injection.
-  # Allow session:window (numeric or named) and session:window.pane
-  if ! [[ "$WINDOW" =~ ^[a-zA-Z0-9_.-]+:[a-zA-Z0-9_.-]+(\.[0-9]+)?$ ]]; then
-    echo "Skipping agent with invalid window value: $WINDOW" >&2
-    UPDATED_AGENTS=$(echo "$UPDATED_AGENTS" | jq --argjson a "$agent" '. + [$a]')
-    continue
-  fi
-
-  # Pass-through terminal-state agents
-  if [[ "$STATE" == "done" || "$STATE" == "escalated" || "$STATE" == "complete" || "$STATE" == "pending_evaluation" ]]; then
-    UPDATED_AGENTS=$(echo "$UPDATED_AGENTS" | jq --argjson a "$agent" '. + [$a]')
-    continue
-  fi
-
-  # Classify pane.
-  # classify-pane.sh always emits JSON before exit (even on error), so using
-  # "|| echo '...'" would concatenate two JSON objects when it exits non-zero.
-  # Use "|| true" inside the substitution so set -euo pipefail does not abort
-  # the poll cycle when classify exits with a non-zero status code.
-  CLASSIFICATION=$("$CLASSIFY" "$WINDOW" 2>/dev/null || true)
-  [ -z "$CLASSIFICATION" ] && CLASSIFICATION='{"state":"error","reason":"classify failed","pane_cmd":"unknown"}'
-
-  PANE_STATE=$(echo "$CLASSIFICATION" | jq -r '.state')
-  PANE_REASON=$(echo "$CLASSIFICATION" | jq -r '.reason')
-
-  # Capture full pane output once — used for hash (stuck detection) and checkpoint parsing.
-  # Use -S -500 to get the last ~500 lines of scrollback so checkpoints aren't missed.
-  RAW=$(tmux capture-pane -t "$WINDOW" -p -S -500 2>/dev/null || echo "")
-
-  # --- Checkpoint tracking ---
-  # Parse any "CHECKPOINT:<step>" lines the agent has output and merge into state file.
-  # The agent writes these as it completes each required step so verify-complete.sh can gate recycling.
-  EXISTING_CPS=$(echo "$agent" | jq -c '.checkpoints // []')
-  NEW_CHECKPOINTS_JSON="$EXISTING_CPS"
-  if [ -n "$RAW" ]; then
-    FOUND_CPS=$(echo "$RAW" \
-      | grep -oE "CHECKPOINT:[a-zA-Z0-9_-]+" \
-      | sed 's/CHECKPOINT://' \
-      | sort -u \
-      | jq -R . | jq -s . 2>/dev/null || echo "[]")
-    NEW_CHECKPOINTS_JSON=$(jq -n \
-      --argjson existing "$EXISTING_CPS" \
-      --argjson found "$FOUND_CPS" \
-      '($existing + $found) | unique' 2>/dev/null || echo "$EXISTING_CPS")
-  fi
-
-  # Compute content hash for stuck-detection (only for running agents)
-  CURRENT_HASH=""
-  if [[ "$PANE_STATE" == "running" ]] && [ -n "$RAW" ]; then
-    CURRENT_HASH=$(echo "$RAW" | tail -20 | md5_hash)
-  fi
-
-  NEW_STATE="$STATE"
-  NEW_IDLE_SINCE="$IDLE_SINCE"
-  NEW_REVISION_COUNT="$REVISION_COUNT"
-  ACTION="none"
-  REASON="$PANE_REASON"
-
-  case "$PANE_STATE" in
-    complete)
-      # Agent output ORCHESTRATOR:DONE — mark pending_evaluation so orchestrator handles it.
-      # run-loop does NOT verify or notify; orchestrator's background poll picks this up.
-      NEW_STATE="pending_evaluation"
-      ACTION="complete"  # run-loop logs it but takes no action
-      ;;
-    waiting_approval)
-      NEW_STATE="waiting_approval"
-      ACTION="approve"
-      ;;
-    idle)
-      # Agent process has exited — needs restart
-      NEW_STATE="idle"
-      ACTION="kick"
-      REASON="agent exited (shell is foreground)"
-      NEW_REVISION_COUNT=$(( REVISION_COUNT + 1 ))
-      NEW_IDLE_SINCE=$NOW
-      if [ "$NEW_REVISION_COUNT" -ge 3 ]; then
-        NEW_STATE="escalated"
-        ACTION="none"
-        REASON="escalated after ${NEW_REVISION_COUNT} kicks — needs human attention"
-      fi
-      ;;
-    running)
-      # Clear idle_since only when transitioning from idle (agent was kicked and
-      # restarted). Do NOT reset for stuck — idle_since must persist across polls
-      # so STUCK_DURATION can accumulate and trigger escalation.
-      # Also update the local IDLE_SINCE so the hash-stability check below uses
-      # the reset value on this same poll, not the stale kick timestamp.
-      if [[ "$STATE" == "idle" ]]; then
-        NEW_IDLE_SINCE=0
-        IDLE_SINCE=0
-      fi
-      # Check if hash has been stable (agent may be stuck mid-task)
-      if [ -n "$CURRENT_HASH" ] && [ "$CURRENT_HASH" = "$LAST_HASH" ] && [ "$LAST_HASH" != "" ]; then
-        if [ "$IDLE_SINCE" = "0" ] || [ "$IDLE_SINCE" = "null" ]; then
-          NEW_IDLE_SINCE=$NOW
-        else
-          STUCK_DURATION=$(( NOW - IDLE_SINCE ))
-          if [ "$STUCK_DURATION" -gt "$IDLE_THRESHOLD" ]; then
-            NEW_REVISION_COUNT=$(( REVISION_COUNT + 1 ))
-            NEW_IDLE_SINCE=$NOW
-            if [ "$NEW_REVISION_COUNT" -ge 3 ]; then
-              NEW_STATE="escalated"
-              ACTION="none"
-              REASON="escalated after ${NEW_REVISION_COUNT} kicks — needs human attention"
-            else
-              NEW_STATE="stuck"
-              ACTION="kick"
-              REASON="output unchanged for ${STUCK_DURATION}s (threshold: ${IDLE_THRESHOLD}s)"
-            fi
-          fi
-        fi
-      else
-        # Only reset the idle timer when we have a valid hash comparison (pane
-        # capture succeeded). If CURRENT_HASH is empty (tmux capture-pane failed),
-        # preserve existing timers so stuck detection is not inadvertently reset.
-        if [ -n "$CURRENT_HASH" ]; then
-          NEW_STATE="running"
-          NEW_IDLE_SINCE=0
-        fi
-      fi
-      ;;
-    error)
-      REASON="classify error: $PANE_REASON"
-      ;;
-  esac
-
-  # Build updated agent record (ensure idle_since and revision_count are numeric)
-  # Use || true on each jq call so a malformed field skips this agent rather than
-  # aborting the entire poll cycle under set -e.
-  UPDATED_AGENT=$(echo "$agent" | jq \
-    --arg state "$NEW_STATE" \
-    --arg hash "$CURRENT_HASH" \
-    --argjson now "$NOW" \
-    --arg idle_since "$NEW_IDLE_SINCE" \
-    --arg revision_count "$NEW_REVISION_COUNT" \
-    --argjson checkpoints "$NEW_CHECKPOINTS_JSON" \
-    '.state = $state
-     | .last_output_hash = (if $hash == "" then .last_output_hash else $hash end)
-     | .last_seen_at = $now
-     | .idle_since = ($idle_since | tonumber)
-     | .revision_count = ($revision_count | tonumber)
-     | .checkpoints = $checkpoints' 2>/dev/null) || {
-    echo "Warning: failed to build updated agent for window $WINDOW — keeping original" >&2
-    UPDATED_AGENTS=$(echo "$UPDATED_AGENTS" | jq --argjson a "$agent" '. + [$a]')
-    continue
-  }
-
-  UPDATED_AGENTS=$(echo "$UPDATED_AGENTS" | jq --argjson a "$UPDATED_AGENT" '. + [$a]')
-
-  # Add action if needed
-  if [ "$ACTION" != "none" ]; then
-    ACTION_OBJ=$(jq -n \
-      --arg window "$WINDOW" \
-      --arg action "$ACTION" \
-      --arg state "$NEW_STATE" \
-      --arg worktree "$WORKTREE" \
-      --arg objective "$OBJECTIVE" \
-      --arg reason "$REASON" \
-      '{window:$window, action:$action, state:$state, worktree:$worktree, objective:$objective, reason:$reason}')
-    ACTIONS=$(echo "$ACTIONS" | jq --argjson a "$ACTION_OBJ" '. + [$a]')
-  fi
-
-done <<< "$AGENTS_JSON"
-
-# Atomic state file update
-jq --argjson agents "$UPDATED_AGENTS" \
-   --argjson now "$NOW" \
-   '.agents = $agents | .last_poll_at = $now' \
-   "$STATE_FILE" > "${STATE_FILE}.tmp" && mv "${STATE_FILE}.tmp" "$STATE_FILE"
-
-echo "$ACTIONS"

.claude/skills/orchestrate/scripts/recycle-agent.sh

@@ -1,32 +0,0 @@
-#!/usr/bin/env bash
-# recycle-agent.sh — kill a tmux window and restore the worktree to its spare branch
-#
-# Usage: recycle-agent.sh WINDOW WORKTREE_PATH SPARE_BRANCH
-#   WINDOW        — tmux target, e.g. autogpt1:3
-#   WORKTREE_PATH — absolute path to the git worktree
-#   SPARE_BRANCH  — branch to restore, e.g. spare/6
-#
-# Stdout: one status line
-
-set -euo pipefail
-
-if [ $# -lt 3 ]; then
-  echo "Usage: recycle-agent.sh WINDOW WORKTREE_PATH SPARE_BRANCH" >&2
-  exit 1
-fi
-
-WINDOW="$1"
-WORKTREE_PATH="$2"
-SPARE_BRANCH="$3"
-
-# Kill the tmux window (ignore error — may already be gone)
-tmux kill-window -t "$WINDOW" 2>/dev/null || true
-
-# Restore to spare branch: abort any in-progress operation, then clean
-git -C "$WORKTREE_PATH" rebase --abort 2>/dev/null || true
-git -C "$WORKTREE_PATH" merge --abort 2>/dev/null || true
-git -C "$WORKTREE_PATH" reset --hard HEAD 2>/dev/null
-git -C "$WORKTREE_PATH" clean -fd 2>/dev/null
-git -C "$WORKTREE_PATH" checkout "$SPARE_BRANCH"
-
-echo "Recycled: $(basename "$WORKTREE_PATH") → $SPARE_BRANCH (window $WINDOW closed)"

.claude/skills/orchestrate/scripts/run-loop.sh

@@ -1,176 +0,0 @@
-#!/usr/bin/env bash
-# run-loop.sh — Mechanical babysitter for the agent fleet (runs in its own tmux window)
-#
-# Handles ONLY two things that need no intelligence:
-#   idle    → restart claude using --resume SESSION_ID (or --continue) to restore context
-#   approve → auto-approve safe dialogs, press Enter on numbered-option dialogs
-#
-# Everything else — ORCHESTRATOR:DONE, verification, /pr-test, final evaluation,
-# marking done, deciding to close windows — is the orchestrating Claude's job.
-# poll-cycle.sh sets state to pending_evaluation when ORCHESTRATOR:DONE is detected;
-# the orchestrator's background poll loop handles it from there.
-#
-# Usage: run-loop.sh
-# Env:   POLL_INTERVAL (default: 30), ORCHESTRATOR_STATE_FILE
-
-set -euo pipefail
-
-# Copy scripts to a stable location outside the repo so they survive branch
-# checkouts (e.g. recycle-agent.sh switching spare/N back into this worktree
-# would wipe .claude/skills/orchestrate/scripts if the skill only exists on the
-# current branch).
-_ORIGIN_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-STABLE_SCRIPTS_DIR="$HOME/.claude/orchestrator/scripts"
-mkdir -p "$STABLE_SCRIPTS_DIR"
-cp "$_ORIGIN_DIR"/*.sh "$STABLE_SCRIPTS_DIR/"
-chmod +x "$STABLE_SCRIPTS_DIR"/*.sh
-SCRIPTS_DIR="$STABLE_SCRIPTS_DIR"
-
-STATE_FILE="${ORCHESTRATOR_STATE_FILE:-$HOME/.claude/orchestrator-state.json}"
-POLL_INTERVAL="${POLL_INTERVAL:-30}"   # base interval: 30 seconds
-POLL_IDLE_MAX=300                       # back off up to 5 minutes when nothing is happening
-POLL_CURRENT=$POLL_INTERVAL             # adaptive: starts at base, increases when idle
-
-# ---------------------------------------------------------------------------
-# update_state WINDOW FIELD VALUE
-# ---------------------------------------------------------------------------
-update_state() {
-  local window="$1" field="$2" value="$3"
-  jq --arg w "$window" --arg f "$field" --arg v "$value" \
-    '.agents |= map(if .window == $w then .[$f] = $v else . end)' \
-    "$STATE_FILE" > "${STATE_FILE}.tmp" && mv "${STATE_FILE}.tmp" "$STATE_FILE"
-}
-
-update_state_int() {
-  local window="$1" field="$2" value="$3"
-  jq --arg w "$window" --arg f "$field" --argjson v "$value" \
-    '.agents |= map(if .window == $w then .[$f] = $v else . end)' \
-    "$STATE_FILE" > "${STATE_FILE}.tmp" && mv "${STATE_FILE}.tmp" "$STATE_FILE"
-}
-
-agent_field() {
-  jq -r --arg w "$1" --arg f "$2" \
-    '.agents[] | select(.window == $w) | .[$f] // ""' \
-    "$STATE_FILE" 2>/dev/null
-}
-
-# ---------------------------------------------------------------------------
-# wait_for_prompt WINDOW — wait up to 60s for Claude's ❯ prompt
-# ---------------------------------------------------------------------------
-wait_for_prompt() {
-  local window="$1"
-  for i in $(seq 1 60); do
-    local cmd pane
-    cmd=$(tmux display-message -t "$window" -p '#{pane_current_command}' 2>/dev/null || echo "")
-    pane=$(tmux capture-pane -t "$window" -p 2>/dev/null || echo "")
-    if echo "$pane" | grep -q "Enter to confirm"; then
-      tmux send-keys -t "$window" Down Enter; sleep 2; continue
-    fi
-    [[ "$cmd" == "node" ]] && echo "$pane" | grep -q "❯" && return 0
-    sleep 1
-  done
-  return 1  # timed out
-}
-
-# ---------------------------------------------------------------------------
-# handle_kick WINDOW STATE — only for idle (crashed) agents, not stuck
-# ---------------------------------------------------------------------------
-handle_kick() {
-  local window="$1" state="$2"
-  [[ "$state" != "idle" ]] && return  # stuck agents handled by supervisor
-
-  local worktree_path session_id
-  worktree_path=$(agent_field "$window" "worktree_path")
-  session_id=$(agent_field "$window" "session_id")
-
-  echo "[$(date +%H:%M:%S)] KICK restart  $window — agent exited, resuming session"
-
-  # Resume the exact session so the agent retains full context — no need to re-send objective
-  if [ -n "$session_id" ]; then
-    tmux send-keys -t "$window" "cd '${worktree_path}' && claude --resume '${session_id}' --permission-mode bypassPermissions" Enter
-  else
-    tmux send-keys -t "$window" "cd '${worktree_path}' && claude --continue --permission-mode bypassPermissions" Enter
-  fi
-
-  wait_for_prompt "$window" || echo "[$(date +%H:%M:%S)] KICK WARNING  $window — timed out waiting for ❯"
-}
-
-# ---------------------------------------------------------------------------
-# handle_approve WINDOW — auto-approve dialogs that need no judgment
-# ---------------------------------------------------------------------------
-handle_approve() {
-  local window="$1"
-  local pane_tail
-  pane_tail=$(tmux capture-pane -t "$window" -p 2>/dev/null | tail -3 || echo "")
-
-  # Settings error dialog at startup
-  if echo "$pane_tail" | grep -q "Enter to confirm"; then
-    echo "[$(date +%H:%M:%S)] APPROVE dialog $window — settings error"
-    tmux send-keys -t "$window" Down Enter
-    return
-  fi
-
-  # Numbered-option dialog (e.g. "Do you want to make this edit?")
-  # ❯ is already on option 1 (Yes) — Enter confirms it
-  if echo "$pane_tail" | grep -qE "❯\s*1\." || echo "$pane_tail" | grep -q "Esc to cancel"; then
-    echo "[$(date +%H:%M:%S)] APPROVE edit   $window"
-    tmux send-keys -t "$window" "" Enter
-    return
-  fi
-
-  # y/n prompt for safe operations
-  if echo "$pane_tail" | grep -qiE "(^git |^npm |^pnpm |^poetry |^pytest|^docker |^make |^cargo |^pip |^yarn |curl .*(localhost|127\.0\.0\.1))"; then
-    echo "[$(date +%H:%M:%S)] APPROVE safe   $window"
-    tmux send-keys -t "$window" "y" Enter
-    return
-  fi
-
-  # Anything else — supervisor handles it, just log
-  echo "[$(date +%H:%M:%S)] APPROVE skip   $window — unknown dialog, supervisor will handle"
-}
-
-# ---------------------------------------------------------------------------
-# Main loop
-# ---------------------------------------------------------------------------
-echo "[$(date +%H:%M:%S)] run-loop started (mechanical only, poll ${POLL_INTERVAL}s→${POLL_IDLE_MAX}s adaptive)"
-echo "[$(date +%H:%M:%S)] Supervisor: orchestrating Claude session (not a separate window)"
-echo "---"
-
-while true; do
-  if ! jq -e '.active == true' "$STATE_FILE" >/dev/null 2>&1; then
-    echo "[$(date +%H:%M:%S)] active=false — exiting."
-    exit 0
-  fi
-
-  ACTIONS=$("$SCRIPTS_DIR/poll-cycle.sh" 2>/dev/null || echo "[]")
-  KICKED=0; DONE=0
-
-  while IFS= read -r action; do
-    [ -z "$action" ] && continue
-    WINDOW=$(echo "$action" | jq -r '.window // ""')
-    ACTION=$(echo "$action" | jq -r '.action // ""')
-    STATE=$(echo "$action"  | jq -r '.state // ""')
-
-    case "$ACTION" in
-      kick)     handle_kick "$WINDOW" "$STATE" || true; KICKED=$(( KICKED + 1 )) ;;
-      approve)  handle_approve "$WINDOW" || true ;;
-      complete) DONE=$(( DONE + 1 )) ;;  # poll-cycle already set state=pending_evaluation; orchestrator handles
-    esac
-  done < <(echo "$ACTIONS" | jq -c '.[]' 2>/dev/null || true)
-
-  RUNNING=$(jq '[.agents[] | select(.state | test("running|stuck|waiting_approval|idle"))] | length' \
-    "$STATE_FILE" 2>/dev/null || echo 0)
-
-  echo "[$(date +%H:%M:%S)] Poll — ${RUNNING} running  ${KICKED} kicked  ${DONE} recycled  (next in ${POLL_CURRENT}s)"
-
-  # Adaptive backoff: reset to base on activity or waiting_approval agents; back off when truly idle
-  WAITING=$(jq '[.agents[] | select(.state == "waiting_approval")] | length' "$STATE_FILE" 2>/dev/null || echo 0)
-  if (( KICKED > 0 || DONE > 0 || WAITING > 0 )); then
-    POLL_CURRENT=$POLL_INTERVAL
-  else
-    POLL_CURRENT=$(( POLL_CURRENT * 3 / 2 ))
-    (( POLL_CURRENT > POLL_IDLE_MAX )) && POLL_CURRENT=$POLL_IDLE_MAX
-  fi
-
-  sleep "$POLL_CURRENT"
-done

.claude/skills/orchestrate/scripts/spawn-agent.sh

@@ -1,122 +0,0 @@
-#!/usr/bin/env bash
-# spawn-agent.sh — create tmux window, checkout branch, launch claude, send task
-#
-# Usage: spawn-agent.sh SESSION WORKTREE_PATH SPARE_BRANCH NEW_BRANCH OBJECTIVE [PR_NUMBER] [STEPS...]
-#   SESSION       — tmux session name, e.g. autogpt1
-#   WORKTREE_PATH — absolute path to the git worktree
-#   SPARE_BRANCH  — spare branch being replaced, e.g. spare/6 (saved for recycle)
-#   NEW_BRANCH    — task branch to create, e.g. feat/my-feature
-#   OBJECTIVE     — task description sent to the agent
-#   PR_NUMBER     — (optional) GitHub PR number for completion verification
-#   STEPS...      — (optional) required checkpoint names, e.g. pr-address pr-test
-#
-# Stdout: SESSION:WINDOW_INDEX (nothing else — callers rely on this)
-# Exit non-zero on failure.
-
-set -euo pipefail
-
-if [ $# -lt 5 ]; then
-  echo "Usage: spawn-agent.sh SESSION WORKTREE_PATH SPARE_BRANCH NEW_BRANCH OBJECTIVE [PR_NUMBER] [STEPS...]" >&2
-  exit 1
-fi
-
-SESSION="$1"
-WORKTREE_PATH="$2"
-SPARE_BRANCH="$3"
-NEW_BRANCH="$4"
-OBJECTIVE="$5"
-PR_NUMBER="${6:-}"
-STEPS=("${@:7}")
-WORKTREE_NAME=$(basename "$WORKTREE_PATH")
-STATE_FILE="${ORCHESTRATOR_STATE_FILE:-$HOME/.claude/orchestrator-state.json}"
-
-# Generate a stable session ID so this agent's Claude session can always be resumed:
-#   claude --resume $SESSION_ID --permission-mode bypassPermissions
-SESSION_ID=$(uuidgen 2>/dev/null || python3 -c "import uuid; print(uuid.uuid4())")
-
-# Create (or switch to) the task branch
-git -C "$WORKTREE_PATH" checkout -b "$NEW_BRANCH" 2>/dev/null \
-  || git -C "$WORKTREE_PATH" checkout "$NEW_BRANCH"
-
-# Open a new named tmux window; capture its numeric index
-WIN_IDX=$(tmux new-window -t "$SESSION" -n "$WORKTREE_NAME" -P -F '#{window_index}')
-WINDOW="${SESSION}:${WIN_IDX}"
-
-# Append the initial agent record to the state file so subsequent jq updates find it.
-# This must happen before the pr_number/steps update below.
-if [ -f "$STATE_FILE" ]; then
-  NOW=$(date +%s)
-  jq --arg window "$WINDOW" \
-     --arg worktree "$WORKTREE_NAME" \
-     --arg worktree_path "$WORKTREE_PATH" \
-     --arg spare_branch "$SPARE_BRANCH" \
-     --arg branch "$NEW_BRANCH" \
-     --arg objective "$OBJECTIVE" \
-     --arg session_id "$SESSION_ID" \
-     --argjson now "$NOW" \
-     '.agents += [{
-       "window": $window,
-       "worktree": $worktree,
-       "worktree_path": $worktree_path,
-       "spare_branch": $spare_branch,
-       "branch": $branch,
-       "objective": $objective,
-       "session_id": $session_id,
-       "state": "running",
-       "checkpoints": [],
-       "last_output_hash": "",
-       "last_seen_at": $now,
-       "spawned_at": $now,
-       "idle_since": 0,
-       "revision_count": 0,
-       "last_rebriefed_at": 0
-     }]' "$STATE_FILE" > "${STATE_FILE}.tmp" && mv "${STATE_FILE}.tmp" "$STATE_FILE"
-fi
-
-# Store pr_number + steps in state file if provided (enables verify-complete.sh).
-# The agent record was appended above so the jq select now finds it.
-if [ -n "$PR_NUMBER" ] && [ -f "$STATE_FILE" ]; then
-  if [ "${#STEPS[@]}" -gt 0 ]; then
-    STEPS_JSON=$(printf '%s\n' "${STEPS[@]}" | jq -R . | jq -s .)
-  else
-    STEPS_JSON='[]'
-  fi
-  jq --arg w "$WINDOW" --arg pr "$PR_NUMBER" --argjson steps "$STEPS_JSON" \
-    '.agents |= map(if .window == $w then . + {pr_number: $pr, steps: $steps, checkpoints: []} else . end)' \
-    "$STATE_FILE" > "${STATE_FILE}.tmp" && mv "${STATE_FILE}.tmp" "$STATE_FILE"
-fi
-
-# Launch claude with a stable session ID so it can always be resumed after a crash:
-#   claude --resume SESSION_ID --permission-mode bypassPermissions
-tmux send-keys -t "$WINDOW" "cd '${WORKTREE_PATH}' && claude --permission-mode bypassPermissions --session-id '${SESSION_ID}'" Enter
-
-# Wait up to 60s for claude to be fully interactive:
-# both pane_current_command == 'node' AND the '❯' prompt is visible.
-PROMPT_FOUND=false
-for i in $(seq 1 60); do
-  CMD=$(tmux display-message -t "$WINDOW" -p '#{pane_current_command}' 2>/dev/null || echo "")
-  PANE=$(tmux capture-pane -t "$WINDOW" -p 2>/dev/null || echo "")
-  if echo "$PANE" | grep -q "Enter to confirm"; then
-    tmux send-keys -t "$WINDOW" Down Enter
-    sleep 2
-    continue
-  fi
-  if [[ "$CMD" == "node" ]] && echo "$PANE" | grep -q "❯"; then
-    PROMPT_FOUND=true
-    break
-  fi
-  sleep 1
-done
-
-if ! $PROMPT_FOUND; then
-  echo "[spawn-agent] WARNING: timed out waiting for ❯ prompt on $WINDOW — sending objective anyway" >&2
-fi
-
-# Send the task. Split text and Enter — if combined, Enter can fire before the string
-# is fully buffered, leaving the message stuck as "[Pasted text +N lines]" unsent.
-tmux send-keys -t "$WINDOW" "${OBJECTIVE} Output each completed step as CHECKPOINT:<step-name>. When ALL steps are done, output ORCHESTRATOR:DONE on its own line."
-sleep 0.3
-tmux send-keys -t "$WINDOW" Enter
-
-# Only output the window address — nothing else (callers parse this)
-echo "$WINDOW"

.claude/skills/orchestrate/scripts/status.sh

@@ -1,43 +0,0 @@
-#!/usr/bin/env bash
-# status.sh — print orchestrator status: state file summary + live tmux pane commands
-#
-# Usage: status.sh
-# Reads: ~/.claude/orchestrator-state.json
-
-set -euo pipefail
-
-STATE_FILE="${ORCHESTRATOR_STATE_FILE:-$HOME/.claude/orchestrator-state.json}"
-
-if [ ! -f "$STATE_FILE" ] || ! jq -e '.' "$STATE_FILE" >/dev/null 2>&1; then
-  echo "No orchestrator state found at $STATE_FILE"
-  exit 0
-fi
-
-# Header: active status, session, thresholds, last poll
-jq -r '
-  "=== Orchestrator [\(if .active then "RUNNING" else "STOPPED" end)] ===",
-  "Session: \(.tmux_session // "unknown")  |  Idle threshold: \(.idle_threshold_seconds // 300)s",
-  "Last poll: \(if (.last_poll_at // 0) == 0 then "never" else (.last_poll_at | strftime("%H:%M:%S")) end)",
-  ""
-' "$STATE_FILE"
-
-# Each agent: state, window, worktree/branch, truncated objective
-AGENT_COUNT=$(jq '.agents | length' "$STATE_FILE")
-if [ "$AGENT_COUNT" -eq 0 ]; then
-  echo "  (no agents registered)"
-else
-  jq -r '
-    .agents[] |
-    "  [\(.state | ascii_upcase)] \(.window)  \(.worktree)/\(.branch)",
-    "    \(.objective // "" | .[0:70])"
-  ' "$STATE_FILE"
-fi
-
-echo ""
-
-# Live pane_current_command for non-done agents
-while IFS= read -r WINDOW; do
-  [ -z "$WINDOW" ] && continue
-  CMD=$(tmux display-message -t "$WINDOW" -p '#{pane_current_command}' 2>/dev/null || echo "unreachable")
-  echo "  $WINDOW live: $CMD"
-done < <(jq -r '.agents[] | select(.state != "done") | .window' "$STATE_FILE" 2>/dev/null || true)

.claude/skills/orchestrate/scripts/verify-complete.sh

@@ -1,180 +0,0 @@
-#!/usr/bin/env bash
-# verify-complete.sh — verify a PR task is truly done before marking the agent done
-#
-# Check order matters:
-#   1. Checkpoints — did the agent do all required steps?
-#   2. CI complete — no pending (bots post comments AFTER their check runs, must wait)
-#   3. CI passing — no failures (agent must fix before done)
-#   4. spawned_at — a new CI run was triggered after agent spawned (proves real work)
-#   5. Unresolved threads — checked AFTER CI so bot-posted comments are included
-#   6. CHANGES_REQUESTED — checked AFTER CI so bot reviews are included
-#
-# Usage: verify-complete.sh WINDOW
-# Exit 0 = verified complete; exit 1 = not complete (stderr has reason)
-
-set -euo pipefail
-
-WINDOW="$1"
-STATE_FILE="${ORCHESTRATOR_STATE_FILE:-$HOME/.claude/orchestrator-state.json}"
-
-PR_NUMBER=$(jq -r --arg w "$WINDOW" '.agents[] | select(.window == $w) | .pr_number // ""' "$STATE_FILE" 2>/dev/null)
-STEPS=$(jq -r --arg w "$WINDOW" '.agents[] | select(.window == $w) | .steps // [] | .[]' "$STATE_FILE" 2>/dev/null || true)
-CHECKPOINTS=$(jq -r --arg w "$WINDOW" '.agents[] | select(.window == $w) | .checkpoints // [] | .[]' "$STATE_FILE" 2>/dev/null || true)
-WORKTREE_PATH=$(jq -r --arg w "$WINDOW" '.agents[] | select(.window == $w) | .worktree_path // ""' "$STATE_FILE" 2>/dev/null)
-BRANCH=$(jq -r --arg w "$WINDOW" '.agents[] | select(.window == $w) | .branch // ""' "$STATE_FILE" 2>/dev/null)
-SPAWNED_AT=$(jq -r --arg w "$WINDOW" '.agents[] | select(.window == $w) | .spawned_at // "0"' "$STATE_FILE" 2>/dev/null || echo "0")
-
-# No PR number = cannot verify
-if [ -z "$PR_NUMBER" ]; then
-  echo "NOT COMPLETE: no pr_number in state — set pr_number or mark done manually" >&2
-  exit 1
-fi
-
-# --- Check 1: all required steps are checkpointed ---
-MISSING=""
-while IFS= read -r step; do
-  [ -z "$step" ] && continue
-  if ! echo "$CHECKPOINTS" | grep -qFx "$step"; then
-    MISSING="$MISSING $step"
-  fi
-done <<< "$STEPS"
-
-if [ -n "$MISSING" ]; then
-  echo "NOT COMPLETE: missing checkpoints:$MISSING on PR #$PR_NUMBER" >&2
-  exit 1
-fi
-
-# Resolve repo for all GitHub checks below
-REPO=$(jq -r '.repo // ""' "$STATE_FILE" 2>/dev/null || echo "")
-if [ -z "$REPO" ] && [ -n "$WORKTREE_PATH" ] && [ -d "$WORKTREE_PATH" ]; then
-  REPO=$(git -C "$WORKTREE_PATH" remote get-url origin 2>/dev/null \
-    | sed 's|.*github\.com[:/]||; s|\.git$||' || echo "")
-fi
-
-if [ -z "$REPO" ]; then
-  echo "Warning: cannot resolve repo — skipping CI/thread checks" >&2
-  echo "VERIFIED: PR #$PR_NUMBER — checkpoints ✓ (CI/thread checks skipped — no repo)"
-  exit 0
-fi
-
-CI_BUCKETS=$(gh pr checks "$PR_NUMBER" --repo "$REPO" --json bucket 2>/dev/null || echo "[]")
-
-# --- Check 2: CI fully complete — no pending checks ---
-# Pending checks MUST finish before we check threads/reviews:
-# bots (Seer, Check PR Status, etc.) post comments and CHANGES_REQUESTED AFTER their CI check runs.
-PENDING=$(echo "$CI_BUCKETS" | jq '[.[] | select(.bucket == "pending")] | length' 2>/dev/null || echo "0")
-if [ "$PENDING" -gt 0 ]; then
-  PENDING_NAMES=$(gh pr checks "$PR_NUMBER" --repo "$REPO" --json bucket,name 2>/dev/null \
-    | jq -r '[.[] | select(.bucket == "pending") | .name] | join(", ")' 2>/dev/null || echo "unknown")
-  echo "NOT COMPLETE: $PENDING CI checks still pending on PR #$PR_NUMBER ($PENDING_NAMES)" >&2
-  exit 1
-fi
-
-# --- Check 3: CI passing — no failures ---
-FAILING=$(echo "$CI_BUCKETS" | jq '[.[] | select(.bucket == "fail")] | length' 2>/dev/null || echo "0")
-if [ "$FAILING" -gt 0 ]; then
-  FAILING_NAMES=$(gh pr checks "$PR_NUMBER" --repo "$REPO" --json bucket,name 2>/dev/null \
-    | jq -r '[.[] | select(.bucket == "fail") | .name] | join(", ")' 2>/dev/null || echo "unknown")
-  echo "NOT COMPLETE: $FAILING failing CI checks on PR #$PR_NUMBER ($FAILING_NAMES)" >&2
-  exit 1
-fi
-
-# --- Check 4: a new CI run was triggered AFTER the agent spawned ---
-if [ -n "$BRANCH" ] && [ "${SPAWNED_AT:-0}" -gt 0 ]; then
-  LATEST_RUN_AT=$(gh run list --repo "$REPO" --branch "$BRANCH" \
-    --json createdAt --limit 1 2>/dev/null | jq -r '.[0].createdAt // ""')
-  if [ -n "$LATEST_RUN_AT" ]; then
-    if date --version >/dev/null 2>&1; then
-      LATEST_RUN_EPOCH=$(date -d "$LATEST_RUN_AT" "+%s" 2>/dev/null || echo "0")
-    else
-      LATEST_RUN_EPOCH=$(TZ=UTC date -j -f "%Y-%m-%dT%H:%M:%SZ" "$LATEST_RUN_AT" "+%s" 2>/dev/null || echo "0")
-    fi
-    if [ "$LATEST_RUN_EPOCH" -le "$SPAWNED_AT" ]; then
-      echo "NOT COMPLETE: latest CI run on $BRANCH predates agent spawn — agent may not have pushed yet" >&2
-      exit 1
-    fi
-  fi
-fi
-
-OWNER=$(echo "$REPO" | cut -d/ -f1)
-REPONAME=$(echo "$REPO" | cut -d/ -f2)
-
-# --- Check 5: no unresolved review threads (checked AFTER CI — bots post after their check) ---
-UNRESOLVED=$(gh api graphql -f query="
-  { repository(owner: \"${OWNER}\", name: \"${REPONAME}\") {
-      pullRequest(number: ${PR_NUMBER}) {
-        reviewThreads(first: 50) { nodes { isResolved } }
-      }
-    }
-  }
-" --jq '[.data.repository.pullRequest.reviewThreads.nodes[] | select(.isResolved == false)] | length' 2>/dev/null || echo "0")
-
-if [ "$UNRESOLVED" -gt 0 ]; then
-  echo "NOT COMPLETE: $UNRESOLVED unresolved review threads on PR #$PR_NUMBER" >&2
-  exit 1
-fi
-
-# --- Check 6: no CHANGES_REQUESTED (checked AFTER CI — bots post reviews after their check) ---
-# A CHANGES_REQUESTED review is stale if the latest commit was pushed AFTER the review was submitted.
-# Stale reviews (pre-dating the fixing commits) should not block verification.
-#
-# Fetch commits and latestReviews in a single call and fail closed — if gh fails,
-# treat that as NOT COMPLETE rather than silently passing.
-# Use latestReviews (not reviews) so each reviewer's latest state is used — superseded
-# CHANGES_REQUESTED entries are automatically excluded when the reviewer later approved.
-# Note: we intentionally use committedDate (not PR updatedAt) because updatedAt changes on any
-# PR activity (bot comments, label changes) which would create false negatives.
-PR_REVIEW_METADATA=$(gh pr view "$PR_NUMBER" --repo "$REPO" \
-  --json commits,latestReviews 2>/dev/null) || {
-  echo "NOT COMPLETE: unable to fetch PR review metadata for PR #$PR_NUMBER" >&2
-  exit 1
-}
-
-LATEST_COMMIT_DATE=$(jq -r '.commits[-1].committedDate // ""' <<< "$PR_REVIEW_METADATA")
-CHANGES_REQUESTED_REVIEWS=$(jq '[.latestReviews[]? | select(.state == "CHANGES_REQUESTED")]' <<< "$PR_REVIEW_METADATA")
-
-BLOCKING_CHANGES_REQUESTED=0
-BLOCKING_REQUESTERS=""
-
-if [ -n "$LATEST_COMMIT_DATE" ] && [ "$(echo "$CHANGES_REQUESTED_REVIEWS" | jq length)" -gt 0 ]; then
-  if date --version >/dev/null 2>&1; then
-    LATEST_COMMIT_EPOCH=$(date -d "$LATEST_COMMIT_DATE" "+%s" 2>/dev/null || echo "0")
-  else
-    LATEST_COMMIT_EPOCH=$(TZ=UTC date -j -f "%Y-%m-%dT%H:%M:%SZ" "$LATEST_COMMIT_DATE" "+%s" 2>/dev/null || echo "0")
-  fi
-
-  while IFS= read -r review; do
-    [ -z "$review" ] && continue
-    REVIEW_DATE=$(echo "$review" | jq -r '.submittedAt // ""')
-    REVIEWER=$(echo "$review" | jq -r '.author.login // "unknown"')
-    if [ -z "$REVIEW_DATE" ]; then
-      # No submission date — treat as fresh (conservative: blocks verification)
-      BLOCKING_CHANGES_REQUESTED=$(( BLOCKING_CHANGES_REQUESTED + 1 ))
-      BLOCKING_REQUESTERS="${BLOCKING_REQUESTERS:+$BLOCKING_REQUESTERS, }${REVIEWER}"
-    else
-      if date --version >/dev/null 2>&1; then
-        REVIEW_EPOCH=$(date -d "$REVIEW_DATE" "+%s" 2>/dev/null || echo "0")
-      else
-        REVIEW_EPOCH=$(TZ=UTC date -j -f "%Y-%m-%dT%H:%M:%SZ" "$REVIEW_DATE" "+%s" 2>/dev/null || echo "0")
-      fi
-      if [ "$REVIEW_EPOCH" -gt "$LATEST_COMMIT_EPOCH" ]; then
-        # Review was submitted AFTER latest commit — still fresh, blocks verification
-        BLOCKING_CHANGES_REQUESTED=$(( BLOCKING_CHANGES_REQUESTED + 1 ))
-        BLOCKING_REQUESTERS="${BLOCKING_REQUESTERS:+$BLOCKING_REQUESTERS, }${REVIEWER}"
-      fi
-      # Review submitted BEFORE latest commit — stale, skip
-    fi
-  done <<< "$(echo "$CHANGES_REQUESTED_REVIEWS" | jq -c '.[]')"
-else
-  # No commit date or no changes_requested — check raw count as fallback
-  BLOCKING_CHANGES_REQUESTED=$(echo "$CHANGES_REQUESTED_REVIEWS" | jq length 2>/dev/null || echo "0")
-  BLOCKING_REQUESTERS=$(echo "$CHANGES_REQUESTED_REVIEWS" | jq -r '[.[].author.login] | join(", ")' 2>/dev/null || echo "unknown")
-fi
-
-if [ "$BLOCKING_CHANGES_REQUESTED" -gt 0 ]; then
-  echo "NOT COMPLETE: CHANGES_REQUESTED (after latest commit) from ${BLOCKING_REQUESTERS} on PR #$PR_NUMBER" >&2
-  exit 1
-fi
-
-echo "VERIFIED: PR #$PR_NUMBER — checkpoints ✓, CI complete + green, 0 unresolved threads, no CHANGES_REQUESTED"
-exit 0

.claude/skills/pr-address/SKILL.md

@@ -1,234 +0,0 @@
----
-name: pr-address
-description: Address PR review comments and loop until CI green and all comments resolved. TRIGGER when user asks to address comments, fix PR feedback, respond to reviewers, or babysit/monitor a PR.
-user-invocable: true
-argument-hint: "[PR number or URL] — if omitted, finds PR for current branch."
-metadata:
-  author: autogpt-team
-  version: "1.0.0"
----
-
-# PR Address
-
-## Find the PR
-
-```bash
-gh pr list --head $(git branch --show-current) --repo Significant-Gravitas/AutoGPT
-gh pr view {N}
-```
-
-## Read the PR description
-
-Understand the **Why / What / How** before addressing comments — you need context to make good fixes:
-
-```bash
-gh pr view {N} --json body --jq '.body'
-```
-
-## Fetch comments (all sources)
-
-### 1. Inline review threads — GraphQL (primary source of actionable items)
-
-Use GraphQL to fetch inline threads. It natively exposes `isResolved`, returns threads already grouped with all replies, and paginates via cursor — no manual thread reconstruction needed.
-
-```bash
-gh api graphql -f query='
-{
-  repository(owner: "Significant-Gravitas", name: "AutoGPT") {
-    pullRequest(number: {N}) {
-      reviewThreads(first: 100) {
-        pageInfo { hasNextPage endCursor }
-        nodes {
-          id
-          isResolved
-          path
-          comments(last: 1) {
-            nodes { databaseId body author { login } createdAt }
-          }
-        }
-      }
-    }
-  }
-}'
-```
-
-If `pageInfo.hasNextPage` is true, fetch subsequent pages by adding `after: "<endCursor>"` to `reviewThreads(first: 100, after: "...")` and repeat until `hasNextPage` is false.
-
-**Filter to unresolved threads only** — skip any thread where `isResolved: true`. `comments(last: 1)` returns the most recent comment in the thread — act on that; it reflects the reviewer's final ask. Use the thread `id` (Relay global ID) to track threads across polls.
-
-### 2. Top-level reviews — REST (MUST paginate)
-
-```bash
-gh api repos/Significant-Gravitas/AutoGPT/pulls/{N}/reviews --paginate
-```
-
-**CRITICAL — always `--paginate`.** Reviews default to 30 per page. PRs can have 80–170+ reviews (mostly empty resolution events). Without pagination you miss reviews past position 30 — including `autogpt-reviewer`'s structured review which is typically posted after several CI runs and sits well beyond the first page.
-
-Two things to extract:
-- **Overall state**: look for `CHANGES_REQUESTED` or `APPROVED` reviews.
-- **Actionable feedback**: non-empty bodies only. Empty-body reviews are thread-resolution events — they indicate progress but have no feedback to act on.
-
-**Where each reviewer posts:**
-- `autogpt-reviewer` — posts detailed structured reviews ("Blockers", "Should Fix", "Nice to Have") as **top-level reviews**. Not present on every PR. Address ALL items.
-- `sentry[bot]` — posts bug predictions as **inline threads**. Fix real bugs, explain false positives.
-- `coderabbitai[bot]` — posts summaries as **top-level reviews** AND actionable items as **inline threads**. Address actionable items.
-- Human reviewers — can post in any source. Address ALL non-empty feedback.
-
-### 3. PR conversation comments — REST
-
-```bash
-gh api repos/Significant-Gravitas/AutoGPT/issues/{N}/comments --paginate
-```
-
-Mostly contains: bot summaries (`coderabbitai[bot]`), CI/conflict detection (`github-actions[bot]`), and author status updates. Scan for non-empty messages from non-bot human reviewers that aren't the PR author — those are the ones that need a response.
-
-## For each unaddressed comment
-
-Address comments **one at a time**: fix → commit → push → inline reply → next.
-
-1. Read the referenced code, make the fix (or reply explaining why it's not needed)
-2. Commit and push the fix
-3. Reply **inline** (not as a new top-level comment) referencing the fixing commit — this is what resolves the conversation for bot reviewers (coderabbitai, sentry):
-
-Use a **markdown commit link** so GitHub renders it as a clickable reference. Get the full SHA with `git rev-parse HEAD` after committing:
-
-| Comment type | How to reply |
-|---|---|
-| Inline review (`pulls/{N}/comments`) | `gh api repos/Significant-Gravitas/AutoGPT/pulls/{N}/comments/{ID}/replies -f body="🤖 Fixed in [abc1234](https://github.com/Significant-Gravitas/AutoGPT/commit/FULL_SHA): <description>"` |
-| Conversation (`issues/{N}/comments`) | `gh api repos/Significant-Gravitas/AutoGPT/issues/{N}/comments -f body="🤖 Fixed in [abc1234](https://github.com/Significant-Gravitas/AutoGPT/commit/FULL_SHA): <description>"` |
-
-## Codecov coverage
-
-Codecov patch target is **80%** on changed lines. Checks are **informational** (not blocking) but should be green.
-
-### Running coverage locally
-
-**Backend** (from `autogpt_platform/backend/`):
-```bash
-poetry run pytest -s -vv --cov=backend --cov-branch --cov-report term-missing
-```
-
-**Frontend** (from `autogpt_platform/frontend/`):
-```bash
-pnpm vitest run --coverage
-```
-
-### When codecov/patch fails
-
-1. Find uncovered files: `git diff --name-only $(gh pr view --json baseRefName --jq '.baseRefName')...HEAD`
-2. For each uncovered file — extract inline logic to `helpers.ts`/`helpers.py` and test those (highest ROI). Colocate tests as `*_test.py` (backend) or `__tests__/*.test.ts` (frontend).
-3. Run coverage locally to verify, commit, push.
-
-## Format and commit
-
-After fixing, format the changed code:
-
-- **Backend** (from `autogpt_platform/backend/`): `poetry run format`
-- **Frontend** (from `autogpt_platform/frontend/`): `pnpm format && pnpm lint && pnpm types`
-
-If API routes changed, regenerate the frontend client:
-```bash
-cd autogpt_platform/backend && poetry run rest &
-REST_PID=$!
-trap "kill $REST_PID 2>/dev/null" EXIT
-WAIT=0; until curl -sf http://localhost:8006/health > /dev/null 2>&1; do sleep 1; WAIT=$((WAIT+1)); [ $WAIT -ge 60 ] && echo "Timed out" && exit 1; done
-cd ../frontend && pnpm generate:api:force
-kill $REST_PID 2>/dev/null; trap - EXIT
-```
-Never manually edit files in `src/app/api/__generated__/`.
-
-Then commit and **push immediately** — never batch commits without pushing. Each fix should be visible on GitHub right away so CI can start and reviewers can see progress.
-
-**Never push empty commits** (`git commit --allow-empty`) to re-trigger CI or bot checks. When a check fails, investigate the root cause (unchecked PR checklist, unaddressed review comments, code issues) and fix those directly. Empty commits add noise to git history.
-
-For backend commits in worktrees: `poetry run git commit` (pre-commit hooks).
-
-## The loop
-
-```text
-address comments → format → commit → push
-→ wait for CI (while addressing new comments) → fix failures → push
-→ re-check comments after CI settles
-→ repeat until: all comments addressed AND CI green AND no new comments arriving
-```
-
-### Polling for CI + new comments
-
-After pushing, poll for **both** CI status and new comments in a single loop. Do not use `gh pr checks --watch` — it blocks the tool and prevents reacting to new comments while CI is running.
-
-> **Note:** `gh pr checks --watch --fail-fast` is tempting but it blocks the entire Bash tool call, meaning the agent cannot check for or address new comments until CI fully completes. Always poll manually instead.
-
-**Polling loop — repeat every 30 seconds:**
-
-1. Check CI status:
-```bash
-gh pr checks {N} --repo Significant-Gravitas/AutoGPT --json bucket,name,link
-```
-   Parse the results: if every check has `bucket` of `"pass"` or `"skipping"`, CI is green. If any has `"fail"`, CI has failed. Otherwise CI is still pending.
-
-2. Check for merge conflicts:
-```bash
-gh pr view {N} --repo Significant-Gravitas/AutoGPT --json mergeable --jq '.mergeable'
-```
-   If the result is `"CONFLICTING"`, the PR has a merge conflict — see "Resolving merge conflicts" below. If `"UNKNOWN"`, GitHub is still computing mergeability — wait and re-check next poll.
-
-3. Check for new/changed comments (all three sources):
-
-   **Inline threads** — re-run the GraphQL query from "Fetch comments". For each unresolved thread, record `{thread_id, last_comment_databaseId}` as your baseline. On each poll, action is needed if:
-   - A new thread `id` appears that wasn't in the baseline (new thread), OR
-   - An existing thread's `last_comment_databaseId` has changed (new reply on existing thread)
-
-   **Conversation comments:**
-   ```bash
-   gh api repos/Significant-Gravitas/AutoGPT/issues/{N}/comments --paginate
-   ```
-   Compare total count and newest `id` against baseline. Filter to non-empty, non-bot, non-author-update messages.
-
-   **Top-level reviews:**
-   ```bash
-   gh api repos/Significant-Gravitas/AutoGPT/pulls/{N}/reviews --paginate
-   ```
-   Watch for new non-empty reviews (`CHANGES_REQUESTED` or `COMMENTED` with body). Compare total count and newest `id` against baseline.
-
-4. **React in this precedence order (first match wins):**
-
-| What happened | Action |
-|---|---|
-| Merge conflict detected | See "Resolving merge conflicts" below. |
-| Mergeability is `UNKNOWN` | GitHub is still computing mergeability. Sleep 30 seconds, then restart polling from the top. |
-| New comments detected | Address them (fix → commit → push → reply). After pushing, re-fetch all comments to update your baseline, then restart this polling loop from the top (new commits invalidate CI status). |
-| CI failed (bucket == "fail") | Get failed check links: `gh pr checks {N} --repo Significant-Gravitas/AutoGPT --json bucket,link --jq '.[] \| select(.bucket == "fail") \| .link'`. Extract run ID from link (format: `.../actions/runs/<run-id>/job/...`), read logs with `gh run view <run-id> --repo Significant-Gravitas/AutoGPT --log-failed`. Fix → commit → push → restart polling. |
-| CI green + no new comments | **Do not exit immediately.** Bots (coderabbitai, sentry) often post reviews shortly after CI settles. Continue polling for **2 more cycles (60s)** after CI goes green. Only exit after 2 consecutive green+quiet polls. |
-| CI pending + no new comments | Sleep 30 seconds, then poll again. |
-
-**The loop ends when:** CI fully green + all comments addressed + **2 consecutive polls with no new comments after CI settled.**
-
-### Resolving merge conflicts
-
-1. Identify the PR's target branch and remote:
-```bash
-gh pr view {N} --repo Significant-Gravitas/AutoGPT --json baseRefName --jq '.baseRefName'
-git remote -v   # find the remote pointing to Significant-Gravitas/AutoGPT (typically 'upstream' in forks, 'origin' for direct contributors)
-```
-
-2. Pull the latest base branch with a 3-way merge:
-```bash
-git pull {base-remote} {base-branch} --no-rebase
-```
-
-3. Resolve conflicting files, then verify no conflict markers remain:
-```bash
-if grep -R -n -E '^(<<<<<<<|=======|>>>>>>>)' <conflicted-files>; then
-  echo "Unresolved conflict markers found — resolve before proceeding."
-  exit 1
-fi
-```
-
-4. Stage and push:
-```bash
-git add <conflicted-files>
-git commit -m "Resolve merge conflicts with {base-branch}"
-git push
-```
-
-5. Restart the polling loop from the top — new commits reset CI status.

.claude/skills/pr-review/SKILL.md

@@ -1,86 +0,0 @@
----
-name: pr-review
-description: Review a PR for correctness, security, code quality, and testing issues. TRIGGER when user asks to review a PR, check PR quality, or give feedback on a PR.
-user-invocable: true
-args: "[PR number or URL] — if omitted, finds PR for current branch."
-metadata:
-  author: autogpt-team
-  version: "1.0.0"
----
-
-# PR Review
-
-## Find the PR
-
-```bash
-gh pr list --head $(git branch --show-current) --repo Significant-Gravitas/AutoGPT
-gh pr view {N}
-```
-
-## Read the PR description
-
-Before reading code, understand the **why**, **what**, and **how** from the PR description:
-
-```bash
-gh pr view {N} --json body --jq '.body'
-```
-
-Every PR should have a Why / What / How structure. If any of these are missing, note it as feedback.
-
-## Read the diff
-
-```bash
-gh pr diff {N}
-```
-
-## Fetch existing review comments
-
-Before posting anything, fetch existing inline comments to avoid duplicates:
-
-```bash
-gh api repos/Significant-Gravitas/AutoGPT/pulls/{N}/comments --paginate
-gh api repos/Significant-Gravitas/AutoGPT/pulls/{N}/reviews
-```
-
-## What to check
-
-**Description quality:** Does the PR description cover Why (motivation/problem), What (summary of changes), and How (approach/implementation details)? If any are missing, request them — you can't judge the approach without understanding the problem and intent.
-
-**Correctness:** logic errors, off-by-one, missing edge cases, race conditions (TOCTOU in file access, credit charging), error handling gaps, async correctness (missing `await`, unclosed resources).
-
-**Security:** input validation at boundaries, no injection (command, XSS, SQL), secrets not logged, file paths sanitized (`os.path.basename()` in error messages).
-
-**Code quality:** apply rules from backend/frontend CLAUDE.md files.
-
-**Architecture:** DRY, single responsibility, modular functions. `Security()` vs `Depends()` for FastAPI auth. `data:` for SSE events, `: comment` for heartbeats. `transaction=True` for Redis pipelines.
-
-**Testing:** edge cases covered, colocated `*_test.py` (backend) / `__tests__/` (frontend), mocks target where symbol is **used** not defined, `AsyncMock` for async.
-
-## Output format
-
-Every comment **must** be prefixed with `🤖` and a criticality badge:
-
-| Tier | Badge | Meaning |
-|---|---|---|
-| Blocker | `🔴 **Blocker**` | Must fix before merge |
-| Should Fix | `🟠 **Should Fix**` | Important improvement |
-| Nice to Have | `🟡 **Nice to Have**` | Minor suggestion |
-| Nit | `🔵 **Nit**` | Style / wording |
-
-Example: `🤖 🔴 **Blocker**: Missing error handling for X — suggest wrapping in try/except.`
-
-## Post inline comments
-
-For each finding, post an inline comment on the PR (do not just write a local report):
-
-```bash
-# Get the latest commit SHA for the PR
-COMMIT_SHA=$(gh api repos/Significant-Gravitas/AutoGPT/pulls/{N} --jq '.head.sha')
-
-# Post an inline comment on a specific file/line
-gh api repos/Significant-Gravitas/AutoGPT/pulls/{N}/comments \
-  -f body="🤖 🔴 **Blocker**: <description>" \
-  -f commit_id="$COMMIT_SHA" \
-  -f path="<file path>" \
-  -F line=<line number>
-```

.claude/skills/pr-test/SKILL.md

@@ -1,893 +0,0 @@
----
-name: pr-test
-description: "E2E manual testing of PRs/branches using docker compose, agent-browser, and API calls. TRIGGER when user asks to manually test a PR, test a feature end-to-end, or run integration tests against a running system."
-user-invocable: true
-argument-hint: "[worktree path or PR number] — tests the PR in the given worktree. Optional flags: --fix (auto-fix issues found)"
-metadata:
-  author: autogpt-team
-  version: "2.0.0"
----
-
-# Manual E2E Test
-
-Test a PR/branch end-to-end by building the full platform, interacting via browser and API, capturing screenshots, and reporting results.
-
-## Critical Requirements
-
-These are NON-NEGOTIABLE. Every test run MUST satisfy ALL the following:
-
-### 1. Screenshots at Every Step
-- Take a screenshot at EVERY significant test step — not just at the end
-- Every test scenario MUST have at least one BEFORE and one AFTER screenshot
-- Name screenshots sequentially: `{NN}-{action}-{state}.png` (e.g., `01-credits-before.png`, `02-credits-after.png`)
-- If a screenshot is missing for a scenario, the test is INCOMPLETE — go back and take it
-
-### 2. Screenshots MUST Be Posted to PR
-- Push ALL screenshots to a temp branch `test-screenshots/pr-{N}`
-- Post a PR comment with ALL screenshots embedded inline using GitHub raw URLs
-- This is NOT optional — every test run MUST end with a PR comment containing screenshots
-- If screenshot upload fails, retry. If it still fails, list failed files and require manual drag-and-drop/paste attachment in the PR comment
-
-### 3. State Verification with Before/After Evidence
-- For EVERY state-changing operation (API call, user action), capture the state BEFORE and AFTER
-- Log the actual API response values (e.g., `credits_before=100, credits_after=95`)
-- Screenshot MUST show the relevant UI state change
-- Compare expected vs actual values explicitly — do not just eyeball it
-
-### 4. Negative Test Cases Are Mandatory
-- Test at least ONE negative case per feature (e.g., insufficient credits, invalid input, unauthorized access)
-- Verify error messages are user-friendly and accurate
-- Verify the system state did NOT change after a rejected operation
-
-### 5. Test Report Must Include Full Evidence
-Each test scenario in the report MUST have:
-- **Steps**: What was done (exact commands or UI actions)
-- **Expected**: What should happen
-- **Actual**: What actually happened
-- **API Evidence**: Before/after API response values for state-changing operations
-- **Screenshot Evidence**: Before/after screenshots with explanations
-
-## State Manipulation for Realistic Testing
-
-When testing features that depend on specific states (rate limits, credits, quotas):
-
-1. **Use Redis CLI to set counters directly:**
-   ```bash
-   # Find the Redis container
-   REDIS_CONTAINER=$(docker ps --format '{{.Names}}' | grep redis | head -1)
-   # Set a key with expiry
-   docker exec $REDIS_CONTAINER redis-cli SET key value EX ttl
-   # Example: Set rate limit counter to near-limit
-   docker exec $REDIS_CONTAINER redis-cli SET "rate_limit:user:test@test.com" 99 EX 3600
-   # Example: Check current value
-   docker exec $REDIS_CONTAINER redis-cli GET "rate_limit:user:test@test.com"
-   ```
-
-2. **Use API calls to check before/after state:**
-   ```bash
-   # BEFORE: Record current state
-   BEFORE=$(curl -s -H "Authorization: Bearer $TOKEN" http://localhost:8006/api/credits | jq '.credits')
-   echo "Credits BEFORE: $BEFORE"
-
-   # Perform the action...
-
-   # AFTER: Record new state and compare
-   AFTER=$(curl -s -H "Authorization: Bearer $TOKEN" http://localhost:8006/api/credits | jq '.credits')
-   echo "Credits AFTER: $AFTER"
-   echo "Delta: $(( BEFORE - AFTER ))"
-   ```
-
-3. **Take screenshots BEFORE and AFTER state changes** — the UI must reflect the backend state change
-
-4. **Never rely on mocked/injected browser state** — always use real backend state. Do NOT use `agent-browser eval` to fake UI state. The backend must be the source of truth.
-
-5. **Use direct DB queries when needed:**
-   ```bash
-   # Query via Supabase's PostgREST or docker exec into the DB
-   docker exec supabase-db psql -U supabase_admin -d postgres -c "SELECT credits FROM user_credits WHERE user_id = '...';"
-   ```
-
-6. **After every API test, verify the state change actually persisted:**
-   ```bash
-   # Example: After a credits purchase, verify DB matches API
-   API_CREDITS=$(curl -s -H "Authorization: Bearer $TOKEN" http://localhost:8006/api/credits | jq '.credits')
-   DB_CREDITS=$(docker exec supabase-db psql -U supabase_admin -d postgres -t -c "SELECT credits FROM user_credits WHERE user_id = '...';" | tr -d ' ')
-   [ "$API_CREDITS" = "$DB_CREDITS" ] && echo "CONSISTENT" || echo "MISMATCH: API=$API_CREDITS DB=$DB_CREDITS"
-   ```
-
-## Arguments
-
-- `$ARGUMENTS` — worktree path (e.g. `$REPO_ROOT`) or PR number
-- If `--fix` flag is present, auto-fix bugs found and push fixes (like pr-address loop)
-
-## Step 0: Resolve the target
-
-```bash
-# If argument is a PR number, find its worktree
-gh pr view {N} --json headRefName --jq '.headRefName'
-# If argument is a path, use it directly
-```
-
-Determine:
-- `REPO_ROOT` — the root repo directory: `git -C "$WORKTREE_PATH" worktree list | head -1 | awk '{print $1}'` (or `git rev-parse --show-toplevel` if not a worktree)
-- `WORKTREE_PATH` — the worktree directory
-- `PLATFORM_DIR` — `$WORKTREE_PATH/autogpt_platform`
-- `BACKEND_DIR` — `$PLATFORM_DIR/backend`
-- `FRONTEND_DIR` — `$PLATFORM_DIR/frontend`
-- `PR_NUMBER` — the PR number (from `gh pr list --head $(git branch --show-current)`)
-- `PR_TITLE` — the PR title, slugified (e.g. "Add copilot permissions" → "add-copilot-permissions")
-- `RESULTS_DIR` — `$REPO_ROOT/test-results/PR-{PR_NUMBER}-{slugified-title}`
-
-Create the results directory:
-```bash
-PR_NUMBER=$(cd $WORKTREE_PATH && gh pr list --head $(git branch --show-current) --repo Significant-Gravitas/AutoGPT --json number --jq '.[0].number')
-PR_TITLE=$(cd $WORKTREE_PATH && gh pr list --head $(git branch --show-current) --repo Significant-Gravitas/AutoGPT --json title --jq '.[0].title' | tr '[:upper:]' '[:lower:]' | sed 's/[^a-z0-9]/-/g' | sed 's/--*/-/g' | sed 's/^-//;s/-$//' | head -c 50)
-RESULTS_DIR="$REPO_ROOT/test-results/PR-${PR_NUMBER}-${PR_TITLE}"
-mkdir -p $RESULTS_DIR
-```
-
-**Test user credentials** (for logging into the UI or verifying results manually):
-- Email: `test@test.com`
-- Password: `testtest123`
-
-## Step 1: Understand the PR
-
-Before testing, understand what changed:
-
-```bash
-cd $WORKTREE_PATH
-
-# Read PR description to understand the WHY
-gh pr view {N} --json body --jq '.body'
-
-git log --oneline dev..HEAD | head -20
-git diff dev --stat
-```
-
-Read the PR description (Why / What / How) and changed files to understand:
-0. **Why** does this PR exist? What problem does it solve?
-1. **What** feature/fix does this PR implement?
-2. **How** does it work? What's the approach?
-3. What components are affected? (backend, frontend, copilot, executor, etc.)
-4. What are the key user-facing behaviors to test?
-
-## Step 2: Write test scenarios
-
-Based on the PR analysis, write a test plan to `$RESULTS_DIR/test-plan.md`:
-
-```markdown
-# Test Plan: PR #{N} — {title}
-
-## Scenarios
-1. [Scenario name] — [what to verify]
-2. ...
-
-## API Tests (if applicable)
-1. [Endpoint] — [expected behavior]
-   - Before state: [what to check before]
-   - After state: [what to verify changed]
-
-## UI Tests (if applicable)
-1. [Page/component] — [interaction to test]
-   - Screenshot before: [what to capture]
-   - Screenshot after: [what to capture]
-
-## Negative Tests (REQUIRED — at least one per feature)
-1. [What should NOT happen] — [how to trigger it]
-   - Expected error: [what error message/code]
-   - State unchanged: [what to verify did NOT change]
-```
-
-**Be critical** — include edge cases, error paths, and security checks. Every scenario MUST specify what screenshots to take and what state to verify.
-
-## Step 3: Environment setup
-
-### 3a. Copy .env files from the root worktree
-
-The root worktree (`$REPO_ROOT`) has the canonical `.env` files with all API keys. Copy them to the target worktree:
-
-```bash
-# CRITICAL: .env files are NOT checked into git. They must be copied manually.
-cp $REPO_ROOT/autogpt_platform/.env $PLATFORM_DIR/.env
-cp $REPO_ROOT/autogpt_platform/backend/.env $BACKEND_DIR/.env
-cp $REPO_ROOT/autogpt_platform/frontend/.env $FRONTEND_DIR/.env
-```
-
-### 3b. Configure copilot authentication
-
-The copilot needs an LLM API to function. Two approaches (try subscription first):
-
-#### Option 1: Subscription mode (preferred — uses your Claude Max/Pro subscription)
-
-The `claude_agent_sdk` Python package **bundles its own Claude CLI binary** — no need to install `@anthropic-ai/claude-code` via npm. The backend auto-provisions credentials from environment variables on startup.
-
-Run the helper script to extract tokens from your host and auto-update `backend/.env` (works on macOS, Linux, and Windows/WSL):
-
-```bash
-# Extracts OAuth tokens and writes CLAUDE_CODE_OAUTH_TOKEN + CLAUDE_CODE_REFRESH_TOKEN into .env
-bash $BACKEND_DIR/scripts/refresh_claude_token.sh --env-file $BACKEND_DIR/.env
-```
-
-**How it works:** The script reads the OAuth token from:
-- **macOS**: system keychain (`"Claude Code-credentials"`)
-- **Linux/WSL**: `~/.claude/.credentials.json`
-- **Windows**: `%APPDATA%/claude/.credentials.json`
-
-It sets `CLAUDE_CODE_OAUTH_TOKEN`, `CLAUDE_CODE_REFRESH_TOKEN`, and `CHAT_USE_CLAUDE_CODE_SUBSCRIPTION=true` in the `.env` file. On container startup, the backend auto-provisions `~/.claude/.credentials.json` inside the container from these env vars. The SDK's bundled CLI then authenticates using that file. No `claude login`, no npm install needed.
-
-**Note:** The OAuth token expires (~24h). If copilot returns auth errors, re-run the script and restart: `$BACKEND_DIR/scripts/refresh_claude_token.sh --env-file $BACKEND_DIR/.env && docker compose up -d copilot_executor`
-
-#### Option 2: OpenRouter API key mode (fallback)
-
-If subscription mode doesn't work, switch to API key mode using OpenRouter:
-
-```bash
-# In $BACKEND_DIR/.env, ensure these are set:
-CHAT_USE_CLAUDE_CODE_SUBSCRIPTION=false
-CHAT_API_KEY=<value of OPEN_ROUTER_API_KEY from the same .env>
-CHAT_BASE_URL=https://openrouter.ai/api/v1
-CHAT_USE_CLAUDE_AGENT_SDK=true
-```
-
-Use `sed` to update these values:
-```bash
-ORKEY=$(grep "^OPEN_ROUTER_API_KEY=" $BACKEND_DIR/.env | cut -d= -f2)
-[ -n "$ORKEY" ] || { echo "ERROR: OPEN_ROUTER_API_KEY is missing in $BACKEND_DIR/.env"; exit 1; }
-perl -i -pe 's/CHAT_USE_CLAUDE_CODE_SUBSCRIPTION=true/CHAT_USE_CLAUDE_CODE_SUBSCRIPTION=false/' $BACKEND_DIR/.env
-# Add or update CHAT_API_KEY and CHAT_BASE_URL
-grep -q "^CHAT_API_KEY=" $BACKEND_DIR/.env && perl -i -pe "s|^CHAT_API_KEY=.*|CHAT_API_KEY=$ORKEY|" $BACKEND_DIR/.env || echo "CHAT_API_KEY=$ORKEY" >> $BACKEND_DIR/.env
-grep -q "^CHAT_BASE_URL=" $BACKEND_DIR/.env && perl -i -pe 's|^CHAT_BASE_URL=.*|CHAT_BASE_URL=https://openrouter.ai/api/v1|' $BACKEND_DIR/.env || echo "CHAT_BASE_URL=https://openrouter.ai/api/v1" >> $BACKEND_DIR/.env
-```
-
-### 3c. Stop conflicting containers
-
-```bash
-# Stop any running app containers (keep infra: supabase, redis, rabbitmq, clamav)
-docker ps --format "{{.Names}}" | grep -E "rest_server|executor|copilot|websocket|database_manager|scheduler|notification|frontend|migrate" | while read name; do
-  docker stop "$name" 2>/dev/null
-done
-```
-
-### 3e. Build and start
-
-```bash
-cd $PLATFORM_DIR && docker compose build --no-cache 2>&1 | tail -20
-if [ ${PIPESTATUS[0]} -ne 0 ]; then echo "ERROR: Docker build failed"; exit 1; fi
-
-cd $PLATFORM_DIR && docker compose up -d 2>&1 | tail -20
-if [ ${PIPESTATUS[0]} -ne 0 ]; then echo "ERROR: Docker compose up failed"; exit 1; fi
-```
-
-**Note:** If the container appears to be running old code (e.g. missing PR changes), use `docker compose build --no-cache` to force a full rebuild. Docker BuildKit may sometimes reuse cached `COPY` layers from a previous build on a different branch.
-
-**Expected time: 3-8 minutes** for build, 5-10 minutes with `--no-cache`.
-
-### 3f. Wait for services to be ready
-
-```bash
-# Poll until backend and frontend respond
-for i in $(seq 1 60); do
-  BACKEND=$(curl -s -o /dev/null -w "%{http_code}" http://localhost:8006/docs 2>/dev/null)
-  FRONTEND=$(curl -s -o /dev/null -w "%{http_code}" http://localhost:3000 2>/dev/null)
-  if [ "$BACKEND" = "200" ] && [ "$FRONTEND" = "200" ]; then
-    echo "Services ready"
-    break
-  fi
-  sleep 5
-done
-```
-
-
-### 3h. Create test user and get auth token
-
-```bash
-ANON_KEY=$(grep "NEXT_PUBLIC_SUPABASE_ANON_KEY=" $FRONTEND_DIR/.env | sed 's/.*NEXT_PUBLIC_SUPABASE_ANON_KEY=//' | tr -d '[:space:]')
-
-# Signup (idempotent — returns "User already registered" if exists)
-RESULT=$(curl -s -X POST 'http://localhost:8000/auth/v1/signup' \
-  -H "apikey: $ANON_KEY" \
-  -H 'Content-Type: application/json' \
-  -d '{"email":"test@test.com","password":"testtest123"}')
-
-# If "Database error finding user", restart supabase-auth and retry
-if echo "$RESULT" | grep -q "Database error"; then
-  docker restart supabase-auth && sleep 5
-  curl -s -X POST 'http://localhost:8000/auth/v1/signup' \
-    -H "apikey: $ANON_KEY" \
-    -H 'Content-Type: application/json' \
-    -d '{"email":"test@test.com","password":"testtest123"}'
-fi
-
-# Get auth token
-TOKEN=$(curl -s -X POST 'http://localhost:8000/auth/v1/token?grant_type=password' \
-  -H "apikey: $ANON_KEY" \
-  -H 'Content-Type: application/json' \
-  -d '{"email":"test@test.com","password":"testtest123"}' | jq -r '.access_token // ""')
-```
-
-**Use this token for ALL API calls:**
-```bash
-curl -H "Authorization: Bearer $TOKEN" http://localhost:8006/api/...
-```
-
-### 3i. Disable onboarding for test user
-
-The frontend redirects to `/onboarding` when the `VISIT_COPILOT` step is not in `completedSteps`.
-Mark it complete via the backend API so every browser test lands on the real feature UI:
-
-```bash
-ONBOARDING_RESULT=$(curl -s -X POST \
-  "http://localhost:8006/api/onboarding/step?step=VISIT_COPILOT" \
-  -H "Authorization: Bearer $TOKEN")
-echo "Onboarding bypass: $ONBOARDING_RESULT"
-
-# Verify it took effect
-ONBOARDING_STATUS=$(curl -s \
-  "http://localhost:8006/api/onboarding/completed" \
-  -H "Authorization: Bearer $TOKEN" | jq -r '.is_completed')
-echo "Onboarding completed: $ONBOARDING_STATUS"
-[ "$ONBOARDING_STATUS" = "true" ] || echo "WARNING: onboarding bypass may have failed — browser tests may hit the onboarding flow"
-```
-
-## Step 4: Run tests
-
-### Service ports reference
-
-| Service | Port | URL |
-|---------|------|-----|
-| Frontend | 3000 | http://localhost:3000 |
-| Backend REST | 8006 | http://localhost:8006 |
-| Supabase Auth (via Kong) | 8000 | http://localhost:8000 |
-| Executor | 8002 | http://localhost:8002 |
-| Copilot Executor | 8008 | http://localhost:8008 |
-| WebSocket | 8001 | http://localhost:8001 |
-| Database Manager | 8005 | http://localhost:8005 |
-| Redis | 6379 | localhost:6379 |
-| RabbitMQ | 5672 | localhost:5672 |
-
-### API testing
-
-Use `curl` with the auth token for backend API tests. **For EVERY API call that changes state, record before/after values:**
-
-```bash
-# Example: List agents
-curl -s -H "Authorization: Bearer $TOKEN" http://localhost:8006/api/graphs | jq . | head -20
-
-# Example: Create an agent
-curl -s -X POST http://localhost:8006/api/graphs \
-  -H "Authorization: Bearer $TOKEN" \
-  -H 'Content-Type: application/json' \
-  -d '{...}' | jq .
-
-# Example: Run an agent
-curl -s -X POST "http://localhost:8006/api/graphs/{graph_id}/execute" \
-  -H "Authorization: Bearer $TOKEN" \
-  -H 'Content-Type: application/json' \
-  -d '{"data": {...}}'
-
-# Example: Get execution results
-curl -s -H "Authorization: Bearer $TOKEN" \
-  "http://localhost:8006/api/graphs/{graph_id}/executions/{exec_id}" | jq .
-```
-
-**State verification pattern (use for EVERY state-changing API call):**
-```bash
-# 1. Record BEFORE state
-BEFORE_STATE=$(curl -s -H "Authorization: Bearer $TOKEN" http://localhost:8006/api/{resource} | jq '{relevant_fields}')
-echo "BEFORE: $BEFORE_STATE"
-
-# 2. Perform the action
-ACTION_RESULT=$(curl -s -X POST ... | jq .)
-echo "ACTION RESULT: $ACTION_RESULT"
-
-# 3. Record AFTER state
-AFTER_STATE=$(curl -s -H "Authorization: Bearer $TOKEN" http://localhost:8006/api/{resource} | jq '{relevant_fields}')
-echo "AFTER: $AFTER_STATE"
-
-# 4. Log the comparison
-echo "=== STATE CHANGE VERIFICATION ==="
-echo "Before: $BEFORE_STATE"
-echo "After: $AFTER_STATE"
-echo "Expected change: {describe what should have changed}"
-```
-
-### Browser testing with agent-browser
-
-```bash
-# Close any existing session
-agent-browser close 2>/dev/null || true
-
-# Use --session-name to persist cookies across navigations
-# This means login only needs to happen once per test session
-agent-browser --session-name pr-test open 'http://localhost:3000/login' --timeout 15000
-
-# Get interactive elements
-agent-browser --session-name pr-test snapshot | grep "textbox\|button"
-
-# Login
-agent-browser --session-name pr-test fill {email_ref} "test@test.com"
-agent-browser --session-name pr-test fill {password_ref} "testtest123"
-agent-browser --session-name pr-test click {login_button_ref}
-sleep 5
-
-# Dismiss cookie banner if present
-agent-browser --session-name pr-test click 'text=Accept All' 2>/dev/null || true
-
-# Navigate — cookies are preserved so login persists
-agent-browser --session-name pr-test open 'http://localhost:3000/copilot' --timeout 10000
-
-# Take screenshot
-agent-browser --session-name pr-test screenshot $RESULTS_DIR/01-page.png
-
-# Interact with elements
-agent-browser --session-name pr-test fill {ref} "text"
-agent-browser --session-name pr-test press "Enter"
-agent-browser --session-name pr-test click {ref}
-agent-browser --session-name pr-test click 'text=Button Text'
-
-# Read page content
-agent-browser --session-name pr-test snapshot | grep "text:"
-```
-
-**Key pages:**
-- `/copilot` — CoPilot chat (for testing copilot features)
-- `/build` — Agent builder (for testing block/node features)
-- `/build?flowID={id}` — Specific agent in builder
-- `/library` — Agent library (for testing listing/import features)
-- `/library/agents/{id}` — Agent detail with run history
-- `/marketplace` — Marketplace
-
-### Checking logs
-
-```bash
-# Backend REST server
-docker logs autogpt_platform-rest_server-1 2>&1 | tail -30
-
-# Executor (runs agent graphs)
-docker logs autogpt_platform-executor-1 2>&1 | tail -30
-
-# Copilot executor (runs copilot chat sessions)
-docker logs autogpt_platform-copilot_executor-1 2>&1 | tail -30
-
-# Frontend
-docker logs autogpt_platform-frontend-1 2>&1 | tail -30
-
-# Filter for errors
-docker logs autogpt_platform-executor-1 2>&1 | grep -i "error\|exception\|traceback" | tail -20
-```
-
-### Copilot chat testing
-
-The copilot uses SSE streaming. To test via API:
-
-```bash
-# Create a session
-SESSION_ID=$(curl -s -X POST 'http://localhost:8006/api/chat/sessions' \
-  -H "Authorization: Bearer $TOKEN" \
-  -H 'Content-Type: application/json' \
-  -d '{}' | jq -r '.id // .session_id // ""')
-
-# Stream a message (SSE - will stream chunks)
-curl -N -X POST "http://localhost:8006/api/chat/sessions/$SESSION_ID/stream" \
-  -H "Authorization: Bearer $TOKEN" \
-  -H 'Content-Type: application/json' \
-  -d '{"message": "Hello, what can you help me with?"}' \
-  --max-time 60 2>/dev/null | head -50
-```
-
-Or test via browser (preferred for UI verification):
-```bash
-agent-browser --session-name pr-test open 'http://localhost:3000/copilot' --timeout 10000
-# ... fill chat input and press Enter, wait 20-30s for response
-```
-
-## Step 5: Record results and take screenshots
-
-**Take a screenshot at EVERY significant test step** — before and after interactions, on success, and on failure. This is NON-NEGOTIABLE.
-
-**Required screenshot pattern for each test scenario:**
-```bash
-# BEFORE the action
-agent-browser --session-name pr-test screenshot $RESULTS_DIR/{NN}-{scenario}-before.png
-
-# Perform the action...
-
-# AFTER the action
-agent-browser --session-name pr-test screenshot $RESULTS_DIR/{NN}-{scenario}-after.png
-```
-
-**Naming convention:**
-```bash
-# Examples:
-# $RESULTS_DIR/01-login-page-before.png
-# $RESULTS_DIR/02-login-page-after.png
-# $RESULTS_DIR/03-credits-page-before.png
-# $RESULTS_DIR/04-credits-purchase-after.png
-# $RESULTS_DIR/05-negative-insufficient-credits.png
-# $RESULTS_DIR/06-error-state.png
-```
-
-**Minimum requirements:**
-- At least TWO screenshots per test scenario (before + after)
-- At least ONE screenshot for each negative test case showing the error state
-- If a test fails, screenshot the failure state AND any error logs visible in the UI
-
-## Step 6: Show results to user with screenshots
-
-**CRITICAL: After all tests complete, you MUST show every screenshot to the user using the Read tool, with an explanation of what each screenshot shows.** This is the most important part of the test report — the user needs to visually verify the results.
-
-For each screenshot:
-1. Use the `Read` tool to display the PNG file (Claude can read images)
-2. Write a 1-2 sentence explanation below it describing:
-   - What page/state is being shown
-   - What the screenshot proves (which test scenario it validates)
-   - Any notable details visible in the UI
-
-Format the output like this:
-
-```markdown
-### Screenshot 1: {descriptive title}
-[Read the PNG file here]
-
-**What it shows:** {1-2 sentence explanation of what this screenshot proves}
-
----
-```
-
-After showing all screenshots, output a **detailed** summary table:
-
-| # | Scenario | Result | API Evidence | Screenshot Evidence |
-|---|----------|--------|-------------|-------------------|
-| 1 | {name} | PASS/FAIL | Before: X, After: Y | 01-before.png, 02-after.png |
-| 2 | ... | ... | ... | ... |
-
-**IMPORTANT:** As you show each screenshot and record test results, persist them in shell variables for Step 7:
-
-```bash
-# Build these variables during Step 6 — they are required by Step 7's script
-# NOTE: declare -A requires Bash 4.0+. This is standard on modern systems (macOS ships zsh
-# but Homebrew bash is 5.x; Linux typically has bash 5.x). If running on Bash <4, use a
-# plain variable with a lookup function instead.
-declare -A SCREENSHOT_EXPLANATIONS=(
-  ["01-login-page.png"]="Shows the login page loaded successfully with SSO options visible."
-  ["02-builder-with-block.png"]="The builder canvas displays the newly added block connected to the trigger."
-  # ... one entry per screenshot, using the same explanations you showed the user above
-)
-
-TEST_RESULTS_TABLE="| 1 | Login flow | PASS | N/A | 01-login-before.png, 02-login-after.png |
-| 2 | Credits purchase | PASS | Before: 100, After: 95 | 03-credits-before.png, 04-credits-after.png |
-| 3 | Insufficient credits (negative) | PASS | Credits: 0, rejected | 05-insufficient-credits-error.png |"
-# ... one row per test scenario with actual results
-```
-
-## Step 7: Post test report as PR comment with screenshots
-
-Upload screenshots to the PR using the GitHub Git API (no local git operations — safe for worktrees), then post a comment with inline images and per-screenshot explanations.
-
-**This step is MANDATORY. Every test run MUST post a PR comment with screenshots. No exceptions.**
-
-**CRITICAL — NEVER post a bare directory link like `https://github.com/.../tree/...`.** Every screenshot MUST appear as `![name](raw_url)` inline in the PR comment so reviewers can see them without clicking any links. After posting, the verification step below greps the comment for `![` tags and exits 1 if none are found — the test run is considered incomplete until this passes.
-
-```bash
-# Upload screenshots via GitHub Git API (creates blobs, tree, commit, and ref remotely)
-REPO="Significant-Gravitas/AutoGPT"
-SCREENSHOTS_BRANCH="test-screenshots/pr-${PR_NUMBER}"
-SCREENSHOTS_DIR="test-screenshots/PR-${PR_NUMBER}"
-
-# Step 1: Create blobs for each screenshot and build tree JSON
-# Retry each blob upload up to 3 times. If still failing, list them at end of report.
-shopt -s nullglob
-SCREENSHOT_FILES=("$RESULTS_DIR"/*.png)
-if [ ${#SCREENSHOT_FILES[@]} -eq 0 ]; then
-  echo "ERROR: No screenshots found in $RESULTS_DIR. Test run is incomplete."
-  exit 1
-fi
-TREE_JSON='['
-FIRST=true
-FAILED_UPLOADS=()
-for img in "${SCREENSHOT_FILES[@]}"; do
-  BASENAME=$(basename "$img")
-  B64=$(base64 < "$img")
-  BLOB_SHA=""
-  for attempt in 1 2 3; do
-    BLOB_SHA=$(gh api "repos/${REPO}/git/blobs" -f content="$B64" -f encoding="base64" --jq '.sha' 2>/dev/null || true)
-    [ -n "$BLOB_SHA" ] && break
-    sleep 1
-  done
-  if [ -z "$BLOB_SHA" ]; then
-    FAILED_UPLOADS+=("$img")
-    continue
-  fi
-  if [ "$FIRST" = true ]; then FIRST=false; else TREE_JSON+=','; fi
-  TREE_JSON+="{\"path\":\"${SCREENSHOTS_DIR}/${BASENAME}\",\"mode\":\"100644\",\"type\":\"blob\",\"sha\":\"${BLOB_SHA}\"}"
-done
-TREE_JSON+=']'
-
-# Step 2: Create tree, commit, and branch ref
-TREE_SHA=$(echo "$TREE_JSON" | jq -c '{tree: .}' | gh api "repos/${REPO}/git/trees" --input - --jq '.sha')
-
-# Resolve parent commit so screenshots are chained, not orphan root commits
-PARENT_SHA=$(gh api "repos/${REPO}/git/refs/heads/${SCREENSHOTS_BRANCH}" --jq '.object.sha' 2>/dev/null || echo "")
-if [ -n "$PARENT_SHA" ]; then
-  COMMIT_SHA=$(gh api "repos/${REPO}/git/commits" \
-    -f message="test: add E2E test screenshots for PR #${PR_NUMBER}" \
-    -f tree="$TREE_SHA" \
-    -f "parents[]=$PARENT_SHA" \
-    --jq '.sha')
-else
-  COMMIT_SHA=$(gh api "repos/${REPO}/git/commits" \
-    -f message="test: add E2E test screenshots for PR #${PR_NUMBER}" \
-    -f tree="$TREE_SHA" \
-    --jq '.sha')
-fi
-
-gh api "repos/${REPO}/git/refs" \
-  -f ref="refs/heads/${SCREENSHOTS_BRANCH}" \
-  -f sha="$COMMIT_SHA" 2>/dev/null \
-  || gh api "repos/${REPO}/git/refs/heads/${SCREENSHOTS_BRANCH}" \
-    -X PATCH -f sha="$COMMIT_SHA" -F force=true
-```
-
-Then post the comment with **inline images AND explanations for each screenshot**:
-
-```bash
-REPO_URL="https://raw.githubusercontent.com/${REPO}/${SCREENSHOTS_BRANCH}"
-
-# Build image markdown using uploaded image URLs; skip FAILED_UPLOADS (listed separately)
-
-IMAGE_MARKDOWN=""
-for img in "${SCREENSHOT_FILES[@]}"; do
-  BASENAME=$(basename "$img")
-  TITLE=$(echo "${BASENAME%.png}" | sed 's/^[0-9]*-//' | sed 's/-/ /g' | awk '{for(i=1;i<=NF;i++) $i=toupper(substr($i,1,1)) tolower(substr($i,2))}1')
-  # Skip images that failed to upload — they will be listed at the end
-  IS_FAILED=false
-  for failed in "${FAILED_UPLOADS[@]}"; do
-    [ "$(basename "$failed")" = "$BASENAME" ] && IS_FAILED=true && break
-  done
-  if [ "$IS_FAILED" = true ]; then
-    continue
-  fi
-  EXPLANATION="${SCREENSHOT_EXPLANATIONS[$BASENAME]}"
-  if [ -z "$EXPLANATION" ]; then
-    echo "ERROR: Missing screenshot explanation for $BASENAME. Add it to SCREENSHOT_EXPLANATIONS in Step 6."
-    exit 1
-  fi
-  IMAGE_MARKDOWN="${IMAGE_MARKDOWN}
-### ${TITLE}
-![${BASENAME}](${REPO_URL}/${SCREENSHOTS_DIR}/${BASENAME})
-${EXPLANATION}
-"
-done
-
-# Write comment body to file to avoid shell interpretation issues with special characters
-COMMENT_FILE=$(mktemp)
-# If any uploads failed, append a section listing them with instructions
-FAILED_SECTION=""
-if [ ${#FAILED_UPLOADS[@]} -gt 0 ]; then
-  FAILED_SECTION="
-## ⚠️ Failed Screenshot Uploads
-The following screenshots could not be uploaded via the GitHub API after 3 retries.
-**To add them:** drag-and-drop or paste these files into a PR comment manually:
-"
-  for failed in "${FAILED_UPLOADS[@]}"; do
-    FAILED_SECTION="${FAILED_SECTION}
-- \`$(basename "$failed")\` (local path: \`$failed\`)"
-  done
-  FAILED_SECTION="${FAILED_SECTION}
-
-**Run status:** INCOMPLETE until the files above are manually attached and visible inline in the PR."
-fi
-
-cat > "$COMMENT_FILE" <<INNEREOF
-## E2E Test Report
-
-| # | Scenario | Result | API Evidence | Screenshot Evidence |
-|---|----------|--------|-------------|-------------------|
-${TEST_RESULTS_TABLE}
-
-${IMAGE_MARKDOWN}
-${FAILED_SECTION}
-INNEREOF
-
-gh api "repos/${REPO}/issues/$PR_NUMBER/comments" -F body=@"$COMMENT_FILE"
-rm -f "$COMMENT_FILE"
-
-# Verify the posted comment contains inline images — exit 1 if none found
-# Use separate --paginate + jq pipe: --jq applies per-page, not to the full list
-LAST_COMMENT=$(gh api "repos/${REPO}/issues/$PR_NUMBER/comments" --paginate 2>/dev/null | jq -r '.[-1].body // ""')
-if ! echo "$LAST_COMMENT" | grep -q '!\['; then
-  echo "ERROR: Posted comment contains no inline images (![). Bare directory links are not acceptable." >&2
-  exit 1
-fi
-echo "✓ Inline images verified in posted comment"
-```
-
-**The PR comment MUST include:**
-1. A summary table of all scenarios with PASS/FAIL and before/after API evidence
-2. Every successfully uploaded screenshot rendered inline; any failed uploads listed with manual attachment instructions
-3. A 1-2 sentence explanation below each screenshot describing what it proves
-
-This approach uses the GitHub Git API to create blobs, trees, commits, and refs entirely server-side. No local `git checkout` or `git push` — safe for worktrees and won't interfere with the PR branch.
-
-## Step 8: Evaluate and post a formal PR review
-
-After the test comment is posted, evaluate whether the run was thorough enough to make a merge decision, then post a formal GitHub review (approve or request changes). **This step is mandatory — every test run MUST end with a formal review decision.**
-
-### Evaluation criteria
-
-Re-read the PR description:
-```bash
-gh pr view "$PR_NUMBER" --json body --jq '.body' --repo "$REPO"
-```
-
-Score the run against each criterion:
-
-| Criterion | Pass condition |
-|-----------|---------------|
-| **Coverage** | Every feature/change described in the PR has at least one test scenario |
-| **All scenarios pass** | No FAIL rows in the results table |
-| **Negative tests** | At least one failure-path test per feature (invalid input, unauthorized, edge case) |
-| **Before/after evidence** | Every state-changing API call has before/after values logged |
-| **Screenshots are meaningful** | Screenshots show the actual state change, not just a loading spinner or blank page |
-| **No regressions** | Existing core flows (login, agent create/run) still work |
-
-### Decision logic
-
-```
-ALL criteria pass                            → APPROVE
-Any scenario FAIL or missing PR feature      → REQUEST_CHANGES (list gaps)
-Evidence weak (no before/after, vague shots) → REQUEST_CHANGES (list what's missing)
-```
-
-### Post the review
-
-```bash
-REVIEW_FILE=$(mktemp)
-
-# Count results
-PASS_COUNT=$(echo "$TEST_RESULTS_TABLE" | grep -c "PASS" || true)
-FAIL_COUNT=$(echo "$TEST_RESULTS_TABLE" | grep -c "FAIL" || true)
-TOTAL=$(( PASS_COUNT + FAIL_COUNT ))
-
-# List any coverage gaps found during evaluation (populate this array as you assess)
-# e.g. COVERAGE_GAPS=("PR claims to add X but no test covers it")
-COVERAGE_GAPS=()
-```
-
-**If APPROVING** — all criteria met, zero failures, full coverage:
-
-```bash
-cat > "$REVIEW_FILE" <<REVIEWEOF
-## E2E Test Evaluation — APPROVED
-
-**Results:** ${PASS_COUNT}/${TOTAL} scenarios passed.
-
-**Coverage:** All features described in the PR were exercised.
-
-**Evidence:** Before/after API values logged for all state-changing operations; screenshots show meaningful state transitions.
-
-**Negative tests:** Failure paths tested for each feature.
-
-No regressions observed on core flows.
-REVIEWEOF
-
-gh pr review "$PR_NUMBER" --repo "$REPO" --approve --body "$(cat "$REVIEW_FILE")"
-echo "✅ PR approved"
-```
-
-**If REQUESTING CHANGES** — any failure, coverage gap, or missing evidence:
-
-```bash
-FAIL_LIST=$(echo "$TEST_RESULTS_TABLE" | grep "FAIL" | awk -F'|' '{print "- Scenario" $2 "failed"}' || true)
-
-cat > "$REVIEW_FILE" <<REVIEWEOF
-## E2E Test Evaluation — Changes Requested
-
-**Results:** ${PASS_COUNT}/${TOTAL} scenarios passed, ${FAIL_COUNT} failed.
-
-### Required before merge
-
-${FAIL_LIST}
-$(for gap in "${COVERAGE_GAPS[@]}"; do echo "- $gap"; done)
-
-Please fix the above and re-run the E2E tests.
-REVIEWEOF
-
-gh pr review "$PR_NUMBER" --repo "$REPO" --request-changes --body "$(cat "$REVIEW_FILE")"
-echo "❌ Changes requested"
-```
-
-```bash
-rm -f "$REVIEW_FILE"
-```
-
-**Rules:**
-- In `--fix` mode, fix all failures before posting the review — the review reflects the final state after fixes
-- Never approve if any scenario failed, even if it seems like a flake — rerun that scenario first
-- Never request changes for issues already fixed in this run
-
-## Fix mode (--fix flag)
-
-When `--fix` is present, the standard is HIGHER. Do not just note issues — FIX them immediately.
-
-### Fix protocol for EVERY issue found (including UX issues):
-
-1. **Identify** the root cause in the code — read the relevant source files
-2. **Write a failing test first** (TDD): For backend bugs, write a test marked with `pytest.mark.xfail(reason="...")`. For frontend/Playwright bugs, write a test with `.fixme` annotation. Run it to confirm it fails as expected.
-3. **Screenshot** the broken state: `agent-browser screenshot $RESULTS_DIR/{NN}-broken-{description}.png`
-4. **Fix** the code in the worktree
-5. **Rebuild** ONLY the affected service (not the whole stack):
-   ```bash
-   cd $PLATFORM_DIR && docker compose up --build -d {service_name}
-   # e.g., docker compose up --build -d rest_server
-   # e.g., docker compose up --build -d frontend
-   ```
-6. **Wait** for the service to be ready (poll health endpoint)
-7. **Re-test** the same scenario
-8. **Screenshot** the fixed state: `agent-browser screenshot $RESULTS_DIR/{NN}-fixed-{description}.png`
-9. **Remove the xfail/fixme marker** from the test written in step 2, and verify it passes
-10. **Verify** the fix did not break other scenarios (run a quick smoke test)
-11. **Commit and push** immediately:
-   ```bash
-   cd $WORKTREE_PATH
-   git add -A
-   git commit -m "fix: {description of fix}"
-   git push
-   ```
-12. **Continue** to the next test scenario
-
-### Fix loop (like pr-address)
-
-```text
-test scenario → find issue (bug OR UX problem) → screenshot broken state
-→ fix code → rebuild affected service only → re-test → screenshot fixed state
-→ verify no regressions → commit + push
-→ repeat for next scenario
-→ after ALL scenarios pass, run full re-test to verify everything together
-```
-
-**Key differences from non-fix mode:**
-- UX issues count as bugs — fix them (bad alignment, confusing labels, missing loading states)
-- Every fix MUST have a before/after screenshot pair proving it works
-- Commit after EACH fix, not in a batch at the end
-- The final re-test must produce a clean set of all-passing screenshots
-
-## Known issues and workarounds
-
-### Problem: "Database error finding user" on signup
-**Cause:** Supabase auth service schema cache is stale after migration.
-**Fix:** `docker restart supabase-auth && sleep 5` then retry signup.
-
-### Problem: Copilot returns auth errors in subscription mode
-**Cause:** `CHAT_USE_CLAUDE_CODE_SUBSCRIPTION=true` but `CLAUDE_CODE_OAUTH_TOKEN` is not set or expired.
-**Fix:** Re-extract the OAuth token from macOS keychain (see step 3b, Option 1) and recreate the container (`docker compose up -d copilot_executor`). The backend auto-provisions `~/.claude/.credentials.json` from the env var on startup. No `npm install` or `claude login` needed — the SDK bundles its own CLI binary.
-
-### Problem: agent-browser can't find chromium
-**Cause:** The Dockerfile auto-provisions system chromium on all architectures (including ARM64). If your branch is behind `dev`, this may not be present yet.
-**Fix:** Check if chromium exists: `which chromium || which chromium-browser`. If missing, install it: `apt-get install -y chromium` and set `AGENT_BROWSER_EXECUTABLE_PATH=/usr/bin/chromium` in the container environment.
-
-### Problem: agent-browser selector matches multiple elements
-**Cause:** `text=X` matches all elements containing that text.
-**Fix:** Use `agent-browser snapshot` to get specific `ref=eNN` references, then use those: `agent-browser click eNN`.
-
-### Problem: Frontend shows cookie banner blocking interaction
-**Fix:** `agent-browser click 'text=Accept All'` before other interactions.
-
-### Problem: Container loses npm packages after rebuild
-**Cause:** `docker compose up --build` rebuilds the image, losing runtime installs.
-**Fix:** Add packages to the Dockerfile instead of installing at runtime.
-
-### Problem: Services not starting after `docker compose up`
-**Fix:** Wait and check health: `docker compose ps`. Common cause: migration hasn't finished. Check: `docker logs autogpt_platform-migrate-1 2>&1 | tail -5`. If supabase-db isn't healthy: `docker restart supabase-db && sleep 10`.
-
-### Problem: Docker uses cached layers with old code (PR changes not visible)
-**Cause:** `docker compose up --build` reuses cached `COPY` layers from previous builds. If the PR branch changes Python files but the previous build already cached that layer from `dev`, the container runs `dev` code.
-**Fix:** Always use `docker compose build --no-cache` for the first build of a PR branch. Subsequent rebuilds within the same branch can use `--build`.
-
-### Problem: `agent-browser open` loses login session
-**Cause:** Without session persistence, `agent-browser open` starts fresh.
-**Fix:** Use `--session-name pr-test` on ALL agent-browser commands. This auto-saves/restores cookies and localStorage across navigations. Alternatively, use `agent-browser eval "window.location.href = '...'"` to navigate within the same context.
-
-### Problem: Supabase auth returns "Database error querying schema"
-**Cause:** The database schema changed (migration ran) but supabase-auth has a stale schema cache.
-**Fix:** `docker restart supabase-db && sleep 10 && docker restart supabase-auth && sleep 8`. If user data was lost, re-signup.

.claude/skills/setup-repo/SKILL.md

@@ -1,195 +0,0 @@
----
-name: setup-repo
-description: Initialize a worktree-based repo layout for parallel development. Creates a main worktree, a reviews worktree for PR reviews, and N numbered work branches. Handles .env creation, dependency installation, and branchlet config. TRIGGER when user asks to set up the repo from scratch, initialize worktrees, bootstrap their dev environment, "setup repo", "setup worktrees", "initialize dev environment", "set up branches", or when a freshly cloned repo has no sibling worktrees.
-user-invocable: true
-args: "No arguments — interactive setup via prompts."
-metadata:
-  author: autogpt-team
-  version: "1.0.0"
----
-
-# Repository Setup
-
-This skill sets up a worktree-based development layout from a freshly cloned repo. It creates:
-- A **main** worktree (the primary checkout)
-- A **reviews** worktree (for PR reviews)
-- **N work branches** (branch1..branchN) for parallel development
-
-## Step 1: Identify the repo
-
-Determine the repo root and parent directory:
-
-```bash
-ROOT=$(git rev-parse --show-toplevel)
-REPO_NAME=$(basename "$ROOT")
-PARENT=$(dirname "$ROOT")
-```
-
-Detect if the repo is already inside a worktree layout by counting sibling worktrees (not just checking the directory name, which could be anything):
-
-```bash
-# Count worktrees that are siblings (live under $PARENT but aren't $ROOT itself)
-SIBLING_COUNT=$(git worktree list --porcelain 2>/dev/null | grep "^worktree " | grep -c "$PARENT/" || true)
-if [ "$SIBLING_COUNT" -gt 1 ]; then
-  echo "INFO: Existing worktree layout detected at $PARENT ($SIBLING_COUNT worktrees)"
-  # Use $ROOT as-is; skip renaming/restructuring
-else
-  echo "INFO: Fresh clone detected, proceeding with setup"
-fi
-```
-
-## Step 2: Ask the user questions
-
-Use AskUserQuestion to gather setup preferences:
-
-1. **How many parallel work branches do you need?** (Options: 4, 8, 16, or custom)
-   - These become `branch1` through `branchN`
-2. **Which branch should be the base?** (Options: origin/master, origin/dev, or custom)
-   - All work branches and reviews will start from this
-
-## Step 3: Fetch and set up branches
-
-```bash
-cd "$ROOT"
-git fetch origin
-
-# Create the reviews branch from base (skip if already exists)
-if git show-ref --verify --quiet refs/heads/reviews; then
-  echo "INFO: Branch 'reviews' already exists, skipping"
-else
-  git branch reviews <base-branch>
-fi
-
-# Create numbered work branches from base (skip if already exists)
-for i in $(seq 1 "$COUNT"); do
-  if git show-ref --verify --quiet "refs/heads/branch$i"; then
-    echo "INFO: Branch 'branch$i' already exists, skipping"
-  else
-    git branch "branch$i" <base-branch>
-  fi
-done
-```
-
-## Step 4: Create worktrees
-
-Create worktrees as siblings to the main checkout:
-
-```bash
-if [ -d "$PARENT/reviews" ]; then
-  echo "INFO: Worktree '$PARENT/reviews' already exists, skipping"
-else
-  git worktree add "$PARENT/reviews" reviews
-fi
-
-for i in $(seq 1 "$COUNT"); do
-  if [ -d "$PARENT/branch$i" ]; then
-    echo "INFO: Worktree '$PARENT/branch$i' already exists, skipping"
-  else
-    git worktree add "$PARENT/branch$i" "branch$i"
-  fi
-done
-```
-
-## Step 5: Set up environment files
-
-**Do NOT assume .env files exist.** For each worktree (including main if needed):
-
-1. Check if `.env` exists in the source worktree for each path
-2. If `.env` exists, copy it
-3. If only `.env.default` or `.env.example` exists, copy that as `.env`
-4. If neither exists, warn the user and list which env files are missing
-
-Env file locations to check (same as the `/worktree` skill — keep these in sync):
-- `autogpt_platform/.env`
-- `autogpt_platform/backend/.env`
-- `autogpt_platform/frontend/.env`
-
-> **Note:** This env copying logic intentionally mirrors the `/worktree` skill's approach. If you update the path list or fallback logic here, update `/worktree` as well.
-
-```bash
-SOURCE="$ROOT"
-WORKTREES="reviews"
-for i in $(seq 1 "$COUNT"); do WORKTREES="$WORKTREES branch$i"; done
-
-FOUND_ANY_ENV=0
-for wt in $WORKTREES; do
-  TARGET="$PARENT/$wt"
-  for envpath in autogpt_platform autogpt_platform/backend autogpt_platform/frontend; do
-    if [ -f "$SOURCE/$envpath/.env" ]; then
-      FOUND_ANY_ENV=1
-      cp "$SOURCE/$envpath/.env" "$TARGET/$envpath/.env"
-    elif [ -f "$SOURCE/$envpath/.env.default" ]; then
-      FOUND_ANY_ENV=1
-      cp "$SOURCE/$envpath/.env.default" "$TARGET/$envpath/.env"
-      echo "NOTE: $wt/$envpath/.env was created from .env.default — you may need to edit it"
-    elif [ -f "$SOURCE/$envpath/.env.example" ]; then
-      FOUND_ANY_ENV=1
-      cp "$SOURCE/$envpath/.env.example" "$TARGET/$envpath/.env"
-      echo "NOTE: $wt/$envpath/.env was created from .env.example — you may need to edit it"
-    else
-      echo "WARNING: No .env, .env.default, or .env.example found at $SOURCE/$envpath/"
-    fi
-  done
-done
-
-if [ "$FOUND_ANY_ENV" -eq 0 ]; then
-  echo "WARNING: No environment files or templates were found in the source worktree."
-  # Use AskUserQuestion to confirm: "Continue setup without env files?"
-  # If the user declines, stop here and let them set up .env files first.
-fi
-```
-
-## Step 6: Copy branchlet config
-
-Copy `.branchlet.json` from main to each worktree so branchlet can manage sub-worktrees:
-
-```bash
-if [ -f "$ROOT/.branchlet.json" ]; then
-  for wt in $WORKTREES; do
-    cp "$ROOT/.branchlet.json" "$PARENT/$wt/.branchlet.json"
-  done
-fi
-```
-
-## Step 7: Install dependencies
-
-Install deps in all worktrees. Run these sequentially per worktree:
-
-```bash
-for wt in $WORKTREES; do
-  TARGET="$PARENT/$wt"
-  echo "=== Installing deps for $wt ==="
-  (cd "$TARGET/autogpt_platform/autogpt_libs" && poetry install) &&
-  (cd "$TARGET/autogpt_platform/backend" && poetry install && poetry run prisma generate) &&
-  (cd "$TARGET/autogpt_platform/frontend" && pnpm install) &&
-  echo "=== Done: $wt ===" ||
-  echo "=== FAILED: $wt ==="
-done
-```
-
-This is slow. Run in background if possible and notify when complete.
-
-## Step 8: Verify and report
-
-After setup, verify and report to the user:
-
-```bash
-git worktree list
-```
-
-Summarize:
-- Number of worktrees created
-- Which env files were copied vs created from defaults vs missing
-- Any warnings or errors encountered
-
-## Final directory layout
-
-```
-parent/
-  main/              # Primary checkout (already exists)
-  reviews/           # PR review worktree
-  branch1/           # Work branch 1
-  branch2/           # Work branch 2
-  ...
-  branchN/           # Work branch N
-```

.claude/skills/worktree/SKILL.md

@@ -1,85 +0,0 @@
----
-name: worktree
-description: Set up a new git worktree for parallel development. Creates the worktree, copies .env files, installs dependencies, and generates Prisma client. TRIGGER when user asks to set up a worktree, work on a branch in isolation, or needs a separate environment for a branch or PR.
-user-invocable: true
-args: "[name] — optional worktree name (e.g., 'AutoGPT7'). If omitted, uses next available AutoGPT<N>."
-metadata:
-  author: autogpt-team
-  version: "3.0.0"
----
-
-# Worktree Setup
-
-## Create the worktree
-
-Derive paths from the git toplevel. If a name is provided as argument, use it. Otherwise, check `git worktree list` and pick the next `AutoGPT<N>`.
-
-```bash
-ROOT=$(git rev-parse --show-toplevel)
-PARENT=$(dirname "$ROOT")
-
-# From an existing branch
-git worktree add "$PARENT/<NAME>" <branch-name>
-
-# From a new branch off dev
-git worktree add -b <new-branch> "$PARENT/<NAME>" dev
-```
-
-## Copy environment files
-
-Copy `.env` from the root worktree. Falls back to `.env.default` if `.env` doesn't exist.
-
-```bash
-ROOT=$(git rev-parse --show-toplevel)
-TARGET="$(dirname "$ROOT")/<NAME>"
-
-for envpath in autogpt_platform/backend autogpt_platform/frontend autogpt_platform; do
-  if [ -f "$ROOT/$envpath/.env" ]; then
-    cp "$ROOT/$envpath/.env" "$TARGET/$envpath/.env"
-  elif [ -f "$ROOT/$envpath/.env.default" ]; then
-    cp "$ROOT/$envpath/.env.default" "$TARGET/$envpath/.env"
-  fi
-done
-```
-
-## Install dependencies
-
-```bash
-TARGET="$(dirname "$(git rev-parse --show-toplevel)")/<NAME>"
-cd "$TARGET/autogpt_platform/autogpt_libs" && poetry install
-cd "$TARGET/autogpt_platform/backend" && poetry install && poetry run prisma generate
-cd "$TARGET/autogpt_platform/frontend" && pnpm install
-```
-
-Replace `<NAME>` with the actual worktree name (e.g., `AutoGPT7`).
-
-## Running the app (optional)
-
-Backend uses ports: 8001, 8002, 8003, 8005, 8006, 8007, 8008. Free them first if needed:
-
-```bash
-TARGET="$(dirname "$(git rev-parse --show-toplevel)")/<NAME>"
-for port in 8001 8002 8003 8005 8006 8007 8008; do
-  lsof -ti :$port | xargs kill -9 2>/dev/null || true
-done
-cd "$TARGET/autogpt_platform/backend" && poetry run app
-```
-
-## CoPilot testing
-
-SDK mode spawns a Claude subprocess — won't work inside Claude Code. Set `CHAT_USE_CLAUDE_AGENT_SDK=false` in `backend/.env` to use baseline mode.
-
-## Cleanup
-
-```bash
-# Replace <NAME> with the actual worktree name (e.g., AutoGPT7)
-git worktree remove "$(dirname "$(git rev-parse --show-toplevel)")/<NAME>"
-```
-
-## Alternative: Branchlet (optional)
-
-If [branchlet](https://www.npmjs.com/package/branchlet) is installed:
-
-```bash
-branchlet create -n <name> -s <source-branch> -b <new-branch>
-```

.claude/skills/write-frontend-tests/SKILL.md

@@ -1,224 +0,0 @@
----
-name: write-frontend-tests
-description: "Analyze the current branch diff against dev, plan integration tests for changed frontend pages/components, and write them. TRIGGER when user asks to write frontend tests, add test coverage, or 'write tests for my changes'."
-user-invocable: true
-args: "[base branch] — defaults to dev. Optionally pass a specific base branch to diff against."
-metadata:
-  author: autogpt-team
-  version: "1.0.0"
----
-
-# Write Frontend Tests
-
-Analyze the current branch's frontend changes, plan integration tests, and write them.
-
-## References
-
-Before writing any tests, read the testing rules and conventions:
-
-- `autogpt_platform/frontend/TESTING.md` — testing strategy, file locations, examples
-- `autogpt_platform/frontend/src/tests/AGENTS.md` — detailed testing rules, MSW patterns, decision flowchart
-- `autogpt_platform/frontend/src/tests/integrations/test-utils.tsx` — custom render with providers
-- `autogpt_platform/frontend/src/tests/integrations/vitest.setup.tsx` — MSW server setup
-
-## Step 1: Identify changed frontend files
-
-```bash
-BASE_BRANCH="${ARGUMENTS:-dev}"
-cd autogpt_platform/frontend
-
-# Get changed frontend files (excluding generated, config, and test files)
-git diff "$BASE_BRANCH"...HEAD --name-only -- src/ \
-  | grep -v '__generated__' \
-  | grep -v '__tests__' \
-  | grep -v '\.test\.' \
-  | grep -v '\.stories\.' \
-  | grep -v '\.spec\.'
-```
-
-Also read the diff to understand what changed:
-
-```bash
-git diff "$BASE_BRANCH"...HEAD --stat -- src/
-git diff "$BASE_BRANCH"...HEAD -- src/ | head -500
-```
-
-## Step 2: Categorize changes and find test targets
-
-For each changed file, determine:
-
-1. **Is it a page?** (`page.tsx`) — these are the primary test targets
-2. **Is it a hook?** (`use*.ts`) — test via the page that uses it
-3. **Is it a component?** (`.tsx` in `components/`) — test via the parent page unless it's complex enough to warrant isolation
-4. **Is it a helper?** (`helpers.ts`, `utils.ts`) — unit test directly if pure logic
-
-**Priority order:**
-1. Pages with new/changed data fetching or user interactions
-2. Components with complex internal logic (modals, forms, wizards)
-3. Hooks with non-trivial business logic
-4. Pure helper functions
-
-Skip: styling-only changes, type-only changes, config changes.
-
-## Step 3: Check for existing tests
-
-For each test target, check if tests already exist:
-
-```bash
-# For a page at src/app/(platform)/library/page.tsx
-ls src/app/\(platform\)/library/__tests__/ 2>/dev/null
-
-# For a component at src/app/(platform)/library/components/AgentCard/AgentCard.tsx
-ls src/app/\(platform\)/library/components/AgentCard/__tests__/ 2>/dev/null
-```
-
-Note which targets have no tests (need new files) vs which have tests that need updating.
-
-## Step 4: Identify API endpoints used
-
-For each test target, find which API hooks are used:
-
-```bash
-# Find generated API hook imports in the changed files
-grep -rn 'from.*__generated__/endpoints' src/app/\(platform\)/library/
-grep -rn 'use[A-Z].*V[12]' src/app/\(platform\)/library/
-```
-
-For each API hook found, locate the corresponding MSW handler:
-
-```bash
-# If the page uses useGetV2ListLibraryAgents, find its MSW handlers
-grep -rn 'getGetV2ListLibraryAgents.*Handler' src/app/api/__generated__/endpoints/library/library.msw.ts
-```
-
-List every MSW handler you will need (200 for happy path, 4xx for error paths).
-
-## Step 5: Write the test plan
-
-Before writing code, output a plan as a numbered list:
-
-```
-Test plan for [branch name]:
-
-1. src/app/(platform)/library/__tests__/main.test.tsx (NEW)
-   - Renders page with agent list (MSW 200)
-   - Shows loading state
-   - Shows error state (MSW 422)
-   - Handles empty agent list
-
-2. src/app/(platform)/library/__tests__/search.test.tsx (NEW)
-   - Filters agents by search query
-   - Shows no results message
-   - Clears search
-
-3. src/app/(platform)/library/components/AgentCard/__tests__/AgentCard.test.tsx (UPDATE)
-   - Add test for new "duplicate" action
-```
-
-Present this plan to the user. Wait for confirmation before proceeding. If the user has feedback, adjust the plan.
-
-## Step 6: Write the tests
-
-For each test file in the plan, follow these conventions:
-
-### File structure
-
-```tsx
-import { render, screen, waitFor } from "@/tests/integrations/test-utils";
-import { server } from "@/mocks/mock-server";
-// Import MSW handlers for endpoints the page uses
-import {
-  getGetV2ListLibraryAgentsMockHandler200,
-  getGetV2ListLibraryAgentsMockHandler422,
-} from "@/app/api/__generated__/endpoints/library/library.msw";
-// Import the component under test
-import LibraryPage from "../page";
-
-describe("LibraryPage", () => {
-  test("renders agent list from API", async () => {
-    server.use(getGetV2ListLibraryAgentsMockHandler200());
-
-    render(<LibraryPage />);
-
-    expect(await screen.findByText(/my agents/i)).toBeDefined();
-  });
-
-  test("shows error state on API failure", async () => {
-    server.use(getGetV2ListLibraryAgentsMockHandler422());
-
-    render(<LibraryPage />);
-
-    expect(await screen.findByText(/error/i)).toBeDefined();
-  });
-});
-```
-
-### Rules
-
-- Use `render()` from `@/tests/integrations/test-utils` (NOT from `@testing-library/react` directly)
-- Use `server.use()` to set up MSW handlers BEFORE rendering
-- Use `findBy*` (async) for elements that appear after data fetching — NOT `getBy*`
-- Use `getBy*` only for elements that are immediately present in the DOM
-- Use `screen` queries — do NOT destructure from `render()`
-- Use `waitFor` when asserting side effects or state changes after interactions
-- Import `fireEvent` or `userEvent` from the test-utils for interactions
-- Do NOT mock internal hooks or functions — mock at the API boundary via MSW
-- Do NOT use `act()` manually — `render` and `fireEvent` handle it
-- Keep tests focused: one behavior per test
-- Use descriptive test names that read like sentences
-
-### Test location
-
-```
-# For pages: __tests__/ next to page.tsx
-src/app/(platform)/library/__tests__/main.test.tsx
-
-# For complex standalone components: __tests__/ inside component folder
-src/app/(platform)/library/components/AgentCard/__tests__/AgentCard.test.tsx
-
-# For pure helpers: co-located .test.ts
-src/app/(platform)/library/helpers.test.ts
-```
-
-### Custom MSW overrides
-
-When the auto-generated faker data is not enough, override with specific data:
-
-```tsx
-import { http, HttpResponse } from "msw";
-
-server.use(
-  http.get("http://localhost:3000/api/proxy/api/v2/library/agents", () => {
-    return HttpResponse.json({
-      agents: [
-        { id: "1", name: "Test Agent", description: "A test agent" },
-      ],
-      pagination: { total_items: 1, total_pages: 1, page: 1, page_size: 10 },
-    });
-  }),
-);
-```
-
-Use the proxy URL pattern: `http://localhost:3000/api/proxy/api/v{version}/{path}` — this matches the MSW base URL configured in `orval.config.ts`.
-
-## Step 7: Run and verify
-
-After writing all tests:
-
-```bash
-cd autogpt_platform/frontend
-pnpm test:unit --reporter=verbose
-```
-
-If tests fail:
-1. Read the error output carefully
-2. Fix the test (not the source code, unless there is a genuine bug)
-3. Re-run until all pass
-
-Then run the full checks:
-
-```bash
-pnpm format
-pnpm lint
-pnpm types
-```

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,12 +1,8 @@
-### Why / What / How
-
-<!-- Why: Why does this PR exist? What problem does it solve, or what's broken/missing without it? -->
-<!-- What: What does this PR change? Summarize the changes at a high level. -->
-<!-- How: How does it work? Describe the approach, key implementation details, or architecture decisions. -->
+<!-- Clearly explain the need for these changes: -->
 
 ### Changes 🏗️
 
-<!-- List the key changes. Keep it higher level than the diff but specific enough to highlight what's new/modified. -->
+<!-- Concisely describe all of the changes made in this pull request: -->
 
 ### Checklist 📋
 

.github/workflows/classic-autogpt-ci.yml

@@ -6,19 +6,11 @@ on:
     paths:
       - '.github/workflows/classic-autogpt-ci.yml'
       - 'classic/original_autogpt/**'
-      - 'classic/direct_benchmark/**'
-      - 'classic/forge/**'
-      - 'classic/pyproject.toml'
-      - 'classic/poetry.lock'
   pull_request:
     branches: [ master, dev, release-* ]
     paths:
       - '.github/workflows/classic-autogpt-ci.yml'
       - 'classic/original_autogpt/**'
-      - 'classic/direct_benchmark/**'
-      - 'classic/forge/**'
-      - 'classic/pyproject.toml'
-      - 'classic/poetry.lock'
 
 concurrency:
   group: ${{ format('classic-autogpt-ci-{0}', github.head_ref && format('{0}-{1}', github.event_name, github.event.pull_request.number) || github.sha) }}
@@ -27,22 +19,47 @@ concurrency:
 defaults:
   run:
     shell: bash
-    working-directory: classic
+    working-directory: classic/original_autogpt
 
 jobs:
   test:
     permissions:
       contents: read
     timeout-minutes: 30
-    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10"]
+        platform-os: [ubuntu, macos, macos-arm64, windows]
+    runs-on: ${{ matrix.platform-os != 'macos-arm64' && format('{0}-latest', matrix.platform-os) || 'macos-14' }}
 
     steps:
-      - name: Start MinIO service
+      # Quite slow on macOS (2~4 minutes to set up Docker)
+      # - name: Set up Docker (macOS)
+      #   if: runner.os == 'macOS'
+      #   uses: crazy-max/ghaction-setup-docker@v3
+
+      - name: Start MinIO service (Linux)
+        if: runner.os == 'Linux'
         working-directory: '.'
         run: |
           docker pull minio/minio:edge-cicd
           docker run -d -p 9000:9000 minio/minio:edge-cicd
 
+      - name: Start MinIO service (macOS)
+        if: runner.os == 'macOS'
+        working-directory: ${{ runner.temp }}
+        run: |
+          brew install minio/stable/minio
+          mkdir data
+          minio server ./data &
+
+      # No MinIO on Windows:
+      # - Windows doesn't support running Linux Docker containers
+      # - It doesn't seem possible to start background processes on Windows. They are
+      #   killed after the step returns.
+      #   See: https://github.com/actions/runner/issues/598#issuecomment-2011890429
+
       - name: Checkout repository
         uses: actions/checkout@v4
         with:
@@ -54,23 +71,41 @@ jobs:
           git config --global user.name "Auto-GPT-Bot"
           git config --global user.email "github-bot@agpt.co"
 
-      - name: Set up Python 3.12
+      - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:
-          python-version: "3.12"
+          python-version: ${{ matrix.python-version }}
 
       - id: get_date
         name: Get date
         run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_OUTPUT
 
       - name: Set up Python dependency cache
+        # On Windows, unpacking cached dependencies takes longer than just installing them
+        if: runner.os != 'Windows'
         uses: actions/cache@v4
         with:
-          path: ~/.cache/pypoetry
-          key: poetry-${{ runner.os }}-${{ hashFiles('classic/poetry.lock') }}
+          path: ${{ runner.os == 'macOS' && '~/Library/Caches/pypoetry' || '~/.cache/pypoetry' }}
+          key: poetry-${{ runner.os }}-${{ hashFiles('classic/original_autogpt/poetry.lock') }}
 
-      - name: Install Poetry
-        run: curl -sSL https://install.python-poetry.org | python3 -
+      - name: Install Poetry (Unix)
+        if: runner.os != 'Windows'
+        run: |
+          curl -sSL https://install.python-poetry.org | python3 -
+
+          if [ "${{ runner.os }}" = "macOS" ]; then
+            PATH="$HOME/.local/bin:$PATH"
+            echo "$HOME/.local/bin" >> $GITHUB_PATH
+          fi
+
+      - name: Install Poetry (Windows)
+        if: runner.os == 'Windows'
+        shell: pwsh
+        run: |
+          (Invoke-WebRequest -Uri https://install.python-poetry.org -UseBasicParsing).Content | python -
+
+          $env:PATH += ";$env:APPDATA\Python\Scripts"
+          echo "$env:APPDATA\Python\Scripts" >> $env:GITHUB_PATH
 
       - name: Install Python dependencies
         run: poetry install
@@ -81,13 +116,12 @@ jobs:
             --cov=autogpt --cov-branch --cov-report term-missing --cov-report xml \
             --numprocesses=logical --durations=10 \
             --junitxml=junit.xml -o junit_family=legacy \
-            original_autogpt/tests/unit original_autogpt/tests/integration
+            tests/unit tests/integration
         env:
           CI: true
           PLAIN_OUTPUT: True
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
-          S3_ENDPOINT_URL: http://127.0.0.1:9000
+          S3_ENDPOINT_URL: ${{ runner.os != 'Windows' && 'http://127.0.0.1:9000' || '' }}
           AWS_ACCESS_KEY_ID: minioadmin
           AWS_SECRET_ACCESS_KEY: minioadmin
 
@@ -101,11 +135,11 @@ jobs:
         uses: codecov/codecov-action@v5
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
-          flags: autogpt-agent
+          flags: autogpt-agent,${{ runner.os }}
 
       - name: Upload logs to artifact
         if: always()
         uses: actions/upload-artifact@v4
         with:
           name: test-logs
-          path: classic/logs/
+          path: classic/original_autogpt/logs/

.github/workflows/classic-autogpt-docker-ci.yml

@@ -148,7 +148,7 @@ jobs:
             --entrypoint poetry ${{ env.IMAGE_NAME }} run \
             pytest -v --cov=autogpt --cov-branch --cov-report term-missing \
             --numprocesses=4 --durations=10 \
-            original_autogpt/tests/unit original_autogpt/tests/integration 2>&1 | tee test_output.txt
+            tests/unit tests/integration 2>&1 | tee test_output.txt
 
           test_failure=${PIPESTATUS[0]}
 

.github/workflows/classic-autogpts-ci.yml

@@ -10,9 +10,10 @@ on:
       - '.github/workflows/classic-autogpts-ci.yml'
       - 'classic/original_autogpt/**'
       - 'classic/forge/**'
-      - 'classic/direct_benchmark/**'
-      - 'classic/pyproject.toml'
-      - 'classic/poetry.lock'
+      - 'classic/benchmark/**'
+      - 'classic/run'
+      - 'classic/cli.py'
+      - 'classic/setup.py'
       - '!**/*.md'
   pull_request:
     branches: [ master, dev, release-* ]
@@ -20,9 +21,10 @@ on:
       - '.github/workflows/classic-autogpts-ci.yml'
       - 'classic/original_autogpt/**'
       - 'classic/forge/**'
-      - 'classic/direct_benchmark/**'
-      - 'classic/pyproject.toml'
-      - 'classic/poetry.lock'
+      - 'classic/benchmark/**'
+      - 'classic/run'
+      - 'classic/cli.py'
+      - 'classic/setup.py'
       - '!**/*.md'
 
 defaults:
@@ -33,9 +35,13 @@ defaults:
 jobs:
   serve-agent-protocol:
     runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        agent-name: [ original_autogpt ]
+      fail-fast: false
     timeout-minutes: 20
     env:
-      min-python-version: '3.12'
+      min-python-version: '3.10'
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
@@ -49,22 +55,22 @@ jobs:
           python-version: ${{ env.min-python-version }}
 
       - name: Install Poetry
+        working-directory: ./classic/${{ matrix.agent-name }}/
         run: |
           curl -sSL https://install.python-poetry.org | python -
 
-      - name: Install dependencies
-        run: poetry install
-
-      - name: Run smoke tests with direct-benchmark
+      - name: Run regression tests
         run: |
-          poetry run direct-benchmark run \
-            --strategies one_shot \
-            --models claude \
-            --tests ReadFile,WriteFile \
-            --json
+          ./run agent start ${{ matrix.agent-name }}
+          cd ${{ matrix.agent-name }}
+          poetry run agbenchmark --mock --test=BasicRetrieval --test=Battleship --test=WebArenaTask_0
+          poetry run agbenchmark --test=WriteFile
         env:
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+          AGENT_NAME: ${{ matrix.agent-name }}
           REQUESTS_CA_BUNDLE: /etc/ssl/certs/ca-certificates.crt
-          NONINTERACTIVE_MODE: "true"
-          CI: true
+          HELICONE_CACHE_ENABLED: false
+          HELICONE_PROPERTY_AGENT: ${{ matrix.agent-name }}
+          REPORTS_FOLDER: ${{ format('../../reports/{0}', matrix.agent-name) }}
+          TELEMETRY_ENVIRONMENT: autogpt-ci
+          TELEMETRY_OPT_IN: ${{ github.ref_name == 'master' }}

.github/workflows/classic-benchmark-ci.yml

@@ -1,24 +1,18 @@
-name: Classic - Direct Benchmark CI
+name: Classic - AGBenchmark CI
 
 on:
   push:
     branches: [ master, dev, ci-test* ]
     paths:
-      - 'classic/direct_benchmark/**'
-      - 'classic/original_autogpt/**'
-      - 'classic/forge/**'
+      - 'classic/benchmark/**'
+      - '!classic/benchmark/reports/**'
       - .github/workflows/classic-benchmark-ci.yml
-      - 'classic/pyproject.toml'
-      - 'classic/poetry.lock'
   pull_request:
     branches: [ master, dev, release-* ]
     paths:
-      - 'classic/direct_benchmark/**'
-      - 'classic/original_autogpt/**'
-      - 'classic/forge/**'
+      - 'classic/benchmark/**'
+      - '!classic/benchmark/reports/**'
       - .github/workflows/classic-benchmark-ci.yml
-      - 'classic/pyproject.toml'
-      - 'classic/poetry.lock'
 
 concurrency:
   group: ${{ format('benchmark-ci-{0}', github.head_ref && format('{0}-{1}', github.event_name, github.event.pull_request.number) || github.sha) }}
@@ -29,16 +23,23 @@ defaults:
     shell: bash
 
 env:
-  min-python-version: '3.12'
+  min-python-version: '3.10'
 
 jobs:
-  benchmark-tests:
-    runs-on: ubuntu-latest
+  test:
+    permissions:
+      contents: read
     timeout-minutes: 30
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10"]
+        platform-os: [ubuntu, macos, macos-arm64, windows]
+    runs-on: ${{ matrix.platform-os != 'macos-arm64' && format('{0}-latest', matrix.platform-os) || 'macos-14' }}
     defaults:
       run:
         shell: bash
-        working-directory: classic
+        working-directory: classic/benchmark
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
@@ -46,88 +47,71 @@ jobs:
           fetch-depth: 0
           submodules: true
 
-      - name: Set up Python ${{ env.min-python-version }}
+      - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:
-          python-version: ${{ env.min-python-version }}
+          python-version: ${{ matrix.python-version }}
 
       - name: Set up Python dependency cache
+        # On Windows, unpacking cached dependencies takes longer than just installing them
+        if: runner.os != 'Windows'
         uses: actions/cache@v4
         with:
-          path: ~/.cache/pypoetry
-          key: poetry-${{ runner.os }}-${{ hashFiles('classic/poetry.lock') }}
+          path: ${{ runner.os == 'macOS' && '~/Library/Caches/pypoetry' || '~/.cache/pypoetry' }}
+          key: poetry-${{ runner.os }}-${{ hashFiles('classic/benchmark/poetry.lock') }}
 
-      - name: Install Poetry
+      - name: Install Poetry (Unix)
+        if: runner.os != 'Windows'
         run: |
           curl -sSL https://install.python-poetry.org | python3 -
 
-      - name: Install dependencies
+          if [ "${{ runner.os }}" = "macOS" ]; then
+            PATH="$HOME/.local/bin:$PATH"
+            echo "$HOME/.local/bin" >> $GITHUB_PATH
+          fi
+
+      - name: Install Poetry (Windows)
+        if: runner.os == 'Windows'
+        shell: pwsh
+        run: |
+          (Invoke-WebRequest -Uri https://install.python-poetry.org -UseBasicParsing).Content | python -
+
+          $env:PATH += ";$env:APPDATA\Python\Scripts"
+          echo "$env:APPDATA\Python\Scripts" >> $env:GITHUB_PATH
+
+      - name: Install Python dependencies
         run: poetry install
 
-      - name: Run basic benchmark tests
+      - name: Run pytest with coverage
         run: |
-          echo "Testing ReadFile challenge with one_shot strategy..."
-          poetry run direct-benchmark run \
-            --fresh \
-            --strategies one_shot \
-            --models claude \
-            --tests ReadFile \
-            --json
-
-          echo "Testing WriteFile challenge..."
-          poetry run direct-benchmark run \
-            --fresh \
-            --strategies one_shot \
-            --models claude \
-            --tests WriteFile \
-            --json
+          poetry run pytest -vv \
+            --cov=agbenchmark --cov-branch --cov-report term-missing --cov-report xml \
+            --durations=10 \
+            --junitxml=junit.xml -o junit_family=legacy \
+            tests
         env:
           CI: true
-          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          NONINTERACTIVE_MODE: "true"
 
-      - name: Test category filtering
-        run: |
-          echo "Testing coding category..."
-          poetry run direct-benchmark run \
-            --fresh \
-            --strategies one_shot \
-            --models claude \
-            --categories coding \
-            --tests ReadFile,WriteFile \
-            --json
-        env:
-          CI: true
-          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
-          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          NONINTERACTIVE_MODE: "true"
+      - name: Upload test results to Codecov
+        if: ${{ !cancelled() }}  # Run even if tests fail
+        uses: codecov/test-results-action@v1
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
 
-      - name: Test multiple strategies
-        run: |
-          echo "Testing multiple strategies..."
-          poetry run direct-benchmark run \
-            --fresh \
-            --strategies one_shot,plan_execute \
-            --models claude \
-            --tests ReadFile \
-            --parallel 2 \
-            --json
-        env:
-          CI: true
-          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
-          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          NONINTERACTIVE_MODE: "true"
+      - name: Upload coverage reports to Codecov
+        uses: codecov/codecov-action@v5
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+          flags: agbenchmark,${{ runner.os }}
 
-  # Run regression tests on maintain challenges
-  regression-tests:
+  self-test-with-agent:
     runs-on: ubuntu-latest
-    timeout-minutes: 45
-    if: github.ref == 'refs/heads/master' || github.ref == 'refs/heads/dev'
-    defaults:
-      run:
-        shell: bash
-        working-directory: classic
+    strategy:
+      matrix:
+        agent-name: [forge]
+      fail-fast: false
+    timeout-minutes: 20
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
@@ -140,31 +124,53 @@ jobs:
         with:
           python-version: ${{ env.min-python-version }}
 
-      - name: Set up Python dependency cache
-        uses: actions/cache@v4
-        with:
-          path: ~/.cache/pypoetry
-          key: poetry-${{ runner.os }}-${{ hashFiles('classic/poetry.lock') }}
-
       - name: Install Poetry
         run: |
-          curl -sSL https://install.python-poetry.org | python3 -
-
-      - name: Install dependencies
-        run: poetry install
+          curl -sSL https://install.python-poetry.org | python -
 
       - name: Run regression tests
+        working-directory: classic
         run: |
-          echo "Running regression tests (previously beaten challenges)..."
-          poetry run direct-benchmark run \
-            --fresh \
-            --strategies one_shot \
-            --models claude \
-            --maintain \
-            --parallel 4 \
-            --json
+          ./run agent start ${{ matrix.agent-name }}
+          cd ${{ matrix.agent-name }}
+
+          set +e # Ignore non-zero exit codes and continue execution
+          echo "Running the following command: poetry run agbenchmark --maintain --mock"
+          poetry run agbenchmark --maintain --mock
+          EXIT_CODE=$?
+          set -e  # Stop ignoring non-zero exit codes
+          # Check if the exit code was 5, and if so, exit with 0 instead
+          if [ $EXIT_CODE -eq 5 ]; then
+            echo "regression_tests.json is empty."
+          fi
+
+          echo "Running the following command: poetry run agbenchmark --mock"
+          poetry run agbenchmark --mock
+
+          echo "Running the following command: poetry run agbenchmark --mock --category=data"
+          poetry run agbenchmark --mock --category=data
+
+          echo "Running the following command: poetry run agbenchmark --mock --category=coding"
+          poetry run agbenchmark --mock --category=coding
+
+          # echo "Running the following command: poetry run agbenchmark --test=WriteFile"
+          # poetry run agbenchmark --test=WriteFile
+          cd ../benchmark
+          poetry install
+          echo "Adding the BUILD_SKILL_TREE environment variable. This will attempt to add new elements in the skill tree. If new elements are added, the CI fails because they should have been pushed"
+          export BUILD_SKILL_TREE=true
+
+          # poetry run agbenchmark --mock
+
+          # CHANGED=$(git diff --name-only | grep -E '(agbenchmark/challenges)|(../classic/frontend/assets)') || echo "No diffs"
+          # if [ ! -z "$CHANGED" ]; then
+          #   echo "There are unstaged changes please run agbenchmark and commit those changes since they are needed."
+          #   echo "$CHANGED"
+          #   exit 1
+          # else
+          #   echo "No unstaged changes."
+          # fi
         env:
-          CI: true
-          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          NONINTERACTIVE_MODE: "true"
+          TELEMETRY_ENVIRONMENT: autogpt-benchmark-ci
+          TELEMETRY_OPT_IN: ${{ github.ref_name == 'master' }}

.github/workflows/classic-forge-ci.yml

@@ -6,15 +6,13 @@ on:
     paths:
       - '.github/workflows/classic-forge-ci.yml'
       - 'classic/forge/**'
-      - 'classic/pyproject.toml'
-      - 'classic/poetry.lock'
+      - '!classic/forge/tests/vcr_cassettes'
   pull_request:
     branches: [ master, dev, release-* ]
     paths:
       - '.github/workflows/classic-forge-ci.yml'
       - 'classic/forge/**'
-      - 'classic/pyproject.toml'
-      - 'classic/poetry.lock'
+      - '!classic/forge/tests/vcr_cassettes'
 
 concurrency:
   group: ${{ format('forge-ci-{0}', github.head_ref && format('{0}-{1}', github.event_name, github.event.pull_request.number) || github.sha) }}
@@ -23,60 +21,131 @@ concurrency:
 defaults:
   run:
     shell: bash
-    working-directory: classic
+    working-directory: classic/forge
 
 jobs:
   test:
     permissions:
       contents: read
     timeout-minutes: 30
-    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10"]
+        platform-os: [ubuntu, macos, macos-arm64, windows]
+    runs-on: ${{ matrix.platform-os != 'macos-arm64' && format('{0}-latest', matrix.platform-os) || 'macos-14' }}
 
     steps:
-      - name: Start MinIO service
+      # Quite slow on macOS (2~4 minutes to set up Docker)
+      # - name: Set up Docker (macOS)
+      #   if: runner.os == 'macOS'
+      #   uses: crazy-max/ghaction-setup-docker@v3
+
+      - name: Start MinIO service (Linux)
+        if: runner.os == 'Linux'
         working-directory: '.'
         run: |
           docker pull minio/minio:edge-cicd
           docker run -d -p 9000:9000 minio/minio:edge-cicd
 
+      - name: Start MinIO service (macOS)
+        if: runner.os == 'macOS'
+        working-directory: ${{ runner.temp }}
+        run: |
+          brew install minio/stable/minio
+          mkdir data
+          minio server ./data &
+
+      # No MinIO on Windows:
+      # - Windows doesn't support running Linux Docker containers
+      # - It doesn't seem possible to start background processes on Windows. They are
+      #   killed after the step returns.
+      #   See: https://github.com/actions/runner/issues/598#issuecomment-2011890429
+
       - name: Checkout repository
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          submodules: true
 
-      - name: Set up Python 3.12
+      - name: Checkout cassettes
+        if: ${{ startsWith(github.event_name, 'pull_request') }}
+        env:
+          PR_BASE: ${{ github.event.pull_request.base.ref }}
+          PR_BRANCH: ${{ github.event.pull_request.head.ref }}
+          PR_AUTHOR: ${{ github.event.pull_request.user.login }}
+        run: |
+          cassette_branch="${PR_AUTHOR}-${PR_BRANCH}"
+          cassette_base_branch="${PR_BASE}"
+          cd tests/vcr_cassettes
+
+          if ! git ls-remote --exit-code --heads origin $cassette_base_branch ; then
+            cassette_base_branch="master"
+          fi
+
+          if git ls-remote --exit-code --heads origin $cassette_branch ; then
+            git fetch origin $cassette_branch
+            git fetch origin $cassette_base_branch
+
+            git checkout $cassette_branch
+
+            # Pick non-conflicting cassette updates from the base branch
+            git merge --no-commit --strategy-option=ours origin/$cassette_base_branch
+            echo "Using cassettes from mirror branch '$cassette_branch'," \
+              "synced to upstream branch '$cassette_base_branch'."
+          else
+            git checkout -b $cassette_branch
+            echo "Branch '$cassette_branch' does not exist in cassette submodule." \
+              "Using cassettes from '$cassette_base_branch'."
+          fi
+
+      - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:
-          python-version: "3.12"
+          python-version: ${{ matrix.python-version }}
 
       - name: Set up Python dependency cache
+        # On Windows, unpacking cached dependencies takes longer than just installing them
+        if: runner.os != 'Windows'
         uses: actions/cache@v4
         with:
-          path: ~/.cache/pypoetry
-          key: poetry-${{ runner.os }}-${{ hashFiles('classic/poetry.lock') }}
+          path: ${{ runner.os == 'macOS' && '~/Library/Caches/pypoetry' || '~/.cache/pypoetry' }}
+          key: poetry-${{ runner.os }}-${{ hashFiles('classic/forge/poetry.lock') }}
 
-      - name: Install Poetry
-        run: curl -sSL https://install.python-poetry.org | python3 -
+      - name: Install Poetry (Unix)
+        if: runner.os != 'Windows'
+        run: |
+          curl -sSL https://install.python-poetry.org | python3 -
+
+          if [ "${{ runner.os }}" = "macOS" ]; then
+            PATH="$HOME/.local/bin:$PATH"
+            echo "$HOME/.local/bin" >> $GITHUB_PATH
+          fi
+
+      - name: Install Poetry (Windows)
+        if: runner.os == 'Windows'
+        shell: pwsh
+        run: |
+          (Invoke-WebRequest -Uri https://install.python-poetry.org -UseBasicParsing).Content | python -
+
+          $env:PATH += ";$env:APPDATA\Python\Scripts"
+          echo "$env:APPDATA\Python\Scripts" >> $env:GITHUB_PATH
 
       - name: Install Python dependencies
         run: poetry install
 
-      - name: Install Playwright browsers
-        run: poetry run playwright install chromium
-
       - name: Run pytest with coverage
         run: |
           poetry run pytest -vv \
             --cov=forge --cov-branch --cov-report term-missing --cov-report xml \
             --durations=10 \
             --junitxml=junit.xml -o junit_family=legacy \
-            forge/forge forge/tests
+            forge
         env:
           CI: true
           PLAIN_OUTPUT: True
-          # API keys - tests that need these will skip if not available
-          # Secrets are not available to fork PRs (GitHub security feature)
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
-          S3_ENDPOINT_URL: http://127.0.0.1:9000
+          S3_ENDPOINT_URL: ${{ runner.os != 'Windows' && 'http://127.0.0.1:9000' || '' }}
           AWS_ACCESS_KEY_ID: minioadmin
           AWS_SECRET_ACCESS_KEY: minioadmin
 
@@ -90,11 +159,85 @@ jobs:
         uses: codecov/codecov-action@v5
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
-          flags: forge
+          flags: forge,${{ runner.os }}
+
+      - id: setup_git_auth
+        name: Set up git token authentication
+        # Cassettes may be pushed even when tests fail
+        if: success() || failure()
+        run: |
+          config_key="http.${{ github.server_url }}/.extraheader"
+          if [ "${{ runner.os }}" = 'macOS' ]; then
+            base64_pat=$(echo -n "pat:${{ secrets.PAT_REVIEW }}" | base64)
+          else
+            base64_pat=$(echo -n "pat:${{ secrets.PAT_REVIEW }}" | base64 -w0)
+          fi
+
+          git config "$config_key" \
+            "Authorization: Basic $base64_pat"
+
+          cd tests/vcr_cassettes
+          git config "$config_key" \
+            "Authorization: Basic $base64_pat"
+
+          echo "config_key=$config_key" >> $GITHUB_OUTPUT
+
+      - id: push_cassettes
+        name: Push updated cassettes
+        # For pull requests, push updated cassettes even when tests fail
+        if: github.event_name == 'push' || (! github.event.pull_request.head.repo.fork && (success() || failure()))
+        env:
+          PR_BRANCH: ${{ github.event.pull_request.head.ref }}
+          PR_AUTHOR: ${{ github.event.pull_request.user.login }}
+        run: |
+          if [ "${{ startsWith(github.event_name, 'pull_request') }}" = "true" ]; then
+            is_pull_request=true
+            cassette_branch="${PR_AUTHOR}-${PR_BRANCH}"
+          else
+            cassette_branch="${{ github.ref_name }}"
+          fi
+
+          cd tests/vcr_cassettes
+          # Commit & push changes to cassettes if any
+          if ! git diff --quiet; then
+            git add .
+            git commit -m "Auto-update cassettes"
+            git push origin HEAD:$cassette_branch
+            if [ ! $is_pull_request ]; then
+              cd ../..
+              git add tests/vcr_cassettes
+              git commit -m "Update cassette submodule"
+              git push origin HEAD:$cassette_branch
+            fi
+            echo "updated=true" >> $GITHUB_OUTPUT
+          else
+            echo "updated=false" >> $GITHUB_OUTPUT
+            echo "No cassette changes to commit"
+          fi
+
+      - name: Post Set up git token auth
+        if: steps.setup_git_auth.outcome == 'success'
+        run: |
+          git config --unset-all '${{ steps.setup_git_auth.outputs.config_key }}'
+          git submodule foreach git config --unset-all '${{ steps.setup_git_auth.outputs.config_key }}'
+
+      - name: Apply "behaviour change" label and comment on PR
+        if: ${{ startsWith(github.event_name, 'pull_request') }}
+        run: |
+          PR_NUMBER="${{ github.event.pull_request.number }}"
+          TOKEN="${{ secrets.PAT_REVIEW }}"
+          REPO="${{ github.repository }}"
+
+          if [[ "${{ steps.push_cassettes.outputs.updated }}" == "true" ]]; then
+            echo "Adding label and comment..."
+            echo $TOKEN | gh auth login --with-token
+            gh issue edit $PR_NUMBER --add-label "behaviour change"
+            gh issue comment $PR_NUMBER --body "You changed AutoGPT's behaviour on ${{ runner.os }}. The cassettes have been updated and will be merged to the submodule when this Pull Request gets merged."
+          fi
 
       - name: Upload logs to artifact
         if: always()
         uses: actions/upload-artifact@v4
         with:
           name: test-logs
-          path: classic/logs/
+          path: classic/forge/logs/

.github/workflows/classic-frontend-ci.yml

@@ -0,0 +1,60 @@
+name: Classic - Frontend CI/CD
+
+on:
+  push:
+    branches:
+      - master
+      - dev
+      - 'ci-test*' # This will match any branch that starts with "ci-test"
+    paths:
+      - 'classic/frontend/**'
+      - '.github/workflows/classic-frontend-ci.yml'
+  pull_request:
+    paths:
+      - 'classic/frontend/**'
+      - '.github/workflows/classic-frontend-ci.yml'
+
+jobs:
+  build:
+    permissions:
+      contents: write
+      pull-requests: write
+    runs-on: ubuntu-latest
+    env:
+      BUILD_BRANCH: ${{ format('classic-frontend-build/{0}', github.ref_name) }}
+
+    steps:
+      - name: Checkout Repo
+        uses: actions/checkout@v4
+
+      - name: Setup Flutter
+        uses: subosito/flutter-action@v2
+        with:
+          flutter-version: '3.13.2'
+
+      - name: Build Flutter to Web
+        run: |
+          cd classic/frontend
+          flutter build web --base-href /app/
+
+      # - name: Commit and Push to ${{ env.BUILD_BRANCH }}
+      #   if: github.event_name == 'push'
+      #   run: |
+      #     git config --local user.email "action@github.com"
+      #     git config --local user.name "GitHub Action"
+      #     git add classic/frontend/build/web
+      #     git checkout -B ${{ env.BUILD_BRANCH }}
+      #     git commit -m "Update frontend build to ${GITHUB_SHA:0:7}" -a
+      #     git push -f origin ${{ env.BUILD_BRANCH }}
+
+      - name: Create PR ${{ env.BUILD_BRANCH }} -> ${{ github.ref_name }}
+        if: github.event_name == 'push'
+        uses: peter-evans/create-pull-request@v8
+        with:
+          add-paths: classic/frontend/build/web
+          base: ${{ github.ref_name }}
+          branch: ${{ env.BUILD_BRANCH }}
+          delete-branch: true
+          title: "Update frontend build in `${{ github.ref_name }}`"
+          body: "This PR updates the frontend build based on commit ${{ github.sha }}."
+          commit-message: "Update frontend build based on commit ${{ github.sha }}"

.github/workflows/classic-python-checks.yml

@@ -7,9 +7,7 @@ on:
       - '.github/workflows/classic-python-checks-ci.yml'
       - 'classic/original_autogpt/**'
       - 'classic/forge/**'
-      - 'classic/direct_benchmark/**'
-      - 'classic/pyproject.toml'
-      - 'classic/poetry.lock'
+      - 'classic/benchmark/**'
       - '**.py'
       - '!classic/forge/tests/vcr_cassettes'
   pull_request:
@@ -18,9 +16,7 @@ on:
       - '.github/workflows/classic-python-checks-ci.yml'
       - 'classic/original_autogpt/**'
       - 'classic/forge/**'
-      - 'classic/direct_benchmark/**'
-      - 'classic/pyproject.toml'
-      - 'classic/poetry.lock'
+      - 'classic/benchmark/**'
       - '**.py'
       - '!classic/forge/tests/vcr_cassettes'
 
@@ -31,13 +27,44 @@ concurrency:
 defaults:
   run:
     shell: bash
-    working-directory: classic
 
 jobs:
+  get-changed-parts:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - id: changes-in
+        name: Determine affected subprojects
+        uses: dorny/paths-filter@v3
+        with:
+          filters: |
+            original_autogpt:
+              - classic/original_autogpt/autogpt/**
+              - classic/original_autogpt/tests/**
+              - classic/original_autogpt/poetry.lock
+            forge:
+              - classic/forge/forge/**
+              - classic/forge/tests/**
+              - classic/forge/poetry.lock
+            benchmark:
+              - classic/benchmark/agbenchmark/**
+              - classic/benchmark/tests/**
+              - classic/benchmark/poetry.lock
+    outputs:
+      changed-parts: ${{ steps.changes-in.outputs.changes }}
+
   lint:
+    needs: get-changed-parts
     runs-on: ubuntu-latest
     env:
-      min-python-version: "3.12"
+      min-python-version: "3.10"
+
+    strategy:
+      matrix:
+        sub-package: ${{ fromJson(needs.get-changed-parts.outputs.changed-parts) }}
+      fail-fast: false
 
     steps:
       - name: Checkout repository
@@ -54,31 +81,42 @@ jobs:
         uses: actions/cache@v4
         with:
           path: ~/.cache/pypoetry
-          key: ${{ runner.os }}-poetry-${{ hashFiles('classic/poetry.lock') }}
+          key: ${{ runner.os }}-poetry-${{ hashFiles(format('{0}/poetry.lock', matrix.sub-package)) }}
 
       - name: Install Poetry
         run: curl -sSL https://install.python-poetry.org | python3 -
 
+      # Install dependencies
+
       - name: Install Python dependencies
-        run: poetry install
+        run: poetry -C classic/${{ matrix.sub-package }} install
 
       # Lint
 
       - name: Lint (isort)
         run: poetry run isort --check .
+        working-directory: classic/${{ matrix.sub-package }}
 
       - name: Lint (Black)
         if: success() || failure()
         run: poetry run black --check .
+        working-directory: classic/${{ matrix.sub-package }}
 
       - name: Lint (Flake8)
         if: success() || failure()
         run: poetry run flake8 .
+        working-directory: classic/${{ matrix.sub-package }}
 
   types:
+    needs: get-changed-parts
     runs-on: ubuntu-latest
     env:
-      min-python-version: "3.12"
+      min-python-version: "3.10"
+
+    strategy:
+      matrix:
+        sub-package: ${{ fromJson(needs.get-changed-parts.outputs.changed-parts) }}
+      fail-fast: false
 
     steps:
       - name: Checkout repository
@@ -95,16 +133,19 @@ jobs:
         uses: actions/cache@v4
         with:
           path: ~/.cache/pypoetry
-          key: ${{ runner.os }}-poetry-${{ hashFiles('classic/poetry.lock') }}
+          key: ${{ runner.os }}-poetry-${{ hashFiles(format('{0}/poetry.lock', matrix.sub-package)) }}
 
       - name: Install Poetry
         run: curl -sSL https://install.python-poetry.org | python3 -
 
+      # Install dependencies
+
       - name: Install Python dependencies
-        run: poetry install
+        run: poetry -C classic/${{ matrix.sub-package }} install
 
       # Typecheck
 
       - name: Typecheck
         if: success() || failure()
         run: poetry run pyright
+        working-directory: classic/${{ matrix.sub-package }}

.github/workflows/platform-backend-ci.yml

@@ -5,14 +5,12 @@ on:
     branches: [master, dev, ci-test*]
     paths:
       - ".github/workflows/platform-backend-ci.yml"
-      - ".github/workflows/scripts/get_package_version_from_lockfile.py"
       - "autogpt_platform/backend/**"
       - "autogpt_platform/autogpt_libs/**"
   pull_request:
     branches: [master, dev, release-*]
     paths:
       - ".github/workflows/platform-backend-ci.yml"
-      - ".github/workflows/scripts/get_package_version_from_lockfile.py"
       - "autogpt_platform/backend/**"
       - "autogpt_platform/autogpt_libs/**"
   merge_group:
@@ -27,91 +25,10 @@ defaults:
     working-directory: autogpt_platform/backend
 
 jobs:
-  lint:
-    permissions:
-      contents: read
-    timeout-minutes: 10
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v6
-
-      - name: Set up Python 3.12
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.12"
-
-      - name: Set up Python dependency cache
-        uses: actions/cache@v5
-        with:
-          path: ~/.cache/pypoetry
-          key: poetry-${{ runner.os }}-py3.12-${{ hashFiles('autogpt_platform/backend/poetry.lock') }}
-
-      - name: Install Poetry
-        run: |
-          HEAD_POETRY_VERSION=$(python ../../.github/workflows/scripts/get_package_version_from_lockfile.py poetry)
-          echo "Using Poetry version ${HEAD_POETRY_VERSION}"
-          curl -sSL https://install.python-poetry.org | POETRY_VERSION=$HEAD_POETRY_VERSION python3 -
-
-      - name: Install Python dependencies
-        run: poetry install
-
-      - name: Run Linters
-        run: poetry run lint --skip-pyright
-
-    env:
-      CI: true
-      PLAIN_OUTPUT: True
-
-  type-check:
-    permissions:
-      contents: read
-    timeout-minutes: 10
-    strategy:
-      fail-fast: false
-      matrix:
-        python-version: ["3.11", "3.12", "3.13"]
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v6
-
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ matrix.python-version }}
-
-      - name: Set up Python dependency cache
-        uses: actions/cache@v5
-        with:
-          path: ~/.cache/pypoetry
-          key: poetry-${{ runner.os }}-py${{ matrix.python-version }}-${{ hashFiles('autogpt_platform/backend/poetry.lock') }}
-
-      - name: Install Poetry
-        run: |
-          HEAD_POETRY_VERSION=$(python ../../.github/workflows/scripts/get_package_version_from_lockfile.py poetry)
-          echo "Using Poetry version ${HEAD_POETRY_VERSION}"
-          curl -sSL https://install.python-poetry.org | POETRY_VERSION=$HEAD_POETRY_VERSION python3 -
-
-      - name: Install Python dependencies
-        run: poetry install
-
-      - name: Generate Prisma Client
-        run: poetry run prisma generate && poetry run gen-prisma-stub
-
-      - name: Run Pyright
-        run: poetry run pyright --pythonversion ${{ matrix.python-version }}
-
-    env:
-      CI: true
-      PLAIN_OUTPUT: True
-
   test:
     permissions:
       contents: read
-    timeout-minutes: 15
+    timeout-minutes: 30
     strategy:
       fail-fast: false
       matrix:
@@ -179,9 +96,9 @@ jobs:
         uses: actions/cache@v5
         with:
           path: ~/.cache/pypoetry
-          key: poetry-${{ runner.os }}-py${{ matrix.python-version }}-${{ hashFiles('autogpt_platform/backend/poetry.lock') }}
+          key: poetry-${{ runner.os }}-${{ hashFiles('autogpt_platform/backend/poetry.lock') }}
 
-      - name: Install Poetry
+      - name: Install Poetry (Unix)
         run: |
           # Extract Poetry version from backend/poetry.lock
           HEAD_POETRY_VERSION=$(python ../../.github/workflows/scripts/get_package_version_from_lockfile.py poetry)
@@ -239,22 +156,22 @@ jobs:
           echo "Waiting for ClamAV daemon to start..."
           max_attempts=60
           attempt=0
-
+          
           until nc -z localhost 3310 || [ $attempt -eq $max_attempts ]; do
             echo "ClamAV is unavailable - sleeping (attempt $((attempt+1))/$max_attempts)"
             sleep 5
             attempt=$((attempt+1))
           done
-
+          
           if [ $attempt -eq $max_attempts ]; then
             echo "ClamAV failed to start after $((max_attempts*5)) seconds"
             echo "Checking ClamAV service logs..."
             docker logs $(docker ps -q --filter "ancestor=clamav/clamav-debian:latest") 2>&1 | tail -50 || echo "No ClamAV container found"
             exit 1
           fi
-
+          
           echo "ClamAV is ready!"
-
+          
           # Verify ClamAV is responsive
           echo "Testing ClamAV connection..."
           timeout 10 bash -c 'echo "PING" | nc localhost 3310' || {
@@ -269,15 +186,18 @@ jobs:
           DATABASE_URL: ${{ steps.supabase.outputs.DB_URL }}
           DIRECT_URL: ${{ steps.supabase.outputs.DB_URL }}
 
+      - id: lint
+        name: Run Linter
+        run: poetry run lint
+
       - name: Run pytest with coverage
         run: |
           if [[ "${{ runner.debug }}" == "1" ]]; then
-            poetry run pytest -s -vv -o log_cli=true -o log_cli_level=DEBUG \
-              --cov=backend --cov-branch --cov-report term-missing --cov-report xml
+            poetry run pytest -s -vv -o log_cli=true -o log_cli_level=DEBUG
           else
-            poetry run pytest -s -vv \
-              --cov=backend --cov-branch --cov-report term-missing --cov-report xml
+            poetry run pytest -s -vv
           fi
+        if: success() || (failure() && steps.lint.outcome == 'failure')
         env:
           LOG_LEVEL: ${{ runner.debug && 'DEBUG' || 'INFO' }}
           DATABASE_URL: ${{ steps.supabase.outputs.DB_URL }}
@@ -289,14 +209,6 @@ jobs:
           REDIS_PORT: "6379"
           ENCRYPTION_KEY: "dvziYgz0KSK8FENhju0ZYi8-fRTfAdlz6YLhdB_jhNw=" # DO NOT USE IN PRODUCTION!!
 
-      - name: Upload coverage reports to Codecov
-        if: ${{ !cancelled() }}
-        uses: codecov/codecov-action@v5
-        with:
-          token: ${{ secrets.CODECOV_TOKEN }}
-          flags: platform-backend
-          files: ./autogpt_platform/backend/coverage.xml
-
     env:
       CI: true
       PLAIN_OUTPUT: True
@@ -310,3 +222,9 @@ jobs:
       # the backend service, docker composes, and examples
       RABBITMQ_DEFAULT_USER: "rabbitmq_user_default"
       RABBITMQ_DEFAULT_PASS: "k0VMxyIJF9S35f3x2uaw5IWAl6Y536O7"
+
+      # - name: Upload coverage reports to Codecov
+      #   uses: codecov/codecov-action@v4
+      #   with:
+      #     token: ${{ secrets.CODECOV_TOKEN }}
+      #     flags: backend,${{ runner.os }}

.github/workflows/platform-frontend-ci.yml

@@ -120,6 +120,175 @@ jobs:
           token: ${{ secrets.GITHUB_TOKEN }}
           exitOnceUploaded: true
 
+  e2e_test:
+    name: end-to-end tests
+    runs-on: big-boi
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v6
+        with:
+          submodules: recursive
+
+      - name: Set up Platform - Copy default supabase .env
+        run: |
+          cp ../.env.default ../.env
+
+      - name: Set up Platform - Copy backend .env and set OpenAI API key
+        run: |
+          cp ../backend/.env.default ../backend/.env
+          echo "OPENAI_INTERNAL_API_KEY=${{ secrets.OPENAI_API_KEY }}" >> ../backend/.env
+        env:
+          # Used by E2E test data script to generate embeddings for approved store agents
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+
+      - name: Set up Platform - Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+        with:
+          driver: docker-container
+          driver-opts: network=host
+
+      - name: Set up Platform - Expose GHA cache to docker buildx CLI
+        uses: crazy-max/ghaction-github-runtime@v4
+
+      - name: Set up Platform - Build Docker images (with cache)
+        working-directory: autogpt_platform
+        run: |
+          pip install pyyaml
+
+          # Resolve extends and generate a flat compose file that bake can understand
+          docker compose -f docker-compose.yml config > docker-compose.resolved.yml
+
+          # Add cache configuration to the resolved compose file
+          python ../.github/workflows/scripts/docker-ci-fix-compose-build-cache.py \
+            --source docker-compose.resolved.yml \
+            --cache-from "type=gha" \
+            --cache-to "type=gha,mode=max" \
+            --backend-hash "${{ hashFiles('autogpt_platform/backend/Dockerfile', 'autogpt_platform/backend/poetry.lock', 'autogpt_platform/backend/backend') }}" \
+            --frontend-hash "${{ hashFiles('autogpt_platform/frontend/Dockerfile', 'autogpt_platform/frontend/pnpm-lock.yaml', 'autogpt_platform/frontend/src') }}" \
+            --git-ref "${{ github.ref }}"
+
+          # Build with bake using the resolved compose file (now includes cache config)
+          docker buildx bake --allow=fs.read=.. -f docker-compose.resolved.yml --load
+        env:
+          NEXT_PUBLIC_PW_TEST: true
+
+      - name: Set up tests - Cache E2E test data
+        id: e2e-data-cache
+        uses: actions/cache@v5
+        with:
+          path: /tmp/e2e_test_data.sql
+          key: e2e-test-data-${{ hashFiles('autogpt_platform/backend/test/e2e_test_data.py', 'autogpt_platform/backend/migrations/**', '.github/workflows/platform-frontend-ci.yml') }}
+
+      - name: Set up Platform - Start Supabase DB + Auth
+        run: |
+          docker compose -f ../docker-compose.resolved.yml up -d db auth --no-build
+          echo "Waiting for database to be ready..."
+          timeout 60 sh -c 'until docker compose -f ../docker-compose.resolved.yml exec -T db pg_isready -U postgres 2>/dev/null; do sleep 2; done'
+          echo "Waiting for auth service to be ready..."
+          timeout 60 sh -c 'until docker compose -f ../docker-compose.resolved.yml exec -T db psql -U postgres -d postgres -c "SELECT 1 FROM auth.users LIMIT 1" 2>/dev/null; do sleep 2; done' || echo "Auth schema check timeout, continuing..."
+
+      - name: Set up Platform - Run migrations
+        run: |
+          echo "Running migrations..."
+          docker compose -f ../docker-compose.resolved.yml run --rm migrate
+          echo "✅ Migrations completed"
+        env:
+          NEXT_PUBLIC_PW_TEST: true
+
+      - name: Set up tests - Load cached E2E test data
+        if: steps.e2e-data-cache.outputs.cache-hit == 'true'
+        run: |
+          echo "✅ Found cached E2E test data, restoring..."
+          {
+            echo "SET session_replication_role = 'replica';"
+            cat /tmp/e2e_test_data.sql
+            echo "SET session_replication_role = 'origin';"
+          } | docker compose -f ../docker-compose.resolved.yml exec -T db psql -U postgres -d postgres -b
+          # Refresh materialized views after restore
+          docker compose -f ../docker-compose.resolved.yml exec -T db \
+            psql -U postgres -d postgres -b -c "SET search_path TO platform; SELECT refresh_store_materialized_views();" || true
+
+          echo "✅ E2E test data restored from cache"
+
+      - name: Set up Platform - Start (all other services)
+        run: |
+          docker compose -f ../docker-compose.resolved.yml up -d --no-build
+          echo "Waiting for rest_server to be ready..."
+          timeout 60 sh -c 'until curl -f http://localhost:8006/health 2>/dev/null; do sleep 2; done' || echo "Rest server health check timeout, continuing..."
+        env:
+          NEXT_PUBLIC_PW_TEST: true
+
+      - name: Set up tests - Create E2E test data
+        if: steps.e2e-data-cache.outputs.cache-hit != 'true'
+        run: |
+          echo "Creating E2E test data..."
+          docker cp ../backend/test/e2e_test_data.py $(docker compose -f ../docker-compose.resolved.yml ps -q rest_server):/tmp/e2e_test_data.py
+          docker compose -f ../docker-compose.resolved.yml exec -T rest_server sh -c "cd /app/autogpt_platform && python /tmp/e2e_test_data.py" || {
+            echo "❌ E2E test data creation failed!"
+            docker compose -f ../docker-compose.resolved.yml logs --tail=50 rest_server
+            exit 1
+          }
+
+          # Dump auth.users + platform schema for cache (two separate dumps)
+          echo "Dumping database for cache..."
+          {
+            docker compose -f ../docker-compose.resolved.yml exec -T db \
+              pg_dump -U postgres --data-only --column-inserts \
+              --table='auth.users' postgres
+            docker compose -f ../docker-compose.resolved.yml exec -T db \
+              pg_dump -U postgres --data-only --column-inserts \
+              --schema=platform \
+              --exclude-table='platform._prisma_migrations' \
+              --exclude-table='platform.apscheduler_jobs' \
+              --exclude-table='platform.apscheduler_jobs_batched_notifications' \
+              postgres
+          } > /tmp/e2e_test_data.sql
+
+          echo "✅ Database dump created for caching ($(wc -l < /tmp/e2e_test_data.sql) lines)"
+
+      - name: Set up tests - Enable corepack
+        run: corepack enable
+
+      - name: Set up tests - Set up Node
+        uses: actions/setup-node@v6
+        with:
+          node-version: "22.18.0"
+          cache: "pnpm"
+          cache-dependency-path: autogpt_platform/frontend/pnpm-lock.yaml
+
+      - name: Set up tests - Install dependencies
+        run: pnpm install --frozen-lockfile
+
+      - name: Set up tests - Install browser 'chromium'
+        run: pnpm playwright install --with-deps chromium
+
+      - name: Run Playwright tests
+        run: pnpm test:no-build
+        continue-on-error: false
+
+      - name: Upload Playwright report
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: playwright-report
+          path: playwright-report
+          if-no-files-found: ignore
+          retention-days: 3
+
+      - name: Upload Playwright test results
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: playwright-test-results
+          path: test-results
+          if-no-files-found: ignore
+          retention-days: 3
+
+      - name: Print Final Docker Compose logs
+        if: always()
+        run: docker compose -f ../docker-compose.resolved.yml logs
+
   integration_test:
     runs-on: ubuntu-latest
     needs: setup
@@ -148,11 +317,3 @@ jobs:
 
       - name: Run Integration Tests
         run: pnpm test:unit
-
-      - name: Upload coverage reports to Codecov
-        if: ${{ !cancelled() }}
-        uses: codecov/codecov-action@v5
-        with:
-          token: ${{ secrets.CODECOV_TOKEN }}
-          flags: platform-frontend
-          files: ./autogpt_platform/frontend/coverage/cobertura-coverage.xml

.github/workflows/platform-fullstack-ci.yml

@@ -1,18 +1,14 @@
-name: AutoGPT Platform - Full-stack CI
+name: AutoGPT Platform - Frontend CI
 
 on:
   push:
     branches: [master, dev]
     paths:
       - ".github/workflows/platform-fullstack-ci.yml"
-      - ".github/workflows/scripts/docker-ci-fix-compose-build-cache.py"
-      - ".github/workflows/scripts/get_package_version_from_lockfile.py"
       - "autogpt_platform/**"
   pull_request:
     paths:
       - ".github/workflows/platform-fullstack-ci.yml"
-      - ".github/workflows/scripts/docker-ci-fix-compose-build-cache.py"
-      - ".github/workflows/scripts/get_package_version_from_lockfile.py"
       - "autogpt_platform/**"
   merge_group:
 
@@ -28,28 +24,42 @@ defaults:
 jobs:
   setup:
     runs-on: ubuntu-latest
+    outputs:
+      cache-key: ${{ steps.cache-key.outputs.key }}
 
     steps:
       - name: Checkout repository
         uses: actions/checkout@v6
 
-      - name: Enable corepack
-        run: corepack enable
-
-      - name: Set up Node
+      - name: Set up Node.js
         uses: actions/setup-node@v6
         with:
           node-version: "22.18.0"
-          cache: "pnpm"
-          cache-dependency-path: autogpt_platform/frontend/pnpm-lock.yaml
 
-      - name: Install dependencies to populate cache
+      - name: Enable corepack
+        run: corepack enable
+
+      - name: Generate cache key
+        id: cache-key
+        run: echo "key=${{ runner.os }}-pnpm-${{ hashFiles('autogpt_platform/frontend/pnpm-lock.yaml', 'autogpt_platform/frontend/package.json') }}" >> $GITHUB_OUTPUT
+
+      - name: Cache dependencies
+        uses: actions/cache@v5
+        with:
+          path: ~/.pnpm-store
+          key: ${{ steps.cache-key.outputs.key }}
+          restore-keys: |
+            ${{ runner.os }}-pnpm-${{ hashFiles('autogpt_platform/frontend/pnpm-lock.yaml') }}
+            ${{ runner.os }}-pnpm-
+
+      - name: Install dependencies
         run: pnpm install --frozen-lockfile
 
-  check-api-types:
-    name: check API types
-    runs-on: ubuntu-latest
+  types:
+    runs-on: big-boi
     needs: setup
+    strategy:
+      fail-fast: false
 
     steps:
       - name: Checkout repository
@@ -57,279 +67,70 @@ jobs:
         with:
           submodules: recursive
 
-      # ------------------------ Backend setup ------------------------
-
-      - name: Set up Backend - Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.12"
-
-      - name: Set up Backend - Install Poetry
-        working-directory: autogpt_platform/backend
-        run: |
-          POETRY_VERSION=$(python ../../.github/workflows/scripts/get_package_version_from_lockfile.py poetry)
-          echo "Installing Poetry version ${POETRY_VERSION}"
-          curl -sSL https://install.python-poetry.org | POETRY_VERSION=$POETRY_VERSION python3 -
-
-      - name: Set up Backend - Set up dependency cache
-        uses: actions/cache@v5
-        with:
-          path: ~/.cache/pypoetry
-          key: poetry-${{ runner.os }}-${{ hashFiles('autogpt_platform/backend/poetry.lock') }}
-
-      - name: Set up Backend - Install dependencies
-        working-directory: autogpt_platform/backend
-        run: poetry install
-
-      - name: Set up Backend - Generate Prisma client
-        working-directory: autogpt_platform/backend
-        run: poetry run prisma generate && poetry run gen-prisma-stub
-
-      - name: Set up Frontend - Export OpenAPI schema from Backend
-        working-directory: autogpt_platform/backend
-        run: poetry run export-api-schema --output ../frontend/src/app/api/openapi.json
-
-      # ------------------------ Frontend setup ------------------------
-
-      - name: Set up Frontend - Enable corepack
-        run: corepack enable
-
-      - name: Set up Frontend - Set up Node
+      - name: Set up Node.js
         uses: actions/setup-node@v6
         with:
           node-version: "22.18.0"
-          cache: "pnpm"
-          cache-dependency-path: autogpt_platform/frontend/pnpm-lock.yaml
 
-      - name: Set up Frontend - Install dependencies
+      - name: Enable corepack
+        run: corepack enable
+
+      - name: Copy default supabase .env
+        run: |
+          cp ../.env.default ../.env
+
+      - name: Copy backend .env
+        run: |
+          cp ../backend/.env.default ../backend/.env
+
+      - name: Run docker compose
+        run: |
+          docker compose -f ../docker-compose.yml --profile local up -d deps_backend
+
+      - name: Restore dependencies cache
+        uses: actions/cache@v5
+        with:
+          path: ~/.pnpm-store
+          key: ${{ needs.setup.outputs.cache-key }}
+          restore-keys: |
+            ${{ runner.os }}-pnpm-
+
+      - name: Install dependencies
         run: pnpm install --frozen-lockfile
 
-      - name: Set up Frontend - Format OpenAPI schema
-        id: format-schema
-        run: pnpm prettier --write ./src/app/api/openapi.json
+      - name: Setup .env
+        run: cp .env.default .env
+
+      - name: Wait for services to be ready
+        run: |
+          echo "Waiting for rest_server to be ready..."
+          timeout 60 sh -c 'until curl -f http://localhost:8006/health 2>/dev/null; do sleep 2; done' || echo "Rest server health check timeout, continuing..."
+          echo "Waiting for database to be ready..."
+          timeout 60 sh -c 'until docker compose -f ../docker-compose.yml exec -T db pg_isready -U postgres 2>/dev/null; do sleep 2; done' || echo "Database ready check timeout, continuing..."
+
+      - name: Generate API queries
+        run: pnpm generate:api:force
 
       - name: Check for API schema changes
         run: |
           if ! git diff --exit-code src/app/api/openapi.json; then
             echo "❌ API schema changes detected in src/app/api/openapi.json"
             echo ""
-            echo "The openapi.json file has been modified after exporting the API schema."
+            echo "The openapi.json file has been modified after running 'pnpm generate:api-all'."
             echo "This usually means changes have been made in the BE endpoints without updating the Frontend."
             echo "The API schema is now out of sync with the Front-end queries."
             echo ""
             echo "To fix this:"
-            echo "\nIn the backend directory:"
-            echo "1. Run 'poetry run export-api-schema --output ../frontend/src/app/api/openapi.json'"
-            echo "\nIn the frontend directory:"
-            echo "2. Run 'pnpm prettier --write src/app/api/openapi.json'"
-            echo "3. Run 'pnpm generate:api'"
-            echo "4. Run 'pnpm types'"
-            echo "5. Fix any TypeScript errors that may have been introduced"
-            echo "6. Commit and push your changes"
+            echo "1. Pull the backend 'docker compose pull && docker compose up -d --build --force-recreate'"
+            echo "2. Run 'pnpm generate:api' locally"
+            echo "3. Run 'pnpm types' locally"
+            echo "4. Fix any TypeScript errors that may have been introduced"
+            echo "5. Commit and push your changes"
             echo ""
             exit 1
           else
             echo "✅ No API schema changes detected"
           fi
 
-      - name: Set up Frontend - Generate API client
-        id: generate-api-client
-        run: pnpm orval --config ./orval.config.ts
-        # Continue with type generation & check even if there are schema changes
-        if: success() || (steps.format-schema.outcome == 'success')
-
-      - name: Check for TypeScript errors
+      - name: Run Typescript checks
         run: pnpm types
-        if: success() || (steps.generate-api-client.outcome == 'success')
-
-  e2e_test:
-    name: end-to-end tests
-    runs-on: big-boi
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v6
-        with:
-          submodules: recursive
-
-      - name: Set up Platform - Copy default supabase .env
-        run: |
-          cp ../.env.default ../.env
-
-      - name: Set up Platform - Copy backend .env and set OpenAI API key
-        run: |
-          cp ../backend/.env.default ../backend/.env
-          echo "OPENAI_INTERNAL_API_KEY=${{ secrets.OPENAI_API_KEY }}" >> ../backend/.env
-        env:
-          # Used by E2E test data script to generate embeddings for approved store agents
-          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-
-      - name: Set up Platform - Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-        with:
-          driver: docker-container
-          driver-opts: network=host
-
-      - name: Set up Platform - Expose GHA cache to docker buildx CLI
-        uses: crazy-max/ghaction-github-runtime@v4
-
-      - name: Set up Platform - Build Docker images (with cache)
-        working-directory: autogpt_platform
-        run: |
-          pip install pyyaml
-
-          # Resolve extends and generate a flat compose file that bake can understand
-          export NEXT_PUBLIC_SOURCEMAPS NEXT_PUBLIC_PW_TEST
-          docker compose -f docker-compose.yml config > docker-compose.resolved.yml
-
-          # Ensure NEXT_PUBLIC_SOURCEMAPS is in resolved compose
-          # (docker compose config on some versions drops this arg)
-          if ! grep -q "NEXT_PUBLIC_SOURCEMAPS" docker-compose.resolved.yml; then
-            echo "Injecting NEXT_PUBLIC_SOURCEMAPS into resolved compose (docker compose config dropped it)"
-            sed -i '/NEXT_PUBLIC_PW_TEST/a\        NEXT_PUBLIC_SOURCEMAPS: "true"' docker-compose.resolved.yml
-          fi
-
-          # Add cache configuration to the resolved compose file
-          python ../.github/workflows/scripts/docker-ci-fix-compose-build-cache.py \
-            --source docker-compose.resolved.yml \
-            --cache-from "type=gha" \
-            --cache-to "type=gha,mode=max" \
-            --backend-hash "${{ hashFiles('autogpt_platform/backend/Dockerfile', 'autogpt_platform/backend/poetry.lock', 'autogpt_platform/backend/backend/**') }}" \
-            --frontend-hash "${{ hashFiles('autogpt_platform/frontend/Dockerfile', 'autogpt_platform/frontend/pnpm-lock.yaml', 'autogpt_platform/frontend/src/**') }}-sourcemaps" \
-            --git-ref "${{ github.ref }}"
-
-          # Build with bake using the resolved compose file (now includes cache config)
-          docker buildx bake --allow=fs.read=.. -f docker-compose.resolved.yml --load
-        env:
-          NEXT_PUBLIC_PW_TEST: true
-          NEXT_PUBLIC_SOURCEMAPS: true
-
-      - name: Set up tests - Cache E2E test data
-        id: e2e-data-cache
-        uses: actions/cache@v5
-        with:
-          path: /tmp/e2e_test_data.sql
-          key: e2e-test-data-${{ hashFiles('autogpt_platform/backend/test/e2e_test_data.py', 'autogpt_platform/backend/migrations/**', '.github/workflows/platform-fullstack-ci.yml') }}
-
-      - name: Set up Platform - Start Supabase DB + Auth
-        run: |
-          docker compose -f ../docker-compose.resolved.yml up -d db auth --no-build
-          echo "Waiting for database to be ready..."
-          timeout 60 sh -c 'until docker compose -f ../docker-compose.resolved.yml exec -T db pg_isready -U postgres 2>/dev/null; do sleep 2; done'
-          echo "Waiting for auth service to be ready..."
-          timeout 60 sh -c 'until docker compose -f ../docker-compose.resolved.yml exec -T db psql -U postgres -d postgres -c "SELECT 1 FROM auth.users LIMIT 1" 2>/dev/null; do sleep 2; done' || echo "Auth schema check timeout, continuing..."
-
-      - name: Set up Platform - Run migrations
-        run: |
-          echo "Running migrations..."
-          docker compose -f ../docker-compose.resolved.yml run --rm migrate
-          echo "✅ Migrations completed"
-        env:
-          NEXT_PUBLIC_PW_TEST: true
-
-      - name: Set up tests - Load cached E2E test data
-        if: steps.e2e-data-cache.outputs.cache-hit == 'true'
-        run: |
-          echo "✅ Found cached E2E test data, restoring..."
-          {
-            echo "SET session_replication_role = 'replica';"
-            cat /tmp/e2e_test_data.sql
-            echo "SET session_replication_role = 'origin';"
-          } | docker compose -f ../docker-compose.resolved.yml exec -T db psql -U postgres -d postgres -b
-          # Refresh materialized views after restore
-          docker compose -f ../docker-compose.resolved.yml exec -T db \
-            psql -U postgres -d postgres -b -c "SET search_path TO platform; SELECT refresh_store_materialized_views();" || true
-
-          echo "✅ E2E test data restored from cache"
-
-      - name: Set up Platform - Start (all other services)
-        run: |
-          docker compose -f ../docker-compose.resolved.yml up -d --no-build
-          echo "Waiting for rest_server to be ready..."
-          timeout 60 sh -c 'until curl -f http://localhost:8006/health 2>/dev/null; do sleep 2; done' || echo "Rest server health check timeout, continuing..."
-        env:
-          NEXT_PUBLIC_PW_TEST: true
-
-      - name: Set up tests - Create E2E test data
-        if: steps.e2e-data-cache.outputs.cache-hit != 'true'
-        run: |
-          echo "Creating E2E test data..."
-          docker cp ../backend/test/e2e_test_data.py $(docker compose -f ../docker-compose.resolved.yml ps -q rest_server):/tmp/e2e_test_data.py
-          docker compose -f ../docker-compose.resolved.yml exec -T rest_server sh -c "cd /app/autogpt_platform && python /tmp/e2e_test_data.py" || {
-            echo "❌ E2E test data creation failed!"
-            docker compose -f ../docker-compose.resolved.yml logs --tail=50 rest_server
-            exit 1
-          }
-
-          # Dump auth.users + platform schema for cache (two separate dumps)
-          echo "Dumping database for cache..."
-          {
-            docker compose -f ../docker-compose.resolved.yml exec -T db \
-              pg_dump -U postgres --data-only --column-inserts \
-              --table='auth.users' postgres
-            docker compose -f ../docker-compose.resolved.yml exec -T db \
-              pg_dump -U postgres --data-only --column-inserts \
-              --schema=platform \
-              --exclude-table='platform._prisma_migrations' \
-              --exclude-table='platform.apscheduler_jobs' \
-              --exclude-table='platform.apscheduler_jobs_batched_notifications' \
-              postgres
-          } > /tmp/e2e_test_data.sql
-
-          echo "✅ Database dump created for caching ($(wc -l < /tmp/e2e_test_data.sql) lines)"
-
-      - name: Set up tests - Enable corepack
-        run: corepack enable
-
-      - name: Set up tests - Set up Node
-        uses: actions/setup-node@v6
-        with:
-          node-version: "22.18.0"
-          cache: "pnpm"
-          cache-dependency-path: autogpt_platform/frontend/pnpm-lock.yaml
-
-      - name: Copy source maps from Docker for E2E coverage
-        run: |
-          FRONTEND_CONTAINER=$(docker compose -f ../docker-compose.resolved.yml ps -q frontend)
-          docker cp "$FRONTEND_CONTAINER":/app/.next/static .next-static-coverage
-
-      - name: Set up tests - Install dependencies
-        run: pnpm install --frozen-lockfile
-
-      - name: Set up tests - Install browser 'chromium'
-        run: pnpm playwright install --with-deps chromium
-
-      - name: Run Playwright tests
-        run: pnpm test:no-build
-        continue-on-error: false
-
-      - name: Upload E2E coverage to Codecov
-        if: ${{ !cancelled() }}
-        uses: codecov/codecov-action@v5
-        with:
-          token: ${{ secrets.CODECOV_TOKEN }}
-          flags: platform-frontend-e2e
-          files: ./autogpt_platform/frontend/coverage/e2e/cobertura-coverage.xml
-          disable_search: true
-
-      - name: Upload Playwright report
-        if: always()
-        uses: actions/upload-artifact@v4
-        with:
-          name: playwright-report
-          path: autogpt_platform/frontend/playwright-report
-          if-no-files-found: ignore
-          retention-days: 3
-
-      - name: Upload Playwright test results
-        if: always()
-        uses: actions/upload-artifact@v4
-        with:
-          name: playwright-test-results
-          path: autogpt_platform/frontend/test-results
-          if-no-files-found: ignore
-          retention-days: 3
-
-      - name: Print Final Docker Compose logs
-        if: always()
-        run: docker compose -f ../docker-compose.resolved.yml logs

.gitignore

@@ -3,7 +3,6 @@
 classic/original_autogpt/keys.py
 classic/original_autogpt/*.json
 auto_gpt_workspace/*
-.autogpt/
 *.mpeg
 .env
 # Root .env files
@@ -17,7 +16,6 @@ log-ingestion.txt
 /logs
 *.log
 *.mp3
-!autogpt_platform/frontend/public/notification.mp3
 mem.sqlite3
 venvAutoGPT
 
@@ -161,10 +159,6 @@ CURRENT_BULLETIN.md
 
 # AgBenchmark
 classic/benchmark/agbenchmark/reports/
-classic/reports/
-classic/direct_benchmark/reports/
-classic/.benchmark_workspaces/
-classic/direct_benchmark/.benchmark_workspaces/
 
 # Nodejs
 package-lock.json
@@ -183,13 +177,9 @@ autogpt_platform/backend/settings.py
 
 *.ign.*
 .test-contents
-**/.claude/settings.local.json
 .claude/settings.local.json
 CLAUDE.local.md
 /autogpt_platform/backend/logs
-
-# Test database
-test.db
 .next
 # Implementation plans (generated by AI agents)
 plans/

.gitleaks.toml

@@ -1,36 +0,0 @@
-title = "AutoGPT Gitleaks Config"
-
-[extend]
-useDefault = true
-
-[allowlist]
-description = "Global allowlist"
-paths = [
-    # Template/example env files (no real secrets)
-    '''\.env\.(default|example|template)$''',
-    # Lock files
-    '''pnpm-lock\.yaml$''',
-    '''poetry\.lock$''',
-    # Secrets baseline
-    '''\.secrets\.baseline$''',
-    # Build artifacts and caches (should not be committed)
-    '''__pycache__/''',
-    '''classic/frontend/build/''',
-    # Docker dev setup (local dev JWTs/keys only)
-    '''autogpt_platform/db/docker/''',
-    # Load test configs (dev JWTs)
-    '''load-tests/configs/''',
-    # Test files with fake/fixture keys (_test.py, test_*.py, conftest.py)
-    '''(_test|test_.*|conftest)\.py$''',
-    # Documentation (only contains placeholder keys in curl/API examples)
-    '''docs/.*\.md$''',
-    # Firebase config (public API keys by design)
-    '''google-services\.json$''',
-    '''classic/frontend/(lib|web)/''',
-]
-# CI test-only encryption key (marked DO NOT USE IN PRODUCTION)
-regexes = [
-    '''dvziYgz0KSK8FENhju0ZYi8''',
-    # LLM model name enum values falsely flagged as API keys
-    '''Llama-\d.*Instruct''',
-]

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "classic/forge/tests/vcr_cassettes"]
+	path = classic/forge/tests/vcr_cassettes
+	url = https://github.com/Significant-Gravitas/Auto-GPT-test-cassettes

.pre-commit-config.yaml

@@ -23,15 +23,9 @@ repos:
       - id: detect-secrets
         name: Detect secrets
         description: Detects high entropy strings that are likely to be passwords.
-        args: ["--baseline", ".secrets.baseline"]
         files: ^autogpt_platform/
-        exclude: (pnpm-lock\.yaml|\.env\.(default|example|template))$
-
-  - repo: https://github.com/gitleaks/gitleaks
-    rev: v8.24.3
-    hooks:
-      - id: gitleaks
-        name: Detect secrets (gitleaks)
+        exclude: pnpm-lock\.yaml$
+        stages: [pre-push]
 
   - repo: local
     # For proper type checking, all dependencies need to be up-to-date.
@@ -90,16 +84,51 @@ repos:
         stages: [pre-commit, post-checkout]
 
       - id: poetry-install
-        name: Check & Install dependencies - Classic
-        alias: poetry-install-classic
+        name: Check & Install dependencies - Classic - AutoGPT
+        alias: poetry-install-classic-autogpt
         entry: >
           bash -c '
           if [ -n "$PRE_COMMIT_FROM_REF" ]; then
             git diff --name-only "$PRE_COMMIT_FROM_REF" "$PRE_COMMIT_TO_REF"
           else
             git diff --cached --name-only
-          fi | grep -qE "^classic/poetry\.lock$" || exit 0;
-          poetry -C classic install
+          fi | grep -qE "^classic/(original_autogpt|forge)/poetry\.lock$" || exit 0;
+          poetry -C classic/original_autogpt install
+          '
+        # include forge source (since it's a path dependency)
+        always_run: true
+        language: system
+        pass_filenames: false
+        stages: [pre-commit, post-checkout]
+
+      - id: poetry-install
+        name: Check & Install dependencies - Classic - Forge
+        alias: poetry-install-classic-forge
+        entry: >
+          bash -c '
+          if [ -n "$PRE_COMMIT_FROM_REF" ]; then
+            git diff --name-only "$PRE_COMMIT_FROM_REF" "$PRE_COMMIT_TO_REF"
+          else
+            git diff --cached --name-only
+          fi | grep -qE "^classic/forge/poetry\.lock$" || exit 0;
+          poetry -C classic/forge install
+          '
+        always_run: true
+        language: system
+        pass_filenames: false
+        stages: [pre-commit, post-checkout]
+
+      - id: poetry-install
+        name: Check & Install dependencies - Classic - Benchmark
+        alias: poetry-install-classic-benchmark
+        entry: >
+          bash -c '
+          if [ -n "$PRE_COMMIT_FROM_REF" ]; then
+            git diff --name-only "$PRE_COMMIT_FROM_REF" "$PRE_COMMIT_TO_REF"
+          else
+            git diff --cached --name-only
+          fi | grep -qE "^classic/benchmark/poetry\.lock$" || exit 0;
+          poetry -C classic/benchmark install
           '
         always_run: true
         language: system
@@ -194,10 +223,26 @@ repos:
         language: system
 
       - id: isort
-        name: Lint (isort) - Classic
-        alias: isort-classic
-        entry: bash -c 'cd classic && poetry run isort $(echo "$@" | sed "s|classic/||g")' --
-        files: ^classic/(original_autogpt|forge|direct_benchmark)/
+        name: Lint (isort) - Classic - AutoGPT
+        alias: isort-classic-autogpt
+        entry: poetry -P classic/original_autogpt run isort -p autogpt
+        files: ^classic/original_autogpt/
+        types: [file, python]
+        language: system
+
+      - id: isort
+        name: Lint (isort) - Classic - Forge
+        alias: isort-classic-forge
+        entry: poetry -P classic/forge run isort -p forge
+        files: ^classic/forge/
+        types: [file, python]
+        language: system
+
+      - id: isort
+        name: Lint (isort) - Classic - Benchmark
+        alias: isort-classic-benchmark
+        entry: poetry -P classic/benchmark run isort -p agbenchmark
+        files: ^classic/benchmark/
         types: [file, python]
         language: system
 
@@ -211,13 +256,26 @@ repos:
 
   - repo: https://github.com/PyCQA/flake8
     rev: 7.0.0
-    # Use consolidated flake8 config at classic/.flake8
+    # To have flake8 load the config of the individual subprojects, we have to call
+    # them separately.
     hooks:
       - id: flake8
-        name: Lint (Flake8) - Classic
-        alias: flake8-classic
-        files: ^classic/(original_autogpt|forge|direct_benchmark)/
-        args: [--config=classic/.flake8]
+        name: Lint (Flake8) - Classic - AutoGPT
+        alias: flake8-classic-autogpt
+        files: ^classic/original_autogpt/(autogpt|scripts|tests)/
+        args: [--config=classic/original_autogpt/.flake8]
+
+      - id: flake8
+        name: Lint (Flake8) - Classic - Forge
+        alias: flake8-classic-forge
+        files: ^classic/forge/(forge|tests)/
+        args: [--config=classic/forge/.flake8]
+
+      - id: flake8
+        name: Lint (Flake8) - Classic - Benchmark
+        alias: flake8-classic-benchmark
+        files: ^classic/benchmark/(agbenchmark|tests)/((?!reports).)*[/.]
+        args: [--config=classic/benchmark/.flake8]
 
   - repo: local
     hooks:
@@ -253,10 +311,29 @@ repos:
         pass_filenames: false
 
       - id: pyright
-        name: Typecheck - Classic
-        alias: pyright-classic
-        entry: poetry -C classic run pyright
-        files: ^classic/(original_autogpt|forge|direct_benchmark)/.*\.py$|^classic/poetry\.lock$
+        name: Typecheck - Classic - AutoGPT
+        alias: pyright-classic-autogpt
+        entry: poetry -C classic/original_autogpt run pyright
+        # include forge source (since it's a path dependency) but exclude *_test.py files:
+        files: ^(classic/original_autogpt/((autogpt|scripts|tests)/|poetry\.lock$)|classic/forge/(forge/.*(?<!_test)\.py|poetry\.lock)$)
+        types: [file]
+        language: system
+        pass_filenames: false
+
+      - id: pyright
+        name: Typecheck - Classic - Forge
+        alias: pyright-classic-forge
+        entry: poetry -C classic/forge run pyright
+        files: ^classic/forge/(forge/|poetry\.lock$)
+        types: [file]
+        language: system
+        pass_filenames: false
+
+      - id: pyright
+        name: Typecheck - Classic - Benchmark
+        alias: pyright-classic-benchmark
+        entry: poetry -C classic/benchmark run pyright
+        files: ^classic/benchmark/(agbenchmark/|tests/|poetry\.lock$)
         types: [file]
         language: system
         pass_filenames: false
@@ -283,9 +360,26 @@ repos:
   #       pass_filenames: false
 
   #     - id: pytest
-  #       name: Run tests - Classic (excl. slow tests)
-  #       alias: pytest-classic
-  #       entry: bash -c 'cd classic && poetry run pytest -m "not slow"'
-  #       files: ^classic/(original_autogpt|forge|direct_benchmark)/
+  #       name: Run tests - Classic - AutoGPT (excl. slow tests)
+  #       alias: pytest-classic-autogpt
+  #       entry: bash -c 'cd classic/original_autogpt && poetry run pytest --cov=autogpt -m "not slow" tests/unit tests/integration'
+  #       # include forge source (since it's a path dependency) but exclude *_test.py files:
+  #       files: ^(classic/original_autogpt/((autogpt|tests)/|poetry\.lock$)|classic/forge/(forge/.*(?<!_test)\.py|poetry\.lock)$)
+  #       language: system
+  #       pass_filenames: false
+
+  #     - id: pytest
+  #       name: Run tests - Classic - Forge (excl. slow tests)
+  #       alias: pytest-classic-forge
+  #       entry: bash -c 'cd classic/forge && poetry run pytest --cov=forge -m "not slow"'
+  #       files: ^classic/forge/(forge/|tests/|poetry\.lock$)
+  #       language: system
+  #       pass_filenames: false
+
+  #     - id: pytest
+  #       name: Run tests - Classic - Benchmark
+  #       alias: pytest-classic-benchmark
+  #       entry: bash -c 'cd classic/benchmark && poetry run pytest --cov=benchmark'
+  #       files: ^classic/benchmark/(agbenchmark/|tests/|poetry\.lock$)
   #       language: system
   #       pass_filenames: false

.secrets.baseline

@@ -1,467 +0,0 @@
-{
-  "version": "1.5.0",
-  "plugins_used": [
-    {
-      "name": "ArtifactoryDetector"
-    },
-    {
-      "name": "AWSKeyDetector"
-    },
-    {
-      "name": "AzureStorageKeyDetector"
-    },
-    {
-      "name": "Base64HighEntropyString",
-      "limit": 4.5
-    },
-    {
-      "name": "BasicAuthDetector"
-    },
-    {
-      "name": "CloudantDetector"
-    },
-    {
-      "name": "DiscordBotTokenDetector"
-    },
-    {
-      "name": "GitHubTokenDetector"
-    },
-    {
-      "name": "GitLabTokenDetector"
-    },
-    {
-      "name": "HexHighEntropyString",
-      "limit": 3.0
-    },
-    {
-      "name": "IbmCloudIamDetector"
-    },
-    {
-      "name": "IbmCosHmacDetector"
-    },
-    {
-      "name": "IPPublicDetector"
-    },
-    {
-      "name": "JwtTokenDetector"
-    },
-    {
-      "name": "KeywordDetector",
-      "keyword_exclude": ""
-    },
-    {
-      "name": "MailchimpDetector"
-    },
-    {
-      "name": "NpmDetector"
-    },
-    {
-      "name": "OpenAIDetector"
-    },
-    {
-      "name": "PrivateKeyDetector"
-    },
-    {
-      "name": "PypiTokenDetector"
-    },
-    {
-      "name": "SendGridDetector"
-    },
-    {
-      "name": "SlackDetector"
-    },
-    {
-      "name": "SoftlayerDetector"
-    },
-    {
-      "name": "SquareOAuthDetector"
-    },
-    {
-      "name": "StripeDetector"
-    },
-    {
-      "name": "TelegramBotTokenDetector"
-    },
-    {
-      "name": "TwilioKeyDetector"
-    }
-  ],
-  "filters_used": [
-    {
-      "path": "detect_secrets.filters.allowlist.is_line_allowlisted"
-    },
-    {
-      "path": "detect_secrets.filters.common.is_ignored_due_to_verification_policies",
-      "min_level": 2
-    },
-    {
-      "path": "detect_secrets.filters.heuristic.is_indirect_reference"
-    },
-    {
-      "path": "detect_secrets.filters.heuristic.is_likely_id_string"
-    },
-    {
-      "path": "detect_secrets.filters.heuristic.is_lock_file"
-    },
-    {
-      "path": "detect_secrets.filters.heuristic.is_not_alphanumeric_string"
-    },
-    {
-      "path": "detect_secrets.filters.heuristic.is_potential_uuid"
-    },
-    {
-      "path": "detect_secrets.filters.heuristic.is_prefixed_with_dollar_sign"
-    },
-    {
-      "path": "detect_secrets.filters.heuristic.is_sequential_string"
-    },
-    {
-      "path": "detect_secrets.filters.heuristic.is_swagger_file"
-    },
-    {
-      "path": "detect_secrets.filters.heuristic.is_templated_secret"
-    },
-    {
-      "path": "detect_secrets.filters.regex.should_exclude_file",
-      "pattern": [
-        "\\.env$",
-        "pnpm-lock\\.yaml$",
-        "\\.env\\.(default|example|template)$",
-        "__pycache__",
-        "_test\\.py$",
-        "test_.*\\.py$",
-        "conftest\\.py$",
-        "poetry\\.lock$",
-        "node_modules"
-      ]
-    }
-  ],
-  "results": {
-    "autogpt_platform/backend/backend/api/external/v1/integrations.py": [
-      {
-        "type": "Secret Keyword",
-        "filename": "autogpt_platform/backend/backend/api/external/v1/integrations.py",
-        "hashed_secret": "665b1e3851eefefa3fb878654292f16597d25155",
-        "is_verified": false,
-        "line_number": 289
-      }
-    ],
-    "autogpt_platform/backend/backend/blocks/airtable/_config.py": [
-      {
-        "type": "Secret Keyword",
-        "filename": "autogpt_platform/backend/backend/blocks/airtable/_config.py",
-        "hashed_secret": "57e168b03afb7c1ee3cdc4ee3db2fe1cc6e0df26",
-        "is_verified": false,
-        "line_number": 29
-      }
-    ],
-    "autogpt_platform/backend/backend/blocks/dataforseo/_config.py": [
-      {
-        "type": "Secret Keyword",
-        "filename": "autogpt_platform/backend/backend/blocks/dataforseo/_config.py",
-        "hashed_secret": "32ce93887331fa5d192f2876ea15ec000c7d58b8",
-        "is_verified": false,
-        "line_number": 12
-      }
-    ],
-    "autogpt_platform/backend/backend/blocks/github/checks.py": [
-      {
-        "type": "Hex High Entropy String",
-        "filename": "autogpt_platform/backend/backend/blocks/github/checks.py",
-        "hashed_secret": "8ac6f92737d8586790519c5d7bfb4d2eb172c238",
-        "is_verified": false,
-        "line_number": 108
-      }
-    ],
-    "autogpt_platform/backend/backend/blocks/github/ci.py": [
-      {
-        "type": "Hex High Entropy String",
-        "filename": "autogpt_platform/backend/backend/blocks/github/ci.py",
-        "hashed_secret": "90bd1b48e958257948487b90bee080ba5ed00caa",
-        "is_verified": false,
-        "line_number": 123
-      }
-    ],
-    "autogpt_platform/backend/backend/blocks/github/example_payloads/pull_request.synchronize.json": [
-      {
-        "type": "Hex High Entropy String",
-        "filename": "autogpt_platform/backend/backend/blocks/github/example_payloads/pull_request.synchronize.json",
-        "hashed_secret": "f96896dafced7387dcd22343b8ea29d3d2c65663",
-        "is_verified": false,
-        "line_number": 42
-      },
-      {
-        "type": "Hex High Entropy String",
-        "filename": "autogpt_platform/backend/backend/blocks/github/example_payloads/pull_request.synchronize.json",
-        "hashed_secret": "b80a94d5e70bedf4f5f89d2f5a5255cc9492d12e",
-        "is_verified": false,
-        "line_number": 193
-      },
-      {
-        "type": "Hex High Entropy String",
-        "filename": "autogpt_platform/backend/backend/blocks/github/example_payloads/pull_request.synchronize.json",
-        "hashed_secret": "75b17e517fe1b3136394f6bec80c4f892da75e42",
-        "is_verified": false,
-        "line_number": 344
-      },
-      {
-        "type": "Hex High Entropy String",
-        "filename": "autogpt_platform/backend/backend/blocks/github/example_payloads/pull_request.synchronize.json",
-        "hashed_secret": "b0bfb5e4e2394e7f8906e5ed1dffd88b2bc89dd5",
-        "is_verified": false,
-        "line_number": 534
-      }
-    ],
-    "autogpt_platform/backend/backend/blocks/github/statuses.py": [
-      {
-        "type": "Hex High Entropy String",
-        "filename": "autogpt_platform/backend/backend/blocks/github/statuses.py",
-        "hashed_secret": "8ac6f92737d8586790519c5d7bfb4d2eb172c238",
-        "is_verified": false,
-        "line_number": 85
-      }
-    ],
-    "autogpt_platform/backend/backend/blocks/google/docs.py": [
-      {
-        "type": "Hex High Entropy String",
-        "filename": "autogpt_platform/backend/backend/blocks/google/docs.py",
-        "hashed_secret": "c95da0c6696342c867ef0c8258d2f74d20fd94d4",
-        "is_verified": false,
-        "line_number": 203
-      }
-    ],
-    "autogpt_platform/backend/backend/blocks/google/sheets.py": [
-      {
-        "type": "Base64 High Entropy String",
-        "filename": "autogpt_platform/backend/backend/blocks/google/sheets.py",
-        "hashed_secret": "bd5a04fa3667e693edc13239b6d310c5c7a8564b",
-        "is_verified": false,
-        "line_number": 57
-      }
-    ],
-    "autogpt_platform/backend/backend/blocks/linear/_config.py": [
-      {
-        "type": "Secret Keyword",
-        "filename": "autogpt_platform/backend/backend/blocks/linear/_config.py",
-        "hashed_secret": "b37f020f42d6d613b6ce30103e4d408c4499b3bb",
-        "is_verified": false,
-        "line_number": 53
-      }
-    ],
-    "autogpt_platform/backend/backend/blocks/medium.py": [
-      {
-        "type": "Hex High Entropy String",
-        "filename": "autogpt_platform/backend/backend/blocks/medium.py",
-        "hashed_secret": "ff998abc1ce6d8f01a675fa197368e44c8916e9c",
-        "is_verified": false,
-        "line_number": 131
-      }
-    ],
-    "autogpt_platform/backend/backend/blocks/replicate/replicate_block.py": [
-      {
-        "type": "Hex High Entropy String",
-        "filename": "autogpt_platform/backend/backend/blocks/replicate/replicate_block.py",
-        "hashed_secret": "8bbdd6f26368f58ea4011d13d7f763cb662e66f0",
-        "is_verified": false,
-        "line_number": 55
-      }
-    ],
-    "autogpt_platform/backend/backend/blocks/slant3d/webhook.py": [
-      {
-        "type": "Hex High Entropy String",
-        "filename": "autogpt_platform/backend/backend/blocks/slant3d/webhook.py",
-        "hashed_secret": "36263c76947443b2f6e6b78153967ac4a7da99f9",
-        "is_verified": false,
-        "line_number": 100
-      }
-    ],
-    "autogpt_platform/backend/backend/blocks/talking_head.py": [
-      {
-        "type": "Base64 High Entropy String",
-        "filename": "autogpt_platform/backend/backend/blocks/talking_head.py",
-        "hashed_secret": "44ce2d66222529eea4a32932823466fc0601c799",
-        "is_verified": false,
-        "line_number": 113
-      }
-    ],
-    "autogpt_platform/backend/backend/blocks/wordpress/_config.py": [
-      {
-        "type": "Secret Keyword",
-        "filename": "autogpt_platform/backend/backend/blocks/wordpress/_config.py",
-        "hashed_secret": "e62679512436161b78e8a8d68c8829c2a1031ccb",
-        "is_verified": false,
-        "line_number": 17
-      }
-    ],
-    "autogpt_platform/backend/backend/util/cache.py": [
-      {
-        "type": "Secret Keyword",
-        "filename": "autogpt_platform/backend/backend/util/cache.py",
-        "hashed_secret": "37f0c918c3fa47ca4a70e42037f9f123fdfbc75b",
-        "is_verified": false,
-        "line_number": 449
-      }
-    ],
-    "autogpt_platform/frontend/src/app/(platform)/build/components/FlowEditor/nodes/helpers.ts": [
-      {
-        "type": "Secret Keyword",
-        "filename": "autogpt_platform/frontend/src/app/(platform)/build/components/FlowEditor/nodes/helpers.ts",
-        "hashed_secret": "5baa61e4c9b93f3f0682250b6cf8331b7ee68fd8",
-        "is_verified": false,
-        "line_number": 6
-      }
-    ],
-    "autogpt_platform/frontend/src/app/(platform)/dictionaries/en.json": [
-      {
-        "type": "Secret Keyword",
-        "filename": "autogpt_platform/frontend/src/app/(platform)/dictionaries/en.json",
-        "hashed_secret": "8be3c943b1609fffbfc51aad666d0a04adf83c9d",
-        "is_verified": false,
-        "line_number": 5
-      }
-    ],
-    "autogpt_platform/frontend/src/app/(platform)/dictionaries/es.json": [
-      {
-        "type": "Secret Keyword",
-        "filename": "autogpt_platform/frontend/src/app/(platform)/dictionaries/es.json",
-        "hashed_secret": "5a6d1c612954979ea99ee33dbb2d231b00f6ac0a",
-        "is_verified": false,
-        "line_number": 5
-      }
-    ],
-    "autogpt_platform/frontend/src/app/(platform)/library/agents/[id]/components/NewAgentLibraryView/components/modals/AgentInputsReadOnly/helpers.ts": [
-      {
-        "type": "Secret Keyword",
-        "filename": "autogpt_platform/frontend/src/app/(platform)/library/agents/[id]/components/NewAgentLibraryView/components/modals/AgentInputsReadOnly/helpers.ts",
-        "hashed_secret": "cf678cab87dc1f7d1b95b964f15375e088461679",
-        "is_verified": false,
-        "line_number": 6
-      },
-      {
-        "type": "Secret Keyword",
-        "filename": "autogpt_platform/frontend/src/app/(platform)/library/agents/[id]/components/NewAgentLibraryView/components/modals/AgentInputsReadOnly/helpers.ts",
-        "hashed_secret": "f72cbb45464d487064610c5411c576ca4019d380",
-        "is_verified": false,
-        "line_number": 8
-      }
-    ],
-    "autogpt_platform/frontend/src/app/(platform)/library/agents/[id]/components/NewAgentLibraryView/components/modals/RunAgentModal/components/ModalRunSection/helpers.ts": [
-      {
-        "type": "Secret Keyword",
-        "filename": "autogpt_platform/frontend/src/app/(platform)/library/agents/[id]/components/NewAgentLibraryView/components/modals/RunAgentModal/components/ModalRunSection/helpers.ts",
-        "hashed_secret": "cf678cab87dc1f7d1b95b964f15375e088461679",
-        "is_verified": false,
-        "line_number": 5
-      },
-      {
-        "type": "Secret Keyword",
-        "filename": "autogpt_platform/frontend/src/app/(platform)/library/agents/[id]/components/NewAgentLibraryView/components/modals/RunAgentModal/components/ModalRunSection/helpers.ts",
-        "hashed_secret": "f72cbb45464d487064610c5411c576ca4019d380",
-        "is_verified": false,
-        "line_number": 7
-      }
-    ],
-    "autogpt_platform/frontend/src/app/(platform)/profile/(user)/integrations/page.tsx": [
-      {
-        "type": "Secret Keyword",
-        "filename": "autogpt_platform/frontend/src/app/(platform)/profile/(user)/integrations/page.tsx",
-        "hashed_secret": "cf678cab87dc1f7d1b95b964f15375e088461679",
-        "is_verified": false,
-        "line_number": 192
-      },
-      {
-        "type": "Secret Keyword",
-        "filename": "autogpt_platform/frontend/src/app/(platform)/profile/(user)/integrations/page.tsx",
-        "hashed_secret": "86275db852204937bbdbdebe5fabe8536e030ab6",
-        "is_verified": false,
-        "line_number": 193
-      }
-    ],
-    "autogpt_platform/frontend/src/components/contextual/CredentialsInput/helpers.ts": [
-      {
-        "type": "Secret Keyword",
-        "filename": "autogpt_platform/frontend/src/components/contextual/CredentialsInput/helpers.ts",
-        "hashed_secret": "47acd2028cf81b5da88ddeedb2aea4eca4b71fbd",
-        "is_verified": false,
-        "line_number": 102
-      },
-      {
-        "type": "Secret Keyword",
-        "filename": "autogpt_platform/frontend/src/components/contextual/CredentialsInput/helpers.ts",
-        "hashed_secret": "8be3c943b1609fffbfc51aad666d0a04adf83c9d",
-        "is_verified": false,
-        "line_number": 103
-      }
-    ],
-    "autogpt_platform/frontend/src/lib/autogpt-server-api/utils.ts": [
-      {
-        "type": "Base64 High Entropy String",
-        "filename": "autogpt_platform/frontend/src/lib/autogpt-server-api/utils.ts",
-        "hashed_secret": "9c486c92f1a7420e1045c7ad963fbb7ba3621025",
-        "is_verified": false,
-        "line_number": 73
-      },
-      {
-        "type": "Base64 High Entropy String",
-        "filename": "autogpt_platform/frontend/src/lib/autogpt-server-api/utils.ts",
-        "hashed_secret": "9277508c7a6effc8fb59163efbfada189e35425c",
-        "is_verified": false,
-        "line_number": 75
-      },
-      {
-        "type": "Base64 High Entropy String",
-        "filename": "autogpt_platform/frontend/src/lib/autogpt-server-api/utils.ts",
-        "hashed_secret": "8dc7e2cb1d0935897d541bf5facab389b8a50340",
-        "is_verified": false,
-        "line_number": 77
-      },
-      {
-        "type": "Base64 High Entropy String",
-        "filename": "autogpt_platform/frontend/src/lib/autogpt-server-api/utils.ts",
-        "hashed_secret": "79a26ad48775944299be6aaf9fb1d5302c1ed75b",
-        "is_verified": false,
-        "line_number": 79
-      },
-      {
-        "type": "Base64 High Entropy String",
-        "filename": "autogpt_platform/frontend/src/lib/autogpt-server-api/utils.ts",
-        "hashed_secret": "a3b62b44500a1612e48d4cab8294df81561b3b1a",
-        "is_verified": false,
-        "line_number": 81
-      },
-      {
-        "type": "Base64 High Entropy String",
-        "filename": "autogpt_platform/frontend/src/lib/autogpt-server-api/utils.ts",
-        "hashed_secret": "a58979bd0b21ef4f50417d001008e60dd7a85c64",
-        "is_verified": false,
-        "line_number": 83
-      },
-      {
-        "type": "Base64 High Entropy String",
-        "filename": "autogpt_platform/frontend/src/lib/autogpt-server-api/utils.ts",
-        "hashed_secret": "6cb6e075f8e8c7c850f9d128d6608e5dbe209a79",
-        "is_verified": false,
-        "line_number": 85
-      }
-    ],
-    "autogpt_platform/frontend/src/lib/constants.ts": [
-      {
-        "type": "Secret Keyword",
-        "filename": "autogpt_platform/frontend/src/lib/constants.ts",
-        "hashed_secret": "27b924db06a28cc755fb07c54f0fddc30659fe4d",
-        "is_verified": false,
-        "line_number": 10
-      }
-    ],
-    "autogpt_platform/frontend/src/tests/credentials/index.ts": [
-      {
-        "type": "Secret Keyword",
-        "filename": "autogpt_platform/frontend/src/tests/credentials/index.ts",
-        "hashed_secret": "c18006fc138809314751cd1991f1e0b820fabd37",
-        "is_verified": false,
-        "line_number": 4
-      }
-    ]
-  },
-  "generated_at": "2026-04-02T13:10:54Z"
-}

AGENTS.md

@@ -1,6 +1,6 @@
 # AutoGPT Platform Contribution Guide
 
-This guide provides context for coding agents when updating the **autogpt_platform** folder.
+This guide provides context for Codex when updating the **autogpt_platform** folder.
 
 ## Directory overview
 
@@ -30,7 +30,7 @@ See `/frontend/CONTRIBUTING.md` for complete patterns. Quick reference:
    - Regenerate with `pnpm generate:api`
    - Pattern: `use{Method}{Version}{OperationName}`
 4. **Styling**: Tailwind CSS only, use design tokens, Phosphor Icons only
-5. **Testing**: Integration tests (Vitest + RTL + MSW) are the default (~90%, page-level). Playwright for E2E critical flows. Storybook for design system components. See `autogpt_platform/frontend/TESTING.md`
+5. **Testing**: Add Storybook stories for new components, Playwright for E2E
 6. **Code conventions**: Function declarations (not arrow functions) for components/handlers
 
 - Component props should be `interface Props { ... }` (not exported) unless the interface needs to be used outside the component
@@ -47,9 +47,7 @@ See `/frontend/CONTRIBUTING.md` for complete patterns. Quick reference:
 ## Testing
 
 - Backend: `poetry run test` (runs pytest with a docker based postgres + prisma).
-- Frontend integration tests: `pnpm test:unit` (Vitest + RTL + MSW, primary testing approach).
-- Frontend E2E tests: `pnpm test` or `pnpm test-ui` for Playwright tests.
-- See `autogpt_platform/frontend/TESTING.md` for the full testing strategy.
+- Frontend: `pnpm test` or `pnpm test-ui` for Playwright tests. See `docs/content/platform/contributing/tests.md` for tips.
 
 Always run the relevant linters and tests before committing.
 Use conventional commit messages for all commits (e.g. `feat(backend): add API`).

CLAUDE.md

@@ -1 +0,0 @@
-@AGENTS.md

README.md

@@ -83,13 +83,13 @@ The AutoGPT frontend is where users interact with our powerful AI automation pla
 
    **Agent Builder:** For those who want to customize, our intuitive, low-code interface allows you to design and configure your own AI agents. 
    
-   **Workflow Management:** Build, modify, and optimize your automation workflows with ease. You build your agent by connecting blocks, where each block performs a single action.
+   **Workflow Management:** Build, modify, and optimize your automation workflows with ease. You build your agent by connecting blocks, where each block     performs a single action.
    
    **Deployment Controls:** Manage the lifecycle of your agents, from testing to production.
    
    **Ready-to-Use Agents:** Don't want to build? Simply select from our library of pre-configured agents and put them to work immediately.
    
-   **Agent Interaction:** Whether you've built your own or are using pre-configured agents, easily run and interact with them through our user-friendly interface.
+   **Agent Interaction:** Whether you've built your own or are using pre-configured agents, easily run and interact with them through our user-friendly      interface.
 
    **Monitoring and Analytics:** Keep track of your agents' performance and gain insights to continually improve your automation processes.
 

autogpt_platform/AGENTS.md

@@ -1,120 +0,0 @@
-# AutoGPT Platform
-
-This file provides guidance to coding agents when working with code in this repository.
-
-## Repository Overview
-
-AutoGPT Platform is a monorepo containing:
-
-- **Backend** (`backend`): Python FastAPI server with async support
-- **Frontend** (`frontend`): Next.js React application
-- **Shared Libraries** (`autogpt_libs`): Common Python utilities
-
-## Component Documentation
-
-- **Backend**: See @backend/AGENTS.md for backend-specific commands, architecture, and development tasks
-- **Frontend**: See @frontend/AGENTS.md for frontend-specific commands, architecture, and development patterns
-
-## Key Concepts
-
-1. **Agent Graphs**: Workflow definitions stored as JSON, executed by the backend
-2. **Blocks**: Reusable components in `backend/backend/blocks/` that perform specific tasks
-3. **Integrations**: OAuth and API connections stored per user
-4. **Store**: Marketplace for sharing agent templates
-5. **Virus Scanning**: ClamAV integration for file upload security
-
-### Environment Configuration
-
-#### Configuration Files
-
-- **Backend**: `backend/.env.default` (defaults) → `backend/.env` (user overrides)
-- **Frontend**: `frontend/.env.default` (defaults) → `frontend/.env` (user overrides)
-- **Platform**: `.env.default` (Supabase/shared defaults) → `.env` (user overrides)
-
-#### Docker Environment Loading Order
-
-1. `.env.default` files provide base configuration (tracked in git)
-2. `.env` files provide user-specific overrides (gitignored)
-3. Docker Compose `environment:` sections provide service-specific overrides
-4. Shell environment variables have highest precedence
-
-#### Key Points
-
-- All services use hardcoded defaults in docker-compose files (no `${VARIABLE}` substitutions)
-- The `env_file` directive loads variables INTO containers at runtime
-- Backend/Frontend services use YAML anchors for consistent configuration
-- Supabase services (`db/docker/docker-compose.yml`) follow the same pattern
-
-### Branching Strategy
-
-- **`dev`** is the main development branch. All PRs should target `dev`.
-- **`master`** is the production branch. Only used for production releases.
-
-### Creating Pull Requests
-
-- Create the PR against the `dev` branch of the repository.
-- **Split PRs by concern** — each PR should have a single clear purpose. For example, "usage tracking" and "credit charging" should be separate PRs even if related. Combining multiple concerns makes it harder for reviewers to understand what belongs to what.
-- Ensure the branch name is descriptive (e.g., `feature/add-new-block`)
-- Use conventional commit messages (see below)
-- **Structure the PR description with Why / What / How** — Why: the motivation (what problem it solves, what's broken/missing without it); What: high-level summary of changes; How: approach, key implementation details, or architecture decisions. Reviewers need all three to judge whether the approach fits the problem.
-- Fill out the .github/PULL_REQUEST_TEMPLATE.md template as the PR description
-- Always use `--body-file` to pass PR body — avoids shell interpretation of backticks and special characters:
-  ```bash
-  PR_BODY=$(mktemp)
-  cat > "$PR_BODY" << 'PREOF'
-  ## Summary
-  - use `backticks` freely here
-  PREOF
-  gh pr create --title "..." --body-file "$PR_BODY" --base dev
-  rm "$PR_BODY"
-  ```
-- Run the github pre-commit hooks to ensure code quality.
-
-### Test-Driven Development (TDD)
-
-When fixing a bug or adding a feature, follow a test-first approach:
-
-1. **Write a failing test first** — create a test that reproduces the bug or validates the new behavior, marked with `@pytest.mark.xfail` (backend) or `.fixme` (Playwright). Run it to confirm it fails for the right reason.
-2. **Implement the fix/feature** — write the minimal code to make the test pass.
-3. **Remove the xfail marker** — once the test passes, remove the `xfail`/`.fixme` annotation and run the full test suite to confirm nothing else broke.
-
-This ensures every change is covered by a test and that the test actually validates the intended behavior.
-
-### Reviewing/Revising Pull Requests
-
-Use `/pr-review` to review a PR or `/pr-address` to address comments.
-
-When fetching comments manually:
-- `gh api repos/Significant-Gravitas/AutoGPT/pulls/{N}/reviews --paginate` — top-level reviews
-- `gh api repos/Significant-Gravitas/AutoGPT/pulls/{N}/comments --paginate` — inline review comments (always paginate to avoid missing comments beyond page 1)
-- `gh api repos/Significant-Gravitas/AutoGPT/issues/{N}/comments` — PR conversation comments
-
-### Conventional Commits
-
-Use this format for commit messages and Pull Request titles:
-
-**Conventional Commit Types:**
-
-- `feat`: Introduces a new feature to the codebase
-- `fix`: Patches a bug in the codebase
-- `refactor`: Code change that neither fixes a bug nor adds a feature; also applies to removing features
-- `ci`: Changes to CI configuration
-- `docs`: Documentation-only changes
-- `dx`: Improvements to the developer experience
-
-**Recommended Base Scopes:**
-
-- `platform`: Changes affecting both frontend and backend
-- `frontend`
-- `backend`
-- `infra`
-- `blocks`: Modifications/additions of individual blocks
-
-**Subscope Examples:**
-
-- `backend/executor`
-- `backend/db`
-- `frontend/builder` (includes changes to the block UI component)
-- `infra/prod`
-
-Use these scopes and subscopes for clarity and consistency in commit messages.

autogpt_platform/CLAUDE.md

@@ -1 +1,95 @@
-@AGENTS.md
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+## Repository Overview
+
+AutoGPT Platform is a monorepo containing:
+
+- **Backend** (`backend`): Python FastAPI server with async support
+- **Frontend** (`frontend`): Next.js React application
+- **Shared Libraries** (`autogpt_libs`): Common Python utilities
+
+## Component Documentation
+
+- **Backend**: See @backend/CLAUDE.md for backend-specific commands, architecture, and development tasks
+- **Frontend**: See @frontend/CLAUDE.md for frontend-specific commands, architecture, and development patterns
+
+## Key Concepts
+
+1. **Agent Graphs**: Workflow definitions stored as JSON, executed by the backend
+2. **Blocks**: Reusable components in `backend/backend/blocks/` that perform specific tasks
+3. **Integrations**: OAuth and API connections stored per user
+4. **Store**: Marketplace for sharing agent templates
+5. **Virus Scanning**: ClamAV integration for file upload security
+
+### Environment Configuration
+
+#### Configuration Files
+
+- **Backend**: `backend/.env.default` (defaults) → `backend/.env` (user overrides)
+- **Frontend**: `frontend/.env.default` (defaults) → `frontend/.env` (user overrides)
+- **Platform**: `.env.default` (Supabase/shared defaults) → `.env` (user overrides)
+
+#### Docker Environment Loading Order
+
+1. `.env.default` files provide base configuration (tracked in git)
+2. `.env` files provide user-specific overrides (gitignored)
+3. Docker Compose `environment:` sections provide service-specific overrides
+4. Shell environment variables have highest precedence
+
+#### Key Points
+
+- All services use hardcoded defaults in docker-compose files (no `${VARIABLE}` substitutions)
+- The `env_file` directive loads variables INTO containers at runtime
+- Backend/Frontend services use YAML anchors for consistent configuration
+- Supabase services (`db/docker/docker-compose.yml`) follow the same pattern
+
+### Branching Strategy
+
+- **`dev`** is the main development branch. All PRs should target `dev`.
+- **`master`** is the production branch. Only used for production releases.
+
+### Creating Pull Requests
+
+- Create the PR against the `dev` branch of the repository.
+- Ensure the branch name is descriptive (e.g., `feature/add-new-block`)
+- Use conventional commit messages (see below)
+- Fill out the .github/PULL_REQUEST_TEMPLATE.md template as the PR description
+- Run the github pre-commit hooks to ensure code quality.
+
+### Reviewing/Revising Pull Requests
+
+- When the user runs /pr-comments or tries to fetch them, also run gh api /repos/Significant-Gravitas/AutoGPT/pulls/[issuenum]/reviews to get the reviews
+- Use gh api /repos/Significant-Gravitas/AutoGPT/pulls/[issuenum]/reviews/[review_id]/comments to get the review contents
+- Use gh api /repos/Significant-Gravitas/AutoGPT/issues/9924/comments to get the pr specific comments
+
+### Conventional Commits
+
+Use this format for commit messages and Pull Request titles:
+
+**Conventional Commit Types:**
+
+- `feat`: Introduces a new feature to the codebase
+- `fix`: Patches a bug in the codebase
+- `refactor`: Code change that neither fixes a bug nor adds a feature; also applies to removing features
+- `ci`: Changes to CI configuration
+- `docs`: Documentation-only changes
+- `dx`: Improvements to the developer experience
+
+**Recommended Base Scopes:**
+
+- `platform`: Changes affecting both frontend and backend
+- `frontend`
+- `backend`
+- `infra`
+- `blocks`: Modifications/additions of individual blocks
+
+**Subscope Examples:**
+
+- `backend/executor`
+- `backend/db`
+- `frontend/builder` (includes changes to the block UI component)
+- `infra/prod`
+
+Use these scopes and subscopes for clarity and consistency in commit messages.

autogpt_platform/analytics/queries/auth_activities.sql

@@ -1,40 +0,0 @@
--- =============================================================
--- View: analytics.auth_activities
--- Looker source alias: ds49  |  Charts: 1
--- =============================================================
--- DESCRIPTION
---   Tracks authentication events (login, logout, SSO, password
---   reset, etc.) from Supabase's internal audit log.
---   Useful for monitoring sign-in patterns and detecting anomalies.
---
--- SOURCE TABLES
---   auth.audit_log_entries  — Supabase internal auth event log
---
--- OUTPUT COLUMNS
---   created_at      TIMESTAMPTZ  When the auth event occurred
---   actor_id        TEXT         User ID who triggered the event
---   actor_via_sso   TEXT         Whether the action was via SSO ('true'/'false')
---   action          TEXT         Event type (e.g. 'login', 'logout', 'token_refreshed')
---
--- WINDOW
---   Rolling 90 days from current date
---
--- EXAMPLE QUERIES
---   -- Daily login counts
---   SELECT DATE_TRUNC('day', created_at) AS day, COUNT(*) AS logins
---   FROM analytics.auth_activities
---   WHERE action = 'login'
---   GROUP BY 1 ORDER BY 1;
---
---   -- SSO vs password login breakdown
---   SELECT actor_via_sso, COUNT(*) FROM analytics.auth_activities
---   WHERE action = 'login' GROUP BY 1;
--- =============================================================
-
-SELECT
-    created_at,
-    payload->>'actor_id'      AS actor_id,
-    payload->>'actor_via_sso' AS actor_via_sso,
-    payload->>'action'        AS action
-FROM auth.audit_log_entries
-WHERE created_at >= NOW() - INTERVAL '90 days'

autogpt_platform/analytics/queries/graph_execution.sql

@@ -1,105 +0,0 @@
--- =============================================================
--- View: analytics.graph_execution
--- Looker source alias: ds16  |  Charts: 21
--- =============================================================
--- DESCRIPTION
---   One row per agent graph execution (last 90 days).
---   Unpacks the JSONB stats column into individual numeric columns
---   and normalises the executionStatus — runs that failed due to
---   insufficient credits are reclassified as 'NO_CREDITS' for
---   easier filtering.  Error messages are scrubbed of IDs and URLs
---   to allow safe grouping.
---
--- SOURCE TABLES
---   platform.AgentGraphExecution  — Execution records
---   platform.AgentGraph           — Agent graph metadata (for name)
---   platform.LibraryAgent         — To flag possibly-AI (safe-mode) agents
---
--- OUTPUT COLUMNS
---   id                TEXT         Execution UUID
---   agentGraphId      TEXT         Agent graph UUID
---   agentGraphVersion INT          Graph version number
---   executionStatus   TEXT         COMPLETED | FAILED | NO_CREDITS | RUNNING | QUEUED | TERMINATED
---   createdAt         TIMESTAMPTZ  When the execution was queued
---   updatedAt         TIMESTAMPTZ  Last status update time
---   userId            TEXT         Owner user UUID
---   agentGraphName    TEXT         Human-readable agent name
---   cputime           DECIMAL      Total CPU seconds consumed
---   walltime          DECIMAL      Total wall-clock seconds
---   node_count        DECIMAL      Number of nodes in the graph
---   nodes_cputime     DECIMAL      CPU time across all nodes
---   nodes_walltime    DECIMAL      Wall time across all nodes
---   execution_cost    DECIMAL      Credit cost of this execution
---   correctness_score FLOAT        AI correctness score (if available)
---   possibly_ai       BOOLEAN      True if agent has sensitive_action_safe_mode enabled
---   groupedErrorMessage TEXT       Scrubbed error string (IDs/URLs replaced with wildcards)
---
--- WINDOW
---   Rolling 90 days (createdAt > CURRENT_DATE - 90 days)
---
--- EXAMPLE QUERIES
---   -- Daily execution counts by status
---   SELECT DATE_TRUNC('day', "createdAt") AS day, "executionStatus", COUNT(*)
---   FROM analytics.graph_execution
---   GROUP BY 1, 2 ORDER BY 1;
---
---   -- Average cost per execution by agent
---   SELECT "agentGraphName", AVG("execution_cost") AS avg_cost, COUNT(*) AS runs
---   FROM analytics.graph_execution
---   WHERE "executionStatus" = 'COMPLETED'
---   GROUP BY 1 ORDER BY avg_cost DESC;
---
---   -- Top error messages
---   SELECT "groupedErrorMessage", COUNT(*) AS occurrences
---   FROM analytics.graph_execution
---   WHERE "executionStatus" = 'FAILED'
---   GROUP BY 1 ORDER BY 2 DESC LIMIT 20;
--- =============================================================
-
-SELECT
-    ge."id"                                                        AS id,
-    ge."agentGraphId"                                              AS agentGraphId,
-    ge."agentGraphVersion"                                         AS agentGraphVersion,
-    CASE
-        WHEN jsonb_exists(ge."stats"::jsonb, 'error')
-         AND (
-               (ge."stats"::jsonb->>'error') ILIKE '%insufficient balance%'
-            OR (ge."stats"::jsonb->>'error') ILIKE '%you have no credits left%'
-             )
-        THEN 'NO_CREDITS'
-        ELSE CAST(ge."executionStatus" AS TEXT)
-    END                                                            AS executionStatus,
-    ge."createdAt"                                                 AS createdAt,
-    ge."updatedAt"                                                 AS updatedAt,
-    ge."userId"                                                    AS userId,
-    g."name"                                                       AS agentGraphName,
-    (ge."stats"::jsonb->>'cputime')::decimal                       AS cputime,
-    (ge."stats"::jsonb->>'walltime')::decimal                      AS walltime,
-    (ge."stats"::jsonb->>'node_count')::decimal                    AS node_count,
-    (ge."stats"::jsonb->>'nodes_cputime')::decimal                 AS nodes_cputime,
-    (ge."stats"::jsonb->>'nodes_walltime')::decimal                AS nodes_walltime,
-    (ge."stats"::jsonb->>'cost')::decimal                          AS execution_cost,
-    (ge."stats"::jsonb->>'correctness_score')::float               AS correctness_score,
-    COALESCE(la.possibly_ai, FALSE)                                AS possibly_ai,
-    REGEXP_REPLACE(
-        REGEXP_REPLACE(
-            TRIM(BOTH '"' FROM ge."stats"::jsonb->>'error'),
-            '(https?://)([A-Za-z0-9.-]+)(:[0-9]+)?(/[^\s]*)?',
-            '\1\2/...', 'gi'
-        ),
-        '[a-zA-Z0-9_:-]*\d[a-zA-Z0-9_:-]*', '*', 'g'
-    )                                                              AS groupedErrorMessage
-FROM platform."AgentGraphExecution" ge
-LEFT JOIN platform."AgentGraph" g
-       ON ge."agentGraphId" = g."id"
-      AND ge."agentGraphVersion" = g."version"
-LEFT JOIN (
-    SELECT DISTINCT ON ("userId", "agentGraphId")
-           "userId", "agentGraphId",
-           ("settings"::jsonb->>'sensitive_action_safe_mode')::boolean AS possibly_ai
-    FROM platform."LibraryAgent"
-    WHERE "isDeleted"  = FALSE
-      AND "isArchived" = FALSE
-    ORDER BY "userId", "agentGraphId", "agentGraphVersion" DESC
-) la ON la."userId" = ge."userId" AND la."agentGraphId" = ge."agentGraphId"
-WHERE ge."createdAt" > CURRENT_DATE - INTERVAL '90 days'

autogpt_platform/analytics/queries/node_block_execution.sql

@@ -1,101 +0,0 @@
--- =============================================================
--- View: analytics.node_block_execution
--- Looker source alias: ds14  |  Charts: 11
--- =============================================================
--- DESCRIPTION
---   One row per node (block) execution (last 90 days).
---   Unpacks stats JSONB and joins to identify which block type
---   was run.  For failed nodes, joins the error output and
---   scrubs it for safe grouping.
---
--- SOURCE TABLES
---   platform.AgentNodeExecution              — Node execution records
---   platform.AgentNode                       — Node → block mapping
---   platform.AgentBlock                      — Block name/ID
---   platform.AgentNodeExecutionInputOutput   — Error output values
---
--- OUTPUT COLUMNS
---   id                    TEXT         Node execution UUID
---   agentGraphExecutionId TEXT         Parent graph execution UUID
---   agentNodeId           TEXT         Node UUID within the graph
---   executionStatus       TEXT         COMPLETED | FAILED | QUEUED | RUNNING | TERMINATED
---   addedTime             TIMESTAMPTZ  When the node was queued
---   queuedTime            TIMESTAMPTZ  When it entered the queue
---   startedTime           TIMESTAMPTZ  When execution started
---   endedTime             TIMESTAMPTZ  When execution finished
---   inputSize             BIGINT       Input payload size in bytes
---   outputSize            BIGINT       Output payload size in bytes
---   walltime              NUMERIC      Wall-clock seconds for this node
---   cputime               NUMERIC      CPU seconds for this node
---   llmRetryCount         INT          Number of LLM retries
---   llmCallCount          INT          Number of LLM API calls made
---   inputTokenCount       BIGINT       LLM input tokens consumed
---   outputTokenCount      BIGINT       LLM output tokens produced
---   blockName             TEXT         Human-readable block name (e.g. 'OpenAIBlock')
---   blockId               TEXT         Block UUID
---   groupedErrorMessage   TEXT         Scrubbed error (IDs/URLs wildcarded)
---   errorMessage          TEXT         Raw error output (only set when FAILED)
---
--- WINDOW
---   Rolling 90 days (addedTime > CURRENT_DATE - 90 days)
---
--- EXAMPLE QUERIES
---   -- Most-used blocks by execution count
---   SELECT "blockName", COUNT(*) AS executions,
---          COUNT(*) FILTER (WHERE "executionStatus"='FAILED') AS failures
---   FROM analytics.node_block_execution
---   GROUP BY 1 ORDER BY executions DESC LIMIT 20;
---
---   -- Average LLM token usage per block
---   SELECT "blockName",
---          AVG("inputTokenCount") AS avg_input_tokens,
---          AVG("outputTokenCount") AS avg_output_tokens
---   FROM analytics.node_block_execution
---   WHERE "llmCallCount" > 0
---   GROUP BY 1 ORDER BY avg_input_tokens DESC;
---
---   -- Top failure reasons
---   SELECT "blockName", "groupedErrorMessage", COUNT(*) AS count
---   FROM analytics.node_block_execution
---   WHERE "executionStatus" = 'FAILED'
---   GROUP BY 1, 2 ORDER BY count DESC LIMIT 20;
--- =============================================================
-
-SELECT
-    ne."id"                                                            AS id,
-    ne."agentGraphExecutionId"                                         AS agentGraphExecutionId,
-    ne."agentNodeId"                                                   AS agentNodeId,
-    CAST(ne."executionStatus" AS TEXT)                                 AS executionStatus,
-    ne."addedTime"                                                     AS addedTime,
-    ne."queuedTime"                                                    AS queuedTime,
-    ne."startedTime"                                                   AS startedTime,
-    ne."endedTime"                                                     AS endedTime,
-    (ne."stats"::jsonb->>'input_size')::bigint                         AS inputSize,
-    (ne."stats"::jsonb->>'output_size')::bigint                        AS outputSize,
-    (ne."stats"::jsonb->>'walltime')::numeric                          AS walltime,
-    (ne."stats"::jsonb->>'cputime')::numeric                           AS cputime,
-    (ne."stats"::jsonb->>'llm_retry_count')::int                       AS llmRetryCount,
-    (ne."stats"::jsonb->>'llm_call_count')::int                        AS llmCallCount,
-    (ne."stats"::jsonb->>'input_token_count')::bigint                  AS inputTokenCount,
-    (ne."stats"::jsonb->>'output_token_count')::bigint                 AS outputTokenCount,
-    b."name"                                                           AS blockName,
-    b."id"                                                             AS blockId,
-    REGEXP_REPLACE(
-        REGEXP_REPLACE(
-            TRIM(BOTH '"' FROM eio."data"::text),
-            '(https?://)([A-Za-z0-9.-]+)(:[0-9]+)?(/[^\s]*)?',
-            '\1\2/...', 'gi'
-        ),
-        '[a-zA-Z0-9_:-]*\d[a-zA-Z0-9_:-]*', '*', 'g'
-    )                                                                  AS groupedErrorMessage,
-    eio."data"                                                         AS errorMessage
-FROM platform."AgentNodeExecution" ne
-LEFT JOIN platform."AgentNode" nd
-       ON ne."agentNodeId" = nd."id"
-LEFT JOIN platform."AgentBlock" b
-       ON nd."agentBlockId" = b."id"
-LEFT JOIN platform."AgentNodeExecutionInputOutput" eio
-       ON eio."referencedByOutputExecId" = ne."id"
-      AND eio."name" = 'error'
-      AND ne."executionStatus" = 'FAILED'
-WHERE ne."addedTime" > CURRENT_DATE - INTERVAL '90 days'

autogpt_platform/analytics/queries/retention_agent.sql

@@ -1,97 +0,0 @@
--- =============================================================
--- View: analytics.retention_agent
--- Looker source alias: ds35  |  Charts: 2
--- =============================================================
--- DESCRIPTION
---   Weekly cohort retention broken down per individual agent.
---   Cohort = week of a user's first use of THAT specific agent.
---   Tells you which agents keep users coming back vs. one-shot
---   use. Only includes cohorts from the last 180 days.
---
--- SOURCE TABLES
---   platform.AgentGraphExecution  — Execution records (user × agent × time)
---   platform.AgentGraph           — Agent names
---
--- OUTPUT COLUMNS
---   agent_id            TEXT   Agent graph UUID
---   agent_label         TEXT   'AgentName [first8chars]'
---   agent_label_n       TEXT   'AgentName [first8chars] (n=total_users)'
---   cohort_week_start   DATE   Week users first ran this agent
---   cohort_label        TEXT   ISO week label
---   cohort_label_n      TEXT   ISO week label with cohort size
---   user_lifetime_week  INT    Weeks since first use of this agent
---   cohort_users        BIGINT Users in this cohort for this agent
---   active_users        BIGINT Users who ran the agent again in week k
---   retention_rate      FLOAT  active_users / cohort_users
---   cohort_users_w0     BIGINT cohort_users only at week 0 (safe to SUM)
---   agent_total_users   BIGINT Total users across all cohorts for this agent
---
--- EXAMPLE QUERIES
---   -- Best-retained agents at week 2
---   SELECT agent_label, AVG(retention_rate) AS w2_retention
---   FROM analytics.retention_agent
---   WHERE user_lifetime_week = 2 AND cohort_users >= 10
---   GROUP BY 1 ORDER BY w2_retention DESC LIMIT 10;
---
---   -- Agents with most unique users
---   SELECT DISTINCT agent_label, agent_total_users
---   FROM analytics.retention_agent
---   ORDER BY agent_total_users DESC LIMIT 20;
--- =============================================================
-
-WITH params AS (SELECT 12::int AS max_weeks, (CURRENT_DATE - INTERVAL '180 days') AS cohort_start),
-events AS (
-  SELECT e."userId"::text AS user_id, e."agentGraphId" AS agent_id,
-         e."createdAt"::timestamptz AS created_at,
-         DATE_TRUNC('week', e."createdAt")::date AS week_start
-  FROM platform."AgentGraphExecution" e
-),
-first_use AS (
-  SELECT user_id, agent_id, MIN(created_at) AS first_use_at,
-         DATE_TRUNC('week', MIN(created_at))::date AS cohort_week_start
-  FROM events GROUP BY 1,2
-  HAVING MIN(created_at) >= (SELECT cohort_start FROM params)
-),
-activity_weeks AS (SELECT DISTINCT user_id, agent_id, week_start FROM events),
-user_week_age AS (
-  SELECT aw.user_id, aw.agent_id, fu.cohort_week_start,
-         ((aw.week_start - DATE_TRUNC('week',fu.first_use_at)::date)/7)::int AS user_lifetime_week
-  FROM activity_weeks aw JOIN first_use fu USING (user_id, agent_id)
-  WHERE aw.week_start >= DATE_TRUNC('week',fu.first_use_at)::date
-),
-active_counts AS (
-  SELECT agent_id, cohort_week_start, user_lifetime_week, COUNT(DISTINCT user_id) AS active_users
-  FROM user_week_age WHERE user_lifetime_week >= 0 GROUP BY 1,2,3
-),
-cohort_sizes AS (
-  SELECT agent_id, cohort_week_start, COUNT(DISTINCT user_id) AS cohort_users FROM first_use GROUP BY 1,2
-),
-cohort_caps AS (
-  SELECT cs.agent_id, cs.cohort_week_start, cs.cohort_users,
-         LEAST((SELECT max_weeks FROM params),
-               GREATEST(0,((DATE_TRUNC('week',CURRENT_DATE)::date-cs.cohort_week_start)/7)::int)) AS cap_weeks
-  FROM cohort_sizes cs
-),
-grid AS (
-  SELECT cc.agent_id, cc.cohort_week_start, gs AS user_lifetime_week, cc.cohort_users
-  FROM cohort_caps cc CROSS JOIN LATERAL generate_series(0, cc.cap_weeks) gs
-),
-agent_names AS (SELECT DISTINCT ON (g."id") g."id" AS agent_id, g."name" AS agent_name FROM platform."AgentGraph" g ORDER BY g."id", g."version" DESC),
-agent_total_users AS (SELECT agent_id, SUM(cohort_users) AS agent_total_users FROM cohort_sizes GROUP BY 1)
-SELECT
-  g.agent_id,
-  COALESCE(an.agent_name,'(unnamed)')||' ['||LEFT(g.agent_id::text,8)||']'  AS agent_label,
-  COALESCE(an.agent_name,'(unnamed)')||' ['||LEFT(g.agent_id::text,8)||'] (n='||COALESCE(atu.agent_total_users,0)||')' AS agent_label_n,
-  g.cohort_week_start,
-  TO_CHAR(g.cohort_week_start,'IYYY-"W"IW')                               AS cohort_label,
-  TO_CHAR(g.cohort_week_start,'IYYY-"W"IW')||' (n='||g.cohort_users||')'  AS cohort_label_n,
-  g.user_lifetime_week, g.cohort_users,
-  COALESCE(ac.active_users,0)                                              AS active_users,
-  COALESCE(ac.active_users,0)::float / NULLIF(g.cohort_users,0)           AS retention_rate,
-  CASE WHEN g.user_lifetime_week=0 THEN g.cohort_users ELSE 0 END         AS cohort_users_w0,
-  COALESCE(atu.agent_total_users,0)                                        AS agent_total_users
-FROM grid g
-LEFT JOIN active_counts     ac  ON ac.agent_id=g.agent_id AND ac.cohort_week_start=g.cohort_week_start AND ac.user_lifetime_week=g.user_lifetime_week
-LEFT JOIN agent_names       an  ON an.agent_id=g.agent_id
-LEFT JOIN agent_total_users atu ON atu.agent_id=g.agent_id
-ORDER BY agent_label, g.cohort_week_start, g.user_lifetime_week;

autogpt_platform/analytics/queries/retention_execution_daily.sql

@@ -1,81 +0,0 @@
--- =============================================================
--- View: analytics.retention_execution_daily
--- Looker source alias: ds111  |  Charts: 1
--- =============================================================
--- DESCRIPTION
---   Daily cohort retention based on agent executions.
---   Cohort anchor = day of user's FIRST ever execution.
---   Only includes cohorts from the last 90 days, up to day 30.
---   Great for early engagement analysis (did users run another
---   agent the next day?).
---
--- SOURCE TABLES
---   platform.AgentGraphExecution  — Execution records
---
--- OUTPUT COLUMNS
---   Same pattern as retention_login_daily.
---   cohort_day_start = day of first execution (not first login)
---
--- EXAMPLE QUERIES
---   -- Day-3 execution retention
---   SELECT cohort_label, retention_rate_bounded AS d3_retention
---   FROM analytics.retention_execution_daily
---   WHERE user_lifetime_day = 3 ORDER BY cohort_day_start;
--- =============================================================
-
-WITH params AS (SELECT 30::int AS max_days, (CURRENT_DATE - INTERVAL '90 days') AS cohort_start),
-events AS (
-  SELECT e."userId"::text AS user_id, e."createdAt"::timestamptz AS created_at,
-         DATE_TRUNC('day', e."createdAt")::date AS day_start
-  FROM platform."AgentGraphExecution" e WHERE e."userId" IS NOT NULL
-),
-first_exec AS (
-  SELECT user_id, MIN(created_at) AS first_exec_at,
-         DATE_TRUNC('day', MIN(created_at))::date AS cohort_day_start
-  FROM events GROUP BY 1
-  HAVING MIN(created_at) >= (SELECT cohort_start FROM params)
-),
-activity_days AS (SELECT DISTINCT user_id, day_start FROM events),
-user_day_age AS (
-  SELECT ad.user_id, fe.cohort_day_start,
-         (ad.day_start - DATE_TRUNC('day',fe.first_exec_at)::date)::int AS user_lifetime_day
-  FROM activity_days ad JOIN first_exec fe USING (user_id)
-  WHERE ad.day_start >= DATE_TRUNC('day',fe.first_exec_at)::date
-),
-bounded_counts AS (
-  SELECT cohort_day_start, user_lifetime_day, COUNT(DISTINCT user_id) AS active_users_bounded
-  FROM user_day_age WHERE user_lifetime_day >= 0 GROUP BY 1,2
-),
-last_active AS (
-  SELECT cohort_day_start, user_id, MAX(user_lifetime_day) AS last_active_day FROM user_day_age GROUP BY 1,2
-),
-unbounded_counts AS (
-  SELECT la.cohort_day_start, gs AS user_lifetime_day, COUNT(*) AS retained_users_unbounded
-  FROM last_active la
-  CROSS JOIN LATERAL generate_series(0, LEAST(la.last_active_day,(SELECT max_days FROM params))) gs
-  GROUP BY 1,2
-),
-cohort_sizes AS (SELECT cohort_day_start, COUNT(DISTINCT user_id) AS cohort_users FROM first_exec GROUP BY 1),
-cohort_caps AS (
-  SELECT cs.cohort_day_start, cs.cohort_users,
-         LEAST((SELECT max_days FROM params), GREATEST(0,(CURRENT_DATE-cs.cohort_day_start)::int)) AS cap_days
-  FROM cohort_sizes cs
-),
-grid AS (
-  SELECT cc.cohort_day_start, gs AS user_lifetime_day, cc.cohort_users
-  FROM cohort_caps cc CROSS JOIN LATERAL generate_series(0, cc.cap_days) gs
-)
-SELECT
-  g.cohort_day_start,
-  TO_CHAR(g.cohort_day_start,'YYYY-MM-DD')                                AS cohort_label,
-  TO_CHAR(g.cohort_day_start,'YYYY-MM-DD')||' (n='||g.cohort_users||')'   AS cohort_label_n,
-  g.user_lifetime_day, g.cohort_users,
-  COALESCE(b.active_users_bounded,0)     AS active_users_bounded,
-  COALESCE(u.retained_users_unbounded,0) AS retained_users_unbounded,
-  CASE WHEN g.cohort_users>0 THEN COALESCE(b.active_users_bounded,0)::float/g.cohort_users END    AS retention_rate_bounded,
-  CASE WHEN g.cohort_users>0 THEN COALESCE(u.retained_users_unbounded,0)::float/g.cohort_users END AS retention_rate_unbounded,
-  CASE WHEN g.user_lifetime_day=0 THEN g.cohort_users ELSE 0 END          AS cohort_users_d0
-FROM grid g
-LEFT JOIN bounded_counts   b ON b.cohort_day_start=g.cohort_day_start AND b.user_lifetime_day=g.user_lifetime_day
-LEFT JOIN unbounded_counts u ON u.cohort_day_start=g.cohort_day_start AND u.user_lifetime_day=g.user_lifetime_day
-ORDER BY g.cohort_day_start, g.user_lifetime_day;

autogpt_platform/analytics/queries/retention_execution_weekly.sql

@@ -1,81 +0,0 @@
--- =============================================================
--- View: analytics.retention_execution_weekly
--- Looker source alias: ds92  |  Charts: 2
--- =============================================================
--- DESCRIPTION
---   Weekly cohort retention based on agent executions.
---   Cohort anchor = week of user's FIRST ever agent execution
---   (not first login). Only includes cohorts from the last 180 days.
---   Useful when you care about product engagement, not just visits.
---
--- SOURCE TABLES
---   platform.AgentGraphExecution  — Execution records
---
--- OUTPUT COLUMNS
---   Same pattern as retention_login_weekly.
---   cohort_week_start = week of first execution (not first login)
---
--- EXAMPLE QUERIES
---   -- Week-2 execution retention
---   SELECT cohort_label, retention_rate_bounded
---   FROM analytics.retention_execution_weekly
---   WHERE user_lifetime_week = 2 ORDER BY cohort_week_start;
--- =============================================================
-
-WITH params AS (SELECT 12::int AS max_weeks, (CURRENT_DATE - INTERVAL '180 days') AS cohort_start),
-events AS (
-  SELECT e."userId"::text AS user_id, e."createdAt"::timestamptz AS created_at,
-         DATE_TRUNC('week', e."createdAt")::date AS week_start
-  FROM platform."AgentGraphExecution" e WHERE e."userId" IS NOT NULL
-),
-first_exec AS (
-  SELECT user_id, MIN(created_at) AS first_exec_at,
-         DATE_TRUNC('week', MIN(created_at))::date AS cohort_week_start
-  FROM events GROUP BY 1
-  HAVING MIN(created_at) >= (SELECT cohort_start FROM params)
-),
-activity_weeks AS (SELECT DISTINCT user_id, week_start FROM events),
-user_week_age AS (
-  SELECT aw.user_id, fe.cohort_week_start,
-         ((aw.week_start - DATE_TRUNC('week',fe.first_exec_at)::date)/7)::int AS user_lifetime_week
-  FROM activity_weeks aw JOIN first_exec fe USING (user_id)
-  WHERE aw.week_start >= DATE_TRUNC('week',fe.first_exec_at)::date
-),
-bounded_counts AS (
-  SELECT cohort_week_start, user_lifetime_week, COUNT(DISTINCT user_id) AS active_users_bounded
-  FROM user_week_age WHERE user_lifetime_week >= 0 GROUP BY 1,2
-),
-last_active AS (
-  SELECT cohort_week_start, user_id, MAX(user_lifetime_week) AS last_active_week FROM user_week_age GROUP BY 1,2
-),
-unbounded_counts AS (
-  SELECT la.cohort_week_start, gs AS user_lifetime_week, COUNT(*) AS retained_users_unbounded
-  FROM last_active la
-  CROSS JOIN LATERAL generate_series(0, LEAST(la.last_active_week,(SELECT max_weeks FROM params))) gs
-  GROUP BY 1,2
-),
-cohort_sizes AS (SELECT cohort_week_start, COUNT(DISTINCT user_id) AS cohort_users FROM first_exec GROUP BY 1),
-cohort_caps AS (
-  SELECT cs.cohort_week_start, cs.cohort_users,
-         LEAST((SELECT max_weeks FROM params),
-               GREATEST(0,((DATE_TRUNC('week',CURRENT_DATE)::date-cs.cohort_week_start)/7)::int)) AS cap_weeks
-  FROM cohort_sizes cs
-),
-grid AS (
-  SELECT cc.cohort_week_start, gs AS user_lifetime_week, cc.cohort_users
-  FROM cohort_caps cc CROSS JOIN LATERAL generate_series(0, cc.cap_weeks) gs
-)
-SELECT
-  g.cohort_week_start,
-  TO_CHAR(g.cohort_week_start,'IYYY-"W"IW')                               AS cohort_label,
-  TO_CHAR(g.cohort_week_start,'IYYY-"W"IW')||' (n='||g.cohort_users||')'  AS cohort_label_n,
-  g.user_lifetime_week, g.cohort_users,
-  COALESCE(b.active_users_bounded,0)     AS active_users_bounded,
-  COALESCE(u.retained_users_unbounded,0) AS retained_users_unbounded,
-  CASE WHEN g.cohort_users>0 THEN COALESCE(b.active_users_bounded,0)::float/g.cohort_users END    AS retention_rate_bounded,
-  CASE WHEN g.cohort_users>0 THEN COALESCE(u.retained_users_unbounded,0)::float/g.cohort_users END AS retention_rate_unbounded,
-  CASE WHEN g.user_lifetime_week=0 THEN g.cohort_users ELSE 0 END         AS cohort_users_w0
-FROM grid g
-LEFT JOIN bounded_counts   b ON b.cohort_week_start=g.cohort_week_start AND b.user_lifetime_week=g.user_lifetime_week
-LEFT JOIN unbounded_counts u ON u.cohort_week_start=g.cohort_week_start AND u.user_lifetime_week=g.user_lifetime_week
-ORDER BY g.cohort_week_start, g.user_lifetime_week;

autogpt_platform/analytics/queries/retention_login_daily.sql

@@ -1,94 +0,0 @@
--- =============================================================
--- View: analytics.retention_login_daily
--- Looker source alias: ds112  |  Charts: 1
--- =============================================================
--- DESCRIPTION
---   Daily cohort retention based on login sessions.
---   Same logic as retention_login_weekly but at day granularity,
---   showing up to day 30 for cohorts from the last 90 days.
---   Useful for analysing early activation (days 1-7) in detail.
---
--- SOURCE TABLES
---   auth.sessions  — Login session records
---
--- OUTPUT COLUMNS (same pattern as retention_login_weekly)
---   cohort_day_start          DATE     First day the cohort logged in
---   cohort_label              TEXT     Date string (e.g. '2025-03-01')
---   cohort_label_n            TEXT     Date + cohort size (e.g. '2025-03-01 (n=12)')
---   user_lifetime_day         INT      Days since first login (0 = signup day)
---   cohort_users              BIGINT   Total users in cohort
---   active_users_bounded      BIGINT   Users active on exactly day k
---   retained_users_unbounded  BIGINT   Users active any time on/after day k
---   retention_rate_bounded    FLOAT    bounded / cohort_users
---   retention_rate_unbounded  FLOAT    unbounded / cohort_users
---   cohort_users_d0           BIGINT   cohort_users only at day 0, else 0 (safe to SUM)
---
--- EXAMPLE QUERIES
---   -- Day-1 retention rate (came back next day)
---   SELECT cohort_label, retention_rate_bounded AS d1_retention
---   FROM analytics.retention_login_daily
---   WHERE user_lifetime_day = 1 ORDER BY cohort_day_start;
---
---   -- Average retention curve across all cohorts
---   SELECT user_lifetime_day,
---          SUM(active_users_bounded)::float / NULLIF(SUM(cohort_users_d0), 0) AS avg_retention
---   FROM analytics.retention_login_daily
---   GROUP BY 1 ORDER BY 1;
--- =============================================================
-
-WITH params AS (SELECT 30::int AS max_days, (CURRENT_DATE - INTERVAL '90 days')::date AS cohort_start),
-events AS (
-  SELECT s.user_id::text AS user_id, s.created_at::timestamptz AS created_at,
-         DATE_TRUNC('day', s.created_at)::date AS day_start
-  FROM auth.sessions s WHERE s.user_id IS NOT NULL
-),
-first_login AS (
-  SELECT user_id, MIN(created_at) AS first_login_time,
-         DATE_TRUNC('day', MIN(created_at))::date AS cohort_day_start
-  FROM events GROUP BY 1
-  HAVING MIN(created_at) >= (SELECT cohort_start FROM params)
-),
-activity_days AS (SELECT DISTINCT user_id, day_start FROM events),
-user_day_age AS (
-  SELECT ad.user_id, fl.cohort_day_start,
-         (ad.day_start - DATE_TRUNC('day', fl.first_login_time)::date)::int AS user_lifetime_day
-  FROM activity_days ad JOIN first_login fl USING (user_id)
-  WHERE ad.day_start >= DATE_TRUNC('day', fl.first_login_time)::date
-),
-bounded_counts AS (
-  SELECT cohort_day_start, user_lifetime_day, COUNT(DISTINCT user_id) AS active_users_bounded
-  FROM user_day_age WHERE user_lifetime_day >= 0 GROUP BY 1,2
-),
-last_active AS (
-  SELECT cohort_day_start, user_id, MAX(user_lifetime_day) AS last_active_day FROM user_day_age GROUP BY 1,2
-),
-unbounded_counts AS (
-  SELECT la.cohort_day_start, gs AS user_lifetime_day, COUNT(*) AS retained_users_unbounded
-  FROM last_active la
-  CROSS JOIN LATERAL generate_series(0, LEAST(la.last_active_day,(SELECT max_days FROM params))) gs
-  GROUP BY 1,2
-),
-cohort_sizes AS (SELECT cohort_day_start, COUNT(DISTINCT user_id) AS cohort_users FROM first_login GROUP BY 1),
-cohort_caps AS (
-  SELECT cs.cohort_day_start, cs.cohort_users,
-         LEAST((SELECT max_days FROM params), GREATEST(0,(CURRENT_DATE-cs.cohort_day_start)::int)) AS cap_days
-  FROM cohort_sizes cs
-),
-grid AS (
-  SELECT cc.cohort_day_start, gs AS user_lifetime_day, cc.cohort_users
-  FROM cohort_caps cc CROSS JOIN LATERAL generate_series(0, cc.cap_days) gs
-)
-SELECT
-  g.cohort_day_start,
-  TO_CHAR(g.cohort_day_start,'YYYY-MM-DD')                                  AS cohort_label,
-  TO_CHAR(g.cohort_day_start,'YYYY-MM-DD')||' (n='||g.cohort_users||')'     AS cohort_label_n,
-  g.user_lifetime_day, g.cohort_users,
-  COALESCE(b.active_users_bounded,0)     AS active_users_bounded,
-  COALESCE(u.retained_users_unbounded,0) AS retained_users_unbounded,
-  CASE WHEN g.cohort_users>0 THEN COALESCE(b.active_users_bounded,0)::float/g.cohort_users END    AS retention_rate_bounded,
-  CASE WHEN g.cohort_users>0 THEN COALESCE(u.retained_users_unbounded,0)::float/g.cohort_users END AS retention_rate_unbounded,
-  CASE WHEN g.user_lifetime_day=0 THEN g.cohort_users ELSE 0 END            AS cohort_users_d0
-FROM grid g
-LEFT JOIN bounded_counts   b ON b.cohort_day_start=g.cohort_day_start AND b.user_lifetime_day=g.user_lifetime_day
-LEFT JOIN unbounded_counts u ON u.cohort_day_start=g.cohort_day_start AND u.user_lifetime_day=g.user_lifetime_day
-ORDER BY g.cohort_day_start, g.user_lifetime_day;

autogpt_platform/analytics/queries/retention_login_onboarded_weekly.sql

@@ -1,96 +0,0 @@
--- =============================================================
--- View: analytics.retention_login_onboarded_weekly
--- Looker source alias: ds101  |  Charts: 2
--- =============================================================
--- DESCRIPTION
---   Weekly cohort retention from login sessions, restricted to
---   users who "onboarded" — defined as running at least one
---   agent within 365 days of their first login.
---   Filters out users who signed up but never activated,
---   giving a cleaner view of engaged-user retention.
---
--- SOURCE TABLES
---   auth.sessions                  — Login session records
---   platform.AgentGraphExecution   — Used to identify onboarders
---
--- OUTPUT COLUMNS
---   Same as retention_login_weekly (cohort_week_start, user_lifetime_week,
---   retention_rate_bounded, retention_rate_unbounded, etc.)
---   Only difference: cohort is filtered to onboarded users only.
---
--- EXAMPLE QUERIES
---   -- Compare week-4 retention: all users vs onboarded only
---   SELECT 'all_users' AS segment, AVG(retention_rate_bounded) AS w4_retention
---   FROM analytics.retention_login_weekly WHERE user_lifetime_week = 4
---   UNION ALL
---   SELECT 'onboarded', AVG(retention_rate_bounded)
---   FROM analytics.retention_login_onboarded_weekly WHERE user_lifetime_week = 4;
--- =============================================================
-
-WITH params AS (SELECT 12::int AS max_weeks, 365::int AS onboarding_window_days),
-events AS (
-  SELECT s.user_id::text AS user_id, s.created_at::timestamptz AS created_at,
-         DATE_TRUNC('week', s.created_at)::date AS week_start
-  FROM auth.sessions s WHERE s.user_id IS NOT NULL
-),
-first_login_all AS (
-  SELECT user_id, MIN(created_at) AS first_login_time,
-         DATE_TRUNC('week', MIN(created_at))::date AS cohort_week_start
-  FROM events GROUP BY 1
-),
-onboarders AS (
-  SELECT fl.user_id FROM first_login_all fl
-  WHERE EXISTS (
-    SELECT 1 FROM platform."AgentGraphExecution" e
-    WHERE e."userId"::text = fl.user_id
-      AND e."createdAt" >= fl.first_login_time
-      AND e."createdAt" < fl.first_login_time
-          + make_interval(days => (SELECT onboarding_window_days FROM params))
-  )
-),
-first_login AS (SELECT * FROM first_login_all WHERE user_id IN (SELECT user_id FROM onboarders)),
-activity_weeks AS (SELECT DISTINCT user_id, week_start FROM events),
-user_week_age AS (
-  SELECT aw.user_id, fl.cohort_week_start,
-         ((aw.week_start - DATE_TRUNC('week',fl.first_login_time)::date)/7)::int AS user_lifetime_week
-  FROM activity_weeks aw JOIN first_login fl USING (user_id)
-  WHERE aw.week_start >= DATE_TRUNC('week',fl.first_login_time)::date
-),
-bounded_counts AS (
-  SELECT cohort_week_start, user_lifetime_week, COUNT(DISTINCT user_id) AS active_users_bounded
-  FROM user_week_age WHERE user_lifetime_week >= 0 GROUP BY 1,2
-),
-last_active AS (
-  SELECT cohort_week_start, user_id, MAX(user_lifetime_week) AS last_active_week FROM user_week_age GROUP BY 1,2
-),
-unbounded_counts AS (
-  SELECT la.cohort_week_start, gs AS user_lifetime_week, COUNT(*) AS retained_users_unbounded
-  FROM last_active la
-  CROSS JOIN LATERAL generate_series(0, LEAST(la.last_active_week,(SELECT max_weeks FROM params))) gs
-  GROUP BY 1,2
-),
-cohort_sizes AS (SELECT cohort_week_start, COUNT(DISTINCT user_id) AS cohort_users FROM first_login GROUP BY 1),
-cohort_caps AS (
-  SELECT cs.cohort_week_start, cs.cohort_users,
-         LEAST((SELECT max_weeks FROM params),
-               GREATEST(0,((DATE_TRUNC('week',CURRENT_DATE)::date-cs.cohort_week_start)/7)::int)) AS cap_weeks
-  FROM cohort_sizes cs
-),
-grid AS (
-  SELECT cc.cohort_week_start, gs AS user_lifetime_week, cc.cohort_users
-  FROM cohort_caps cc CROSS JOIN LATERAL generate_series(0, cc.cap_weeks) gs
-)
-SELECT
-  g.cohort_week_start,
-  TO_CHAR(g.cohort_week_start,'IYYY-"W"IW')                               AS cohort_label,
-  TO_CHAR(g.cohort_week_start,'IYYY-"W"IW')||' (n='||g.cohort_users||')'  AS cohort_label_n,
-  g.user_lifetime_week, g.cohort_users,
-  COALESCE(b.active_users_bounded,0)     AS active_users_bounded,
-  COALESCE(u.retained_users_unbounded,0) AS retained_users_unbounded,
-  CASE WHEN g.cohort_users>0 THEN COALESCE(b.active_users_bounded,0)::float/g.cohort_users END    AS retention_rate_bounded,
-  CASE WHEN g.cohort_users>0 THEN COALESCE(u.retained_users_unbounded,0)::float/g.cohort_users END AS retention_rate_unbounded,
-  CASE WHEN g.user_lifetime_week=0 THEN g.cohort_users ELSE 0 END         AS cohort_users_w0
-FROM grid g
-LEFT JOIN bounded_counts   b ON b.cohort_week_start=g.cohort_week_start AND b.user_lifetime_week=g.user_lifetime_week
-LEFT JOIN unbounded_counts u ON u.cohort_week_start=g.cohort_week_start AND u.user_lifetime_week=g.user_lifetime_week
-ORDER BY g.cohort_week_start, g.user_lifetime_week;

autogpt_platform/analytics/queries/retention_login_weekly.sql

@@ -1,103 +0,0 @@
--- =============================================================
--- View: analytics.retention_login_weekly
--- Looker source alias: ds83  |  Charts: 2
--- =============================================================
--- DESCRIPTION
---   Weekly cohort retention based on login sessions.
---   Users are grouped by the ISO week of their first ever login.
---   For each cohort × lifetime-week combination, outputs both:
---     - bounded rate: % active in exactly that week
---     - unbounded rate: % who were ever active on or after that week
---   Weeks are capped to the cohort's actual age (no future data points).
---
--- SOURCE TABLES
---   auth.sessions  — Login session records
---
--- HOW TO READ THE OUTPUT
---   cohort_week_start   The Monday of the week users first logged in
---   user_lifetime_week  0 = signup week, 1 = one week later, etc.
---   retention_rate_bounded   = active_users_bounded / cohort_users
---   retention_rate_unbounded = retained_users_unbounded / cohort_users
---
--- OUTPUT COLUMNS
---   cohort_week_start         DATE     First day of the cohort's signup week
---   cohort_label              TEXT     ISO week label (e.g. '2025-W01')
---   cohort_label_n            TEXT     ISO week label with cohort size (e.g. '2025-W01 (n=42)')
---   user_lifetime_week        INT      Weeks since first login (0 = signup week)
---   cohort_users              BIGINT   Total users in this cohort (denominator)
---   active_users_bounded      BIGINT   Users active in exactly week k
---   retained_users_unbounded  BIGINT   Users active any time on/after week k
---   retention_rate_bounded    FLOAT    bounded active / cohort_users
---   retention_rate_unbounded  FLOAT    unbounded retained / cohort_users
---   cohort_users_w0           BIGINT   cohort_users only at week 0, else 0 (safe to SUM in pivot tables)
---
--- EXAMPLE QUERIES
---   -- Week-1 retention rate per cohort
---   SELECT cohort_label, retention_rate_bounded AS w1_retention
---   FROM analytics.retention_login_weekly
---   WHERE user_lifetime_week = 1
---   ORDER BY cohort_week_start;
---
---   -- Overall average retention curve (all cohorts combined)
---   SELECT user_lifetime_week,
---          SUM(active_users_bounded)::float / NULLIF(SUM(cohort_users_w0), 0) AS avg_retention
---   FROM analytics.retention_login_weekly
---   GROUP BY 1 ORDER BY 1;
--- =============================================================
-
-WITH params AS (SELECT 12::int AS max_weeks),
-events AS (
-  SELECT s.user_id::text AS user_id, s.created_at::timestamptz AS created_at,
-         DATE_TRUNC('week', s.created_at)::date AS week_start
-  FROM auth.sessions s WHERE s.user_id IS NOT NULL
-),
-first_login AS (
-  SELECT user_id, MIN(created_at) AS first_login_time,
-         DATE_TRUNC('week', MIN(created_at))::date AS cohort_week_start
-  FROM events GROUP BY 1
-),
-activity_weeks AS (SELECT DISTINCT user_id, week_start FROM events),
-user_week_age AS (
-  SELECT aw.user_id, fl.cohort_week_start,
-         ((aw.week_start - DATE_TRUNC('week', fl.first_login_time)::date) / 7)::int AS user_lifetime_week
-  FROM activity_weeks aw JOIN first_login fl USING (user_id)
-  WHERE aw.week_start >= DATE_TRUNC('week', fl.first_login_time)::date
-),
-bounded_counts AS (
-  SELECT cohort_week_start, user_lifetime_week, COUNT(DISTINCT user_id) AS active_users_bounded
-  FROM user_week_age WHERE user_lifetime_week >= 0 GROUP BY 1,2
-),
-last_active AS (
-  SELECT cohort_week_start, user_id, MAX(user_lifetime_week) AS last_active_week FROM user_week_age GROUP BY 1,2
-),
-unbounded_counts AS (
-  SELECT la.cohort_week_start, gs AS user_lifetime_week, COUNT(*) AS retained_users_unbounded
-  FROM last_active la
-  CROSS JOIN LATERAL generate_series(0, LEAST(la.last_active_week,(SELECT max_weeks FROM params))) gs
-  GROUP BY 1,2
-),
-cohort_sizes AS (SELECT cohort_week_start, COUNT(DISTINCT user_id) AS cohort_users FROM first_login GROUP BY 1),
-cohort_caps AS (
-  SELECT cs.cohort_week_start, cs.cohort_users,
-         LEAST((SELECT max_weeks FROM params),
-               GREATEST(0,((DATE_TRUNC('week',CURRENT_DATE)::date - cs.cohort_week_start)/7)::int)) AS cap_weeks
-  FROM cohort_sizes cs
-),
-grid AS (
-  SELECT cc.cohort_week_start, gs AS user_lifetime_week, cc.cohort_users
-  FROM cohort_caps cc CROSS JOIN LATERAL generate_series(0, cc.cap_weeks) gs
-)
-SELECT
-  g.cohort_week_start,
-  TO_CHAR(g.cohort_week_start,'IYYY-"W"IW')                                    AS cohort_label,
-  TO_CHAR(g.cohort_week_start,'IYYY-"W"IW')||' (n='||g.cohort_users||')'       AS cohort_label_n,
-  g.user_lifetime_week, g.cohort_users,
-  COALESCE(b.active_users_bounded,0)     AS active_users_bounded,
-  COALESCE(u.retained_users_unbounded,0) AS retained_users_unbounded,
-  CASE WHEN g.cohort_users>0 THEN COALESCE(b.active_users_bounded,0)::float/g.cohort_users END    AS retention_rate_bounded,
-  CASE WHEN g.cohort_users>0 THEN COALESCE(u.retained_users_unbounded,0)::float/g.cohort_users END AS retention_rate_unbounded,
-  CASE WHEN g.user_lifetime_week=0 THEN g.cohort_users ELSE 0 END               AS cohort_users_w0
-FROM grid g
-LEFT JOIN bounded_counts   b ON b.cohort_week_start=g.cohort_week_start AND b.user_lifetime_week=g.user_lifetime_week
-LEFT JOIN unbounded_counts u ON u.cohort_week_start=g.cohort_week_start AND u.user_lifetime_week=g.user_lifetime_week
-ORDER BY g.cohort_week_start, g.user_lifetime_week

autogpt_platform/analytics/queries/user_block_spending.sql

@@ -1,71 +0,0 @@
--- =============================================================
--- View: analytics.user_block_spending
--- Looker source alias: ds6  |  Charts: 5
--- =============================================================
--- DESCRIPTION
---   One row per credit transaction (last 90 days).
---   Shows how users spend credits broken down by block type,
---   LLM provider and model.  Joins node execution stats for
---   token-level detail.
---
--- SOURCE TABLES
---   platform.CreditTransaction   — Credit debit/credit records
---   platform.AgentNodeExecution  — Node execution stats (for token counts)
---
--- OUTPUT COLUMNS
---   transactionKey        TEXT         Unique transaction identifier
---   userId                TEXT         User who was charged
---   amount                DECIMAL      Credit amount (positive = credit, negative = debit)
---   negativeAmount        DECIMAL      amount * -1 (convenience for spend charts)
---   transactionType       TEXT         Transaction type (e.g. 'USAGE', 'REFUND', 'TOP_UP')
---   transactionTime       TIMESTAMPTZ  When the transaction was recorded
---   blockId               TEXT         Block UUID that triggered the spend
---   blockName             TEXT         Human-readable block name
---   llm_provider          TEXT         LLM provider (e.g. 'openai', 'anthropic')
---   llm_model             TEXT         Model name (e.g. 'gpt-4o', 'claude-3-5-sonnet')
---   node_exec_id          TEXT         Linked node execution UUID
---   llm_call_count        INT          LLM API calls made in that execution
---   llm_retry_count       INT          LLM retries in that execution
---   llm_input_token_count INT          Input tokens consumed
---   llm_output_token_count INT         Output tokens produced
---
--- WINDOW
---   Rolling 90 days (createdAt > CURRENT_DATE - 90 days)
---
--- EXAMPLE QUERIES
---   -- Total spend per user (last 90 days)
---   SELECT "userId", SUM("negativeAmount") AS total_spent
---   FROM analytics.user_block_spending
---   WHERE "transactionType" = 'USAGE'
---   GROUP BY 1 ORDER BY total_spent DESC;
---
---   -- Spend by LLM provider + model
---   SELECT "llm_provider", "llm_model",
---          SUM("negativeAmount") AS total_cost,
---          SUM("llm_input_token_count") AS input_tokens,
---          SUM("llm_output_token_count") AS output_tokens
---   FROM analytics.user_block_spending
---   WHERE "llm_provider" IS NOT NULL
---   GROUP BY 1, 2 ORDER BY total_cost DESC;
--- =============================================================
-
-SELECT
-    c."transactionKey"                                        AS transactionKey,
-    c."userId"                                                AS userId,
-    c."amount"                                                AS amount,
-    c."amount" * -1                                           AS negativeAmount,
-    c."type"                                                  AS transactionType,
-    c."createdAt"                                             AS transactionTime,
-    c.metadata->>'block_id'                                   AS blockId,
-    c.metadata->>'block'                                      AS blockName,
-    c.metadata->'input'->'credentials'->>'provider'           AS llm_provider,
-    c.metadata->'input'->>'model'                             AS llm_model,
-    c.metadata->>'node_exec_id'                               AS node_exec_id,
-    (ne."stats"->>'llm_call_count')::int                       AS llm_call_count,
-    (ne."stats"->>'llm_retry_count')::int                      AS llm_retry_count,
-    (ne."stats"->>'input_token_count')::int                    AS llm_input_token_count,
-    (ne."stats"->>'output_token_count')::int                   AS llm_output_token_count
-FROM platform."CreditTransaction" c
-LEFT JOIN platform."AgentNodeExecution" ne
-       ON (c.metadata->>'node_exec_id') = ne."id"::text
-WHERE c."createdAt" > CURRENT_DATE - INTERVAL '90 days'

autogpt_platform/analytics/queries/user_onboarding.sql

@@ -1,45 +0,0 @@
--- =============================================================
--- View: analytics.user_onboarding
--- Looker source alias: ds68  |  Charts: 3
--- =============================================================
--- DESCRIPTION
---   One row per user onboarding record.  Contains the user's
---   stated usage reason, selected integrations, completed
---   onboarding steps and optional first agent selection.
---   Full history (no date filter) since onboarding happens
---   once per user.
---
--- SOURCE TABLES
---   platform.UserOnboarding  — Onboarding state per user
---
--- OUTPUT COLUMNS
---   id                            TEXT         Onboarding record UUID
---   createdAt                     TIMESTAMPTZ  When onboarding started
---   updatedAt                     TIMESTAMPTZ  Last update to onboarding state
---   usageReason                   TEXT         Why user signed up (e.g. 'work', 'personal')
---   integrations                  TEXT[]       Array of integration names the user selected
---   userId                        TEXT         User UUID
---   completedSteps                TEXT[]       Array of onboarding step enums completed
---   selectedStoreListingVersionId TEXT         First marketplace agent the user chose (if any)
---
--- EXAMPLE QUERIES
---   -- Usage reason breakdown
---   SELECT "usageReason", COUNT(*) FROM analytics.user_onboarding GROUP BY 1;
---
---   -- Completion rate per step
---   SELECT step, COUNT(*) AS users_completed
---   FROM analytics.user_onboarding
---   CROSS JOIN LATERAL UNNEST("completedSteps") AS step
---   GROUP BY 1 ORDER BY users_completed DESC;
--- =============================================================
-
-SELECT
-    id,
-    "createdAt",
-    "updatedAt",
-    "usageReason",
-    integrations,
-    "userId",
-    "completedSteps",
-    "selectedStoreListingVersionId"
-FROM platform."UserOnboarding"

autogpt_platform/analytics/queries/user_onboarding_funnel.sql

@@ -1,100 +0,0 @@
--- =============================================================
--- View: analytics.user_onboarding_funnel
--- Looker source alias: ds74  |  Charts: 1
--- =============================================================
--- DESCRIPTION
---   Pre-aggregated onboarding funnel showing how many users
---   completed each step and the drop-off percentage from the
---   previous step.  One row per onboarding step (all 22 steps
---   always present, even with 0 completions — prevents sparse
---   gaps from making LAG compare the wrong predecessors).
---
--- SOURCE TABLES
---   platform.UserOnboarding  — Onboarding records with completedSteps array
---
--- OUTPUT COLUMNS
---   step             TEXT     Onboarding step enum name (e.g. 'WELCOME', 'CONGRATS')
---   step_order       INT      Numeric position in the funnel (1=first, 22=last)
---   users_completed  BIGINT   Distinct users who completed this step
---   pct_from_prev    NUMERIC  % of users from the previous step who reached this one
---
--- STEP ORDER
---   1  WELCOME               9  MARKETPLACE_VISIT     17  SCHEDULE_AGENT
---   2  USAGE_REASON         10  MARKETPLACE_ADD_AGENT  18  RUN_AGENTS
---   3  INTEGRATIONS         11  MARKETPLACE_RUN_AGENT  19  RUN_3_DAYS
---   4  AGENT_CHOICE         12  BUILDER_OPEN           20  TRIGGER_WEBHOOK
---   5  AGENT_NEW_RUN        13  BUILDER_SAVE_AGENT     21  RUN_14_DAYS
---   6  AGENT_INPUT          14  BUILDER_RUN_AGENT      22  RUN_AGENTS_100
---   7  CONGRATS             15  VISIT_COPILOT
---   8  GET_RESULTS          16  RE_RUN_AGENT
---
--- WINDOW
---   Users who started onboarding in the last 90 days
---
--- EXAMPLE QUERIES
---   -- Full funnel
---   SELECT * FROM analytics.user_onboarding_funnel ORDER BY step_order;
---
---   -- Biggest drop-off point
---   SELECT step, pct_from_prev FROM analytics.user_onboarding_funnel
---   ORDER BY pct_from_prev ASC LIMIT 3;
--- =============================================================
-
-WITH all_steps AS (
-  -- Complete ordered grid of all 22 steps so zero-completion steps
-  -- are always present, keeping LAG comparisons correct.
-  SELECT step_name, step_order
-  FROM (VALUES
-    ('WELCOME',               1),
-    ('USAGE_REASON',          2),
-    ('INTEGRATIONS',          3),
-    ('AGENT_CHOICE',          4),
-    ('AGENT_NEW_RUN',         5),
-    ('AGENT_INPUT',           6),
-    ('CONGRATS',              7),
-    ('GET_RESULTS',           8),
-    ('MARKETPLACE_VISIT',     9),
-    ('MARKETPLACE_ADD_AGENT', 10),
-    ('MARKETPLACE_RUN_AGENT', 11),
-    ('BUILDER_OPEN',          12),
-    ('BUILDER_SAVE_AGENT',    13),
-    ('BUILDER_RUN_AGENT',     14),
-    ('VISIT_COPILOT',         15),
-    ('RE_RUN_AGENT',          16),
-    ('SCHEDULE_AGENT',        17),
-    ('RUN_AGENTS',            18),
-    ('RUN_3_DAYS',            19),
-    ('TRIGGER_WEBHOOK',       20),
-    ('RUN_14_DAYS',           21),
-    ('RUN_AGENTS_100',        22)
-  ) AS t(step_name, step_order)
-),
-raw AS (
-  SELECT
-      u."userId",
-      step_txt::text AS step
-  FROM platform."UserOnboarding" u
-  CROSS JOIN LATERAL UNNEST(u."completedSteps") AS step_txt
-  WHERE u."createdAt" >= CURRENT_DATE - INTERVAL '90 days'
-),
-step_counts AS (
-  SELECT step, COUNT(DISTINCT "userId") AS users_completed
-  FROM raw GROUP BY step
-),
-funnel AS (
-  SELECT
-      a.step_name                          AS step,
-      a.step_order,
-      COALESCE(sc.users_completed, 0)      AS users_completed,
-      ROUND(
-        100.0 * COALESCE(sc.users_completed, 0)
-        / NULLIF(
-            LAG(COALESCE(sc.users_completed, 0)) OVER (ORDER BY a.step_order),
-            0
-          ),
-        2
-      )                                    AS pct_from_prev
-  FROM all_steps a
-  LEFT JOIN step_counts sc ON sc.step = a.step_name
-)
-SELECT * FROM funnel ORDER BY step_order

autogpt_platform/analytics/queries/user_onboarding_integration.sql

@@ -1,41 +0,0 @@
--- =============================================================
--- View: analytics.user_onboarding_integration
--- Looker source alias: ds75  |  Charts: 1
--- =============================================================
--- DESCRIPTION
---   Pre-aggregated count of users who selected each integration
---   during onboarding.  One row per integration type, sorted
---   by popularity.
---
--- SOURCE TABLES
---   platform.UserOnboarding  — integrations array column
---
--- OUTPUT COLUMNS
---   integration            TEXT    Integration name (e.g. 'github', 'slack', 'notion')
---   users_with_integration BIGINT  Distinct users who selected this integration
---
--- WINDOW
---   Users who started onboarding in the last 90 days
---
--- EXAMPLE QUERIES
---   -- Full integration popularity ranking
---   SELECT * FROM analytics.user_onboarding_integration;
---
---   -- Top 5 integrations
---   SELECT * FROM analytics.user_onboarding_integration LIMIT 5;
--- =============================================================
-
-WITH exploded AS (
-  SELECT
-      u."userId" AS user_id,
-      UNNEST(u."integrations") AS integration
-  FROM platform."UserOnboarding" u
-  WHERE u."createdAt" >= CURRENT_DATE - INTERVAL '90 days'
-)
-SELECT
-    integration,
-    COUNT(DISTINCT user_id) AS users_with_integration
-FROM exploded
-WHERE integration IS NOT NULL AND integration <> ''
-GROUP BY integration
-ORDER BY users_with_integration DESC

autogpt_platform/analytics/queries/users_activities.sql

@@ -1,145 +0,0 @@
--- =============================================================
--- View: analytics.users_activities
--- Looker source alias: ds56  |  Charts: 5
--- =============================================================
--- DESCRIPTION
---   One row per user with lifetime activity summary.
---   Joins login sessions with agent graphs, executions and
---   node-level runs to give a full picture of how engaged
---   each user is.  Includes a convenience flag for 7-day
---   activation (did the user return at least 7 days after
---   their first login?).
---
--- SOURCE TABLES
---   auth.sessions                    — Login/session records
---   platform.AgentGraph              — Graphs (agents) built by the user
---   platform.AgentGraphExecution     — Agent run history
---   platform.AgentNodeExecution      — Individual block execution history
---
--- PERFORMANCE NOTE
---   Each CTE aggregates its own table independently by userId.
---   This avoids the fan-out that occurs when driving every join
---   from user_logins across the two largest tables
---   (AgentGraphExecution and AgentNodeExecution).
---
--- OUTPUT COLUMNS
---   user_id                   TEXT         Supabase user UUID
---   first_login_time          TIMESTAMPTZ  First ever session created_at
---   last_login_time           TIMESTAMPTZ  Most recent session created_at
---   last_visit_time           TIMESTAMPTZ  Max of last refresh or login
---   last_agent_save_time      TIMESTAMPTZ  Last time user saved an agent graph
---   agent_count               BIGINT       Number of distinct active graphs built (0 if none)
---   first_agent_run_time      TIMESTAMPTZ  First ever graph execution
---   last_agent_run_time       TIMESTAMPTZ  Most recent graph execution
---   unique_agent_runs         BIGINT       Distinct agent graphs ever run (0 if none)
---   agent_runs                BIGINT       Total graph execution count (0 if none)
---   node_execution_count      BIGINT       Total node executions across all runs
---   node_execution_failed     BIGINT       Node executions with FAILED status
---   node_execution_completed  BIGINT       Node executions with COMPLETED status
---   node_execution_terminated BIGINT       Node executions with TERMINATED status
---   node_execution_queued     BIGINT       Node executions with QUEUED status
---   node_execution_running    BIGINT       Node executions with RUNNING status
---   is_active_after_7d        INT          1=returned after day 7, 0=did not, NULL=too early to tell
---   node_execution_incomplete BIGINT       Node executions with INCOMPLETE status
---   node_execution_review     BIGINT       Node executions with REVIEW status
---
--- EXAMPLE QUERIES
---   -- Users who ran at least one agent and returned after 7 days
---   SELECT COUNT(*) FROM analytics.users_activities
---   WHERE agent_runs > 0 AND is_active_after_7d = 1;
---
---   -- Top 10 most active users by agent runs
---   SELECT user_id, agent_runs, node_execution_count
---   FROM analytics.users_activities
---   ORDER BY agent_runs DESC LIMIT 10;
---
---   -- 7-day activation rate
---   SELECT
---     SUM(CASE WHEN is_active_after_7d = 1 THEN 1 ELSE 0 END)::float
---     / NULLIF(COUNT(CASE WHEN is_active_after_7d IS NOT NULL THEN 1 END), 0)
---     AS activation_rate
---   FROM analytics.users_activities;
--- =============================================================
-
-WITH user_logins AS (
-  SELECT
-    user_id::text                                    AS user_id,
-    MIN(created_at)                                  AS first_login_time,
-    MAX(created_at)                                  AS last_login_time,
-    GREATEST(
-      MAX(refreshed_at)::timestamptz,
-      MAX(created_at)::timestamptz
-    )                                                AS last_visit_time
-  FROM auth.sessions
-  GROUP BY user_id
-),
-user_agents AS (
-  -- Aggregate AgentGraph directly by userId (no fan-out from user_logins)
-  SELECT
-    "userId"::text                AS user_id,
-    MAX("updatedAt")              AS last_agent_save_time,
-    COUNT(DISTINCT "id")          AS agent_count
-  FROM platform."AgentGraph"
-  WHERE "isActive"
-  GROUP BY "userId"
-),
-user_graph_runs AS (
-  -- Aggregate AgentGraphExecution directly by userId
-  SELECT
-    "userId"::text                        AS user_id,
-    MIN("createdAt")                      AS first_agent_run_time,
-    MAX("createdAt")                      AS last_agent_run_time,
-    COUNT(DISTINCT "agentGraphId")        AS unique_agent_runs,
-    COUNT("id")                           AS agent_runs
-  FROM platform."AgentGraphExecution"
-  GROUP BY "userId"
-),
-user_node_runs AS (
-  -- Aggregate AgentNodeExecution directly; resolve userId via a
-  -- single join to AgentGraphExecution instead of fanning out from
-  -- user_logins through both large tables.
-  SELECT
-    g."userId"::text                                                   AS user_id,
-    COUNT(*)                                                           AS node_execution_count,
-    COUNT(*) FILTER (WHERE n."executionStatus" = 'FAILED')             AS node_execution_failed,
-    COUNT(*) FILTER (WHERE n."executionStatus" = 'COMPLETED')          AS node_execution_completed,
-    COUNT(*) FILTER (WHERE n."executionStatus" = 'TERMINATED')         AS node_execution_terminated,
-    COUNT(*) FILTER (WHERE n."executionStatus" = 'QUEUED')             AS node_execution_queued,
-    COUNT(*) FILTER (WHERE n."executionStatus" = 'RUNNING')            AS node_execution_running,
-    COUNT(*) FILTER (WHERE n."executionStatus" = 'INCOMPLETE')         AS node_execution_incomplete,
-    COUNT(*) FILTER (WHERE n."executionStatus" = 'REVIEW')             AS node_execution_review
-  FROM platform."AgentNodeExecution" n
-  JOIN platform."AgentGraphExecution" g
-    ON g."id" = n."agentGraphExecutionId"
-  GROUP BY g."userId"
-)
-SELECT
-  ul.user_id,
-  ul.first_login_time,
-  ul.last_login_time,
-  ul.last_visit_time,
-  ua.last_agent_save_time,
-  COALESCE(ua.agent_count, 0)             AS agent_count,
-  gr.first_agent_run_time,
-  gr.last_agent_run_time,
-  COALESCE(gr.unique_agent_runs, 0)       AS unique_agent_runs,
-  COALESCE(gr.agent_runs, 0)              AS agent_runs,
-  COALESCE(nr.node_execution_count, 0)      AS node_execution_count,
-  COALESCE(nr.node_execution_failed, 0)     AS node_execution_failed,
-  COALESCE(nr.node_execution_completed, 0)  AS node_execution_completed,
-  COALESCE(nr.node_execution_terminated, 0) AS node_execution_terminated,
-  COALESCE(nr.node_execution_queued, 0)     AS node_execution_queued,
-  COALESCE(nr.node_execution_running, 0)    AS node_execution_running,
-  CASE
-    WHEN ul.first_login_time < NOW() - INTERVAL '7 days'
-     AND ul.last_visit_time  >= ul.first_login_time + INTERVAL '7 days' THEN 1
-    WHEN ul.first_login_time < NOW() - INTERVAL '7 days'
-     AND ul.last_visit_time  <  ul.first_login_time + INTERVAL '7 days' THEN 0
-    ELSE NULL
-  END AS is_active_after_7d,
-  COALESCE(nr.node_execution_incomplete, 0) AS node_execution_incomplete,
-  COALESCE(nr.node_execution_review, 0)     AS node_execution_review
-FROM user_logins ul
-LEFT JOIN user_agents     ua ON ul.user_id = ua.user_id
-LEFT JOIN user_graph_runs gr ON ul.user_id = gr.user_id
-LEFT JOIN user_node_runs  nr ON ul.user_id = nr.user_id

autogpt_platform/autogpt_libs/poetry.lock

@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 2.2.1 and should not be changed by hand.
+# This file is automatically @generated by Poetry 2.1.1 and should not be changed by hand.
 
 [[package]]
 name = "annotated-doc"
@@ -67,7 +67,7 @@ description = "Backport of asyncio.Runner, a context manager that controls event
 optional = false
 python-versions = "<3.11,>=3.8"
 groups = ["dev"]
-markers = "python_version == \"3.10\""
+markers = "python_version < \"3.11\""
 files = [
     {file = "backports_asyncio_runner-1.2.0-py3-none-any.whl", hash = "sha256:0da0a936a8aeb554eccb426dc55af3ba63bcdc69fa1a600b5bb305413a4477b5"},
     {file = "backports_asyncio_runner-1.2.0.tar.gz", hash = "sha256:a5aa7b2b7d8f8bfcaa2b57313f70792df84e32a2a746f585213373f900b42162"},
@@ -541,7 +541,7 @@ description = "Backport of PEP 654 (exception groups)"
 optional = false
 python-versions = ">=3.7"
 groups = ["main", "dev"]
-markers = "python_version == \"3.10\""
+markers = "python_version < \"3.11\""
 files = [
     {file = "exceptiongroup-1.3.0-py3-none-any.whl", hash = "sha256:4d111e6e0c13d0644cad6ddaa7ed0261a0b36971f6d23e7ec9b4b9097da78a10"},
     {file = "exceptiongroup-1.3.0.tar.gz", hash = "sha256:b241f5885f560bc56a59ee63ca4c6a8bfa46ae4ad651af316d4e81817bb9fd88"},
@@ -2181,14 +2181,14 @@ testing = ["coverage (>=6.2)", "hypothesis (>=5.7.1)"]
 
 [[package]]
 name = "pytest-cov"
-version = "7.1.0"
+version = "7.0.0"
 description = "Pytest plugin for measuring coverage."
 optional = false
 python-versions = ">=3.9"
 groups = ["dev"]
 files = [
-    {file = "pytest_cov-7.1.0-py3-none-any.whl", hash = "sha256:a0461110b7865f9a271aa1b51e516c9a95de9d696734a2f71e3e78f46e1d4678"},
-    {file = "pytest_cov-7.1.0.tar.gz", hash = "sha256:30674f2b5f6351aa09702a9c8c364f6a01c27aae0c1366ae8016160d1efc56b2"},
+    {file = "pytest_cov-7.0.0-py3-none-any.whl", hash = "sha256:3b8e9558b16cc1479da72058bdecf8073661c7f57f7d3c5f22a1c23507f2d861"},
+    {file = "pytest_cov-7.0.0.tar.gz", hash = "sha256:33c97eda2e049a0c5298e91f519302a1334c26ac65c1a483d6206fd458361af1"},
 ]
 
 [package.dependencies]
@@ -2342,30 +2342,30 @@ pyasn1 = ">=0.1.3"
 
 [[package]]
 name = "ruff"
-version = "0.15.7"
+version = "0.15.0"
 description = "An extremely fast Python linter and code formatter, written in Rust."
 optional = false
 python-versions = ">=3.7"
 groups = ["dev"]
 files = [
-    {file = "ruff-0.15.7-py3-none-linux_armv6l.whl", hash = "sha256:a81cc5b6910fb7dfc7c32d20652e50fa05963f6e13ead3c5915c41ac5d16668e"},
-    {file = "ruff-0.15.7-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:722d165bd52403f3bdabc0ce9e41fc47070ac56d7a91b4e0d097b516a53a3477"},
-    {file = "ruff-0.15.7-py3-none-macosx_11_0_arm64.whl", hash = "sha256:7fbc2448094262552146cbe1b9643a92f66559d3761f1ad0656d4991491af49e"},
-    {file = "ruff-0.15.7-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6b39329b60eba44156d138275323cc726bbfbddcec3063da57caa8a8b1d50adf"},
-    {file = "ruff-0.15.7-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:87768c151808505f2bfc93ae44e5f9e7c8518943e5074f76ac21558ef5627c85"},
-    {file = "ruff-0.15.7-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:fb0511670002c6c529ec66c0e30641c976c8963de26a113f3a30456b702468b0"},
-    {file = "ruff-0.15.7-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e0d19644f801849229db8345180a71bee5407b429dd217f853ec515e968a6912"},
-    {file = "ruff-0.15.7-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:4806d8e09ef5e84eb19ba833d0442f7e300b23fe3f0981cae159a248a10f0036"},
-    {file = "ruff-0.15.7-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dce0896488562f09a27b9c91b1f58a097457143931f3c4d519690dea54e624c5"},
-    {file = "ruff-0.15.7-py3-none-manylinux_2_31_riscv64.whl", hash = "sha256:1852ce241d2bc89e5dc823e03cff4ce73d816b5c6cdadd27dbfe7b03217d2a12"},
-    {file = "ruff-0.15.7-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:5f3e4b221fb4bd293f79912fc5e93a9063ebd6d0dcbd528f91b89172a9b8436c"},
-    {file = "ruff-0.15.7-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:b15e48602c9c1d9bdc504b472e90b90c97dc7d46c7028011ae67f3861ceba7b4"},
-    {file = "ruff-0.15.7-py3-none-musllinux_1_2_i686.whl", hash = "sha256:1b4705e0e85cedc74b0a23cf6a179dbb3df184cb227761979cc76c0440b5ab0d"},
-    {file = "ruff-0.15.7-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:112c1fa316a558bb34319282c1200a8bf0495f1b735aeb78bfcb2991e6087580"},
-    {file = "ruff-0.15.7-py3-none-win32.whl", hash = "sha256:6d39e2d3505b082323352f733599f28169d12e891f7dd407f2d4f54b4c2886de"},
-    {file = "ruff-0.15.7-py3-none-win_amd64.whl", hash = "sha256:4d53d712ddebcd7dace1bc395367aec12c057aacfe9adbb6d832302575f4d3a1"},
-    {file = "ruff-0.15.7-py3-none-win_arm64.whl", hash = "sha256:18e8d73f1c3fdf27931497972250340f92e8c861722161a9caeb89a58ead6ed2"},
-    {file = "ruff-0.15.7.tar.gz", hash = "sha256:04f1ae61fc20fe0b148617c324d9d009b5f63412c0b16474f3d5f1a1a665f7ac"},
+    {file = "ruff-0.15.0-py3-none-linux_armv6l.whl", hash = "sha256:aac4ebaa612a82b23d45964586f24ae9bc23ca101919f5590bdb368d74ad5455"},
+    {file = "ruff-0.15.0-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:dcd4be7cc75cfbbca24a98d04d0b9b36a270d0833241f776b788d59f4142b14d"},
+    {file = "ruff-0.15.0-py3-none-macosx_11_0_arm64.whl", hash = "sha256:d747e3319b2bce179c7c1eaad3d884dc0a199b5f4d5187620530adf9105268ce"},
+    {file = "ruff-0.15.0-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:650bd9c56ae03102c51a5e4b554d74d825ff3abe4db22b90fd32d816c2e90621"},
+    {file = "ruff-0.15.0-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:a6664b7eac559e3048223a2da77769c2f92b43a6dfd4720cef42654299a599c9"},
+    {file = "ruff-0.15.0-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6f811f97b0f092b35320d1556f3353bf238763420ade5d9e62ebd2b73f2ff179"},
+    {file = "ruff-0.15.0-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:761ec0a66680fab6454236635a39abaf14198818c8cdf691e036f4bc0f406b2d"},
+    {file = "ruff-0.15.0-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:940f11c2604d317e797b289f4f9f3fa5555ffe4fb574b55ed006c3d9b6f0eb78"},
+    {file = "ruff-0.15.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bcbca3d40558789126da91d7ef9a7c87772ee107033db7191edefa34e2c7f1b4"},
+    {file = "ruff-0.15.0-py3-none-manylinux_2_31_riscv64.whl", hash = "sha256:9a121a96db1d75fa3eb39c4539e607f628920dd72ff1f7c5ee4f1b768ac62d6e"},
+    {file = "ruff-0.15.0-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:5298d518e493061f2eabd4abd067c7e4fb89e2f63291c94332e35631c07c3662"},
+    {file = "ruff-0.15.0-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:afb6e603d6375ff0d6b0cee563fa21ab570fd15e65c852cb24922cef25050cf1"},
+    {file = "ruff-0.15.0-py3-none-musllinux_1_2_i686.whl", hash = "sha256:77e515f6b15f828b94dc17d2b4ace334c9ddb7d9468c54b2f9ed2b9c1593ef16"},
+    {file = "ruff-0.15.0-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:6f6e80850a01eb13b3e42ee0ebdf6e4497151b48c35051aab51c101266d187a3"},
+    {file = "ruff-0.15.0-py3-none-win32.whl", hash = "sha256:238a717ef803e501b6d51e0bdd0d2c6e8513fe9eec14002445134d3907cd46c3"},
+    {file = "ruff-0.15.0-py3-none-win_amd64.whl", hash = "sha256:dd5e4d3301dc01de614da3cdffc33d4b1b96fb89e45721f1598e5532ccf78b18"},
+    {file = "ruff-0.15.0-py3-none-win_arm64.whl", hash = "sha256:c480d632cc0ca3f0727acac8b7d053542d9e114a462a145d0b00e7cd658c515a"},
+    {file = "ruff-0.15.0.tar.gz", hash = "sha256:6bdea47cdbea30d40f8f8d7d69c0854ba7c15420ec75a26f463290949d7f7e9a"},
 ]
 
 [[package]]
@@ -2564,7 +2564,7 @@ description = "A lil' TOML parser"
 optional = false
 python-versions = ">=3.8"
 groups = ["dev"]
-markers = "python_version == \"3.10\""
+markers = "python_version < \"3.11\""
 files = [
     {file = "tomli-2.2.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:678e4fa69e4575eb77d103de3df8a895e1591b48e740211bd1067378c69e8249"},
     {file = "tomli-2.2.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:023aa114dd824ade0100497eb2318602af309e5a55595f76b626d6d9f3b7b0a6"},
@@ -2912,4 +2912,4 @@ type = ["pytest-mypy"]
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.10,<4.0"
-content-hash = "e0936a065565550afed18f6298b7e04e814b44100def7049f1a0d68662624a39"
+content-hash = "9619cae908ad38fa2c48016a58bcf4241f6f5793aa0e6cc140276e91c433cbbb"

autogpt_platform/autogpt_libs/pyproject.toml

@@ -26,8 +26,8 @@ pyright = "^1.1.408"
 pytest = "^8.4.1"
 pytest-asyncio = "^1.3.0"
 pytest-mock = "^3.15.1"
-pytest-cov = "^7.1.0"
-ruff = "^0.15.7"
+pytest-cov = "^7.0.0"
+ruff = "^0.15.0"
 
 [build-system]
 requires = ["poetry-core"]

autogpt_platform/backend/.env.default

@@ -178,7 +178,6 @@ SMTP_USERNAME=
 SMTP_PASSWORD=
 
 # Business & Marketing Tools
-AGENTMAIL_API_KEY=
 APOLLO_API_KEY=
 ENRICHLAYER_API_KEY=
 AYRSHARE_API_KEY=

autogpt_platform/backend/AGENTS.md

@@ -1,227 +0,0 @@
-# Backend
-
-This file provides guidance to coding agents when working with the backend.
-
-## Essential Commands
-
-To run something with Python package dependencies you MUST use `poetry run ...`.
-
-```bash
-# Install dependencies
-poetry install
-
-# Run database migrations
-poetry run prisma migrate dev
-
-# Start all services (database, redis, rabbitmq, clamav)
-docker compose up -d
-
-# Run the backend as a whole
-poetry run app
-
-# Run tests
-poetry run test
-
-# Run specific test
-poetry run pytest path/to/test_file.py::test_function_name
-
-# Run block tests (tests that validate all blocks work correctly)
-poetry run pytest backend/blocks/test/test_block.py -xvs
-
-# Run tests for a specific block (e.g., GetCurrentTimeBlock)
-poetry run pytest 'backend/blocks/test/test_block.py::test_available_blocks[GetCurrentTimeBlock]' -xvs
-
-# Lint and format
-# prefer format if you want to just "fix" it and only get the errors that can't be autofixed
-poetry run format  # Black + isort
-poetry run lint    # ruff
-```
-
-More details can be found in @TESTING.md
-
-### Creating/Updating Snapshots
-
-When you first write a test or when the expected output changes:
-
-```bash
-poetry run pytest path/to/test.py --snapshot-update
-```
-
-⚠️ **Important**: Always review snapshot changes before committing! Use `git diff` to verify the changes are expected.
-
-## Architecture
-
-- **API Layer**: FastAPI with REST and WebSocket endpoints
-- **Database**: PostgreSQL with Prisma ORM, includes pgvector for embeddings
-- **Queue System**: RabbitMQ for async task processing
-- **Execution Engine**: Separate executor service processes agent workflows
-- **Authentication**: JWT-based with Supabase integration
-- **Security**: Cache protection middleware prevents sensitive data caching in browsers/proxies
-
-## Code Style
-
-- **Top-level imports only** — no local/inner imports (lazy imports only for heavy optional deps like `openpyxl`)
-- **Absolute imports** — use `from backend.module import ...` for cross-package imports. Single-dot relative (`from .sibling import ...`) is acceptable for sibling modules within the same package (e.g., blocks). Avoid double-dot relative imports (`from ..parent import ...`) — use the absolute path instead
-- **No duck typing** — no `hasattr`/`getattr`/`isinstance` for type dispatch; use typed interfaces/unions/protocols
-- **Pydantic models** over dataclass/namedtuple/dict for structured data
-- **No linter suppressors** — no `# type: ignore`, `# noqa`, `# pyright: ignore`; fix the type/code
-- **List comprehensions** over manual loop-and-append
-- **Early return** — guard clauses first, avoid deep nesting
-- **f-strings vs printf syntax in log statements** — Use `%s` for deferred interpolation in `debug` statements, f-strings elsewhere for readability: `logger.debug("Processing %s items", count)`, `logger.info(f"Processing {count} items")`
-- **Sanitize error paths** — `os.path.basename()` in error messages to avoid leaking directory structure
-- **TOCTOU awareness** — avoid check-then-act patterns for file access and credit charging
-- **`Security()` vs `Depends()`** — use `Security()` for auth deps to get proper OpenAPI security spec
-- **Redis pipelines** — `transaction=True` for atomicity on multi-step operations
-- **`max(0, value)` guards** — for computed values that should never be negative
-- **SSE protocol** — `data:` lines for frontend-parsed events (must match Zod schema), `: comment` lines for heartbeats/status
-- **File length** — keep files under ~300 lines; if a file grows beyond this, split by responsibility (e.g. extract helpers, models, or a sub-module into a new file). Never keep appending to a long file.
-- **Function length** — keep functions under ~40 lines; extract named helpers when a function grows longer. Long functions are a sign of mixed concerns, not complexity.
-- **Top-down ordering** — define the main/public function or class first, then the helpers it uses below. A reader should encounter high-level logic before implementation details.
-
-## Testing Approach
-
-- Uses pytest with snapshot testing for API responses
-- Test files are colocated with source files (`*_test.py`)
-- Mock at boundaries — mock where the symbol is **used**, not where it's **defined**
-- After refactoring, update mock targets to match new module paths
-- Use `AsyncMock` for async functions (`from unittest.mock import AsyncMock`)
-
-### Test-Driven Development (TDD)
-
-When fixing a bug or adding a feature, write the test **before** the implementation:
-
-```python
-# 1. Write a failing test marked xfail
-@pytest.mark.xfail(reason="Bug #1234: widget crashes on empty input")
-def test_widget_handles_empty_input():
-    result = widget.process("")
-    assert result == Widget.EMPTY_RESULT
-
-# 2. Run it — confirm it fails (XFAIL)
-# poetry run pytest path/to/test.py::test_widget_handles_empty_input -xvs
-
-# 3. Implement the fix
-
-# 4. Remove xfail, run again — confirm it passes
-def test_widget_handles_empty_input():
-    result = widget.process("")
-    assert result == Widget.EMPTY_RESULT
-```
-
-This catches regressions and proves the fix actually works. **Every bug fix should include a test that would have caught it.**
-
-## Database Schema
-
-Key models (defined in `schema.prisma`):
-
-- `User`: Authentication and profile data
-- `AgentGraph`: Workflow definitions with version control
-- `AgentGraphExecution`: Execution history and results
-- `AgentNode`: Individual nodes in a workflow
-- `StoreListing`: Marketplace listings for sharing agents
-
-## Environment Configuration
-
-- **Backend**: `.env.default` (defaults) → `.env` (user overrides)
-
-## Common Development Tasks
-
-### Adding a new block
-
-Follow the comprehensive [Block SDK Guide](@../../docs/platform/block-sdk-guide.md) which covers:
-
-- Provider configuration with `ProviderBuilder`
-- Block schema definition
-- Authentication (API keys, OAuth, webhooks)
-- Testing and validation
-- File organization
-
-Quick steps:
-
-1. Create new file in `backend/blocks/`
-2. Configure provider using `ProviderBuilder` in `_config.py`
-3. Inherit from `Block` base class
-4. Define input/output schemas using `BlockSchema`
-5. Implement async `run` method
-6. Generate unique block ID using `uuid.uuid4()`
-7. Test with `poetry run pytest backend/blocks/test/test_block.py`
-
-Note: when making many new blocks analyze the interfaces for each of these blocks and picture if they would go well together in a graph-based editor or would they struggle to connect productively?
-ex: do the inputs and outputs tie well together?
-
-If you get any pushback or hit complex block conditions check the new_blocks guide in the docs.
-
-#### Handling files in blocks with `store_media_file()`
-
-When blocks need to work with files (images, videos, documents), use `store_media_file()` from `backend.util.file`. The `return_format` parameter determines what you get back:
-
-| Format | Use When | Returns |
-|--------|----------|---------|
-| `"for_local_processing"` | Processing with local tools (ffmpeg, MoviePy, PIL) | Local file path (e.g., `"image.png"`) |
-| `"for_external_api"` | Sending content to external APIs (Replicate, OpenAI) | Data URI (e.g., `"data:image/png;base64,..."`) |
-| `"for_block_output"` | Returning output from your block | Smart: `workspace://` in CoPilot, data URI in graphs |
-
-**Examples:**
-
-```python
-# INPUT: Need to process file locally with ffmpeg
-local_path = await store_media_file(
-    file=input_data.video,
-    execution_context=execution_context,
-    return_format="for_local_processing",
-)
-# local_path = "video.mp4" - use with Path/ffmpeg/etc
-
-# INPUT: Need to send to external API like Replicate
-image_b64 = await store_media_file(
-    file=input_data.image,
-    execution_context=execution_context,
-    return_format="for_external_api",
-)
-# image_b64 = "data:image/png;base64,iVBORw0..." - send to API
-
-# OUTPUT: Returning result from block
-result_url = await store_media_file(
-    file=generated_image_url,
-    execution_context=execution_context,
-    return_format="for_block_output",
-)
-yield "image_url", result_url
-# In CoPilot: result_url = "workspace://abc123"
-# In graphs:  result_url = "data:image/png;base64,..."
-```
-
-**Key points:**
-
-- `for_block_output` is the ONLY format that auto-adapts to execution context
-- Always use `for_block_output` for block outputs unless you have a specific reason not to
-- Never hardcode workspace checks - let `for_block_output` handle it
-
-### Modifying the API
-
-1. Update route in `backend/api/features/`
-2. Add/update Pydantic models in same directory
-3. Write tests alongside the route file
-4. Run `poetry run test` to verify
-
-## Workspace & Media Files
-
-**Read [Workspace & Media Architecture](../../docs/platform/workspace-media-architecture.md) when:**
-- Working on CoPilot file upload/download features
-- Building blocks that handle `MediaFileType` inputs/outputs
-- Modifying `WorkspaceManager` or `store_media_file()`
-- Debugging file persistence or virus scanning issues
-
-Covers: `WorkspaceManager` (persistent storage with session scoping), `store_media_file()` (media normalization pipeline), and responsibility boundaries for virus scanning and persistence.
-
-## Security Implementation
-
-### Cache Protection Middleware
-
-- Located in `backend/api/middleware/security.py`
-- Default behavior: Disables caching for ALL endpoints with `Cache-Control: no-store, no-cache, must-revalidate, private`
-- Uses an allow list approach - only explicitly permitted paths can be cached
-- Cacheable paths include: static assets (`static/*`, `_next/static/*`), health checks, public store pages, documentation
-- Prevents sensitive data (auth tokens, API keys, user data) from being cached by browsers/proxies
-- To allow caching for a new endpoint, add it to `CACHEABLE_PATHS` in the middleware
-- Applied to both main API server and external API applications

autogpt_platform/backend/CLAUDE.md

@@ -1 +1,170 @@
-@AGENTS.md
+# CLAUDE.md - Backend
+
+This file provides guidance to Claude Code when working with the backend.
+
+## Essential Commands
+
+To run something with Python package dependencies you MUST use `poetry run ...`.
+
+```bash
+# Install dependencies
+poetry install
+
+# Run database migrations
+poetry run prisma migrate dev
+
+# Start all services (database, redis, rabbitmq, clamav)
+docker compose up -d
+
+# Run the backend as a whole
+poetry run app
+
+# Run tests
+poetry run test
+
+# Run specific test
+poetry run pytest path/to/test_file.py::test_function_name
+
+# Run block tests (tests that validate all blocks work correctly)
+poetry run pytest backend/blocks/test/test_block.py -xvs
+
+# Run tests for a specific block (e.g., GetCurrentTimeBlock)
+poetry run pytest 'backend/blocks/test/test_block.py::test_available_blocks[GetCurrentTimeBlock]' -xvs
+
+# Lint and format
+# prefer format if you want to just "fix" it and only get the errors that can't be autofixed
+poetry run format  # Black + isort
+poetry run lint    # ruff
+```
+
+More details can be found in @TESTING.md
+
+### Creating/Updating Snapshots
+
+When you first write a test or when the expected output changes:
+
+```bash
+poetry run pytest path/to/test.py --snapshot-update
+```
+
+⚠️ **Important**: Always review snapshot changes before committing! Use `git diff` to verify the changes are expected.
+
+## Architecture
+
+- **API Layer**: FastAPI with REST and WebSocket endpoints
+- **Database**: PostgreSQL with Prisma ORM, includes pgvector for embeddings
+- **Queue System**: RabbitMQ for async task processing
+- **Execution Engine**: Separate executor service processes agent workflows
+- **Authentication**: JWT-based with Supabase integration
+- **Security**: Cache protection middleware prevents sensitive data caching in browsers/proxies
+
+## Testing Approach
+
+- Uses pytest with snapshot testing for API responses
+- Test files are colocated with source files (`*_test.py`)
+
+## Database Schema
+
+Key models (defined in `schema.prisma`):
+
+- `User`: Authentication and profile data
+- `AgentGraph`: Workflow definitions with version control
+- `AgentGraphExecution`: Execution history and results
+- `AgentNode`: Individual nodes in a workflow
+- `StoreListing`: Marketplace listings for sharing agents
+
+## Environment Configuration
+
+- **Backend**: `.env.default` (defaults) → `.env` (user overrides)
+
+## Common Development Tasks
+
+### Adding a new block
+
+Follow the comprehensive [Block SDK Guide](@../../docs/content/platform/block-sdk-guide.md) which covers:
+
+- Provider configuration with `ProviderBuilder`
+- Block schema definition
+- Authentication (API keys, OAuth, webhooks)
+- Testing and validation
+- File organization
+
+Quick steps:
+
+1. Create new file in `backend/blocks/`
+2. Configure provider using `ProviderBuilder` in `_config.py`
+3. Inherit from `Block` base class
+4. Define input/output schemas using `BlockSchema`
+5. Implement async `run` method
+6. Generate unique block ID using `uuid.uuid4()`
+7. Test with `poetry run pytest backend/blocks/test/test_block.py`
+
+Note: when making many new blocks analyze the interfaces for each of these blocks and picture if they would go well together in a graph-based editor or would they struggle to connect productively?
+ex: do the inputs and outputs tie well together?
+
+If you get any pushback or hit complex block conditions check the new_blocks guide in the docs.
+
+#### Handling files in blocks with `store_media_file()`
+
+When blocks need to work with files (images, videos, documents), use `store_media_file()` from `backend.util.file`. The `return_format` parameter determines what you get back:
+
+| Format | Use When | Returns |
+|--------|----------|---------|
+| `"for_local_processing"` | Processing with local tools (ffmpeg, MoviePy, PIL) | Local file path (e.g., `"image.png"`) |
+| `"for_external_api"` | Sending content to external APIs (Replicate, OpenAI) | Data URI (e.g., `"data:image/png;base64,..."`) |
+| `"for_block_output"` | Returning output from your block | Smart: `workspace://` in CoPilot, data URI in graphs |
+
+**Examples:**
+
+```python
+# INPUT: Need to process file locally with ffmpeg
+local_path = await store_media_file(
+    file=input_data.video,
+    execution_context=execution_context,
+    return_format="for_local_processing",
+)
+# local_path = "video.mp4" - use with Path/ffmpeg/etc
+
+# INPUT: Need to send to external API like Replicate
+image_b64 = await store_media_file(
+    file=input_data.image,
+    execution_context=execution_context,
+    return_format="for_external_api",
+)
+# image_b64 = "data:image/png;base64,iVBORw0..." - send to API
+
+# OUTPUT: Returning result from block
+result_url = await store_media_file(
+    file=generated_image_url,
+    execution_context=execution_context,
+    return_format="for_block_output",
+)
+yield "image_url", result_url
+# In CoPilot: result_url = "workspace://abc123"
+# In graphs:  result_url = "data:image/png;base64,..."
+```
+
+**Key points:**
+
+- `for_block_output` is the ONLY format that auto-adapts to execution context
+- Always use `for_block_output` for block outputs unless you have a specific reason not to
+- Never hardcode workspace checks - let `for_block_output` handle it
+
+### Modifying the API
+
+1. Update route in `backend/api/features/`
+2. Add/update Pydantic models in same directory
+3. Write tests alongside the route file
+4. Run `poetry run test` to verify
+
+## Security Implementation
+
+### Cache Protection Middleware
+
+- Located in `backend/api/middleware/security.py`
+- Default behavior: Disables caching for ALL endpoints with `Cache-Control: no-store, no-cache, must-revalidate, private`
+- Uses an allow list approach - only explicitly permitted paths can be cached
+- Cacheable paths include: static assets (`static/*`, `_next/static/*`), health checks, public store pages, documentation
+- Prevents sensitive data (auth tokens, API keys, user data) from being cached by browsers/proxies
+- To allow caching for a new endpoint, add it to `CACHEABLE_PATHS` in the middleware
+- Applied to both main API server and external API applications

autogpt_platform/backend/Dockerfile

@@ -50,7 +50,7 @@ RUN poetry install --no-ansi --no-root
 # Generate Prisma client
 COPY autogpt_platform/backend/schema.prisma ./
 COPY autogpt_platform/backend/backend/data/partial_types.py ./backend/data/partial_types.py
-COPY autogpt_platform/backend/scripts/gen_prisma_types_stub.py ./scripts/
+COPY autogpt_platform/backend/gen_prisma_types_stub.py ./
 RUN poetry run prisma generate && poetry run gen-prisma-stub
 
 # =============================== DB MIGRATOR =============================== #
@@ -82,7 +82,7 @@ RUN pip3 install prisma>=0.15.0 --break-system-packages
 
 COPY autogpt_platform/backend/schema.prisma ./
 COPY autogpt_platform/backend/backend/data/partial_types.py ./backend/data/partial_types.py
-COPY autogpt_platform/backend/scripts/gen_prisma_types_stub.py ./scripts/
+COPY autogpt_platform/backend/gen_prisma_types_stub.py ./
 COPY autogpt_platform/backend/migrations ./migrations
 
 # ============================== BACKEND SERVER ============================== #
@@ -121,21 +121,19 @@ RUN ln -s ../lib/node_modules/npm/bin/npm-cli.js /usr/bin/npm \
     && ln -s ../lib/node_modules/npm/bin/npx-cli.js /usr/bin/npx
 COPY --from=builder /root/.cache/prisma-python/binaries /root/.cache/prisma-python/binaries
 
-# Install agent-browser (Copilot browser tool) using the system chromium package.
-# Chrome for Testing (the binary agent-browser downloads via `agent-browser install`)
-# has no ARM64 builds, so we use the distro-packaged chromium instead — verified to
-# work with agent-browser via Docker tests on arm64; amd64 is validated in CI.
-# Note: system chromium tracks the Debian package schedule rather than a pinned
-# Chrome for Testing release. If agent-browser requires a specific Chrome version,
-# verify compatibility against the chromium package version in the base image.
-RUN apt-get update \
-    && apt-get install -y --no-install-recommends chromium fonts-liberation \
+# Install agent-browser (Copilot browser tool) + Chromium runtime dependencies.
+# These are the runtime libraries Chromium/Playwright needs on Debian 13 (trixie).
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    libnss3 libnspr4 libatk1.0-0 libatk-bridge2.0-0 libcups2 libdrm2 \
+    libdbus-1-3 libxkbcommon0 libatspi2.0-0t64 libxcomposite1 libxdamage1 \
+    libxfixes3 libxrandr2 libgbm1 libasound2t64 libpango-1.0-0 libcairo2 \
+    libx11-6 libx11-xcb1 libxcb1 libxext6 libglib2.0-0t64 \
+    fonts-liberation libfontconfig1 \
     && rm -rf /var/lib/apt/lists/* \
     && npm install -g agent-browser \
+    && agent-browser install \
     && rm -rf /tmp/* /root/.npm
 
-ENV AGENT_BROWSER_EXECUTABLE_PATH=/usr/bin/chromium
-
 WORKDIR /app/autogpt_platform/backend
 
 # Copy only the .venv from builder (not the entire /app directory)

autogpt_platform/backend/backend/api/external/v1/integrations.py

@@ -18,22 +18,14 @@ from pydantic import BaseModel, Field, SecretStr
 
 from backend.api.external.middleware import require_permission
 from backend.api.features.integrations.models import get_all_provider_names
-from backend.api.features.integrations.router import (
-    CredentialsMetaResponse,
-    to_meta_response,
-)
 from backend.data.auth.base import APIAuthorizationInfo
 from backend.data.model import (
     APIKeyCredentials,
     Credentials,
     CredentialsType,
     HostScopedCredentials,
+    OAuth2Credentials,
     UserPasswordCredentials,
-    is_sdk_default,
-)
-from backend.integrations.credentials_store import (
-    is_system_credential,
-    provider_matches,
 )
 from backend.integrations.creds_manager import IntegrationCredentialsManager
 from backend.integrations.oauth import CREDENTIALS_BY_PROVIDER, HANDLERS_BY_NAME
@@ -99,6 +91,18 @@ class OAuthCompleteResponse(BaseModel):
     )
 
 
+class CredentialSummary(BaseModel):
+    """Summary of a credential without sensitive data."""
+
+    id: str
+    provider: str
+    type: CredentialsType
+    title: Optional[str] = None
+    scopes: Optional[list[str]] = None
+    username: Optional[str] = None
+    host: Optional[str] = None
+
+
 class ProviderInfo(BaseModel):
     """Information about an integration provider."""
 
@@ -469,12 +473,12 @@ async def complete_oauth(
     )
 
 
-@integrations_router.get("/credentials", response_model=list[CredentialsMetaResponse])
+@integrations_router.get("/credentials", response_model=list[CredentialSummary])
 async def list_credentials(
     auth: APIAuthorizationInfo = Security(
         require_permission(APIKeyPermission.READ_INTEGRATIONS)
     ),
-) -> list[CredentialsMetaResponse]:
+) -> list[CredentialSummary]:
     """
     List all credentials for the authenticated user.
 
@@ -482,19 +486,28 @@ async def list_credentials(
     """
     credentials = await creds_manager.store.get_all_creds(auth.user_id)
     return [
-        to_meta_response(cred) for cred in credentials if not is_sdk_default(cred.id)
+        CredentialSummary(
+            id=cred.id,
+            provider=cred.provider,
+            type=cred.type,
+            title=cred.title,
+            scopes=cred.scopes if isinstance(cred, OAuth2Credentials) else None,
+            username=cred.username if isinstance(cred, OAuth2Credentials) else None,
+            host=cred.host if isinstance(cred, HostScopedCredentials) else None,
+        )
+        for cred in credentials
     ]
 
 
 @integrations_router.get(
-    "/{provider}/credentials", response_model=list[CredentialsMetaResponse]
+    "/{provider}/credentials", response_model=list[CredentialSummary]
 )
 async def list_credentials_by_provider(
     provider: Annotated[str, Path(title="The provider to list credentials for")],
     auth: APIAuthorizationInfo = Security(
         require_permission(APIKeyPermission.READ_INTEGRATIONS)
     ),
-) -> list[CredentialsMetaResponse]:
+) -> list[CredentialSummary]:
     """
     List credentials for a specific provider.
     """
@@ -502,7 +515,16 @@ async def list_credentials_by_provider(
         auth.user_id, provider
     )
     return [
-        to_meta_response(cred) for cred in credentials if not is_sdk_default(cred.id)
+        CredentialSummary(
+            id=cred.id,
+            provider=cred.provider,
+            type=cred.type,
+            title=cred.title,
+            scopes=cred.scopes if isinstance(cred, OAuth2Credentials) else None,
+            username=cred.username if isinstance(cred, OAuth2Credentials) else None,
+            host=cred.host if isinstance(cred, HostScopedCredentials) else None,
+        )
+        for cred in credentials
     ]
 
 
@@ -575,11 +597,11 @@ async def create_credential(
     # Store credentials
     try:
         await creds_manager.create(auth.user_id, credentials)
-    except Exception:
-        logger.exception("Failed to store credentials")
+    except Exception as e:
+        logger.error(f"Failed to store credentials: {e}")
         raise HTTPException(
             status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
-            detail="Failed to store credentials",
+            detail=f"Failed to store credentials: {str(e)}",
         )
 
     logger.info(f"Created {request.type} credentials for provider {provider}")
@@ -617,23 +639,15 @@ async def delete_credential(
     use the main API's delete endpoint which handles webhook cleanup and
     token revocation.
     """
-    if is_sdk_default(cred_id):
-        raise HTTPException(
-            status_code=status.HTTP_404_NOT_FOUND, detail="Credentials not found"
-        )
-    if is_system_credential(cred_id):
-        raise HTTPException(
-            status_code=status.HTTP_403_FORBIDDEN,
-            detail="System-managed credentials cannot be deleted",
-        )
     creds = await creds_manager.store.get_creds_by_id(auth.user_id, cred_id)
     if not creds:
         raise HTTPException(
             status_code=status.HTTP_404_NOT_FOUND, detail="Credentials not found"
         )
-    if not provider_matches(creds.provider, provider):
+    if creds.provider != provider:
         raise HTTPException(
-            status_code=status.HTTP_404_NOT_FOUND, detail="Credentials not found"
+            status_code=status.HTTP_404_NOT_FOUND,
+            detail="Credentials do not match the specified provider",
         )
 
     await creds_manager.delete(auth.user_id, cred_id)

autogpt_platform/backend/backend/api/external/v1/routes.py

@@ -1,7 +1,7 @@
 import logging
 import urllib.parse
 from collections import defaultdict
-from typing import Annotated, Any, Optional, Sequence
+from typing import Annotated, Any, Literal, Optional, Sequence
 
 from fastapi import APIRouter, Body, HTTPException, Security
 from prisma.enums import AgentExecutionStatus, APIKeyPermission
@@ -9,10 +9,9 @@ from pydantic import BaseModel, Field
 from typing_extensions import TypedDict
 
 import backend.api.features.store.cache as store_cache
-import backend.api.features.store.db as store_db
 import backend.api.features.store.model as store_model
 import backend.blocks
-from backend.api.external.middleware import require_auth, require_permission
+from backend.api.external.middleware import require_permission
 from backend.data import execution as execution_db
 from backend.data import graph as graph_db
 from backend.data import user as user_db
@@ -231,13 +230,13 @@ async def get_graph_execution_results(
 @v1_router.get(
     path="/store/agents",
     tags=["store"],
-    dependencies=[Security(require_auth)],  # data is public; auth required as anti-DDoS
+    dependencies=[Security(require_permission(APIKeyPermission.READ_STORE))],
     response_model=store_model.StoreAgentsResponse,
 )
 async def get_store_agents(
     featured: bool = False,
     creator: str | None = None,
-    sorted_by: store_db.StoreAgentsSortOptions | None = None,
+    sorted_by: Literal["rating", "runs", "name", "updated_at"] | None = None,
     search_query: str | None = None,
     category: str | None = None,
     page: int = 1,
@@ -279,7 +278,7 @@ async def get_store_agents(
 @v1_router.get(
     path="/store/agents/{username}/{agent_name}",
     tags=["store"],
-    dependencies=[Security(require_auth)],  # data is public; auth required as anti-DDoS
+    dependencies=[Security(require_permission(APIKeyPermission.READ_STORE))],
     response_model=store_model.StoreAgentDetails,
 )
 async def get_store_agent(
@@ -307,13 +306,13 @@ async def get_store_agent(
 @v1_router.get(
     path="/store/creators",
     tags=["store"],
-    dependencies=[Security(require_auth)],  # data is public; auth required as anti-DDoS
+    dependencies=[Security(require_permission(APIKeyPermission.READ_STORE))],
     response_model=store_model.CreatorsResponse,
 )
 async def get_store_creators(
     featured: bool = False,
     search_query: str | None = None,
-    sorted_by: store_db.StoreCreatorsSortOptions | None = None,
+    sorted_by: Literal["agent_rating", "agent_runs", "num_agents"] | None = None,
     page: int = 1,
     page_size: int = 20,
 ) -> store_model.CreatorsResponse:
@@ -349,7 +348,7 @@ async def get_store_creators(
 @v1_router.get(
     path="/store/creators/{username}",
     tags=["store"],
-    dependencies=[Security(require_auth)],  # data is public; auth required as anti-DDoS
+    dependencies=[Security(require_permission(APIKeyPermission.READ_STORE))],
     response_model=store_model.CreatorDetails,
 )
 async def get_store_creator(

autogpt_platform/backend/backend/api/external/v1/tools.py

@@ -72,7 +72,7 @@ class RunAgentRequest(BaseModel):
 
 def _create_ephemeral_session(user_id: str) -> ChatSession:
     """Create an ephemeral session for stateless API requests."""
-    return ChatSession.new(user_id, dry_run=False)
+    return ChatSession.new(user_id)
 
 
 @tools_router.post(

autogpt_platform/backend/backend/api/features/admin/rate_limit_admin_routes.py

@@ -1,259 +0,0 @@
-"""Admin endpoints for checking and resetting user CoPilot rate limit usage."""
-
-import logging
-from typing import Optional
-
-from autogpt_libs.auth import get_user_id, requires_admin_user
-from fastapi import APIRouter, Body, HTTPException, Security
-from pydantic import BaseModel
-
-from backend.copilot.config import ChatConfig
-from backend.copilot.rate_limit import (
-    SubscriptionTier,
-    get_global_rate_limits,
-    get_usage_status,
-    get_user_tier,
-    reset_user_usage,
-    set_user_tier,
-)
-from backend.data.user import get_user_by_email, get_user_email_by_id, search_users
-
-logger = logging.getLogger(__name__)
-
-config = ChatConfig()
-
-router = APIRouter(
-    prefix="/admin",
-    tags=["copilot", "admin"],
-    dependencies=[Security(requires_admin_user)],
-)
-
-
-class UserRateLimitResponse(BaseModel):
-    user_id: str
-    user_email: Optional[str] = None
-    daily_token_limit: int
-    weekly_token_limit: int
-    daily_tokens_used: int
-    weekly_tokens_used: int
-    tier: SubscriptionTier
-
-
-class UserTierResponse(BaseModel):
-    user_id: str
-    tier: SubscriptionTier
-
-
-class SetUserTierRequest(BaseModel):
-    user_id: str
-    tier: SubscriptionTier
-
-
-async def _resolve_user_id(
-    user_id: Optional[str], email: Optional[str]
-) -> tuple[str, Optional[str]]:
-    """Resolve a user_id and email from the provided parameters.
-
-    Returns (user_id, email). Accepts either user_id or email; at least one
-    must be provided.  When both are provided, ``email`` takes precedence.
-    """
-    if email:
-        user = await get_user_by_email(email)
-        if not user:
-            raise HTTPException(
-                status_code=404, detail="No user found with the provided email."
-            )
-        return user.id, email
-
-    if not user_id:
-        raise HTTPException(
-            status_code=400,
-            detail="Either user_id or email query parameter is required.",
-        )
-
-    # We have a user_id; try to look up their email for display purposes.
-    # This is non-critical -- a failure should not block the response.
-    try:
-        resolved_email = await get_user_email_by_id(user_id)
-    except Exception:
-        logger.warning("Failed to resolve email for user %s", user_id, exc_info=True)
-        resolved_email = None
-    return user_id, resolved_email
-
-
-@router.get(
-    "/rate_limit",
-    response_model=UserRateLimitResponse,
-    summary="Get User Rate Limit",
-)
-async def get_user_rate_limit(
-    user_id: Optional[str] = None,
-    email: Optional[str] = None,
-    admin_user_id: str = Security(get_user_id),
-) -> UserRateLimitResponse:
-    """Get a user's current usage and effective rate limits. Admin-only.
-
-    Accepts either ``user_id`` or ``email`` as a query parameter.
-    When ``email`` is provided the user is looked up by email first.
-    """
-    resolved_id, resolved_email = await _resolve_user_id(user_id, email)
-
-    logger.info("Admin %s checking rate limit for user %s", admin_user_id, resolved_id)
-
-    daily_limit, weekly_limit, tier = await get_global_rate_limits(
-        resolved_id, config.daily_token_limit, config.weekly_token_limit
-    )
-    usage = await get_usage_status(resolved_id, daily_limit, weekly_limit, tier=tier)
-
-    return UserRateLimitResponse(
-        user_id=resolved_id,
-        user_email=resolved_email,
-        daily_token_limit=daily_limit,
-        weekly_token_limit=weekly_limit,
-        daily_tokens_used=usage.daily.used,
-        weekly_tokens_used=usage.weekly.used,
-        tier=tier,
-    )
-
-
-@router.post(
-    "/rate_limit/reset",
-    response_model=UserRateLimitResponse,
-    summary="Reset User Rate Limit Usage",
-)
-async def reset_user_rate_limit(
-    user_id: str = Body(embed=True),
-    reset_weekly: bool = Body(False, embed=True),
-    admin_user_id: str = Security(get_user_id),
-) -> UserRateLimitResponse:
-    """Reset a user's daily usage counter (and optionally weekly). Admin-only."""
-    logger.info(
-        "Admin %s resetting rate limit for user %s (reset_weekly=%s)",
-        admin_user_id,
-        user_id,
-        reset_weekly,
-    )
-
-    try:
-        await reset_user_usage(user_id, reset_weekly=reset_weekly)
-    except Exception as e:
-        logger.exception("Failed to reset user usage")
-        raise HTTPException(status_code=500, detail="Failed to reset usage") from e
-
-    daily_limit, weekly_limit, tier = await get_global_rate_limits(
-        user_id, config.daily_token_limit, config.weekly_token_limit
-    )
-    usage = await get_usage_status(user_id, daily_limit, weekly_limit, tier=tier)
-
-    try:
-        resolved_email = await get_user_email_by_id(user_id)
-    except Exception:
-        logger.warning("Failed to resolve email for user %s", user_id, exc_info=True)
-        resolved_email = None
-
-    return UserRateLimitResponse(
-        user_id=user_id,
-        user_email=resolved_email,
-        daily_token_limit=daily_limit,
-        weekly_token_limit=weekly_limit,
-        daily_tokens_used=usage.daily.used,
-        weekly_tokens_used=usage.weekly.used,
-        tier=tier,
-    )
-
-
-@router.get(
-    "/rate_limit/tier",
-    response_model=UserTierResponse,
-    summary="Get User Rate Limit Tier",
-)
-async def get_user_rate_limit_tier(
-    user_id: str,
-    admin_user_id: str = Security(get_user_id),
-) -> UserTierResponse:
-    """Get a user's current rate-limit tier. Admin-only.
-
-    Returns 404 if the user does not exist in the database.
-    """
-    logger.info("Admin %s checking tier for user %s", admin_user_id, user_id)
-
-    resolved_email = await get_user_email_by_id(user_id)
-    if resolved_email is None:
-        raise HTTPException(status_code=404, detail=f"User {user_id} not found")
-
-    tier = await get_user_tier(user_id)
-    return UserTierResponse(user_id=user_id, tier=tier)
-
-
-@router.post(
-    "/rate_limit/tier",
-    response_model=UserTierResponse,
-    summary="Set User Rate Limit Tier",
-)
-async def set_user_rate_limit_tier(
-    request: SetUserTierRequest,
-    admin_user_id: str = Security(get_user_id),
-) -> UserTierResponse:
-    """Set a user's rate-limit tier. Admin-only.
-
-    Returns 404 if the user does not exist in the database.
-    """
-    try:
-        resolved_email = await get_user_email_by_id(request.user_id)
-    except Exception:
-        logger.warning(
-            "Failed to resolve email for user %s",
-            request.user_id,
-            exc_info=True,
-        )
-        resolved_email = None
-
-    if resolved_email is None:
-        raise HTTPException(status_code=404, detail=f"User {request.user_id} not found")
-
-    old_tier = await get_user_tier(request.user_id)
-    logger.info(
-        "Admin %s changing tier for user %s (%s): %s -> %s",
-        admin_user_id,
-        request.user_id,
-        resolved_email,
-        old_tier.value,
-        request.tier.value,
-    )
-    try:
-        await set_user_tier(request.user_id, request.tier)
-    except Exception as e:
-        logger.exception("Failed to set user tier")
-        raise HTTPException(status_code=500, detail="Failed to set tier") from e
-
-    return UserTierResponse(user_id=request.user_id, tier=request.tier)
-
-
-class UserSearchResult(BaseModel):
-    user_id: str
-    user_email: Optional[str] = None
-
-
-@router.get(
-    "/rate_limit/search_users",
-    response_model=list[UserSearchResult],
-    summary="Search Users by Name or Email",
-)
-async def admin_search_users(
-    query: str,
-    limit: int = 20,
-    admin_user_id: str = Security(get_user_id),
-) -> list[UserSearchResult]:
-    """Search users by partial email or name. Admin-only.
-
-    Queries the User table directly — returns results even for users
-    without credit transaction history.
-    """
-    if len(query.strip()) < 3:
-        raise HTTPException(
-            status_code=400,
-            detail="Search query must be at least 3 characters.",
-        )
-    logger.info("Admin %s searching users with query=%r", admin_user_id, query)
-    results = await search_users(query, limit=max(1, min(limit, 50)))
-    return [UserSearchResult(user_id=uid, user_email=email) for uid, email in results]

autogpt_platform/backend/backend/api/features/admin/rate_limit_admin_routes_test.py

@@ -1,566 +0,0 @@
-import json
-from types import SimpleNamespace
-from unittest.mock import AsyncMock
-
-import fastapi
-import fastapi.testclient
-import pytest
-import pytest_mock
-from autogpt_libs.auth.jwt_utils import get_jwt_payload
-from pytest_snapshot.plugin import Snapshot
-
-from backend.copilot.rate_limit import CoPilotUsageStatus, SubscriptionTier, UsageWindow
-
-from .rate_limit_admin_routes import router as rate_limit_admin_router
-
-app = fastapi.FastAPI()
-app.include_router(rate_limit_admin_router)
-
-client = fastapi.testclient.TestClient(app)
-
-_MOCK_MODULE = "backend.api.features.admin.rate_limit_admin_routes"
-
-_TARGET_EMAIL = "target@example.com"
-
-
-@pytest.fixture(autouse=True)
-def setup_app_admin_auth(mock_jwt_admin):
-    """Setup admin auth overrides for all tests in this module"""
-    app.dependency_overrides[get_jwt_payload] = mock_jwt_admin["get_jwt_payload"]
-    yield
-    app.dependency_overrides.clear()
-
-
-def _mock_usage_status(
-    daily_used: int = 500_000, weekly_used: int = 3_000_000
-) -> CoPilotUsageStatus:
-    from datetime import UTC, datetime, timedelta
-
-    now = datetime.now(UTC)
-    return CoPilotUsageStatus(
-        daily=UsageWindow(
-            used=daily_used, limit=2_500_000, resets_at=now + timedelta(hours=6)
-        ),
-        weekly=UsageWindow(
-            used=weekly_used, limit=12_500_000, resets_at=now + timedelta(days=3)
-        ),
-    )
-
-
-def _patch_rate_limit_deps(
-    mocker: pytest_mock.MockerFixture,
-    target_user_id: str,
-    daily_used: int = 500_000,
-    weekly_used: int = 3_000_000,
-):
-    """Patch the common rate-limit + user-lookup dependencies."""
-    mocker.patch(
-        f"{_MOCK_MODULE}.get_global_rate_limits",
-        new_callable=AsyncMock,
-        return_value=(2_500_000, 12_500_000, SubscriptionTier.FREE),
-    )
-    mocker.patch(
-        f"{_MOCK_MODULE}.get_usage_status",
-        new_callable=AsyncMock,
-        return_value=_mock_usage_status(daily_used=daily_used, weekly_used=weekly_used),
-    )
-    mocker.patch(
-        f"{_MOCK_MODULE}.get_user_email_by_id",
-        new_callable=AsyncMock,
-        return_value=_TARGET_EMAIL,
-    )
-
-
-def test_get_rate_limit(
-    mocker: pytest_mock.MockerFixture,
-    configured_snapshot: Snapshot,
-    target_user_id: str,
-) -> None:
-    """Test getting rate limit and usage for a user."""
-    _patch_rate_limit_deps(mocker, target_user_id)
-
-    response = client.get("/admin/rate_limit", params={"user_id": target_user_id})
-
-    assert response.status_code == 200
-    data = response.json()
-    assert data["user_id"] == target_user_id
-    assert data["user_email"] == _TARGET_EMAIL
-    assert data["daily_token_limit"] == 2_500_000
-    assert data["weekly_token_limit"] == 12_500_000
-    assert data["daily_tokens_used"] == 500_000
-    assert data["weekly_tokens_used"] == 3_000_000
-    assert data["tier"] == "FREE"
-
-    configured_snapshot.assert_match(
-        json.dumps(data, indent=2, sort_keys=True) + "\n",
-        "get_rate_limit",
-    )
-
-
-def test_get_rate_limit_by_email(
-    mocker: pytest_mock.MockerFixture,
-    target_user_id: str,
-) -> None:
-    """Test looking up rate limits via email instead of user_id."""
-    _patch_rate_limit_deps(mocker, target_user_id)
-
-    mock_user = SimpleNamespace(id=target_user_id, email=_TARGET_EMAIL)
-    mocker.patch(
-        f"{_MOCK_MODULE}.get_user_by_email",
-        new_callable=AsyncMock,
-        return_value=mock_user,
-    )
-
-    response = client.get("/admin/rate_limit", params={"email": _TARGET_EMAIL})
-
-    assert response.status_code == 200
-    data = response.json()
-    assert data["user_id"] == target_user_id
-    assert data["user_email"] == _TARGET_EMAIL
-    assert data["daily_token_limit"] == 2_500_000
-
-
-def test_get_rate_limit_by_email_not_found(
-    mocker: pytest_mock.MockerFixture,
-) -> None:
-    """Test that looking up a non-existent email returns 404."""
-    mocker.patch(
-        f"{_MOCK_MODULE}.get_user_by_email",
-        new_callable=AsyncMock,
-        return_value=None,
-    )
-
-    response = client.get("/admin/rate_limit", params={"email": "nobody@example.com"})
-
-    assert response.status_code == 404
-
-
-def test_get_rate_limit_no_params() -> None:
-    """Test that omitting both user_id and email returns 400."""
-    response = client.get("/admin/rate_limit")
-    assert response.status_code == 400
-
-
-def test_reset_user_usage_daily_only(
-    mocker: pytest_mock.MockerFixture,
-    configured_snapshot: Snapshot,
-    target_user_id: str,
-) -> None:
-    """Test resetting only daily usage (default behaviour)."""
-    mock_reset = mocker.patch(
-        f"{_MOCK_MODULE}.reset_user_usage",
-        new_callable=AsyncMock,
-    )
-    _patch_rate_limit_deps(mocker, target_user_id, daily_used=0, weekly_used=3_000_000)
-
-    response = client.post(
-        "/admin/rate_limit/reset",
-        json={"user_id": target_user_id},
-    )
-
-    assert response.status_code == 200
-    data = response.json()
-    assert data["daily_tokens_used"] == 0
-    # Weekly is untouched
-    assert data["weekly_tokens_used"] == 3_000_000
-    assert data["tier"] == "FREE"
-
-    mock_reset.assert_awaited_once_with(target_user_id, reset_weekly=False)
-
-    configured_snapshot.assert_match(
-        json.dumps(data, indent=2, sort_keys=True) + "\n",
-        "reset_user_usage_daily_only",
-    )
-
-
-def test_reset_user_usage_daily_and_weekly(
-    mocker: pytest_mock.MockerFixture,
-    configured_snapshot: Snapshot,
-    target_user_id: str,
-) -> None:
-    """Test resetting both daily and weekly usage."""
-    mock_reset = mocker.patch(
-        f"{_MOCK_MODULE}.reset_user_usage",
-        new_callable=AsyncMock,
-    )
-    _patch_rate_limit_deps(mocker, target_user_id, daily_used=0, weekly_used=0)
-
-    response = client.post(
-        "/admin/rate_limit/reset",
-        json={"user_id": target_user_id, "reset_weekly": True},
-    )
-
-    assert response.status_code == 200
-    data = response.json()
-    assert data["daily_tokens_used"] == 0
-    assert data["weekly_tokens_used"] == 0
-    assert data["tier"] == "FREE"
-
-    mock_reset.assert_awaited_once_with(target_user_id, reset_weekly=True)
-
-    configured_snapshot.assert_match(
-        json.dumps(data, indent=2, sort_keys=True) + "\n",
-        "reset_user_usage_daily_and_weekly",
-    )
-
-
-def test_reset_user_usage_redis_failure(
-    mocker: pytest_mock.MockerFixture,
-    target_user_id: str,
-) -> None:
-    """Test that Redis failure on reset returns 500."""
-    mocker.patch(
-        f"{_MOCK_MODULE}.reset_user_usage",
-        new_callable=AsyncMock,
-        side_effect=Exception("Redis connection refused"),
-    )
-
-    response = client.post(
-        "/admin/rate_limit/reset",
-        json={"user_id": target_user_id},
-    )
-
-    assert response.status_code == 500
-
-
-def test_get_rate_limit_email_lookup_failure(
-    mocker: pytest_mock.MockerFixture,
-    target_user_id: str,
-) -> None:
-    """Test that failing to resolve a user email degrades gracefully."""
-    mocker.patch(
-        f"{_MOCK_MODULE}.get_global_rate_limits",
-        new_callable=AsyncMock,
-        return_value=(2_500_000, 12_500_000, SubscriptionTier.FREE),
-    )
-    mocker.patch(
-        f"{_MOCK_MODULE}.get_usage_status",
-        new_callable=AsyncMock,
-        return_value=_mock_usage_status(),
-    )
-    mocker.patch(
-        f"{_MOCK_MODULE}.get_user_email_by_id",
-        new_callable=AsyncMock,
-        side_effect=Exception("DB connection lost"),
-    )
-
-    response = client.get("/admin/rate_limit", params={"user_id": target_user_id})
-
-    assert response.status_code == 200
-    data = response.json()
-    assert data["user_id"] == target_user_id
-    assert data["user_email"] is None
-
-
-def test_admin_endpoints_require_admin_role(mock_jwt_user) -> None:
-    """Test that rate limit admin endpoints require admin role."""
-    app.dependency_overrides[get_jwt_payload] = mock_jwt_user["get_jwt_payload"]
-
-    response = client.get("/admin/rate_limit", params={"user_id": "test"})
-    assert response.status_code == 403
-
-    response = client.post(
-        "/admin/rate_limit/reset",
-        json={"user_id": "test"},
-    )
-    assert response.status_code == 403
-
-
-# ---------------------------------------------------------------------------
-# Tier management endpoints
-# ---------------------------------------------------------------------------
-
-
-def test_get_user_tier(
-    mocker: pytest_mock.MockerFixture,
-    target_user_id: str,
-) -> None:
-    """Test getting a user's rate-limit tier."""
-    mocker.patch(
-        f"{_MOCK_MODULE}.get_user_email_by_id",
-        new_callable=AsyncMock,
-        return_value=_TARGET_EMAIL,
-    )
-    mocker.patch(
-        f"{_MOCK_MODULE}.get_user_tier",
-        new_callable=AsyncMock,
-        return_value=SubscriptionTier.PRO,
-    )
-
-    response = client.get("/admin/rate_limit/tier", params={"user_id": target_user_id})
-
-    assert response.status_code == 200
-    data = response.json()
-    assert data["user_id"] == target_user_id
-    assert data["tier"] == "PRO"
-
-
-def test_get_user_tier_user_not_found(
-    mocker: pytest_mock.MockerFixture,
-    target_user_id: str,
-) -> None:
-    """Test that getting tier for a non-existent user returns 404."""
-    mocker.patch(
-        f"{_MOCK_MODULE}.get_user_email_by_id",
-        new_callable=AsyncMock,
-        return_value=None,
-    )
-
-    response = client.get("/admin/rate_limit/tier", params={"user_id": target_user_id})
-
-    assert response.status_code == 404
-
-
-def test_set_user_tier(
-    mocker: pytest_mock.MockerFixture,
-    target_user_id: str,
-) -> None:
-    """Test setting a user's rate-limit tier (upgrade)."""
-    mocker.patch(
-        f"{_MOCK_MODULE}.get_user_email_by_id",
-        new_callable=AsyncMock,
-        return_value=_TARGET_EMAIL,
-    )
-    mocker.patch(
-        f"{_MOCK_MODULE}.get_user_tier",
-        new_callable=AsyncMock,
-        return_value=SubscriptionTier.FREE,
-    )
-    mock_set = mocker.patch(
-        f"{_MOCK_MODULE}.set_user_tier",
-        new_callable=AsyncMock,
-    )
-
-    response = client.post(
-        "/admin/rate_limit/tier",
-        json={"user_id": target_user_id, "tier": "ENTERPRISE"},
-    )
-
-    assert response.status_code == 200
-    data = response.json()
-    assert data["user_id"] == target_user_id
-    assert data["tier"] == "ENTERPRISE"
-    mock_set.assert_awaited_once_with(target_user_id, SubscriptionTier.ENTERPRISE)
-
-
-def test_set_user_tier_downgrade(
-    mocker: pytest_mock.MockerFixture,
-    target_user_id: str,
-) -> None:
-    """Test downgrading a user's tier from PRO to FREE."""
-    mocker.patch(
-        f"{_MOCK_MODULE}.get_user_email_by_id",
-        new_callable=AsyncMock,
-        return_value=_TARGET_EMAIL,
-    )
-    mocker.patch(
-        f"{_MOCK_MODULE}.get_user_tier",
-        new_callable=AsyncMock,
-        return_value=SubscriptionTier.PRO,
-    )
-    mock_set = mocker.patch(
-        f"{_MOCK_MODULE}.set_user_tier",
-        new_callable=AsyncMock,
-    )
-
-    response = client.post(
-        "/admin/rate_limit/tier",
-        json={"user_id": target_user_id, "tier": "FREE"},
-    )
-
-    assert response.status_code == 200
-    data = response.json()
-    assert data["user_id"] == target_user_id
-    assert data["tier"] == "FREE"
-    mock_set.assert_awaited_once_with(target_user_id, SubscriptionTier.FREE)
-
-
-def test_set_user_tier_invalid_tier(
-    target_user_id: str,
-) -> None:
-    """Test that setting an invalid tier returns 422."""
-    response = client.post(
-        "/admin/rate_limit/tier",
-        json={"user_id": target_user_id, "tier": "invalid"},
-    )
-
-    assert response.status_code == 422
-
-
-def test_set_user_tier_invalid_tier_uppercase(
-    target_user_id: str,
-) -> None:
-    """Test that setting an unrecognised uppercase tier (e.g. 'INVALID') returns 422.
-
-    Regression: ensures Pydantic enum validation rejects values that are not
-    members of SubscriptionTier, even when they look like valid enum names.
-    """
-    response = client.post(
-        "/admin/rate_limit/tier",
-        json={"user_id": target_user_id, "tier": "INVALID"},
-    )
-
-    assert response.status_code == 422
-    body = response.json()
-    assert "detail" in body
-
-
-def test_set_user_tier_email_lookup_failure_returns_404(
-    mocker: pytest_mock.MockerFixture,
-    target_user_id: str,
-) -> None:
-    """Test that email lookup failure returns 404 (user unverifiable)."""
-    mocker.patch(
-        f"{_MOCK_MODULE}.get_user_email_by_id",
-        new_callable=AsyncMock,
-        side_effect=Exception("DB connection failed"),
-    )
-
-    response = client.post(
-        "/admin/rate_limit/tier",
-        json={"user_id": target_user_id, "tier": "PRO"},
-    )
-
-    assert response.status_code == 404
-
-
-def test_set_user_tier_user_not_found(
-    mocker: pytest_mock.MockerFixture,
-    target_user_id: str,
-) -> None:
-    """Test that setting tier for a non-existent user returns 404."""
-    mocker.patch(
-        f"{_MOCK_MODULE}.get_user_email_by_id",
-        new_callable=AsyncMock,
-        return_value=None,
-    )
-
-    response = client.post(
-        "/admin/rate_limit/tier",
-        json={"user_id": target_user_id, "tier": "PRO"},
-    )
-
-    assert response.status_code == 404
-
-
-def test_set_user_tier_db_failure(
-    mocker: pytest_mock.MockerFixture,
-    target_user_id: str,
-) -> None:
-    """Test that DB failure on set tier returns 500."""
-    mocker.patch(
-        f"{_MOCK_MODULE}.get_user_email_by_id",
-        new_callable=AsyncMock,
-        return_value=_TARGET_EMAIL,
-    )
-    mocker.patch(
-        f"{_MOCK_MODULE}.get_user_tier",
-        new_callable=AsyncMock,
-        return_value=SubscriptionTier.FREE,
-    )
-    mocker.patch(
-        f"{_MOCK_MODULE}.set_user_tier",
-        new_callable=AsyncMock,
-        side_effect=Exception("DB connection refused"),
-    )
-
-    response = client.post(
-        "/admin/rate_limit/tier",
-        json={"user_id": target_user_id, "tier": "PRO"},
-    )
-
-    assert response.status_code == 500
-
-
-def test_tier_endpoints_require_admin_role(mock_jwt_user) -> None:
-    """Test that tier admin endpoints require admin role."""
-    app.dependency_overrides[get_jwt_payload] = mock_jwt_user["get_jwt_payload"]
-
-    response = client.get("/admin/rate_limit/tier", params={"user_id": "test"})
-    assert response.status_code == 403
-
-    response = client.post(
-        "/admin/rate_limit/tier",
-        json={"user_id": "test", "tier": "PRO"},
-    )
-    assert response.status_code == 403
-
-
-# ─── search_users endpoint ──────────────────────────────────────────
-
-
-def test_search_users_returns_matching_users(
-    mocker: pytest_mock.MockerFixture,
-    admin_user_id: str,
-) -> None:
-    """Partial search should return all matching users from the User table."""
-    mocker.patch(
-        _MOCK_MODULE + ".search_users",
-        new_callable=AsyncMock,
-        return_value=[
-            ("user-1", "zamil.majdy@gmail.com"),
-            ("user-2", "zamil.majdy@agpt.co"),
-        ],
-    )
-
-    response = client.get("/admin/rate_limit/search_users", params={"query": "zamil"})
-
-    assert response.status_code == 200
-    results = response.json()
-    assert len(results) == 2
-    assert results[0]["user_email"] == "zamil.majdy@gmail.com"
-    assert results[1]["user_email"] == "zamil.majdy@agpt.co"
-
-
-def test_search_users_empty_results(
-    mocker: pytest_mock.MockerFixture,
-    admin_user_id: str,
-) -> None:
-    """Search with no matches returns empty list."""
-    mocker.patch(
-        _MOCK_MODULE + ".search_users",
-        new_callable=AsyncMock,
-        return_value=[],
-    )
-
-    response = client.get(
-        "/admin/rate_limit/search_users", params={"query": "nonexistent"}
-    )
-
-    assert response.status_code == 200
-    assert response.json() == []
-
-
-def test_search_users_short_query_rejected(
-    admin_user_id: str,
-) -> None:
-    """Query shorter than 3 characters should return 400."""
-    response = client.get("/admin/rate_limit/search_users", params={"query": "ab"})
-    assert response.status_code == 400
-
-
-def test_search_users_negative_limit_clamped(
-    mocker: pytest_mock.MockerFixture,
-    admin_user_id: str,
-) -> None:
-    """Negative limit should be clamped to 1, not passed through."""
-    mock_search = mocker.patch(
-        _MOCK_MODULE + ".search_users",
-        new_callable=AsyncMock,
-        return_value=[],
-    )
-
-    response = client.get(
-        "/admin/rate_limit/search_users", params={"query": "test", "limit": -1}
-    )
-
-    assert response.status_code == 200
-    mock_search.assert_awaited_once_with("test", limit=1)
-
-
-def test_search_users_requires_admin_role(mock_jwt_user) -> None:
-    """Test that the search_users endpoint requires admin role."""
-    app.dependency_overrides[get_jwt_payload] = mock_jwt_user["get_jwt_payload"]
-
-    response = client.get("/admin/rate_limit/search_users", params={"query": "test"})
-    assert response.status_code == 403

autogpt_platform/backend/backend/api/features/admin/store_admin_routes.py

@@ -7,8 +7,6 @@ import fastapi
 import fastapi.responses
 import prisma.enums
 
-import backend.api.features.library.db as library_db
-import backend.api.features.library.model as library_model
 import backend.api.features.store.cache as store_cache
 import backend.api.features.store.db as store_db
 import backend.api.features.store.model as store_model
@@ -26,13 +24,14 @@ router = fastapi.APIRouter(
 @router.get(
     "/listings",
     summary="Get Admin Listings History",
+    response_model=store_model.StoreListingsWithVersionsResponse,
 )
 async def get_admin_listings_with_versions(
     status: typing.Optional[prisma.enums.SubmissionStatus] = None,
     search: typing.Optional[str] = None,
     page: int = 1,
     page_size: int = 20,
-) -> store_model.StoreListingsWithVersionsAdminViewResponse:
+):
     """
     Get store listings with their version history for admins.
 
@@ -46,26 +45,36 @@ async def get_admin_listings_with_versions(
         page_size: Number of items per page
 
     Returns:
-        Paginated listings with their versions
+        StoreListingsWithVersionsResponse with listings and their versions
     """
-    listings = await store_db.get_admin_listings_with_versions(
-        status=status,
-        search_query=search,
-        page=page,
-        page_size=page_size,
-    )
-    return listings
+    try:
+        listings = await store_db.get_admin_listings_with_versions(
+            status=status,
+            search_query=search,
+            page=page,
+            page_size=page_size,
+        )
+        return listings
+    except Exception as e:
+        logger.exception("Error getting admin listings with versions: %s", e)
+        return fastapi.responses.JSONResponse(
+            status_code=500,
+            content={
+                "detail": "An error occurred while retrieving listings with versions"
+            },
+        )
 
 
 @router.post(
     "/submissions/{store_listing_version_id}/review",
     summary="Review Store Submission",
+    response_model=store_model.StoreSubmission,
 )
 async def review_submission(
     store_listing_version_id: str,
     request: store_model.ReviewSubmissionRequest,
     user_id: str = fastapi.Security(autogpt_libs.auth.get_user_id),
-) -> store_model.StoreSubmissionAdminView:
+):
     """
     Review a store listing submission.
 
@@ -75,24 +84,31 @@ async def review_submission(
         user_id: Authenticated admin user performing the review
 
     Returns:
-        StoreSubmissionAdminView with updated review information
+        StoreSubmission with updated review information
     """
-    already_approved = await store_db.check_submission_already_approved(
-        store_listing_version_id=store_listing_version_id,
-    )
-    submission = await store_db.review_store_submission(
-        store_listing_version_id=store_listing_version_id,
-        is_approved=request.is_approved,
-        external_comments=request.comments,
-        internal_comments=request.internal_comments or "",
-        reviewer_id=user_id,
-    )
+    try:
+        already_approved = await store_db.check_submission_already_approved(
+            store_listing_version_id=store_listing_version_id,
+        )
+        submission = await store_db.review_store_submission(
+            store_listing_version_id=store_listing_version_id,
+            is_approved=request.is_approved,
+            external_comments=request.comments,
+            internal_comments=request.internal_comments or "",
+            reviewer_id=user_id,
+        )
 
-    state_changed = already_approved != request.is_approved
-    # Clear caches whenever approval state changes, since store visibility can change
-    if state_changed:
-        store_cache.clear_all_caches()
-    return submission
+        state_changed = already_approved != request.is_approved
+        # Clear caches when the request is approved as it updates what is shown on the store
+        if state_changed:
+            store_cache.clear_all_caches()
+        return submission
+    except Exception as e:
+        logger.exception("Error reviewing submission: %s", e)
+        return fastapi.responses.JSONResponse(
+            status_code=500,
+            content={"detail": "An error occurred while reviewing the submission"},
+        )
 
 
 @router.get(
@@ -134,40 +150,3 @@ async def admin_download_agent_file(
         return fastapi.responses.FileResponse(
             tmp_file.name, filename=file_name, media_type="application/json"
         )
-
-
-@router.get(
-    "/submissions/{store_listing_version_id}/preview",
-    summary="Admin Preview Submission Listing",
-)
-async def admin_preview_submission(
-    store_listing_version_id: str,
-) -> store_model.StoreAgentDetails:
-    """
-    Preview a marketplace submission as it would appear on the listing page.
-    Bypasses the APPROVED-only StoreAgent view so admins can preview pending
-    submissions before approving.
-    """
-    return await store_db.get_store_agent_details_as_admin(store_listing_version_id)
-
-
-@router.post(
-    "/submissions/{store_listing_version_id}/add-to-library",
-    summary="Admin Add Pending Agent to Library",
-    status_code=201,
-)
-async def admin_add_agent_to_library(
-    store_listing_version_id: str,
-    user_id: str = fastapi.Security(autogpt_libs.auth.get_user_id),
-) -> library_model.LibraryAgent:
-    """
-    Add a pending marketplace agent to the admin's library for review.
-    Uses admin-level access to bypass marketplace APPROVED-only checks.
-
-    The builder can load the graph because get_graph() checks library
-    membership as a fallback: "you added it, you keep it."
-    """
-    return await library_db.add_store_agent_to_library_as_admin(
-        store_listing_version_id=store_listing_version_id,
-        user_id=user_id,
-    )

autogpt_platform/backend/backend/api/features/admin/store_admin_routes_test.py

@@ -1,335 +0,0 @@
-"""Tests for admin store routes and the bypass logic they depend on.
-
-Tests are organized by what they protect:
-- SECRT-2162: get_graph_as_admin bypasses ownership/marketplace checks
-- SECRT-2167 security: admin endpoints reject non-admin users
-- SECRT-2167 bypass: preview queries StoreListingVersion (not StoreAgent view),
-  and add-to-library uses get_graph_as_admin (not get_graph)
-"""
-
-from datetime import datetime, timezone
-from unittest.mock import AsyncMock, MagicMock, patch
-
-import fastapi
-import fastapi.responses
-import fastapi.testclient
-import pytest
-import pytest_mock
-from autogpt_libs.auth.jwt_utils import get_jwt_payload
-
-from backend.data.graph import get_graph_as_admin
-from backend.util.exceptions import NotFoundError
-
-from .store_admin_routes import router as store_admin_router
-
-# Shared constants
-ADMIN_USER_ID = "admin-user-id"
-CREATOR_USER_ID = "other-creator-id"
-GRAPH_ID = "test-graph-id"
-GRAPH_VERSION = 3
-SLV_ID = "test-store-listing-version-id"
-
-
-def _make_mock_graph(user_id: str = CREATOR_USER_ID) -> MagicMock:
-    graph = MagicMock()
-    graph.userId = user_id
-    graph.id = GRAPH_ID
-    graph.version = GRAPH_VERSION
-    graph.Nodes = []
-    return graph
-
-
-# ---- SECRT-2162: get_graph_as_admin bypasses ownership checks ---- #
-
-
-@pytest.mark.asyncio
-async def test_admin_can_access_pending_agent_not_owned() -> None:
-    """get_graph_as_admin must return a graph even when the admin doesn't own
-    it and it's not APPROVED in the marketplace."""
-    mock_graph = _make_mock_graph()
-    mock_graph_model = MagicMock(name="GraphModel")
-
-    with (
-        patch("backend.data.graph.AgentGraph.prisma") as mock_prisma,
-        patch(
-            "backend.data.graph.GraphModel.from_db",
-            return_value=mock_graph_model,
-        ),
-    ):
-        mock_prisma.return_value.find_first = AsyncMock(return_value=mock_graph)
-
-        result = await get_graph_as_admin(
-            graph_id=GRAPH_ID,
-            version=GRAPH_VERSION,
-            user_id=ADMIN_USER_ID,
-            for_export=False,
-        )
-
-    assert result is mock_graph_model
-
-
-@pytest.mark.asyncio
-async def test_admin_download_pending_agent_with_subagents() -> None:
-    """get_graph_as_admin with for_export=True must call get_sub_graphs
-    and pass sub_graphs to GraphModel.from_db."""
-    mock_graph = _make_mock_graph()
-    mock_sub_graph = MagicMock(name="SubGraph")
-    mock_graph_model = MagicMock(name="GraphModel")
-
-    with (
-        patch("backend.data.graph.AgentGraph.prisma") as mock_prisma,
-        patch(
-            "backend.data.graph.get_sub_graphs",
-            new_callable=AsyncMock,
-            return_value=[mock_sub_graph],
-        ) as mock_get_sub,
-        patch(
-            "backend.data.graph.GraphModel.from_db",
-            return_value=mock_graph_model,
-        ) as mock_from_db,
-    ):
-        mock_prisma.return_value.find_first = AsyncMock(return_value=mock_graph)
-
-        result = await get_graph_as_admin(
-            graph_id=GRAPH_ID,
-            version=GRAPH_VERSION,
-            user_id=ADMIN_USER_ID,
-            for_export=True,
-        )
-
-    assert result is mock_graph_model
-    mock_get_sub.assert_awaited_once_with(mock_graph)
-    mock_from_db.assert_called_once_with(
-        graph=mock_graph,
-        sub_graphs=[mock_sub_graph],
-        for_export=True,
-    )
-
-
-# ---- SECRT-2167 security: admin endpoints reject non-admin users ---- #
-
-app = fastapi.FastAPI()
-app.include_router(store_admin_router)
-
-
-@app.exception_handler(NotFoundError)
-async def _not_found_handler(
-    request: fastapi.Request, exc: NotFoundError
-) -> fastapi.responses.JSONResponse:
-    return fastapi.responses.JSONResponse(status_code=404, content={"detail": str(exc)})
-
-
-client = fastapi.testclient.TestClient(app)
-
-
-@pytest.fixture(autouse=True)
-def setup_app_admin_auth(mock_jwt_admin):
-    """Setup admin auth overrides for all route tests in this module."""
-    app.dependency_overrides[get_jwt_payload] = mock_jwt_admin["get_jwt_payload"]
-    yield
-    app.dependency_overrides.clear()
-
-
-def test_preview_requires_admin(mock_jwt_user) -> None:
-    """Non-admin users must get 403 on the preview endpoint."""
-    app.dependency_overrides[get_jwt_payload] = mock_jwt_user["get_jwt_payload"]
-    response = client.get(f"/admin/submissions/{SLV_ID}/preview")
-    assert response.status_code == 403
-
-
-def test_add_to_library_requires_admin(mock_jwt_user) -> None:
-    """Non-admin users must get 403 on the add-to-library endpoint."""
-    app.dependency_overrides[get_jwt_payload] = mock_jwt_user["get_jwt_payload"]
-    response = client.post(f"/admin/submissions/{SLV_ID}/add-to-library")
-    assert response.status_code == 403
-
-
-def test_preview_nonexistent_submission(
-    mocker: pytest_mock.MockerFixture,
-) -> None:
-    """Preview of a nonexistent submission returns 404."""
-    mocker.patch(
-        "backend.api.features.admin.store_admin_routes.store_db"
-        ".get_store_agent_details_as_admin",
-        side_effect=NotFoundError("not found"),
-    )
-    response = client.get(f"/admin/submissions/{SLV_ID}/preview")
-    assert response.status_code == 404
-
-
-# ---- SECRT-2167 bypass: verify the right data sources are used ---- #
-
-
-@pytest.mark.asyncio
-async def test_preview_queries_store_listing_version_not_store_agent() -> None:
-    """get_store_agent_details_as_admin must query StoreListingVersion
-    directly (not the APPROVED-only StoreAgent view). This is THE test that
-    prevents the bypass from being accidentally reverted."""
-    from backend.api.features.store.db import get_store_agent_details_as_admin
-
-    mock_slv = MagicMock()
-    mock_slv.id = SLV_ID
-    mock_slv.name = "Test Agent"
-    mock_slv.subHeading = "Short desc"
-    mock_slv.description = "Long desc"
-    mock_slv.videoUrl = None
-    mock_slv.agentOutputDemoUrl = None
-    mock_slv.imageUrls = ["https://example.com/img.png"]
-    mock_slv.instructions = None
-    mock_slv.categories = ["productivity"]
-    mock_slv.version = 1
-    mock_slv.agentGraphId = GRAPH_ID
-    mock_slv.agentGraphVersion = GRAPH_VERSION
-    mock_slv.updatedAt = datetime(2026, 3, 24, tzinfo=timezone.utc)
-    mock_slv.recommendedScheduleCron = "0 9 * * *"
-
-    mock_listing = MagicMock()
-    mock_listing.id = "listing-id"
-    mock_listing.slug = "test-agent"
-    mock_listing.activeVersionId = SLV_ID
-    mock_listing.hasApprovedVersion = False
-    mock_listing.CreatorProfile = MagicMock(username="creator", avatarUrl="")
-    mock_slv.StoreListing = mock_listing
-
-    with (
-        patch(
-            "backend.api.features.store.db.prisma.models" ".StoreListingVersion.prisma",
-        ) as mock_slv_prisma,
-        patch(
-            "backend.api.features.store.db.prisma.models.StoreAgent.prisma",
-        ) as mock_store_agent_prisma,
-    ):
-        mock_slv_prisma.return_value.find_unique = AsyncMock(return_value=mock_slv)
-
-        result = await get_store_agent_details_as_admin(SLV_ID)
-
-    # Verify it queried StoreListingVersion (not the APPROVED-only StoreAgent)
-    mock_slv_prisma.return_value.find_unique.assert_awaited_once()
-    await_args = mock_slv_prisma.return_value.find_unique.await_args
-    assert await_args is not None
-    assert await_args.kwargs["where"] == {"id": SLV_ID}
-
-    # Verify the APPROVED-only StoreAgent view was NOT touched
-    mock_store_agent_prisma.assert_not_called()
-
-    # Verify the result has the right data
-    assert result.agent_name == "Test Agent"
-    assert result.agent_image == ["https://example.com/img.png"]
-    assert result.has_approved_version is False
-    assert result.runs == 0
-    assert result.rating == 0.0
-
-
-@pytest.mark.asyncio
-async def test_resolve_graph_admin_uses_get_graph_as_admin() -> None:
-    """resolve_graph_for_library(admin=True) must call get_graph_as_admin,
-    not get_graph. This is THE test that prevents the add-to-library bypass
-    from being accidentally reverted."""
-    from backend.api.features.library._add_to_library import resolve_graph_for_library
-
-    mock_slv = MagicMock()
-    mock_slv.AgentGraph = MagicMock(id=GRAPH_ID, version=GRAPH_VERSION)
-    mock_graph_model = MagicMock(name="GraphModel")
-
-    with (
-        patch(
-            "backend.api.features.library._add_to_library.prisma.models"
-            ".StoreListingVersion.prisma",
-        ) as mock_prisma,
-        patch(
-            "backend.api.features.library._add_to_library.graph_db"
-            ".get_graph_as_admin",
-            new_callable=AsyncMock,
-            return_value=mock_graph_model,
-        ) as mock_admin,
-        patch(
-            "backend.api.features.library._add_to_library.graph_db.get_graph",
-            new_callable=AsyncMock,
-        ) as mock_regular,
-    ):
-        mock_prisma.return_value.find_unique = AsyncMock(return_value=mock_slv)
-
-        result = await resolve_graph_for_library(SLV_ID, ADMIN_USER_ID, admin=True)
-
-    assert result is mock_graph_model
-    mock_admin.assert_awaited_once_with(
-        graph_id=GRAPH_ID, version=GRAPH_VERSION, user_id=ADMIN_USER_ID
-    )
-    mock_regular.assert_not_awaited()
-
-
-@pytest.mark.asyncio
-async def test_resolve_graph_regular_uses_get_graph() -> None:
-    """resolve_graph_for_library(admin=False) must call get_graph,
-    not get_graph_as_admin. Ensures the non-admin path is preserved."""
-    from backend.api.features.library._add_to_library import resolve_graph_for_library
-
-    mock_slv = MagicMock()
-    mock_slv.AgentGraph = MagicMock(id=GRAPH_ID, version=GRAPH_VERSION)
-    mock_graph_model = MagicMock(name="GraphModel")
-
-    with (
-        patch(
-            "backend.api.features.library._add_to_library.prisma.models"
-            ".StoreListingVersion.prisma",
-        ) as mock_prisma,
-        patch(
-            "backend.api.features.library._add_to_library.graph_db"
-            ".get_graph_as_admin",
-            new_callable=AsyncMock,
-        ) as mock_admin,
-        patch(
-            "backend.api.features.library._add_to_library.graph_db.get_graph",
-            new_callable=AsyncMock,
-            return_value=mock_graph_model,
-        ) as mock_regular,
-    ):
-        mock_prisma.return_value.find_unique = AsyncMock(return_value=mock_slv)
-
-        result = await resolve_graph_for_library(SLV_ID, "regular-user-id", admin=False)
-
-    assert result is mock_graph_model
-    mock_regular.assert_awaited_once_with(
-        graph_id=GRAPH_ID, version=GRAPH_VERSION, user_id="regular-user-id"
-    )
-    mock_admin.assert_not_awaited()
-
-
-# ---- Library membership grants graph access (product decision) ---- #
-
-
-@pytest.mark.asyncio
-async def test_library_member_can_view_pending_agent_in_builder() -> None:
-    """After adding a pending agent to their library, the user should be
-    able to load the graph in the builder via get_graph()."""
-    mock_graph = _make_mock_graph()
-    mock_graph_model = MagicMock(name="GraphModel")
-    mock_library_agent = MagicMock()
-    mock_library_agent.AgentGraph = mock_graph
-
-    with (
-        patch("backend.data.graph.AgentGraph.prisma") as mock_ag_prisma,
-        patch(
-            "backend.data.graph.StoreListingVersion.prisma",
-        ) as mock_slv_prisma,
-        patch("backend.data.graph.LibraryAgent.prisma") as mock_lib_prisma,
-        patch(
-            "backend.data.graph.GraphModel.from_db",
-            return_value=mock_graph_model,
-        ),
-    ):
-        mock_ag_prisma.return_value.find_first = AsyncMock(return_value=None)
-        mock_slv_prisma.return_value.find_first = AsyncMock(return_value=None)
-        mock_lib_prisma.return_value.find_first = AsyncMock(
-            return_value=mock_library_agent
-        )
-
-        from backend.data.graph import get_graph
-
-        result = await get_graph(
-            graph_id=GRAPH_ID,
-            version=GRAPH_VERSION,
-            user_id=ADMIN_USER_ID,
-        )
-
-    assert result is mock_graph_model, "Library membership should grant graph access"

autogpt_platform/backend/backend/api/features/builder/db.py

@@ -4,12 +4,14 @@ from difflib import SequenceMatcher
 from typing import Any, Sequence, get_args, get_origin
 
 import prisma
+from prisma.enums import ContentType
 from prisma.models import mv_suggested_blocks
 
 import backend.api.features.library.db as library_db
 import backend.api.features.library.model as library_model
 import backend.api.features.store.db as store_db
 import backend.api.features.store.model as store_model
+from backend.api.features.store.hybrid_search import unified_hybrid_search
 from backend.blocks import load_all_blocks
 from backend.blocks._base import (
     AnyBlockSchema,
@@ -22,7 +24,6 @@ from backend.blocks.llm import LlmModel
 from backend.integrations.providers import ProviderName
 from backend.util.cache import cached
 from backend.util.models import Pagination
-from backend.util.text import split_camelcase
 
 from .model import (
     BlockCategoryResponse,
@@ -270,7 +271,7 @@ async def _build_cached_search_results(
 
     # Use hybrid search when query is present, otherwise list all blocks
     if (include_blocks or include_integrations) and normalized_query:
-        block_results, block_total, integration_total = await _text_search_blocks(
+        block_results, block_total, integration_total = await _hybrid_search_blocks(
             query=search_query,
             include_blocks=include_blocks,
             include_integrations=include_integrations,
@@ -382,75 +383,117 @@ def _collect_block_results(
     return results, block_count, integration_count
 
 
-async def _text_search_blocks(
+async def _hybrid_search_blocks(
     *,
     query: str,
     include_blocks: bool,
     include_integrations: bool,
 ) -> tuple[list[_ScoredItem], int, int]:
     """
-    Search blocks using in-memory text matching over the block registry.
+    Search blocks using hybrid search with builder-specific filtering.
 
-    All blocks are already loaded in memory, so this is fast and reliable
-    regardless of whether OpenAI embeddings are available.
+    Uses unified_hybrid_search for semantic + lexical search, then applies
+    post-filtering for block/integration types and scoring adjustments.
 
     Scoring:
-        - Base: text relevance via _score_primary_fields, plus BLOCK_SCORE_BOOST
+        - Base: hybrid relevance score (0-1) scaled to 0-100, plus BLOCK_SCORE_BOOST
           to prioritize blocks over marketplace agents in combined results
+        - +30 for exact name match, +15 for prefix name match
         - +20 if the block has an LlmModel field and the query matches an LLM model name
+
+    Args:
+        query: The search query string
+        include_blocks: Whether to include regular blocks
+        include_integrations: Whether to include integration blocks
+
+    Returns:
+        Tuple of (scored_items, block_count, integration_count)
     """
     results: list[_ScoredItem] = []
+    block_count = 0
+    integration_count = 0
 
     if not include_blocks and not include_integrations:
-        return results, 0, 0
+        return results, block_count, integration_count
 
     normalized_query = query.strip().lower()
 
-    all_results, _, _ = _collect_block_results(
-        include_blocks=include_blocks,
-        include_integrations=include_integrations,
+    # Fetch more results to account for post-filtering
+    search_results, _ = await unified_hybrid_search(
+        query=query,
+        content_types=[ContentType.BLOCK],
+        page=1,
+        page_size=150,
+        min_score=0.10,
     )
 
+    # Load all blocks for getting BlockInfo
     all_blocks = load_all_blocks()
 
-    for item in all_results:
-        block_info = item.item
-        assert isinstance(block_info, BlockInfo)
-        name = split_camelcase(block_info.name).lower()
+    for result in search_results:
+        block_id = result["content_id"]
 
-        # Build rich description including input field descriptions,
-        # matching the searchable text that the embedding pipeline uses
-        desc_parts = [block_info.description or ""]
-        block_cls = all_blocks.get(block_info.id)
-        if block_cls is not None:
-            block: AnyBlockSchema = block_cls()
-            desc_parts += [
-                f"{f}: {info.description}"
-                for f, info in block.input_schema.model_fields.items()
-                if info.description
-            ]
-        description = " ".join(desc_parts).lower()
+        # Skip excluded blocks
+        if block_id in EXCLUDED_BLOCK_IDS:
+            continue
 
-        score = _score_primary_fields(name, description, normalized_query)
+        metadata = result.get("metadata", {})
+        hybrid_score = result.get("relevance", 0.0)
+
+        # Get the actual block class
+        if block_id not in all_blocks:
+            continue
+
+        block_cls = all_blocks[block_id]
+        block: AnyBlockSchema = block_cls()
+
+        if block.disabled:
+            continue
+
+        # Check block/integration filter using metadata
+        is_integration = metadata.get("is_integration", False)
+
+        if is_integration and not include_integrations:
+            continue
+        if not is_integration and not include_blocks:
+            continue
+
+        # Get block info
+        block_info = block.get_info()
+
+        # Calculate final score: scale hybrid score and add builder-specific bonuses
+        # Hybrid scores are 0-1, builder scores were 0-200+
+        # Add BLOCK_SCORE_BOOST to prioritize blocks over marketplace agents
+        final_score = hybrid_score * 100 + BLOCK_SCORE_BOOST
 
         # Add LLM model match bonus
-        if block_cls is not None and _matches_llm_model(
-            block_cls().input_schema, normalized_query
-        ):
-            score += 20
+        has_llm_field = metadata.get("has_llm_model_field", False)
+        if has_llm_field and _matches_llm_model(block.input_schema, normalized_query):
+            final_score += 20
 
-        if score >= MIN_SCORE_FOR_FILTERED_RESULTS:
-            results.append(
-                _ScoredItem(
-                    item=block_info,
-                    filter_type=item.filter_type,
-                    score=score + BLOCK_SCORE_BOOST,
-                    sort_key=name,
-                )
+        # Add exact/prefix match bonus for deterministic tie-breaking
+        name = block_info.name.lower()
+        if name == normalized_query:
+            final_score += 30
+        elif name.startswith(normalized_query):
+            final_score += 15
+
+        # Track counts
+        filter_type: FilterType = "integrations" if is_integration else "blocks"
+        if is_integration:
+            integration_count += 1
+        else:
+            block_count += 1
+
+        results.append(
+            _ScoredItem(
+                item=block_info,
+                filter_type=filter_type,
+                score=final_score,
+                sort_key=name,
             )
+        )
 
-    block_count = sum(1 for r in results if r.filter_type == "blocks")
-    integration_count = sum(1 for r in results if r.filter_type == "integrations")
     return results, block_count, integration_count
 
 

autogpt_platform/backend/backend/api/features/chat/routes.py

@@ -8,20 +8,18 @@ from typing import Annotated
 from uuid import uuid4
 
 from autogpt_libs import auth
-from fastapi import APIRouter, HTTPException, Query, Response, Security
+from fastapi import APIRouter, Depends, HTTPException, Query, Response, Security
 from fastapi.responses import StreamingResponse
 from prisma.models import UserWorkspaceFile
-from pydantic import BaseModel, ConfigDict, Field, field_validator
+from pydantic import BaseModel, Field, field_validator
 
 from backend.copilot import service as chat_service
 from backend.copilot import stream_registry
-from backend.copilot.config import ChatConfig, CopilotMode
-from backend.copilot.db import get_chat_messages_paginated
+from backend.copilot.config import ChatConfig
 from backend.copilot.executor.utils import enqueue_cancel_task, enqueue_copilot_turn
 from backend.copilot.model import (
     ChatMessage,
     ChatSession,
-    ChatSessionMetadata,
     append_and_save_message,
     create_chat_session,
     delete_chat_session,
@@ -29,20 +27,7 @@ from backend.copilot.model import (
     get_user_sessions,
     update_session_title,
 )
-from backend.copilot.rate_limit import (
-    CoPilotUsageStatus,
-    RateLimitExceeded,
-    acquire_reset_lock,
-    check_rate_limit,
-    get_daily_reset_count,
-    get_global_rate_limits,
-    get_usage_status,
-    increment_daily_reset_count,
-    release_reset_lock,
-    reset_daily_usage,
-)
 from backend.copilot.response_model import StreamError, StreamFinish, StreamHeartbeat
-from backend.copilot.tools.e2b_sandbox import kill_sandbox
 from backend.copilot.tools.models import (
     AgentDetailsResponse,
     AgentOutputResponse,
@@ -67,16 +52,8 @@ from backend.copilot.tools.models import (
     UnderstandingUpdatedResponse,
 )
 from backend.copilot.tracking import track_user_message
-from backend.data.credit import UsageTransactionMetadata, get_user_credit_model
-from backend.data.redis_client import get_redis_async
-from backend.data.understanding import get_business_understanding
 from backend.data.workspace import get_or_create_workspace
-from backend.util.exceptions import InsufficientBalanceError, NotFoundError
-from backend.util.settings import Settings
-
-settings = Settings()
-
-logger = logging.getLogger(__name__)
+from backend.util.exceptions import NotFoundError
 
 config = ChatConfig()
 
@@ -84,6 +61,8 @@ _UUID_RE = re.compile(
     r"^[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12}$", re.I
 )
 
+logger = logging.getLogger(__name__)
+
 
 async def _validate_and_get_session(
     session_id: str,
@@ -112,23 +91,6 @@ class StreamChatRequest(BaseModel):
     file_ids: list[str] | None = Field(
         default=None, max_length=20
     )  # Workspace file IDs attached to this message
-    mode: CopilotMode | None = Field(
-        default=None,
-        description="Autopilot mode: 'fast' for baseline LLM, 'extended_thinking' for Claude Agent SDK. "
-        "If None, uses the server default (extended_thinking).",
-    )
-
-
-class CreateSessionRequest(BaseModel):
-    """Request model for creating a new chat session.
-
-    ``dry_run`` is a **top-level** field — do not nest it inside ``metadata``.
-    Extra/unknown fields are rejected (422) to prevent silent mis-use.
-    """
-
-    model_config = ConfigDict(extra="forbid")
-
-    dry_run: bool = False
 
 
 class CreateSessionResponse(BaseModel):
@@ -137,7 +99,6 @@ class CreateSessionResponse(BaseModel):
     id: str
     created_at: str
     user_id: str | None
-    metadata: ChatSessionMetadata = ChatSessionMetadata()
 
 
 class ActiveStreamInfo(BaseModel):
@@ -156,11 +117,6 @@ class SessionDetailResponse(BaseModel):
     user_id: str | None
     messages: list[dict]
     active_stream: ActiveStreamInfo | None = None  # Present if stream is still active
-    has_more_messages: bool = False
-    oldest_sequence: int | None = None
-    total_prompt_tokens: int = 0
-    total_completion_tokens: int = 0
-    metadata: ChatSessionMetadata = ChatSessionMetadata()
 
 
 class SessionSummaryResponse(BaseModel):
@@ -170,7 +126,6 @@ class SessionSummaryResponse(BaseModel):
     created_at: str
     updated_at: str
     title: str | None = None
-    is_processing: bool
 
 
 class ListSessionsResponse(BaseModel):
@@ -229,28 +184,6 @@ async def list_sessions(
     """
     sessions, total_count = await get_user_sessions(user_id, limit, offset)
 
-    # Batch-check Redis for active stream status on each session
-    processing_set: set[str] = set()
-    if sessions:
-        try:
-            redis = await get_redis_async()
-            pipe = redis.pipeline(transaction=False)
-            for session in sessions:
-                pipe.hget(
-                    f"{config.session_meta_prefix}{session.session_id}",
-                    "status",
-                )
-            statuses = await pipe.execute()
-            processing_set = {
-                session.session_id
-                for session, st in zip(sessions, statuses)
-                if st == "running"
-            }
-        except Exception:
-            logger.warning(
-                "Failed to fetch processing status from Redis; defaulting to empty"
-            )
-
     return ListSessionsResponse(
         sessions=[
             SessionSummaryResponse(
@@ -258,7 +191,6 @@ async def list_sessions(
                 created_at=session.started_at.isoformat(),
                 updated_at=session.updated_at.isoformat(),
                 title=session.title,
-                is_processing=session.session_id in processing_set,
             )
             for session in sessions
         ],
@@ -270,8 +202,7 @@ async def list_sessions(
     "/sessions",
 )
 async def create_session(
-    user_id: Annotated[str, Security(auth.get_user_id)],
-    request: CreateSessionRequest | None = None,
+    user_id: Annotated[str, Depends(auth.get_user_id)],
 ) -> CreateSessionResponse:
     """
     Create a new chat session.
@@ -280,28 +211,22 @@ async def create_session(
 
     Args:
         user_id: The authenticated user ID parsed from the JWT (required).
-        request: Optional request body. When provided, ``dry_run=True``
-            forces run_block and run_agent calls to use dry-run simulation.
 
     Returns:
         CreateSessionResponse: Details of the created session.
 
     """
-    dry_run = request.dry_run if request else False
-
     logger.info(
         f"Creating session with user_id: "
         f"...{user_id[-8:] if len(user_id) > 8 else '<redacted>'}"
-        f"{', dry_run=True' if dry_run else ''}"
     )
 
-    session = await create_chat_session(user_id, dry_run=dry_run)
+    session = await create_chat_session(user_id)
 
     return CreateSessionResponse(
         id=session.session_id,
         created_at=session.started_at.isoformat(),
         user_id=session.user_id,
-        metadata=session.metadata,
     )
 
 
@@ -340,12 +265,12 @@ async def delete_session(
         )
 
     # Best-effort cleanup of the E2B sandbox (if any).
-    # sandbox_id is in Redis; kill_sandbox() fetches it from there.
-    e2b_cfg = ChatConfig()
-    if e2b_cfg.e2b_active:
-        assert e2b_cfg.e2b_api_key  # guaranteed by e2b_active check
+    config = ChatConfig()
+    if config.use_e2b_sandbox and config.e2b_api_key:
+        from backend.copilot.tools.e2b_sandbox import kill_sandbox
+
         try:
-            await kill_sandbox(session_id, e2b_cfg.e2b_api_key)
+            await kill_sandbox(session_id, config.e2b_api_key)
         except Exception:
             logger.warning(
                 "[E2B] Failed to kill sandbox for session %s", session_id[:12]
@@ -396,278 +321,54 @@ async def update_session_title_route(
 )
 async def get_session(
     session_id: str,
-    user_id: Annotated[str, Security(auth.get_user_id)],
-    limit: int = Query(default=50, ge=1, le=200),
-    before_sequence: int | None = Query(default=None, ge=0),
+    user_id: Annotated[str | None, Depends(auth.get_user_id)],
 ) -> SessionDetailResponse:
     """
     Retrieve the details of a specific chat session.
 
-    Supports cursor-based pagination via ``limit`` and ``before_sequence``.
-    When no pagination params are provided, returns the most recent messages.
+    Looks up a chat session by ID for the given user (if authenticated) and returns all session data including messages.
+    If there's an active stream for this session, returns active_stream info for reconnection.
 
     Args:
         session_id: The unique identifier for the desired chat session.
-        user_id: The authenticated user's ID.
-        limit: Maximum number of messages to return (1-200, default 50).
-        before_sequence: Return messages with sequence < this value (cursor).
+        user_id: The optional authenticated user ID, or None for anonymous access.
 
     Returns:
-        SessionDetailResponse: Details for the requested session, including
-            active_stream info and pagination metadata.
+        SessionDetailResponse: Details for the requested session, including active_stream info if applicable.
+
     """
-    page = await get_chat_messages_paginated(
-        session_id, limit, before_sequence, user_id=user_id
-    )
-    if page is None:
+    session = await get_chat_session(session_id, user_id)
+    if not session:
         raise NotFoundError(f"Session {session_id} not found.")
-    messages = [message.model_dump() for message in page.messages]
 
-    # Only check active stream on initial load (not on "load more" requests)
+    messages = [message.model_dump() for message in session.messages]
+
+    # Check if there's an active stream for this session
     active_stream_info = None
-    if before_sequence is None:
-        active_session, last_message_id = await stream_registry.get_active_session(
-            session_id, user_id
+    active_session, last_message_id = await stream_registry.get_active_session(
+        session_id, user_id
+    )
+    logger.info(
+        f"[GET_SESSION] session={session_id}, active_session={active_session is not None}, "
+        f"msg_count={len(messages)}, last_role={messages[-1].get('role') if messages else 'none'}"
+    )
+    if active_session:
+        # Keep the assistant message (including tool_calls) so the frontend can
+        # render the correct tool UI (e.g. CreateAgent with mini game).
+        # convertChatSessionToUiMessages handles isComplete=false by setting
+        # tool parts without output to state "input-available".
+        active_stream_info = ActiveStreamInfo(
+            turn_id=active_session.turn_id,
+            last_message_id=last_message_id,
         )
-        logger.info(
-            f"[GET_SESSION] session={session_id}, active_session={active_session is not None}, "
-            f"msg_count={len(messages)}, last_role={messages[-1].get('role') if messages else 'none'}"
-        )
-        if active_session:
-            active_stream_info = ActiveStreamInfo(
-                turn_id=active_session.turn_id,
-                last_message_id=last_message_id,
-            )
-
-    # Skip session metadata on "load more" — frontend only needs messages
-    if before_sequence is not None:
-        return SessionDetailResponse(
-            id=page.session.session_id,
-            created_at=page.session.started_at.isoformat(),
-            updated_at=page.session.updated_at.isoformat(),
-            user_id=page.session.user_id or None,
-            messages=messages,
-            active_stream=None,
-            has_more_messages=page.has_more,
-            oldest_sequence=page.oldest_sequence,
-            total_prompt_tokens=0,
-            total_completion_tokens=0,
-        )
-
-    total_prompt = sum(u.prompt_tokens for u in page.session.usage)
-    total_completion = sum(u.completion_tokens for u in page.session.usage)
 
     return SessionDetailResponse(
-        id=page.session.session_id,
-        created_at=page.session.started_at.isoformat(),
-        updated_at=page.session.updated_at.isoformat(),
-        user_id=page.session.user_id or None,
+        id=session.session_id,
+        created_at=session.started_at.isoformat(),
+        updated_at=session.updated_at.isoformat(),
+        user_id=session.user_id or None,
         messages=messages,
         active_stream=active_stream_info,
-        has_more_messages=page.has_more,
-        oldest_sequence=page.oldest_sequence,
-        total_prompt_tokens=total_prompt,
-        total_completion_tokens=total_completion,
-        metadata=page.session.metadata,
-    )
-
-
-@router.get(
-    "/usage",
-)
-async def get_copilot_usage(
-    user_id: Annotated[str, Security(auth.get_user_id)],
-) -> CoPilotUsageStatus:
-    """Get CoPilot usage status for the authenticated user.
-
-    Returns current token usage vs limits for daily and weekly windows.
-    Global defaults sourced from LaunchDarkly (falling back to config).
-    Includes the user's rate-limit tier.
-    """
-    daily_limit, weekly_limit, tier = await get_global_rate_limits(
-        user_id, config.daily_token_limit, config.weekly_token_limit
-    )
-    return await get_usage_status(
-        user_id=user_id,
-        daily_token_limit=daily_limit,
-        weekly_token_limit=weekly_limit,
-        rate_limit_reset_cost=config.rate_limit_reset_cost,
-        tier=tier,
-    )
-
-
-class RateLimitResetResponse(BaseModel):
-    """Response from resetting the daily rate limit."""
-
-    success: bool
-    credits_charged: int = Field(description="Credits charged (in cents)")
-    remaining_balance: int = Field(description="Credit balance after charge (in cents)")
-    usage: CoPilotUsageStatus = Field(description="Updated usage status after reset")
-
-
-@router.post(
-    "/usage/reset",
-    status_code=200,
-    responses={
-        400: {
-            "description": "Bad Request (feature disabled or daily limit not reached)"
-        },
-        402: {"description": "Payment Required (insufficient credits)"},
-        429: {
-            "description": "Too Many Requests (max daily resets exceeded or reset in progress)"
-        },
-        503: {
-            "description": "Service Unavailable (Redis reset failed; credits refunded or support needed)"
-        },
-    },
-)
-async def reset_copilot_usage(
-    user_id: Annotated[str, Security(auth.get_user_id)],
-) -> RateLimitResetResponse:
-    """Reset the daily CoPilot rate limit by spending credits.
-
-    Allows users who have hit their daily token limit to spend credits
-    to reset their daily usage counter and continue working.
-    Returns 400 if the feature is disabled or the user is not over the limit.
-    Returns 402 if the user has insufficient credits.
-    """
-    cost = config.rate_limit_reset_cost
-    if cost <= 0:
-        raise HTTPException(
-            status_code=400,
-            detail="Rate limit reset is not available.",
-        )
-
-    if not settings.config.enable_credit:
-        raise HTTPException(
-            status_code=400,
-            detail="Rate limit reset is not available (credit system is disabled).",
-        )
-
-    daily_limit, weekly_limit, tier = await get_global_rate_limits(
-        user_id, config.daily_token_limit, config.weekly_token_limit
-    )
-
-    if daily_limit <= 0:
-        raise HTTPException(
-            status_code=400,
-            detail="No daily limit is configured — nothing to reset.",
-        )
-
-    # Check max daily resets.  get_daily_reset_count returns None when Redis
-    # is unavailable; reject the reset in that case to prevent unlimited
-    # free resets when the counter store is down.
-    reset_count = await get_daily_reset_count(user_id)
-    if reset_count is None:
-        raise HTTPException(
-            status_code=503,
-            detail="Unable to verify reset eligibility — please try again later.",
-        )
-    if config.max_daily_resets > 0 and reset_count >= config.max_daily_resets:
-        raise HTTPException(
-            status_code=429,
-            detail=f"You've used all {config.max_daily_resets} resets for today.",
-        )
-
-    # Acquire a per-user lock to prevent TOCTOU races (concurrent resets).
-    if not await acquire_reset_lock(user_id):
-        raise HTTPException(
-            status_code=429,
-            detail="A reset is already in progress. Please try again.",
-        )
-
-    try:
-        # Verify the user is actually at or over their daily limit.
-        # (rate_limit_reset_cost intentionally omitted — this object is only
-        # used for limit checks, not returned to the client.)
-        usage_status = await get_usage_status(
-            user_id=user_id,
-            daily_token_limit=daily_limit,
-            weekly_token_limit=weekly_limit,
-            tier=tier,
-        )
-        if daily_limit > 0 and usage_status.daily.used < daily_limit:
-            raise HTTPException(
-                status_code=400,
-                detail="You have not reached your daily limit yet.",
-            )
-
-        # If the weekly limit is also exhausted, resetting the daily counter
-        # won't help — the user would still be blocked by the weekly limit.
-        if weekly_limit > 0 and usage_status.weekly.used >= weekly_limit:
-            raise HTTPException(
-                status_code=400,
-                detail="Your weekly limit is also reached. Resetting the daily limit won't help.",
-            )
-
-        # Charge credits.
-        credit_model = await get_user_credit_model(user_id)
-        try:
-            remaining = await credit_model.spend_credits(
-                user_id=user_id,
-                cost=cost,
-                metadata=UsageTransactionMetadata(
-                    reason="CoPilot daily rate limit reset",
-                ),
-            )
-        except InsufficientBalanceError as e:
-            raise HTTPException(
-                status_code=402,
-                detail="Insufficient credits to reset your rate limit.",
-            ) from e
-
-        # Reset daily usage in Redis.  If this fails, refund the credits
-        # so the user is not charged for a service they did not receive.
-        if not await reset_daily_usage(user_id, daily_token_limit=daily_limit):
-            # Compensate: refund the charged credits.
-            refunded = False
-            try:
-                await credit_model.top_up_credits(user_id, cost)
-                refunded = True
-                logger.warning(
-                    "Refunded %d credits to user %s after Redis reset failure",
-                    cost,
-                    user_id[:8],
-                )
-            except Exception:
-                logger.error(
-                    "CRITICAL: Failed to refund %d credits to user %s "
-                    "after Redis reset failure — manual intervention required",
-                    cost,
-                    user_id[:8],
-                    exc_info=True,
-                )
-            if refunded:
-                raise HTTPException(
-                    status_code=503,
-                    detail="Rate limit reset failed — please try again later. "
-                    "Your credits have not been charged.",
-                )
-            raise HTTPException(
-                status_code=503,
-                detail="Rate limit reset failed and the automatic refund "
-                "also failed. Please contact support for assistance.",
-            )
-
-        # Track the reset count for daily cap enforcement.
-        await increment_daily_reset_count(user_id)
-    finally:
-        await release_reset_lock(user_id)
-
-    # Return updated usage status.
-    updated_usage = await get_usage_status(
-        user_id=user_id,
-        daily_token_limit=daily_limit,
-        weekly_token_limit=weekly_limit,
-        rate_limit_reset_cost=config.rate_limit_reset_cost,
-        tier=tier,
-    )
-
-    return RateLimitResetResponse(
-        success=True,
-        credits_charged=cost,
-        remaining_balance=remaining,
-        usage=updated_usage,
     )
 
 
@@ -677,7 +378,7 @@ async def reset_copilot_usage(
 )
 async def cancel_session_task(
     session_id: str,
-    user_id: Annotated[str, Security(auth.get_user_id)],
+    user_id: Annotated[str | None, Depends(auth.get_user_id)],
 ) -> CancelSessionResponse:
     """Cancel the active streaming task for a session.
 
@@ -722,7 +423,7 @@ async def cancel_session_task(
 async def stream_chat_post(
     session_id: str,
     request: StreamChatRequest,
-    user_id: str = Security(auth.get_user_id),
+    user_id: str | None = Depends(auth.get_user_id),
 ):
     """
     Stream chat responses for a session (POST with context support).
@@ -739,7 +440,7 @@ async def stream_chat_post(
     Args:
         session_id: The chat session identifier to associate with the streamed messages.
         request: Request body containing message, is_user_message, and optional context.
-        user_id: Authenticated user ID.
+        user_id: Optional authenticated user ID.
     Returns:
         StreamingResponse: SSE-formatted response chunks.
 
@@ -748,7 +449,9 @@ async def stream_chat_post(
     import time
 
     stream_start_time = time.perf_counter()
-    log_meta = {"component": "ChatStream", "session_id": session_id, "user_id": user_id}
+    log_meta = {"component": "ChatStream", "session_id": session_id}
+    if user_id:
+        log_meta["user_id"] = user_id
 
     logger.info(
         f"[TIMING] stream_chat_post STARTED, session={session_id}, "
@@ -766,22 +469,6 @@ async def stream_chat_post(
         },
     )
 
-    # Pre-turn rate limit check (token-based).
-    # check_rate_limit short-circuits internally when both limits are 0.
-    # Global defaults sourced from LaunchDarkly, falling back to config.
-    if user_id:
-        try:
-            daily_limit, weekly_limit, _ = await get_global_rate_limits(
-                user_id, config.daily_token_limit, config.weekly_token_limit
-            )
-            await check_rate_limit(
-                user_id=user_id,
-                daily_token_limit=daily_limit,
-                weekly_token_limit=weekly_limit,
-            )
-        except RateLimitExceeded as e:
-            raise HTTPException(status_code=429, detail=str(e)) from e
-
     # Enrich message with file metadata if file_ids are provided.
     # Also sanitise file_ids so only validated, workspace-scoped IDs are
     # forwarded downstream (e.g. to the executor via enqueue_copilot_turn).
@@ -866,7 +553,6 @@ async def stream_chat_post(
         is_user_message=request.is_user_message,
         context=request.context,
         file_ids=sanitized_file_ids,
-        mode=request.mode,
     )
 
     setup_time = (time.perf_counter() - stream_start_time) * 1000
@@ -1017,7 +703,7 @@ async def stream_chat_post(
 )
 async def resume_session_stream(
     session_id: str,
-    user_id: str = Security(auth.get_user_id),
+    user_id: str | None = Depends(auth.get_user_id),
 ):
     """
     Resume an active stream for a session.
@@ -1119,6 +805,7 @@ async def resume_session_stream(
 @router.patch(
     "/sessions/{session_id}/assign-user",
     dependencies=[Security(auth.requires_user)],
+    status_code=200,
 )
 async def session_assign_user(
     session_id: str,
@@ -1141,47 +828,6 @@ async def session_assign_user(
     return {"status": "ok"}
 
 
-# ========== Suggested Prompts ==========
-
-
-class SuggestedTheme(BaseModel):
-    """A themed group of suggested prompts."""
-
-    name: str
-    prompts: list[str]
-
-
-class SuggestedPromptsResponse(BaseModel):
-    """Response model for user-specific suggested prompts grouped by theme."""
-
-    themes: list[SuggestedTheme]
-
-
-@router.get(
-    "/suggested-prompts",
-    dependencies=[Security(auth.requires_user)],
-)
-async def get_suggested_prompts(
-    user_id: Annotated[str, Security(auth.get_user_id)],
-) -> SuggestedPromptsResponse:
-    """
-    Get LLM-generated suggested prompts grouped by theme.
-
-    Returns personalized quick-action prompts based on the user's
-    business understanding. Returns empty themes list if no custom
-    prompts are available.
-    """
-    understanding = await get_business_understanding(user_id)
-    if understanding is None or not understanding.suggested_prompts:
-        return SuggestedPromptsResponse(themes=[])
-
-    themes = [
-        SuggestedTheme(name=name, prompts=prompts)
-        for name, prompts in understanding.suggested_prompts.items()
-    ]
-    return SuggestedPromptsResponse(themes=themes)
-
-
 # ========== Configuration ==========
 
 
@@ -1230,7 +876,7 @@ async def health_check() -> dict:
     )
 
     # Create and retrieve session to verify full data layer
-    session = await create_chat_session(health_check_user_id, dry_run=False)
+    session = await create_chat_session(health_check_user_id)
     await get_chat_session(session.session_id, health_check_user_id)
 
     return {

autogpt_platform/backend/backend/api/features/chat/routes_test.py

@@ -1,7 +1,6 @@
-"""Tests for chat API routes: session title update, file attachment validation, usage, and rate limiting."""
+"""Tests for chat API routes: session title update and file attachment validation."""
 
-from datetime import UTC, datetime, timedelta
-from unittest.mock import AsyncMock, MagicMock
+from unittest.mock import AsyncMock
 
 import fastapi
 import fastapi.testclient
@@ -9,7 +8,6 @@ import pytest
 import pytest_mock
 
 from backend.api.features.chat import routes as chat_routes
-from backend.copilot.rate_limit import SubscriptionTier
 
 app = fastapi.FastAPI()
 app.include_router(chat_routes.router)
@@ -251,331 +249,3 @@ def test_file_ids_scoped_to_workspace(mocker: pytest_mock.MockFixture):
     call_kwargs = mock_prisma.find_many.call_args[1]
     assert call_kwargs["where"]["workspaceId"] == "my-workspace-id"
     assert call_kwargs["where"]["isDeleted"] is False
-
-
-# ─── Rate limit → 429 ─────────────────────────────────────────────────
-
-
-def test_stream_chat_returns_429_on_daily_rate_limit(mocker: pytest_mock.MockFixture):
-    """When check_rate_limit raises RateLimitExceeded for daily limit the endpoint returns 429."""
-    from backend.copilot.rate_limit import RateLimitExceeded
-
-    _mock_stream_internals(mocker)
-    # Ensure the rate-limit branch is entered by setting a non-zero limit.
-    mocker.patch.object(chat_routes.config, "daily_token_limit", 10000)
-    mocker.patch.object(chat_routes.config, "weekly_token_limit", 50000)
-    mocker.patch(
-        "backend.api.features.chat.routes.check_rate_limit",
-        side_effect=RateLimitExceeded("daily", datetime.now(UTC) + timedelta(hours=1)),
-    )
-
-    response = client.post(
-        "/sessions/sess-1/stream",
-        json={"message": "hello"},
-    )
-    assert response.status_code == 429
-    assert "daily" in response.json()["detail"].lower()
-
-
-def test_stream_chat_returns_429_on_weekly_rate_limit(mocker: pytest_mock.MockFixture):
-    """When check_rate_limit raises RateLimitExceeded for weekly limit the endpoint returns 429."""
-    from backend.copilot.rate_limit import RateLimitExceeded
-
-    _mock_stream_internals(mocker)
-    mocker.patch.object(chat_routes.config, "daily_token_limit", 10000)
-    mocker.patch.object(chat_routes.config, "weekly_token_limit", 50000)
-    resets_at = datetime.now(UTC) + timedelta(days=3)
-    mocker.patch(
-        "backend.api.features.chat.routes.check_rate_limit",
-        side_effect=RateLimitExceeded("weekly", resets_at),
-    )
-
-    response = client.post(
-        "/sessions/sess-1/stream",
-        json={"message": "hello"},
-    )
-    assert response.status_code == 429
-    detail = response.json()["detail"].lower()
-    assert "weekly" in detail
-    assert "resets in" in detail
-
-
-def test_stream_chat_429_includes_reset_time(mocker: pytest_mock.MockFixture):
-    """The 429 response detail should include the human-readable reset time."""
-    from backend.copilot.rate_limit import RateLimitExceeded
-
-    _mock_stream_internals(mocker)
-    mocker.patch.object(chat_routes.config, "daily_token_limit", 10000)
-    mocker.patch.object(chat_routes.config, "weekly_token_limit", 50000)
-    mocker.patch(
-        "backend.api.features.chat.routes.check_rate_limit",
-        side_effect=RateLimitExceeded(
-            "daily", datetime.now(UTC) + timedelta(hours=2, minutes=30)
-        ),
-    )
-
-    response = client.post(
-        "/sessions/sess-1/stream",
-        json={"message": "hello"},
-    )
-    assert response.status_code == 429
-    detail = response.json()["detail"]
-    assert "2h" in detail
-    assert "Resets in" in detail
-
-
-# ─── Usage endpoint ───────────────────────────────────────────────────
-
-
-def _mock_usage(
-    mocker: pytest_mock.MockerFixture,
-    *,
-    daily_used: int = 500,
-    weekly_used: int = 2000,
-    daily_limit: int = 10000,
-    weekly_limit: int = 50000,
-    tier: "SubscriptionTier" = SubscriptionTier.FREE,
-) -> AsyncMock:
-    """Mock get_usage_status and get_global_rate_limits for usage endpoint tests.
-
-    Mocks both ``get_global_rate_limits`` (returns the given limits + tier) and
-    ``get_usage_status`` so that tests exercise the endpoint without hitting
-    LaunchDarkly or Prisma.
-    """
-    from backend.copilot.rate_limit import CoPilotUsageStatus, UsageWindow
-
-    mocker.patch(
-        "backend.api.features.chat.routes.get_global_rate_limits",
-        new_callable=AsyncMock,
-        return_value=(daily_limit, weekly_limit, tier),
-    )
-
-    resets_at = datetime.now(UTC) + timedelta(days=1)
-    status = CoPilotUsageStatus(
-        daily=UsageWindow(used=daily_used, limit=daily_limit, resets_at=resets_at),
-        weekly=UsageWindow(used=weekly_used, limit=weekly_limit, resets_at=resets_at),
-    )
-    return mocker.patch(
-        "backend.api.features.chat.routes.get_usage_status",
-        new_callable=AsyncMock,
-        return_value=status,
-    )
-
-
-def test_usage_returns_daily_and_weekly(
-    mocker: pytest_mock.MockerFixture,
-    test_user_id: str,
-) -> None:
-    """GET /usage returns daily and weekly usage."""
-    mock_get = _mock_usage(mocker, daily_used=500, weekly_used=2000)
-
-    mocker.patch.object(chat_routes.config, "daily_token_limit", 10000)
-    mocker.patch.object(chat_routes.config, "weekly_token_limit", 50000)
-
-    response = client.get("/usage")
-
-    assert response.status_code == 200
-    data = response.json()
-    assert data["daily"]["used"] == 500
-    assert data["weekly"]["used"] == 2000
-
-    mock_get.assert_called_once_with(
-        user_id=test_user_id,
-        daily_token_limit=10000,
-        weekly_token_limit=50000,
-        rate_limit_reset_cost=chat_routes.config.rate_limit_reset_cost,
-        tier=SubscriptionTier.FREE,
-    )
-
-
-def test_usage_uses_config_limits(
-    mocker: pytest_mock.MockerFixture,
-    test_user_id: str,
-) -> None:
-    """The endpoint forwards resolved limits from get_global_rate_limits to get_usage_status."""
-    mock_get = _mock_usage(mocker, daily_limit=99999, weekly_limit=77777)
-
-    mocker.patch.object(chat_routes.config, "rate_limit_reset_cost", 500)
-
-    response = client.get("/usage")
-
-    assert response.status_code == 200
-    mock_get.assert_called_once_with(
-        user_id=test_user_id,
-        daily_token_limit=99999,
-        weekly_token_limit=77777,
-        rate_limit_reset_cost=500,
-        tier=SubscriptionTier.FREE,
-    )
-
-
-def test_usage_rejects_unauthenticated_request() -> None:
-    """GET /usage should return 401 when no valid JWT is provided."""
-    unauthenticated_app = fastapi.FastAPI()
-    unauthenticated_app.include_router(chat_routes.router)
-    unauthenticated_client = fastapi.testclient.TestClient(unauthenticated_app)
-
-    response = unauthenticated_client.get("/usage")
-
-    assert response.status_code == 401
-
-
-# ─── Suggested prompts endpoint ──────────────────────────────────────
-
-
-def _mock_get_business_understanding(
-    mocker: pytest_mock.MockerFixture,
-    *,
-    return_value=None,
-):
-    """Mock get_business_understanding."""
-    return mocker.patch(
-        "backend.api.features.chat.routes.get_business_understanding",
-        new_callable=AsyncMock,
-        return_value=return_value,
-    )
-
-
-def test_suggested_prompts_returns_themes(
-    mocker: pytest_mock.MockerFixture,
-    test_user_id: str,
-) -> None:
-    """User with themed prompts gets them back as themes list."""
-    mock_understanding = MagicMock()
-    mock_understanding.suggested_prompts = {
-        "Learn": ["L1", "L2"],
-        "Create": ["C1"],
-    }
-    _mock_get_business_understanding(mocker, return_value=mock_understanding)
-
-    response = client.get("/suggested-prompts")
-
-    assert response.status_code == 200
-    data = response.json()
-    assert "themes" in data
-    themes_by_name = {t["name"]: t["prompts"] for t in data["themes"]}
-    assert themes_by_name["Learn"] == ["L1", "L2"]
-    assert themes_by_name["Create"] == ["C1"]
-
-
-def test_suggested_prompts_no_understanding(
-    mocker: pytest_mock.MockerFixture,
-    test_user_id: str,
-) -> None:
-    """User with no understanding gets empty themes list."""
-    _mock_get_business_understanding(mocker, return_value=None)
-
-    response = client.get("/suggested-prompts")
-
-    assert response.status_code == 200
-    assert response.json() == {"themes": []}
-
-
-def test_suggested_prompts_empty_prompts(
-    mocker: pytest_mock.MockerFixture,
-    test_user_id: str,
-) -> None:
-    """User with understanding but empty prompts gets empty themes list."""
-    mock_understanding = MagicMock()
-    mock_understanding.suggested_prompts = {}
-    _mock_get_business_understanding(mocker, return_value=mock_understanding)
-
-    response = client.get("/suggested-prompts")
-
-    assert response.status_code == 200
-    assert response.json() == {"themes": []}
-
-
-# ─── Create session: dry_run contract ─────────────────────────────────
-
-
-def _mock_create_chat_session(mocker: pytest_mock.MockerFixture):
-    """Mock create_chat_session to return a fake session."""
-    from backend.copilot.model import ChatSession
-
-    async def _fake_create(user_id: str, *, dry_run: bool):
-        return ChatSession.new(user_id, dry_run=dry_run)
-
-    return mocker.patch(
-        "backend.api.features.chat.routes.create_chat_session",
-        new_callable=AsyncMock,
-        side_effect=_fake_create,
-    )
-
-
-def test_create_session_dry_run_true(
-    mocker: pytest_mock.MockerFixture,
-    test_user_id: str,
-) -> None:
-    """Sending ``{"dry_run": true}`` sets metadata.dry_run to True."""
-    _mock_create_chat_session(mocker)
-
-    response = client.post("/sessions", json={"dry_run": True})
-
-    assert response.status_code == 200
-    assert response.json()["metadata"]["dry_run"] is True
-
-
-def test_create_session_dry_run_default_false(
-    mocker: pytest_mock.MockerFixture,
-    test_user_id: str,
-) -> None:
-    """Empty body defaults dry_run to False."""
-    _mock_create_chat_session(mocker)
-
-    response = client.post("/sessions")
-
-    assert response.status_code == 200
-    assert response.json()["metadata"]["dry_run"] is False
-
-
-def test_create_session_rejects_nested_metadata(
-    test_user_id: str,
-) -> None:
-    """Sending ``{"metadata": {"dry_run": true}}`` must return 422, not silently
-    default to ``dry_run=False``. This guards against the common mistake of
-    nesting dry_run inside metadata instead of providing it at the top level."""
-    response = client.post(
-        "/sessions",
-        json={"metadata": {"dry_run": True}},
-    )
-
-    assert response.status_code == 422
-
-
-class TestStreamChatRequestModeValidation:
-    """Pydantic-level validation of the ``mode`` field on StreamChatRequest."""
-
-    def test_rejects_invalid_mode_value(self) -> None:
-        """Any string outside the Literal set must raise ValidationError."""
-        from pydantic import ValidationError
-
-        from backend.api.features.chat.routes import StreamChatRequest
-
-        with pytest.raises(ValidationError):
-            StreamChatRequest(message="hi", mode="turbo")  # type: ignore[arg-type]
-
-    def test_accepts_fast_mode(self) -> None:
-        from backend.api.features.chat.routes import StreamChatRequest
-
-        req = StreamChatRequest(message="hi", mode="fast")
-        assert req.mode == "fast"
-
-    def test_accepts_extended_thinking_mode(self) -> None:
-        from backend.api.features.chat.routes import StreamChatRequest
-
-        req = StreamChatRequest(message="hi", mode="extended_thinking")
-        assert req.mode == "extended_thinking"
-
-    def test_accepts_none_mode(self) -> None:
-        """``mode=None`` is valid (server decides via feature flags)."""
-        from backend.api.features.chat.routes import StreamChatRequest
-
-        req = StreamChatRequest(message="hi", mode=None)
-        assert req.mode is None
-
-    def test_mode_defaults_to_none_when_omitted(self) -> None:
-        from backend.api.features.chat.routes import StreamChatRequest
-
-        req = StreamChatRequest(message="hi")
-        assert req.mode is None

autogpt_platform/backend/backend/api/features/executions/review/review_routes_test.py

@@ -638,7 +638,7 @@ async def test_process_review_action_auto_approve_creates_auto_approval_records(
 
     # Mock get_node_executions to return node_id mapping
     mock_get_node_executions = mocker.patch(
-        "backend.api.features.executions.review.routes.get_node_executions"
+        "backend.data.execution.get_node_executions"
     )
     mock_node_exec = mocker.Mock(spec=NodeExecutionResult)
     mock_node_exec.node_exec_id = "test_node_123"
@@ -936,7 +936,7 @@ async def test_process_review_action_auto_approve_only_applies_to_approved_revie
 
     # Mock get_node_executions to return node_id mapping
     mock_get_node_executions = mocker.patch(
-        "backend.api.features.executions.review.routes.get_node_executions"
+        "backend.data.execution.get_node_executions"
     )
     mock_node_exec = mocker.Mock(spec=NodeExecutionResult)
     mock_node_exec.node_exec_id = "node_exec_approved"
@@ -1148,7 +1148,7 @@ async def test_process_review_action_per_review_auto_approve_granularity(
 
     # Mock get_node_executions to return batch node data
     mock_get_node_executions = mocker.patch(
-        "backend.api.features.executions.review.routes.get_node_executions"
+        "backend.data.execution.get_node_executions"
     )
     # Create mock node executions for each review
     mock_node_execs = []

autogpt_platform/backend/backend/api/features/executions/review/routes.py

@@ -6,15 +6,10 @@ import autogpt_libs.auth as autogpt_auth_lib
 from fastapi import APIRouter, HTTPException, Query, Security, status
 from prisma.enums import ReviewStatus
 
-from backend.copilot.constants import (
-    is_copilot_synthetic_id,
-    parse_node_id_from_exec_id,
-)
 from backend.data.execution import (
     ExecutionContext,
     ExecutionStatus,
     get_graph_execution_meta,
-    get_node_executions,
 )
 from backend.data.graph import get_graph_settings
 from backend.data.human_review import (
@@ -41,38 +36,6 @@ router = APIRouter(
 )
 
 
-async def _resolve_node_ids(
-    node_exec_ids: list[str],
-    graph_exec_id: str,
-    is_copilot: bool,
-) -> dict[str, str]:
-    """Resolve node_exec_id -> node_id for auto-approval records.
-
-    CoPilot synthetic IDs encode node_id in the format "{node_id}:{random}".
-    Graph executions look up node_id from NodeExecution records.
-    """
-    if not node_exec_ids:
-        return {}
-
-    if is_copilot:
-        return {neid: parse_node_id_from_exec_id(neid) for neid in node_exec_ids}
-
-    node_execs = await get_node_executions(
-        graph_exec_id=graph_exec_id, include_exec_data=False
-    )
-    node_exec_map = {ne.node_exec_id: ne.node_id for ne in node_execs}
-
-    result = {}
-    for neid in node_exec_ids:
-        if neid in node_exec_map:
-            result[neid] = node_exec_map[neid]
-        else:
-            logger.error(
-                f"Failed to resolve node_id for {neid}: Node execution not found."
-            )
-    return result
-
-
 @router.get(
     "/pending",
     summary="Get Pending Reviews",
@@ -147,16 +110,14 @@ async def list_pending_reviews_for_execution(
     """
 
     # Verify user owns the graph execution before returning reviews
-    # (CoPilot synthetic IDs don't have graph execution records)
-    if not is_copilot_synthetic_id(graph_exec_id):
-        graph_exec = await get_graph_execution_meta(
-            user_id=user_id, execution_id=graph_exec_id
+    graph_exec = await get_graph_execution_meta(
+        user_id=user_id, execution_id=graph_exec_id
+    )
+    if not graph_exec:
+        raise HTTPException(
+            status_code=status.HTTP_404_NOT_FOUND,
+            detail=f"Graph execution #{graph_exec_id} not found",
         )
-        if not graph_exec:
-            raise HTTPException(
-                status_code=status.HTTP_404_NOT_FOUND,
-                detail=f"Graph execution #{graph_exec_id} not found",
-            )
 
     return await get_pending_reviews_for_execution(graph_exec_id, user_id)
 
@@ -199,26 +160,30 @@ async def process_review_action(
         )
 
     graph_exec_id = next(iter(graph_exec_ids))
-    is_copilot = is_copilot_synthetic_id(graph_exec_id)
 
-    # Validate execution status for graph executions (skip for CoPilot synthetic IDs)
-    if not is_copilot:
-        graph_exec_meta = await get_graph_execution_meta(
-            user_id=user_id, execution_id=graph_exec_id
+    # Validate execution status before processing reviews
+    graph_exec_meta = await get_graph_execution_meta(
+        user_id=user_id, execution_id=graph_exec_id
+    )
+
+    if not graph_exec_meta:
+        raise HTTPException(
+            status_code=status.HTTP_404_NOT_FOUND,
+            detail=f"Graph execution #{graph_exec_id} not found",
+        )
+
+    # Only allow processing reviews if execution is paused for review
+    # or incomplete (partial execution with some reviews already processed)
+    if graph_exec_meta.status not in (
+        ExecutionStatus.REVIEW,
+        ExecutionStatus.INCOMPLETE,
+    ):
+        raise HTTPException(
+            status_code=status.HTTP_409_CONFLICT,
+            detail=f"Cannot process reviews while execution status is {graph_exec_meta.status}. "
+            f"Reviews can only be processed when execution is paused (REVIEW status). "
+            f"Current status: {graph_exec_meta.status}",
         )
-        if not graph_exec_meta:
-            raise HTTPException(
-                status_code=status.HTTP_404_NOT_FOUND,
-                detail=f"Graph execution #{graph_exec_id} not found",
-            )
-        if graph_exec_meta.status not in (
-            ExecutionStatus.REVIEW,
-            ExecutionStatus.INCOMPLETE,
-        ):
-            raise HTTPException(
-                status_code=status.HTTP_409_CONFLICT,
-                detail=f"Cannot process reviews while execution status is {graph_exec_meta.status}",
-            )
 
     # Build review decisions map and track which reviews requested auto-approval
     # Auto-approved reviews use original data (no modifications allowed)
@@ -271,7 +236,7 @@ async def process_review_action(
             )
             return (node_id, False)
 
-    # Collect node_exec_ids that need auto-approval and resolve their node_ids
+    # Collect node_exec_ids that need auto-approval
     node_exec_ids_needing_auto_approval = [
         node_exec_id
         for node_exec_id, review_result in updated_reviews.items()
@@ -279,16 +244,29 @@ async def process_review_action(
         and auto_approve_requests.get(node_exec_id, False)
     ]
 
-    node_id_map = await _resolve_node_ids(
-        node_exec_ids_needing_auto_approval, graph_exec_id, is_copilot
-    )
-
-    # Deduplicate by node_id — one auto-approval per node
+    # Batch-fetch node executions to get node_ids
     nodes_needing_auto_approval: dict[str, Any] = {}
-    for node_exec_id in node_exec_ids_needing_auto_approval:
-        node_id = node_id_map.get(node_exec_id)
-        if node_id and node_id not in nodes_needing_auto_approval:
-            nodes_needing_auto_approval[node_id] = updated_reviews[node_exec_id]
+    if node_exec_ids_needing_auto_approval:
+        from backend.data.execution import get_node_executions
+
+        node_execs = await get_node_executions(
+            graph_exec_id=graph_exec_id, include_exec_data=False
+        )
+        node_exec_map = {node_exec.node_exec_id: node_exec for node_exec in node_execs}
+
+        for node_exec_id in node_exec_ids_needing_auto_approval:
+            node_exec = node_exec_map.get(node_exec_id)
+            if node_exec:
+                review_result = updated_reviews[node_exec_id]
+                # Use the first approved review for this node (deduplicate by node_id)
+                if node_exec.node_id not in nodes_needing_auto_approval:
+                    nodes_needing_auto_approval[node_exec.node_id] = review_result
+            else:
+                logger.error(
+                    f"Failed to create auto-approval record for {node_exec_id}: "
+                    f"Node execution not found. This may indicate a race condition "
+                    f"or data inconsistency."
+                )
 
     # Execute all auto-approval creations in parallel (deduplicated by node_id)
     auto_approval_results = await asyncio.gather(
@@ -303,11 +281,13 @@ async def process_review_action(
     auto_approval_failed_count = 0
     for result in auto_approval_results:
         if isinstance(result, Exception):
+            # Unexpected exception during auto-approval creation
             auto_approval_failed_count += 1
             logger.error(
                 f"Unexpected exception during auto-approval creation: {result}"
             )
         elif isinstance(result, tuple) and len(result) == 2 and not result[1]:
+            # Auto-approval creation failed (returned False)
             auto_approval_failed_count += 1
 
     # Count results
@@ -322,20 +302,22 @@ async def process_review_action(
         if review.status == ReviewStatus.REJECTED
     )
 
-    # Resume graph execution only for real graph executions (not CoPilot)
-    # CoPilot sessions are resumed by the LLM retrying run_block with review_id
-    if not is_copilot and updated_reviews:
+    # Resume execution only if ALL pending reviews for this execution have been processed
+    if updated_reviews:
         still_has_pending = await has_pending_reviews_for_graph_exec(graph_exec_id)
 
         if not still_has_pending:
+            # Get the graph_id from any processed review
             first_review = next(iter(updated_reviews.values()))
 
             try:
+                # Fetch user and settings to build complete execution context
                 user = await get_user_by_id(user_id)
                 settings = await get_graph_settings(
                     user_id=user_id, graph_id=first_review.graph_id
                 )
 
+                # Preserve user's timezone preference when resuming execution
                 user_timezone = (
                     user.timezone if user.timezone != USER_TIMEZONE_NOT_SET else "UTC"
                 )

autogpt_platform/backend/backend/api/features/integrations/conftest.py

@@ -1,13 +0,0 @@
-"""Override session-scoped fixtures so unit tests run without the server."""
-
-import pytest
-
-
-@pytest.fixture(scope="session")
-def server():
-    yield None
-
-
-@pytest.fixture(scope="session", autouse=True)
-def graph_cleanup():
-    yield

autogpt_platform/backend/backend/api/features/integrations/router.py

@@ -34,21 +34,16 @@ from backend.data.model import (
     HostScopedCredentials,
     OAuth2Credentials,
     UserIntegrations,
-    is_sdk_default,
 )
 from backend.data.onboarding import OnboardingStep, complete_onboarding_step
 from backend.data.user import get_user_integrations
 from backend.executor.utils import add_graph_execution
 from backend.integrations.ayrshare import AyrshareClient, SocialPlatform
-from backend.integrations.credentials_store import (
-    is_system_credential,
-    provider_matches,
-)
+from backend.integrations.credentials_store import provider_matches
 from backend.integrations.creds_manager import (
     IntegrationCredentialsManager,
     create_mcp_oauth_handler,
 )
-from backend.integrations.managed_credentials import ensure_managed_credentials
 from backend.integrations.oauth import CREDENTIALS_BY_PROVIDER, HANDLERS_BY_NAME
 from backend.integrations.providers import ProviderName
 from backend.integrations.webhooks import get_webhook_manager
@@ -114,7 +109,6 @@ class CredentialsMetaResponse(BaseModel):
         default=None,
         description="Host pattern for host-scoped or MCP server URL for MCP credentials",
     )
-    is_managed: bool = False
 
     @model_validator(mode="before")
     @classmethod
@@ -144,19 +138,6 @@ class CredentialsMetaResponse(BaseModel):
         return None
 
 
-def to_meta_response(cred: Credentials) -> CredentialsMetaResponse:
-    return CredentialsMetaResponse(
-        id=cred.id,
-        provider=cred.provider,
-        type=cred.type,
-        title=cred.title,
-        scopes=cred.scopes if isinstance(cred, OAuth2Credentials) else None,
-        username=cred.username if isinstance(cred, OAuth2Credentials) else None,
-        host=CredentialsMetaResponse.get_host(cred),
-        is_managed=cred.is_managed,
-    )
-
-
 @router.post("/{provider}/callback", summary="Exchange OAuth code for tokens")
 async def callback(
     provider: Annotated[
@@ -223,20 +204,34 @@ async def callback(
         f"and provider {provider.value}"
     )
 
-    return to_meta_response(credentials)
+    return CredentialsMetaResponse(
+        id=credentials.id,
+        provider=credentials.provider,
+        type=credentials.type,
+        title=credentials.title,
+        scopes=credentials.scopes,
+        username=credentials.username,
+        host=(CredentialsMetaResponse.get_host(credentials)),
+    )
 
 
 @router.get("/credentials", summary="List Credentials")
 async def list_credentials(
     user_id: Annotated[str, Security(get_user_id)],
 ) -> list[CredentialsMetaResponse]:
-    # Fire-and-forget: provision missing managed credentials in the background.
-    # The credential appears on the next page load; listing is never blocked.
-    asyncio.create_task(ensure_managed_credentials(user_id, creds_manager.store))
     credentials = await creds_manager.store.get_all_creds(user_id)
 
     return [
-        to_meta_response(cred) for cred in credentials if not is_sdk_default(cred.id)
+        CredentialsMetaResponse(
+            id=cred.id,
+            provider=cred.provider,
+            type=cred.type,
+            title=cred.title,
+            scopes=cred.scopes if isinstance(cred, OAuth2Credentials) else None,
+            username=cred.username if isinstance(cred, OAuth2Credentials) else None,
+            host=CredentialsMetaResponse.get_host(cred),
+        )
+        for cred in credentials
     ]
 
 
@@ -247,11 +242,19 @@ async def list_credentials_by_provider(
     ],
     user_id: Annotated[str, Security(get_user_id)],
 ) -> list[CredentialsMetaResponse]:
-    asyncio.create_task(ensure_managed_credentials(user_id, creds_manager.store))
     credentials = await creds_manager.store.get_creds_by_provider(user_id, provider)
 
     return [
-        to_meta_response(cred) for cred in credentials if not is_sdk_default(cred.id)
+        CredentialsMetaResponse(
+            id=cred.id,
+            provider=cred.provider,
+            type=cred.type,
+            title=cred.title,
+            scopes=cred.scopes if isinstance(cred, OAuth2Credentials) else None,
+            username=cred.username if isinstance(cred, OAuth2Credentials) else None,
+            host=CredentialsMetaResponse.get_host(cred),
+        )
+        for cred in credentials
     ]
 
 
@@ -264,21 +267,18 @@ async def get_credential(
     ],
     cred_id: Annotated[str, Path(title="The ID of the credentials to retrieve")],
     user_id: Annotated[str, Security(get_user_id)],
-) -> CredentialsMetaResponse:
-    if is_sdk_default(cred_id):
-        raise HTTPException(
-            status_code=status.HTTP_404_NOT_FOUND, detail="Credentials not found"
-        )
+) -> Credentials:
     credential = await creds_manager.get(user_id, cred_id)
     if not credential:
         raise HTTPException(
             status_code=status.HTTP_404_NOT_FOUND, detail="Credentials not found"
         )
-    if not provider_matches(credential.provider, provider):
+    if credential.provider != provider:
         raise HTTPException(
-            status_code=status.HTTP_404_NOT_FOUND, detail="Credentials not found"
+            status_code=status.HTTP_404_NOT_FOUND,
+            detail="Credentials do not match the specified provider",
         )
-    return to_meta_response(credential)
+    return credential
 
 
 @router.post("/{provider}/credentials", status_code=201, summary="Create Credentials")
@@ -288,22 +288,16 @@ async def create_credentials(
         ProviderName, Path(title="The provider to create credentials for")
     ],
     credentials: Credentials,
-) -> CredentialsMetaResponse:
-    if is_sdk_default(credentials.id):
-        raise HTTPException(
-            status_code=status.HTTP_403_FORBIDDEN,
-            detail="Cannot create credentials with a reserved ID",
-        )
+) -> Credentials:
     credentials.provider = provider
     try:
         await creds_manager.create(user_id, credentials)
-    except Exception:
-        logger.exception("Failed to store credentials")
+    except Exception as e:
         raise HTTPException(
             status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
-            detail="Failed to store credentials",
+            detail=f"Failed to store credentials: {str(e)}",
         )
-    return to_meta_response(credentials)
+    return credentials
 
 
 class CredentialsDeletionResponse(BaseModel):
@@ -338,29 +332,15 @@ async def delete_credentials(
         bool, Query(title="Whether to proceed if any linked webhooks are still in use")
     ] = False,
 ) -> CredentialsDeletionResponse | CredentialsDeletionNeedsConfirmationResponse:
-    if is_sdk_default(cred_id):
-        raise HTTPException(
-            status_code=status.HTTP_404_NOT_FOUND, detail="Credentials not found"
-        )
-    if is_system_credential(cred_id):
-        raise HTTPException(
-            status_code=status.HTTP_403_FORBIDDEN,
-            detail="System-managed credentials cannot be deleted",
-        )
     creds = await creds_manager.store.get_creds_by_id(user_id, cred_id)
     if not creds:
         raise HTTPException(
             status_code=status.HTTP_404_NOT_FOUND, detail="Credentials not found"
         )
-    if not provider_matches(creds.provider, provider):
+    if creds.provider != provider:
         raise HTTPException(
             status_code=status.HTTP_404_NOT_FOUND,
-            detail="Credentials not found",
-        )
-    if creds.is_managed:
-        raise HTTPException(
-            status_code=status.HTTP_403_FORBIDDEN,
-            detail="AutoGPT-managed credentials cannot be deleted",
+            detail="Credentials do not match the specified provider",
         )
 
     try:

autogpt_platform/backend/backend/api/features/integrations/router_test.py

@@ -1,570 +0,0 @@
-"""Tests for credentials API security: no secret leakage, SDK defaults filtered."""
-
-from contextlib import asynccontextmanager
-from unittest.mock import AsyncMock, MagicMock, patch
-
-import fastapi
-import fastapi.testclient
-import pytest
-from pydantic import SecretStr
-
-from backend.api.features.integrations.router import router
-from backend.data.model import (
-    APIKeyCredentials,
-    HostScopedCredentials,
-    OAuth2Credentials,
-    UserPasswordCredentials,
-)
-
-app = fastapi.FastAPI()
-app.include_router(router)
-client = fastapi.testclient.TestClient(app)
-
-TEST_USER_ID = "test-user-id"
-
-
-def _make_api_key_cred(cred_id: str = "cred-123", provider: str = "openai"):
-    return APIKeyCredentials(
-        id=cred_id,
-        provider=provider,
-        title="My API Key",
-        api_key=SecretStr("sk-secret-key-value"),
-    )
-
-
-def _make_oauth2_cred(cred_id: str = "cred-456", provider: str = "github"):
-    return OAuth2Credentials(
-        id=cred_id,
-        provider=provider,
-        title="My OAuth",
-        access_token=SecretStr("ghp_secret_token"),
-        refresh_token=SecretStr("ghp_refresh_secret"),
-        scopes=["repo", "user"],
-        username="testuser",
-    )
-
-
-def _make_user_password_cred(cred_id: str = "cred-789", provider: str = "openai"):
-    return UserPasswordCredentials(
-        id=cred_id,
-        provider=provider,
-        title="My Login",
-        username=SecretStr("admin"),
-        password=SecretStr("s3cret-pass"),
-    )
-
-
-def _make_host_scoped_cred(cred_id: str = "cred-host", provider: str = "openai"):
-    return HostScopedCredentials(
-        id=cred_id,
-        provider=provider,
-        title="Host Cred",
-        host="https://api.example.com",
-        headers={"Authorization": SecretStr("Bearer top-secret")},
-    )
-
-
-def _make_sdk_default_cred(provider: str = "openai"):
-    return APIKeyCredentials(
-        id=f"{provider}-default",
-        provider=provider,
-        title=f"{provider} (default)",
-        api_key=SecretStr("sk-platform-secret-key"),
-    )
-
-
-@pytest.fixture(autouse=True)
-def setup_auth(mock_jwt_user):
-    from autogpt_libs.auth.jwt_utils import get_jwt_payload
-
-    app.dependency_overrides[get_jwt_payload] = mock_jwt_user["get_jwt_payload"]
-    yield
-    app.dependency_overrides.clear()
-
-
-class TestGetCredentialReturnsMetaOnly:
-    """GET /{provider}/credentials/{cred_id} must not return secrets."""
-
-    def test_api_key_credential_no_secret(self):
-        cred = _make_api_key_cred()
-        with (
-            patch.object(router, "dependencies", []),
-            patch("backend.api.features.integrations.router.creds_manager") as mock_mgr,
-        ):
-            mock_mgr.get = AsyncMock(return_value=cred)
-            resp = client.get("/openai/credentials/cred-123")
-
-        assert resp.status_code == 200
-        data = resp.json()
-        assert data["id"] == "cred-123"
-        assert data["provider"] == "openai"
-        assert data["type"] == "api_key"
-        assert "api_key" not in data
-        assert "sk-secret-key-value" not in str(data)
-
-    def test_oauth2_credential_no_secret(self):
-        cred = _make_oauth2_cred()
-        with patch(
-            "backend.api.features.integrations.router.creds_manager"
-        ) as mock_mgr:
-            mock_mgr.get = AsyncMock(return_value=cred)
-            resp = client.get("/github/credentials/cred-456")
-
-        assert resp.status_code == 200
-        data = resp.json()
-        assert data["id"] == "cred-456"
-        assert data["scopes"] == ["repo", "user"]
-        assert data["username"] == "testuser"
-        assert "access_token" not in data
-        assert "refresh_token" not in data
-        assert "ghp_" not in str(data)
-
-    def test_user_password_credential_no_secret(self):
-        cred = _make_user_password_cred()
-        with patch(
-            "backend.api.features.integrations.router.creds_manager"
-        ) as mock_mgr:
-            mock_mgr.get = AsyncMock(return_value=cred)
-            resp = client.get("/openai/credentials/cred-789")
-
-        assert resp.status_code == 200
-        data = resp.json()
-        assert data["id"] == "cred-789"
-        assert "password" not in data
-        assert "username" not in data or data["username"] is None
-        assert "s3cret-pass" not in str(data)
-        assert "admin" not in str(data)
-
-    def test_host_scoped_credential_no_secret(self):
-        cred = _make_host_scoped_cred()
-        with patch(
-            "backend.api.features.integrations.router.creds_manager"
-        ) as mock_mgr:
-            mock_mgr.get = AsyncMock(return_value=cred)
-            resp = client.get("/openai/credentials/cred-host")
-
-        assert resp.status_code == 200
-        data = resp.json()
-        assert data["id"] == "cred-host"
-        assert data["host"] == "https://api.example.com"
-        assert "headers" not in data
-        assert "top-secret" not in str(data)
-
-    def test_get_credential_wrong_provider_returns_404(self):
-        """Provider mismatch should return generic 404, not leak credential existence."""
-        cred = _make_api_key_cred(provider="openai")
-        with patch(
-            "backend.api.features.integrations.router.creds_manager"
-        ) as mock_mgr:
-            mock_mgr.get = AsyncMock(return_value=cred)
-            resp = client.get("/github/credentials/cred-123")
-
-        assert resp.status_code == 404
-        assert resp.json()["detail"] == "Credentials not found"
-
-    def test_list_credentials_no_secrets(self):
-        """List endpoint must not leak secrets in any credential."""
-        creds = [_make_api_key_cred(), _make_oauth2_cred()]
-        with patch(
-            "backend.api.features.integrations.router.creds_manager"
-        ) as mock_mgr:
-            mock_mgr.store.get_all_creds = AsyncMock(return_value=creds)
-            resp = client.get("/credentials")
-
-        assert resp.status_code == 200
-        raw = str(resp.json())
-        assert "sk-secret-key-value" not in raw
-        assert "ghp_secret_token" not in raw
-        assert "ghp_refresh_secret" not in raw
-
-
-class TestSdkDefaultCredentialsNotAccessible:
-    """SDK default credentials (ID ending in '-default') must be hidden."""
-
-    def test_get_sdk_default_returns_404(self):
-        with patch(
-            "backend.api.features.integrations.router.creds_manager"
-        ) as mock_mgr:
-            mock_mgr.get = AsyncMock()
-            resp = client.get("/openai/credentials/openai-default")
-
-        assert resp.status_code == 404
-        mock_mgr.get.assert_not_called()
-
-    def test_list_credentials_excludes_sdk_defaults(self):
-        user_cred = _make_api_key_cred()
-        sdk_cred = _make_sdk_default_cred("openai")
-        with patch(
-            "backend.api.features.integrations.router.creds_manager"
-        ) as mock_mgr:
-            mock_mgr.store.get_all_creds = AsyncMock(return_value=[user_cred, sdk_cred])
-            resp = client.get("/credentials")
-
-        assert resp.status_code == 200
-        data = resp.json()
-        ids = [c["id"] for c in data]
-        assert "cred-123" in ids
-        assert "openai-default" not in ids
-
-    def test_list_by_provider_excludes_sdk_defaults(self):
-        user_cred = _make_api_key_cred()
-        sdk_cred = _make_sdk_default_cred("openai")
-        with patch(
-            "backend.api.features.integrations.router.creds_manager"
-        ) as mock_mgr:
-            mock_mgr.store.get_creds_by_provider = AsyncMock(
-                return_value=[user_cred, sdk_cred]
-            )
-            resp = client.get("/openai/credentials")
-
-        assert resp.status_code == 200
-        data = resp.json()
-        ids = [c["id"] for c in data]
-        assert "cred-123" in ids
-        assert "openai-default" not in ids
-
-    def test_delete_sdk_default_returns_404(self):
-        with patch(
-            "backend.api.features.integrations.router.creds_manager"
-        ) as mock_mgr:
-            mock_mgr.store.get_creds_by_id = AsyncMock()
-            resp = client.request("DELETE", "/openai/credentials/openai-default")
-
-        assert resp.status_code == 404
-        mock_mgr.store.get_creds_by_id.assert_not_called()
-
-
-class TestCreateCredentialNoSecretInResponse:
-    """POST /{provider}/credentials must not return secrets."""
-
-    def test_create_api_key_no_secret_in_response(self):
-        with patch(
-            "backend.api.features.integrations.router.creds_manager"
-        ) as mock_mgr:
-            mock_mgr.create = AsyncMock()
-            resp = client.post(
-                "/openai/credentials",
-                json={
-                    "id": "new-cred",
-                    "provider": "openai",
-                    "type": "api_key",
-                    "title": "New Key",
-                    "api_key": "sk-newsecret",
-                },
-            )
-
-        assert resp.status_code == 201
-        data = resp.json()
-        assert data["id"] == "new-cred"
-        assert "api_key" not in data
-        assert "sk-newsecret" not in str(data)
-
-    def test_create_with_sdk_default_id_rejected(self):
-        with patch(
-            "backend.api.features.integrations.router.creds_manager"
-        ) as mock_mgr:
-            mock_mgr.create = AsyncMock()
-            resp = client.post(
-                "/openai/credentials",
-                json={
-                    "id": "openai-default",
-                    "provider": "openai",
-                    "type": "api_key",
-                    "title": "Sneaky",
-                    "api_key": "sk-evil",
-                },
-            )
-
-        assert resp.status_code == 403
-        mock_mgr.create.assert_not_called()
-
-
-class TestManagedCredentials:
-    """AutoGPT-managed credentials cannot be deleted by users."""
-
-    def test_delete_is_managed_returns_403(self):
-        cred = APIKeyCredentials(
-            id="managed-cred-1",
-            provider="agent_mail",
-            title="AgentMail (managed by AutoGPT)",
-            api_key=SecretStr("sk-managed-key"),
-            is_managed=True,
-        )
-        with patch(
-            "backend.api.features.integrations.router.creds_manager"
-        ) as mock_mgr:
-            mock_mgr.store.get_creds_by_id = AsyncMock(return_value=cred)
-            resp = client.request("DELETE", "/agent_mail/credentials/managed-cred-1")
-
-        assert resp.status_code == 403
-        assert "AutoGPT-managed" in resp.json()["detail"]
-
-    def test_list_credentials_includes_is_managed_field(self):
-        managed = APIKeyCredentials(
-            id="managed-1",
-            provider="agent_mail",
-            title="AgentMail (managed)",
-            api_key=SecretStr("sk-key"),
-            is_managed=True,
-        )
-        regular = APIKeyCredentials(
-            id="regular-1",
-            provider="openai",
-            title="My Key",
-            api_key=SecretStr("sk-key"),
-        )
-        with patch(
-            "backend.api.features.integrations.router.creds_manager"
-        ) as mock_mgr:
-            mock_mgr.store.get_all_creds = AsyncMock(return_value=[managed, regular])
-            resp = client.get("/credentials")
-
-        assert resp.status_code == 200
-        data = resp.json()
-        managed_cred = next(c for c in data if c["id"] == "managed-1")
-        regular_cred = next(c for c in data if c["id"] == "regular-1")
-        assert managed_cred["is_managed"] is True
-        assert regular_cred["is_managed"] is False
-
-
-# ---------------------------------------------------------------------------
-# Managed credential provisioning infrastructure
-# ---------------------------------------------------------------------------
-
-
-def _make_managed_cred(
-    provider: str = "agent_mail", pod_id: str = "pod-abc"
-) -> APIKeyCredentials:
-    return APIKeyCredentials(
-        id="managed-auto",
-        provider=provider,
-        title="AgentMail (managed by AutoGPT)",
-        api_key=SecretStr("sk-pod-key"),
-        is_managed=True,
-        metadata={"pod_id": pod_id},
-    )
-
-
-def _make_store_mock(**kwargs) -> MagicMock:
-    """Create a store mock with a working async ``locks()`` context manager."""
-
-    @asynccontextmanager
-    async def _noop_locked(key):
-        yield
-
-    locks_obj = MagicMock()
-    locks_obj.locked = _noop_locked
-
-    store = MagicMock(**kwargs)
-    store.locks = AsyncMock(return_value=locks_obj)
-    return store
-
-
-class TestEnsureManagedCredentials:
-    """Unit tests for the ensure/cleanup helpers in managed_credentials.py."""
-
-    @pytest.mark.asyncio
-    async def test_provisions_when_missing(self):
-        """Provider.provision() is called when no managed credential exists."""
-        from backend.integrations.managed_credentials import (
-            _PROVIDERS,
-            _provisioned_users,
-            ensure_managed_credentials,
-        )
-
-        cred = _make_managed_cred()
-        provider = MagicMock()
-        provider.provider_name = "test_provider"
-        provider.is_available = AsyncMock(return_value=True)
-        provider.provision = AsyncMock(return_value=cred)
-
-        store = _make_store_mock()
-        store.has_managed_credential = AsyncMock(return_value=False)
-        store.add_managed_credential = AsyncMock()
-
-        saved = dict(_PROVIDERS)
-        _PROVIDERS.clear()
-        _PROVIDERS["test_provider"] = provider
-        _provisioned_users.pop("user-1", None)
-        try:
-            await ensure_managed_credentials("user-1", store)
-        finally:
-            _PROVIDERS.clear()
-            _PROVIDERS.update(saved)
-            _provisioned_users.pop("user-1", None)
-
-        provider.provision.assert_awaited_once_with("user-1")
-        store.add_managed_credential.assert_awaited_once_with("user-1", cred)
-
-    @pytest.mark.asyncio
-    async def test_skips_when_already_exists(self):
-        """Provider.provision() is NOT called when managed credential exists."""
-        from backend.integrations.managed_credentials import (
-            _PROVIDERS,
-            _provisioned_users,
-            ensure_managed_credentials,
-        )
-
-        provider = MagicMock()
-        provider.provider_name = "test_provider"
-        provider.is_available = AsyncMock(return_value=True)
-        provider.provision = AsyncMock()
-
-        store = _make_store_mock()
-        store.has_managed_credential = AsyncMock(return_value=True)
-
-        saved = dict(_PROVIDERS)
-        _PROVIDERS.clear()
-        _PROVIDERS["test_provider"] = provider
-        _provisioned_users.pop("user-1", None)
-        try:
-            await ensure_managed_credentials("user-1", store)
-        finally:
-            _PROVIDERS.clear()
-            _PROVIDERS.update(saved)
-            _provisioned_users.pop("user-1", None)
-
-        provider.provision.assert_not_awaited()
-
-    @pytest.mark.asyncio
-    async def test_skips_when_unavailable(self):
-        """Provider.provision() is NOT called when provider is not available."""
-        from backend.integrations.managed_credentials import (
-            _PROVIDERS,
-            _provisioned_users,
-            ensure_managed_credentials,
-        )
-
-        provider = MagicMock()
-        provider.provider_name = "test_provider"
-        provider.is_available = AsyncMock(return_value=False)
-        provider.provision = AsyncMock()
-
-        store = _make_store_mock()
-        store.has_managed_credential = AsyncMock()
-
-        saved = dict(_PROVIDERS)
-        _PROVIDERS.clear()
-        _PROVIDERS["test_provider"] = provider
-        _provisioned_users.pop("user-1", None)
-        try:
-            await ensure_managed_credentials("user-1", store)
-        finally:
-            _PROVIDERS.clear()
-            _PROVIDERS.update(saved)
-            _provisioned_users.pop("user-1", None)
-
-        provider.provision.assert_not_awaited()
-        store.has_managed_credential.assert_not_awaited()
-
-    @pytest.mark.asyncio
-    async def test_provision_failure_does_not_propagate(self):
-        """A failed provision is logged but does not raise."""
-        from backend.integrations.managed_credentials import (
-            _PROVIDERS,
-            _provisioned_users,
-            ensure_managed_credentials,
-        )
-
-        provider = MagicMock()
-        provider.provider_name = "test_provider"
-        provider.is_available = AsyncMock(return_value=True)
-        provider.provision = AsyncMock(side_effect=RuntimeError("boom"))
-
-        store = _make_store_mock()
-        store.has_managed_credential = AsyncMock(return_value=False)
-
-        saved = dict(_PROVIDERS)
-        _PROVIDERS.clear()
-        _PROVIDERS["test_provider"] = provider
-        _provisioned_users.pop("user-1", None)
-        try:
-            await ensure_managed_credentials("user-1", store)
-        finally:
-            _PROVIDERS.clear()
-            _PROVIDERS.update(saved)
-            _provisioned_users.pop("user-1", None)
-
-        # No exception raised — provisioning failure is swallowed.
-
-
-class TestCleanupManagedCredentials:
-    """Unit tests for cleanup_managed_credentials."""
-
-    @pytest.mark.asyncio
-    async def test_calls_deprovision_for_managed_creds(self):
-        from backend.integrations.managed_credentials import (
-            _PROVIDERS,
-            cleanup_managed_credentials,
-        )
-
-        cred = _make_managed_cred()
-        provider = MagicMock()
-        provider.provider_name = "agent_mail"
-        provider.deprovision = AsyncMock()
-
-        store = MagicMock()
-        store.get_all_creds = AsyncMock(return_value=[cred])
-
-        saved = dict(_PROVIDERS)
-        _PROVIDERS.clear()
-        _PROVIDERS["agent_mail"] = provider
-        try:
-            await cleanup_managed_credentials("user-1", store)
-        finally:
-            _PROVIDERS.clear()
-            _PROVIDERS.update(saved)
-
-        provider.deprovision.assert_awaited_once_with("user-1", cred)
-
-    @pytest.mark.asyncio
-    async def test_skips_non_managed_creds(self):
-        from backend.integrations.managed_credentials import (
-            _PROVIDERS,
-            cleanup_managed_credentials,
-        )
-
-        regular = _make_api_key_cred()
-        provider = MagicMock()
-        provider.provider_name = "openai"
-        provider.deprovision = AsyncMock()
-
-        store = MagicMock()
-        store.get_all_creds = AsyncMock(return_value=[regular])
-
-        saved = dict(_PROVIDERS)
-        _PROVIDERS.clear()
-        _PROVIDERS["openai"] = provider
-        try:
-            await cleanup_managed_credentials("user-1", store)
-        finally:
-            _PROVIDERS.clear()
-            _PROVIDERS.update(saved)
-
-        provider.deprovision.assert_not_awaited()
-
-    @pytest.mark.asyncio
-    async def test_deprovision_failure_does_not_propagate(self):
-        from backend.integrations.managed_credentials import (
-            _PROVIDERS,
-            cleanup_managed_credentials,
-        )
-
-        cred = _make_managed_cred()
-        provider = MagicMock()
-        provider.provider_name = "agent_mail"
-        provider.deprovision = AsyncMock(side_effect=RuntimeError("boom"))
-
-        store = MagicMock()
-        store.get_all_creds = AsyncMock(return_value=[cred])
-
-        saved = dict(_PROVIDERS)
-        _PROVIDERS.clear()
-        _PROVIDERS["agent_mail"] = provider
-        try:
-            await cleanup_managed_credentials("user-1", store)
-        finally:
-            _PROVIDERS.clear()
-            _PROVIDERS.update(saved)
-
-        # No exception raised — cleanup failure is swallowed.

autogpt_platform/backend/backend/api/features/library/_add_to_library.py

@@ -1,120 +0,0 @@
-"""Shared logic for adding store agents to a user's library.
-
-Both `add_store_agent_to_library` and `add_store_agent_to_library_as_admin`
-delegate to these helpers so the duplication-prone create/restore/dedup
-logic lives in exactly one place.
-"""
-
-import logging
-
-import prisma.errors
-import prisma.models
-
-import backend.api.features.library.model as library_model
-import backend.data.graph as graph_db
-from backend.data.graph import GraphModel, GraphSettings
-from backend.data.includes import library_agent_include
-from backend.util.exceptions import NotFoundError
-from backend.util.json import SafeJson
-
-logger = logging.getLogger(__name__)
-
-
-async def resolve_graph_for_library(
-    store_listing_version_id: str,
-    user_id: str,
-    *,
-    admin: bool,
-) -> GraphModel:
-    """Look up a StoreListingVersion and resolve its graph.
-
-    When ``admin=True``, uses ``get_graph_as_admin`` to bypass the marketplace
-    APPROVED-only check.  Otherwise uses the regular ``get_graph``.
-    """
-    slv = await prisma.models.StoreListingVersion.prisma().find_unique(
-        where={"id": store_listing_version_id}, include={"AgentGraph": True}
-    )
-    if not slv or not slv.AgentGraph:
-        raise NotFoundError(
-            f"Store listing version {store_listing_version_id} not found or invalid"
-        )
-
-    ag = slv.AgentGraph
-    if admin:
-        graph_model = await graph_db.get_graph_as_admin(
-            graph_id=ag.id, version=ag.version, user_id=user_id
-        )
-    else:
-        graph_model = await graph_db.get_graph(
-            graph_id=ag.id, version=ag.version, user_id=user_id
-        )
-
-    if not graph_model:
-        raise NotFoundError(f"Graph #{ag.id} v{ag.version} not found or accessible")
-    return graph_model
-
-
-async def add_graph_to_library(
-    store_listing_version_id: str,
-    graph_model: GraphModel,
-    user_id: str,
-) -> library_model.LibraryAgent:
-    """Check existing / restore soft-deleted / create new LibraryAgent.
-
-    Uses a create-then-catch-UniqueViolationError-then-update pattern on
-    the (userId, agentGraphId, agentGraphVersion) composite unique constraint.
-    This is more robust than ``upsert`` because Prisma's upsert atomicity
-    guarantees are not well-documented for all versions.
-    """
-    settings_json = SafeJson(GraphSettings.from_graph(graph_model).model_dump())
-    _include = library_agent_include(
-        user_id, include_nodes=False, include_executions=False
-    )
-
-    try:
-        added_agent = await prisma.models.LibraryAgent.prisma().create(
-            data={
-                "User": {"connect": {"id": user_id}},
-                "AgentGraph": {
-                    "connect": {
-                        "graphVersionId": {
-                            "id": graph_model.id,
-                            "version": graph_model.version,
-                        }
-                    }
-                },
-                "isCreatedByUser": False,
-                "useGraphIsActiveVersion": False,
-                "settings": settings_json,
-            },
-            include=_include,
-        )
-    except prisma.errors.UniqueViolationError:
-        # Already exists — update to restore if previously soft-deleted/archived
-        added_agent = await prisma.models.LibraryAgent.prisma().update(
-            where={
-                "userId_agentGraphId_agentGraphVersion": {
-                    "userId": user_id,
-                    "agentGraphId": graph_model.id,
-                    "agentGraphVersion": graph_model.version,
-                }
-            },
-            data={
-                "isDeleted": False,
-                "isArchived": False,
-                "settings": settings_json,
-            },
-            include=_include,
-        )
-        if added_agent is None:
-            raise NotFoundError(
-                f"LibraryAgent for graph #{graph_model.id} "
-                f"v{graph_model.version} not found after UniqueViolationError"
-            )
-
-    logger.debug(
-        f"Added graph #{graph_model.id} v{graph_model.version} "
-        f"for store listing version #{store_listing_version_id} "
-        f"to library for user #{user_id}"
-    )
-    return library_model.LibraryAgent.from_db(added_agent)

autogpt_platform/backend/backend/api/features/library/_add_to_library_test.py

@@ -1,80 +0,0 @@
-from unittest.mock import AsyncMock, MagicMock, patch
-
-import prisma.errors
-import pytest
-
-from ._add_to_library import add_graph_to_library
-
-
-@pytest.mark.asyncio
-async def test_add_graph_to_library_create_new_agent() -> None:
-    """When no matching LibraryAgent exists, create inserts a new one."""
-    graph_model = MagicMock(id="graph-id", version=2, nodes=[])
-    created_agent = MagicMock(name="CreatedLibraryAgent")
-    converted_agent = MagicMock(name="ConvertedLibraryAgent")
-
-    with (
-        patch(
-            "backend.api.features.library._add_to_library.prisma.models.LibraryAgent.prisma"
-        ) as mock_prisma,
-        patch(
-            "backend.api.features.library._add_to_library.library_model.LibraryAgent.from_db",
-            return_value=converted_agent,
-        ) as mock_from_db,
-    ):
-        mock_prisma.return_value.create = AsyncMock(return_value=created_agent)
-
-        result = await add_graph_to_library("slv-id", graph_model, "user-id")
-
-    assert result is converted_agent
-    mock_from_db.assert_called_once_with(created_agent)
-    # Verify create was called with correct data
-    create_call = mock_prisma.return_value.create.call_args
-    create_data = create_call.kwargs["data"]
-    assert create_data["User"] == {"connect": {"id": "user-id"}}
-    assert create_data["AgentGraph"] == {
-        "connect": {"graphVersionId": {"id": "graph-id", "version": 2}}
-    }
-    assert create_data["isCreatedByUser"] is False
-    assert create_data["useGraphIsActiveVersion"] is False
-
-
-@pytest.mark.asyncio
-async def test_add_graph_to_library_unique_violation_updates_existing() -> None:
-    """UniqueViolationError on create falls back to update."""
-    graph_model = MagicMock(id="graph-id", version=2, nodes=[])
-    updated_agent = MagicMock(name="UpdatedLibraryAgent")
-    converted_agent = MagicMock(name="ConvertedLibraryAgent")
-
-    with (
-        patch(
-            "backend.api.features.library._add_to_library.prisma.models.LibraryAgent.prisma"
-        ) as mock_prisma,
-        patch(
-            "backend.api.features.library._add_to_library.library_model.LibraryAgent.from_db",
-            return_value=converted_agent,
-        ) as mock_from_db,
-    ):
-        mock_prisma.return_value.create = AsyncMock(
-            side_effect=prisma.errors.UniqueViolationError(
-                MagicMock(), message="unique constraint"
-            )
-        )
-        mock_prisma.return_value.update = AsyncMock(return_value=updated_agent)
-
-        result = await add_graph_to_library("slv-id", graph_model, "user-id")
-
-    assert result is converted_agent
-    mock_from_db.assert_called_once_with(updated_agent)
-    # Verify update was called with correct where and data
-    update_call = mock_prisma.return_value.update.call_args
-    assert update_call.kwargs["where"] == {
-        "userId_agentGraphId_agentGraphVersion": {
-            "userId": "user-id",
-            "agentGraphId": "graph-id",
-            "agentGraphVersion": 2,
-        }
-    }
-    update_data = update_call.kwargs["data"]
-    assert update_data["isDeleted"] is False
-    assert update_data["isArchived"] is False

autogpt_platform/backend/backend/api/features/library/db.py

@@ -8,6 +8,7 @@ import prisma.errors
 import prisma.models
 import prisma.types
 
+import backend.api.features.store.exceptions as store_exceptions
 import backend.api.features.store.image_gen as store_image_gen
 import backend.api.features.store.media as store_media
 import backend.data.graph as graph_db
@@ -250,7 +251,7 @@ async def get_library_agent(id: str, user_id: str) -> library_model.LibraryAgent
         The requested LibraryAgent.
 
     Raises:
-        NotFoundError: If the specified agent does not exist.
+        AgentNotFoundError: If the specified agent does not exist.
         DatabaseError: If there's an error during retrieval.
     """
     library_agent = await prisma.models.LibraryAgent.prisma().find_first(
@@ -336,15 +337,12 @@ async def get_library_agent_by_graph_id(
     user_id: str,
     graph_id: str,
     graph_version: Optional[int] = None,
-    include_archived: bool = False,
 ) -> library_model.LibraryAgent | None:
     filter: prisma.types.LibraryAgentWhereInput = {
         "agentGraphId": graph_id,
         "userId": user_id,
         "isDeleted": False,
     }
-    if not include_archived:
-        filter["isArchived"] = False
     if graph_version is not None:
         filter["agentGraphVersion"] = graph_version
 
@@ -400,7 +398,6 @@ async def create_library_agent(
     hitl_safe_mode: bool = True,
     sensitive_action_safe_mode: bool = False,
     create_library_agents_for_sub_graphs: bool = True,
-    folder_id: str | None = None,
 ) -> list[library_model.LibraryAgent]:
     """
     Adds an agent to the user's library (LibraryAgent table).
@@ -417,18 +414,12 @@ async def create_library_agent(
         If the graph has sub-graphs, the parent graph will always be the first entry in the list.
 
     Raises:
-        NotFoundError: If the specified agent does not exist.
+        AgentNotFoundError: If the specified agent does not exist.
         DatabaseError: If there's an error during creation or if image generation fails.
     """
     logger.info(
         f"Creating library agent for graph #{graph.id} v{graph.version}; user:<redacted>"
     )
-
-    # Authorization: FK only checks existence, not ownership.
-    # Verify the folder belongs to this user to prevent cross-user nesting.
-    if folder_id:
-        await get_folder(folder_id, user_id)
-
     graph_entries = (
         [graph, *graph.sub_graphs] if create_library_agents_for_sub_graphs else [graph]
     )
@@ -436,58 +427,28 @@ async def create_library_agent(
     async with transaction() as tx:
         library_agents = await asyncio.gather(
             *(
-                prisma.models.LibraryAgent.prisma(tx).upsert(
-                    where={
-                        "userId_agentGraphId_agentGraphVersion": {
-                            "userId": user_id,
-                            "agentGraphId": graph_entry.id,
-                            "agentGraphVersion": graph_entry.version,
-                        }
-                    },
-                    data={
-                        "create": prisma.types.LibraryAgentCreateInput(
-                            isCreatedByUser=(user_id == graph.user_id),
-                            useGraphIsActiveVersion=True,
-                            User={"connect": {"id": user_id}},
-                            AgentGraph={
-                                "connect": {
-                                    "graphVersionId": {
-                                        "id": graph_entry.id,
-                                        "version": graph_entry.version,
-                                    }
+                prisma.models.LibraryAgent.prisma(tx).create(
+                    data=prisma.types.LibraryAgentCreateInput(
+                        isCreatedByUser=(user_id == user_id),
+                        useGraphIsActiveVersion=True,
+                        User={"connect": {"id": user_id}},
+                        # Creator={"connect": {"id": user_id}},
+                        AgentGraph={
+                            "connect": {
+                                "graphVersionId": {
+                                    "id": graph_entry.id,
+                                    "version": graph_entry.version,
                                 }
-                            },
-                            settings=SafeJson(
-                                GraphSettings.from_graph(
-                                    graph_entry,
-                                    hitl_safe_mode=hitl_safe_mode,
-                                    sensitive_action_safe_mode=sensitive_action_safe_mode,
-                                ).model_dump()
-                            ),
-                            **(
-                                {"Folder": {"connect": {"id": folder_id}}}
-                                if folder_id and graph_entry is graph
-                                else {}
-                            ),
-                        ),
-                        "update": {
-                            "isDeleted": False,
-                            "isArchived": False,
-                            "useGraphIsActiveVersion": True,
-                            "settings": SafeJson(
-                                GraphSettings.from_graph(
-                                    graph_entry,
-                                    hitl_safe_mode=hitl_safe_mode,
-                                    sensitive_action_safe_mode=sensitive_action_safe_mode,
-                                ).model_dump()
-                            ),
-                            **(
-                                {"Folder": {"connect": {"id": folder_id}}}
-                                if folder_id and graph_entry is graph
-                                else {}
-                            ),
+                            }
                         },
-                    },
+                        settings=SafeJson(
+                            GraphSettings.from_graph(
+                                graph_entry,
+                                hitl_safe_mode=hitl_safe_mode,
+                                sensitive_action_safe_mode=sensitive_action_safe_mode,
+                            ).model_dump()
+                        ),
+                    ),
                     include=library_agent_include(
                         user_id, include_nodes=False, include_executions=False
                     ),
@@ -568,7 +529,6 @@ async def update_agent_version_in_library(
 async def create_graph_in_library(
     graph: graph_db.Graph,
     user_id: str,
-    folder_id: str | None = None,
 ) -> tuple[graph_db.GraphModel, library_model.LibraryAgent]:
     """Create a new graph and add it to the user's library."""
     graph.version = 1
@@ -582,7 +542,6 @@ async def create_graph_in_library(
         user_id=user_id,
         sensitive_action_safe_mode=True,
         create_library_agents_for_sub_graphs=False,
-        folder_id=folder_id,
     )
 
     if created_graph.is_active:
@@ -611,9 +570,7 @@ async def update_graph_in_library(
 
     created_graph = await graph_db.create_graph(graph_model, user_id)
 
-    library_agent = await get_library_agent_by_graph_id(
-        user_id, created_graph.id, include_archived=True
-    )
+    library_agent = await get_library_agent_by_graph_id(user_id, created_graph.id)
     if not library_agent:
         raise NotFoundError(f"Library agent not found for graph {created_graph.id}")
 
@@ -849,38 +806,92 @@ async def delete_library_agent_by_graph_id(graph_id: str, user_id: str) -> None:
 async def add_store_agent_to_library(
     store_listing_version_id: str, user_id: str
 ) -> library_model.LibraryAgent:
-    """Adds a marketplace agent to the user’s library.
-
-    See also: `add_store_agent_to_library_as_admin()` which uses
-    `get_graph_as_admin` to bypass marketplace status checks for admin review.
     """
-    from ._add_to_library import add_graph_to_library, resolve_graph_for_library
+    Adds an agent from a store listing version to the user's library if they don't already have it.
 
+    Args:
+        store_listing_version_id: The ID of the store listing version containing the agent.
+        user_id: The user’s library to which the agent is being added.
+
+    Returns:
+        The newly created LibraryAgent if successfully added, the existing corresponding one if any.
+
+    Raises:
+        AgentNotFoundError: If the store listing or associated agent is not found.
+        DatabaseError: If there's an issue creating the LibraryAgent record.
+    """
     logger.debug(
         f"Adding agent from store listing version #{store_listing_version_id} "
         f"to library for user #{user_id}"
     )
-    graph_model = await resolve_graph_for_library(
-        store_listing_version_id, user_id, admin=False
-    )
-    return await add_graph_to_library(store_listing_version_id, graph_model, user_id)
 
-
-async def add_store_agent_to_library_as_admin(
-    store_listing_version_id: str, user_id: str
-) -> library_model.LibraryAgent:
-    """Admin variant that uses `get_graph_as_admin` to bypass marketplace
-    APPROVED-only checks, allowing admins to add pending agents for review."""
-    from ._add_to_library import add_graph_to_library, resolve_graph_for_library
-
-    logger.warning(
-        f"ADMIN adding agent from store listing version "
-        f"#{store_listing_version_id} to library for user #{user_id}"
+    store_listing_version = (
+        await prisma.models.StoreListingVersion.prisma().find_unique(
+            where={"id": store_listing_version_id}, include={"AgentGraph": True}
+        )
     )
-    graph_model = await resolve_graph_for_library(
-        store_listing_version_id, user_id, admin=True
+    if not store_listing_version or not store_listing_version.AgentGraph:
+        logger.warning(f"Store listing version not found: {store_listing_version_id}")
+        raise store_exceptions.AgentNotFoundError(
+            f"Store listing version {store_listing_version_id} not found or invalid"
+        )
+
+    graph = store_listing_version.AgentGraph
+
+    # Convert to GraphModel to check for HITL blocks
+    graph_model = await graph_db.get_graph(
+        graph_id=graph.id,
+        version=graph.version,
+        user_id=user_id,
+        include_subgraphs=False,
     )
-    return await add_graph_to_library(store_listing_version_id, graph_model, user_id)
+    if not graph_model:
+        raise store_exceptions.AgentNotFoundError(
+            f"Graph #{graph.id} v{graph.version} not found or accessible"
+        )
+
+    # Check if user already has this agent (non-deleted)
+    if existing := await get_library_agent_by_graph_id(
+        user_id, graph.id, graph.version
+    ):
+        return existing
+
+    # Check for soft-deleted version and restore it
+    deleted_agent = await prisma.models.LibraryAgent.prisma().find_unique(
+        where={
+            "userId_agentGraphId_agentGraphVersion": {
+                "userId": user_id,
+                "agentGraphId": graph.id,
+                "agentGraphVersion": graph.version,
+            }
+        },
+    )
+    if deleted_agent and deleted_agent.isDeleted:
+        return await update_library_agent(deleted_agent.id, user_id, is_deleted=False)
+
+    # Create LibraryAgent entry
+    added_agent = await prisma.models.LibraryAgent.prisma().create(
+        data={
+            "User": {"connect": {"id": user_id}},
+            "AgentGraph": {
+                "connect": {
+                    "graphVersionId": {"id": graph.id, "version": graph.version}
+                }
+            },
+            "isCreatedByUser": False,
+            "useGraphIsActiveVersion": False,
+            "settings": SafeJson(GraphSettings.from_graph(graph_model).model_dump()),
+        },
+        include=library_agent_include(
+            user_id, include_nodes=False, include_executions=False
+        ),
+    )
+    logger.debug(
+        f"Added graph #{graph.id} v{graph.version}"
+        f"for store listing version #{store_listing_version.id} "
+        f"to library for user #{user_id}"
+    )
+    return library_model.LibraryAgent.from_db(added_agent)
 
 
 ##############################################
@@ -1470,67 +1481,6 @@ async def bulk_move_agents_to_folder(
     return [library_model.LibraryAgent.from_db(agent) for agent in agents]
 
 
-def collect_tree_ids(
-    nodes: list[library_model.LibraryFolderTree],
-    visited: set[str] | None = None,
-) -> list[str]:
-    """Collect all folder IDs from a folder tree."""
-    if visited is None:
-        visited = set()
-    ids: list[str] = []
-    for n in nodes:
-        if n.id in visited:
-            continue
-        visited.add(n.id)
-        ids.append(n.id)
-        ids.extend(collect_tree_ids(n.children, visited))
-    return ids
-
-
-async def get_folder_agent_summaries(
-    user_id: str, folder_id: str
-) -> list[dict[str, str | None]]:
-    """Get a lightweight list of agents in a folder (id, name, description)."""
-    all_agents: list[library_model.LibraryAgent] = []
-    for page in itertools.count(1):
-        resp = await list_library_agents(
-            user_id=user_id, folder_id=folder_id, page=page
-        )
-        all_agents.extend(resp.agents)
-        if page >= resp.pagination.total_pages:
-            break
-    return [
-        {"id": a.id, "name": a.name, "description": a.description} for a in all_agents
-    ]
-
-
-async def get_root_agent_summaries(
-    user_id: str,
-) -> list[dict[str, str | None]]:
-    """Get a lightweight list of root-level agents (folderId IS NULL)."""
-    all_agents: list[library_model.LibraryAgent] = []
-    for page in itertools.count(1):
-        resp = await list_library_agents(
-            user_id=user_id, include_root_only=True, page=page
-        )
-        all_agents.extend(resp.agents)
-        if page >= resp.pagination.total_pages:
-            break
-    return [
-        {"id": a.id, "name": a.name, "description": a.description} for a in all_agents
-    ]
-
-
-async def get_folder_agents_map(
-    user_id: str, folder_ids: list[str]
-) -> dict[str, list[dict[str, str | None]]]:
-    """Get agent summaries for multiple folders concurrently."""
-    results = await asyncio.gather(
-        *(get_folder_agent_summaries(user_id, fid) for fid in folder_ids)
-    )
-    return dict(zip(folder_ids, results))
-
-
 ##############################################
 ########### Presets DB Functions #############
 ##############################################

autogpt_platform/backend/backend/api/features/library/db_test.py

@@ -1,11 +1,10 @@
-from contextlib import asynccontextmanager
 from datetime import datetime
-from unittest.mock import AsyncMock, MagicMock, patch
 
 import prisma.enums
 import prisma.models
 import pytest
 
+import backend.api.features.store.exceptions
 from backend.data.db import connect
 from backend.data.includes import library_agent_include
 
@@ -87,6 +86,10 @@ async def test_get_library_agents(mocker):
 async def test_add_agent_to_library(mocker):
     await connect()
 
+    # Mock the transaction context
+    mock_transaction = mocker.patch("backend.api.features.library.db.transaction")
+    mock_transaction.return_value.__aenter__ = mocker.AsyncMock(return_value=None)
+    mock_transaction.return_value.__aexit__ = mocker.AsyncMock(return_value=None)
     # Mock data
     mock_store_listing_data = prisma.models.StoreListingVersion(
         id="version123",
@@ -141,18 +144,15 @@ async def test_add_agent_to_library(mocker):
     )
 
     mock_library_agent = mocker.patch("prisma.models.LibraryAgent.prisma")
+    mock_library_agent.return_value.find_first = mocker.AsyncMock(return_value=None)
+    mock_library_agent.return_value.find_unique = mocker.AsyncMock(return_value=None)
     mock_library_agent.return_value.create = mocker.AsyncMock(
         return_value=mock_library_agent_data
     )
 
-    # Mock graph_db.get_graph function that's called in resolve_graph_for_library
-    # (lives in _add_to_library.py after refactor, not db.py)
-    mock_graph_db = mocker.patch(
-        "backend.api.features.library._add_to_library.graph_db"
-    )
+    # Mock graph_db.get_graph function that's called to check for HITL blocks
+    mock_graph_db = mocker.patch("backend.api.features.library.db.graph_db")
     mock_graph_model = mocker.Mock()
-    mock_graph_model.id = "agent1"
-    mock_graph_model.version = 1
     mock_graph_model.nodes = (
         []
     )  # Empty list so _has_human_in_the_loop_blocks returns False
@@ -171,27 +171,37 @@ async def test_add_agent_to_library(mocker):
     mock_store_listing_version.return_value.find_unique.assert_called_once_with(
         where={"id": "version123"}, include={"AgentGraph": True}
     )
+    mock_library_agent.return_value.find_unique.assert_called_once_with(
+        where={
+            "userId_agentGraphId_agentGraphVersion": {
+                "userId": "test-user",
+                "agentGraphId": "agent1",
+                "agentGraphVersion": 1,
+            }
+        },
+    )
     # Check that create was called with the expected data including settings
     create_call_args = mock_library_agent.return_value.create.call_args
     assert create_call_args is not None
 
-    # Verify the create data structure
-    create_data = create_call_args.kwargs["data"]
-    expected_create = {
+    # Verify the main structure
+    expected_data = {
         "User": {"connect": {"id": "test-user"}},
         "AgentGraph": {"connect": {"graphVersionId": {"id": "agent1", "version": 1}}},
         "isCreatedByUser": False,
-        "useGraphIsActiveVersion": False,
     }
-    for key, value in expected_create.items():
-        assert create_data[key] == value
+
+    actual_data = create_call_args[1]["data"]
+    # Check that all expected fields are present
+    for key, value in expected_data.items():
+        assert actual_data[key] == value
 
     # Check that settings field is present and is a SafeJson object
-    assert "settings" in create_data
-    assert hasattr(create_data["settings"], "__class__")  # Should be a SafeJson object
+    assert "settings" in actual_data
+    assert hasattr(actual_data["settings"], "__class__")  # Should be a SafeJson object
 
     # Check include parameter
-    assert create_call_args.kwargs["include"] == library_agent_include(
+    assert create_call_args[1]["include"] == library_agent_include(
         "test-user", include_nodes=False, include_executions=False
     )
 
@@ -208,148 +218,10 @@ async def test_add_agent_to_library_not_found(mocker):
     )
 
     # Call function and verify exception
-    with pytest.raises(db.NotFoundError):
+    with pytest.raises(backend.api.features.store.exceptions.AgentNotFoundError):
         await db.add_store_agent_to_library("version123", "test-user")
 
     # Verify mock called correctly
     mock_store_listing_version.return_value.find_unique.assert_called_once_with(
         where={"id": "version123"}, include={"AgentGraph": True}
     )
-
-
-@pytest.mark.asyncio
-async def test_get_library_agent_by_graph_id_excludes_archived(mocker):
-    mock_library_agent = mocker.patch("prisma.models.LibraryAgent.prisma")
-    mock_library_agent.return_value.find_first = mocker.AsyncMock(return_value=None)
-
-    result = await db.get_library_agent_by_graph_id("test-user", "agent1", 7)
-
-    assert result is None
-    mock_library_agent.return_value.find_first.assert_called_once()
-    where = mock_library_agent.return_value.find_first.call_args.kwargs["where"]
-    assert where == {
-        "agentGraphId": "agent1",
-        "userId": "test-user",
-        "isDeleted": False,
-        "isArchived": False,
-        "agentGraphVersion": 7,
-    }
-
-
-@pytest.mark.asyncio
-async def test_get_library_agent_by_graph_id_can_include_archived(mocker):
-    mock_library_agent = mocker.patch("prisma.models.LibraryAgent.prisma")
-    mock_library_agent.return_value.find_first = mocker.AsyncMock(return_value=None)
-
-    result = await db.get_library_agent_by_graph_id(
-        "test-user",
-        "agent1",
-        7,
-        include_archived=True,
-    )
-
-    assert result is None
-    mock_library_agent.return_value.find_first.assert_called_once()
-    where = mock_library_agent.return_value.find_first.call_args.kwargs["where"]
-    assert where == {
-        "agentGraphId": "agent1",
-        "userId": "test-user",
-        "isDeleted": False,
-        "agentGraphVersion": 7,
-    }
-
-
-@pytest.mark.asyncio
-async def test_update_graph_in_library_allows_archived_library_agent(mocker):
-    graph = mocker.Mock(id="graph-id")
-    existing_version = mocker.Mock(version=1, is_active=True)
-    graph_model = mocker.Mock()
-    created_graph = mocker.Mock(id="graph-id", version=2, is_active=False)
-    current_library_agent = mocker.Mock()
-    updated_library_agent = mocker.Mock()
-
-    mocker.patch(
-        "backend.api.features.library.db.graph_db.get_graph_all_versions",
-        new=mocker.AsyncMock(return_value=[existing_version]),
-    )
-    mocker.patch(
-        "backend.api.features.library.db.graph_db.make_graph_model",
-        return_value=graph_model,
-    )
-    mocker.patch(
-        "backend.api.features.library.db.graph_db.create_graph",
-        new=mocker.AsyncMock(return_value=created_graph),
-    )
-    mock_get_library_agent = mocker.patch(
-        "backend.api.features.library.db.get_library_agent_by_graph_id",
-        new=mocker.AsyncMock(return_value=current_library_agent),
-    )
-    mock_update_library_agent = mocker.patch(
-        "backend.api.features.library.db.update_library_agent_version_and_settings",
-        new=mocker.AsyncMock(return_value=updated_library_agent),
-    )
-
-    result_graph, result_library_agent = await db.update_graph_in_library(
-        graph,
-        "test-user",
-    )
-
-    assert result_graph is created_graph
-    assert result_library_agent is updated_library_agent
-    assert graph.version == 2
-    graph_model.reassign_ids.assert_called_once_with(
-        user_id="test-user", reassign_graph_id=False
-    )
-    mock_get_library_agent.assert_awaited_once_with(
-        "test-user",
-        "graph-id",
-        include_archived=True,
-    )
-    mock_update_library_agent.assert_awaited_once_with("test-user", created_graph)
-
-
-@pytest.mark.asyncio
-async def test_create_library_agent_uses_upsert():
-    """create_library_agent should use upsert (not create) to handle duplicates."""
-    mock_graph = MagicMock()
-    mock_graph.id = "graph-1"
-    mock_graph.version = 1
-    mock_graph.user_id = "user-1"
-    mock_graph.nodes = []
-    mock_graph.sub_graphs = []
-
-    mock_upserted = MagicMock(name="UpsertedLibraryAgent")
-
-    @asynccontextmanager
-    async def fake_tx():
-        yield None
-
-    with (
-        patch("backend.api.features.library.db.transaction", fake_tx),
-        patch("prisma.models.LibraryAgent.prisma") as mock_prisma,
-        patch(
-            "backend.api.features.library.db.add_generated_agent_image",
-            new=AsyncMock(),
-        ),
-        patch(
-            "backend.api.features.library.model.LibraryAgent.from_db",
-            return_value=MagicMock(),
-        ),
-    ):
-        mock_prisma.return_value.upsert = AsyncMock(return_value=mock_upserted)
-
-        result = await db.create_library_agent(mock_graph, "user-1")
-
-    assert len(result) == 1
-    upsert_call = mock_prisma.return_value.upsert.call_args
-    assert upsert_call is not None
-    # Verify the upsert where clause uses the composite unique key
-    where = upsert_call.kwargs["where"]
-    assert "userId_agentGraphId_agentGraphVersion" in where
-    # Verify the upsert data has both create and update branches
-    data = upsert_call.kwargs["data"]
-    assert "create" in data
-    assert "update" in data
-    # Verify update branch restores soft-deleted/archived agents
-    assert data["update"]["isDeleted"] is False
-    assert data["update"]["isArchived"] is False

autogpt_platform/backend/backend/api/features/library/model.py

@@ -165,6 +165,7 @@ class LibraryAgent(pydantic.BaseModel):
     id: str
     graph_id: str
     graph_version: int
+    owner_user_id: str
 
     image_url: str | None
 
@@ -205,9 +206,7 @@ class LibraryAgent(pydantic.BaseModel):
         default_factory=list,
         description="List of recent executions with status, score, and summary",
     )
-    can_access_graph: bool = pydantic.Field(
-        description="Indicates whether the same user owns the corresponding graph"
-    )
+    can_access_graph: bool
     is_latest_version: bool
     is_favorite: bool
     folder_id: str | None = None
@@ -325,6 +324,7 @@ class LibraryAgent(pydantic.BaseModel):
             id=agent.id,
             graph_id=agent.agentGraphId,
             graph_version=agent.agentGraphVersion,
+            owner_user_id=agent.userId,
             image_url=agent.imageUrl,
             creator_name=creator_name,
             creator_image_url=creator_image_url,

autogpt_platform/backend/backend/api/features/library/routes_test.py

@@ -42,6 +42,7 @@ async def test_get_library_agents_success(
                 id="test-agent-1",
                 graph_id="test-agent-1",
                 graph_version=1,
+                owner_user_id=test_user_id,
                 name="Test Agent 1",
                 description="Test Description 1",
                 image_url=None,
@@ -66,6 +67,7 @@ async def test_get_library_agents_success(
                 id="test-agent-2",
                 graph_id="test-agent-2",
                 graph_version=1,
+                owner_user_id=test_user_id,
                 name="Test Agent 2",
                 description="Test Description 2",
                 image_url=None,
@@ -129,6 +131,7 @@ async def test_get_favorite_library_agents_success(
                 id="test-agent-1",
                 graph_id="test-agent-1",
                 graph_version=1,
+                owner_user_id=test_user_id,
                 name="Favorite Agent 1",
                 description="Test Favorite Description 1",
                 image_url=None,
@@ -181,6 +184,7 @@ def test_add_agent_to_library_success(
         id="test-library-agent-id",
         graph_id="test-agent-1",
         graph_version=1,
+        owner_user_id=test_user_id,
         name="Test Agent 1",
         description="Test Description 1",
         image_url=None,

autogpt_platform/backend/backend/api/features/mcp/routes.py

@@ -24,7 +24,7 @@ from backend.blocks.mcp.oauth import MCPOAuthHandler
 from backend.data.model import OAuth2Credentials
 from backend.integrations.creds_manager import IntegrationCredentialsManager
 from backend.integrations.providers import ProviderName
-from backend.util.request import HTTPClientError, Requests, validate_url_host
+from backend.util.request import HTTPClientError, Requests, validate_url
 from backend.util.settings import Settings
 
 logger = logging.getLogger(__name__)
@@ -80,7 +80,7 @@ async def discover_tools(
     """
     # Validate URL to prevent SSRF — blocks loopback and private IP ranges.
     try:
-        await validate_url_host(request.server_url)
+        await validate_url(request.server_url, trusted_origins=[])
     except ValueError as e:
         raise fastapi.HTTPException(status_code=400, detail=f"Invalid server URL: {e}")
 
@@ -167,7 +167,7 @@ async def mcp_oauth_login(
     """
     # Validate URL to prevent SSRF — blocks loopback and private IP ranges.
     try:
-        await validate_url_host(request.server_url)
+        await validate_url(request.server_url, trusted_origins=[])
     except ValueError as e:
         raise fastapi.HTTPException(status_code=400, detail=f"Invalid server URL: {e}")
 
@@ -187,7 +187,7 @@ async def mcp_oauth_login(
 
         # Validate the auth server URL from metadata to prevent SSRF.
         try:
-            await validate_url_host(auth_server_url)
+            await validate_url(auth_server_url, trusted_origins=[])
         except ValueError as e:
             raise fastapi.HTTPException(
                 status_code=400,
@@ -234,7 +234,7 @@ async def mcp_oauth_login(
     if registration_endpoint:
         # Validate the registration endpoint to prevent SSRF via metadata.
         try:
-            await validate_url_host(registration_endpoint)
+            await validate_url(registration_endpoint, trusted_origins=[])
         except ValueError:
             pass  # Skip registration, fall back to default client_id
         else:
@@ -429,7 +429,7 @@ async def mcp_store_token(
 
     # Validate URL to prevent SSRF — blocks loopback and private IP ranges.
     try:
-        await validate_url_host(request.server_url)
+        await validate_url(request.server_url, trusted_origins=[])
     except ValueError as e:
         raise fastapi.HTTPException(status_code=400, detail=f"Invalid server URL: {e}")
 

autogpt_platform/backend/backend/api/features/mcp/test_routes.py

@@ -32,9 +32,9 @@ async def client():
 
 @pytest.fixture(autouse=True)
 def _bypass_ssrf_validation():
-    """Bypass validate_url_host in all route tests (test URLs don't resolve)."""
+    """Bypass validate_url in all route tests (test URLs don't resolve)."""
     with patch(
-        "backend.api.features.mcp.routes.validate_url_host",
+        "backend.api.features.mcp.routes.validate_url",
         new_callable=AsyncMock,
     ):
         yield
@@ -521,12 +521,12 @@ class TestStoreToken:
 
 
 class TestSSRFValidation:
-    """Verify that validate_url_host is enforced on all endpoints."""
+    """Verify that validate_url is enforced on all endpoints."""
 
     @pytest.mark.asyncio(loop_scope="session")
     async def test_discover_tools_ssrf_blocked(self, client):
         with patch(
-            "backend.api.features.mcp.routes.validate_url_host",
+            "backend.api.features.mcp.routes.validate_url",
             new_callable=AsyncMock,
             side_effect=ValueError("blocked loopback"),
         ):
@@ -541,7 +541,7 @@ class TestSSRFValidation:
     @pytest.mark.asyncio(loop_scope="session")
     async def test_oauth_login_ssrf_blocked(self, client):
         with patch(
-            "backend.api.features.mcp.routes.validate_url_host",
+            "backend.api.features.mcp.routes.validate_url",
             new_callable=AsyncMock,
             side_effect=ValueError("blocked private IP"),
         ):
@@ -556,7 +556,7 @@ class TestSSRFValidation:
     @pytest.mark.asyncio(loop_scope="session")
     async def test_store_token_ssrf_blocked(self, client):
         with patch(
-            "backend.api.features.mcp.routes.validate_url_host",
+            "backend.api.features.mcp.routes.validate_url",
             new_callable=AsyncMock,
             side_effect=ValueError("blocked loopback"),
         ):

autogpt_platform/backend/backend/api/features/oauth_test.py

@@ -12,7 +12,6 @@ Tests cover:
 5. Complete OAuth flow end-to-end
 """
 
-import asyncio
 import base64
 import hashlib
 import secrets
@@ -59,27 +58,14 @@ async def test_user(server, test_user_id: str):
 
     yield test_user_id
 
-    # Cleanup - delete in correct order due to foreign key constraints.
-    # Wrap in try/except because the event loop or Prisma engine may already
-    # be closed during session teardown on Python 3.12+.
-    try:
-        await asyncio.gather(
-            PrismaOAuthAccessToken.prisma().delete_many(where={"userId": test_user_id}),
-            PrismaOAuthRefreshToken.prisma().delete_many(
-                where={"userId": test_user_id}
-            ),
-            PrismaOAuthAuthorizationCode.prisma().delete_many(
-                where={"userId": test_user_id}
-            ),
-        )
-        await asyncio.gather(
-            PrismaOAuthApplication.prisma().delete_many(
-                where={"ownerId": test_user_id}
-            ),
-            PrismaUser.prisma().delete(where={"id": test_user_id}),
-        )
-    except RuntimeError:
-        pass
+    # Cleanup - delete in correct order due to foreign key constraints
+    await PrismaOAuthAccessToken.prisma().delete_many(where={"userId": test_user_id})
+    await PrismaOAuthRefreshToken.prisma().delete_many(where={"userId": test_user_id})
+    await PrismaOAuthAuthorizationCode.prisma().delete_many(
+        where={"userId": test_user_id}
+    )
+    await PrismaOAuthApplication.prisma().delete_many(where={"ownerId": test_user_id})
+    await PrismaUser.prisma().delete(where={"id": test_user_id})
 
 
 @pytest_asyncio.fixture

autogpt_platform/backend/backend/api/features/onboarding_profile_test.py

@@ -1,61 +0,0 @@
-from unittest.mock import AsyncMock
-
-import fastapi
-import fastapi.testclient
-import pytest
-
-from backend.api.features.v1 import v1_router
-
-app = fastapi.FastAPI()
-app.include_router(v1_router)
-client = fastapi.testclient.TestClient(app)
-
-
-@pytest.fixture(autouse=True)
-def setup_app_auth(mock_jwt_user):
-    from autogpt_libs.auth.jwt_utils import get_jwt_payload
-
-    app.dependency_overrides[get_jwt_payload] = mock_jwt_user["get_jwt_payload"]
-    yield
-    app.dependency_overrides.clear()
-
-
-def test_onboarding_profile_success(mocker):
-    mock_extract = mocker.patch(
-        "backend.api.features.v1.extract_business_understanding",
-        new_callable=AsyncMock,
-    )
-    mock_upsert = mocker.patch(
-        "backend.api.features.v1.upsert_business_understanding",
-        new_callable=AsyncMock,
-    )
-
-    from backend.data.understanding import BusinessUnderstandingInput
-
-    mock_extract.return_value = BusinessUnderstandingInput.model_construct(
-        user_name="John",
-        user_role="Founder/CEO",
-        pain_points=["Finding leads"],
-        suggested_prompts={"Learn": ["How do I automate lead gen?"]},
-    )
-    mock_upsert.return_value = AsyncMock()
-
-    response = client.post(
-        "/onboarding/profile",
-        json={
-            "user_name": "John",
-            "user_role": "Founder/CEO",
-            "pain_points": ["Finding leads", "Email & outreach"],
-        },
-    )
-    assert response.status_code == 200
-    mock_extract.assert_awaited_once()
-    mock_upsert.assert_awaited_once()
-
-
-def test_onboarding_profile_missing_fields():
-    response = client.post(
-        "/onboarding/profile",
-        json={"user_name": "John"},
-    )
-    assert response.status_code == 422

autogpt_platform/backend/backend/api/features/store/cache.py

@@ -1,3 +1,5 @@
+from typing import Literal
+
 from backend.util.cache import cached
 
 from . import db as store_db
@@ -21,7 +23,7 @@ def clear_all_caches():
 async def _get_cached_store_agents(
     featured: bool,
     creator: str | None,
-    sorted_by: store_db.StoreAgentsSortOptions | None,
+    sorted_by: Literal["rating", "runs", "name", "updated_at"] | None,
     search_query: str | None,
     category: str | None,
     page: int,
@@ -55,7 +57,7 @@ async def _get_cached_agent_details(
 async def _get_cached_store_creators(
     featured: bool,
     search_query: str | None,
-    sorted_by: store_db.StoreCreatorsSortOptions | None,
+    sorted_by: Literal["agent_rating", "agent_runs", "num_agents"] | None,
     page: int,
     page_size: int,
 ):
@@ -73,4 +75,4 @@ async def _get_cached_store_creators(
 @cached(maxsize=100, ttl_seconds=300, shared_cache=True)
 async def _get_cached_creator_details(username: str):
     """Cached helper to get creator details."""
-    return await store_db.get_store_creator(username=username.lower())
+    return await store_db.get_store_creator_details(username=username.lower())

autogpt_platform/backend/backend/api/features/store/content_handlers.py

@@ -5,26 +5,16 @@ Pluggable system for different content sources (store agents, blocks, docs).
 Each handler knows how to fetch and process its content type for embedding.
 """
 
-from __future__ import annotations
-
-import asyncio
-import functools
-import itertools
 import logging
 from abc import ABC, abstractmethod
 from dataclasses import dataclass
 from pathlib import Path
-from typing import TYPE_CHECKING, Any, get_args, get_origin
+from typing import Any, get_args, get_origin
 
 from prisma.enums import ContentType
 
-from backend.blocks import get_blocks
 from backend.blocks.llm import LlmModel
 from backend.data.db import query_raw_with_schema
-from backend.util.text import split_camelcase
-
-if TYPE_CHECKING:
-    from backend.blocks._base import AnyBlockSchema
 
 logger = logging.getLogger(__name__)
 
@@ -164,28 +154,6 @@ class StoreAgentHandler(ContentHandler):
         }
 
 
-@functools.lru_cache(maxsize=1)
-def _get_enabled_blocks() -> dict[str, AnyBlockSchema]:
-    """Return ``{block_id: block_instance}`` for all enabled, instantiable blocks.
-
-    Disabled blocks and blocks that fail to instantiate are silently skipped
-    (with a warning log), so callers never need their own try/except loop.
-
-    Results are cached for the process lifetime via ``lru_cache`` because
-    blocks are registered at import time and never change while running.
-    """
-    enabled: dict[str, AnyBlockSchema] = {}
-    for block_id, block_cls in get_blocks().items():
-        try:
-            instance = block_cls()
-        except Exception as e:
-            logger.warning(f"Skipping block {block_id}: init failed: {e}")
-            continue
-        if not instance.disabled:
-            enabled[block_id] = instance
-    return enabled
-
-
 class BlockHandler(ContentHandler):
     """Handler for block definitions (Python classes)."""
 
@@ -195,14 +163,16 @@ class BlockHandler(ContentHandler):
 
     async def get_missing_items(self, batch_size: int) -> list[ContentItem]:
         """Fetch blocks without embeddings."""
-        # to_thread keeps the first (heavy) call off the event loop.  On
-        # subsequent calls the lru_cache makes this a dict lookup, so the
-        # thread-pool overhead is negligible compared to the DB queries below.
-        enabled = await asyncio.to_thread(_get_enabled_blocks)
-        if not enabled:
+        from backend.blocks import get_blocks
+
+        # Get all available blocks
+        all_blocks = get_blocks()
+
+        # Check which ones have embeddings
+        if not all_blocks:
             return []
 
-        block_ids = list(enabled.keys())
+        block_ids = list(all_blocks.keys())
 
         # Query for existing embeddings
         placeholders = ",".join([f"${i+1}" for i in range(len(block_ids))])
@@ -217,42 +187,52 @@ class BlockHandler(ContentHandler):
         )
 
         existing_ids = {row["contentId"] for row in existing_result}
+        missing_blocks = [
+            (block_id, block_cls)
+            for block_id, block_cls in all_blocks.items()
+            if block_id not in existing_ids
+        ]
 
-        # Convert to ContentItem — disabled filtering already done by
-        # _get_enabled_blocks so batch_size won't be exhausted by disabled blocks.
-        missing = ((bid, b) for bid, b in enabled.items() if bid not in existing_ids)
+        # Convert to ContentItem
         items = []
-        for block_id, block in itertools.islice(missing, batch_size):
+        for block_id, block_cls in missing_blocks[:batch_size]:
             try:
+                block_instance = block_cls()
+
+                if block_instance.disabled:
+                    continue
+
                 # Build searchable text from block metadata
-                if not block.name:
-                    logger.warning(
-                        f"Block {block_id} has no name — using block_id as fallback"
-                    )
-                display_name = split_camelcase(block.name) if block.name else ""
                 parts = []
-                if display_name:
-                    parts.append(display_name)
-                if block.description:
-                    parts.append(block.description)
-                if block.categories:
-                    parts.append(" ".join(str(cat.value) for cat in block.categories))
+                if block_instance.name:
+                    parts.append(block_instance.name)
+                if block_instance.description:
+                    parts.append(block_instance.description)
+                if block_instance.categories:
+                    parts.append(
+                        " ".join(str(cat.value) for cat in block_instance.categories)
+                    )
 
                 # Add input schema field descriptions
+                block_input_fields = block_instance.input_schema.model_fields
                 parts += [
                     f"{field_name}: {field_info.description}"
-                    for field_name, field_info in block.input_schema.model_fields.items()
+                    for field_name, field_info in block_input_fields.items()
                     if field_info.description
                 ]
 
                 searchable_text = " ".join(parts)
 
                 categories_list = (
-                    [cat.value for cat in block.categories] if block.categories else []
+                    [cat.value for cat in block_instance.categories]
+                    if block_instance.categories
+                    else []
                 )
 
                 # Extract provider names from credentials fields
-                credentials_info = block.input_schema.get_credentials_fields_info()
+                credentials_info = (
+                    block_instance.input_schema.get_credentials_fields_info()
+                )
                 is_integration = len(credentials_info) > 0
                 provider_names = [
                     provider.value.lower()
@@ -263,7 +243,7 @@ class BlockHandler(ContentHandler):
                 # Check if block has LlmModel field in input schema
                 has_llm_model_field = any(
                     _contains_type(field.annotation, LlmModel)
-                    for field in block.input_schema.model_fields.values()
+                    for field in block_instance.input_schema.model_fields.values()
                 )
 
                 items.append(
@@ -272,13 +252,13 @@ class BlockHandler(ContentHandler):
                         content_type=ContentType.BLOCK,
                         searchable_text=searchable_text,
                         metadata={
-                            "name": display_name or block.name or block_id,
+                            "name": block_instance.name,
                             "categories": categories_list,
                             "providers": provider_names,
                             "has_llm_model_field": has_llm_model_field,
                             "is_integration": is_integration,
                         },
-                        user_id=None,
+                        user_id=None,  # Blocks are public
                     )
                 )
             except Exception as e:
@@ -289,13 +269,22 @@ class BlockHandler(ContentHandler):
 
     async def get_stats(self) -> dict[str, int]:
         """Get statistics about block embedding coverage."""
-        enabled = await asyncio.to_thread(_get_enabled_blocks)
-        total_blocks = len(enabled)
+        from backend.blocks import get_blocks
+
+        all_blocks = get_blocks()
+
+        # Filter out disabled blocks - they're not indexed
+        enabled_block_ids = [
+            block_id
+            for block_id, block_cls in all_blocks.items()
+            if not block_cls().disabled
+        ]
+        total_blocks = len(enabled_block_ids)
 
         if total_blocks == 0:
             return {"total": 0, "with_embeddings": 0, "without_embeddings": 0}
 
-        block_ids = list(enabled.keys())
+        block_ids = enabled_block_ids
         placeholders = ",".join([f"${i+1}" for i in range(len(block_ids))])
 
         embedded_result = await query_raw_with_schema(

autogpt_platform/backend/backend/api/features/store/content_handlers_test.py

@@ -1,5 +1,7 @@
 """
-Tests for content handlers (blocks, store agents, documentation).
+E2E tests for content handlers (blocks, store agents, documentation).
+
+Tests the full flow: discovering content → generating embeddings → storing.
 """
 
 from pathlib import Path
@@ -13,103 +15,15 @@ from backend.api.features.store.content_handlers import (
     BlockHandler,
     DocumentationHandler,
     StoreAgentHandler,
-    _get_enabled_blocks,
 )
 
 
-@pytest.fixture(autouse=True)
-def _clear_block_cache():
-    """Clear the lru_cache on _get_enabled_blocks before each test."""
-    _get_enabled_blocks.cache_clear()
-    yield
-    _get_enabled_blocks.cache_clear()
-
-
-# ---------------------------------------------------------------------------
-# Helper to build a mock block class that returns a pre-configured instance
-# ---------------------------------------------------------------------------
-
-
-def _make_block_class(
-    *,
-    name: str = "Block",
-    description: str = "",
-    disabled: bool = False,
-    categories: list[MagicMock] | None = None,
-    fields: dict[str, str] | None = None,
-    raise_on_init: Exception | None = None,
-) -> MagicMock:
-    cls = MagicMock()
-    if raise_on_init is not None:
-        cls.side_effect = raise_on_init
-        return cls
-    inst = MagicMock()
-    inst.name = name
-    inst.disabled = disabled
-    inst.description = description
-    inst.categories = categories or []
-    field_mocks = {
-        fname: MagicMock(description=fdesc) for fname, fdesc in (fields or {}).items()
-    }
-    inst.input_schema.model_fields = field_mocks
-    inst.input_schema.get_credentials_fields_info.return_value = {}
-    cls.return_value = inst
-    return cls
-
-
-# ---------------------------------------------------------------------------
-# _get_enabled_blocks
-# ---------------------------------------------------------------------------
-
-
-def test_get_enabled_blocks_filters_disabled():
-    """Disabled blocks are excluded."""
-    blocks = {
-        "enabled": _make_block_class(name="E", disabled=False),
-        "disabled": _make_block_class(name="D", disabled=True),
-    }
-    with patch(
-        "backend.api.features.store.content_handlers.get_blocks", return_value=blocks
-    ):
-        result = _get_enabled_blocks()
-    assert list(result.keys()) == ["enabled"]
-
-
-def test_get_enabled_blocks_skips_broken():
-    """Blocks that raise on init are skipped without crashing."""
-    blocks = {
-        "good": _make_block_class(name="Good"),
-        "bad": _make_block_class(raise_on_init=RuntimeError("boom")),
-    }
-    with patch(
-        "backend.api.features.store.content_handlers.get_blocks", return_value=blocks
-    ):
-        result = _get_enabled_blocks()
-    assert list(result.keys()) == ["good"]
-
-
-def test_get_enabled_blocks_cached():
-    """_get_enabled_blocks() calls get_blocks() only once across multiple calls."""
-    blocks = {"b1": _make_block_class(name="B1")}
-    with patch(
-        "backend.api.features.store.content_handlers.get_blocks", return_value=blocks
-    ) as mock_get_blocks:
-        result1 = _get_enabled_blocks()
-        result2 = _get_enabled_blocks()
-    assert result1 is result2
-    mock_get_blocks.assert_called_once()
-
-
-# ---------------------------------------------------------------------------
-# StoreAgentHandler
-# ---------------------------------------------------------------------------
-
-
 @pytest.mark.asyncio(loop_scope="session")
 async def test_store_agent_handler_get_missing_items(mocker):
     """Test StoreAgentHandler fetches approved agents without embeddings."""
     handler = StoreAgentHandler()
 
+    # Mock database query
     mock_missing = [
         {
             "id": "agent-1",
@@ -140,7 +54,9 @@ async def test_store_agent_handler_get_stats(mocker):
     """Test StoreAgentHandler returns correct stats."""
     handler = StoreAgentHandler()
 
+    # Mock approved count query
     mock_approved = [{"count": 50}]
+    # Mock embedded count query
     mock_embedded = [{"count": 30}]
 
     with patch(
@@ -154,130 +70,74 @@ async def test_store_agent_handler_get_stats(mocker):
         assert stats["without_embeddings"] == 20
 
 
-# ---------------------------------------------------------------------------
-# BlockHandler
-# ---------------------------------------------------------------------------
-
-
 @pytest.mark.asyncio(loop_scope="session")
-async def test_block_handler_get_missing_items():
+async def test_block_handler_get_missing_items(mocker):
     """Test BlockHandler discovers blocks without embeddings."""
     handler = BlockHandler()
 
-    blocks = {
-        "block-uuid-1": _make_block_class(
-            name="CalculatorBlock",
-            description="Performs calculations",
-            categories=[MagicMock(value="MATH")],
-            fields={"expression": "Math expression to evaluate"},
-        ),
-    }
+    # Mock get_blocks to return test blocks
+    mock_block_class = MagicMock()
+    mock_block_instance = MagicMock()
+    mock_block_instance.name = "Calculator Block"
+    mock_block_instance.description = "Performs calculations"
+    mock_block_instance.categories = [MagicMock(value="MATH")]
+    mock_block_instance.disabled = False
+    mock_field = MagicMock()
+    mock_field.description = "Math expression to evaluate"
+    mock_block_instance.input_schema.model_fields = {"expression": mock_field}
+    mock_block_instance.input_schema.get_credentials_fields_info.return_value = {}
+    mock_block_class.return_value = mock_block_instance
+
+    mock_blocks = {"block-uuid-1": mock_block_class}
+
+    # Mock existing embeddings query (no embeddings exist)
+    mock_existing = []
 
     with patch(
-        "backend.api.features.store.content_handlers.get_blocks", return_value=blocks
+        "backend.blocks.get_blocks",
+        return_value=mock_blocks,
     ):
         with patch(
             "backend.api.features.store.content_handlers.query_raw_with_schema",
-            return_value=[],
+            return_value=mock_existing,
         ):
             items = await handler.get_missing_items(batch_size=10)
 
             assert len(items) == 1
             assert items[0].content_id == "block-uuid-1"
             assert items[0].content_type == ContentType.BLOCK
-            # CamelCase should be split in searchable text and metadata name
             assert "Calculator Block" in items[0].searchable_text
             assert "Performs calculations" in items[0].searchable_text
             assert "MATH" in items[0].searchable_text
             assert "expression: Math expression" in items[0].searchable_text
-            assert items[0].metadata["name"] == "Calculator Block"
             assert items[0].user_id is None
 
 
 @pytest.mark.asyncio(loop_scope="session")
-async def test_block_handler_get_missing_items_splits_camelcase():
-    """CamelCase block names are split for better search indexing."""
-    handler = BlockHandler()
-
-    blocks = {
-        "ai-block": _make_block_class(name="AITextGeneratorBlock"),
-    }
-
-    with patch(
-        "backend.api.features.store.content_handlers.get_blocks", return_value=blocks
-    ):
-        with patch(
-            "backend.api.features.store.content_handlers.query_raw_with_schema",
-            return_value=[],
-        ):
-            items = await handler.get_missing_items(batch_size=10)
-
-            assert len(items) == 1
-            assert "AI Text Generator Block" in items[0].searchable_text
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_block_handler_get_missing_items_batch_size_zero():
-    """batch_size=0 returns an empty list; the DB is still queried to find missing IDs."""
-    handler = BlockHandler()
-
-    blocks = {"b1": _make_block_class(name="B1")}
-
-    with patch(
-        "backend.api.features.store.content_handlers.get_blocks", return_value=blocks
-    ):
-        with patch(
-            "backend.api.features.store.content_handlers.query_raw_with_schema",
-            return_value=[],
-        ) as mock_query:
-            items = await handler.get_missing_items(batch_size=0)
-            assert items == []
-            # DB query is still issued to learn which blocks lack embeddings;
-            # the empty result comes from itertools.islice limiting to 0 items.
-            mock_query.assert_called_once()
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_block_handler_disabled_dont_exhaust_batch():
-    """Disabled blocks don't consume batch budget, so enabled blocks get indexed."""
-    handler = BlockHandler()
-
-    # 5 disabled + 3 enabled, batch_size=2
-    blocks = {
-        **{
-            f"dis-{i}": _make_block_class(name=f"D{i}", disabled=True) for i in range(5)
-        },
-        **{f"en-{i}": _make_block_class(name=f"E{i}") for i in range(3)},
-    }
-
-    with patch(
-        "backend.api.features.store.content_handlers.get_blocks", return_value=blocks
-    ):
-        with patch(
-            "backend.api.features.store.content_handlers.query_raw_with_schema",
-            return_value=[],
-        ):
-            items = await handler.get_missing_items(batch_size=2)
-
-            assert len(items) == 2
-            assert all(item.content_id.startswith("en-") for item in items)
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_block_handler_get_stats():
+async def test_block_handler_get_stats(mocker):
     """Test BlockHandler returns correct stats."""
     handler = BlockHandler()
 
-    blocks = {
-        "block-1": _make_block_class(name="B1"),
-        "block-2": _make_block_class(name="B2"),
-        "block-3": _make_block_class(name="B3"),
+    # Mock get_blocks - each block class returns an instance with disabled=False
+    def make_mock_block_class():
+        mock_class = MagicMock()
+        mock_instance = MagicMock()
+        mock_instance.disabled = False
+        mock_class.return_value = mock_instance
+        return mock_class
+
+    mock_blocks = {
+        "block-1": make_mock_block_class(),
+        "block-2": make_mock_block_class(),
+        "block-3": make_mock_block_class(),
     }
 
+    # Mock embedded count query (2 blocks have embeddings)
     mock_embedded = [{"count": 2}]
 
     with patch(
-        "backend.api.features.store.content_handlers.get_blocks", return_value=blocks
+        "backend.blocks.get_blocks",
+        return_value=mock_blocks,
     ):
         with patch(
             "backend.api.features.store.content_handlers.query_raw_with_schema",
@@ -290,123 +150,21 @@ async def test_block_handler_get_stats():
             assert stats["without_embeddings"] == 1
 
 
-@pytest.mark.asyncio(loop_scope="session")
-async def test_block_handler_get_stats_skips_broken():
-    """get_stats skips broken blocks instead of crashing."""
-    handler = BlockHandler()
-
-    blocks = {
-        "good": _make_block_class(name="Good"),
-        "bad": _make_block_class(raise_on_init=RuntimeError("boom")),
-    }
-
-    mock_embedded = [{"count": 1}]
-
-    with patch(
-        "backend.api.features.store.content_handlers.get_blocks", return_value=blocks
-    ):
-        with patch(
-            "backend.api.features.store.content_handlers.query_raw_with_schema",
-            return_value=mock_embedded,
-        ):
-            stats = await handler.get_stats()
-
-            assert stats["total"] == 1  # only the good block
-            assert stats["with_embeddings"] == 1
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_block_handler_handles_none_name():
-    """When block.name is None the fallback display name logic is used."""
-    handler = BlockHandler()
-
-    blocks = {
-        "none-name-block": _make_block_class(
-            name="placeholder",  # will be overridden to None below
-            description="A block with no name",
-        ),
-    }
-    # Override the name to None after construction so _make_block_class
-    # doesn't interfere with the mock wiring.
-    blocks["none-name-block"].return_value.name = None
-
-    with patch(
-        "backend.api.features.store.content_handlers.get_blocks", return_value=blocks
-    ):
-        with patch(
-            "backend.api.features.store.content_handlers.query_raw_with_schema",
-            return_value=[],
-        ):
-            items = await handler.get_missing_items(batch_size=10)
-
-            assert len(items) == 1
-            # display_name should be "" because block.name is None
-            # searchable_text should still contain the description
-            assert "A block with no name" in items[0].searchable_text
-            # metadata["name"] falls back to block_id when both display_name
-            # and block.name are falsy, ensuring it is always a non-empty string.
-            assert items[0].metadata["name"] == "none-name-block"
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_block_handler_handles_empty_attributes():
-    """Test BlockHandler handles blocks with empty/falsy attribute values."""
-    handler = BlockHandler()
-
-    blocks = {"block-minimal": _make_block_class(name="Minimal Block")}
-
-    with patch(
-        "backend.api.features.store.content_handlers.get_blocks", return_value=blocks
-    ):
-        with patch(
-            "backend.api.features.store.content_handlers.query_raw_with_schema",
-            return_value=[],
-        ):
-            items = await handler.get_missing_items(batch_size=10)
-
-            assert len(items) == 1
-            assert items[0].searchable_text == "Minimal Block"
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_block_handler_skips_failed_blocks():
-    """Test BlockHandler skips blocks that fail to instantiate."""
-    handler = BlockHandler()
-
-    blocks = {
-        "good-block": _make_block_class(name="Good Block", description="Works fine"),
-        "bad-block": _make_block_class(raise_on_init=Exception("Instantiation failed")),
-    }
-
-    with patch(
-        "backend.api.features.store.content_handlers.get_blocks", return_value=blocks
-    ):
-        with patch(
-            "backend.api.features.store.content_handlers.query_raw_with_schema",
-            return_value=[],
-        ):
-            items = await handler.get_missing_items(batch_size=10)
-
-            assert len(items) == 1
-            assert items[0].content_id == "good-block"
-
-
-# ---------------------------------------------------------------------------
-# DocumentationHandler
-# ---------------------------------------------------------------------------
-
-
 @pytest.mark.asyncio(loop_scope="session")
 async def test_documentation_handler_get_missing_items(tmp_path, mocker):
     """Test DocumentationHandler discovers docs without embeddings."""
     handler = DocumentationHandler()
 
+    # Create temporary docs directory with test files
     docs_root = tmp_path / "docs"
     docs_root.mkdir()
+
     (docs_root / "guide.md").write_text("# Getting Started\n\nThis is a guide.")
     (docs_root / "api.mdx").write_text("# API Reference\n\nAPI documentation.")
 
+    # Mock _get_docs_root to return temp dir
     with patch.object(handler, "_get_docs_root", return_value=docs_root):
+        # Mock existing embeddings query (no embeddings exist)
         with patch(
             "backend.api.features.store.content_handlers.query_raw_with_schema",
             return_value=[],
@@ -415,6 +173,7 @@ async def test_documentation_handler_get_missing_items(tmp_path, mocker):
 
             assert len(items) == 2
 
+            # Check guide.md (content_id format: doc_path::section_index)
             guide_item = next(
                 (item for item in items if item.content_id == "guide.md::0"), None
             )
@@ -425,6 +184,7 @@ async def test_documentation_handler_get_missing_items(tmp_path, mocker):
             assert guide_item.metadata["doc_title"] == "Getting Started"
             assert guide_item.user_id is None
 
+            # Check api.mdx (content_id format: doc_path::section_index)
             api_item = next(
                 (item for item in items if item.content_id == "api.mdx::0"), None
             )
@@ -437,12 +197,14 @@ async def test_documentation_handler_get_stats(tmp_path, mocker):
     """Test DocumentationHandler returns correct stats."""
     handler = DocumentationHandler()
 
+    # Create temporary docs directory
     docs_root = tmp_path / "docs"
     docs_root.mkdir()
     (docs_root / "doc1.md").write_text("# Doc 1")
     (docs_root / "doc2.md").write_text("# Doc 2")
     (docs_root / "doc3.mdx").write_text("# Doc 3")
 
+    # Mock embedded count query (1 doc has embedding)
     mock_embedded = [{"count": 1}]
 
     with patch.object(handler, "_get_docs_root", return_value=docs_root):
@@ -462,11 +224,13 @@ async def test_documentation_handler_title_extraction(tmp_path):
     """Test DocumentationHandler extracts title from markdown heading."""
     handler = DocumentationHandler()
 
+    # Test with heading
     doc_with_heading = tmp_path / "with_heading.md"
     doc_with_heading.write_text("# My Title\n\nContent here")
     title = handler._extract_doc_title(doc_with_heading)
     assert title == "My Title"
 
+    # Test without heading
     doc_without_heading = tmp_path / "no-heading.md"
     doc_without_heading.write_text("Just content, no heading")
     title = handler._extract_doc_title(doc_without_heading)
@@ -478,6 +242,7 @@ async def test_documentation_handler_markdown_chunking(tmp_path):
     """Test DocumentationHandler chunks markdown by headings."""
     handler = DocumentationHandler()
 
+    # Test document with multiple sections
     doc_with_sections = tmp_path / "sections.md"
     doc_with_sections.write_text(
         "# Document Title\n\n"
@@ -489,6 +254,7 @@ async def test_documentation_handler_markdown_chunking(tmp_path):
     )
     sections = handler._chunk_markdown_by_headings(doc_with_sections)
 
+    # Should have 3 sections: intro (with doc title), section one, section two
     assert len(sections) == 3
     assert sections[0].title == "Document Title"
     assert sections[0].index == 0
@@ -502,6 +268,7 @@ async def test_documentation_handler_markdown_chunking(tmp_path):
     assert sections[2].index == 2
     assert "Content for section two" in sections[2].content
 
+    # Test document without headings
     doc_no_sections = tmp_path / "no-sections.md"
     doc_no_sections.write_text("Just plain content without any headings.")
     sections = handler._chunk_markdown_by_headings(doc_no_sections)
@@ -515,39 +282,21 @@ async def test_documentation_handler_section_content_ids():
     """Test DocumentationHandler creates and parses section content IDs."""
     handler = DocumentationHandler()
 
+    # Test making content ID
     content_id = handler._make_section_content_id("docs/guide.md", 2)
     assert content_id == "docs/guide.md::2"
 
+    # Test parsing content ID
     doc_path, section_index = handler._parse_section_content_id("docs/guide.md::2")
     assert doc_path == "docs/guide.md"
     assert section_index == 2
 
+    # Test parsing legacy format (no section index)
     doc_path, section_index = handler._parse_section_content_id("docs/old-format.md")
     assert doc_path == "docs/old-format.md"
     assert section_index == 0
 
 
-@pytest.mark.asyncio(loop_scope="session")
-async def test_documentation_handler_missing_docs_directory():
-    """Test DocumentationHandler handles missing docs directory gracefully."""
-    handler = DocumentationHandler()
-
-    fake_path = Path("/nonexistent/docs")
-    with patch.object(handler, "_get_docs_root", return_value=fake_path):
-        items = await handler.get_missing_items(batch_size=10)
-        assert items == []
-
-        stats = await handler.get_stats()
-        assert stats["total"] == 0
-        assert stats["with_embeddings"] == 0
-        assert stats["without_embeddings"] == 0
-
-
-# ---------------------------------------------------------------------------
-# Registry
-# ---------------------------------------------------------------------------
-
-
 @pytest.mark.asyncio(loop_scope="session")
 async def test_content_handlers_registry():
     """Test all content types are registered."""
@@ -558,3 +307,88 @@ async def test_content_handlers_registry():
     assert isinstance(CONTENT_HANDLERS[ContentType.STORE_AGENT], StoreAgentHandler)
     assert isinstance(CONTENT_HANDLERS[ContentType.BLOCK], BlockHandler)
     assert isinstance(CONTENT_HANDLERS[ContentType.DOCUMENTATION], DocumentationHandler)
+
+
+@pytest.mark.asyncio(loop_scope="session")
+async def test_block_handler_handles_empty_attributes():
+    """Test BlockHandler handles blocks with empty/falsy attribute values."""
+    handler = BlockHandler()
+
+    # Mock block with empty values (all attributes exist but are falsy)
+    mock_block_class = MagicMock()
+    mock_block_instance = MagicMock()
+    mock_block_instance.name = "Minimal Block"
+    mock_block_instance.disabled = False
+    mock_block_instance.description = ""
+    mock_block_instance.categories = set()
+    mock_block_instance.input_schema.model_fields = {}
+    mock_block_instance.input_schema.get_credentials_fields_info.return_value = {}
+    mock_block_class.return_value = mock_block_instance
+
+    mock_blocks = {"block-minimal": mock_block_class}
+
+    with patch(
+        "backend.blocks.get_blocks",
+        return_value=mock_blocks,
+    ):
+        with patch(
+            "backend.api.features.store.content_handlers.query_raw_with_schema",
+            return_value=[],
+        ):
+            items = await handler.get_missing_items(batch_size=10)
+
+            assert len(items) == 1
+            assert items[0].searchable_text == "Minimal Block"
+
+
+@pytest.mark.asyncio(loop_scope="session")
+async def test_block_handler_skips_failed_blocks():
+    """Test BlockHandler skips blocks that fail to instantiate."""
+    handler = BlockHandler()
+
+    # Mock one good block and one bad block
+    good_block = MagicMock()
+    good_instance = MagicMock()
+    good_instance.name = "Good Block"
+    good_instance.description = "Works fine"
+    good_instance.categories = []
+    good_instance.disabled = False
+    good_instance.input_schema.model_fields = {}
+    good_instance.input_schema.get_credentials_fields_info.return_value = {}
+    good_block.return_value = good_instance
+
+    bad_block = MagicMock()
+    bad_block.side_effect = Exception("Instantiation failed")
+
+    mock_blocks = {"good-block": good_block, "bad-block": bad_block}
+
+    with patch(
+        "backend.blocks.get_blocks",
+        return_value=mock_blocks,
+    ):
+        with patch(
+            "backend.api.features.store.content_handlers.query_raw_with_schema",
+            return_value=[],
+        ):
+            items = await handler.get_missing_items(batch_size=10)
+
+            # Should only get the good block
+            assert len(items) == 1
+            assert items[0].content_id == "good-block"
+
+
+@pytest.mark.asyncio(loop_scope="session")
+async def test_documentation_handler_missing_docs_directory():
+    """Test DocumentationHandler handles missing docs directory gracefully."""
+    handler = DocumentationHandler()
+
+    # Mock _get_docs_root to return non-existent path
+    fake_path = Path("/nonexistent/docs")
+    with patch.object(handler, "_get_docs_root", return_value=fake_path):
+        items = await handler.get_missing_items(batch_size=10)
+        assert items == []
+
+        stats = await handler.get_stats()
+        assert stats["total"] == 0
+        assert stats["with_embeddings"] == 0
+        assert stats["without_embeddings"] == 0

autogpt_platform/backend/backend/api/features/store/db_test.py

@@ -26,7 +26,7 @@ async def test_get_store_agents(mocker):
     mock_agents = [
         prisma.models.StoreAgent(
             listing_id="test-id",
-            listing_version_id="version123",
+            storeListingVersionId="version123",
             slug="test-agent",
             agent_name="Test Agent",
             agent_video=None,
@@ -40,11 +40,11 @@ async def test_get_store_agents(mocker):
             runs=10,
             rating=4.5,
             versions=["1.0"],
-            graph_id="test-graph-id",
-            graph_versions=["1"],
+            agentGraphVersions=["1"],
+            agentGraphId="test-graph-id",
             updated_at=datetime.now(),
             is_available=False,
-            use_for_onboarding=False,
+            useForOnboarding=False,
         )
     ]
 
@@ -68,10 +68,10 @@ async def test_get_store_agents(mocker):
 
 @pytest.mark.asyncio(loop_scope="session")
 async def test_get_store_agent_details(mocker):
-    # Mock data - StoreAgent view already contains the active version data
+    # Mock data
     mock_agent = prisma.models.StoreAgent(
         listing_id="test-id",
-        listing_version_id="version123",
+        storeListingVersionId="version123",
         slug="test-agent",
         agent_name="Test Agent",
         agent_video="video.mp4",
@@ -85,38 +85,102 @@ async def test_get_store_agent_details(mocker):
         runs=10,
         rating=4.5,
         versions=["1.0"],
-        graph_id="test-graph-id",
-        graph_versions=["1"],
+        agentGraphVersions=["1"],
+        agentGraphId="test-graph-id",
         updated_at=datetime.now(),
-        is_available=True,
-        use_for_onboarding=False,
+        is_available=False,
+        useForOnboarding=False,
     )
 
-    # Mock StoreAgent prisma call
+    # Mock active version agent (what we want to return for active version)
+    mock_active_agent = prisma.models.StoreAgent(
+        listing_id="test-id",
+        storeListingVersionId="active-version-id",
+        slug="test-agent",
+        agent_name="Test Agent Active",
+        agent_video="active_video.mp4",
+        agent_image=["active_image.jpg"],
+        featured=False,
+        creator_username="creator",
+        creator_avatar="avatar.jpg",
+        sub_heading="Test heading active",
+        description="Test description active",
+        categories=["test"],
+        runs=15,
+        rating=4.8,
+        versions=["1.0", "2.0"],
+        agentGraphVersions=["1", "2"],
+        agentGraphId="test-graph-id-active",
+        updated_at=datetime.now(),
+        is_available=True,
+        useForOnboarding=False,
+    )
+
+    # Create a mock StoreListing result
+    mock_store_listing = mocker.MagicMock()
+    mock_store_listing.activeVersionId = "active-version-id"
+    mock_store_listing.hasApprovedVersion = True
+    mock_store_listing.ActiveVersion = mocker.MagicMock()
+    mock_store_listing.ActiveVersion.recommendedScheduleCron = None
+
+    # Mock StoreAgent prisma call - need to handle multiple calls
     mock_store_agent = mocker.patch("prisma.models.StoreAgent.prisma")
-    mock_store_agent.return_value.find_first = mocker.AsyncMock(return_value=mock_agent)
+
+    # Set up side_effect to return different results for different calls
+    def mock_find_first_side_effect(*args, **kwargs):
+        where_clause = kwargs.get("where", {})
+        if "storeListingVersionId" in where_clause:
+            # Second call for active version
+            return mock_active_agent
+        else:
+            # First call for initial lookup
+            return mock_agent
+
+    mock_store_agent.return_value.find_first = mocker.AsyncMock(
+        side_effect=mock_find_first_side_effect
+    )
+
+    # Mock Profile prisma call
+    mock_profile = mocker.MagicMock()
+    mock_profile.userId = "user-id-123"
+    mock_profile_db = mocker.patch("prisma.models.Profile.prisma")
+    mock_profile_db.return_value.find_first = mocker.AsyncMock(
+        return_value=mock_profile
+    )
+
+    # Mock StoreListing prisma call
+    mock_store_listing_db = mocker.patch("prisma.models.StoreListing.prisma")
+    mock_store_listing_db.return_value.find_first = mocker.AsyncMock(
+        return_value=mock_store_listing
+    )
 
     # Call function
     result = await db.get_store_agent_details("creator", "test-agent")
 
-    # Verify results - constructed from the StoreAgent view
+    # Verify results - should use active version data
     assert result.slug == "test-agent"
-    assert result.agent_name == "Test Agent"
-    assert result.active_version_id == "version123"
+    assert result.agent_name == "Test Agent Active"  # From active version
+    assert result.active_version_id == "active-version-id"
     assert result.has_approved_version is True
-    assert result.store_listing_version_id == "version123"
-    assert result.graph_id == "test-graph-id"
-    assert result.runs == 10
-    assert result.rating == 4.5
+    assert (
+        result.store_listing_version_id == "active-version-id"
+    )  # Should be active version ID
 
-    # Verify single StoreAgent lookup
-    mock_store_agent.return_value.find_first.assert_called_once_with(
+    # Verify mocks called correctly - now expecting 2 calls
+    assert mock_store_agent.return_value.find_first.call_count == 2
+
+    # Check the specific calls
+    calls = mock_store_agent.return_value.find_first.call_args_list
+    assert calls[0] == mocker.call(
         where={"creator_username": "creator", "slug": "test-agent"}
     )
+    assert calls[1] == mocker.call(where={"storeListingVersionId": "active-version-id"})
+
+    mock_store_listing_db.return_value.find_first.assert_called_once()
 
 
 @pytest.mark.asyncio(loop_scope="session")
-async def test_get_store_creator(mocker):
+async def test_get_store_creator_details(mocker):
     # Mock data
     mock_creator_data = prisma.models.Creator(
         name="Test Creator",
@@ -138,7 +202,7 @@ async def test_get_store_creator(mocker):
     mock_creator.return_value.find_unique.return_value = mock_creator_data
 
     # Call function
-    result = await db.get_store_creator("creator")
+    result = await db.get_store_creator_details("creator")
 
     # Verify results
     assert result.username == "creator"
@@ -154,111 +218,61 @@ async def test_get_store_creator(mocker):
 
 @pytest.mark.asyncio(loop_scope="session")
 async def test_create_store_submission(mocker):
-    now = datetime.now()
-
-    # Mock agent graph (with no pending submissions) and user with profile
-    mock_profile = prisma.models.Profile(
-        id="profile-id",
-        userId="user-id",
-        name="Test User",
-        username="testuser",
-        description="Test",
-        isFeatured=False,
-        links=[],
-        createdAt=now,
-        updatedAt=now,
-    )
-    mock_user = prisma.models.User(
-        id="user-id",
-        email="test@example.com",
-        createdAt=now,
-        updatedAt=now,
-        Profile=[mock_profile],
-        emailVerified=True,
-        metadata="{}",  # type: ignore[reportArgumentType]
-        integrations="",
-        maxEmailsPerDay=1,
-        notifyOnAgentRun=True,
-        notifyOnZeroBalance=True,
-        notifyOnLowBalance=True,
-        notifyOnBlockExecutionFailed=True,
-        notifyOnContinuousAgentError=True,
-        notifyOnDailySummary=True,
-        notifyOnWeeklySummary=True,
-        notifyOnMonthlySummary=True,
-        notifyOnAgentApproved=True,
-        notifyOnAgentRejected=True,
-        timezone="Europe/Delft",
-        subscriptionTier=prisma.enums.SubscriptionTier.FREE,  # type: ignore[reportCallIssue,reportAttributeAccessIssue]
-    )
+    # Mock data
     mock_agent = prisma.models.AgentGraph(
         id="agent-id",
         version=1,
         userId="user-id",
-        createdAt=now,
+        createdAt=datetime.now(),
         isActive=True,
-        StoreListingVersions=[],
-        User=mock_user,
     )
 
-    # Mock the created StoreListingVersion (returned by create)
-    mock_store_listing_obj = prisma.models.StoreListing(
+    mock_listing = prisma.models.StoreListing(
         id="listing-id",
-        createdAt=now,
-        updatedAt=now,
+        createdAt=datetime.now(),
+        updatedAt=datetime.now(),
         isDeleted=False,
         hasApprovedVersion=False,
         slug="test-agent",
         agentGraphId="agent-id",
-        owningUserId="user-id",
-        useForOnboarding=False,
-    )
-    mock_version = prisma.models.StoreListingVersion(
-        id="version-id",
-        agentGraphId="agent-id",
         agentGraphVersion=1,
-        name="Test Agent",
-        description="Test description",
-        createdAt=now,
-        updatedAt=now,
-        subHeading="",
-        imageUrls=[],
-        categories=[],
-        isFeatured=False,
-        isDeleted=False,
-        version=1,
-        storeListingId="listing-id",
-        submissionStatus=prisma.enums.SubmissionStatus.PENDING,
-        isAvailable=True,
-        submittedAt=now,
-        StoreListing=mock_store_listing_obj,
+        owningUserId="user-id",
+        Versions=[
+            prisma.models.StoreListingVersion(
+                id="version-id",
+                agentGraphId="agent-id",
+                agentGraphVersion=1,
+                name="Test Agent",
+                description="Test description",
+                createdAt=datetime.now(),
+                updatedAt=datetime.now(),
+                subHeading="Test heading",
+                imageUrls=["image.jpg"],
+                categories=["test"],
+                isFeatured=False,
+                isDeleted=False,
+                version=1,
+                storeListingId="listing-id",
+                submissionStatus=prisma.enums.SubmissionStatus.PENDING,
+                isAvailable=True,
+            )
+        ],
+        useForOnboarding=False,
     )
 
     # Mock prisma calls
     mock_agent_graph = mocker.patch("prisma.models.AgentGraph.prisma")
     mock_agent_graph.return_value.find_first = mocker.AsyncMock(return_value=mock_agent)
 
-    # Mock transaction context manager
-    mock_tx = mocker.MagicMock()
-    mocker.patch(
-        "backend.api.features.store.db.transaction",
-        return_value=mocker.AsyncMock(
-            __aenter__=mocker.AsyncMock(return_value=mock_tx),
-            __aexit__=mocker.AsyncMock(return_value=False),
-        ),
-    )
-
-    mock_sl = mocker.patch("prisma.models.StoreListing.prisma")
-    mock_sl.return_value.find_unique = mocker.AsyncMock(return_value=None)
-
-    mock_slv = mocker.patch("prisma.models.StoreListingVersion.prisma")
-    mock_slv.return_value.create = mocker.AsyncMock(return_value=mock_version)
+    mock_store_listing = mocker.patch("prisma.models.StoreListing.prisma")
+    mock_store_listing.return_value.find_first = mocker.AsyncMock(return_value=None)
+    mock_store_listing.return_value.create = mocker.AsyncMock(return_value=mock_listing)
 
     # Call function
     result = await db.create_store_submission(
         user_id="user-id",
-        graph_id="agent-id",
-        graph_version=1,
+        agent_id="agent-id",
+        agent_version=1,
         slug="test-agent",
         name="Test Agent",
         description="Test description",
@@ -267,11 +281,11 @@ async def test_create_store_submission(mocker):
     # Verify results
     assert result.name == "Test Agent"
     assert result.description == "Test description"
-    assert result.listing_version_id == "version-id"
+    assert result.store_listing_version_id == "version-id"
 
     # Verify mocks called correctly
     mock_agent_graph.return_value.find_first.assert_called_once()
-    mock_slv.return_value.create.assert_called_once()
+    mock_store_listing.return_value.create.assert_called_once()
 
 
 @pytest.mark.asyncio(loop_scope="session")
@@ -304,6 +318,7 @@ async def test_update_profile(mocker):
         description="Test description",
         links=["link1"],
         avatar_url="avatar.jpg",
+        is_featured=False,
     )
 
     # Call function
@@ -374,7 +389,7 @@ async def test_get_store_agents_with_search_and_filters_parameterized():
         creators=["creator1'; DROP TABLE Users; --", "creator2"],
         category="AI'; DELETE FROM StoreAgent; --",
         featured=True,
-        sorted_by=db.StoreAgentsSortOptions.RATING,
+        sorted_by="rating",
         page=1,
         page_size=20,
     )

autogpt_platform/backend/backend/api/features/store/embeddings.py

@@ -15,7 +15,6 @@ from prisma.enums import ContentType
 from tiktoken import encoding_for_model
 
 from backend.api.features.store.content_handlers import CONTENT_HANDLERS
-from backend.blocks import get_blocks
 from backend.data.db import execute_raw_with_schema, query_raw_with_schema
 from backend.util.clients import get_openai_client
 from backend.util.json import dumps
@@ -663,6 +662,8 @@ async def cleanup_orphaned_embeddings() -> dict[str, Any]:
                 )
                 current_ids = {row["id"] for row in valid_agents}
             elif content_type == ContentType.BLOCK:
+                from backend.blocks import get_blocks
+
                 current_ids = set(get_blocks().keys())
             elif content_type == ContentType.DOCUMENTATION:
                 # Use DocumentationHandler to get section-based content IDs

autogpt_platform/backend/backend/api/features/store/exceptions.py

@@ -57,6 +57,12 @@ class StoreError(ValueError):
     pass
 
 
+class AgentNotFoundError(NotFoundError):
+    """Raised when an agent is not found"""
+
+    pass
+
+
 class CreatorNotFoundError(NotFoundError):
     """Raised when a creator is not found"""
 

autogpt_platform/backend/backend/api/features/store/hybrid_search.py

@@ -31,10 +31,12 @@ logger = logging.getLogger(__name__)
 
 
 def tokenize(text: str) -> list[str]:
-    """Tokenize text for BM25."""
+    """Simple tokenizer for BM25 - lowercase and split on non-alphanumeric."""
     if not text:
         return []
-    return re.findall(r"\b\w+\b", text.lower())
+    # Lowercase and split on non-alphanumeric characters
+    tokens = re.findall(r"\b\w+\b", text.lower())
+    return tokens
 
 
 def bm25_rerank(
@@ -566,7 +568,7 @@ async def hybrid_search(
             SELECT uce."contentId" as "storeListingVersionId"
             FROM {{schema_prefix}}"UnifiedContentEmbedding" uce
             INNER JOIN {{schema_prefix}}"StoreAgent" sa
-                ON uce."contentId" = sa.listing_version_id
+                ON uce."contentId" = sa."storeListingVersionId"
             WHERE uce."contentType" = 'STORE_AGENT'::{{schema_prefix}}"ContentType"
             AND uce."userId" IS NULL
             AND uce.search @@ plainto_tsquery('english', {query_param})
@@ -580,7 +582,7 @@ async def hybrid_search(
                 SELECT uce."contentId", uce.embedding
                 FROM {{schema_prefix}}"UnifiedContentEmbedding" uce
                 INNER JOIN {{schema_prefix}}"StoreAgent" sa
-                    ON uce."contentId" = sa.listing_version_id
+                    ON uce."contentId" = sa."storeListingVersionId"
                 WHERE uce."contentType" = 'STORE_AGENT'::{{schema_prefix}}"ContentType"
                 AND uce."userId" IS NULL
                 AND {where_clause}
@@ -603,7 +605,7 @@ async def hybrid_search(
                 sa.featured,
                 sa.is_available,
                 sa.updated_at,
-                sa.graph_id,
+                sa."agentGraphId",
                 -- Searchable text for BM25 reranking
                 COALESCE(sa.agent_name, '') || ' ' || COALESCE(sa.sub_heading, '') || ' ' || COALESCE(sa.description, '') as searchable_text,
                 -- Semantic score
@@ -625,9 +627,9 @@ async def hybrid_search(
                 sa.runs as popularity_raw
             FROM candidates c
             INNER JOIN {{schema_prefix}}"StoreAgent" sa
-                ON c."storeListingVersionId" = sa.listing_version_id
+                ON c."storeListingVersionId" = sa."storeListingVersionId"
             INNER JOIN {{schema_prefix}}"UnifiedContentEmbedding" uce
-                ON sa.listing_version_id = uce."contentId"
+                ON sa."storeListingVersionId" = uce."contentId"
                 AND uce."contentType" = 'STORE_AGENT'::{{schema_prefix}}"ContentType"
         ),
         max_vals AS (
@@ -663,7 +665,7 @@ async def hybrid_search(
                 featured,
                 is_available,
                 updated_at,
-                graph_id,
+                "agentGraphId",
                 searchable_text,
                 semantic_score,
                 lexical_score,

autogpt_platform/backend/backend/api/features/store/hybrid_search_test.py

@@ -14,27 +14,9 @@ from backend.api.features.store.hybrid_search import (
     HybridSearchWeights,
     UnifiedSearchWeights,
     hybrid_search,
-    tokenize,
     unified_hybrid_search,
 )
 
-# ---------------------------------------------------------------------------
-# tokenize (BM25)
-# ---------------------------------------------------------------------------
-
-
-@pytest.mark.parametrize(
-    "input_text, expected",
-    [
-        ("AITextGeneratorBlock", ["aitextgeneratorblock"]),
-        ("hello world", ["hello", "world"]),
-        ("", []),
-        ("HTTPRequest", ["httprequest"]),
-    ],
-)
-def test_tokenize(input_text: str, expected: list[str]):
-    assert tokenize(input_text) == expected
-
 
 @pytest.mark.asyncio(loop_scope="session")
 @pytest.mark.integration

autogpt_platform/backend/backend/api/features/store/model.py

@@ -1,14 +1,11 @@
 import datetime
-from typing import TYPE_CHECKING, List, Self
+from typing import List
 
 import prisma.enums
 import pydantic
 
 from backend.util.models import Pagination
 
-if TYPE_CHECKING:
-    import prisma.models
-
 
 class ChangelogEntry(pydantic.BaseModel):
     version: str
@@ -16,9 +13,9 @@ class ChangelogEntry(pydantic.BaseModel):
     date: datetime.datetime
 
 
-class MyUnpublishedAgent(pydantic.BaseModel):
-    graph_id: str
-    graph_version: int
+class MyAgent(pydantic.BaseModel):
+    agent_id: str
+    agent_version: int
     agent_name: str
     agent_image: str | None = None
     description: str
@@ -26,8 +23,8 @@ class MyUnpublishedAgent(pydantic.BaseModel):
     recommended_schedule_cron: str | None = None
 
 
-class MyUnpublishedAgentsResponse(pydantic.BaseModel):
-    agents: list[MyUnpublishedAgent]
+class MyAgentsResponse(pydantic.BaseModel):
+    agents: list[MyAgent]
     pagination: Pagination
 
 
@@ -43,21 +40,6 @@ class StoreAgent(pydantic.BaseModel):
     rating: float
     agent_graph_id: str
 
-    @classmethod
-    def from_db(cls, agent: "prisma.models.StoreAgent") -> "StoreAgent":
-        return cls(
-            slug=agent.slug,
-            agent_name=agent.agent_name,
-            agent_image=agent.agent_image[0] if agent.agent_image else "",
-            creator=agent.creator_username or "Needs Profile",
-            creator_avatar=agent.creator_avatar or "",
-            sub_heading=agent.sub_heading,
-            description=agent.description,
-            runs=agent.runs,
-            rating=agent.rating,
-            agent_graph_id=agent.graph_id,
-        )
-
 
 class StoreAgentsResponse(pydantic.BaseModel):
     agents: list[StoreAgent]
@@ -80,192 +62,81 @@ class StoreAgentDetails(pydantic.BaseModel):
     runs: int
     rating: float
     versions: list[str]
-    graph_id: str
-    graph_versions: list[str]
+    agentGraphVersions: list[str]
+    agentGraphId: str
     last_updated: datetime.datetime
     recommended_schedule_cron: str | None = None
 
-    active_version_id: str
-    has_approved_version: bool
+    active_version_id: str | None = None
+    has_approved_version: bool = False
 
     # Optional changelog data when include_changelog=True
     changelog: list[ChangelogEntry] | None = None
 
-    @classmethod
-    def from_db(cls, agent: "prisma.models.StoreAgent") -> "StoreAgentDetails":
-        return cls(
-            store_listing_version_id=agent.listing_version_id,
-            slug=agent.slug,
-            agent_name=agent.agent_name,
-            agent_video=agent.agent_video or "",
-            agent_output_demo=agent.agent_output_demo or "",
-            agent_image=agent.agent_image,
-            creator=agent.creator_username or "",
-            creator_avatar=agent.creator_avatar or "",
-            sub_heading=agent.sub_heading,
-            description=agent.description,
-            categories=agent.categories,
-            runs=agent.runs,
-            rating=agent.rating,
-            versions=agent.versions,
-            graph_id=agent.graph_id,
-            graph_versions=agent.graph_versions,
-            last_updated=agent.updated_at,
-            recommended_schedule_cron=agent.recommended_schedule_cron,
-            active_version_id=agent.listing_version_id,
-            has_approved_version=True,  # StoreAgent view only has approved agents
-        )
 
-
-class Profile(pydantic.BaseModel):
-    """Marketplace user profile (only attributes that the user can update)"""
-
-    username: str
+class Creator(pydantic.BaseModel):
     name: str
+    username: str
     description: str
-    avatar_url: str | None
-    links: list[str]
-
-
-class ProfileDetails(Profile):
-    """Marketplace user profile (including read-only fields)"""
-
-    is_featured: bool
-
-    @classmethod
-    def from_db(cls, profile: "prisma.models.Profile") -> "ProfileDetails":
-        return cls(
-            name=profile.name,
-            username=profile.username,
-            avatar_url=profile.avatarUrl,
-            description=profile.description,
-            links=profile.links,
-            is_featured=profile.isFeatured,
-        )
-
-
-class CreatorDetails(ProfileDetails):
-    """Marketplace creator profile details, including aggregated stats"""
-
+    avatar_url: str
     num_agents: int
-    agent_runs: int
     agent_rating: float
-    top_categories: list[str]
-
-    @classmethod
-    def from_db(cls, creator: "prisma.models.Creator") -> "CreatorDetails":  # type: ignore[override]
-        return cls(
-            name=creator.name,
-            username=creator.username,
-            avatar_url=creator.avatar_url,
-            description=creator.description,
-            links=creator.links,
-            is_featured=creator.is_featured,
-            num_agents=creator.num_agents,
-            agent_runs=creator.agent_runs,
-            agent_rating=creator.agent_rating,
-            top_categories=creator.top_categories,
-        )
+    agent_runs: int
+    is_featured: bool
 
 
 class CreatorsResponse(pydantic.BaseModel):
-    creators: List[CreatorDetails]
+    creators: List[Creator]
     pagination: Pagination
 
 
-class StoreSubmission(pydantic.BaseModel):
-    # From StoreListing:
-    listing_id: str
-    user_id: str
-    slug: str
+class CreatorDetails(pydantic.BaseModel):
+    name: str
+    username: str
+    description: str
+    links: list[str]
+    avatar_url: str
+    agent_rating: float
+    agent_runs: int
+    top_categories: list[str]
 
-    # From StoreListingVersion:
-    listing_version_id: str
-    listing_version: int
-    graph_id: str
-    graph_version: int
+
+class Profile(pydantic.BaseModel):
+    name: str
+    username: str
+    description: str
+    links: list[str]
+    avatar_url: str
+    is_featured: bool = False
+
+
+class StoreSubmission(pydantic.BaseModel):
+    listing_id: str
+    agent_id: str
+    agent_version: int
     name: str
     sub_heading: str
+    slug: str
     description: str
-    instructions: str | None
-    categories: list[str]
+    instructions: str | None = None
     image_urls: list[str]
-    video_url: str | None
-    agent_output_demo_url: str | None
-
-    submitted_at: datetime.datetime | None
-    changes_summary: str | None
+    date_submitted: datetime.datetime
     status: prisma.enums.SubmissionStatus
-    reviewed_at: datetime.datetime | None = None
+    runs: int
+    rating: float
+    store_listing_version_id: str | None = None
+    version: int | None = None  # Actual version number from the database
+
     reviewer_id: str | None = None
     review_comments: str | None = None  # External comments visible to creator
+    internal_comments: str | None = None  # Private notes for admin use only
+    reviewed_at: datetime.datetime | None = None
+    changes_summary: str | None = None
 
-    # Aggregated from AgentGraphExecutions and StoreListingReviews:
-    run_count: int = 0
-    review_count: int = 0
-    review_avg_rating: float = 0.0
-
-    @classmethod
-    def from_db(cls, _sub: "prisma.models.StoreSubmission") -> Self:
-        """Construct from the StoreSubmission Prisma view."""
-        return cls(
-            listing_id=_sub.listing_id,
-            user_id=_sub.user_id,
-            slug=_sub.slug,
-            listing_version_id=_sub.listing_version_id,
-            listing_version=_sub.listing_version,
-            graph_id=_sub.graph_id,
-            graph_version=_sub.graph_version,
-            name=_sub.name,
-            sub_heading=_sub.sub_heading,
-            description=_sub.description,
-            instructions=_sub.instructions,
-            categories=_sub.categories,
-            image_urls=_sub.image_urls,
-            video_url=_sub.video_url,
-            agent_output_demo_url=_sub.agent_output_demo_url,
-            submitted_at=_sub.submitted_at,
-            changes_summary=_sub.changes_summary,
-            status=_sub.status,
-            reviewed_at=_sub.reviewed_at,
-            reviewer_id=_sub.reviewer_id,
-            review_comments=_sub.review_comments,
-            run_count=_sub.run_count,
-            review_count=_sub.review_count,
-            review_avg_rating=_sub.review_avg_rating,
-        )
-
-    @classmethod
-    def from_listing_version(cls, _lv: "prisma.models.StoreListingVersion") -> Self:
-        """
-        Construct from the StoreListingVersion Prisma model (with StoreListing included)
-        """
-        if not (_l := _lv.StoreListing):
-            raise ValueError("StoreListingVersion must have included StoreListing")
-
-        return cls(
-            listing_id=_l.id,
-            user_id=_l.owningUserId,
-            slug=_l.slug,
-            listing_version_id=_lv.id,
-            listing_version=_lv.version,
-            graph_id=_lv.agentGraphId,
-            graph_version=_lv.agentGraphVersion,
-            name=_lv.name,
-            sub_heading=_lv.subHeading,
-            description=_lv.description,
-            instructions=_lv.instructions,
-            categories=_lv.categories,
-            image_urls=_lv.imageUrls,
-            video_url=_lv.videoUrl,
-            agent_output_demo_url=_lv.agentOutputDemoUrl,
-            submitted_at=_lv.submittedAt,
-            changes_summary=_lv.changesSummary,
-            status=_lv.submissionStatus,
-            reviewed_at=_lv.reviewedAt,
-            reviewer_id=_lv.reviewerId,
-            review_comments=_lv.reviewComments,
-        )
+    # Additional fields for editing
+    video_url: str | None = None
+    agent_output_demo_url: str | None = None
+    categories: list[str] = []
 
 
 class StoreSubmissionsResponse(pydantic.BaseModel):
@@ -273,12 +144,33 @@ class StoreSubmissionsResponse(pydantic.BaseModel):
     pagination: Pagination
 
 
+class StoreListingWithVersions(pydantic.BaseModel):
+    """A store listing with its version history"""
+
+    listing_id: str
+    slug: str
+    agent_id: str
+    agent_version: int
+    active_version_id: str | None = None
+    has_approved_version: bool = False
+    creator_email: str | None = None
+    latest_version: StoreSubmission | None = None
+    versions: list[StoreSubmission] = []
+
+
+class StoreListingsWithVersionsResponse(pydantic.BaseModel):
+    """Response model for listings with version history"""
+
+    listings: list[StoreListingWithVersions]
+    pagination: Pagination
+
+
 class StoreSubmissionRequest(pydantic.BaseModel):
-    graph_id: str = pydantic.Field(
-        ..., min_length=1, description="Graph ID cannot be empty"
+    agent_id: str = pydantic.Field(
+        ..., min_length=1, description="Agent ID cannot be empty"
     )
-    graph_version: int = pydantic.Field(
-        ..., gt=0, description="Graph version must be greater than 0"
+    agent_version: int = pydantic.Field(
+        ..., gt=0, description="Agent version must be greater than 0"
     )
     slug: str
     name: str
@@ -306,42 +198,12 @@ class StoreSubmissionEditRequest(pydantic.BaseModel):
     recommended_schedule_cron: str | None = None
 
 
-class StoreSubmissionAdminView(StoreSubmission):
-    internal_comments: str | None  # Private admin notes
-
-    @classmethod
-    def from_db(cls, _sub: "prisma.models.StoreSubmission") -> Self:
-        return cls(
-            **StoreSubmission.from_db(_sub).model_dump(),
-            internal_comments=_sub.internal_comments,
-        )
-
-    @classmethod
-    def from_listing_version(cls, _lv: "prisma.models.StoreListingVersion") -> Self:
-        return cls(
-            **StoreSubmission.from_listing_version(_lv).model_dump(),
-            internal_comments=_lv.internalComments,
-        )
-
-
-class StoreListingWithVersionsAdminView(pydantic.BaseModel):
-    """A store listing with its version history"""
-
-    listing_id: str
-    graph_id: str
-    slug: str
-    active_listing_version_id: str | None = None
-    has_approved_version: bool = False
-    creator_email: str | None = None
-    latest_version: StoreSubmissionAdminView | None = None
-    versions: list[StoreSubmissionAdminView] = []
-
-
-class StoreListingsWithVersionsAdminViewResponse(pydantic.BaseModel):
-    """Response model for listings with version history"""
-
-    listings: list[StoreListingWithVersionsAdminView]
-    pagination: Pagination
+class ProfileDetails(pydantic.BaseModel):
+    name: str
+    username: str
+    description: str
+    links: list[str]
+    avatar_url: str | None = None
 
 
 class StoreReview(pydantic.BaseModel):

autogpt_platform/backend/backend/api/features/store/model_test.py

@@ -0,0 +1,203 @@
+import datetime
+
+import prisma.enums
+
+from . import model as store_model
+
+
+def test_pagination():
+    pagination = store_model.Pagination(
+        total_items=100, total_pages=5, current_page=2, page_size=20
+    )
+    assert pagination.total_items == 100
+    assert pagination.total_pages == 5
+    assert pagination.current_page == 2
+    assert pagination.page_size == 20
+
+
+def test_store_agent():
+    agent = store_model.StoreAgent(
+        slug="test-agent",
+        agent_name="Test Agent",
+        agent_image="test.jpg",
+        creator="creator1",
+        creator_avatar="avatar.jpg",
+        sub_heading="Test subheading",
+        description="Test description",
+        runs=50,
+        rating=4.5,
+        agent_graph_id="test-graph-id",
+    )
+    assert agent.slug == "test-agent"
+    assert agent.agent_name == "Test Agent"
+    assert agent.runs == 50
+    assert agent.rating == 4.5
+    assert agent.agent_graph_id == "test-graph-id"
+
+
+def test_store_agents_response():
+    response = store_model.StoreAgentsResponse(
+        agents=[
+            store_model.StoreAgent(
+                slug="test-agent",
+                agent_name="Test Agent",
+                agent_image="test.jpg",
+                creator="creator1",
+                creator_avatar="avatar.jpg",
+                sub_heading="Test subheading",
+                description="Test description",
+                runs=50,
+                rating=4.5,
+                agent_graph_id="test-graph-id",
+            )
+        ],
+        pagination=store_model.Pagination(
+            total_items=1, total_pages=1, current_page=1, page_size=20
+        ),
+    )
+    assert len(response.agents) == 1
+    assert response.pagination.total_items == 1
+
+
+def test_store_agent_details():
+    details = store_model.StoreAgentDetails(
+        store_listing_version_id="version123",
+        slug="test-agent",
+        agent_name="Test Agent",
+        agent_video="video.mp4",
+        agent_output_demo="demo.mp4",
+        agent_image=["image1.jpg", "image2.jpg"],
+        creator="creator1",
+        creator_avatar="avatar.jpg",
+        sub_heading="Test subheading",
+        description="Test description",
+        categories=["cat1", "cat2"],
+        runs=50,
+        rating=4.5,
+        versions=["1.0", "2.0"],
+        agentGraphVersions=["1", "2"],
+        agentGraphId="test-graph-id",
+        last_updated=datetime.datetime.now(),
+    )
+    assert details.slug == "test-agent"
+    assert len(details.agent_image) == 2
+    assert len(details.categories) == 2
+    assert len(details.versions) == 2
+
+
+def test_creator():
+    creator = store_model.Creator(
+        agent_rating=4.8,
+        agent_runs=1000,
+        name="Test Creator",
+        username="creator1",
+        description="Test description",
+        avatar_url="avatar.jpg",
+        num_agents=5,
+        is_featured=False,
+    )
+    assert creator.name == "Test Creator"
+    assert creator.num_agents == 5
+
+
+def test_creators_response():
+    response = store_model.CreatorsResponse(
+        creators=[
+            store_model.Creator(
+                agent_rating=4.8,
+                agent_runs=1000,
+                name="Test Creator",
+                username="creator1",
+                description="Test description",
+                avatar_url="avatar.jpg",
+                num_agents=5,
+                is_featured=False,
+            )
+        ],
+        pagination=store_model.Pagination(
+            total_items=1, total_pages=1, current_page=1, page_size=20
+        ),
+    )
+    assert len(response.creators) == 1
+    assert response.pagination.total_items == 1
+
+
+def test_creator_details():
+    details = store_model.CreatorDetails(
+        name="Test Creator",
+        username="creator1",
+        description="Test description",
+        links=["link1.com", "link2.com"],
+        avatar_url="avatar.jpg",
+        agent_rating=4.8,
+        agent_runs=1000,
+        top_categories=["cat1", "cat2"],
+    )
+    assert details.name == "Test Creator"
+    assert len(details.links) == 2
+    assert details.agent_rating == 4.8
+    assert len(details.top_categories) == 2
+
+
+def test_store_submission():
+    submission = store_model.StoreSubmission(
+        listing_id="listing123",
+        agent_id="agent123",
+        agent_version=1,
+        sub_heading="Test subheading",
+        name="Test Agent",
+        slug="test-agent",
+        description="Test description",
+        image_urls=["image1.jpg", "image2.jpg"],
+        date_submitted=datetime.datetime(2023, 1, 1),
+        status=prisma.enums.SubmissionStatus.PENDING,
+        runs=50,
+        rating=4.5,
+    )
+    assert submission.name == "Test Agent"
+    assert len(submission.image_urls) == 2
+    assert submission.status == prisma.enums.SubmissionStatus.PENDING
+
+
+def test_store_submissions_response():
+    response = store_model.StoreSubmissionsResponse(
+        submissions=[
+            store_model.StoreSubmission(
+                listing_id="listing123",
+                agent_id="agent123",
+                agent_version=1,
+                sub_heading="Test subheading",
+                name="Test Agent",
+                slug="test-agent",
+                description="Test description",
+                image_urls=["image1.jpg"],
+                date_submitted=datetime.datetime(2023, 1, 1),
+                status=prisma.enums.SubmissionStatus.PENDING,
+                runs=50,
+                rating=4.5,
+            )
+        ],
+        pagination=store_model.Pagination(
+            total_items=1, total_pages=1, current_page=1, page_size=20
+        ),
+    )
+    assert len(response.submissions) == 1
+    assert response.pagination.total_items == 1
+
+
+def test_store_submission_request():
+    request = store_model.StoreSubmissionRequest(
+        agent_id="agent123",
+        agent_version=1,
+        slug="test-agent",
+        name="Test Agent",
+        sub_heading="Test subheading",
+        video_url="video.mp4",
+        image_urls=["image1.jpg", "image2.jpg"],
+        description="Test description",
+        categories=["cat1", "cat2"],
+    )
+    assert request.agent_id == "agent123"
+    assert request.agent_version == 1
+    assert len(request.image_urls) == 2
+    assert len(request.categories) == 2

autogpt_platform/backend/backend/api/features/store/routes.py

@@ -1,16 +1,16 @@
 import logging
+import tempfile
+import typing
 import urllib.parse
+from typing import Literal
 
 import autogpt_libs.auth
 import fastapi
 import fastapi.responses
 import prisma.enums
-from fastapi import Query, Security
-from pydantic import BaseModel
 
 import backend.data.graph
 import backend.util.json
-from backend.util.exceptions import NotFoundError
 from backend.util.models import Pagination
 
 from . import cache as store_cache
@@ -34,15 +34,22 @@ router = fastapi.APIRouter()
     "/profile",
     summary="Get user profile",
     tags=["store", "private"],
-    dependencies=[Security(autogpt_libs.auth.requires_user)],
+    dependencies=[fastapi.Security(autogpt_libs.auth.requires_user)],
+    response_model=store_model.ProfileDetails,
 )
 async def get_profile(
-    user_id: str = Security(autogpt_libs.auth.get_user_id),
-) -> store_model.ProfileDetails:
-    """Get the profile details for the authenticated user."""
+    user_id: str = fastapi.Security(autogpt_libs.auth.get_user_id),
+):
+    """
+    Get the profile details for the authenticated user.
+    Cached for 1 hour per user.
+    """
     profile = await store_db.get_user_profile(user_id)
     if profile is None:
-        raise NotFoundError("User does not have a profile yet")
+        return fastapi.responses.JSONResponse(
+            status_code=404,
+            content={"detail": "Profile not found"},
+        )
     return profile
 
 
@@ -50,17 +57,98 @@ async def get_profile(
     "/profile",
     summary="Update user profile",
     tags=["store", "private"],
-    dependencies=[Security(autogpt_libs.auth.requires_user)],
+    dependencies=[fastapi.Security(autogpt_libs.auth.requires_user)],
+    response_model=store_model.CreatorDetails,
 )
 async def update_or_create_profile(
     profile: store_model.Profile,
-    user_id: str = Security(autogpt_libs.auth.get_user_id),
-) -> store_model.ProfileDetails:
-    """Update the store profile for the authenticated user."""
+    user_id: str = fastapi.Security(autogpt_libs.auth.get_user_id),
+):
+    """
+    Update the store profile for the authenticated user.
+
+    Args:
+        profile (Profile): The updated profile details
+        user_id (str): ID of the authenticated user
+
+    Returns:
+        CreatorDetails: The updated profile
+
+    Raises:
+        HTTPException: If there is an error updating the profile
+    """
     updated_profile = await store_db.update_profile(user_id=user_id, profile=profile)
     return updated_profile
 
 
+##############################################
+############### Agent Endpoints ##############
+##############################################
+
+
+@router.get(
+    "/agents",
+    summary="List store agents",
+    tags=["store", "public"],
+    response_model=store_model.StoreAgentsResponse,
+)
+async def get_agents(
+    featured: bool = False,
+    creator: str | None = None,
+    sorted_by: Literal["rating", "runs", "name", "updated_at"] | None = None,
+    search_query: str | None = None,
+    category: str | None = None,
+    page: int = 1,
+    page_size: int = 20,
+):
+    """
+    Get a paginated list of agents from the store with optional filtering and sorting.
+
+    Args:
+        featured (bool, optional): Filter to only show featured agents. Defaults to False.
+        creator (str | None, optional): Filter agents by creator username. Defaults to None.
+        sorted_by (str | None, optional): Sort agents by "runs" or "rating". Defaults to None.
+        search_query (str | None, optional): Search agents by name, subheading and description. Defaults to None.
+        category (str | None, optional): Filter agents by category. Defaults to None.
+        page (int, optional): Page number for pagination. Defaults to 1.
+        page_size (int, optional): Number of agents per page. Defaults to 20.
+
+    Returns:
+        StoreAgentsResponse: Paginated list of agents matching the filters
+
+    Raises:
+        HTTPException: If page or page_size are less than 1
+
+    Used for:
+    - Home Page Featured Agents
+    - Home Page Top Agents
+    - Search Results
+    - Agent Details - Other Agents By Creator
+    - Agent Details - Similar Agents
+    - Creator Details - Agents By Creator
+    """
+    if page < 1:
+        raise fastapi.HTTPException(
+            status_code=422, detail="Page must be greater than 0"
+        )
+
+    if page_size < 1:
+        raise fastapi.HTTPException(
+            status_code=422, detail="Page size must be greater than 0"
+        )
+
+    agents = await store_cache._get_cached_store_agents(
+        featured=featured,
+        creator=creator,
+        sorted_by=sorted_by,
+        search_query=search_query,
+        category=category,
+        page=page,
+        page_size=page_size,
+    )
+    return agents
+
+
 ##############################################
 ############### Search Endpoints #############
 ##############################################
@@ -70,30 +158,60 @@ async def update_or_create_profile(
     "/search",
     summary="Unified search across all content types",
     tags=["store", "public"],
+    response_model=store_model.UnifiedSearchResponse,
 )
 async def unified_search(
     query: str,
-    content_types: list[prisma.enums.ContentType] | None = Query(
+    content_types: list[str] | None = fastapi.Query(
         default=None,
-        description="Content types to search. If not specified, searches all.",
+        description="Content types to search: STORE_AGENT, BLOCK, DOCUMENTATION. If not specified, searches all.",
     ),
-    page: int = Query(ge=1, default=1),
-    page_size: int = Query(ge=1, default=20),
-    user_id: str | None = Security(
+    page: int = 1,
+    page_size: int = 20,
+    user_id: str | None = fastapi.Security(
         autogpt_libs.auth.get_optional_user_id, use_cache=False
     ),
-) -> store_model.UnifiedSearchResponse:
+):
     """
-    Search across all content types (marketplace agents, blocks, documentation)
-    using hybrid search.
+    Search across all content types (store agents, blocks, documentation) using hybrid search.
 
     Combines semantic (embedding-based) and lexical (text-based) search for best results.
+
+    Args:
+        query: The search query string
+        content_types: Optional list of content types to filter by (STORE_AGENT, BLOCK, DOCUMENTATION)
+        page: Page number for pagination (default 1)
+        page_size: Number of results per page (default 20)
+        user_id: Optional authenticated user ID (for user-scoped content in future)
+
+    Returns:
+        UnifiedSearchResponse: Paginated list of search results with relevance scores
     """
+    if page < 1:
+        raise fastapi.HTTPException(
+            status_code=422, detail="Page must be greater than 0"
+        )
+
+    if page_size < 1:
+        raise fastapi.HTTPException(
+            status_code=422, detail="Page size must be greater than 0"
+        )
+
+    # Convert string content types to enum
+    content_type_enums: list[prisma.enums.ContentType] | None = None
+    if content_types:
+        try:
+            content_type_enums = [prisma.enums.ContentType(ct) for ct in content_types]
+        except ValueError as e:
+            raise fastapi.HTTPException(
+                status_code=422,
+                detail=f"Invalid content type. Valid values: STORE_AGENT, BLOCK, DOCUMENTATION. Error: {e}",
+            )
 
     # Perform unified hybrid search
     results, total = await store_hybrid_search.unified_hybrid_search(
         query=query,
-        content_types=content_types,
+        content_types=content_type_enums,
         user_id=user_id,
         page=page,
         page_size=page_size,
@@ -127,69 +245,22 @@ async def unified_search(
     )
 
 
-##############################################
-############### Agent Endpoints ##############
-##############################################
-
-
-@router.get(
-    "/agents",
-    summary="List store agents",
-    tags=["store", "public"],
-)
-async def get_agents(
-    featured: bool = Query(
-        default=False, description="Filter to only show featured agents"
-    ),
-    creator: str | None = Query(
-        default=None, description="Filter agents by creator username"
-    ),
-    category: str | None = Query(default=None, description="Filter agents by category"),
-    search_query: str | None = Query(
-        default=None, description="Literal + semantic search on names and descriptions"
-    ),
-    sorted_by: store_db.StoreAgentsSortOptions | None = Query(
-        default=None,
-        description="Property to sort results by. Ignored if search_query is provided.",
-    ),
-    page: int = Query(ge=1, default=1),
-    page_size: int = Query(ge=1, default=20),
-) -> store_model.StoreAgentsResponse:
-    """
-    Get a paginated list of agents from the marketplace,
-    with optional filtering and sorting.
-
-    Used for:
-    - Home Page Featured Agents
-    - Home Page Top Agents
-    - Search Results
-    - Agent Details - Other Agents By Creator
-    - Agent Details - Similar Agents
-    - Creator Details - Agents By Creator
-    """
-    agents = await store_cache._get_cached_store_agents(
-        featured=featured,
-        creator=creator,
-        sorted_by=sorted_by,
-        search_query=search_query,
-        category=category,
-        page=page,
-        page_size=page_size,
-    )
-    return agents
-
-
 @router.get(
     "/agents/{username}/{agent_name}",
     summary="Get specific agent",
     tags=["store", "public"],
+    response_model=store_model.StoreAgentDetails,
 )
-async def get_agent_by_name(
+async def get_agent(
     username: str,
     agent_name: str,
-    include_changelog: bool = Query(default=False),
-) -> store_model.StoreAgentDetails:
-    """Get details of a marketplace agent"""
+    include_changelog: bool = fastapi.Query(default=False),
+):
+    """
+    This is only used on the AgentDetails Page.
+
+    It returns the store listing agents details.
+    """
     username = urllib.parse.unquote(username).lower()
     # URL decode the agent name since it comes from the URL path
     agent_name = urllib.parse.unquote(agent_name).lower()
@@ -199,79 +270,76 @@ async def get_agent_by_name(
     return agent
 
 
+@router.get(
+    "/graph/{store_listing_version_id}",
+    summary="Get agent graph",
+    tags=["store"],
+    dependencies=[fastapi.Security(autogpt_libs.auth.requires_user)],
+)
+async def get_graph_meta_by_store_listing_version_id(
+    store_listing_version_id: str,
+) -> backend.data.graph.GraphModelWithoutNodes:
+    """
+    Get Agent Graph from Store Listing Version ID.
+    """
+    graph = await store_db.get_available_graph(store_listing_version_id)
+    return graph
+
+
+@router.get(
+    "/agents/{store_listing_version_id}",
+    summary="Get agent by version",
+    tags=["store"],
+    dependencies=[fastapi.Security(autogpt_libs.auth.requires_user)],
+    response_model=store_model.StoreAgentDetails,
+)
+async def get_store_agent(store_listing_version_id: str):
+    """
+    Get Store Agent Details from Store Listing Version ID.
+    """
+    agent = await store_db.get_store_agent_by_version_id(store_listing_version_id)
+
+    return agent
+
+
 @router.post(
     "/agents/{username}/{agent_name}/review",
     summary="Create agent review",
     tags=["store"],
-    dependencies=[Security(autogpt_libs.auth.requires_user)],
+    dependencies=[fastapi.Security(autogpt_libs.auth.requires_user)],
+    response_model=store_model.StoreReview,
 )
-async def post_user_review_for_agent(
+async def create_review(
     username: str,
     agent_name: str,
     review: store_model.StoreReviewCreate,
-    user_id: str = Security(autogpt_libs.auth.get_user_id),
-) -> store_model.StoreReview:
-    """Post a user review on a marketplace agent listing"""
+    user_id: str = fastapi.Security(autogpt_libs.auth.get_user_id),
+):
+    """
+    Create a review for a store agent.
+
+    Args:
+        username: Creator's username
+        agent_name: Name/slug of the agent
+        review: Review details including score and optional comments
+        user_id: ID of authenticated user creating the review
+
+    Returns:
+        The created review
+    """
     username = urllib.parse.unquote(username).lower()
     agent_name = urllib.parse.unquote(agent_name).lower()
-
+    # Create the review
     created_review = await store_db.create_store_review(
         user_id=user_id,
         store_listing_version_id=review.store_listing_version_id,
         score=review.score,
         comments=review.comments,
     )
+
     return created_review
 
 
-@router.get(
-    "/listings/versions/{store_listing_version_id}",
-    summary="Get agent by version",
-    tags=["store"],
-    dependencies=[Security(autogpt_libs.auth.requires_user)],
-)
-async def get_agent_by_listing_version(
-    store_listing_version_id: str,
-) -> store_model.StoreAgentDetails:
-    agent = await store_db.get_store_agent_by_version_id(store_listing_version_id)
-    return agent
-
-
-@router.get(
-    "/listings/versions/{store_listing_version_id}/graph",
-    summary="Get agent graph",
-    tags=["store"],
-    dependencies=[Security(autogpt_libs.auth.requires_user)],
-)
-async def get_graph_meta_by_store_listing_version_id(
-    store_listing_version_id: str,
-) -> backend.data.graph.GraphModelWithoutNodes:
-    """Get outline of graph belonging to a specific marketplace listing version"""
-    graph = await store_db.get_available_graph(store_listing_version_id)
-    return graph
-
-
-@router.get(
-    "/listings/versions/{store_listing_version_id}/graph/download",
-    summary="Download agent file",
-    tags=["store", "public"],
-)
-async def download_agent_file(
-    store_listing_version_id: str,
-) -> fastapi.responses.Response:
-    """Download agent graph file for a specific marketplace listing version"""
-    graph_data = await store_db.get_agent(store_listing_version_id)
-    file_name = f"agent_{graph_data.id}_v{graph_data.version or 'latest'}.json"
-
-    return fastapi.responses.Response(
-        content=backend.util.json.dumps(graph_data),
-        media_type="application/json",
-        headers={
-            "Content-Disposition": f'attachment; filename="{file_name}"',
-        },
-    )
-
-
 ##############################################
 ############# Creator Endpoints #############
 ##############################################
@@ -281,19 +349,37 @@ async def download_agent_file(
     "/creators",
     summary="List store creators",
     tags=["store", "public"],
+    response_model=store_model.CreatorsResponse,
 )
 async def get_creators(
-    featured: bool = Query(
-        default=False, description="Filter to only show featured creators"
-    ),
-    search_query: str | None = Query(
-        default=None, description="Literal + semantic search on names and descriptions"
-    ),
-    sorted_by: store_db.StoreCreatorsSortOptions | None = None,
-    page: int = Query(ge=1, default=1),
-    page_size: int = Query(ge=1, default=20),
-) -> store_model.CreatorsResponse:
-    """List or search marketplace creators"""
+    featured: bool = False,
+    search_query: str | None = None,
+    sorted_by: Literal["agent_rating", "agent_runs", "num_agents"] | None = None,
+    page: int = 1,
+    page_size: int = 20,
+):
+    """
+    This is needed for:
+    - Home Page Featured Creators
+    - Search Results Page
+
+    ---
+
+    To support this functionality we need:
+    - featured: bool - to limit the list to just featured agents
+    - search_query: str - vector search based on the creators profile description.
+    - sorted_by: [agent_rating, agent_runs] -
+    """
+    if page < 1:
+        raise fastapi.HTTPException(
+            status_code=422, detail="Page must be greater than 0"
+        )
+
+    if page_size < 1:
+        raise fastapi.HTTPException(
+            status_code=422, detail="Page size must be greater than 0"
+        )
+
     creators = await store_cache._get_cached_store_creators(
         featured=featured,
         search_query=search_query,
@@ -305,12 +391,18 @@ async def get_creators(
 
 
 @router.get(
-    "/creators/{username}",
+    "/creator/{username}",
     summary="Get creator details",
     tags=["store", "public"],
+    response_model=store_model.CreatorDetails,
 )
-async def get_creator(username: str) -> store_model.CreatorDetails:
-    """Get details on a marketplace creator"""
+async def get_creator(
+    username: str,
+):
+    """
+    Get the details of a creator.
+    - Creator Details Page
+    """
     username = urllib.parse.unquote(username).lower()
     creator = await store_cache._get_cached_creator_details(username=username)
     return creator
@@ -322,17 +414,20 @@ async def get_creator(username: str) -> store_model.CreatorDetails:
 
 
 @router.get(
-    "/my-unpublished-agents",
+    "/myagents",
     summary="Get my agents",
     tags=["store", "private"],
-    dependencies=[Security(autogpt_libs.auth.requires_user)],
+    dependencies=[fastapi.Security(autogpt_libs.auth.requires_user)],
+    response_model=store_model.MyAgentsResponse,
 )
-async def get_my_unpublished_agents(
-    user_id: str = Security(autogpt_libs.auth.get_user_id),
-    page: int = Query(ge=1, default=1),
-    page_size: int = Query(ge=1, default=20),
-) -> store_model.MyUnpublishedAgentsResponse:
-    """List the authenticated user's unpublished agents"""
+async def get_my_agents(
+    user_id: str = fastapi.Security(autogpt_libs.auth.get_user_id),
+    page: typing.Annotated[int, fastapi.Query(ge=1)] = 1,
+    page_size: typing.Annotated[int, fastapi.Query(ge=1)] = 20,
+):
+    """
+    Get user's own agents.
+    """
     agents = await store_db.get_my_agents(user_id, page=page, page_size=page_size)
     return agents
 
@@ -341,17 +436,28 @@ async def get_my_unpublished_agents(
     "/submissions/{submission_id}",
     summary="Delete store submission",
     tags=["store", "private"],
-    dependencies=[Security(autogpt_libs.auth.requires_user)],
+    dependencies=[fastapi.Security(autogpt_libs.auth.requires_user)],
+    response_model=bool,
 )
 async def delete_submission(
     submission_id: str,
-    user_id: str = Security(autogpt_libs.auth.get_user_id),
-) -> bool:
-    """Delete a marketplace listing submission"""
+    user_id: str = fastapi.Security(autogpt_libs.auth.get_user_id),
+):
+    """
+    Delete a store listing submission.
+
+    Args:
+        user_id (str): ID of the authenticated user
+        submission_id (str): ID of the submission to be deleted
+
+    Returns:
+        bool: True if the submission was successfully deleted, False otherwise
+    """
     result = await store_db.delete_store_submission(
         user_id=user_id,
         submission_id=submission_id,
     )
+
     return result
 
 
@@ -359,14 +465,37 @@ async def delete_submission(
     "/submissions",
     summary="List my submissions",
     tags=["store", "private"],
-    dependencies=[Security(autogpt_libs.auth.requires_user)],
+    dependencies=[fastapi.Security(autogpt_libs.auth.requires_user)],
+    response_model=store_model.StoreSubmissionsResponse,
 )
 async def get_submissions(
-    user_id: str = Security(autogpt_libs.auth.get_user_id),
-    page: int = Query(ge=1, default=1),
-    page_size: int = Query(ge=1, default=20),
-) -> store_model.StoreSubmissionsResponse:
-    """List the authenticated user's marketplace listing submissions"""
+    user_id: str = fastapi.Security(autogpt_libs.auth.get_user_id),
+    page: int = 1,
+    page_size: int = 20,
+):
+    """
+    Get a paginated list of store submissions for the authenticated user.
+
+    Args:
+        user_id (str): ID of the authenticated user
+        page (int, optional): Page number for pagination. Defaults to 1.
+        page_size (int, optional): Number of submissions per page. Defaults to 20.
+
+    Returns:
+        StoreListingsResponse: Paginated list of store submissions
+
+    Raises:
+        HTTPException: If page or page_size are less than 1
+    """
+    if page < 1:
+        raise fastapi.HTTPException(
+            status_code=422, detail="Page must be greater than 0"
+        )
+
+    if page_size < 1:
+        raise fastapi.HTTPException(
+            status_code=422, detail="Page size must be greater than 0"
+        )
     listings = await store_db.get_store_submissions(
         user_id=user_id,
         page=page,
@@ -379,17 +508,30 @@ async def get_submissions(
     "/submissions",
     summary="Create store submission",
     tags=["store", "private"],
-    dependencies=[Security(autogpt_libs.auth.requires_user)],
+    dependencies=[fastapi.Security(autogpt_libs.auth.requires_user)],
+    response_model=store_model.StoreSubmission,
 )
 async def create_submission(
     submission_request: store_model.StoreSubmissionRequest,
-    user_id: str = Security(autogpt_libs.auth.get_user_id),
-) -> store_model.StoreSubmission:
-    """Submit a new marketplace listing for review"""
+    user_id: str = fastapi.Security(autogpt_libs.auth.get_user_id),
+):
+    """
+    Create a new store listing submission.
+
+    Args:
+        submission_request (StoreSubmissionRequest): The submission details
+        user_id (str): ID of the authenticated user submitting the listing
+
+    Returns:
+        StoreSubmission: The created store submission
+
+    Raises:
+        HTTPException: If there is an error creating the submission
+    """
     result = await store_db.create_store_submission(
         user_id=user_id,
-        graph_id=submission_request.graph_id,
-        graph_version=submission_request.graph_version,
+        agent_id=submission_request.agent_id,
+        agent_version=submission_request.agent_version,
         slug=submission_request.slug,
         name=submission_request.name,
         video_url=submission_request.video_url,
@@ -402,6 +544,7 @@ async def create_submission(
         changes_summary=submission_request.changes_summary or "Initial Submission",
         recommended_schedule_cron=submission_request.recommended_schedule_cron,
     )
+
     return result
 
 
@@ -409,14 +552,28 @@ async def create_submission(
     "/submissions/{store_listing_version_id}",
     summary="Edit store submission",
     tags=["store", "private"],
-    dependencies=[Security(autogpt_libs.auth.requires_user)],
+    dependencies=[fastapi.Security(autogpt_libs.auth.requires_user)],
+    response_model=store_model.StoreSubmission,
 )
 async def edit_submission(
     store_listing_version_id: str,
     submission_request: store_model.StoreSubmissionEditRequest,
-    user_id: str = Security(autogpt_libs.auth.get_user_id),
-) -> store_model.StoreSubmission:
-    """Update a pending marketplace listing submission"""
+    user_id: str = fastapi.Security(autogpt_libs.auth.get_user_id),
+):
+    """
+    Edit an existing store listing submission.
+
+    Args:
+        store_listing_version_id (str): ID of the store listing version to edit
+        submission_request (StoreSubmissionRequest): The updated submission details
+        user_id (str): ID of the authenticated user editing the listing
+
+    Returns:
+        StoreSubmission: The updated store submission
+
+    Raises:
+        HTTPException: If there is an error editing the submission
+    """
     result = await store_db.edit_store_submission(
         user_id=user_id,
         store_listing_version_id=store_listing_version_id,
@@ -431,6 +588,7 @@ async def edit_submission(
         changes_summary=submission_request.changes_summary,
         recommended_schedule_cron=submission_request.recommended_schedule_cron,
     )
+
     return result
 
 
@@ -438,61 +596,115 @@ async def edit_submission(
     "/submissions/media",
     summary="Upload submission media",
     tags=["store", "private"],
-    dependencies=[Security(autogpt_libs.auth.requires_user)],
+    dependencies=[fastapi.Security(autogpt_libs.auth.requires_user)],
 )
 async def upload_submission_media(
     file: fastapi.UploadFile,
-    user_id: str = Security(autogpt_libs.auth.get_user_id),
-) -> str:
-    """Upload media for a marketplace listing submission"""
+    user_id: str = fastapi.Security(autogpt_libs.auth.get_user_id),
+):
+    """
+    Upload media (images/videos) for a store listing submission.
+
+    Args:
+        file (UploadFile): The media file to upload
+        user_id (str): ID of the authenticated user uploading the media
+
+    Returns:
+        str: URL of the uploaded media file
+
+    Raises:
+        HTTPException: If there is an error uploading the media
+    """
     media_url = await store_media.upload_media(user_id=user_id, file=file)
     return media_url
 
 
-class ImageURLResponse(BaseModel):
-    image_url: str
-
-
 @router.post(
     "/submissions/generate_image",
     summary="Generate submission image",
     tags=["store", "private"],
-    dependencies=[Security(autogpt_libs.auth.requires_user)],
+    dependencies=[fastapi.Security(autogpt_libs.auth.requires_user)],
 )
 async def generate_image(
-    graph_id: str,
-    user_id: str = Security(autogpt_libs.auth.get_user_id),
-) -> ImageURLResponse:
+    agent_id: str,
+    user_id: str = fastapi.Security(autogpt_libs.auth.get_user_id),
+) -> fastapi.responses.Response:
     """
-    Generate an image for a marketplace listing submission based on the properties
-    of a given graph.
+    Generate an image for a store listing submission.
+
+    Args:
+        agent_id (str): ID of the agent to generate an image for
+        user_id (str): ID of the authenticated user
+
+    Returns:
+        JSONResponse: JSON containing the URL of the generated image
     """
-    graph = await backend.data.graph.get_graph(
-        graph_id=graph_id, version=None, user_id=user_id
+    agent = await backend.data.graph.get_graph(
+        graph_id=agent_id, version=None, user_id=user_id
     )
 
-    if not graph:
-        raise NotFoundError(f"Agent graph #{graph_id} not found")
+    if not agent:
+        raise fastapi.HTTPException(
+            status_code=404, detail=f"Agent with ID {agent_id} not found"
+        )
     # Use .jpeg here since we are generating JPEG images
-    filename = f"agent_{graph_id}.jpeg"
+    filename = f"agent_{agent_id}.jpeg"
 
     existing_url = await store_media.check_media_exists(user_id, filename)
     if existing_url:
-        logger.info(f"Using existing image for agent graph {graph_id}")
-        return ImageURLResponse(image_url=existing_url)
+        logger.info(f"Using existing image for agent {agent_id}")
+        return fastapi.responses.JSONResponse(content={"image_url": existing_url})
     # Generate agent image as JPEG
-    image = await store_image_gen.generate_agent_image(agent=graph)
+    image = await store_image_gen.generate_agent_image(agent=agent)
 
     # Create UploadFile with the correct filename and content_type
     image_file = fastapi.UploadFile(
         file=image,
         filename=filename,
     )
+
     image_url = await store_media.upload_media(
         user_id=user_id, file=image_file, use_file_name=True
     )
 
-    return ImageURLResponse(image_url=image_url)
+    return fastapi.responses.JSONResponse(content={"image_url": image_url})
+
+
+@router.get(
+    "/download/agents/{store_listing_version_id}",
+    summary="Download agent file",
+    tags=["store", "public"],
+)
+async def download_agent_file(
+    store_listing_version_id: str = fastapi.Path(
+        ..., description="The ID of the agent to download"
+    ),
+) -> fastapi.responses.FileResponse:
+    """
+    Download the agent file by streaming its content.
+
+    Args:
+        store_listing_version_id (str): The ID of the agent to download
+
+    Returns:
+        StreamingResponse: A streaming response containing the agent's graph data.
+
+    Raises:
+        HTTPException: If the agent is not found or an unexpected error occurs.
+    """
+    graph_data = await store_db.get_agent(store_listing_version_id)
+    file_name = f"agent_{graph_data.id}_v{graph_data.version or 'latest'}.json"
+
+    # Sending graph as a stream (similar to marketplace v1)
+    with tempfile.NamedTemporaryFile(
+        mode="w", suffix=".json", delete=False
+    ) as tmp_file:
+        tmp_file.write(backend.util.json.dumps(graph_data))
+        tmp_file.flush()
+
+        return fastapi.responses.FileResponse(
+            tmp_file.name, filename=file_name, media_type="application/json"
+        )
 
 
 ##############################################

autogpt_platform/backend/backend/api/features/store/routes_test.py

@@ -8,8 +8,6 @@ import pytest
 import pytest_mock
 from pytest_snapshot.plugin import Snapshot
 
-from backend.api.features.store.db import StoreAgentsSortOptions
-
 from . import model as store_model
 from . import routes as store_routes
 
@@ -198,7 +196,7 @@ def test_get_agents_sorted(
     mock_db_call.assert_called_once_with(
         featured=False,
         creators=None,
-        sorted_by=StoreAgentsSortOptions.RUNS,
+        sorted_by="runs",
         search_query=None,
         category=None,
         page=1,
@@ -382,11 +380,9 @@ def test_get_agent_details(
         runs=100,
         rating=4.5,
         versions=["1.0.0", "1.1.0"],
-        graph_versions=["1", "2"],
-        graph_id="test-graph-id",
+        agentGraphVersions=["1", "2"],
+        agentGraphId="test-graph-id",
         last_updated=FIXED_NOW,
-        active_version_id="test-version-id",
-        has_approved_version=True,
     )
     mock_db_call = mocker.patch("backend.api.features.store.db.get_store_agent_details")
     mock_db_call.return_value = mocked_value
@@ -439,17 +435,15 @@ def test_get_creators_pagination(
 ) -> None:
     mocked_value = store_model.CreatorsResponse(
         creators=[
-            store_model.CreatorDetails(
+            store_model.Creator(
                 name=f"Creator {i}",
                 username=f"creator{i}",
-                avatar_url=f"avatar{i}.jpg",
                 description=f"Creator {i} description",
-                links=[f"user{i}.link.com"],
-                is_featured=False,
+                avatar_url=f"avatar{i}.jpg",
                 num_agents=1,
-                agent_runs=100,
                 agent_rating=4.5,
-                top_categories=["cat1", "cat2", "cat3"],
+                agent_runs=100,
+                is_featured=False,
             )
             for i in range(5)
         ],
@@ -502,19 +496,19 @@ def test_get_creator_details(
     mocked_value = store_model.CreatorDetails(
         name="Test User",
         username="creator1",
-        avatar_url="avatar.jpg",
         description="Test creator description",
         links=["link1.com", "link2.com"],
-        is_featured=True,
-        num_agents=5,
-        agent_runs=1000,
+        avatar_url="avatar.jpg",
         agent_rating=4.8,
+        agent_runs=1000,
         top_categories=["category1", "category2"],
     )
-    mock_db_call = mocker.patch("backend.api.features.store.db.get_store_creator")
+    mock_db_call = mocker.patch(
+        "backend.api.features.store.db.get_store_creator_details"
+    )
     mock_db_call.return_value = mocked_value
 
-    response = client.get("/creators/creator1")
+    response = client.get("/creator/creator1")
     assert response.status_code == 200
 
     data = store_model.CreatorDetails.model_validate(response.json())
@@ -534,26 +528,19 @@ def test_get_submissions_success(
         submissions=[
             store_model.StoreSubmission(
                 listing_id="test-listing-id",
-                user_id="test-user-id",
-                slug="test-agent",
-                listing_version_id="test-version-id",
-                listing_version=1,
-                graph_id="test-agent-id",
-                graph_version=1,
                 name="Test Agent",
-                sub_heading="Test agent subheading",
                 description="Test agent description",
-                instructions="Click the button!",
-                categories=["test-category"],
                 image_urls=["test.jpg"],
-                video_url="test.mp4",
-                agent_output_demo_url="demo_video.mp4",
-                submitted_at=FIXED_NOW,
-                changes_summary="Initial Submission",
+                date_submitted=FIXED_NOW,
                 status=prisma.enums.SubmissionStatus.APPROVED,
-                run_count=50,
-                review_count=5,
-                review_avg_rating=4.2,
+                runs=50,
+                rating=4.2,
+                agent_id="test-agent-id",
+                agent_version=1,
+                sub_heading="Test agent subheading",
+                slug="test-agent",
+                video_url="test.mp4",
+                categories=["test-category"],
             )
         ],
         pagination=store_model.Pagination(

autogpt_platform/backend/backend/api/features/store/test_cache_delete.py

@@ -11,7 +11,6 @@ import pytest
 from backend.util.models import Pagination
 
 from . import cache as store_cache
-from .db import StoreAgentsSortOptions
 from .model import StoreAgent, StoreAgentsResponse
 
 
@@ -216,7 +215,7 @@ class TestCacheDeletion:
             await store_cache._get_cached_store_agents(
                 featured=True,
                 creator="testuser",
-                sorted_by=StoreAgentsSortOptions.RATING,
+                sorted_by="rating",
                 search_query="AI assistant",
                 category="productivity",
                 page=2,
@@ -228,7 +227,7 @@ class TestCacheDeletion:
             deleted = store_cache._get_cached_store_agents.cache_delete(
                 featured=True,
                 creator="testuser",
-                sorted_by=StoreAgentsSortOptions.RATING,
+                sorted_by="rating",
                 search_query="AI assistant",
                 category="productivity",
                 page=2,
@@ -240,7 +239,7 @@ class TestCacheDeletion:
             deleted = store_cache._get_cached_store_agents.cache_delete(
                 featured=True,
                 creator="testuser",
-                sorted_by=StoreAgentsSortOptions.RATING,
+                sorted_by="rating",
                 search_query="AI assistant",
                 category="productivity",
                 page=2,