The strategy was stuck in a loop because it tracked plan steps but never
advanced them - the record_step_success() method existed but was never
called by the agent's execution loop.
Fix by using a _pending_step_advance flag to track when an action has
been proposed. On the next parse_response_content() call, advance the
previous step before processing the new response. This keeps step
tracking self-contained in the strategy without requiring agent changes.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implement four new prompt strategies based on research papers:
- ReWOO: Reasoning Without Observation (5x token efficiency)
- Plan-and-Execute: Separate planning from execution phases
- Reflexion: Verbal reinforcement learning with episodic memory
- Tree of Thoughts: Deliberate problem solving with tree search
Each strategy extends a new BaseMultiStepPromptStrategy base class
with shared utilities. Strategies are selectable via PROMPT_STRATEGY
environment variable or config.prompt_strategy setting.
Fix JSONSchema generation issue where Optional/Union types created
anyOf schemas without direct type field - resolved by storing
plan/phase state in strategy instances rather than ActionProposal.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Remove openai_functions config option - native tool calling is now always enabled
- Remove use_functions_api from BaseAgentConfiguration and prompt strategy
- Add use_prefill config to disable prefill for Anthropic (prefill + tools incompatible)
- Update anthropic dependency to ^0.45.0 for tools API support
- Simplify prompt strategy to always expect tool_calls from LLM response
This fixes the N/A command loop bug where models would output "N/A" as a
command name when function calling was disabled. With native tool calling
always enabled, models are forced to pick from valid tools only.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Update gitignore to use glob pattern for settings.local.json files
in any .claude directory. Also untrack the existing file.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Remove asctime from log formats since terminal output already has
timestamps from the logging infrastructure. Makes logs cleaner
and easier to read.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Environment loading:
- Search for .env in multiple locations (cwd, ~/.autogpt, ~/.config/autogpt)
- Allows running autogpt from any directory
- Document search order in .env.template
Setup simplification:
- Remove interactive AI settings revision (was broken/unused)
- Simplify to just printing current settings
- Clean up unused imports
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add specialized exception classes for better error reporting:
- CodeTimeoutError: For code execution timeouts
- HTTPError: For HTTP request failures with status code/URL
- DataProcessingError: For JSON/CSV processing errors
Each exception includes helpful hints for users.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add a task management component modeled after Claude Code's TodoWrite:
- TodoItem with recursive sub_items for hierarchical task structure
- todo_write: atomic list replacement with sub-items support
- todo_read: retrieve current todos with nested structure
- todo_clear: clear all todos
- todo_decompose: use smart LLM to break down tasks into sub-steps
Features:
- Hierarchical task tracking with independent status per sub-item
- MessageProvider shows todos in LLM context with proper indentation
- DirectiveProvider adds best practices for task management
- Graceful fallback when LLM provider not configured
Integrates with:
- original_autogpt Agent (full LLM decomposition support)
- ForgeAgent (basic task tracking, no decomposition)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Remove references to deleted files (./run, cli.py, setup.py, frontend/)
from CI workflows. Replace ./run agent start with direct poetry commands
to start agent servers in background.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The .autogpt/ directory is where AutoGPT stores agent data when running
from any directory. This should not be committed to version control.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add --workspace option to CLI that defaults to current working directory,
allowing users to run `autogpt` from any folder. Agent data is now stored
in `.autogpt/` subdirectory of the workspace instead of a hardcoded path.
Changes:
- Add -w/--workspace CLI option to run and serve commands
- Remove dependency on forge package location for PROJECT_ROOT
- Update config to use workspace instead of project_root
- Store agent data in .autogpt/ within workspace directory
- Update pyproject.toml files with proper PyPI metadata
- Fix outdated tests to match current implementation
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add Claude 3.5 v2, Claude 4 Sonnet, Claude 4 Opus, and Claude 4.5 Opus models
- Add rolling aliases (CLAUDE_SONNET, CLAUDE_OPUS, CLAUDE_HAIKU)
- Fix deprecated beta.tools.messages.create API call to use standard messages.create
- Update anthropic SDK from ^0.25.1 to >=0.40,<1.0
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
## Summary
This PR adds proper execution end time tracking and fixes timestamp
handling throughout the execution analytics system.
### Key Changes
1. **Added `endedAt` field to database schema** - Executions now have a
dedicated field for tracking when they finish
2. **Fixed timestamp nullable handling** - `started_at` and `ended_at`
are now properly nullable in types
3. **Fixed chart aggregation** - Reduced threshold from ≥3 to ≥1
executions per day
4. **Improved timestamp display** - Moved timestamps to expandable
details section in analytics table
5. **Fixed nullable timestamp bugs** - Updated all frontend code to
handle null timestamps correctly
## Problem Statement
### Issue 1: Missing Execution End Times
Previously, executions used `updatedAt` (last DB update) as a proxy for
"end time". This broke when adding correctness scores retroactively -
the end time would change to whenever the score was added, not when the
execution actually finished.
### Issue 2: Chart Shows Only One Data Point
The accuracy trends chart showed only one data point despite having
executions across multiple days. Root cause: aggregation required ≥3
executions per day.
### Issue 3: Incorrect Type Definitions
Manually maintained types defined `started_at` and `ended_at` as
non-nullable `Date`, contradicting reality where QUEUED executions
haven't started yet.
## Solution
### Database Schema (`schema.prisma`)
```prisma
model AgentGraphExecution {
// ...
startedAt DateTime?
endedAt DateTime? // NEW FIELD
// ...
}
```
### Execution Lifecycle
- **QUEUED**: `startedAt = null`, `endedAt = null` (not started)
- **RUNNING**: `startedAt = set`, `endedAt = null` (in progress)
- **COMPLETED/FAILED/TERMINATED**: `startedAt = set`, `endedAt = set`
(finished)
### Migration Strategy
```sql
-- Add endedAt column
ALTER TABLE "AgentGraphExecution" ADD COLUMN "endedAt" TIMESTAMP(3);
-- Backfill ONLY terminal executions (prevents marking RUNNING executions as ended)
UPDATE "AgentGraphExecution"
SET "endedAt" = "updatedAt"
WHERE "endedAt" IS NULL
AND "executionStatus" IN ('COMPLETED', 'FAILED', 'TERMINATED');
```
## Changes by Component
### Backend
**`schema.prisma`**
- Added `endedAt` field to `AgentGraphExecution`
**`execution.py`**
- Made `started_at` and `ended_at` optional with Field descriptions
- Updated `from_db()` to use `endedAt` instead of `updatedAt`
- `update_graph_execution_stats()` sets `endedAt` when status becomes
terminal
**`execution_analytics_routes.py`**
- Removed `created_at`/`updated_at` from `ExecutionAnalyticsResult` (DB
metadata, not execution data)
- Kept only `started_at`/`ended_at` (actual execution runtime)
- Made settings global (avoid recreation)
- Moved OpenAI key validation to `_process_batch` (only check when LLM
actually runs)
**`analytics.py`**
- Fixed aggregation: `COUNT(*) >= 1` (was 3) - include all days with ≥1
execution
- Uses `createdAt` for chart grouping (when execution was queued)
**`late_execution_monitor.py`**
- Handle optional `started_at` with fallback to `datetime.min` for
sorting
- Display "Not started" when `started_at` is null
### Frontend
**Type Definitions**
- Fixed manually maintained `types.ts`: `started_at: Date | null` (was
non-nullable)
- Generated types were already correct
**Analytics Components**
- `AnalyticsResultsTable.tsx`: Show only `started_at`/`ended_at` in
2-column expandable grid
- `ExecutionAnalyticsForm.tsx`: Added filter explanation UI
**Monitoring Components** - Fixed null handling bugs:
- `OldAgentLibraryView.tsx`: Handle null in reduce function
- `agent-runs-selector-list.tsx`: Safe sorting with `?.getTime() ?? 0`
- `AgentFlowList.tsx`: Filter/sort with null checks
- `FlowRunsStatus.tsx`: Filter null timestamps
- `FlowRunsTimeline.tsx`: Filter executions with null timestamps before
rendering
- `monitoring/page.tsx`: Safe sorting
- `ActivityItem.tsx`: Fallback to "recently" for null timestamps
## Benefits
✅ **Accurate End Times**: `endedAt` is frozen when execution finishes,
not updated later
✅ **Type Safety**: Nullable types match reality, exposing real bugs
✅ **Better UX**: Chart shows all days with data (not just days with ≥3
executions)
✅ **Bug Fixes**: 7+ frontend components now handle null timestamps
correctly
✅ **Documentation**: Field descriptions explain when timestamps are null
## Testing
### Backend
```bash
cd autogpt_platform/backend
poetry run format # ✅ All checks passed
poetry run lint # ✅ All checks passed
```
### Frontend
```bash
cd autogpt_platform/frontend
pnpm format # ✅ All checks passed
pnpm lint # ✅ All checks passed
pnpm types # ✅ All type errors fixed
```
### Test Data Generation
Created script to generate 35 test executions across 7 days with
correctness scores:
```bash
poetry run python scripts/generate_test_analytics_data.py
```
## Migration Notes
⚠️ **Important**: The migration only backfills `endedAt` for executions
with terminal status (COMPLETED, FAILED, TERMINATED). Active executions
(QUEUED, RUNNING) correctly keep `endedAt = null`.
## Breaking Changes
None - this is backward compatible:
- `endedAt` is nullable, existing code that doesn't use it is unaffected
- Frontend already used generated types which were correct
- Migration safely backfills historical data
<!-- CURSOR_SUMMARY -->
---
> [!NOTE]
> Introduces explicit execution end-time tracking and normalizes
timestamp handling across backend and frontend.
>
> - Adds `endedAt` to `AgentGraphExecution` (schema + migration);
backfills terminal executions; sets `endedAt` on terminal status updates
> - Makes `GraphExecutionMeta.started_at/ended_at` optional; updates
`from_db()` to use DB `endedAt`; exposes timestamps in
`ExecutionAnalyticsResult`
> - Moves OpenAI key validation into batch processing; instantiates
`Settings` once
> - Accuracy trends: reduce daily aggregation threshold to `>= 1`;
optional historical series
> - Monitoring/analytics UI: results table shows/export
`started_at`/`ended_at`; adds chart filter explainer
> - Frontend null-safety: update types (`Date | null`) and fix
sorting/filtering/rendering for nullable timestamps across monitoring
and library views
> - Late execution monitor: safe sorting/display when `started_at` is
null
> - OpenAPI specs updated for new/nullable fields
>
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
1d987ca6e5. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
---------
Co-authored-by: Nicholas Tindle <nicholas.tindle@agpt.co>
### Changes 🏗️
**Fixed missing default credentials and provider name mismatch in the
credentials store:**
1. **Provider name correction** (`credentials_store.py:97-103`)
- Changed `provider="unreal"` → `provider="unreal_speech"` to match the
existing `unreal_speech_api_key` setting and block usage
- Updated title from "Use Credits for Unreal" → "Use Credits for Unreal
Speech" for clarity
2. **Added missing OpenWeatherMap credentials**
(`credentials_store.py:219-226`)
- New `openweathermap_credentials` definition with `APIKeyCredentials`
- Uses existing `settings.secrets.openweathermap_api_key` setting that
was previously defined but had no credential object
- Added to `DEFAULT_CREDENTIALS` list
3. **Fixed credentials not exposed in `get_all_creds()`**
(`credentials_store.py:343-354`)
- Added `llama_api_credentials` conditional append (was defined but not
returned to users)
- Added `v0_credentials` conditional append (was defined but not
returned to users)
- Added `openweathermap_credentials` conditional append
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Verified provider name `unreal_speech` matches block usage in
`text_to_speech_block.py`
- [x] Confirmed `openweathermap_api_key` setting exists in secrets
- [x] Confirmed `llama_api_key` and `v0_api_key` settings exist in
secrets
<!-- CURSOR_SUMMARY -->
---
> [!NOTE]
> Aligns backend credential definitions and exposes missing system
creds; updates frontend to hide new built-ins.
>
> - Backend `credentials_store.py`:
> - Corrects `provider` to `unreal_speech` and updates title
> - Adds `openweathermap_credentials`; includes in `DEFAULT_CREDENTIALS`
and `get_all_creds()` when key present
> - Ensures `llama_api_credentials` and `v0_credentials` are returned by
`get_all_creds()`
> - Frontend `integrations/page.tsx`:
> - Extends `hiddenCredentials` with IDs for `v0`, `webshare_proxy`, and
`openweathermap`
>
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
e7d46b76c6. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: Nicholas Tindle <ntindle@users.noreply.github.com>
This PR fixes flaky agent-activity Playwright tests that were failing
intermittently in CI.
Closes#11789
### Changes 🏗️
- **Navigate to specific agent by name**: Replace
`LibraryPage.clickFirstAgent(page)` with
`LibraryPage.navigateToAgentByName(page, "Test Agent")` to ensure we're
testing the correct agent rather than relying on the first agent in the
list
- **Add retry mechanism for async data loading**: Replace direct
visibility check with `expect(...).toPass({ timeout: 15000 })` pattern
to properly handle asynchronous agent data fetching
- **Increase timeout**: Extended timeout from 8000ms to 15000ms to
accommodate slower CI environments
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Verified the test file syntax is correct
- [x] Changes target the correct file
(`autogpt_platform/frontend/src/tests/agent-activity.spec.ts`)
- [x] The retry mechanism follows Playwright best practices using
`toPass()`
#### For configuration changes:
- [x] `.env.default` is updated or already compatible with my changes
(N/A - no config changes)
- [x] `docker-compose.yml` is updated or already compatible with my
changes (N/A - no config changes)
- [x] I have included a list of my configuration changes in the PR
description (under **Changes**) (N/A - no config changes)
---------
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: Nicholas Tindle <ntindle@users.noreply.github.com>
This PR adds the ability to create and edit agents from natural language
descriptions in the chat copilot.
### Changes 🏗️
- Added `agent_generator/` module with:
- LLM client for OpenAI API calls
- Core generation logic for decomposing goals and generating agent JSON
- Fixer module to correct common LLM generation errors
- Validator to ensure generated agents are structurally valid
- Prompts for goal decomposition and agent generation
- Utility functions for blocks info and agent saving
- Added `CreateAgentTool` - creates new agents from natural language
descriptions
- Added `EditAgentTool` - edits existing agents using natural language
patches
- Added response models: `AgentPreviewResponse`, `AgentSavedResponse`,
`ClarificationNeededResponse`
- Registered new tools in the tools registry
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Run `poetry run format` to ensure code passes linting
- [x] Test creating an agent via chat with a natural language
description
- [x] Test editing an existing agent via chat
This PR adds new chat tools for searching blocks and documentation,
along with BM25 reranking for improved search relevance.
### Changes 🏗️
**New Chat Tools:**
- `find_block` - Search for available blocks by name/description using
hybrid search
- `run_block` - Execute a block directly with provided inputs and
credentials
- `search_docs` - Search documentation with section-level granularity
- `get_doc_page` - Retrieve full documentation page content
**Search Improvements:**
- Added BM25 reranking to hybrid search for better lexical relevance
- Documentation handler now chunks markdown by headings (##) for
finer-grained embeddings
- Section-based content IDs (`doc_path::section_index`) for precise doc
retrieval
- Startup embedding backfill in scheduler for immediate searchability
**Other Changes:**
- New response models for block and documentation search results
- Updated orphan cleanup to handle section-based doc embeddings
- Added `rank-bm25` dependency for BM25 scoring
- Removed max message limit check in chat service
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Run find_block tool to search for blocks (e.g., "current time")
- [x] Run run_block tool to execute a found block
- [x] Run search_docs tool to search documentation
- [x] Run get_doc_page tool to retrieve full doc content
- [x] Verify BM25 reranking improves search relevance for exact term
matches
- [x] Verify documentation sections are properly chunked and embedded
#### For configuration changes:
- [x] `.env.default` is updated or already compatible with my changes
- [x] `docker-compose.yml` is updated or already compatible with my
changes
- [x] I have included a list of my configuration changes in the PR
description (under **Changes**)
**Dependencies added:** `rank-bm25` for BM25 scoring algorithm
Frontend changes extracted from the hackathon/copilot branch for the
copilot feature development.
### Changes 🏗️
- New Chat system with contextual components (`Chat`, `ChatDrawer`,
`ChatContainer`, `ChatMessage`, etc.)
- Form renderer system with RJSF v6 integration and new input renderers
- Enhanced credentials management with improved OAuth flow and
credential selection
- New output renderers for various content types (Code, Image, JSON,
Markdown, Text, Video)
- Scrollable tabs component for better UI organization
- Marketplace update notifications and publishing workflow improvements
- Draft recovery feature with IndexedDB persistence
- Safe mode toggle functionality
- Various UI/UX improvements across the platform
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [ ] Test new Chat components functionality
- [ ] Verify form renderer with various input types
- [ ] Test credential management flows
- [ ] Verify output renderers display correctly
- [ ] Test draft recovery feature
#### For configuration changes:
- [x] `.env.default` is updated or already compatible with my changes
- [x] `docker-compose.yml` is updated or already compatible with my
changes
- [x] I have included a list of my configuration changes in the PR
description (under **Changes**)
---------
Co-authored-by: Lluis Agusti <hi@llu.lu>
## Summary
- Makes Redis connection lazy in the cache module - connection is only
established when `shared_cache=True` is actually used
- Fixes DatabaseManager failing to start because it imports
`onboarding.py` which imports `cache.py`, triggering Redis connection at
module load time even though it only uses in-memory caching
## Root Cause
Commit `b01ea3fcb` (merged today) added `increment_onboarding_runs` to
DatabaseManager, which imports from `onboarding.py`. That module imports
`@cached` decorator from `cache.py`, which was creating a Redis
connection at module import time:
```python
# Old code - ran at import time!
redis = Redis(connection_pool=_get_cache_pool())
```
Since `onboarding.py` only uses `@cached(shared_cache=False)` (in-memory
caching), it doesn't actually need Redis. But the import triggered the
connection attempt.
## Changes
- Wrapped Redis connection in a singleton class with lazy initialization
- Connection is only established when `_get_redis()` is first called
(i.e., when `shared_cache=True` is used)
- Services using only in-memory caching can now import `cache.py`
without Redis configuration
## Test plan
- [ ] Services using `shared_cache=False` work without Redis configured
- [ ] Services using `shared_cache=True` still work correctly with Redis
- [ ] Existing cache tests pass
🤖 Generated with [Claude Code](https://claude.com/claude-code)
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
### Changes 🏗️
- **Improved Error Handling**: Enhanced error handling in
`useRunInputDialog.ts` to properly handle cases where node errors are
empty or undefined
- **Fixed Node Collision Resolution**: Updated `Flow.tsx` to use the
current state from the store instead of stale props
- **Enhanced History Management**:
- Added proper state tracking for edge removal operations
- Improved undo/redo functionality to prevent duplicate states
- Fixed edge case where history wasn't properly tracked during node
dragging
- **UI Improvements**:
- Fixed potential null reference in NodeHeader when accessing agent_name
- Added placeholder for GoogleDrivePicker in INPUT mode
- Fixed spacing in ArrayFieldTemplate
- **Bug Fixes**:
- Added proper state tracking before modifying nodes/edges
- Fixed history tracking to avoid redundant states
- Improved collision detection and resolution
### Checklist ���
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Test undo/redo functionality after adding, removing, and moving
nodes
- [x] Test edge creation and deletion with history tracking
- [x] Verify error handling when graph validation fails
- [x] Test Google Drive picker in different UI modes
- [x] Verify node collision resolution works correctly
### Changes 🏗️
- Added a placeholder UI for Google Drive Picker in INPUT block type
- Improved detection of Google Drive file objects in schema validation
- Extracted `isGoogleDrivePickerSchema` function for better code
organization
- Added spacing between array field elements with a gap-2 class
- Added debug logging for preprocessed schema in FormRenderer
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Verified Google Drive Picker shows placeholder in INPUT blocks
- [x] Confirmed array field elements have proper spacing
- [x] Tested that Google Drive file objects are properly detected
### Changes 🏗️
- Enhanced error handling for graph validation failures with detailed
user feedback
- Added automatic viewport navigation to the first node with errors when
validation fails
- Improved node title display to prioritize agent_name from hardcoded
values
- Removed console.log debugging statement from OutputHandler
- Added ApiError import and improved error type handling
- Reorganized imports for better code organization
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Create a graph with intentional validation errors and verify error
messages display correctly
- [x] Verify the viewport automatically navigates to the first node with
errors
- [x] Check that node titles correctly display customized names or agent
names
- [x] Test error recovery by fixing validation errors and successfully
running the graph
### Changes 🏗️
Added support for Note blocks in the FieldTemplate component by:
- Importing the BlockUIType enum from the build components types
- Extracting the uiType from the registry.formContext
- Adding a conditional rendering check that returns children directly
when the uiType is BlockUIType.NOTE
This change allows Note blocks to render without the standard field
template wrapper, providing a cleaner display for note-type content.
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Created a Note block and verified it renders correctly without
field template wrapper
- [x] Confirmed other block types still render with proper field
template
- [x] Verified that Note blocks maintain proper functionality in the
node graph
## Summary
This PR extends the embedding system to support **blocks** and
**documentation** content types in addition to store agents, and
introduces **unified hybrid search** across all content types using a
single `UnifiedContentEmbedding` table.
### Key Changes
1. **Unified Hybrid Search Architecture**
- Added `search` tsvector column to `UnifiedContentEmbedding` table
- New `unified_hybrid_search()` function searches across all content
types (agents, blocks, docs)
- Updated `hybrid_search()` for store agents to use
`UnifiedContentEmbedding.search`
- Removed deprecated `search` column from `StoreListingVersion` table
2. **Pluggable Content Handler Architecture**
- Created abstract `ContentHandler` base class for extensibility
- Implemented handlers: `StoreAgentHandler`, `BlockHandler`,
`DocumentationHandler`
- Registry pattern for easy addition of new content types
3. **Block Embeddings**
- Discovers all blocks using `get_blocks()`
- Extracts searchable text from: name, description, categories,
input/output schemas
4. **Documentation Embeddings**
- Scans `/docs/` directory for `.md` and `.mdx` files
- Extracts title from first `#` heading or uses filename as fallback
5. **Hybrid Search Graceful Degradation**
- Falls back to lexical-only search if query embedding generation fails
- Redistributes semantic weight proportionally to other components
- Logs warning instead of throwing error
6. **Database Migrations**
- `20260115200000_add_unified_search_tsvector`: Adds search column to
UnifiedContentEmbedding with auto-update trigger
- `20260115210000_remove_storelistingversion_search`: Removes deprecated
search column and updates StoreAgent view
7. **Orphan Cleanup**
- `cleanup_orphaned_embeddings()` removes embeddings for deleted content
- Always runs after backfill, even at 100% coverage
### Review Comments Addressed
- ✅ SQL parameter index bug when user_id provided (embeddings.py)
- ✅ Early return skipping cleanup at 100% coverage (scheduler.py)
- ✅ Inconsistent return structure across code paths (scheduler.py)
- ✅ SQL UNION syntax error - added parentheses for ORDER BY/LIMIT
(hybrid_search.py)
- ✅ Version numeric ordering in aggregations (migration)
- ✅ Embedding dimension uses EMBEDDING_DIM constant
### Files Changed
- `backend/api/features/store/content_handlers.py` (NEW): Handler
architecture
- `backend/api/features/store/embeddings.py`: Refactored to use handlers
- `backend/api/features/store/hybrid_search.py`: Unified search +
graceful degradation
- `backend/executor/scheduler.py`: Process all content types, consistent
returns
- `migrations/20260115200000_add_unified_search_tsvector/`: Add tsvector
to unified table
- `migrations/20260115210000_remove_storelistingversion_search/`: Remove
old search column
- `schema.prisma`: Updated UnifiedContentEmbedding and
StoreListingVersion models
- `*_test.py`: Added tests for unified_hybrid_search
## Test Plan
1. ✅ All tests passing on Python 3.11, 3.12, 3.13
2. ✅ Types check passing
3. ✅ CodeRabbit and Sentry reviews addressed
4. Deploy to staging and verify:
- Backfill job processes all content types
- Search results include blocks and docs
- Search works without OpenAI API (graceful degradation)
🤖 Generated with [Claude Code](https://claude.ai/code)
---------
Co-authored-by: Swifty <craigswift13@gmail.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
<!-- Clearly explain the need for these changes: -->
gitbook changes via ui
<!-- CURSOR_SUMMARY -->
---
> [!NOTE]
> **Docs sync from GitBook**
>
> - Updates `docs/home/README.md` with a new Developer Platform landing
page (cards, links to Platform, Integrations, Contribute, Discord,
GitHub) and metadata/cover settings
> - Adds `docs/home/SUMMARY.md` defining the table of contents linking
to `README.md`
> - No application/runtime code changes
>
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
446c71fec8. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
## Changes 🏗️
### System credentials in Run Modal
We had the issue that "system" credentials were mixed with "user"
credentials in the run agent modal:
#### Before
<img width="400" height="466" alt="Screenshot 2026-01-14 at 19 05 56"
src="https://github.com/user-attachments/assets/9d1ee766-5004-491f-ae14-a0cf89a9118e"
/>
This created confusion among the users. This "system" credentials are
supplied by AutoGPT ( _most of the time_ ) and a user running an agent
should not bother with them ( _unless they want to change them_ ). For
example in this case, the credential that matters is the **Google** one
🙇🏽
### After
<img width="400" height="350" alt="Screenshot 2026-01-14 at 19 04 12"
src="https://github.com/user-attachments/assets/e2bbc015-ce4c-496c-a76f-293c01a11c6f"
/>
<img width="400" height="672" alt="Screenshot 2026-01-14 at 19 04 19"
src="https://github.com/user-attachments/assets/d704dae2-ecb2-4306-bd04-3d812fed4401"
/>
"System" credentials are collapsed by default, reducing noise in the
Task Credentials section. The user can still see and change them by
expanding the accordion.
<img width="400" height="190" alt="Screenshot 2026-01-14 at 19 04 27"
src="https://github.com/user-attachments/assets/edc69612-4588-48e4-981a-f59c26cfa390"
/>
If some "system" credentials are missing, there is a red label
indicating so, it wasn't that obvious with the previous implementation,
<img width="400" height="309" alt="Screenshot 2026-01-14 at 19 04 30"
src="https://github.com/user-attachments/assets/f27081c7-40ad-4757-97b3-f29636616fc2"
/>
### New endpoint
There is a new REST endpoint, `GET /providers/system`, to list system
credential providers so it is easy to access in the Front-end to group
them together vs user ones.
### Other improvements
#### `<CredentialsInput />` refinements
<img width="715" height="200" alt="Screenshot 2026-01-14 at 19 09 31"
src="https://github.com/user-attachments/assets/01b39b16-25f3-428d-a6c8-da608038a38b"
/>
Use a normal browser `<select>` for the Credentials Dropdown ( _when you
have more than 1 for a provider_ ). This simplifies the UI shennagians a
lot and provides a better UX in 📱 ( _eventually we should move all our
selects to the native ones as they are much better for mobile and touch
screens and less code to maintain our end_ ).
I also renamed some files for clarity and tidied up some of the existing
logic.
#### Other
- Fix **Open telemetry** warnings on the server console by making the
packages external
- Fix `require-in-the-middle` console warnings
- Prettier tidy ups
## Checklist 📋
### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Run the app locally and test the above
This PR extracts backend changes from the hackathon/copilot branch,
adding enhanced chat capabilities, agent management tools, store
embeddings, and hybrid search functionality.
### Changes 🏗️
**Chat Features:**
- Added chat database layer (`db.py`) for conversation and message
persistence
- Extended chat models with new types and response structures
- New onboarding system prompt for guided user experiences
- Enhanced chat routes with additional endpoints
- Expanded chat service with more capabilities
**Chat Agent Tools:**
- `agent_output.py` - Handle agent execution outputs
- `create_agent.py` - Tool for creating new agents via chat
- `edit_agent.py` - Tool for modifying existing agents
- `find_library_agent.py` - Search and discover library agents
- Enhanced `run_agent.py` with additional functionality
- New `models.py` for shared tool types
**Store Enhancements:**
- `embeddings.py` - Vector embeddings support for semantic search
- `hybrid_search.py` - Combined keyword and semantic search
- `backfill_embeddings.py` - Utility for backfilling existing data
- Updated store database operations
**Admin:**
- Enhanced store admin routes
**Data Layer:**
- New `understanding.py` module for agent understanding/context
**Database Migrations:**
- `add_chat_tables` - Chat conversation and message tables
- `add_store_embeddings` - Embeddings storage for store items
- `enhance_search` - Search index improvements
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Chat endpoints respond correctly
- [x] Agent tools (create/edit/find/run) function properly
- [x] Store embeddings and hybrid search work
- [x] Database migrations apply cleanly
#### For configuration changes:
- [x] `.env.default` is updated or already compatible with my changes
- [x] `docker-compose.yml` is updated or already compatible with my
changes
- [x] I have included a list of my configuration changes in the PR
description (under **Changes**)
---------
Co-authored-by: Torantulino <40276179@live.napier.ac.uk>
(#11770)
### Changes 🏗️
- Added conditional rendering for array and object field children based
on connection status
- Implemented `shouldShowChildren` logic in `ArrayFieldTemplate` and
`ObjectFieldTemplate` components
- Modified the `shouldShowChildren` condition in `FieldTemplate` to
handle different schema types
- Imported and utilized `cleanUpHandleId` and `useEdgeStore` to check if
inputs are connected
- Added connection status checks to hide form fields when their inputs
are connected to other nodes
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Verified that object and array fields hide their children when
connected to other nodes
- [x] Confirmed that unconnected fields display their children properly
- [x] Tested with various schema types to ensure correct rendering
behavior
- [x] Checked that the connection status is properly detected and
applied
### Changes 🏗️
This PR adds a comprehensive interactive tutorial for the new Builder UI
to help users learn how to create agents. Key changes include:
- Added a tutorial button to the canvas controls that launches a
step-by-step guide
- Created a Shepherd.js-based tutorial with multiple steps covering:
- Adding blocks from the Block Menu
- Understanding input and output handles
- Configuring block values
- Connecting blocks together
- Saving and running agents
- Added data-id attributes to key UI elements for tutorial targeting
- Implemented tutorial state management with a new tutorialStore
- Added helper functions for tutorial navigation and block manipulation
- Created CSS styles for tutorial tooltips and highlights
- Integrated with the Run Input dialog to support tutorial flow
- Added prefetching of tutorial blocks for better performance
https://github.com/user-attachments/assets/3db964b3-855c-4fcc-aa5f-6cd74ab33d7d
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Complete the tutorial from start to finish
- [x] Test tutorial on different screen sizes
- [x] Verify all tutorial steps work correctly
- [x] Ensure tutorial can be canceled and restarted
- [x] Check that tutorial doesn't interfere with normal builder
functionality
This PR adds hybrid search functionality combining semantic embeddings
with traditional text search for improved store listing discovery.
### Changes 🏗️
- Add `embeddings.py` - OpenAI-based embedding generation and similarity
search
- Add `hybrid_search.py` - Combines vector similarity with text matching
for better search results
- Add `backfill_embeddings.py` - Script to generate embeddings for
existing store listings
- Update `db.py` - Integrate hybrid search into store database queries
- Update `schema.prisma` - Add embedding storage fields and indexes
- Add migrations for embedding columns and HNSW index for vector search
### Architecture Decisions 🏛️
**Fail-Fast Approach (No Silent Fallbacks)**
We explicitly chose NOT to implement graceful degradation when hybrid
search fails. Here's why:
✅ **Benefits:**
- Errors surface immediately → faster fixes
- Tests verify hybrid search actually works (not just fallback)
- Consistent search quality for all users
- Forces proper infrastructure setup (API keys, database)
❌ **Why Not Fallback:**
- Silent degradation hides production issues
- Users get inconsistent results without knowing why
- Tests can pass even when hybrid search is broken
- Reduces operational visibility
**How We Prevent Failures:**
1. Embedding generation in approval flow (db.py:1545)
2. Error logging with `logger.error` (not warning)
3. Clear error messages (ValueError explains what's wrong)
4. Comprehensive test coverage (9/9 tests passing)
If embeddings fail, it indicates a real infrastructure issue (missing
API key, OpenAI down, database issues) that needs immediate attention,
not silent degradation.
### Test Coverage ✅
**All tests passing (1625 total):**
- 9/9 hybrid_search tests (including fail-fast validation)
- 3/3 db search integration tests
- Full schema compatibility (public/platform schemas)
- Error handling verification
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Test hybrid search returns relevant results
- [x] Test embedding generation for new listings
- [x] Test backfill script on existing data
- [x] Verify search performance with embeddings
- [x] Test fail-fast behavior when embeddings unavailable
#### For configuration changes:
- [x] `.env.default` is updated or already compatible with my changes
- [x] `docker-compose.yml` is updated or already compatible with my
changes
- [x] Configuration: Requires `openai_internal_api_key` in secrets
---------
Co-authored-by: Zamil Majdy <zamil.majdy@agpt.co>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
[OPEN-2946: \[Scheduler\] Error executing graph <graph_id> after 19.83s:
ClientNotConnectedError: Client is not connected to the query engine,
you must call `connect()` before attempting to query
data.](https://linear.app/autogpt/issue/OPEN-2946)
- Follow-up to #11375
<sub>(broken `increment_runs` call)</sub>
- Follow-up to #11380
<sub>(direct `get_graph_execution` call)</sub>
### Changes 🏗️
- Move `increment_runs` call from `scheduler._execute_graph` to
`executor.utils.add_graph_execution` so it can be made through
`DatabaseManager`
- Add `increment_onboarding_runs` to `DatabaseManager`
- Remove now-redundant `increment_onboarding_runs` calls in other places
- Make `add_graph_execution` more resilient
- Split up large try/except block
- Fix direct `get_graph_execution` call
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- CI + a thorough review
[OPEN-2743: Ability to Update Sub-Agents in Graph (Without
Re-Adding)](https://linear.app/autogpt/issue/OPEN-2743/ability-to-update-sub-agents-in-graph-without-re-adding)
Updating sub-graphs is a cumbersome experience at the moment, this
should help. :)
Demo in Builder v2:
https://github.com/user-attachments/assets/df564f32-4d1d-432c-bb91-fe9065068360https://github.com/user-attachments/assets/f169471a-1f22-46e9-a958-ddb72d3f65af
### Changes 🏗️
- Add sub-graph update banner with I/O incompatibility notification and
resolution mode
- Red visual indicators for broken inputs/outputs and edges
- Update bars and tooltips show compatibility details
- Sub-agent update UI with compatibility checks, incompatibility dialog,
and guided resolution workflow
- Resolution mode banner guiding users to remove incompatible
connections
- Visual controls to stage/apply updates and auto-apply when broken
connections are fixed
Technical:
- Builder v1: Add `CustomNode` > `IncompatibilityDialog` +
`SubAgentUpdateBar` sub-components
- Builder v2: Add `SubAgentUpdateFeature` + `ResolutionModeBar` +
`IncompatibleUpdateDialog` + `useSubAgentUpdateState` sub-components
- Add `useSubAgentUpdate` hook
- Related fixes in Builder v1:
- Fix static edges not rendering as such
- Fix edge styling not applying
- Related fixes in Builder v2:
- Fix excess spacing for nested node input fields
Other:
- "Retry" button in error view now reloads the page instead of
navigating to `/marketplace`
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- CI for existing frontend UX flows
- [x] Updating to a new sub-agent version with compatibility issues: UX
flow works
- [x] Updating to a new sub-agent version with *no* compatibility
issues: works
- [x] Designer approves of the look
---------
Co-authored-by: abhi1992002 <abhimanyu1992002@gmail.com>
Co-authored-by: Abhimanyu Yadav <122007096+Abhi1992002@users.noreply.github.com>
## Summary
Fixes a critical security issue where the billing button in the settings
sidebar was always visible to all users, bypassing the
`ENABLE_PLATFORM_PAYMENT` feature flag.
## Changes 🏗️
- Removed hardcoded `|| true` condition in
`frontend/src/app/(platform)/profile/(user)/layout.tsx:32` that was
bypassing the feature flag check
- The billing button is now properly gated by the
`ENABLE_PLATFORM_PAYMENT` feature flag as intended
## Root Cause
The `|| true` was accidentally left in commit
3dbc03e488 (PR #11617 - OAuth API & Single
Sign-On) from December 19, 2025. It was likely added temporarily during
development/testing to always show the billing button, but was not
removed before merging.
## Test Plan
1. Verify feature flag is set to disabled in LaunchDarkly
2. Navigate to settings page (`/profile/settings`)
3. Confirm billing button is NOT visible in the sidebar
4. Enable feature flag in LaunchDarkly
5. Refresh page and confirm billing button IS now visible
6. Verify billing page (`/profile/credits`) is still accessible via
direct URL when feature flag is disabled
## Checklist 📋
### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan
Fixes SECRT-1791
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **Bug Fixes**
* The Billing link in the profile sidebar now respects the payment
feature flag configuration and will only display when payment
functionality is enabled.
<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
The GetWikipediaSummaryBlock was returning HTTP 403 errors from
Wikipedia's API because it wasn't explicitly setting a User-Agent header
that complies with https://wikitech.wikimedia.org/wiki/Robot_policy.
Additionally, topics with spaces or special characters would cause
malformed URLs.
Fixes: OPEN-2889
Changes 🏗️
- URL-encode the topic parameter using urllib.parse.quote() to handle
spaces and special characters
- Explicitly set required headers per Wikimedia robot policy:
- User-Agent: Platform default user agent (includes app name, URL, and
contact email)
- Accept-Encoding: gzip, deflate: Recommended by Wikimedia to reduce
bandwidth
- Updated test mock to match the new function signature
Checklist 📋
For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Verify code passes syntax check
- [x] Verify code passes ruff linting
- [x] Create an agent using GetWikipediaSummaryBlock with a topic
containing spaces (e.g., "Artificial Intelligence")
- [x] Verify the block returns a Wikipedia summary without 403 errors
For configuration changes:
- .env.default is updated or already compatible with my changes
- docker-compose.yml is updated or already compatible with my changes
- I have included a list of my configuration changes in the PR
description (under Changes)
.
N/A - No configuration changes required.
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **Bug Fixes**
* Improved Wikipedia API requests by adding compatible request headers
(including a proper user agent and encoding acceptance) for more
reliable responses.
* Enhanced handling of search topics by URL-encoding terms so queries
with spaces or special characters return correct results.
<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
**Implements issue #11002**
This PR adds WordPress post management functionality and improves error
handling in DataForSEO blocks.
### Changes 🏗️
1. **New WordPress Blocks:**
- Added `WordPressGetAllPostsBlock` - Fetches posts from WordPress sites
with filtering and pagination support
- Enhanced `WordPressCreatePostBlock` with `publish_as_draft` toggle to
control post publication status
2. **WordPress API Enhancements:**
- Added `get_posts()` function in `_api.py` to retrieve posts with
filtering by status
- Added `PostsResponse` model for handling WordPress posts list API
responses
- Support for pagination with `number` and `offset` parameters (max 100
posts per request)
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
**Test Plan:**
- [x] Test `WordPressGetAllPostsBlock` with valid WordPress credentials
- [x] Verify filtering posts by status (publish, draft, pending, etc.)
- [x] Test pagination with different number and offset values
- [x] Test `WordPressCreatePostBlock` with publish_as_draft=True to
create draft posts
- [x] Test `WordPressCreatePostBlock` with publish_as_draft=False to
publish posts publicly
#### For configuration changes:
- [x] `.env.default` is updated or already compatible with my changes
- [x] `docker-compose.yml` is updated or already compatible with my
changes
- [x] I have included a list of my configuration changes in the PR
description (under **Changes**)
**Note:** No configuration changes were required for this PR.
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Added a WordPress “Get All Posts” block to fetch posts with optional
status filtering and pagination; returns total found and post details.
* **Enhancements**
* WordPress “Create Post” block now supports a “Publish as draft”
option, allowing posts to be created as drafts or published immediately.
* WordPress blocks are now surfaced consistently in the block catalog
for easier use.
* **Error Handling**
* Clearer error messages when fetching posts fails, aiding
troubleshooting.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
<!-- CURSOR_SUMMARY -->
---
> [!NOTE]
> Introduces WordPress post listing and improves post creation and API
robustness.
>
> - Adds `WordPressGetAllPostsBlock` to fetch posts with optional
`status` filter and pagination (`number`, `offset`); outputs `found`,
`posts`, and streams each `post`
> - Enhances `WordPressCreatePostBlock` with `publish_as_draft` input
and adds `site` to outputs; sets `status` accordingly
> - WordPress API updates in `_api.py`: new `get_posts`, `Post`,
`PostsResponse`, and `normalize_site`; apply
`Requests(raise_for_status=False)` across OAuth/token/info and post
creation; better error propagation
>
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
10be1c4709. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
---------
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: Toran Bruce Richards <Torantulino@users.noreply.github.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
Co-authored-by: Nicholas Tindle <ntindle@users.noreply.github.com>
Co-authored-by: Nicholas Tindle <nicholas.tindle@agpt.co>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
### Changes 🏗️
- Added a new `JsonTextField` component to handle complex nested JSON
types (objects/arrays inside other objects/arrays)
- Created helper functions for JSON parsing, validation, and formatting
- Implemented `useJsonTextField` hook to manage state and validation
- Enhanced `generateUiSchemaForCustomFields` to detect nested complex
types and render them as JSON text fields
- Updated `TextInputExpanderModal` to support JSON-specific styling
- Added `JSON_TEXT_FIELD_ID` constant to custom registry for field
identification
This change improves the user experience by preventing deeply nested
form UIs. Instead, complex nested structures are presented as editable
JSON text fields with proper validation and formatting.
### Before
### After
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Test with simple JSON objects in forms
- [x] Test with nested arrays and objects
- [x] Test with anyOf/oneOf schemas containing complex types
- [x] Test the expander modal with JSON content
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* New JSON text field with expandable modal editor, inline validation,
and helpful placeholders.
* Complex nested objects/arrays now render as JSON fields to simplify
editing.
* Modal editor uses monospace, smaller text when editing JSON for
improved readability.
* **Chores**
* Added a non-functional runtime debug log (no user-facing behavior
changes).
<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
### Changes 🏗️
- Added a new `variant` prop to `CredentialsInput` component with
options "default" or "node"
- Implemented compact styling for the "node" variant in `CredentialRow`
component
- Modified layout and overflow handling for credential display in node
context
- Added conditional rendering of masked key display based on variant
- Passed the variant prop through the component hierarchy
- Applied the "node" variant to the `CredentialsField` component with
appropriate styling
Before
After
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Verified credential selection works correctly in node context
- [x] Confirmed compact styling is applied properly in node variant
- [x] Tested overflow handling for long credential names
- [x] Verified both default and node variants display correctly
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Credential input and selection components now support multiple
configurable visual variants, enabling better text display handling,
optimized layouts, and improved visual consistency across different
application contexts and specific use cases.
* **Style**
* Credential field displays now feature enhanced text truncation and
overflow management for a more polished and consistent user interface
experience.
<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
### Changes 🏗️
- Added a new `Table` component for handling tabular data input
- Created supporting hooks and helper functions for the Table component
- Added Storybook stories to showcase different Table configurations
- Implemented a custom `TableField` renderer for JSON Schema forms
- Updated type display info to support the new "table" format
- Added schema matcher to detect and render table fields appropriately
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Verified Table component renders correctly with various
configurations
- [x] Tested adding and removing rows in the Table
- [x] Confirmed data changes are properly tracked and reported via
onChange
- [x] Verified TableField renderer works with JSON Schema forms
- [x] Checked that table format is properly detected in the schema
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
## Release Notes
* **New Features**
* Added a Table component for displaying and editing tabular data with
support for adding/deleting rows, read-only mode, and customizable
labels.
* Added support for rendering array fields as tables in form inputs with
configurable columns and values.
* **Tests**
* Added comprehensive Storybook stories demonstrating various Table
configurations and behaviors.
<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
## Changes 🏗️
- Added a new `MultiSelectField` component for handling multiple boolean
selections in a dropdown format
- Implemented `useMultiSelectField` hook to manage the state and logic
of the multi-select component
- Added support for custom fields in `AnyOfField` by checking if the
option schema matches a custom field
- Added `isMultiSelectSchema` utility function to detect schemas
suitable for the multi-select component
- Added hover cursor styling to node headers to indicate text
editability
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Verified that multi-select fields render correctly in the UI
- [x] Confirmed that selecting multiple options works as expected
- [x] Tested that the node header shows the text cursor on hover
- [x] Verified that AnyOf fields correctly use custom field renderers
when applicable
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Added a multi-select field allowing selection of multiple options with
improved selection UI.
* AnyOf options can now resolve and render custom field types, improving
form composition when schemas map to custom controls.
* **Style**
* Tooltip header cursor updated for clearer hover feedback.
<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
### Changes 🏗️
Fixed the `isAnyOfSchema` function in schema-utils.ts to exclude schemas
that have an `enum` property. This prevents incorrect schema processing
for enums that also have anyOf definitions. Added a console.log
statement in FormRenderer.tsx to help debug schema preprocessing.
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Verified that forms with enum values render correctly
- [x] Confirmed that anyOf schemas are properly identified and processed
- [x] Tested with various schema combinations to ensure the fix doesn't
break existing functionality
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
## Bug Fixes
* Improved validation logic for form field schemas to correctly handle
edge cases when multiple constraint types are defined.
<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
This PR fixes failing SmartDecisionMaker tests by adding missing
`metadata` attribute to mock nodes.
### Changes 🏗️
Mock nodes in SmartDecisionMaker tests were missing the `metadata = {}`
attribute, which was introduced in commit 4a52b7eca for the
customized_name feature. This caused tests to fail with:
```
TypeError: expected string or bytes-like object, got 'Mock'
```
**Files fixed**:
- `backend/blocks/test/test_smart_decision_maker_dict.py`: Added
`metadata = {}` to mock nodes in all 3 tests
- `backend/blocks/test/test_smart_decision_maker_dynamic_fields.py`:
Added `metadata = {}` to mock nodes in all 8 tests
**Root cause**: The `_create_block_function_signature` method calls
`sink_node.metadata.get("customized_name")`, but mock nodes in tests
didn't have the metadata attribute initialized.
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Run `poetry run pytest
backend/blocks/test/test_smart_decision_maker_dict.py -xvs` - 3 passed
- [x] Run `poetry run pytest
backend/blocks/test/test_smart_decision_maker_dynamic_fields.py -xvs` -
8 passed
- [x] All tests pass successfully
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
## Release Notes
* **Tests**
* Updated test infrastructure to enhance mock object configuration for
improved test reliability and consistency across test suites.
<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
## Root Cause
Execution a40bdb4a-964d-4684-94e8-b148eb6bcfc2 and all similar
executions have been failing since Nov 12, 2025 when tool pin routing
was refactored to use node IDs. The SmartDecisionMakerBlock was
double-sanitizing field names when emitting tool call outputs:
```python
# Original field name from link: "Max Keyword Difficulty"
original_field_name = field_mapping.get(clean_arg_name) # ✅ Retrieved correctly
sanitized_arg_name = self.cleanup(original_field_name) # ❌ Sanitized AGAIN!
emit_key = f"tools_^_{node_id}_~_{sanitized_arg_name}" # Emits "max_keyword_difficulty"
```
But the parser expected original names from graph links:
```python
# Parser expects: "Max Keyword Difficulty" (from link.sink_name)
# Emit provides: "max_keyword_difficulty" (sanitized)
# Result: Mismatch → Tool never executes
```
### Changes 🏗️
**1. Fixed Emit Logic** (`smart_decision_maker.py` line 1135)
- Removed double sanitization: `sanitized_arg_name =
self.cleanup(original_field_name)`
- Now emits with original field names: `emit_key =
f"tools_^_{node_id}_~_{original_field_name}"`
**2. Made Agent Nodes Consistent** (`smart_decision_maker.py` lines
497-530)
- Added `field_mapping` to agent function signatures (was missing)
- Agent signatures now sanitize property keys for Anthropic API (like
block signatures)
- Stores field_mapping for use during emit
### Impact
**Fixes:**
- ✅ All graphs with multi-word field names (e.g., "Max Keyword
Difficulty", "Minimum Volume")
- ✅ All graphs with special characters in field names (e.g., "API-Key")
- ✅ Both block nodes AND agent nodes now work consistently
**Unaffected:**
- Single-word lowercase field names (e.g., "keyword", "url") - these
were already working
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Verified parse_execution_output handles exact match correctly
- [x] Verified emit uses original field names
- [x] Verified field_mapping works for both block and agent nodes
- [x] Re-run execution a40bdb4a-964d-4684-94e8-b148eb6bcfc2 after
deployment to verify fix
#### For configuration changes:
- [x] `.env.default` is updated or already compatible with my changes
(no changes)
- [x] `docker-compose.yml` is updated or already compatible with my
changes (no changes)
- [x] No configuration changes in this PR
### Test Plan
1. **Unit test validation** (completed):
- Field name cleanup: "Max Keyword Difficulty" →
"max_keyword_difficulty" ✅
- Parse with exact match: Success ✅
- Parse with mismatch: Returns None ✅
2. **Production validation** (to be done after deployment):
- Re-run execution a40bdb4a-964d-4684-94e8-b148eb6bcfc2
- Verify AgentExecutor (node 767682f5-694f-4b2a-bf52-fbdcad6a4a4f)
executes successfully
- Verify execution completes with high correctness score (not 0.20)
- Monitor for any regressions in existing graphs
### Files Changed
- `backend/blocks/smart_decision_maker.py`: Remove double sanitization,
add agent field_mapping
### Related Issues
- Resolves execution failure a40bdb4a-964d-4684-94e8-b148eb6bcfc2
- Fixes bug introduced in commit 536e2a5ec (Nov 12, 2025)
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **Bug Fixes**
* Improved field name mapping consistency in the SmartDecisionMaker
block to ensure proper handling of field names throughout function
signatures and tool execution workflows.
<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
