chore(deps): bump actions/cache from 4 to 5

Bumps [actions/cache](https://github.com/actions/cache) from 4 to 5.
- [Release notes](https://github.com/actions/cache/releases)
- [Changelog](https://github.com/actions/cache/blob/main/RELEASES.md)
- [Commits](https://github.com/actions/cache/compare/v4...v5)

---
updated-dependencies:
- dependency-name: actions/cache
  dependency-version: '5'
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>

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

@@ -83,7 +83,7 @@ jobs:
       - 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
+        uses: actions/cache@v5
         with:
           path: ${{ runner.os == 'macOS' && '~/Library/Caches/pypoetry' || '~/.cache/pypoetry' }}
           key: poetry-${{ runner.os }}-${{ hashFiles('classic/original_autogpt/poetry.lock') }}

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

@@ -55,7 +55,7 @@ jobs:
       - 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
+        uses: actions/cache@v5
         with:
           path: ${{ runner.os == 'macOS' && '~/Library/Caches/pypoetry' || '~/.cache/pypoetry' }}
           key: poetry-${{ runner.os }}-${{ hashFiles('classic/benchmark/poetry.lock') }}

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

@@ -107,7 +107,7 @@ jobs:
       - 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
+        uses: actions/cache@v5
         with:
           path: ${{ runner.os == 'macOS' && '~/Library/Caches/pypoetry' || '~/.cache/pypoetry' }}
           key: poetry-${{ runner.os }}-${{ hashFiles('classic/forge/poetry.lock') }}

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

@@ -49,7 +49,7 @@ jobs:
 
       - name: Create PR ${{ env.BUILD_BRANCH }} -> ${{ github.ref_name }}
         if: github.event_name == 'push'
-        uses: peter-evans/create-pull-request@v7
+        uses: peter-evans/create-pull-request@v8
         with:
           add-paths: classic/frontend/build/web
           base: ${{ github.ref_name }}

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

@@ -78,7 +78,7 @@ jobs:
           python-version: ${{ env.min-python-version }}
 
       - name: Set up Python dependency cache
-        uses: actions/cache@v4
+        uses: actions/cache@v5
         with:
           path: ~/.cache/pypoetry
           key: ${{ runner.os }}-poetry-${{ hashFiles(format('{0}/poetry.lock', matrix.sub-package)) }}
@@ -130,7 +130,7 @@ jobs:
           python-version: ${{ env.min-python-version }}
 
       - name: Set up Python dependency cache
-        uses: actions/cache@v4
+        uses: actions/cache@v5
         with:
           path: ~/.cache/pypoetry
           key: ${{ runner.os }}-poetry-${{ hashFiles(format('{0}/poetry.lock', matrix.sub-package)) }}

.github/workflows/claude-ci-failure-auto-fix.yml

@@ -42,7 +42,7 @@ jobs:
 
       - name: Get CI failure details
         id: failure_details
-        uses: actions/github-script@v7
+        uses: actions/github-script@v8
         with:
           script: |
             const run = await github.rest.actions.getWorkflowRun({

.github/workflows/claude-dependabot.yml

@@ -41,7 +41,7 @@ jobs:
           python-version: "3.11"  # Use standard version matching CI
 
       - name: Set up Python dependency cache
-        uses: actions/cache@v4
+        uses: actions/cache@v5
         with:
           path: ~/.cache/pypoetry
           key: poetry-${{ runner.os }}-${{ hashFiles('autogpt_platform/backend/poetry.lock') }}
@@ -78,7 +78,7 @@ jobs:
 
       # Frontend Node.js/pnpm setup (mirrors platform-frontend-ci.yml)
       - name: Set up Node.js
-        uses: actions/setup-node@v4
+        uses: actions/setup-node@v6
         with:
           node-version: "22"
 
@@ -91,7 +91,7 @@ jobs:
           echo "PNPM_HOME=$HOME/.pnpm-store" >> $GITHUB_ENV
 
       - name: Cache frontend dependencies
-        uses: actions/cache@v4
+        uses: actions/cache@v5
         with:
           path: ~/.pnpm-store
           key: ${{ runner.os }}-pnpm-${{ hashFiles('autogpt_platform/frontend/pnpm-lock.yaml', 'autogpt_platform/frontend/package.json') }}
@@ -124,7 +124,7 @@ jobs:
       # Phase 1: Cache and load Docker images for faster setup
       - name: Set up Docker image cache
         id: docker-cache
-        uses: actions/cache@v4
+        uses: actions/cache@v5
         with:
           path: ~/docker-cache
           # Use a versioned key for cache invalidation when image list changes
@@ -309,6 +309,7 @@ jobs:
         uses: anthropics/claude-code-action@v1
         with:
           claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
+          allowed_bots: "dependabot[bot]"
           claude_args: |
             --allowedTools "Bash(npm:*),Bash(pnpm:*),Bash(poetry:*),Bash(git:*),Edit,Replace,NotebookEditCell,mcp__github_inline_comment__create_inline_comment,Bash(gh pr comment:*), Bash(gh pr diff:*), Bash(gh pr view:*)"
           prompt: |

.github/workflows/claude.yml

@@ -57,7 +57,7 @@ jobs:
           python-version: "3.11"  # Use standard version matching CI
 
       - name: Set up Python dependency cache
-        uses: actions/cache@v4
+        uses: actions/cache@v5
         with:
           path: ~/.cache/pypoetry
           key: poetry-${{ runner.os }}-${{ hashFiles('autogpt_platform/backend/poetry.lock') }}
@@ -94,7 +94,7 @@ jobs:
 
       # Frontend Node.js/pnpm setup (mirrors platform-frontend-ci.yml)
       - name: Set up Node.js
-        uses: actions/setup-node@v4
+        uses: actions/setup-node@v6
         with:
           node-version: "22"
 
@@ -107,7 +107,7 @@ jobs:
           echo "PNPM_HOME=$HOME/.pnpm-store" >> $GITHUB_ENV
 
       - name: Cache frontend dependencies
-        uses: actions/cache@v4
+        uses: actions/cache@v5
         with:
           path: ~/.pnpm-store
           key: ${{ runner.os }}-pnpm-${{ hashFiles('autogpt_platform/frontend/pnpm-lock.yaml', 'autogpt_platform/frontend/package.json') }}
@@ -140,7 +140,7 @@ jobs:
       # Phase 1: Cache and load Docker images for faster setup
       - name: Set up Docker image cache
         id: docker-cache
-        uses: actions/cache@v4
+        uses: actions/cache@v5
         with:
           path: ~/docker-cache
           # Use a versioned key for cache invalidation when image list changes

.github/workflows/copilot-setup-steps.yml

@@ -39,7 +39,7 @@ jobs:
           python-version: "3.11"  # Use standard version matching CI
 
       - name: Set up Python dependency cache
-        uses: actions/cache@v4
+        uses: actions/cache@v5
         with:
           path: ~/.cache/pypoetry
           key: poetry-${{ runner.os }}-${{ hashFiles('autogpt_platform/backend/poetry.lock') }}
@@ -76,7 +76,7 @@ jobs:
 
       # Frontend Node.js/pnpm setup (mirrors platform-frontend-ci.yml)
       - name: Set up Node.js
-        uses: actions/setup-node@v4
+        uses: actions/setup-node@v6
         with:
           node-version: "22"
 
@@ -89,7 +89,7 @@ jobs:
           echo "PNPM_HOME=$HOME/.pnpm-store" >> $GITHUB_ENV
 
       - name: Cache frontend dependencies
-        uses: actions/cache@v4
+        uses: actions/cache@v5
         with:
           path: ~/.pnpm-store
           key: ${{ runner.os }}-pnpm-${{ hashFiles('autogpt_platform/frontend/pnpm-lock.yaml', 'autogpt_platform/frontend/package.json') }}
@@ -132,7 +132,7 @@ jobs:
       # Phase 1: Cache and load Docker images for faster setup
       - name: Set up Docker image cache
         id: docker-cache
-        uses: actions/cache@v4
+        uses: actions/cache@v5
         with:
           path: ~/docker-cache
           # Use a versioned key for cache invalidation when image list changes

.github/workflows/docs-block-sync.yml

@@ -33,7 +33,7 @@ jobs:
           python-version: "3.11"
 
       - name: Set up Python dependency cache
-        uses: actions/cache@v4
+        uses: actions/cache@v5
         with:
           path: ~/.cache/pypoetry
           key: poetry-${{ runner.os }}-${{ hashFiles('autogpt_platform/backend/poetry.lock') }}

.github/workflows/docs-claude-review.yml

@@ -33,7 +33,7 @@ jobs:
           python-version: "3.11"
 
       - name: Set up Python dependency cache
-        uses: actions/cache@v4
+        uses: actions/cache@v5
         with:
           path: ~/.cache/pypoetry
           key: poetry-${{ runner.os }}-${{ hashFiles('autogpt_platform/backend/poetry.lock') }}

.github/workflows/docs-enhance.yml

@@ -38,7 +38,7 @@ jobs:
           python-version: "3.11"
 
       - name: Set up Python dependency cache
-        uses: actions/cache@v4
+        uses: actions/cache@v5
         with:
           path: ~/.cache/pypoetry
           key: poetry-${{ runner.os }}-${{ hashFiles('autogpt_platform/backend/poetry.lock') }}

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

@@ -88,7 +88,7 @@ jobs:
         run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_OUTPUT
 
       - name: Set up Python dependency cache
-        uses: actions/cache@v4
+        uses: actions/cache@v5
         with:
           path: ~/.cache/pypoetry
           key: poetry-${{ runner.os }}-${{ hashFiles('autogpt_platform/backend/poetry.lock') }}

.github/workflows/platform-dev-deploy-event-dispatcher.yml

@@ -17,7 +17,7 @@ jobs:
       - name: Check comment permissions and deployment status
         id: check_status
         if: github.event_name == 'issue_comment' && github.event.issue.pull_request
-        uses: actions/github-script@v7
+        uses: actions/github-script@v8
         with:
           script: |
             const commentBody = context.payload.comment.body.trim();
@@ -55,7 +55,7 @@ jobs:
 
       - name: Post permission denied comment
         if: steps.check_status.outputs.permission_denied == 'true'
-        uses: actions/github-script@v7
+        uses: actions/github-script@v8
         with:
           script: |
             await github.rest.issues.createComment({
@@ -68,7 +68,7 @@ jobs:
       - name: Get PR details for deployment
         id: pr_details
         if: steps.check_status.outputs.should_deploy == 'true' || steps.check_status.outputs.should_undeploy == 'true'
-        uses: actions/github-script@v7
+        uses: actions/github-script@v8
         with:
           script: |
             const pr = await github.rest.pulls.get({
@@ -98,7 +98,7 @@ jobs:
 
       - name: Post deploy success comment
         if: steps.check_status.outputs.should_deploy == 'true'
-        uses: actions/github-script@v7
+        uses: actions/github-script@v8
         with:
           script: |
             await github.rest.issues.createComment({
@@ -126,7 +126,7 @@ jobs:
 
       - name: Post undeploy success comment
         if: steps.check_status.outputs.should_undeploy == 'true'
-        uses: actions/github-script@v7
+        uses: actions/github-script@v8
         with:
           script: |
             await github.rest.issues.createComment({
@@ -139,7 +139,7 @@ jobs:
       - name: Check deployment status on PR close
         id: check_pr_close
         if: github.event_name == 'pull_request' && github.event.action == 'closed'
-        uses: actions/github-script@v7
+        uses: actions/github-script@v8
         with:
           script: |
             const comments = await github.rest.issues.listComments({
@@ -187,7 +187,7 @@ jobs:
           github.event_name == 'pull_request' &&
           github.event.action == 'closed' &&
           steps.check_pr_close.outputs.should_undeploy == 'true'
-        uses: actions/github-script@v7
+        uses: actions/github-script@v8
         with:
           script: |
             await github.rest.issues.createComment({

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

@@ -42,7 +42,7 @@ jobs:
               - 'autogpt_platform/frontend/src/components/**'
 
       - name: Set up Node.js
-        uses: actions/setup-node@v4
+        uses: actions/setup-node@v6
         with:
           node-version: "22.18.0"
 
@@ -54,7 +54,7 @@ jobs:
         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@v4
+        uses: actions/cache@v5
         with:
           path: ~/.pnpm-store
           key: ${{ steps.cache-key.outputs.key }}
@@ -74,7 +74,7 @@ jobs:
         uses: actions/checkout@v4
 
       - name: Set up Node.js
-        uses: actions/setup-node@v4
+        uses: actions/setup-node@v6
         with:
           node-version: "22.18.0"
 
@@ -82,7 +82,7 @@ jobs:
         run: corepack enable
 
       - name: Restore dependencies cache
-        uses: actions/cache@v4
+        uses: actions/cache@v5
         with:
           path: ~/.pnpm-store
           key: ${{ needs.setup.outputs.cache-key }}
@@ -112,7 +112,7 @@ jobs:
           fetch-depth: 0
 
       - name: Set up Node.js
-        uses: actions/setup-node@v4
+        uses: actions/setup-node@v6
         with:
           node-version: "22.18.0"
 
@@ -120,7 +120,7 @@ jobs:
         run: corepack enable
 
       - name: Restore dependencies cache
-        uses: actions/cache@v4
+        uses: actions/cache@v5
         with:
           path: ~/.pnpm-store
           key: ${{ needs.setup.outputs.cache-key }}
@@ -153,7 +153,7 @@ jobs:
           submodules: recursive
 
       - name: Set up Node.js
-        uses: actions/setup-node@v4
+        uses: actions/setup-node@v6
         with:
           node-version: "22.18.0"
 
@@ -176,7 +176,7 @@ jobs:
         uses: docker/setup-buildx-action@v3
 
       - name: Cache Docker layers
-        uses: actions/cache@v4
+        uses: actions/cache@v5
         with:
           path: /tmp/.buildx-cache
           key: ${{ runner.os }}-buildx-frontend-test-${{ hashFiles('autogpt_platform/docker-compose.yml', 'autogpt_platform/backend/Dockerfile', 'autogpt_platform/backend/pyproject.toml', 'autogpt_platform/backend/poetry.lock') }}
@@ -231,7 +231,7 @@ jobs:
           fi
 
       - name: Restore dependencies cache
-        uses: actions/cache@v4
+        uses: actions/cache@v5
         with:
           path: ~/.pnpm-store
           key: ${{ needs.setup.outputs.cache-key }}
@@ -282,7 +282,7 @@ jobs:
           submodules: recursive
 
       - name: Set up Node.js
-        uses: actions/setup-node@v4
+        uses: actions/setup-node@v6
         with:
           node-version: "22.18.0"
 
@@ -290,7 +290,7 @@ jobs:
         run: corepack enable
 
       - name: Restore dependencies cache
-        uses: actions/cache@v4
+        uses: actions/cache@v5
         with:
           path: ~/.pnpm-store
           key: ${{ needs.setup.outputs.cache-key }}

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

@@ -32,7 +32,7 @@ jobs:
         uses: actions/checkout@v4
 
       - name: Set up Node.js
-        uses: actions/setup-node@v4
+        uses: actions/setup-node@v6
         with:
           node-version: "22.18.0"
 
@@ -44,7 +44,7 @@ jobs:
         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@v4
+        uses: actions/cache@v5
         with:
           path: ~/.pnpm-store
           key: ${{ steps.cache-key.outputs.key }}
@@ -68,7 +68,7 @@ jobs:
           submodules: recursive
 
       - name: Set up Node.js
-        uses: actions/setup-node@v4
+        uses: actions/setup-node@v6
         with:
           node-version: "22.18.0"
 
@@ -88,7 +88,7 @@ jobs:
           docker compose -f ../docker-compose.yml --profile local --profile deps_backend up -d
 
       - name: Restore dependencies cache
-        uses: actions/cache@v4
+        uses: actions/cache@v5
         with:
           path: ~/.pnpm-store
           key: ${{ needs.setup.outputs.cache-key }}

autogpt_platform/autogpt_libs/pyproject.toml

@@ -9,25 +9,25 @@ packages = [{ include = "autogpt_libs" }]
 [tool.poetry.dependencies]
 python = ">=3.10,<4.0"
 colorama = "^0.4.6"
-cryptography = "^45.0"
+cryptography = "^46.0"
 expiringdict = "^1.2.2"
-fastapi = "^0.116.1"
-google-cloud-logging = "^3.12.1"
-launchdarkly-server-sdk = "^9.12.0"
-pydantic = "^2.11.7"
-pydantic-settings = "^2.10.1"
-pyjwt = { version = "^2.10.1", extras = ["crypto"] }
+fastapi = "^0.128.0"
+google-cloud-logging = "^3.13.0"
+launchdarkly-server-sdk = "^9.14.1"
+pydantic = "^2.12.5"
+pydantic-settings = "^2.12.0"
+pyjwt = { version = "^2.11.0", extras = ["crypto"] }
 redis = "^6.2.0"
-supabase = "^2.16.0"
-uvicorn = "^0.35.0"
+supabase = "^2.27.2"
+uvicorn = "^0.40.0"
 
 [tool.poetry.group.dev.dependencies]
-pyright = "^1.1.404"
+pyright = "^1.1.408"
 pytest = "^8.4.1"
-pytest-asyncio = "^1.1.0"
-pytest-mock = "^3.14.1"
+pytest-asyncio = "^1.3.0"
+pytest-mock = "^3.15.1"
 pytest-cov = "^6.2.1"
-ruff = "^0.12.11"
+ruff = "^0.15.0"
 
 [build-system]
 requires = ["poetry-core"]

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

@@ -45,10 +45,7 @@ async def create_chat_session(
         successfulAgentRuns=SafeJson({}),
         successfulAgentSchedules=SafeJson({}),
     )
-    return await PrismaChatSession.prisma().create(
-        data=data,
-        include={"Messages": True},
-    )
+    return await PrismaChatSession.prisma().create(data=data)
 
 
 async def update_chat_session(

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

@@ -266,12 +266,38 @@ async def stream_chat_post(
 
     """
     import asyncio
+    import time
+
+    stream_start_time = time.perf_counter()
+
+    # Base log metadata (task_id added after creation)
+    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}, "
+        f"user={user_id}, message_len={len(request.message)}",
+        extra={"json_fields": log_meta},
+    )
 
     session = await _validate_and_get_session(session_id, user_id)
+    logger.info(
+        f"[TIMING] session validated in {(time.perf_counter() - stream_start_time)*1000:.1f}ms",
+        extra={
+            "json_fields": {
+                **log_meta,
+                "duration_ms": (time.perf_counter() - stream_start_time) * 1000,
+            }
+        },
+    )
 
     # Create a task in the stream registry for reconnection support
     task_id = str(uuid_module.uuid4())
     operation_id = str(uuid_module.uuid4())
+    log_meta["task_id"] = task_id
+
+    task_create_start = time.perf_counter()
     await stream_registry.create_task(
         task_id=task_id,
         session_id=session_id,
@@ -280,14 +306,46 @@ async def stream_chat_post(
         tool_name="chat",
         operation_id=operation_id,
     )
+    logger.info(
+        f"[TIMING] create_task completed in {(time.perf_counter() - task_create_start)*1000:.1f}ms",
+        extra={
+            "json_fields": {
+                **log_meta,
+                "duration_ms": (time.perf_counter() - task_create_start) * 1000,
+            }
+        },
+    )
 
     # Background task that runs the AI generation independently of SSE connection
     async def run_ai_generation():
+        import time as time_module
+
+        gen_start_time = time_module.perf_counter()
+        logger.info(
+            f"[TIMING] run_ai_generation STARTED, task={task_id}, session={session_id}, user={user_id}",
+            extra={"json_fields": log_meta},
+        )
+        first_chunk_time, ttfc = None, None
+        chunk_count = 0
         try:
             # Emit a start event with task_id for reconnection
             start_chunk = StreamStart(messageId=task_id, taskId=task_id)
             await stream_registry.publish_chunk(task_id, start_chunk)
+            logger.info(
+                f"[TIMING] StreamStart published at {(time_module.perf_counter() - gen_start_time)*1000:.1f}ms",
+                extra={
+                    "json_fields": {
+                        **log_meta,
+                        "elapsed_ms": (time_module.perf_counter() - gen_start_time)
+                        * 1000,
+                    }
+                },
+            )
 
+            logger.info(
+                "[TIMING] Calling stream_chat_completion",
+                extra={"json_fields": log_meta},
+            )
             async for chunk in chat_service.stream_chat_completion(
                 session_id,
                 request.message,
@@ -296,54 +354,202 @@ async def stream_chat_post(
                 session=session,  # Pass pre-fetched session to avoid double-fetch
                 context=request.context,
             ):
+                chunk_count += 1
+                if first_chunk_time is None:
+                    first_chunk_time = time_module.perf_counter()
+                    ttfc = first_chunk_time - gen_start_time
+                    logger.info(
+                        f"[TIMING] FIRST AI CHUNK at {ttfc:.2f}s, type={type(chunk).__name__}",
+                        extra={
+                            "json_fields": {
+                                **log_meta,
+                                "chunk_type": type(chunk).__name__,
+                                "time_to_first_chunk_ms": ttfc * 1000,
+                            }
+                        },
+                    )
                 # Write to Redis (subscribers will receive via XREAD)
                 await stream_registry.publish_chunk(task_id, chunk)
 
-            # Mark task as completed
+            gen_end_time = time_module.perf_counter()
+            total_time = (gen_end_time - gen_start_time) * 1000
+            logger.info(
+                f"[TIMING] run_ai_generation FINISHED in {total_time/1000:.1f}s; "
+                f"task={task_id}, session={session_id}, "
+                f"ttfc={ttfc or -1:.2f}s, n_chunks={chunk_count}",
+                extra={
+                    "json_fields": {
+                        **log_meta,
+                        "total_time_ms": total_time,
+                        "time_to_first_chunk_ms": (
+                            ttfc * 1000 if ttfc is not None else None
+                        ),
+                        "n_chunks": chunk_count,
+                    }
+                },
+            )
+
             await stream_registry.mark_task_completed(task_id, "completed")
         except Exception as e:
+            elapsed = time_module.perf_counter() - gen_start_time
             logger.error(
-                f"Error in background AI generation for session {session_id}: {e}"
+                f"[TIMING] run_ai_generation ERROR after {elapsed:.2f}s: {e}",
+                extra={
+                    "json_fields": {
+                        **log_meta,
+                        "elapsed_ms": elapsed * 1000,
+                        "error": str(e),
+                    }
+                },
             )
             await stream_registry.mark_task_completed(task_id, "failed")
 
     # Start the AI generation in a background task
     bg_task = asyncio.create_task(run_ai_generation())
     await stream_registry.set_task_asyncio_task(task_id, bg_task)
+    setup_time = (time.perf_counter() - stream_start_time) * 1000
+    logger.info(
+        f"[TIMING] Background task started, setup={setup_time:.1f}ms",
+        extra={"json_fields": {**log_meta, "setup_time_ms": setup_time}},
+    )
 
     # SSE endpoint that subscribes to the task's stream
     async def event_generator() -> AsyncGenerator[str, None]:
+        import time as time_module
+
+        event_gen_start = time_module.perf_counter()
+        logger.info(
+            f"[TIMING] event_generator STARTED, task={task_id}, session={session_id}, "
+            f"user={user_id}",
+            extra={"json_fields": log_meta},
+        )
         subscriber_queue = None
+        first_chunk_yielded = False
+        chunks_yielded = 0
         try:
             # Subscribe to the task stream (this replays existing messages + live updates)
+            subscribe_start = time_module.perf_counter()
+            logger.info(
+                "[TIMING] Calling subscribe_to_task",
+                extra={"json_fields": log_meta},
+            )
             subscriber_queue = await stream_registry.subscribe_to_task(
                 task_id=task_id,
                 user_id=user_id,
                 last_message_id="0-0",  # Get all messages from the beginning
             )
+            subscribe_time = (time_module.perf_counter() - subscribe_start) * 1000
+            logger.info(
+                f"[TIMING] subscribe_to_task completed in {subscribe_time:.1f}ms, "
+                f"queue_ok={subscriber_queue is not None}",
+                extra={
+                    "json_fields": {
+                        **log_meta,
+                        "duration_ms": subscribe_time,
+                        "queue_obtained": subscriber_queue is not None,
+                    }
+                },
+            )
 
             if subscriber_queue is None:
+                logger.info(
+                    "[TIMING] subscriber_queue is None, yielding finish",
+                    extra={"json_fields": log_meta},
+                )
                 yield StreamFinish().to_sse()
                 yield "data: [DONE]\n\n"
                 return
 
             # Read from the subscriber queue and yield to SSE
+            logger.info(
+                "[TIMING] Starting to read from subscriber_queue",
+                extra={"json_fields": log_meta},
+            )
             while True:
                 try:
+                    queue_wait_start = time_module.perf_counter()
                     chunk = await asyncio.wait_for(subscriber_queue.get(), timeout=30.0)
+                    queue_wait_time = (
+                        time_module.perf_counter() - queue_wait_start
+                    ) * 1000
+                    chunks_yielded += 1
+
+                    if not first_chunk_yielded:
+                        first_chunk_yielded = True
+                        elapsed = time_module.perf_counter() - event_gen_start
+                        logger.info(
+                            f"[TIMING] FIRST CHUNK from queue at {elapsed:.2f}s, "
+                            f"type={type(chunk).__name__}, "
+                            f"wait={queue_wait_time:.1f}ms",
+                            extra={
+                                "json_fields": {
+                                    **log_meta,
+                                    "chunk_type": type(chunk).__name__,
+                                    "elapsed_ms": elapsed * 1000,
+                                    "queue_wait_ms": queue_wait_time,
+                                }
+                            },
+                        )
+                    elif chunks_yielded % 50 == 0:
+                        logger.info(
+                            f"[TIMING] Chunk #{chunks_yielded}, "
+                            f"type={type(chunk).__name__}",
+                            extra={
+                                "json_fields": {
+                                    **log_meta,
+                                    "chunk_number": chunks_yielded,
+                                    "chunk_type": type(chunk).__name__,
+                                }
+                            },
+                        )
+
                     yield chunk.to_sse()
 
                     # Check for finish signal
                     if isinstance(chunk, StreamFinish):
+                        total_time = time_module.perf_counter() - event_gen_start
+                        logger.info(
+                            f"[TIMING] StreamFinish received in {total_time:.2f}s; "
+                            f"n_chunks={chunks_yielded}",
+                            extra={
+                                "json_fields": {
+                                    **log_meta,
+                                    "chunks_yielded": chunks_yielded,
+                                    "total_time_ms": total_time * 1000,
+                                }
+                            },
+                        )
                         break
                 except asyncio.TimeoutError:
                     # Send heartbeat to keep connection alive
+                    logger.info(
+                        f"[TIMING] Heartbeat timeout, chunks_so_far={chunks_yielded}",
+                        extra={
+                            "json_fields": {**log_meta, "chunks_so_far": chunks_yielded}
+                        },
+                    )
                     yield StreamHeartbeat().to_sse()
 
         except GeneratorExit:
+            logger.info(
+                f"[TIMING] GeneratorExit (client disconnected), chunks={chunks_yielded}",
+                extra={
+                    "json_fields": {
+                        **log_meta,
+                        "chunks_yielded": chunks_yielded,
+                        "reason": "client_disconnect",
+                    }
+                },
+            )
             pass  # Client disconnected - background task continues
         except Exception as e:
-            logger.error(f"Error in SSE stream for task {task_id}: {e}")
+            elapsed = (time_module.perf_counter() - event_gen_start) * 1000
+            logger.error(
+                f"[TIMING] event_generator ERROR after {elapsed:.1f}ms: {e}",
+                extra={
+                    "json_fields": {**log_meta, "elapsed_ms": elapsed, "error": str(e)}
+                },
+            )
         finally:
             # Unsubscribe when client disconnects or stream ends to prevent resource leak
             if subscriber_queue is not None:
@@ -357,6 +563,18 @@ async def stream_chat_post(
                         exc_info=True,
                     )
             # AI SDK protocol termination - always yield even if unsubscribe fails
+            total_time = time_module.perf_counter() - event_gen_start
+            logger.info(
+                f"[TIMING] event_generator FINISHED in {total_time:.2f}s; "
+                f"task={task_id}, session={session_id}, n_chunks={chunks_yielded}",
+                extra={
+                    "json_fields": {
+                        **log_meta,
+                        "total_time_ms": total_time * 1000,
+                        "chunks_yielded": chunks_yielded,
+                    }
+                },
+            )
             yield "data: [DONE]\n\n"
 
     return StreamingResponse(
@@ -425,7 +643,7 @@ async def stream_chat_get(
             "Chat stream completed",
             extra={
                 "session_id": session_id,
-                "chunk_count": chunk_count,
+                "n_chunks": chunk_count,
                 "first_chunk_type": first_chunk_type,
             },
         )

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

@@ -371,21 +371,45 @@ async def stream_chat_completion(
         ValueError: If max_context_messages is exceeded
 
     """
+    completion_start = time.monotonic()
+
+    # Build log metadata for structured logging
+    log_meta = {"component": "ChatService", "session_id": session_id}
+    if user_id:
+        log_meta["user_id"] = user_id
+
     logger.info(
-        f"Streaming chat completion for session {session_id} for message {message} and user id {user_id}. Message is user message: {is_user_message}"
+        f"[TIMING] stream_chat_completion STARTED, session={session_id}, user={user_id}, "
+        f"message_len={len(message) if message else 0}, is_user={is_user_message}",
+        extra={
+            "json_fields": {
+                **log_meta,
+                "message_len": len(message) if message else 0,
+                "is_user_message": is_user_message,
+            }
+        },
     )
 
     # Only fetch from Redis if session not provided (initial call)
     if session is None:
+        fetch_start = time.monotonic()
         session = await get_chat_session(session_id, user_id)
+        fetch_time = (time.monotonic() - fetch_start) * 1000
         logger.info(
-            f"Fetched session from Redis: {session.session_id if session else 'None'}, "
-            f"message_count={len(session.messages) if session else 0}"
+            f"[TIMING] get_chat_session took {fetch_time:.1f}ms, "
+            f"n_messages={len(session.messages) if session else 0}",
+            extra={
+                "json_fields": {
+                    **log_meta,
+                    "duration_ms": fetch_time,
+                    "n_messages": len(session.messages) if session else 0,
+                }
+            },
         )
     else:
         logger.info(
-            f"Using provided session object: {session.session_id}, "
-            f"message_count={len(session.messages)}"
+            f"[TIMING] Using provided session, messages={len(session.messages)}",
+            extra={"json_fields": {**log_meta, "n_messages": len(session.messages)}},
         )
 
     if not session:
@@ -406,17 +430,25 @@ async def stream_chat_completion(
 
         # Track user message in PostHog
         if is_user_message:
+            posthog_start = time.monotonic()
             track_user_message(
                 user_id=user_id,
                 session_id=session_id,
                 message_length=len(message),
             )
+            posthog_time = (time.monotonic() - posthog_start) * 1000
+            logger.info(
+                f"[TIMING] track_user_message took {posthog_time:.1f}ms",
+                extra={"json_fields": {**log_meta, "duration_ms": posthog_time}},
+            )
 
-    logger.info(
-        f"Upserting session: {session.session_id} with user id {session.user_id}, "
-        f"message_count={len(session.messages)}"
-    )
+    upsert_start = time.monotonic()
     session = await upsert_chat_session(session)
+    upsert_time = (time.monotonic() - upsert_start) * 1000
+    logger.info(
+        f"[TIMING] upsert_chat_session took {upsert_time:.1f}ms",
+        extra={"json_fields": {**log_meta, "duration_ms": upsert_time}},
+    )
     assert session, "Session not found"
 
     # Generate title for new sessions on first user message (non-blocking)
@@ -454,7 +486,13 @@ async def stream_chat_completion(
             asyncio.create_task(_update_title())
 
     # Build system prompt with business understanding
+    prompt_start = time.monotonic()
     system_prompt, understanding = await _build_system_prompt(user_id)
+    prompt_time = (time.monotonic() - prompt_start) * 1000
+    logger.info(
+        f"[TIMING] _build_system_prompt took {prompt_time:.1f}ms",
+        extra={"json_fields": {**log_meta, "duration_ms": prompt_time}},
+    )
 
     # Initialize variables for streaming
     assistant_response = ChatMessage(
@@ -483,9 +521,18 @@ async def stream_chat_completion(
     text_block_id = str(uuid_module.uuid4())
 
     # Yield message start
+    setup_time = (time.monotonic() - completion_start) * 1000
+    logger.info(
+        f"[TIMING] Setup complete, yielding StreamStart at {setup_time:.1f}ms",
+        extra={"json_fields": {**log_meta, "setup_time_ms": setup_time}},
+    )
     yield StreamStart(messageId=message_id)
 
     try:
+        logger.info(
+            "[TIMING] Calling _stream_chat_chunks",
+            extra={"json_fields": log_meta},
+        )
         async for chunk in _stream_chat_chunks(
             session=session,
             tools=tools,
@@ -893,9 +940,21 @@ async def _stream_chat_chunks(
         SSE formatted JSON response objects
 
     """
+    import time as time_module
+
+    stream_chunks_start = time_module.perf_counter()
     model = config.model
 
-    logger.info("Starting pure chat stream")
+    # Build log metadata for structured logging
+    log_meta = {"component": "ChatService", "session_id": session.session_id}
+    if session.user_id:
+        log_meta["user_id"] = session.user_id
+
+    logger.info(
+        f"[TIMING] _stream_chat_chunks STARTED, session={session.session_id}, "
+        f"user={session.user_id}, n_messages={len(session.messages)}",
+        extra={"json_fields": {**log_meta, "n_messages": len(session.messages)}},
+    )
 
     messages = session.to_openai_messages()
     if system_prompt:
@@ -906,12 +965,18 @@ async def _stream_chat_chunks(
         messages = [system_message] + messages
 
     # Apply context window management
+    context_start = time_module.perf_counter()
     context_result = await _manage_context_window(
         messages=messages,
         model=model,
         api_key=config.api_key,
         base_url=config.base_url,
     )
+    context_time = (time_module.perf_counter() - context_start) * 1000
+    logger.info(
+        f"[TIMING] _manage_context_window took {context_time:.1f}ms",
+        extra={"json_fields": {**log_meta, "duration_ms": context_time}},
+    )
 
     if context_result.error:
         if "System prompt dropped" in context_result.error:
@@ -946,9 +1011,19 @@ async def _stream_chat_chunks(
 
         while retry_count <= MAX_RETRIES:
             try:
+                elapsed = (time_module.perf_counter() - stream_chunks_start) * 1000
+                retry_info = (
+                    f" (retry {retry_count}/{MAX_RETRIES})" if retry_count > 0 else ""
+                )
                 logger.info(
-                    f"Creating OpenAI chat completion stream..."
-                    f"{f' (retry {retry_count}/{MAX_RETRIES})' if retry_count > 0 else ''}"
+                    f"[TIMING] Creating OpenAI stream at {elapsed:.1f}ms{retry_info}",
+                    extra={
+                        "json_fields": {
+                            **log_meta,
+                            "elapsed_ms": elapsed,
+                            "retry_count": retry_count,
+                        }
+                    },
                 )
 
                 # Build extra_body for OpenRouter tracing and PostHog analytics
@@ -965,6 +1040,7 @@ async def _stream_chat_chunks(
                         :128
                     ]  # OpenRouter limit
 
+                api_call_start = time_module.perf_counter()
                 stream = await client.chat.completions.create(
                     model=model,
                     messages=cast(list[ChatCompletionMessageParam], messages),
@@ -974,6 +1050,11 @@ async def _stream_chat_chunks(
                     stream_options=ChatCompletionStreamOptionsParam(include_usage=True),
                     extra_body=extra_body,
                 )
+                api_init_time = (time_module.perf_counter() - api_call_start) * 1000
+                logger.info(
+                    f"[TIMING] OpenAI stream object returned in {api_init_time:.1f}ms",
+                    extra={"json_fields": {**log_meta, "duration_ms": api_init_time}},
+                )
 
                 # Variables to accumulate tool calls
                 tool_calls: list[dict[str, Any]] = []
@@ -984,10 +1065,13 @@ async def _stream_chat_chunks(
 
                 # Track if we've started the text block
                 text_started = False
+                first_content_chunk = True
+                chunk_count = 0
 
                 # Process the stream
                 chunk: ChatCompletionChunk
                 async for chunk in stream:
+                    chunk_count += 1
                     if chunk.usage:
                         yield StreamUsage(
                             promptTokens=chunk.usage.prompt_tokens,
@@ -1010,6 +1094,23 @@ async def _stream_chat_chunks(
                             if not text_started and text_block_id:
                                 yield StreamTextStart(id=text_block_id)
                                 text_started = True
+                            # Log timing for first content chunk
+                            if first_content_chunk:
+                                first_content_chunk = False
+                                ttfc = (
+                                    time_module.perf_counter() - api_call_start
+                                ) * 1000
+                                logger.info(
+                                    f"[TIMING] FIRST CONTENT CHUNK at {ttfc:.1f}ms "
+                                    f"(since API call), n_chunks={chunk_count}",
+                                    extra={
+                                        "json_fields": {
+                                            **log_meta,
+                                            "time_to_first_chunk_ms": ttfc,
+                                            "n_chunks": chunk_count,
+                                        }
+                                    },
+                                )
                             # Stream the text delta
                             text_response = StreamTextDelta(
                                 id=text_block_id or "",
@@ -1066,7 +1167,21 @@ async def _stream_chat_chunks(
                                         toolName=tool_calls[idx]["function"]["name"],
                                     )
                                     emitted_start_for_idx.add(idx)
-                logger.info(f"Stream complete. Finish reason: {finish_reason}")
+                stream_duration = time_module.perf_counter() - api_call_start
+                logger.info(
+                    f"[TIMING] OpenAI stream COMPLETE, finish_reason={finish_reason}, "
+                    f"duration={stream_duration:.2f}s, "
+                    f"n_chunks={chunk_count}, n_tool_calls={len(tool_calls)}",
+                    extra={
+                        "json_fields": {
+                            **log_meta,
+                            "stream_duration_ms": stream_duration * 1000,
+                            "finish_reason": finish_reason,
+                            "n_chunks": chunk_count,
+                            "n_tool_calls": len(tool_calls),
+                        }
+                    },
+                )
 
                 # Yield all accumulated tool calls after the stream is complete
                 # This ensures all tool call arguments have been fully received
@@ -1086,6 +1201,12 @@ async def _stream_chat_chunks(
                         # Re-raise to trigger retry logic in the parent function
                         raise
 
+                total_time = (time_module.perf_counter() - stream_chunks_start) * 1000
+                logger.info(
+                    f"[TIMING] _stream_chat_chunks COMPLETED in {total_time/1000:.1f}s; "
+                    f"session={session.session_id}, user={session.user_id}",
+                    extra={"json_fields": {**log_meta, "total_time_ms": total_time}},
+                )
                 yield StreamFinish()
                 return
             except Exception as e:

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

@@ -104,6 +104,24 @@ async def create_task(
     Returns:
         The created ActiveTask instance (metadata only)
     """
+    import time
+
+    start_time = time.perf_counter()
+
+    # Build log metadata for structured logging
+    log_meta = {
+        "component": "StreamRegistry",
+        "task_id": task_id,
+        "session_id": session_id,
+    }
+    if user_id:
+        log_meta["user_id"] = user_id
+
+    logger.info(
+        f"[TIMING] create_task STARTED, task={task_id}, session={session_id}, user={user_id}",
+        extra={"json_fields": log_meta},
+    )
+
     task = ActiveTask(
         task_id=task_id,
         session_id=session_id,
@@ -114,10 +132,18 @@ async def create_task(
     )
 
     # Store metadata in Redis
+    redis_start = time.perf_counter()
     redis = await get_redis_async()
+    redis_time = (time.perf_counter() - redis_start) * 1000
+    logger.info(
+        f"[TIMING] get_redis_async took {redis_time:.1f}ms",
+        extra={"json_fields": {**log_meta, "duration_ms": redis_time}},
+    )
+
     meta_key = _get_task_meta_key(task_id)
     op_key = _get_operation_mapping_key(operation_id)
 
+    hset_start = time.perf_counter()
     await redis.hset(  # type: ignore[misc]
         meta_key,
         mapping={
@@ -131,12 +157,22 @@ async def create_task(
             "created_at": task.created_at.isoformat(),
         },
     )
+    hset_time = (time.perf_counter() - hset_start) * 1000
+    logger.info(
+        f"[TIMING] redis.hset took {hset_time:.1f}ms",
+        extra={"json_fields": {**log_meta, "duration_ms": hset_time}},
+    )
+
     await redis.expire(meta_key, config.stream_ttl)
 
     # Create operation_id -> task_id mapping for webhook lookups
     await redis.set(op_key, task_id, ex=config.stream_ttl)
 
-    logger.debug(f"Created task {task_id} for session {session_id}")
+    total_time = (time.perf_counter() - start_time) * 1000
+    logger.info(
+        f"[TIMING] create_task COMPLETED in {total_time:.1f}ms; task={task_id}, session={session_id}",
+        extra={"json_fields": {**log_meta, "total_time_ms": total_time}},
+    )
 
     return task
 
@@ -156,26 +192,60 @@ async def publish_chunk(
     Returns:
         The Redis Stream message ID
     """
+    import time
+
+    start_time = time.perf_counter()
+    chunk_type = type(chunk).__name__
     chunk_json = chunk.model_dump_json()
     message_id = "0-0"
 
+    # Build log metadata
+    log_meta = {
+        "component": "StreamRegistry",
+        "task_id": task_id,
+        "chunk_type": chunk_type,
+    }
+
     try:
         redis = await get_redis_async()
         stream_key = _get_task_stream_key(task_id)
 
         # Write to Redis Stream for persistence and real-time delivery
+        xadd_start = time.perf_counter()
         raw_id = await redis.xadd(
             stream_key,
             {"data": chunk_json},
             maxlen=config.stream_max_length,
         )
+        xadd_time = (time.perf_counter() - xadd_start) * 1000
         message_id = raw_id if isinstance(raw_id, str) else raw_id.decode()
 
         # Set TTL on stream to match task metadata TTL
         await redis.expire(stream_key, config.stream_ttl)
+
+        total_time = (time.perf_counter() - start_time) * 1000
+        # Only log timing for significant chunks or slow operations
+        if (
+            chunk_type
+            in ("StreamStart", "StreamFinish", "StreamTextStart", "StreamTextEnd")
+            or total_time > 50
+        ):
+            logger.info(
+                f"[TIMING] publish_chunk {chunk_type} in {total_time:.1f}ms (xadd={xadd_time:.1f}ms)",
+                extra={
+                    "json_fields": {
+                        **log_meta,
+                        "total_time_ms": total_time,
+                        "xadd_time_ms": xadd_time,
+                        "message_id": message_id,
+                    }
+                },
+            )
     except Exception as e:
+        elapsed = (time.perf_counter() - start_time) * 1000
         logger.error(
-            f"Failed to publish chunk for task {task_id}: {e}",
+            f"[TIMING] Failed to publish chunk {chunk_type} after {elapsed:.1f}ms: {e}",
+            extra={"json_fields": {**log_meta, "elapsed_ms": elapsed, "error": str(e)}},
             exc_info=True,
         )
 
@@ -200,24 +270,61 @@ async def subscribe_to_task(
         An asyncio Queue that will receive stream chunks, or None if task not found
         or user doesn't have access
     """
+    import time
+
+    start_time = time.perf_counter()
+
+    # Build log metadata
+    log_meta = {"component": "StreamRegistry", "task_id": task_id}
+    if user_id:
+        log_meta["user_id"] = user_id
+
+    logger.info(
+        f"[TIMING] subscribe_to_task STARTED, task={task_id}, user={user_id}, last_msg={last_message_id}",
+        extra={"json_fields": {**log_meta, "last_message_id": last_message_id}},
+    )
+
+    redis_start = time.perf_counter()
     redis = await get_redis_async()
     meta_key = _get_task_meta_key(task_id)
     meta: dict[Any, Any] = await redis.hgetall(meta_key)  # type: ignore[misc]
+    hgetall_time = (time.perf_counter() - redis_start) * 1000
+    logger.info(
+        f"[TIMING] Redis hgetall took {hgetall_time:.1f}ms",
+        extra={"json_fields": {**log_meta, "duration_ms": hgetall_time}},
+    )
 
     if not meta:
-        logger.debug(f"Task {task_id} not found in Redis")
+        elapsed = (time.perf_counter() - start_time) * 1000
+        logger.info(
+            f"[TIMING] Task not found in Redis after {elapsed:.1f}ms",
+            extra={
+                "json_fields": {
+                    **log_meta,
+                    "elapsed_ms": elapsed,
+                    "reason": "task_not_found",
+                }
+            },
+        )
         return None
 
     # Note: Redis client uses decode_responses=True, so keys are strings
     task_status = meta.get("status", "")
     task_user_id = meta.get("user_id", "") or None
+    log_meta["session_id"] = meta.get("session_id", "")
 
     # Validate ownership - if task has an owner, requester must match
     if task_user_id:
         if user_id != task_user_id:
             logger.warning(
-                f"User {user_id} denied access to task {task_id} "
-                f"owned by {task_user_id}"
+                f"[TIMING] Access denied: user {user_id} tried to access task owned by {task_user_id}",
+                extra={
+                    "json_fields": {
+                        **log_meta,
+                        "task_owner": task_user_id,
+                        "reason": "access_denied",
+                    }
+                },
             )
             return None
 
@@ -225,7 +332,19 @@ async def subscribe_to_task(
     stream_key = _get_task_stream_key(task_id)
 
     # Step 1: Replay messages from Redis Stream
+    xread_start = time.perf_counter()
     messages = await redis.xread({stream_key: last_message_id}, block=0, count=1000)
+    xread_time = (time.perf_counter() - xread_start) * 1000
+    logger.info(
+        f"[TIMING] Redis xread (replay) took {xread_time:.1f}ms, status={task_status}",
+        extra={
+            "json_fields": {
+                **log_meta,
+                "duration_ms": xread_time,
+                "task_status": task_status,
+            }
+        },
+    )
 
     replayed_count = 0
     replay_last_id = last_message_id
@@ -244,19 +363,48 @@ async def subscribe_to_task(
                     except Exception as e:
                         logger.warning(f"Failed to replay message: {e}")
 
-    logger.debug(f"Task {task_id}: replayed {replayed_count} messages")
+    logger.info(
+        f"[TIMING] Replayed {replayed_count} messages, last_id={replay_last_id}",
+        extra={
+            "json_fields": {
+                **log_meta,
+                "n_messages_replayed": replayed_count,
+                "replay_last_id": replay_last_id,
+            }
+        },
+    )
 
     # Step 2: If task is still running, start stream listener for live updates
     if task_status == "running":
+        logger.info(
+            "[TIMING] Task still running, starting _stream_listener",
+            extra={"json_fields": {**log_meta, "task_status": task_status}},
+        )
         listener_task = asyncio.create_task(
-            _stream_listener(task_id, subscriber_queue, replay_last_id)
+            _stream_listener(task_id, subscriber_queue, replay_last_id, log_meta)
         )
         # Track listener task for cleanup on unsubscribe
         _listener_tasks[id(subscriber_queue)] = (task_id, listener_task)
     else:
         # Task is completed/failed - add finish marker
+        logger.info(
+            f"[TIMING] Task already {task_status}, adding StreamFinish",
+            extra={"json_fields": {**log_meta, "task_status": task_status}},
+        )
         await subscriber_queue.put(StreamFinish())
 
+    total_time = (time.perf_counter() - start_time) * 1000
+    logger.info(
+        f"[TIMING] subscribe_to_task COMPLETED in {total_time:.1f}ms; task={task_id}, "
+        f"n_messages_replayed={replayed_count}",
+        extra={
+            "json_fields": {
+                **log_meta,
+                "total_time_ms": total_time,
+                "n_messages_replayed": replayed_count,
+            }
+        },
+    )
     return subscriber_queue
 
 
@@ -264,6 +412,7 @@ async def _stream_listener(
     task_id: str,
     subscriber_queue: asyncio.Queue[StreamBaseResponse],
     last_replayed_id: str,
+    log_meta: dict | None = None,
 ) -> None:
     """Listen to Redis Stream for new messages using blocking XREAD.
 
@@ -274,10 +423,27 @@ async def _stream_listener(
         task_id: Task ID to listen for
         subscriber_queue: Queue to deliver messages to
         last_replayed_id: Last message ID from replay (continue from here)
+        log_meta: Structured logging metadata
     """
+    import time
+
+    start_time = time.perf_counter()
+
+    # Use provided log_meta or build minimal one
+    if log_meta is None:
+        log_meta = {"component": "StreamRegistry", "task_id": task_id}
+
+    logger.info(
+        f"[TIMING] _stream_listener STARTED, task={task_id}, last_id={last_replayed_id}",
+        extra={"json_fields": {**log_meta, "last_replayed_id": last_replayed_id}},
+    )
+
     queue_id = id(subscriber_queue)
     # Track the last successfully delivered message ID for recovery hints
     last_delivered_id = last_replayed_id
+    messages_delivered = 0
+    first_message_time = None
+    xread_count = 0
 
     try:
         redis = await get_redis_async()
@@ -287,9 +453,39 @@ async def _stream_listener(
         while True:
             # Block for up to 30 seconds waiting for new messages
             # This allows periodic checking if task is still running
+            xread_start = time.perf_counter()
+            xread_count += 1
             messages = await redis.xread(
                 {stream_key: current_id}, block=30000, count=100
             )
+            xread_time = (time.perf_counter() - xread_start) * 1000
+
+            if messages:
+                msg_count = sum(len(msgs) for _, msgs in messages)
+                logger.info(
+                    f"[TIMING] xread #{xread_count} returned {msg_count} messages in {xread_time:.1f}ms",
+                    extra={
+                        "json_fields": {
+                            **log_meta,
+                            "xread_count": xread_count,
+                            "n_messages": msg_count,
+                            "duration_ms": xread_time,
+                        }
+                    },
+                )
+            elif xread_time > 1000:
+                # Only log timeouts (30s blocking)
+                logger.info(
+                    f"[TIMING] xread #{xread_count} timeout after {xread_time:.1f}ms",
+                    extra={
+                        "json_fields": {
+                            **log_meta,
+                            "xread_count": xread_count,
+                            "duration_ms": xread_time,
+                            "reason": "timeout",
+                        }
+                    },
+                )
 
             if not messages:
                 # Timeout - check if task is still running
@@ -326,10 +522,30 @@ async def _stream_listener(
                                 )
                                 # Update last delivered ID on successful delivery
                                 last_delivered_id = current_id
+                                messages_delivered += 1
+                                if first_message_time is None:
+                                    first_message_time = time.perf_counter()
+                                    elapsed = (first_message_time - start_time) * 1000
+                                    logger.info(
+                                        f"[TIMING] FIRST live message at {elapsed:.1f}ms, type={type(chunk).__name__}",
+                                        extra={
+                                            "json_fields": {
+                                                **log_meta,
+                                                "elapsed_ms": elapsed,
+                                                "chunk_type": type(chunk).__name__,
+                                            }
+                                        },
+                                    )
                             except asyncio.TimeoutError:
                                 logger.warning(
-                                    f"Subscriber queue full for task {task_id}, "
-                                    f"message delivery timed out after {QUEUE_PUT_TIMEOUT}s"
+                                    f"[TIMING] Subscriber queue full, delivery timed out after {QUEUE_PUT_TIMEOUT}s",
+                                    extra={
+                                        "json_fields": {
+                                            **log_meta,
+                                            "timeout_s": QUEUE_PUT_TIMEOUT,
+                                            "reason": "queue_full",
+                                        }
+                                    },
                                 )
                                 # Send overflow error with recovery info
                                 try:
@@ -351,15 +567,44 @@ async def _stream_listener(
 
                             # Stop listening on finish
                             if isinstance(chunk, StreamFinish):
+                                total_time = (time.perf_counter() - start_time) * 1000
+                                logger.info(
+                                    f"[TIMING] StreamFinish received in {total_time/1000:.1f}s; delivered={messages_delivered}",
+                                    extra={
+                                        "json_fields": {
+                                            **log_meta,
+                                            "total_time_ms": total_time,
+                                            "messages_delivered": messages_delivered,
+                                        }
+                                    },
+                                )
                                 return
                     except Exception as e:
-                        logger.warning(f"Error processing stream message: {e}")
+                        logger.warning(
+                            f"Error processing stream message: {e}",
+                            extra={"json_fields": {**log_meta, "error": str(e)}},
+                        )
 
     except asyncio.CancelledError:
-        logger.debug(f"Stream listener cancelled for task {task_id}")
+        elapsed = (time.perf_counter() - start_time) * 1000
+        logger.info(
+            f"[TIMING] _stream_listener CANCELLED after {elapsed:.1f}ms, delivered={messages_delivered}",
+            extra={
+                "json_fields": {
+                    **log_meta,
+                    "elapsed_ms": elapsed,
+                    "messages_delivered": messages_delivered,
+                    "reason": "cancelled",
+                }
+            },
+        )
         raise  # Re-raise to propagate cancellation
     except Exception as e:
-        logger.error(f"Stream listener error for task {task_id}: {e}")
+        elapsed = (time.perf_counter() - start_time) * 1000
+        logger.error(
+            f"[TIMING] _stream_listener ERROR after {elapsed:.1f}ms: {e}",
+            extra={"json_fields": {**log_meta, "elapsed_ms": elapsed, "error": str(e)}},
+        )
         # On error, send finish to unblock subscriber
         try:
             await asyncio.wait_for(
@@ -368,10 +613,24 @@ async def _stream_listener(
             )
         except (asyncio.TimeoutError, asyncio.QueueFull):
             logger.warning(
-                f"Could not deliver finish event for task {task_id} after error"
+                "Could not deliver finish event after error",
+                extra={"json_fields": log_meta},
             )
     finally:
         # Clean up listener task mapping on exit
+        total_time = (time.perf_counter() - start_time) * 1000
+        logger.info(
+            f"[TIMING] _stream_listener FINISHED in {total_time/1000:.1f}s; task={task_id}, "
+            f"delivered={messages_delivered}, xread_count={xread_count}",
+            extra={
+                "json_fields": {
+                    **log_meta,
+                    "total_time_ms": total_time,
+                    "messages_delivered": messages_delivered,
+                    "xread_count": xread_count,
+                }
+            },
+        )
         _listener_tasks.pop(queue_id, None)
 
 

autogpt_platform/backend/backend/api/features/chat/tools/find_block.py

@@ -13,10 +13,32 @@ from backend.api.features.chat.tools.models import (
     NoResultsResponse,
 )
 from backend.api.features.store.hybrid_search import unified_hybrid_search
-from backend.data.block import get_block
+from backend.data.block import BlockType, get_block
 
 logger = logging.getLogger(__name__)
 
+_TARGET_RESULTS = 10
+# Over-fetch to compensate for post-hoc filtering of graph-only blocks.
+# 40 is 2x current removed; speed of query 10 vs 40 is minimial
+_OVERFETCH_PAGE_SIZE = 40
+
+# Block types that only work within graphs and cannot run standalone in CoPilot.
+COPILOT_EXCLUDED_BLOCK_TYPES = {
+    BlockType.INPUT,  # Graph interface definition - data enters via chat, not graph inputs
+    BlockType.OUTPUT,  # Graph interface definition - data exits via chat, not graph outputs
+    BlockType.WEBHOOK,  # Wait for external events - would hang forever in CoPilot
+    BlockType.WEBHOOK_MANUAL,  # Same as WEBHOOK
+    BlockType.NOTE,  # Visual annotation only - no runtime behavior
+    BlockType.HUMAN_IN_THE_LOOP,  # Pauses for human approval - CoPilot IS human-in-the-loop
+    BlockType.AGENT,  # AgentExecutorBlock requires execution_context - use run_agent tool
+}
+
+# Specific block IDs excluded from CoPilot (STANDARD type but still require graph context)
+COPILOT_EXCLUDED_BLOCK_IDS = {
+    # SmartDecisionMakerBlock - dynamically discovers downstream blocks via graph topology
+    "3b191d9f-356f-482d-8238-ba04b6d18381",
+}
+
 
 class FindBlockTool(BaseTool):
     """Tool for searching available blocks."""
@@ -88,7 +110,7 @@ class FindBlockTool(BaseTool):
                 query=query,
                 content_types=[ContentType.BLOCK],
                 page=1,
-                page_size=10,
+                page_size=_OVERFETCH_PAGE_SIZE,
             )
 
             if not results:
@@ -108,60 +130,90 @@ class FindBlockTool(BaseTool):
                 block = get_block(block_id)
 
                 # Skip disabled blocks
-                if block and not block.disabled:
-                    # Get input/output schemas
-                    input_schema = {}
-                    output_schema = {}
-                    try:
-                        input_schema = block.input_schema.jsonschema()
-                    except Exception:
-                        pass
-                    try:
-                        output_schema = block.output_schema.jsonschema()
-                    except Exception:
-                        pass
+                if not block or block.disabled:
+                    continue
 
-                    # Get categories from block instance
-                    categories = []
-                    if hasattr(block, "categories") and block.categories:
-                        categories = [cat.value for cat in block.categories]
+                # Skip blocks excluded from CoPilot (graph-only blocks)
+                if (
+                    block.block_type in COPILOT_EXCLUDED_BLOCK_TYPES
+                    or block.id in COPILOT_EXCLUDED_BLOCK_IDS
+                ):
+                    continue
 
-                    # Extract required inputs for easier use
-                    required_inputs: list[BlockInputFieldInfo] = []
-                    if input_schema:
-                        properties = input_schema.get("properties", {})
-                        required_fields = set(input_schema.get("required", []))
-                        # Get credential field names to exclude from required inputs
-                        credentials_fields = set(
-                            block.input_schema.get_credentials_fields().keys()
-                        )
-
-                        for field_name, field_schema in properties.items():
-                            # Skip credential fields - they're handled separately
-                            if field_name in credentials_fields:
-                                continue
-
-                            required_inputs.append(
-                                BlockInputFieldInfo(
-                                    name=field_name,
-                                    type=field_schema.get("type", "string"),
-                                    description=field_schema.get("description", ""),
-                                    required=field_name in required_fields,
-                                    default=field_schema.get("default"),
-                                )
-                            )
-
-                    blocks.append(
-                        BlockInfoSummary(
-                            id=block_id,
-                            name=block.name,
-                            description=block.description or "",
-                            categories=categories,
-                            input_schema=input_schema,
-                            output_schema=output_schema,
-                            required_inputs=required_inputs,
-                        )
+                # Get input/output schemas
+                input_schema = {}
+                output_schema = {}
+                try:
+                    input_schema = block.input_schema.jsonschema()
+                except Exception as e:
+                    logger.debug(
+                        "Failed to generate input schema for block %s: %s",
+                        block_id,
+                        e,
                     )
+                try:
+                    output_schema = block.output_schema.jsonschema()
+                except Exception as e:
+                    logger.debug(
+                        "Failed to generate output schema for block %s: %s",
+                        block_id,
+                        e,
+                    )
+
+                # Get categories from block instance
+                categories = []
+                if hasattr(block, "categories") and block.categories:
+                    categories = [cat.value for cat in block.categories]
+
+                # Extract required inputs for easier use
+                required_inputs: list[BlockInputFieldInfo] = []
+                if input_schema:
+                    properties = input_schema.get("properties", {})
+                    required_fields = set(input_schema.get("required", []))
+                    # Get credential field names to exclude from required inputs
+                    credentials_fields = set(
+                        block.input_schema.get_credentials_fields().keys()
+                    )
+
+                    for field_name, field_schema in properties.items():
+                        # Skip credential fields - they're handled separately
+                        if field_name in credentials_fields:
+                            continue
+
+                        required_inputs.append(
+                            BlockInputFieldInfo(
+                                name=field_name,
+                                type=field_schema.get("type", "string"),
+                                description=field_schema.get("description", ""),
+                                required=field_name in required_fields,
+                                default=field_schema.get("default"),
+                            )
+                        )
+
+                blocks.append(
+                    BlockInfoSummary(
+                        id=block_id,
+                        name=block.name,
+                        description=block.description or "",
+                        categories=categories,
+                        input_schema=input_schema,
+                        output_schema=output_schema,
+                        required_inputs=required_inputs,
+                    )
+                )
+
+                if len(blocks) >= _TARGET_RESULTS:
+                    break
+
+            if blocks and len(blocks) < _TARGET_RESULTS:
+                logger.debug(
+                    "find_block returned %d/%d results for query '%s' "
+                    "(filtered %d excluded/disabled blocks)",
+                    len(blocks),
+                    _TARGET_RESULTS,
+                    query,
+                    len(results) - len(blocks),
+                )
 
             if not blocks:
                 return NoResultsResponse(

autogpt_platform/backend/backend/api/features/chat/tools/find_block_test.py

@@ -0,0 +1,139 @@
+"""Tests for block filtering in FindBlockTool."""
+
+from unittest.mock import AsyncMock, MagicMock, patch
+
+import pytest
+
+from backend.api.features.chat.tools.find_block import (
+    COPILOT_EXCLUDED_BLOCK_IDS,
+    COPILOT_EXCLUDED_BLOCK_TYPES,
+    FindBlockTool,
+)
+from backend.api.features.chat.tools.models import BlockListResponse
+from backend.data.block import BlockType
+
+from ._test_data import make_session
+
+_TEST_USER_ID = "test-user-find-block"
+
+
+def make_mock_block(
+    block_id: str, name: str, block_type: BlockType, disabled: bool = False
+):
+    """Create a mock block for testing."""
+    mock = MagicMock()
+    mock.id = block_id
+    mock.name = name
+    mock.description = f"{name} description"
+    mock.block_type = block_type
+    mock.disabled = disabled
+    mock.input_schema = MagicMock()
+    mock.input_schema.jsonschema.return_value = {"properties": {}, "required": []}
+    mock.input_schema.get_credentials_fields.return_value = {}
+    mock.output_schema = MagicMock()
+    mock.output_schema.jsonschema.return_value = {}
+    mock.categories = []
+    return mock
+
+
+class TestFindBlockFiltering:
+    """Tests for block filtering in FindBlockTool."""
+
+    def test_excluded_block_types_contains_expected_types(self):
+        """Verify COPILOT_EXCLUDED_BLOCK_TYPES contains all graph-only types."""
+        assert BlockType.INPUT in COPILOT_EXCLUDED_BLOCK_TYPES
+        assert BlockType.OUTPUT in COPILOT_EXCLUDED_BLOCK_TYPES
+        assert BlockType.WEBHOOK in COPILOT_EXCLUDED_BLOCK_TYPES
+        assert BlockType.WEBHOOK_MANUAL in COPILOT_EXCLUDED_BLOCK_TYPES
+        assert BlockType.NOTE in COPILOT_EXCLUDED_BLOCK_TYPES
+        assert BlockType.HUMAN_IN_THE_LOOP in COPILOT_EXCLUDED_BLOCK_TYPES
+        assert BlockType.AGENT in COPILOT_EXCLUDED_BLOCK_TYPES
+
+    def test_excluded_block_ids_contains_smart_decision_maker(self):
+        """Verify SmartDecisionMakerBlock is in COPILOT_EXCLUDED_BLOCK_IDS."""
+        assert "3b191d9f-356f-482d-8238-ba04b6d18381" in COPILOT_EXCLUDED_BLOCK_IDS
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_excluded_block_type_filtered_from_results(self):
+        """Verify blocks with excluded BlockTypes are filtered from search results."""
+        session = make_session(user_id=_TEST_USER_ID)
+
+        # Mock search returns an INPUT block (excluded) and a STANDARD block (included)
+        search_results = [
+            {"content_id": "input-block-id", "score": 0.9},
+            {"content_id": "standard-block-id", "score": 0.8},
+        ]
+
+        input_block = make_mock_block("input-block-id", "Input Block", BlockType.INPUT)
+        standard_block = make_mock_block(
+            "standard-block-id", "HTTP Request", BlockType.STANDARD
+        )
+
+        def mock_get_block(block_id):
+            return {
+                "input-block-id": input_block,
+                "standard-block-id": standard_block,
+            }.get(block_id)
+
+        with patch(
+            "backend.api.features.chat.tools.find_block.unified_hybrid_search",
+            new_callable=AsyncMock,
+            return_value=(search_results, 2),
+        ):
+            with patch(
+                "backend.api.features.chat.tools.find_block.get_block",
+                side_effect=mock_get_block,
+            ):
+                tool = FindBlockTool()
+                response = await tool._execute(
+                    user_id=_TEST_USER_ID, session=session, query="test"
+                )
+
+        # Should only return the standard block, not the INPUT block
+        assert isinstance(response, BlockListResponse)
+        assert len(response.blocks) == 1
+        assert response.blocks[0].id == "standard-block-id"
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_excluded_block_id_filtered_from_results(self):
+        """Verify SmartDecisionMakerBlock is filtered from search results."""
+        session = make_session(user_id=_TEST_USER_ID)
+
+        smart_decision_id = "3b191d9f-356f-482d-8238-ba04b6d18381"
+        search_results = [
+            {"content_id": smart_decision_id, "score": 0.9},
+            {"content_id": "normal-block-id", "score": 0.8},
+        ]
+
+        # SmartDecisionMakerBlock has STANDARD type but is excluded by ID
+        smart_block = make_mock_block(
+            smart_decision_id, "Smart Decision Maker", BlockType.STANDARD
+        )
+        normal_block = make_mock_block(
+            "normal-block-id", "Normal Block", BlockType.STANDARD
+        )
+
+        def mock_get_block(block_id):
+            return {
+                smart_decision_id: smart_block,
+                "normal-block-id": normal_block,
+            }.get(block_id)
+
+        with patch(
+            "backend.api.features.chat.tools.find_block.unified_hybrid_search",
+            new_callable=AsyncMock,
+            return_value=(search_results, 2),
+        ):
+            with patch(
+                "backend.api.features.chat.tools.find_block.get_block",
+                side_effect=mock_get_block,
+            ):
+                tool = FindBlockTool()
+                response = await tool._execute(
+                    user_id=_TEST_USER_ID, session=session, query="decision"
+                )
+
+        # Should only return normal block, not SmartDecisionMakerBlock
+        assert isinstance(response, BlockListResponse)
+        assert len(response.blocks) == 1
+        assert response.blocks[0].id == "normal-block-id"

autogpt_platform/backend/backend/api/features/chat/tools/helpers.py

@@ -0,0 +1,29 @@
+"""Shared helpers for chat tools."""
+
+from typing import Any
+
+
+def get_inputs_from_schema(
+    input_schema: dict[str, Any],
+    exclude_fields: set[str] | None = None,
+) -> list[dict[str, Any]]:
+    """Extract input field info from JSON schema."""
+    if not isinstance(input_schema, dict):
+        return []
+
+    exclude = exclude_fields or set()
+    properties = input_schema.get("properties", {})
+    required = set(input_schema.get("required", []))
+
+    return [
+        {
+            "name": name,
+            "title": schema.get("title", name),
+            "type": schema.get("type", "string"),
+            "description": schema.get("description", ""),
+            "required": name in required,
+            "default": schema.get("default"),
+        }
+        for name, schema in properties.items()
+        if name not in exclude
+    ]

autogpt_platform/backend/backend/api/features/chat/tools/run_agent.py

@@ -24,6 +24,7 @@ from backend.util.timezone_utils import (
 )
 
 from .base import BaseTool
+from .helpers import get_inputs_from_schema
 from .models import (
     AgentDetails,
     AgentDetailsResponse,
@@ -261,7 +262,7 @@ class RunAgentTool(BaseTool):
                         ),
                         requirements={
                             "credentials": requirements_creds_list,
-                            "inputs": self._get_inputs_list(graph.input_schema),
+                            "inputs": get_inputs_from_schema(graph.input_schema),
                             "execution_modes": self._get_execution_modes(graph),
                         },
                     ),
@@ -369,22 +370,6 @@ class RunAgentTool(BaseTool):
                 session_id=session_id,
             )
 
-    def _get_inputs_list(self, input_schema: dict[str, Any]) -> list[dict[str, Any]]:
-        """Extract inputs list from schema."""
-        inputs_list = []
-        if isinstance(input_schema, dict) and "properties" in input_schema:
-            for field_name, field_schema in input_schema["properties"].items():
-                inputs_list.append(
-                    {
-                        "name": field_name,
-                        "title": field_schema.get("title", field_name),
-                        "type": field_schema.get("type", "string"),
-                        "description": field_schema.get("description", ""),
-                        "required": field_name in input_schema.get("required", []),
-                    }
-                )
-        return inputs_list
-
     def _get_execution_modes(self, graph: GraphModel) -> list[str]:
         """Get available execution modes for the graph."""
         trigger_info = graph.trigger_setup_info
@@ -398,7 +383,7 @@ class RunAgentTool(BaseTool):
         suffix: str,
     ) -> str:
         """Build a message describing available inputs for an agent."""
-        inputs_list = self._get_inputs_list(graph.input_schema)
+        inputs_list = get_inputs_from_schema(graph.input_schema)
         required_names = [i["name"] for i in inputs_list if i["required"]]
         optional_names = [i["name"] for i in inputs_list if not i["required"]]
 

autogpt_platform/backend/backend/api/features/chat/tools/run_block.py

@@ -8,14 +8,19 @@ from typing import Any
 from pydantic_core import PydanticUndefined
 
 from backend.api.features.chat.model import ChatSession
-from backend.data.block import get_block
+from backend.api.features.chat.tools.find_block import (
+    COPILOT_EXCLUDED_BLOCK_IDS,
+    COPILOT_EXCLUDED_BLOCK_TYPES,
+)
+from backend.data.block import AnyBlockSchema, get_block
 from backend.data.execution import ExecutionContext
-from backend.data.model import CredentialsMetaInput
+from backend.data.model import CredentialsFieldInfo, CredentialsMetaInput
 from backend.data.workspace import get_or_create_workspace
 from backend.integrations.creds_manager import IntegrationCredentialsManager
 from backend.util.exceptions import BlockError
 
 from .base import BaseTool
+from .helpers import get_inputs_from_schema
 from .models import (
     BlockOutputResponse,
     ErrorResponse,
@@ -24,7 +29,10 @@ from .models import (
     ToolResponseBase,
     UserReadiness,
 )
-from .utils import build_missing_credentials_from_field_info
+from .utils import (
+    build_missing_credentials_from_field_info,
+    match_credentials_to_requirements,
+)
 
 logger = logging.getLogger(__name__)
 
@@ -73,91 +81,6 @@ class RunBlockTool(BaseTool):
     def requires_auth(self) -> bool:
         return True
 
-    async def _check_block_credentials(
-        self,
-        user_id: str,
-        block: Any,
-        input_data: dict[str, Any] | None = None,
-    ) -> tuple[dict[str, CredentialsMetaInput], list[CredentialsMetaInput]]:
-        """
-        Check if user has required credentials for a block.
-
-        Args:
-            user_id: User ID
-            block: Block to check credentials for
-            input_data: Input data for the block (used to determine provider via discriminator)
-
-        Returns:
-            tuple[matched_credentials, missing_credentials]
-        """
-        matched_credentials: dict[str, CredentialsMetaInput] = {}
-        missing_credentials: list[CredentialsMetaInput] = []
-        input_data = input_data or {}
-
-        # Get credential field info from block's input schema
-        credentials_fields_info = block.input_schema.get_credentials_fields_info()
-
-        if not credentials_fields_info:
-            return matched_credentials, missing_credentials
-
-        # Get user's available credentials
-        creds_manager = IntegrationCredentialsManager()
-        available_creds = await creds_manager.store.get_all_creds(user_id)
-
-        for field_name, field_info in credentials_fields_info.items():
-            effective_field_info = field_info
-            if field_info.discriminator and field_info.discriminator_mapping:
-                # Get discriminator from input, falling back to schema default
-                discriminator_value = input_data.get(field_info.discriminator)
-                if discriminator_value is None:
-                    field = block.input_schema.model_fields.get(
-                        field_info.discriminator
-                    )
-                    if field and field.default is not PydanticUndefined:
-                        discriminator_value = field.default
-
-                if (
-                    discriminator_value
-                    and discriminator_value in field_info.discriminator_mapping
-                ):
-                    effective_field_info = field_info.discriminate(discriminator_value)
-                    logger.debug(
-                        f"Discriminated provider for {field_name}: "
-                        f"{discriminator_value} -> {effective_field_info.provider}"
-                    )
-
-            matching_cred = next(
-                (
-                    cred
-                    for cred in available_creds
-                    if cred.provider in effective_field_info.provider
-                    and cred.type in effective_field_info.supported_types
-                ),
-                None,
-            )
-
-            if matching_cred:
-                matched_credentials[field_name] = CredentialsMetaInput(
-                    id=matching_cred.id,
-                    provider=matching_cred.provider,  # type: ignore
-                    type=matching_cred.type,
-                    title=matching_cred.title,
-                )
-            else:
-                # Create a placeholder for the missing credential
-                provider = next(iter(effective_field_info.provider), "unknown")
-                cred_type = next(iter(effective_field_info.supported_types), "api_key")
-                missing_credentials.append(
-                    CredentialsMetaInput(
-                        id=field_name,
-                        provider=provider,  # type: ignore
-                        type=cred_type,  # type: ignore
-                        title=field_name.replace("_", " ").title(),
-                    )
-                )
-
-        return matched_credentials, missing_credentials
-
     async def _execute(
         self,
         user_id: str | None,
@@ -212,11 +135,24 @@ class RunBlockTool(BaseTool):
                 session_id=session_id,
             )
 
+        # Check if block is excluded from CoPilot (graph-only blocks)
+        if (
+            block.block_type in COPILOT_EXCLUDED_BLOCK_TYPES
+            or block.id in COPILOT_EXCLUDED_BLOCK_IDS
+        ):
+            return ErrorResponse(
+                message=(
+                    f"Block '{block.name}' cannot be run directly in CoPilot. "
+                    "This block is designed for use within graphs only."
+                ),
+                session_id=session_id,
+            )
+
         logger.info(f"Executing block {block.name} ({block_id}) for user {user_id}")
 
         creds_manager = IntegrationCredentialsManager()
-        matched_credentials, missing_credentials = await self._check_block_credentials(
-            user_id, block, input_data
+        matched_credentials, missing_credentials = (
+            await self._resolve_block_credentials(user_id, block, input_data)
         )
 
         if missing_credentials:
@@ -345,29 +281,75 @@ class RunBlockTool(BaseTool):
                 session_id=session_id,
             )
 
-    def _get_inputs_list(self, block: Any) -> list[dict[str, Any]]:
+    async def _resolve_block_credentials(
+        self,
+        user_id: str,
+        block: AnyBlockSchema,
+        input_data: dict[str, Any] | None = None,
+    ) -> tuple[dict[str, CredentialsMetaInput], list[CredentialsMetaInput]]:
+        """
+        Resolve credentials for a block by matching user's available credentials.
+
+        Args:
+            user_id: User ID
+            block: Block to resolve credentials for
+            input_data: Input data for the block (used to determine provider via discriminator)
+
+        Returns:
+            tuple of (matched_credentials, missing_credentials) - matched credentials
+            are used for block execution, missing ones indicate setup requirements.
+        """
+        input_data = input_data or {}
+        requirements = self._resolve_discriminated_credentials(block, input_data)
+
+        if not requirements:
+            return {}, []
+
+        return await match_credentials_to_requirements(user_id, requirements)
+
+    def _get_inputs_list(self, block: AnyBlockSchema) -> list[dict[str, Any]]:
         """Extract non-credential inputs from block schema."""
-        inputs_list = []
         schema = block.input_schema.jsonschema()
-        properties = schema.get("properties", {})
-        required_fields = set(schema.get("required", []))
-
-        # Get credential field names to exclude
         credentials_fields = set(block.input_schema.get_credentials_fields().keys())
+        return get_inputs_from_schema(schema, exclude_fields=credentials_fields)
 
-        for field_name, field_schema in properties.items():
-            # Skip credential fields
-            if field_name in credentials_fields:
-                continue
+    def _resolve_discriminated_credentials(
+        self,
+        block: AnyBlockSchema,
+        input_data: dict[str, Any],
+    ) -> dict[str, CredentialsFieldInfo]:
+        """Resolve credential requirements, applying discriminator logic where needed."""
+        credentials_fields_info = block.input_schema.get_credentials_fields_info()
+        if not credentials_fields_info:
+            return {}
 
-            inputs_list.append(
-                {
-                    "name": field_name,
-                    "title": field_schema.get("title", field_name),
-                    "type": field_schema.get("type", "string"),
-                    "description": field_schema.get("description", ""),
-                    "required": field_name in required_fields,
-                }
-            )
+        resolved: dict[str, CredentialsFieldInfo] = {}
 
-        return inputs_list
+        for field_name, field_info in credentials_fields_info.items():
+            effective_field_info = field_info
+
+            if field_info.discriminator and field_info.discriminator_mapping:
+                discriminator_value = input_data.get(field_info.discriminator)
+                if discriminator_value is None:
+                    field = block.input_schema.model_fields.get(
+                        field_info.discriminator
+                    )
+                    if field and field.default is not PydanticUndefined:
+                        discriminator_value = field.default
+
+                if (
+                    discriminator_value
+                    and discriminator_value in field_info.discriminator_mapping
+                ):
+                    effective_field_info = field_info.discriminate(discriminator_value)
+                    # For host-scoped credentials, add the discriminator value
+                    # (e.g., URL) so _credential_is_for_host can match it
+                    effective_field_info.discriminator_values.add(discriminator_value)
+                    logger.debug(
+                        f"Discriminated provider for {field_name}: "
+                        f"{discriminator_value} -> {effective_field_info.provider}"
+                    )
+
+            resolved[field_name] = effective_field_info
+
+        return resolved

autogpt_platform/backend/backend/api/features/chat/tools/run_block_test.py

@@ -0,0 +1,106 @@
+"""Tests for block execution guards in RunBlockTool."""
+
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+from backend.api.features.chat.tools.models import ErrorResponse
+from backend.api.features.chat.tools.run_block import RunBlockTool
+from backend.data.block import BlockType
+
+from ._test_data import make_session
+
+_TEST_USER_ID = "test-user-run-block"
+
+
+def make_mock_block(
+    block_id: str, name: str, block_type: BlockType, disabled: bool = False
+):
+    """Create a mock block for testing."""
+    mock = MagicMock()
+    mock.id = block_id
+    mock.name = name
+    mock.block_type = block_type
+    mock.disabled = disabled
+    mock.input_schema = MagicMock()
+    mock.input_schema.jsonschema.return_value = {"properties": {}, "required": []}
+    mock.input_schema.get_credentials_fields_info.return_value = []
+    return mock
+
+
+class TestRunBlockFiltering:
+    """Tests for block execution guards in RunBlockTool."""
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_excluded_block_type_returns_error(self):
+        """Attempting to execute a block with excluded BlockType returns error."""
+        session = make_session(user_id=_TEST_USER_ID)
+
+        input_block = make_mock_block("input-block-id", "Input Block", BlockType.INPUT)
+
+        with patch(
+            "backend.api.features.chat.tools.run_block.get_block",
+            return_value=input_block,
+        ):
+            tool = RunBlockTool()
+            response = await tool._execute(
+                user_id=_TEST_USER_ID,
+                session=session,
+                block_id="input-block-id",
+                input_data={},
+            )
+
+        assert isinstance(response, ErrorResponse)
+        assert "cannot be run directly in CoPilot" in response.message
+        assert "designed for use within graphs only" in response.message
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_excluded_block_id_returns_error(self):
+        """Attempting to execute SmartDecisionMakerBlock returns error."""
+        session = make_session(user_id=_TEST_USER_ID)
+
+        smart_decision_id = "3b191d9f-356f-482d-8238-ba04b6d18381"
+        smart_block = make_mock_block(
+            smart_decision_id, "Smart Decision Maker", BlockType.STANDARD
+        )
+
+        with patch(
+            "backend.api.features.chat.tools.run_block.get_block",
+            return_value=smart_block,
+        ):
+            tool = RunBlockTool()
+            response = await tool._execute(
+                user_id=_TEST_USER_ID,
+                session=session,
+                block_id=smart_decision_id,
+                input_data={},
+            )
+
+        assert isinstance(response, ErrorResponse)
+        assert "cannot be run directly in CoPilot" in response.message
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_non_excluded_block_passes_guard(self):
+        """Non-excluded blocks pass the filtering guard (may fail later for other reasons)."""
+        session = make_session(user_id=_TEST_USER_ID)
+
+        standard_block = make_mock_block(
+            "standard-id", "HTTP Request", BlockType.STANDARD
+        )
+
+        with patch(
+            "backend.api.features.chat.tools.run_block.get_block",
+            return_value=standard_block,
+        ):
+            tool = RunBlockTool()
+            response = await tool._execute(
+                user_id=_TEST_USER_ID,
+                session=session,
+                block_id="standard-id",
+                input_data={},
+            )
+
+        # Should NOT be an ErrorResponse about CoPilot exclusion
+        # (may be other errors like missing credentials, but not the exclusion guard)
+        if isinstance(response, ErrorResponse):
+            assert "cannot be run directly in CoPilot" not in response.message

autogpt_platform/backend/backend/api/features/chat/tools/utils.py

@@ -8,6 +8,7 @@ from backend.api.features.library import model as library_model
 from backend.api.features.store import db as store_db
 from backend.data.graph import GraphModel
 from backend.data.model import (
+    Credentials,
     CredentialsFieldInfo,
     CredentialsMetaInput,
     HostScopedCredentials,
@@ -117,7 +118,7 @@ def build_missing_credentials_from_graph(
     preserving all supported credential types for each field.
     """
     matched_keys = set(matched_credentials.keys()) if matched_credentials else set()
-    aggregated_fields = graph.regular_credentials_inputs
+    aggregated_fields = graph.aggregate_credentials_inputs()
 
     return {
         field_key: _serialize_missing_credential(field_key, field_info)
@@ -223,6 +224,99 @@ async def get_or_create_library_agent(
     return library_agents[0]
 
 
+async def match_credentials_to_requirements(
+    user_id: str,
+    requirements: dict[str, CredentialsFieldInfo],
+) -> tuple[dict[str, CredentialsMetaInput], list[CredentialsMetaInput]]:
+    """
+    Match user's credentials against a dictionary of credential requirements.
+
+    This is the core matching logic shared by both graph and block credential matching.
+    """
+    matched: dict[str, CredentialsMetaInput] = {}
+    missing: list[CredentialsMetaInput] = []
+
+    if not requirements:
+        return matched, missing
+
+    available_creds = await get_user_credentials(user_id)
+
+    for field_name, field_info in requirements.items():
+        matching_cred = find_matching_credential(available_creds, field_info)
+
+        if matching_cred:
+            try:
+                matched[field_name] = create_credential_meta_from_match(matching_cred)
+            except Exception as e:
+                logger.error(
+                    f"Failed to create CredentialsMetaInput for field '{field_name}': "
+                    f"provider={matching_cred.provider}, type={matching_cred.type}, "
+                    f"credential_id={matching_cred.id}",
+                    exc_info=True,
+                )
+                provider = next(iter(field_info.provider), "unknown")
+                cred_type = next(iter(field_info.supported_types), "api_key")
+                missing.append(
+                    CredentialsMetaInput(
+                        id=field_name,
+                        provider=provider,  # type: ignore
+                        type=cred_type,  # type: ignore
+                        title=f"{field_name} (validation failed: {e})",
+                    )
+                )
+        else:
+            provider = next(iter(field_info.provider), "unknown")
+            cred_type = next(iter(field_info.supported_types), "api_key")
+            missing.append(
+                CredentialsMetaInput(
+                    id=field_name,
+                    provider=provider,  # type: ignore
+                    type=cred_type,  # type: ignore
+                    title=field_name.replace("_", " ").title(),
+                )
+            )
+
+    return matched, missing
+
+
+async def get_user_credentials(user_id: str) -> list[Credentials]:
+    """Get all available credentials for a user."""
+    creds_manager = IntegrationCredentialsManager()
+    return await creds_manager.store.get_all_creds(user_id)
+
+
+def find_matching_credential(
+    available_creds: list[Credentials],
+    field_info: CredentialsFieldInfo,
+) -> Credentials | None:
+    """Find a credential that matches the required provider, type, scopes, and host."""
+    for cred in available_creds:
+        if cred.provider not in field_info.provider:
+            continue
+        if cred.type not in field_info.supported_types:
+            continue
+        if cred.type == "oauth2" and not _credential_has_required_scopes(
+            cred, field_info
+        ):
+            continue
+        if cred.type == "host_scoped" and not _credential_is_for_host(cred, field_info):
+            continue
+        return cred
+    return None
+
+
+def create_credential_meta_from_match(
+    matching_cred: Credentials,
+) -> CredentialsMetaInput:
+    """Create a CredentialsMetaInput from a matched credential."""
+    return CredentialsMetaInput(
+        id=matching_cred.id,
+        provider=matching_cred.provider,  # type: ignore
+        type=matching_cred.type,
+        title=matching_cred.title,
+    )
+
+
 async def match_user_credentials_to_graph(
     user_id: str,
     graph: GraphModel,
@@ -244,7 +338,7 @@ async def match_user_credentials_to_graph(
     missing_creds: list[str] = []
 
     # Get aggregated credentials requirements from the graph
-    aggregated_creds = graph.regular_credentials_inputs
+    aggregated_creds = graph.aggregate_credentials_inputs()
     logger.debug(
         f"Matching credentials for graph {graph.id}: {len(aggregated_creds)} required"
     )
@@ -331,8 +425,6 @@ def _credential_has_required_scopes(
     # If no scopes are required, any credential matches
     if not requirements.required_scopes:
         return True
-
-    # Check that credential scopes are a superset of required scopes
     return set(credential.scopes).issuperset(requirements.required_scopes)
 
 

autogpt_platform/backend/backend/api/features/chat/tools/utils_test.py

@@ -1,78 +0,0 @@
-"""Tests for chat tools utility functions."""
-
-from unittest.mock import AsyncMock, MagicMock, patch
-
-import pytest
-
-from backend.data.model import CredentialsFieldInfo
-
-
-def _make_regular_field() -> CredentialsFieldInfo:
-    return CredentialsFieldInfo.model_validate(
-        {
-            "credentials_provider": ["github"],
-            "credentials_types": ["api_key"],
-            "is_auto_credential": False,
-        },
-        by_alias=True,
-    )
-
-
-def test_build_missing_credentials_excludes_auto_creds():
-    """
-    build_missing_credentials_from_graph() should use regular_credentials_inputs
-    and thus exclude auto_credentials from the "missing" set.
-    """
-    from backend.api.features.chat.tools.utils import (
-        build_missing_credentials_from_graph,
-    )
-
-    regular_field = _make_regular_field()
-
-    mock_graph = MagicMock()
-    # regular_credentials_inputs should only return the non-auto field
-    mock_graph.regular_credentials_inputs = {
-        "github_api_key": (regular_field, {("node-1", "credentials")}, True),
-    }
-
-    result = build_missing_credentials_from_graph(mock_graph, matched_credentials=None)
-
-    # Should include the regular credential
-    assert "github_api_key" in result
-    # Should NOT include the auto_credential (not in regular_credentials_inputs)
-    assert "google_oauth2" not in result
-
-
-@pytest.mark.asyncio
-async def test_match_user_credentials_excludes_auto_creds():
-    """
-    match_user_credentials_to_graph() should use regular_credentials_inputs
-    and thus exclude auto_credentials from matching.
-    """
-    from backend.api.features.chat.tools.utils import match_user_credentials_to_graph
-
-    regular_field = _make_regular_field()
-
-    mock_graph = MagicMock()
-    mock_graph.id = "test-graph"
-    # regular_credentials_inputs returns only non-auto fields
-    mock_graph.regular_credentials_inputs = {
-        "github_api_key": (regular_field, {("node-1", "credentials")}, True),
-    }
-
-    # Mock the credentials manager to return no credentials
-    with patch(
-        "backend.api.features.chat.tools.utils.IntegrationCredentialsManager"
-    ) as MockCredsMgr:
-        mock_store = AsyncMock()
-        mock_store.get_all_creds.return_value = []
-        MockCredsMgr.return_value.store = mock_store
-
-        matched, missing = await match_user_credentials_to_graph(
-            user_id="test-user", graph=mock_graph
-        )
-
-    # No credentials available, so github should be missing
-    assert len(matched) == 0
-    assert len(missing) == 1
-    assert "github_api_key" in missing[0]

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

@@ -1103,7 +1103,7 @@ async def create_preset_from_graph_execution(
             raise NotFoundError(
                 f"Graph #{graph_execution.graph_id} not found or accessible"
             )
-        elif len(graph.regular_credentials_inputs) > 0:
+        elif len(graph.aggregate_credentials_inputs()) > 0:
             raise ValueError(
                 f"Graph execution #{graph_exec_id} can't be turned into a preset "
                 "because it was run before this feature existed "

autogpt_platform/backend/backend/blocks/exa/websets.py

@@ -478,7 +478,7 @@ class ExaCreateOrFindWebsetBlock(Block):
         aexa = AsyncExa(api_key=credentials.api_key.get_secret_value())
 
         try:
-            webset = aexa.websets.get(id=input_data.external_id)
+            webset = await aexa.websets.get(id=input_data.external_id)
             webset_result = Webset.model_validate(webset.model_dump(by_alias=True))
 
             yield "webset", webset_result
@@ -494,7 +494,7 @@ class ExaCreateOrFindWebsetBlock(Block):
                         count=input_data.search_count,
                     )
 
-                webset = aexa.websets.create(
+                webset = await aexa.websets.create(
                     params=CreateWebsetParameters(
                         search=search_params,
                         external_id=input_data.external_id,
@@ -554,7 +554,7 @@ class ExaUpdateWebsetBlock(Block):
         if input_data.metadata is not None:
             payload["metadata"] = input_data.metadata
 
-        sdk_webset = aexa.websets.update(id=input_data.webset_id, params=payload)
+        sdk_webset = await aexa.websets.update(id=input_data.webset_id, params=payload)
 
         status_str = (
             sdk_webset.status.value
@@ -617,7 +617,7 @@ class ExaListWebsetsBlock(Block):
     ) -> BlockOutput:
         aexa = AsyncExa(api_key=credentials.api_key.get_secret_value())
 
-        response = aexa.websets.list(
+        response = await aexa.websets.list(
             cursor=input_data.cursor,
             limit=input_data.limit,
         )
@@ -678,7 +678,7 @@ class ExaGetWebsetBlock(Block):
     ) -> BlockOutput:
         aexa = AsyncExa(api_key=credentials.api_key.get_secret_value())
 
-        sdk_webset = aexa.websets.get(id=input_data.webset_id)
+        sdk_webset = await aexa.websets.get(id=input_data.webset_id)
 
         status_str = (
             sdk_webset.status.value
@@ -748,7 +748,7 @@ class ExaDeleteWebsetBlock(Block):
     ) -> BlockOutput:
         aexa = AsyncExa(api_key=credentials.api_key.get_secret_value())
 
-        deleted_webset = aexa.websets.delete(id=input_data.webset_id)
+        deleted_webset = await aexa.websets.delete(id=input_data.webset_id)
 
         status_str = (
             deleted_webset.status.value
@@ -798,7 +798,7 @@ class ExaCancelWebsetBlock(Block):
     ) -> BlockOutput:
         aexa = AsyncExa(api_key=credentials.api_key.get_secret_value())
 
-        canceled_webset = aexa.websets.cancel(id=input_data.webset_id)
+        canceled_webset = await aexa.websets.cancel(id=input_data.webset_id)
 
         status_str = (
             canceled_webset.status.value
@@ -968,7 +968,7 @@ class ExaPreviewWebsetBlock(Block):
                 entity["description"] = input_data.entity_description
             payload["entity"] = entity
 
-        sdk_preview = aexa.websets.preview(params=payload)
+        sdk_preview = await aexa.websets.preview(params=payload)
 
         preview = PreviewWebsetModel.from_sdk(sdk_preview)
 
@@ -1051,7 +1051,7 @@ class ExaWebsetStatusBlock(Block):
     ) -> BlockOutput:
         aexa = AsyncExa(api_key=credentials.api_key.get_secret_value())
 
-        webset = aexa.websets.get(id=input_data.webset_id)
+        webset = await aexa.websets.get(id=input_data.webset_id)
 
         status = (
             webset.status.value
@@ -1185,7 +1185,7 @@ class ExaWebsetSummaryBlock(Block):
     ) -> BlockOutput:
         aexa = AsyncExa(api_key=credentials.api_key.get_secret_value())
 
-        webset = aexa.websets.get(id=input_data.webset_id)
+        webset = await aexa.websets.get(id=input_data.webset_id)
 
         # Extract basic info
         webset_id = webset.id
@@ -1211,7 +1211,7 @@ class ExaWebsetSummaryBlock(Block):
         total_items = 0
 
         if input_data.include_sample_items and input_data.sample_size > 0:
-            items_response = aexa.websets.items.list(
+            items_response = await aexa.websets.items.list(
                 webset_id=input_data.webset_id, limit=input_data.sample_size
             )
             sample_items_data = [
@@ -1362,7 +1362,7 @@ class ExaWebsetReadyCheckBlock(Block):
         aexa = AsyncExa(api_key=credentials.api_key.get_secret_value())
 
         # Get webset details
-        webset = aexa.websets.get(id=input_data.webset_id)
+        webset = await aexa.websets.get(id=input_data.webset_id)
 
         status = (
             webset.status.value

autogpt_platform/backend/backend/blocks/exa/websets_enrichment.py

@@ -202,7 +202,7 @@ class ExaCreateEnrichmentBlock(Block):
         # Use AsyncExa SDK
         aexa = AsyncExa(api_key=credentials.api_key.get_secret_value())
 
-        sdk_enrichment = aexa.websets.enrichments.create(
+        sdk_enrichment = await aexa.websets.enrichments.create(
             webset_id=input_data.webset_id, params=payload
         )
 
@@ -223,7 +223,7 @@ class ExaCreateEnrichmentBlock(Block):
             items_enriched = 0
 
             while time.time() - poll_start < input_data.polling_timeout:
-                current_enrich = aexa.websets.enrichments.get(
+                current_enrich = await aexa.websets.enrichments.get(
                     webset_id=input_data.webset_id, id=enrichment_id
                 )
                 current_status = (
@@ -234,7 +234,7 @@ class ExaCreateEnrichmentBlock(Block):
 
                 if current_status in ["completed", "failed", "cancelled"]:
                     # Estimate items from webset searches
-                    webset = aexa.websets.get(id=input_data.webset_id)
+                    webset = await aexa.websets.get(id=input_data.webset_id)
                     if webset.searches:
                         for search in webset.searches:
                             if search.progress:
@@ -329,7 +329,7 @@ class ExaGetEnrichmentBlock(Block):
         # Use AsyncExa SDK
         aexa = AsyncExa(api_key=credentials.api_key.get_secret_value())
 
-        sdk_enrichment = aexa.websets.enrichments.get(
+        sdk_enrichment = await aexa.websets.enrichments.get(
             webset_id=input_data.webset_id, id=input_data.enrichment_id
         )
 
@@ -474,7 +474,7 @@ class ExaDeleteEnrichmentBlock(Block):
         # Use AsyncExa SDK
         aexa = AsyncExa(api_key=credentials.api_key.get_secret_value())
 
-        deleted_enrichment = aexa.websets.enrichments.delete(
+        deleted_enrichment = await aexa.websets.enrichments.delete(
             webset_id=input_data.webset_id, id=input_data.enrichment_id
         )
 
@@ -525,13 +525,13 @@ class ExaCancelEnrichmentBlock(Block):
         # Use AsyncExa SDK
         aexa = AsyncExa(api_key=credentials.api_key.get_secret_value())
 
-        canceled_enrichment = aexa.websets.enrichments.cancel(
+        canceled_enrichment = await aexa.websets.enrichments.cancel(
             webset_id=input_data.webset_id, id=input_data.enrichment_id
         )
 
         # Try to estimate how many items were enriched before cancellation
         items_enriched = 0
-        items_response = aexa.websets.items.list(
+        items_response = await aexa.websets.items.list(
             webset_id=input_data.webset_id, limit=100
         )
 

autogpt_platform/backend/backend/blocks/exa/websets_import_export.py

@@ -222,7 +222,7 @@ class ExaCreateImportBlock(Block):
     def _create_test_mock():
         """Create test mocks for the AsyncExa SDK."""
         from datetime import datetime
-        from unittest.mock import MagicMock
+        from unittest.mock import AsyncMock, MagicMock
 
         # Create mock SDK import object
         mock_import = MagicMock()
@@ -247,7 +247,7 @@ class ExaCreateImportBlock(Block):
         return {
             "_get_client": lambda *args, **kwargs: MagicMock(
                 websets=MagicMock(
-                    imports=MagicMock(create=lambda *args, **kwargs: mock_import)
+                    imports=MagicMock(create=AsyncMock(return_value=mock_import))
                 )
             )
         }
@@ -294,7 +294,7 @@ class ExaCreateImportBlock(Block):
         if input_data.metadata:
             payload["metadata"] = input_data.metadata
 
-        sdk_import = aexa.websets.imports.create(
+        sdk_import = await aexa.websets.imports.create(
             params=payload, csv_data=input_data.csv_data
         )
 
@@ -360,7 +360,7 @@ class ExaGetImportBlock(Block):
         # Use AsyncExa SDK
         aexa = AsyncExa(api_key=credentials.api_key.get_secret_value())
 
-        sdk_import = aexa.websets.imports.get(import_id=input_data.import_id)
+        sdk_import = await aexa.websets.imports.get(import_id=input_data.import_id)
 
         import_obj = ImportModel.from_sdk(sdk_import)
 
@@ -426,7 +426,7 @@ class ExaListImportsBlock(Block):
         # Use AsyncExa SDK
         aexa = AsyncExa(api_key=credentials.api_key.get_secret_value())
 
-        response = aexa.websets.imports.list(
+        response = await aexa.websets.imports.list(
             cursor=input_data.cursor,
             limit=input_data.limit,
         )
@@ -474,7 +474,9 @@ class ExaDeleteImportBlock(Block):
         # Use AsyncExa SDK
         aexa = AsyncExa(api_key=credentials.api_key.get_secret_value())
 
-        deleted_import = aexa.websets.imports.delete(import_id=input_data.import_id)
+        deleted_import = await aexa.websets.imports.delete(
+            import_id=input_data.import_id
+        )
 
         yield "import_id", deleted_import.id
         yield "success", "true"
@@ -573,14 +575,14 @@ class ExaExportWebsetBlock(Block):
             }
         )
 
-        # Create mock iterator
-        mock_items = [mock_item1, mock_item2]
+        # Create async iterator for list_all
+        async def async_item_iterator(*args, **kwargs):
+            for item in [mock_item1, mock_item2]:
+                yield item
 
         return {
             "_get_client": lambda *args, **kwargs: MagicMock(
-                websets=MagicMock(
-                    items=MagicMock(list_all=lambda *args, **kwargs: iter(mock_items))
-                )
+                websets=MagicMock(items=MagicMock(list_all=async_item_iterator))
             )
         }
 
@@ -602,7 +604,7 @@ class ExaExportWebsetBlock(Block):
                 webset_id=input_data.webset_id, limit=input_data.max_items
             )
 
-            for sdk_item in item_iterator:
+            async for sdk_item in item_iterator:
                 if len(all_items) >= input_data.max_items:
                     break
 

autogpt_platform/backend/backend/blocks/exa/websets_items.py

@@ -178,7 +178,7 @@ class ExaGetWebsetItemBlock(Block):
     ) -> BlockOutput:
         aexa = AsyncExa(api_key=credentials.api_key.get_secret_value())
 
-        sdk_item = aexa.websets.items.get(
+        sdk_item = await aexa.websets.items.get(
             webset_id=input_data.webset_id, id=input_data.item_id
         )
 
@@ -269,7 +269,7 @@ class ExaListWebsetItemsBlock(Block):
             response = None
 
             while time.time() - start_time < input_data.wait_timeout:
-                response = aexa.websets.items.list(
+                response = await aexa.websets.items.list(
                     webset_id=input_data.webset_id,
                     cursor=input_data.cursor,
                     limit=input_data.limit,
@@ -282,13 +282,13 @@ class ExaListWebsetItemsBlock(Block):
                 interval = min(interval * 1.2, 10)
 
             if not response:
-                response = aexa.websets.items.list(
+                response = await aexa.websets.items.list(
                     webset_id=input_data.webset_id,
                     cursor=input_data.cursor,
                     limit=input_data.limit,
                 )
         else:
-            response = aexa.websets.items.list(
+            response = await aexa.websets.items.list(
                 webset_id=input_data.webset_id,
                 cursor=input_data.cursor,
                 limit=input_data.limit,
@@ -340,7 +340,7 @@ class ExaDeleteWebsetItemBlock(Block):
     ) -> BlockOutput:
         aexa = AsyncExa(api_key=credentials.api_key.get_secret_value())
 
-        deleted_item = aexa.websets.items.delete(
+        deleted_item = await aexa.websets.items.delete(
             webset_id=input_data.webset_id, id=input_data.item_id
         )
 
@@ -408,7 +408,7 @@ class ExaBulkWebsetItemsBlock(Block):
             webset_id=input_data.webset_id, limit=input_data.max_items
         )
 
-        for sdk_item in item_iterator:
+        async for sdk_item in item_iterator:
             if len(all_items) >= input_data.max_items:
                 break
 
@@ -475,7 +475,7 @@ class ExaWebsetItemsSummaryBlock(Block):
         # Use AsyncExa SDK
         aexa = AsyncExa(api_key=credentials.api_key.get_secret_value())
 
-        webset = aexa.websets.get(id=input_data.webset_id)
+        webset = await aexa.websets.get(id=input_data.webset_id)
 
         entity_type = "unknown"
         if webset.searches:
@@ -495,7 +495,7 @@ class ExaWebsetItemsSummaryBlock(Block):
         # Get sample items if requested
         sample_items: List[WebsetItemModel] = []
         if input_data.sample_size > 0:
-            items_response = aexa.websets.items.list(
+            items_response = await aexa.websets.items.list(
                 webset_id=input_data.webset_id, limit=input_data.sample_size
             )
             # Convert to our stable models
@@ -569,7 +569,7 @@ class ExaGetNewItemsBlock(Block):
         aexa = AsyncExa(api_key=credentials.api_key.get_secret_value())
 
         # Get items starting from cursor
-        response = aexa.websets.items.list(
+        response = await aexa.websets.items.list(
             webset_id=input_data.webset_id,
             cursor=input_data.since_cursor,
             limit=input_data.max_items,

autogpt_platform/backend/backend/blocks/exa/websets_monitor.py

@@ -233,7 +233,7 @@ class ExaCreateMonitorBlock(Block):
     def _create_test_mock():
         """Create test mocks for the AsyncExa SDK."""
         from datetime import datetime
-        from unittest.mock import MagicMock
+        from unittest.mock import AsyncMock, MagicMock
 
         # Create mock SDK monitor object
         mock_monitor = MagicMock()
@@ -263,7 +263,7 @@ class ExaCreateMonitorBlock(Block):
         return {
             "_get_client": lambda *args, **kwargs: MagicMock(
                 websets=MagicMock(
-                    monitors=MagicMock(create=lambda *args, **kwargs: mock_monitor)
+                    monitors=MagicMock(create=AsyncMock(return_value=mock_monitor))
                 )
             )
         }
@@ -320,7 +320,7 @@ class ExaCreateMonitorBlock(Block):
         if input_data.metadata:
             payload["metadata"] = input_data.metadata
 
-        sdk_monitor = aexa.websets.monitors.create(params=payload)
+        sdk_monitor = await aexa.websets.monitors.create(params=payload)
 
         monitor = MonitorModel.from_sdk(sdk_monitor)
 
@@ -384,7 +384,7 @@ class ExaGetMonitorBlock(Block):
         # Use AsyncExa SDK
         aexa = AsyncExa(api_key=credentials.api_key.get_secret_value())
 
-        sdk_monitor = aexa.websets.monitors.get(monitor_id=input_data.monitor_id)
+        sdk_monitor = await aexa.websets.monitors.get(monitor_id=input_data.monitor_id)
 
         monitor = MonitorModel.from_sdk(sdk_monitor)
 
@@ -476,7 +476,7 @@ class ExaUpdateMonitorBlock(Block):
         if input_data.metadata is not None:
             payload["metadata"] = input_data.metadata
 
-        sdk_monitor = aexa.websets.monitors.update(
+        sdk_monitor = await aexa.websets.monitors.update(
             monitor_id=input_data.monitor_id, params=payload
         )
 
@@ -522,7 +522,9 @@ class ExaDeleteMonitorBlock(Block):
         # Use AsyncExa SDK
         aexa = AsyncExa(api_key=credentials.api_key.get_secret_value())
 
-        deleted_monitor = aexa.websets.monitors.delete(monitor_id=input_data.monitor_id)
+        deleted_monitor = await aexa.websets.monitors.delete(
+            monitor_id=input_data.monitor_id
+        )
 
         yield "monitor_id", deleted_monitor.id
         yield "success", "true"
@@ -579,7 +581,7 @@ class ExaListMonitorsBlock(Block):
         # Use AsyncExa SDK
         aexa = AsyncExa(api_key=credentials.api_key.get_secret_value())
 
-        response = aexa.websets.monitors.list(
+        response = await aexa.websets.monitors.list(
             cursor=input_data.cursor,
             limit=input_data.limit,
             webset_id=input_data.webset_id,

autogpt_platform/backend/backend/blocks/exa/websets_polling.py

@@ -121,7 +121,7 @@ class ExaWaitForWebsetBlock(Block):
                 WebsetTargetStatus.IDLE,
                 WebsetTargetStatus.ANY_COMPLETE,
             ]:
-                final_webset = aexa.websets.wait_until_idle(
+                final_webset = await aexa.websets.wait_until_idle(
                     id=input_data.webset_id,
                     timeout=input_data.timeout,
                     poll_interval=input_data.check_interval,
@@ -164,7 +164,7 @@ class ExaWaitForWebsetBlock(Block):
                 interval = input_data.check_interval
                 while time.time() - start_time < input_data.timeout:
                     # Get current webset status
-                    webset = aexa.websets.get(id=input_data.webset_id)
+                    webset = await aexa.websets.get(id=input_data.webset_id)
                     current_status = (
                         webset.status.value
                         if hasattr(webset.status, "value")
@@ -209,7 +209,7 @@ class ExaWaitForWebsetBlock(Block):
 
                 # Timeout reached
                 elapsed = time.time() - start_time
-                webset = aexa.websets.get(id=input_data.webset_id)
+                webset = await aexa.websets.get(id=input_data.webset_id)
                 final_status = (
                     webset.status.value
                     if hasattr(webset.status, "value")
@@ -345,7 +345,7 @@ class ExaWaitForSearchBlock(Block):
         try:
             while time.time() - start_time < input_data.timeout:
                 # Get current search status using SDK
-                search = aexa.websets.searches.get(
+                search = await aexa.websets.searches.get(
                     webset_id=input_data.webset_id, id=input_data.search_id
                 )
 
@@ -401,7 +401,7 @@ class ExaWaitForSearchBlock(Block):
             elapsed = time.time() - start_time
 
             # Get last known status
-            search = aexa.websets.searches.get(
+            search = await aexa.websets.searches.get(
                 webset_id=input_data.webset_id, id=input_data.search_id
             )
             final_status = (
@@ -503,7 +503,7 @@ class ExaWaitForEnrichmentBlock(Block):
         try:
             while time.time() - start_time < input_data.timeout:
                 # Get current enrichment status using SDK
-                enrichment = aexa.websets.enrichments.get(
+                enrichment = await aexa.websets.enrichments.get(
                     webset_id=input_data.webset_id, id=input_data.enrichment_id
                 )
 
@@ -548,7 +548,7 @@ class ExaWaitForEnrichmentBlock(Block):
             elapsed = time.time() - start_time
 
             # Get last known status
-            enrichment = aexa.websets.enrichments.get(
+            enrichment = await aexa.websets.enrichments.get(
                 webset_id=input_data.webset_id, id=input_data.enrichment_id
             )
             final_status = (
@@ -575,7 +575,7 @@ class ExaWaitForEnrichmentBlock(Block):
     ) -> tuple[list[SampleEnrichmentModel], int]:
         """Get sample enriched data and count."""
         # Get a few items to see enrichment results using SDK
-        response = aexa.websets.items.list(webset_id=webset_id, limit=5)
+        response = await aexa.websets.items.list(webset_id=webset_id, limit=5)
 
         sample_data: list[SampleEnrichmentModel] = []
         enriched_count = 0

autogpt_platform/backend/backend/blocks/exa/websets_search.py

@@ -317,7 +317,7 @@ class ExaCreateWebsetSearchBlock(Block):
 
         aexa = AsyncExa(api_key=credentials.api_key.get_secret_value())
 
-        sdk_search = aexa.websets.searches.create(
+        sdk_search = await aexa.websets.searches.create(
             webset_id=input_data.webset_id, params=payload
         )
 
@@ -350,7 +350,7 @@ class ExaCreateWebsetSearchBlock(Block):
             poll_start = time.time()
 
             while time.time() - poll_start < input_data.polling_timeout:
-                current_search = aexa.websets.searches.get(
+                current_search = await aexa.websets.searches.get(
                     webset_id=input_data.webset_id, id=search_id
                 )
                 current_status = (
@@ -442,7 +442,7 @@ class ExaGetWebsetSearchBlock(Block):
         # Use AsyncExa SDK
         aexa = AsyncExa(api_key=credentials.api_key.get_secret_value())
 
-        sdk_search = aexa.websets.searches.get(
+        sdk_search = await aexa.websets.searches.get(
             webset_id=input_data.webset_id, id=input_data.search_id
         )
 
@@ -523,7 +523,7 @@ class ExaCancelWebsetSearchBlock(Block):
         # Use AsyncExa SDK
         aexa = AsyncExa(api_key=credentials.api_key.get_secret_value())
 
-        canceled_search = aexa.websets.searches.cancel(
+        canceled_search = await aexa.websets.searches.cancel(
             webset_id=input_data.webset_id, id=input_data.search_id
         )
 
@@ -604,7 +604,7 @@ class ExaFindOrCreateSearchBlock(Block):
         aexa = AsyncExa(api_key=credentials.api_key.get_secret_value())
 
         # Get webset to check existing searches
-        webset = aexa.websets.get(id=input_data.webset_id)
+        webset = await aexa.websets.get(id=input_data.webset_id)
 
         # Look for existing search with same query
         existing_search = None
@@ -636,7 +636,7 @@ class ExaFindOrCreateSearchBlock(Block):
             if input_data.entity_type != SearchEntityType.AUTO:
                 payload["entity"] = {"type": input_data.entity_type.value}
 
-            sdk_search = aexa.websets.searches.create(
+            sdk_search = await aexa.websets.searches.create(
                 webset_id=input_data.webset_id, params=payload
             )
 

autogpt_platform/backend/backend/blocks/llm.py

@@ -531,12 +531,12 @@ class LLMResponse(BaseModel):
 
 def convert_openai_tool_fmt_to_anthropic(
     openai_tools: list[dict] | None = None,
-) -> Iterable[ToolParam] | anthropic.NotGiven:
+) -> Iterable[ToolParam] | anthropic.Omit:
     """
     Convert OpenAI tool format to Anthropic tool format.
     """
     if not openai_tools or len(openai_tools) == 0:
-        return anthropic.NOT_GIVEN
+        return anthropic.omit
 
     anthropic_tools = []
     for tool in openai_tools:
@@ -596,10 +596,10 @@ def extract_openai_tool_calls(response) -> list[ToolContentBlock] | None:
 
 def get_parallel_tool_calls_param(
     llm_model: LlmModel, parallel_tool_calls: bool | None
-):
+) -> bool | openai.Omit:
     """Get the appropriate parallel_tool_calls parameter for OpenAI-compatible APIs."""
     if llm_model.startswith("o") or parallel_tool_calls is None:
-        return openai.NOT_GIVEN
+        return openai.omit
     return parallel_tool_calls
 
 

autogpt_platform/backend/backend/data/block.py

@@ -319,8 +319,6 @@ class BlockSchema(BaseModel):
                 "credentials_provider": [config.get("provider", "google")],
                 "credentials_types": [config.get("type", "oauth2")],
                 "credentials_scopes": config.get("scopes"),
-                "is_auto_credential": True,
-                "input_field_name": info["field_name"],
             }
             result[kwarg_name] = CredentialsFieldInfo.model_validate(
                 auto_schema, by_alias=True

autogpt_platform/backend/backend/data/execution.py

@@ -1,9 +1,8 @@
 import logging
+import queue
 from collections import defaultdict
 from datetime import datetime, timedelta, timezone
 from enum import Enum
-from multiprocessing import Manager
-from queue import Empty
 from typing import (
     TYPE_CHECKING,
     Annotated,
@@ -1200,12 +1199,16 @@ class NodeExecutionEntry(BaseModel):
 
 class ExecutionQueue(Generic[T]):
     """
-    Queue for managing the execution of agents.
-    This will be shared between different processes
+    Thread-safe queue for managing node execution within a single graph execution.
+
+    Note: Uses queue.Queue (not multiprocessing.Queue) since all access is from
+    threads within the same process. If migrating back to ProcessPoolExecutor,
+    replace with multiprocessing.Manager().Queue() for cross-process safety.
     """
 
     def __init__(self):
-        self.queue = Manager().Queue()
+        # Thread-safe queue (not multiprocessing) — see class docstring
+        self.queue: queue.Queue[T] = queue.Queue()
 
     def add(self, execution: T) -> T:
         self.queue.put(execution)
@@ -1220,7 +1223,7 @@ class ExecutionQueue(Generic[T]):
     def get_or_none(self) -> T | None:
         try:
             return self.queue.get_nowait()
-        except Empty:
+        except queue.Empty:
             return None
 
 

autogpt_platform/backend/backend/data/execution_queue_test.py

@@ -0,0 +1,58 @@
+"""Tests for ExecutionQueue thread-safety."""
+
+import queue
+import threading
+
+from backend.data.execution import ExecutionQueue
+
+
+def test_execution_queue_uses_stdlib_queue():
+    """Verify ExecutionQueue uses queue.Queue (not multiprocessing)."""
+    q = ExecutionQueue()
+    assert isinstance(q.queue, queue.Queue)
+
+
+def test_basic_operations():
+    """Test add, get, empty, and get_or_none."""
+    q = ExecutionQueue()
+
+    assert q.empty() is True
+    assert q.get_or_none() is None
+
+    result = q.add("item1")
+    assert result == "item1"
+    assert q.empty() is False
+
+    item = q.get()
+    assert item == "item1"
+    assert q.empty() is True
+
+
+def test_thread_safety():
+    """Test concurrent access from multiple threads."""
+    q = ExecutionQueue()
+    results = []
+    num_items = 100
+
+    def producer():
+        for i in range(num_items):
+            q.add(f"item_{i}")
+
+    def consumer():
+        count = 0
+        while count < num_items:
+            item = q.get_or_none()
+            if item is not None:
+                results.append(item)
+                count += 1
+
+    producer_thread = threading.Thread(target=producer)
+    consumer_thread = threading.Thread(target=consumer)
+
+    producer_thread.start()
+    consumer_thread.start()
+
+    producer_thread.join(timeout=5)
+    consumer_thread.join(timeout=5)
+
+    assert len(results) == num_items

autogpt_platform/backend/backend/data/graph.py

@@ -447,7 +447,8 @@ class GraphModel(Graph, GraphMeta):
     @computed_field
     @property
     def credentials_input_schema(self) -> dict[str, Any]:
-        graph_credentials_inputs = self.regular_credentials_inputs
+        graph_credentials_inputs = self.aggregate_credentials_inputs()
+
         logger.debug(
             f"Combined credentials input fields for graph #{self.id} ({self.name}): "
             f"{graph_credentials_inputs}"
@@ -603,28 +604,6 @@ class GraphModel(Graph, GraphMeta):
             for key, (field_info, node_field_pairs) in combined.items()
         }
 
-    @property
-    def regular_credentials_inputs(
-        self,
-    ) -> dict[str, tuple[CredentialsFieldInfo, set[tuple[str, str]], bool]]:
-        """Credentials that need explicit user mapping (CredentialsMetaInput fields)."""
-        return {
-            k: v
-            for k, v in self.aggregate_credentials_inputs().items()
-            if not v[0].is_auto_credential
-        }
-
-    @property
-    def auto_credentials_inputs(
-        self,
-    ) -> dict[str, tuple[CredentialsFieldInfo, set[tuple[str, str]], bool]]:
-        """Credentials embedded in file fields (_credentials_id), resolved at execution time."""
-        return {
-            k: v
-            for k, v in self.aggregate_credentials_inputs().items()
-            if v[0].is_auto_credential
-        }
-
     def reassign_ids(self, user_id: str, reassign_graph_id: bool = False):
         """
         Reassigns all IDs in the graph to new UUIDs.
@@ -675,16 +654,6 @@ class GraphModel(Graph, GraphMeta):
             ) and graph_id in graph_id_map:
                 node.input_default["graph_id"] = graph_id_map[graph_id]
 
-        # Clear auto-credentials references (e.g., _credentials_id in
-        # GoogleDriveFile fields) so the new user must re-authenticate
-        # with their own account
-        for node in graph.nodes:
-            if not node.input_default:
-                continue
-            for key, value in node.input_default.items():
-                if isinstance(value, dict) and "_credentials_id" in value:
-                    del value["_credentials_id"]
-
     def validate_graph(
         self,
         for_run: bool = False,

autogpt_platform/backend/backend/data/graph_test.py

@@ -463,329 +463,3 @@ def test_node_credentials_optional_with_other_metadata():
     assert node.credentials_optional is True
     assert node.metadata["position"] == {"x": 100, "y": 200}
     assert node.metadata["customized_name"] == "My Custom Node"
-
-
-# ============================================================================
-# Tests for CredentialsFieldInfo.combine() field propagation
-def test_combine_preserves_is_auto_credential_flag():
-    """
-    CredentialsFieldInfo.combine() must propagate is_auto_credential and
-    input_field_name to the combined result. Regression test for reviewer
-    finding that combine() dropped these fields.
-    """
-    from backend.data.model import CredentialsFieldInfo
-
-    auto_field = CredentialsFieldInfo.model_validate(
-        {
-            "credentials_provider": ["google"],
-            "credentials_types": ["oauth2"],
-            "credentials_scopes": ["drive.readonly"],
-            "is_auto_credential": True,
-            "input_field_name": "spreadsheet",
-        },
-        by_alias=True,
-    )
-
-    # combine() takes *args of (field_info, key) tuples
-    combined = CredentialsFieldInfo.combine(
-        (auto_field, ("node-1", "credentials")),
-        (auto_field, ("node-2", "credentials")),
-    )
-
-    assert len(combined) == 1
-    group_key = next(iter(combined))
-    combined_info, combined_keys = combined[group_key]
-
-    assert combined_info.is_auto_credential is True
-    assert combined_info.input_field_name == "spreadsheet"
-    assert combined_keys == {("node-1", "credentials"), ("node-2", "credentials")}
-
-
-def test_combine_preserves_regular_credential_defaults():
-    """Regular credentials should have is_auto_credential=False after combine()."""
-    from backend.data.model import CredentialsFieldInfo
-
-    regular_field = CredentialsFieldInfo.model_validate(
-        {
-            "credentials_provider": ["github"],
-            "credentials_types": ["api_key"],
-            "is_auto_credential": False,
-        },
-        by_alias=True,
-    )
-
-    combined = CredentialsFieldInfo.combine(
-        (regular_field, ("node-1", "credentials")),
-    )
-
-    group_key = next(iter(combined))
-    combined_info, _ = combined[group_key]
-
-    assert combined_info.is_auto_credential is False
-    assert combined_info.input_field_name is None
-
-
-# ============================================================================
-# Tests for _reassign_ids credential clearing (Fix 3: SECRT-1772)
-
-
-def test_reassign_ids_clears_credentials_id():
-    """
-    [SECRT-1772] _reassign_ids should clear _credentials_id from
-    GoogleDriveFile-style input_default fields so forked agents
-    don't retain the original creator's credential references.
-    """
-    from backend.data.graph import GraphModel
-
-    node = Node(
-        id="node-1",
-        block_id=StoreValueBlock().id,
-        input_default={
-            "spreadsheet": {
-                "_credentials_id": "original-cred-id",
-                "id": "file-123",
-                "name": "test.xlsx",
-                "mimeType": "application/vnd.google-apps.spreadsheet",
-                "url": "https://docs.google.com/spreadsheets/d/file-123",
-            },
-        },
-    )
-
-    graph = Graph(
-        id="test-graph",
-        name="Test",
-        description="Test",
-        nodes=[node],
-        links=[],
-    )
-
-    GraphModel._reassign_ids(graph, user_id="new-user", graph_id_map={})
-
-    # _credentials_id key should be removed (not set to None) so that
-    # _acquire_auto_credentials correctly errors instead of treating it as chained data
-    assert "_credentials_id" not in graph.nodes[0].input_default["spreadsheet"]
-
-
-def test_reassign_ids_preserves_non_credential_fields():
-    """
-    Regression guard: _reassign_ids should NOT modify non-credential fields
-    like name, mimeType, id, url.
-    """
-    from backend.data.graph import GraphModel
-
-    node = Node(
-        id="node-1",
-        block_id=StoreValueBlock().id,
-        input_default={
-            "spreadsheet": {
-                "_credentials_id": "cred-abc",
-                "id": "file-123",
-                "name": "test.xlsx",
-                "mimeType": "application/vnd.google-apps.spreadsheet",
-                "url": "https://docs.google.com/spreadsheets/d/file-123",
-            },
-        },
-    )
-
-    graph = Graph(
-        id="test-graph",
-        name="Test",
-        description="Test",
-        nodes=[node],
-        links=[],
-    )
-
-    GraphModel._reassign_ids(graph, user_id="new-user", graph_id_map={})
-
-    field = graph.nodes[0].input_default["spreadsheet"]
-    assert field["id"] == "file-123"
-    assert field["name"] == "test.xlsx"
-    assert field["mimeType"] == "application/vnd.google-apps.spreadsheet"
-    assert field["url"] == "https://docs.google.com/spreadsheets/d/file-123"
-
-
-def test_reassign_ids_handles_no_credentials():
-    """
-    Regression guard: _reassign_ids should not error when input_default
-    has no dict fields with _credentials_id.
-    """
-    from backend.data.graph import GraphModel
-
-    node = Node(
-        id="node-1",
-        block_id=StoreValueBlock().id,
-        input_default={
-            "input": "some value",
-            "another_input": 42,
-        },
-    )
-
-    graph = Graph(
-        id="test-graph",
-        name="Test",
-        description="Test",
-        nodes=[node],
-        links=[],
-    )
-
-    GraphModel._reassign_ids(graph, user_id="new-user", graph_id_map={})
-
-    # Should not error, fields unchanged
-    assert graph.nodes[0].input_default["input"] == "some value"
-    assert graph.nodes[0].input_default["another_input"] == 42
-
-
-def test_reassign_ids_handles_multiple_credential_fields():
-    """
-    [SECRT-1772] When a node has multiple dict fields with _credentials_id,
-    ALL of them should be cleared.
-    """
-    from backend.data.graph import GraphModel
-
-    node = Node(
-        id="node-1",
-        block_id=StoreValueBlock().id,
-        input_default={
-            "spreadsheet": {
-                "_credentials_id": "cred-1",
-                "id": "file-1",
-                "name": "file1.xlsx",
-            },
-            "doc_file": {
-                "_credentials_id": "cred-2",
-                "id": "file-2",
-                "name": "file2.docx",
-            },
-            "plain_input": "not a dict",
-        },
-    )
-
-    graph = Graph(
-        id="test-graph",
-        name="Test",
-        description="Test",
-        nodes=[node],
-        links=[],
-    )
-
-    GraphModel._reassign_ids(graph, user_id="new-user", graph_id_map={})
-
-    assert "_credentials_id" not in graph.nodes[0].input_default["spreadsheet"]
-    assert "_credentials_id" not in graph.nodes[0].input_default["doc_file"]
-    assert graph.nodes[0].input_default["plain_input"] == "not a dict"
-
-
-# ============================================================================
-# Tests for discriminate() field propagation
-def test_discriminate_preserves_is_auto_credential_flag():
-    """
-    CredentialsFieldInfo.discriminate() must propagate is_auto_credential and
-    input_field_name to the discriminated result. Regression test for
-    discriminate() dropping these fields (same class of bug as combine()).
-    """
-    from backend.data.model import CredentialsFieldInfo
-
-    auto_field = CredentialsFieldInfo.model_validate(
-        {
-            "credentials_provider": ["google", "openai"],
-            "credentials_types": ["oauth2"],
-            "credentials_scopes": ["drive.readonly"],
-            "is_auto_credential": True,
-            "input_field_name": "spreadsheet",
-            "discriminator": "model",
-            "discriminator_mapping": {"gpt-4": "openai", "gemini": "google"},
-        },
-        by_alias=True,
-    )
-
-    discriminated = auto_field.discriminate("gemini")
-
-    assert discriminated.is_auto_credential is True
-    assert discriminated.input_field_name == "spreadsheet"
-    assert discriminated.provider == frozenset(["google"])
-
-
-def test_discriminate_preserves_regular_credential_defaults():
-    """Regular credentials should have is_auto_credential=False after discriminate()."""
-    from backend.data.model import CredentialsFieldInfo
-
-    regular_field = CredentialsFieldInfo.model_validate(
-        {
-            "credentials_provider": ["google", "openai"],
-            "credentials_types": ["api_key"],
-            "is_auto_credential": False,
-            "discriminator": "model",
-            "discriminator_mapping": {"gpt-4": "openai", "gemini": "google"},
-        },
-        by_alias=True,
-    )
-
-    discriminated = regular_field.discriminate("gpt-4")
-
-    assert discriminated.is_auto_credential is False
-    assert discriminated.input_field_name is None
-    assert discriminated.provider == frozenset(["openai"])
-
-
-# ============================================================================
-# Tests for credentials_input_schema excluding auto_credentials
-def test_credentials_input_schema_excludes_auto_creds():
-    """
-    GraphModel.credentials_input_schema should exclude auto_credentials
-    (is_auto_credential=True) from the schema. Auto_credentials are
-    transparently resolved at execution time via file picker data.
-    """
-    from datetime import datetime, timezone
-    from unittest.mock import PropertyMock, patch
-
-    from backend.data.graph import GraphModel, NodeModel
-    from backend.data.model import CredentialsFieldInfo
-
-    regular_field_info = CredentialsFieldInfo.model_validate(
-        {
-            "credentials_provider": ["github"],
-            "credentials_types": ["api_key"],
-            "is_auto_credential": False,
-        },
-        by_alias=True,
-    )
-
-    graph = GraphModel(
-        id="test-graph",
-        version=1,
-        name="Test",
-        description="Test",
-        user_id="test-user",
-        created_at=datetime.now(timezone.utc),
-        nodes=[
-            NodeModel(
-                id="node-1",
-                block_id=StoreValueBlock().id,
-                input_default={},
-                graph_id="test-graph",
-                graph_version=1,
-            ),
-        ],
-        links=[],
-    )
-
-    # Mock regular_credentials_inputs to return only the non-auto field (3-tuple)
-    regular_only = {
-        "github_credentials": (
-            regular_field_info,
-            {("node-1", "credentials")},
-            True,
-        ),
-    }
-
-    with patch.object(
-        type(graph),
-        "regular_credentials_inputs",
-        new_callable=PropertyMock,
-        return_value=regular_only,
-    ):
-        schema = graph.credentials_input_schema
-        field_names = set(schema.get("properties", {}).keys())
-        # Should include regular credential but NOT auto_credential
-        assert "github_credentials" in field_names
-        assert "google_credentials" not in field_names

autogpt_platform/backend/backend/data/model.py

@@ -571,8 +571,6 @@ class CredentialsFieldInfo(BaseModel, Generic[CP, CT]):
     discriminator: Optional[str] = None
     discriminator_mapping: Optional[dict[str, CP]] = None
     discriminator_values: set[Any] = Field(default_factory=set)
-    is_auto_credential: bool = False
-    input_field_name: Optional[str] = None
 
     @classmethod
     def combine(
@@ -653,9 +651,6 @@ class CredentialsFieldInfo(BaseModel, Generic[CP, CT]):
                 + "_credentials"
             )
 
-            # Propagate is_auto_credential from the combined field.
-            # All fields in a group should share the same is_auto_credential
-            # value since auto and regular credentials serve different purposes.
             result[group_key] = (
                 CredentialsFieldInfo[CP, CT](
                     credentials_provider=combined.provider,
@@ -664,8 +659,6 @@ class CredentialsFieldInfo(BaseModel, Generic[CP, CT]):
                     discriminator=combined.discriminator,
                     discriminator_mapping=combined.discriminator_mapping,
                     discriminator_values=set(all_discriminator_values),
-                    is_auto_credential=combined.is_auto_credential,
-                    input_field_name=combined.input_field_name,
                 ),
                 combined_keys,
             )
@@ -691,8 +684,6 @@ class CredentialsFieldInfo(BaseModel, Generic[CP, CT]):
             discriminator=self.discriminator,
             discriminator_mapping=self.discriminator_mapping,
             discriminator_values=self.discriminator_values,
-            is_auto_credential=self.is_auto_credential,
-            input_field_name=self.input_field_name,
         )
 
 

autogpt_platform/backend/backend/data/rabbitmq.py

@@ -1,3 +1,4 @@
+import asyncio
 import logging
 from abc import ABC, abstractmethod
 from enum import Enum
@@ -225,6 +226,10 @@ class SyncRabbitMQ(RabbitMQBase):
 class AsyncRabbitMQ(RabbitMQBase):
     """Asynchronous RabbitMQ client"""
 
+    def __init__(self, config: RabbitMQConfig):
+        super().__init__(config)
+        self._reconnect_lock: asyncio.Lock | None = None
+
     @property
     def is_connected(self) -> bool:
         return bool(self._connection and not self._connection.is_closed)
@@ -235,7 +240,17 @@ class AsyncRabbitMQ(RabbitMQBase):
 
     @conn_retry("AsyncRabbitMQ", "Acquiring async connection")
     async def connect(self):
-        if self.is_connected:
+        if self.is_connected and self._channel and not self._channel.is_closed:
+            return
+
+        if (
+            self.is_connected
+            and self._connection
+            and (self._channel is None or self._channel.is_closed)
+        ):
+            self._channel = await self._connection.channel()
+            await self._channel.set_qos(prefetch_count=1)
+            await self.declare_infrastructure()
             return
 
         self._connection = await aio_pika.connect_robust(
@@ -291,24 +306,46 @@ class AsyncRabbitMQ(RabbitMQBase):
                     exchange, routing_key=queue.routing_key or queue.name
                 )
 
-    @func_retry
-    async def publish_message(
+    @property
+    def _lock(self) -> asyncio.Lock:
+        if self._reconnect_lock is None:
+            self._reconnect_lock = asyncio.Lock()
+        return self._reconnect_lock
+
+    async def _ensure_channel(self) -> aio_pika.abc.AbstractChannel:
+        """Get a valid channel, reconnecting if the current one is stale.
+
+        Uses a lock to prevent concurrent reconnection attempts from racing.
+        """
+        if self.is_ready:
+            return self._channel  # type: ignore  # is_ready guarantees non-None
+
+        async with self._lock:
+            # Double-check after acquiring lock
+            if self.is_ready:
+                return self._channel  # type: ignore
+
+            self._channel = None
+            await self.connect()
+
+            if self._channel is None:
+                raise RuntimeError("Channel should be established after connect")
+
+            return self._channel
+
+    async def _publish_once(
         self,
         routing_key: str,
         message: str,
         exchange: Optional[Exchange] = None,
         persistent: bool = True,
     ) -> None:
-        if not self.is_ready:
-            await self.connect()
-
-        if self._channel is None:
-            raise RuntimeError("Channel should be established after connect")
+        channel = await self._ensure_channel()
 
         if exchange:
-            exchange_obj = await self._channel.get_exchange(exchange.name)
+            exchange_obj = await channel.get_exchange(exchange.name)
         else:
-            exchange_obj = self._channel.default_exchange
+            exchange_obj = channel.default_exchange
 
         await exchange_obj.publish(
             aio_pika.Message(
@@ -322,9 +359,23 @@ class AsyncRabbitMQ(RabbitMQBase):
             routing_key=routing_key,
         )
 
+    @func_retry
+    async def publish_message(
+        self,
+        routing_key: str,
+        message: str,
+        exchange: Optional[Exchange] = None,
+        persistent: bool = True,
+    ) -> None:
+        try:
+            await self._publish_once(routing_key, message, exchange, persistent)
+        except aio_pika.exceptions.ChannelInvalidStateError:
+            logger.warning(
+                "RabbitMQ channel invalid, forcing reconnect and retrying publish"
+            )
+            async with self._lock:
+                self._channel = None
+            await self._publish_once(routing_key, message, exchange, persistent)
+
     async def get_channel(self) -> aio_pika.abc.AbstractChannel:
-        if not self.is_ready:
-            await self.connect()
-        if self._channel is None:
-            raise RuntimeError("Channel should be established after connect")
-        return self._channel
+        return await self._ensure_channel()

autogpt_platform/backend/backend/executor/manager.py

@@ -92,7 +92,6 @@ from .utils import (
     block_usage_cost,
     create_execution_queue_config,
     execution_usage_cost,
-    parse_auto_credential_field,
     validate_exec,
 )
 
@@ -173,60 +172,6 @@ def execute_graph(
 T = TypeVar("T")
 
 
-async def _acquire_auto_credentials(
-    input_model: type[BlockSchema],
-    input_data: dict[str, Any],
-    creds_manager: "IntegrationCredentialsManager",
-    user_id: str,
-) -> tuple[dict[str, Any], list[AsyncRedisLock]]:
-    """
-    Resolve auto_credentials from GoogleDriveFileField-style inputs.
-
-    Returns:
-        (extra_exec_kwargs, locks): kwargs to inject into block execution, and
-        credential locks to release after execution completes.
-    """
-    extra_exec_kwargs: dict[str, Any] = {}
-    locks: list[AsyncRedisLock] = []
-
-    # NOTE: If a block ever has multiple auto-credential fields, a ValueError
-    # on a later field will strand locks acquired for earlier fields. They'll
-    # auto-expire via Redis TTL, but add a try/except to release partial locks
-    # if that becomes a real scenario.
-    for kwarg_name, info in input_model.get_auto_credentials_fields().items():
-        field_name = info["field_name"]
-        field_data = input_data.get(field_name)
-
-        parsed = parse_auto_credential_field(
-            field_name=field_name,
-            info=info,
-            field_data=field_data,
-            field_present_in_input=field_name in input_data,
-        )
-
-        if parsed.error:
-            raise ValueError(parsed.error)
-
-        if parsed.cred_id:
-            # Credential ID provided - acquire credentials
-            try:
-                credentials, lock = await creds_manager.acquire(user_id, parsed.cred_id)
-                locks.append(lock)
-                extra_exec_kwargs[kwarg_name] = credentials
-            except ValueError:
-                raise ValueError(
-                    f"{parsed.provider.capitalize()} credentials for "
-                    f"'{parsed.file_name}' in field '{parsed.field_name}' are not "
-                    f"available in your account. "
-                    f"This can happen if the agent was created by another "
-                    f"user or the credentials were deleted. "
-                    f"Please open the agent in the builder and re-select "
-                    f"the file to authenticate with your own account."
-                )
-
-    return extra_exec_kwargs, locks
-
-
 async def execute_node(
     node: Node,
     data: NodeExecutionEntry,
@@ -326,14 +271,41 @@ async def execute_node(
         extra_exec_kwargs[field_name] = credentials
 
     # Handle auto-generated credentials (e.g., from GoogleDriveFileInput)
-    auto_extra_kwargs, auto_locks = await _acquire_auto_credentials(
-        input_model=input_model,
-        input_data=input_data,
-        creds_manager=creds_manager,
-        user_id=user_id,
-    )
-    extra_exec_kwargs.update(auto_extra_kwargs)
-    creds_locks.extend(auto_locks)
+    for kwarg_name, info in input_model.get_auto_credentials_fields().items():
+        field_name = info["field_name"]
+        field_data = input_data.get(field_name)
+        if field_data and isinstance(field_data, dict):
+            # Check if _credentials_id key exists in the field data
+            if "_credentials_id" in field_data:
+                cred_id = field_data["_credentials_id"]
+                if cred_id:
+                    # Credential ID provided - acquire credentials
+                    provider = info.get("config", {}).get(
+                        "provider", "external service"
+                    )
+                    file_name = field_data.get("name", "selected file")
+                    try:
+                        credentials, lock = await creds_manager.acquire(
+                            user_id, cred_id
+                        )
+                        creds_locks.append(lock)
+                        extra_exec_kwargs[kwarg_name] = credentials
+                    except ValueError:
+                        # Credential was deleted or doesn't exist
+                        raise ValueError(
+                            f"Authentication expired for '{file_name}' in field '{field_name}'. "
+                            f"The saved {provider.capitalize()} credentials no longer exist. "
+                            f"Please re-select the file to re-authenticate."
+                        )
+                # else: _credentials_id is explicitly None, skip credentials (for chained data)
+            else:
+                # _credentials_id key missing entirely - this is an error
+                provider = info.get("config", {}).get("provider", "external service")
+                file_name = field_data.get("name", "selected file")
+                raise ValueError(
+                    f"Authentication missing for '{file_name}' in field '{field_name}'. "
+                    f"Please re-select the file to authenticate with {provider.capitalize()}."
+                )
 
     output_size = 0
 

autogpt_platform/backend/backend/executor/manager_auto_credentials_test.py

@@ -1,320 +0,0 @@
-"""
-Tests for auto_credentials handling in execute_node().
-
-These test the _acquire_auto_credentials() helper function extracted from
-execute_node() (manager.py lines 273-308).
-"""
-
-import pytest
-from pytest_mock import MockerFixture
-
-
-@pytest.fixture
-def google_drive_file_data():
-    return {
-        "valid": {
-            "_credentials_id": "cred-id-123",
-            "id": "file-123",
-            "name": "test.xlsx",
-            "mimeType": "application/vnd.google-apps.spreadsheet",
-        },
-        "chained": {
-            "_credentials_id": None,
-            "id": "file-456",
-            "name": "chained.xlsx",
-            "mimeType": "application/vnd.google-apps.spreadsheet",
-        },
-        "missing_key": {
-            "id": "file-789",
-            "name": "bad.xlsx",
-            "mimeType": "application/vnd.google-apps.spreadsheet",
-        },
-    }
-
-
-@pytest.fixture
-def mock_input_model(mocker: MockerFixture):
-    """Create a mock input model with get_auto_credentials_fields() returning one field."""
-    input_model = mocker.MagicMock()
-    input_model.get_auto_credentials_fields.return_value = {
-        "credentials": {
-            "field_name": "spreadsheet",
-            "config": {
-                "provider": "google",
-                "type": "oauth2",
-                "scopes": ["https://www.googleapis.com/auth/drive.readonly"],
-            },
-        }
-    }
-    return input_model
-
-
-@pytest.fixture
-def mock_creds_manager(mocker: MockerFixture):
-    manager = mocker.AsyncMock()
-    mock_lock = mocker.AsyncMock()
-    mock_creds = mocker.MagicMock()
-    mock_creds.id = "cred-id-123"
-    mock_creds.provider = "google"
-    manager.acquire.return_value = (mock_creds, mock_lock)
-    return manager, mock_creds, mock_lock
-
-
-@pytest.mark.asyncio
-async def test_auto_credentials_happy_path(
-    mocker: MockerFixture,
-    google_drive_file_data,
-    mock_input_model,
-    mock_creds_manager,
-):
-    """When field_data has a valid _credentials_id, credentials should be acquired."""
-    from backend.executor.manager import _acquire_auto_credentials
-
-    manager, mock_creds, mock_lock = mock_creds_manager
-    input_data = {"spreadsheet": google_drive_file_data["valid"]}
-
-    extra_kwargs, locks = await _acquire_auto_credentials(
-        input_model=mock_input_model,
-        input_data=input_data,
-        creds_manager=manager,
-        user_id="user-1",
-    )
-
-    manager.acquire.assert_called_once_with("user-1", "cred-id-123")
-    assert extra_kwargs["credentials"] == mock_creds
-    assert mock_lock in locks
-
-
-@pytest.mark.asyncio
-async def test_auto_credentials_field_none_static_raises(
-    mocker: MockerFixture,
-    mock_input_model,
-    mock_creds_manager,
-):
-    """
-    [THE BUG FIX TEST — OPEN-2895]
-    When field_data is None and the key IS in input_data (user didn't select a file),
-    should raise ValueError instead of silently skipping.
-    """
-    from backend.executor.manager import _acquire_auto_credentials
-
-    manager, _, _ = mock_creds_manager
-    # Key is present but value is None = user didn't select a file
-    input_data = {"spreadsheet": None}
-
-    with pytest.raises(ValueError, match="No file selected"):
-        await _acquire_auto_credentials(
-            input_model=mock_input_model,
-            input_data=input_data,
-            creds_manager=manager,
-            user_id="user-1",
-        )
-
-
-@pytest.mark.asyncio
-async def test_auto_credentials_field_absent_skips(
-    mocker: MockerFixture,
-    mock_input_model,
-    mock_creds_manager,
-):
-    """
-    When the field key is NOT in input_data at all (upstream connection),
-    should skip without error.
-    """
-    from backend.executor.manager import _acquire_auto_credentials
-
-    manager, _, _ = mock_creds_manager
-    # Key not present = connected from upstream block
-    input_data = {}
-
-    extra_kwargs, locks = await _acquire_auto_credentials(
-        input_model=mock_input_model,
-        input_data=input_data,
-        creds_manager=manager,
-        user_id="user-1",
-    )
-
-    manager.acquire.assert_not_called()
-    assert "credentials" not in extra_kwargs
-    assert locks == []
-
-
-@pytest.mark.asyncio
-async def test_auto_credentials_chained_cred_id_none(
-    mocker: MockerFixture,
-    google_drive_file_data,
-    mock_input_model,
-    mock_creds_manager,
-):
-    """
-    When _credentials_id is explicitly None (chained data from upstream),
-    should skip credential acquisition.
-    """
-    from backend.executor.manager import _acquire_auto_credentials
-
-    manager, _, _ = mock_creds_manager
-    input_data = {"spreadsheet": google_drive_file_data["chained"]}
-
-    extra_kwargs, locks = await _acquire_auto_credentials(
-        input_model=mock_input_model,
-        input_data=input_data,
-        creds_manager=manager,
-        user_id="user-1",
-    )
-
-    manager.acquire.assert_not_called()
-    assert "credentials" not in extra_kwargs
-
-
-@pytest.mark.asyncio
-async def test_auto_credentials_missing_cred_id_key_raises(
-    mocker: MockerFixture,
-    google_drive_file_data,
-    mock_input_model,
-    mock_creds_manager,
-):
-    """
-    When _credentials_id key is missing entirely from field_data dict,
-    should raise ValueError.
-    """
-    from backend.executor.manager import _acquire_auto_credentials
-
-    manager, _, _ = mock_creds_manager
-    input_data = {"spreadsheet": google_drive_file_data["missing_key"]}
-
-    with pytest.raises(ValueError, match="Authentication missing"):
-        await _acquire_auto_credentials(
-            input_model=mock_input_model,
-            input_data=input_data,
-            creds_manager=manager,
-            user_id="user-1",
-        )
-
-
-@pytest.mark.asyncio
-async def test_auto_credentials_ownership_mismatch_error(
-    mocker: MockerFixture,
-    google_drive_file_data,
-    mock_input_model,
-    mock_creds_manager,
-):
-    """
-    [SECRT-1772] When acquire() raises ValueError (credential belongs to another user),
-    the error message should mention 'not available' (not 'expired').
-    """
-    from backend.executor.manager import _acquire_auto_credentials
-
-    manager, _, _ = mock_creds_manager
-    manager.acquire.side_effect = ValueError(
-        "Credentials #cred-id-123 for user #user-2 not found"
-    )
-    input_data = {"spreadsheet": google_drive_file_data["valid"]}
-
-    with pytest.raises(ValueError, match="not available in your account"):
-        await _acquire_auto_credentials(
-            input_model=mock_input_model,
-            input_data=input_data,
-            creds_manager=manager,
-            user_id="user-2",
-        )
-
-
-@pytest.mark.asyncio
-async def test_auto_credentials_deleted_credential_error(
-    mocker: MockerFixture,
-    google_drive_file_data,
-    mock_input_model,
-    mock_creds_manager,
-):
-    """
-    [SECRT-1772] When acquire() raises ValueError (credential was deleted),
-    the error message should mention 'not available' (not 'expired').
-    """
-    from backend.executor.manager import _acquire_auto_credentials
-
-    manager, _, _ = mock_creds_manager
-    manager.acquire.side_effect = ValueError(
-        "Credentials #cred-id-123 for user #user-1 not found"
-    )
-    input_data = {"spreadsheet": google_drive_file_data["valid"]}
-
-    with pytest.raises(ValueError, match="not available in your account"):
-        await _acquire_auto_credentials(
-            input_model=mock_input_model,
-            input_data=input_data,
-            creds_manager=manager,
-            user_id="user-1",
-        )
-
-
-@pytest.mark.asyncio
-async def test_auto_credentials_lock_appended(
-    mocker: MockerFixture,
-    google_drive_file_data,
-    mock_input_model,
-    mock_creds_manager,
-):
-    """Lock from acquire() should be included in returned locks list."""
-    from backend.executor.manager import _acquire_auto_credentials
-
-    manager, _, mock_lock = mock_creds_manager
-    input_data = {"spreadsheet": google_drive_file_data["valid"]}
-
-    extra_kwargs, locks = await _acquire_auto_credentials(
-        input_model=mock_input_model,
-        input_data=input_data,
-        creds_manager=manager,
-        user_id="user-1",
-    )
-
-    assert len(locks) == 1
-    assert locks[0] is mock_lock
-
-
-@pytest.mark.asyncio
-async def test_auto_credentials_multiple_fields(
-    mocker: MockerFixture,
-    mock_creds_manager,
-):
-    """When there are multiple auto_credentials fields, only valid ones should acquire."""
-    from backend.executor.manager import _acquire_auto_credentials
-
-    manager, mock_creds, mock_lock = mock_creds_manager
-
-    input_model = mocker.MagicMock()
-    input_model.get_auto_credentials_fields.return_value = {
-        "credentials": {
-            "field_name": "spreadsheet",
-            "config": {"provider": "google", "type": "oauth2"},
-        },
-        "credentials2": {
-            "field_name": "doc_file",
-            "config": {"provider": "google", "type": "oauth2"},
-        },
-    }
-
-    input_data = {
-        "spreadsheet": {
-            "_credentials_id": "cred-id-123",
-            "id": "file-1",
-            "name": "file1.xlsx",
-        },
-        "doc_file": {
-            "_credentials_id": None,
-            "id": "file-2",
-            "name": "chained.doc",
-        },
-    }
-
-    extra_kwargs, locks = await _acquire_auto_credentials(
-        input_model=input_model,
-        input_data=input_data,
-        creds_manager=manager,
-        user_id="user-1",
-    )
-
-    # Only the first field should have acquired credentials
-    manager.acquire.assert_called_once_with("user-1", "cred-id-123")
-    assert "credentials" in extra_kwargs
-    assert "credentials2" not in extra_kwargs
-    assert len(locks) == 1

autogpt_platform/backend/backend/executor/utils.py

@@ -4,7 +4,7 @@ import threading
 import time
 from collections import defaultdict
 from concurrent.futures import Future
-from typing import Any, Mapping, Optional, cast
+from typing import Mapping, Optional, cast
 
 from pydantic import BaseModel, JsonValue, ValidationError
 
@@ -55,87 +55,6 @@ from backend.util.type import convert
 config = Config()
 logger = TruncatedLogger(logging.getLogger(__name__), prefix="[GraphExecutorUtil]")
 
-# ============ Auto-Credentials Helpers ============ #
-
-
-class AutoCredentialFieldInfo(BaseModel):
-    """Parsed info from an auto-credential field (e.g., GoogleDriveFileField)."""
-
-    cred_id: str | None
-    """The credential ID to use, or None if not provided."""
-    provider: str
-    """The provider name (e.g., 'google')."""
-    file_name: str
-    """The display name for error messages."""
-    field_name: str
-    """The original field name in the schema."""
-    error: str | None = None
-    """Validation error message, if any."""
-
-
-def parse_auto_credential_field(
-    field_name: str,
-    info: dict,
-    field_data: Any,
-    *,
-    field_present_in_input: bool = True,
-) -> AutoCredentialFieldInfo:
-    """
-    Parse auto-credential field data and extract credential info.
-
-    This is shared logic used by both credential acquisition (manager.py)
-    and credential validation (utils.py).
-
-    Args:
-        field_name: The name of the field in the schema
-        info: The auto_credentials field info from get_auto_credentials_fields()
-        field_data: The actual field data from input
-        field_present_in_input: Whether the field key exists in input_data
-
-    Returns:
-        AutoCredentialFieldInfo with parsed data and any validation errors
-    """
-    provider = info.get("config", {}).get("provider", "external service")
-    file_name = (
-        field_data.get("name", "selected file")
-        if isinstance(field_data, dict)
-        else "selected file"
-    )
-
-    result = AutoCredentialFieldInfo(
-        cred_id=None,
-        provider=provider,
-        file_name=file_name,
-        field_name=field_name,
-    )
-
-    if field_data and isinstance(field_data, dict):
-        if "_credentials_id" not in field_data:
-            # Key removed (e.g., on fork) — needs re-auth
-            result.error = (
-                f"Authentication missing for '{file_name}' in field "
-                f"'{field_name}'. Please re-select the file to authenticate "
-                f"with {provider.capitalize()}."
-            )
-        else:
-            cred_id = field_data.get("_credentials_id")
-            if cred_id:
-                result.cred_id = cred_id
-            # else: _credentials_id is explicitly None, skip (chained data)
-    elif field_data is None and not field_present_in_input:
-        # Field not in input_data at all = connected from upstream block, skip
-        pass
-    elif field_present_in_input:
-        # field_data is None/empty but key IS in input_data = user didn't select
-        result.error = (
-            f"No file selected for '{field_name}'. "
-            f"Please select a file to provide "
-            f"{provider.capitalize()} authentication."
-        )
-
-    return result
-
-
 # ============ Resource Helpers ============ #
 
 
@@ -340,8 +259,7 @@ async def _validate_node_input_credentials(
 
         # Find any fields of type CredentialsMetaInput
         credentials_fields = block.input_schema.get_credentials_fields()
-        auto_credentials_fields = block.input_schema.get_auto_credentials_fields()
-        if not credentials_fields and not auto_credentials_fields:
+        if not credentials_fields:
             continue
 
         # Track if any credential field is missing for this node
@@ -421,52 +339,6 @@ async def _validate_node_input_credentials(
                 ] = "Invalid credentials: type/provider mismatch"
                 continue
 
-        # Validate auto-credentials (GoogleDriveFileField-based)
-        # These have _credentials_id embedded in the file field data
-        if auto_credentials_fields:
-            for _kwarg_name, info in auto_credentials_fields.items():
-                field_name = info["field_name"]
-                # Check input_default and nodes_input_masks for the field value
-                field_value = node.input_default.get(field_name)
-                if nodes_input_masks and node.id in nodes_input_masks:
-                    field_value = nodes_input_masks[node.id].get(
-                        field_name, field_value
-                    )
-
-                # Use shared helper to parse the field
-                parsed = parse_auto_credential_field(
-                    field_name=field_name,
-                    info=info,
-                    field_data=field_value,
-                    field_present_in_input=True,  # For validation, assume present
-                )
-
-                if parsed.error:
-                    has_missing_credentials = True
-                    credential_errors[node.id][field_name] = parsed.error
-                    continue
-
-                if parsed.cred_id:
-                    # Validate that credentials exist and are accessible
-                    try:
-                        creds_store = get_integration_credentials_store()
-                        creds = await creds_store.get_creds_by_id(
-                            user_id, parsed.cred_id
-                        )
-                    except Exception as e:
-                        has_missing_credentials = True
-                        credential_errors[node.id][
-                            field_name
-                        ] = f"Credentials not available: {e}"
-                        continue
-                    if not creds:
-                        has_missing_credentials = True
-                        credential_errors[node.id][field_name] = (
-                            "The saved credentials are not available "
-                            "for your account. Please re-select the file to "
-                            "authenticate with your own account."
-                        )
-
         # If node has optional credentials and any are missing, mark for skipping
         # But only if there are no other errors for this node
         if (
@@ -498,9 +370,8 @@ def make_node_credentials_input_map(
     """
     result: dict[str, dict[str, JsonValue]] = {}
 
-    # Only map regular credentials (not auto_credentials, which are resolved
-    # at execution time from _credentials_id in file field data)
-    graph_cred_inputs = graph.regular_credentials_inputs
+    # Get aggregated credentials fields for the graph
+    graph_cred_inputs = graph.aggregate_credentials_inputs()
 
     for graph_input_name, (_, compatible_node_fields, _) in graph_cred_inputs.items():
         # Best-effort map: skip missing items

autogpt_platform/backend/backend/executor/utils_test.py

@@ -907,335 +907,3 @@ async def test_stop_graph_execution_cascades_to_child_with_reviews(
 
     # Verify both parent and child status updates
     assert mock_execution_db.update_graph_execution_stats.call_count >= 1
-
-
-# ============================================================================
-# Tests for auto_credentials validation in _validate_node_input_credentials
-# (Fix 3: SECRT-1772 + Fix 4: Path 4)
-# ============================================================================
-
-
-@pytest.mark.asyncio
-async def test_validate_node_input_credentials_auto_creds_valid(
-    mocker: MockerFixture,
-):
-    """
-    [SECRT-1772] When a node has auto_credentials with a valid _credentials_id
-    that exists in the store, validation should pass without errors.
-    """
-    from backend.executor.utils import _validate_node_input_credentials
-
-    mock_node = mocker.MagicMock()
-    mock_node.id = "node-with-auto-creds"
-    mock_node.credentials_optional = False
-    mock_node.input_default = {
-        "spreadsheet": {
-            "_credentials_id": "valid-cred-id",
-            "id": "file-123",
-            "name": "test.xlsx",
-        }
-    }
-
-    mock_block = mocker.MagicMock()
-    # No regular credentials fields
-    mock_block.input_schema.get_credentials_fields.return_value = {}
-    # Has auto_credentials fields
-    mock_block.input_schema.get_auto_credentials_fields.return_value = {
-        "credentials": {
-            "field_name": "spreadsheet",
-            "config": {"provider": "google", "type": "oauth2"},
-        }
-    }
-    mock_node.block = mock_block
-
-    mock_graph = mocker.MagicMock()
-    mock_graph.nodes = [mock_node]
-
-    # Mock the credentials store to return valid credentials
-    mock_store = mocker.MagicMock()
-    mock_creds = mocker.MagicMock()
-    mock_creds.id = "valid-cred-id"
-    mock_store.get_creds_by_id = mocker.AsyncMock(return_value=mock_creds)
-    mocker.patch(
-        "backend.executor.utils.get_integration_credentials_store",
-        return_value=mock_store,
-    )
-
-    errors, nodes_to_skip = await _validate_node_input_credentials(
-        graph=mock_graph,
-        user_id="test-user",
-        nodes_input_masks=None,
-    )
-
-    assert mock_node.id not in errors
-    assert mock_node.id not in nodes_to_skip
-
-
-@pytest.mark.asyncio
-async def test_validate_node_input_credentials_auto_creds_missing(
-    mocker: MockerFixture,
-):
-    """
-    [SECRT-1772] When a node has auto_credentials with a _credentials_id
-    that doesn't exist for the current user, validation should report an error.
-    """
-    from backend.executor.utils import _validate_node_input_credentials
-
-    mock_node = mocker.MagicMock()
-    mock_node.id = "node-with-bad-auto-creds"
-    mock_node.credentials_optional = False
-    mock_node.input_default = {
-        "spreadsheet": {
-            "_credentials_id": "other-users-cred-id",
-            "id": "file-123",
-            "name": "test.xlsx",
-        }
-    }
-
-    mock_block = mocker.MagicMock()
-    mock_block.input_schema.get_credentials_fields.return_value = {}
-    mock_block.input_schema.get_auto_credentials_fields.return_value = {
-        "credentials": {
-            "field_name": "spreadsheet",
-            "config": {"provider": "google", "type": "oauth2"},
-        }
-    }
-    mock_node.block = mock_block
-
-    mock_graph = mocker.MagicMock()
-    mock_graph.nodes = [mock_node]
-
-    # Mock the credentials store to return None (cred not found for this user)
-    mock_store = mocker.MagicMock()
-    mock_store.get_creds_by_id = mocker.AsyncMock(return_value=None)
-    mocker.patch(
-        "backend.executor.utils.get_integration_credentials_store",
-        return_value=mock_store,
-    )
-
-    errors, nodes_to_skip = await _validate_node_input_credentials(
-        graph=mock_graph,
-        user_id="different-user",
-        nodes_input_masks=None,
-    )
-
-    assert mock_node.id in errors
-    assert "spreadsheet" in errors[mock_node.id]
-    assert "not available" in errors[mock_node.id]["spreadsheet"].lower()
-
-
-@pytest.mark.asyncio
-async def test_validate_node_input_credentials_both_regular_and_auto(
-    mocker: MockerFixture,
-):
-    """
-    [SECRT-1772] A node that has BOTH regular credentials AND auto_credentials
-    should have both validated.
-    """
-    from backend.executor.utils import _validate_node_input_credentials
-
-    mock_node = mocker.MagicMock()
-    mock_node.id = "node-with-both-creds"
-    mock_node.credentials_optional = False
-    mock_node.input_default = {
-        "credentials": {
-            "id": "regular-cred-id",
-            "provider": "github",
-            "type": "api_key",
-        },
-        "spreadsheet": {
-            "_credentials_id": "auto-cred-id",
-            "id": "file-123",
-            "name": "test.xlsx",
-        },
-    }
-
-    mock_credentials_field_type = mocker.MagicMock()
-    mock_credentials_meta = mocker.MagicMock()
-    mock_credentials_meta.id = "regular-cred-id"
-    mock_credentials_meta.provider = "github"
-    mock_credentials_meta.type = "api_key"
-    mock_credentials_field_type.model_validate.return_value = mock_credentials_meta
-
-    mock_block = mocker.MagicMock()
-    # Regular credentials field
-    mock_block.input_schema.get_credentials_fields.return_value = {
-        "credentials": mock_credentials_field_type,
-    }
-    # Auto-credentials field
-    mock_block.input_schema.get_auto_credentials_fields.return_value = {
-        "auto_credentials": {
-            "field_name": "spreadsheet",
-            "config": {"provider": "google", "type": "oauth2"},
-        }
-    }
-    mock_node.block = mock_block
-
-    mock_graph = mocker.MagicMock()
-    mock_graph.nodes = [mock_node]
-
-    # Mock the credentials store to return valid credentials for both
-    mock_store = mocker.MagicMock()
-    mock_regular_creds = mocker.MagicMock()
-    mock_regular_creds.id = "regular-cred-id"
-    mock_regular_creds.provider = "github"
-    mock_regular_creds.type = "api_key"
-
-    mock_auto_creds = mocker.MagicMock()
-    mock_auto_creds.id = "auto-cred-id"
-
-    def get_creds_side_effect(user_id, cred_id):
-        if cred_id == "regular-cred-id":
-            return mock_regular_creds
-        elif cred_id == "auto-cred-id":
-            return mock_auto_creds
-        return None
-
-    mock_store.get_creds_by_id = mocker.AsyncMock(side_effect=get_creds_side_effect)
-    mocker.patch(
-        "backend.executor.utils.get_integration_credentials_store",
-        return_value=mock_store,
-    )
-
-    errors, nodes_to_skip = await _validate_node_input_credentials(
-        graph=mock_graph,
-        user_id="test-user",
-        nodes_input_masks=None,
-    )
-
-    # Both should validate successfully - no errors
-    assert mock_node.id not in errors
-    assert mock_node.id not in nodes_to_skip
-
-
-@pytest.mark.asyncio
-async def test_validate_node_input_credentials_auto_creds_skipped_when_none(
-    mocker: MockerFixture,
-):
-    """
-    When a node has auto_credentials but the field value has _credentials_id=None
-    (e.g., from upstream connection), validation should skip it without error.
-    """
-    from backend.executor.utils import _validate_node_input_credentials
-
-    mock_node = mocker.MagicMock()
-    mock_node.id = "node-with-chained-auto-creds"
-    mock_node.credentials_optional = False
-    mock_node.input_default = {
-        "spreadsheet": {
-            "_credentials_id": None,
-            "id": "file-123",
-            "name": "test.xlsx",
-        }
-    }
-
-    mock_block = mocker.MagicMock()
-    mock_block.input_schema.get_credentials_fields.return_value = {}
-    mock_block.input_schema.get_auto_credentials_fields.return_value = {
-        "credentials": {
-            "field_name": "spreadsheet",
-            "config": {"provider": "google", "type": "oauth2"},
-        }
-    }
-    mock_node.block = mock_block
-
-    mock_graph = mocker.MagicMock()
-    mock_graph.nodes = [mock_node]
-
-    errors, nodes_to_skip = await _validate_node_input_credentials(
-        graph=mock_graph,
-        user_id="test-user",
-        nodes_input_masks=None,
-    )
-
-    # No error - chained data with None cred_id is valid
-    assert mock_node.id not in errors
-
-
-# ============================================================================
-# Tests for CredentialsFieldInfo auto_credential tag (Fix 4: Path 4)
-# ============================================================================
-
-
-def test_credentials_field_info_auto_credential_tag():
-    """
-    [Path 4] CredentialsFieldInfo should support is_auto_credential and
-    input_field_name fields for distinguishing auto from regular credentials.
-    """
-    from backend.data.model import CredentialsFieldInfo
-
-    # Regular credential should have is_auto_credential=False by default
-    regular = CredentialsFieldInfo.model_validate(
-        {
-            "credentials_provider": ["github"],
-            "credentials_types": ["api_key"],
-        },
-        by_alias=True,
-    )
-    assert regular.is_auto_credential is False
-    assert regular.input_field_name is None
-
-    # Auto credential should have is_auto_credential=True
-    auto = CredentialsFieldInfo.model_validate(
-        {
-            "credentials_provider": ["google"],
-            "credentials_types": ["oauth2"],
-            "is_auto_credential": True,
-            "input_field_name": "spreadsheet",
-        },
-        by_alias=True,
-    )
-    assert auto.is_auto_credential is True
-    assert auto.input_field_name == "spreadsheet"
-
-
-def test_make_node_credentials_input_map_excludes_auto_creds(
-    mocker: MockerFixture,
-):
-    """
-    [Path 4] make_node_credentials_input_map should only include regular credentials,
-    not auto_credentials (which are resolved at execution time).
-    """
-    from backend.data.model import CredentialsFieldInfo, CredentialsMetaInput
-    from backend.executor.utils import make_node_credentials_input_map
-    from backend.integrations.providers import ProviderName
-
-    # Create a mock graph with aggregate_credentials_inputs that returns
-    # both regular and auto credentials
-    mock_graph = mocker.MagicMock()
-
-    regular_field_info = CredentialsFieldInfo.model_validate(
-        {
-            "credentials_provider": ["github"],
-            "credentials_types": ["api_key"],
-            "is_auto_credential": False,
-        },
-        by_alias=True,
-    )
-
-    # Mock regular_credentials_inputs property (auto_credentials are excluded)
-    mock_graph.regular_credentials_inputs = {
-        "github_creds": (regular_field_info, {("node-1", "credentials")}, True),
-    }
-
-    graph_credentials_input = {
-        "github_creds": CredentialsMetaInput(
-            id="cred-123",
-            provider=ProviderName("github"),
-            type="api_key",
-        ),
-    }
-
-    result = make_node_credentials_input_map(mock_graph, graph_credentials_input)
-
-    # Regular credentials should be mapped
-    assert "node-1" in result
-    assert "credentials" in result["node-1"]
-
-    # Auto credentials should NOT appear in the result
-    # (they would have been mapped to the kwarg_name "credentials" not "spreadsheet")
-    for node_id, fields in result.items():
-        for field_name, value in fields.items():
-            # Verify no auto-credential phantom entries
-            if isinstance(value, dict):
-                assert "_credentials_id" not in value

autogpt_platform/backend/backend/util/file.py

@@ -342,6 +342,14 @@ async def store_media_file(
         if not target_path.is_file():
             raise ValueError(f"Local file does not exist: {target_path}")
 
+        # Virus scan the local file before any further processing
+        local_content = target_path.read_bytes()
+        if len(local_content) > MAX_FILE_SIZE_BYTES:
+            raise ValueError(
+                f"File too large: {len(local_content)} bytes > {MAX_FILE_SIZE_BYTES} bytes"
+            )
+        await scan_content_safe(local_content, filename=sanitized_file)
+
     # Return based on requested format
     if return_format == "for_local_processing":
         # Use when processing files locally with tools like ffmpeg, MoviePy, PIL

autogpt_platform/backend/backend/util/file_test.py

@@ -247,3 +247,100 @@ class TestFileCloudIntegration:
                     execution_context=make_test_context(graph_exec_id=graph_exec_id),
                     return_format="for_local_processing",
                 )
+
+    @pytest.mark.asyncio
+    async def test_store_media_file_local_path_scanned(self):
+        """Test that local file paths are scanned for viruses."""
+        graph_exec_id = "test-exec-123"
+        local_file = "test_video.mp4"
+        file_content = b"fake video content"
+
+        with patch(
+            "backend.util.file.get_cloud_storage_handler"
+        ) as mock_handler_getter, patch(
+            "backend.util.file.scan_content_safe"
+        ) as mock_scan, patch(
+            "backend.util.file.Path"
+        ) as mock_path_class:
+
+            # Mock cloud storage handler - not a cloud path
+            mock_handler = MagicMock()
+            mock_handler.is_cloud_path.return_value = False
+            mock_handler_getter.return_value = mock_handler
+
+            # Mock virus scanner
+            mock_scan.return_value = None
+
+            # Mock file system operations
+            mock_base_path = MagicMock()
+            mock_target_path = MagicMock()
+            mock_resolved_path = MagicMock()
+
+            mock_path_class.return_value = mock_base_path
+            mock_base_path.mkdir = MagicMock()
+            mock_base_path.__truediv__ = MagicMock(return_value=mock_target_path)
+            mock_target_path.resolve.return_value = mock_resolved_path
+            mock_resolved_path.is_relative_to.return_value = True
+            mock_resolved_path.is_file.return_value = True
+            mock_resolved_path.read_bytes.return_value = file_content
+            mock_resolved_path.relative_to.return_value = Path(local_file)
+            mock_resolved_path.name = local_file
+
+            result = await store_media_file(
+                file=MediaFileType(local_file),
+                execution_context=make_test_context(graph_exec_id=graph_exec_id),
+                return_format="for_local_processing",
+            )
+
+            # Verify virus scan was called for local file
+            mock_scan.assert_called_once_with(file_content, filename=local_file)
+
+            # Result should be the relative path
+            assert str(result) == local_file
+
+    @pytest.mark.asyncio
+    async def test_store_media_file_local_path_virus_detected(self):
+        """Test that infected local files raise VirusDetectedError."""
+        from backend.api.features.store.exceptions import VirusDetectedError
+
+        graph_exec_id = "test-exec-123"
+        local_file = "infected.exe"
+        file_content = b"malicious content"
+
+        with patch(
+            "backend.util.file.get_cloud_storage_handler"
+        ) as mock_handler_getter, patch(
+            "backend.util.file.scan_content_safe"
+        ) as mock_scan, patch(
+            "backend.util.file.Path"
+        ) as mock_path_class:
+
+            # Mock cloud storage handler - not a cloud path
+            mock_handler = MagicMock()
+            mock_handler.is_cloud_path.return_value = False
+            mock_handler_getter.return_value = mock_handler
+
+            # Mock virus scanner to detect virus
+            mock_scan.side_effect = VirusDetectedError(
+                "EICAR-Test-File", "File rejected due to virus detection"
+            )
+
+            # Mock file system operations
+            mock_base_path = MagicMock()
+            mock_target_path = MagicMock()
+            mock_resolved_path = MagicMock()
+
+            mock_path_class.return_value = mock_base_path
+            mock_base_path.mkdir = MagicMock()
+            mock_base_path.__truediv__ = MagicMock(return_value=mock_target_path)
+            mock_target_path.resolve.return_value = mock_resolved_path
+            mock_resolved_path.is_relative_to.return_value = True
+            mock_resolved_path.is_file.return_value = True
+            mock_resolved_path.read_bytes.return_value = file_content
+
+            with pytest.raises(VirusDetectedError):
+                await store_media_file(
+                    file=MediaFileType(local_file),
+                    execution_context=make_test_context(graph_exec_id=graph_exec_id),
+                    return_format="for_local_processing",
+                )

autogpt_platform/backend/pyproject.toml

@@ -12,16 +12,16 @@ python = ">=3.10,<3.14"
 aio-pika = "^9.5.5"
 aiohttp = "^3.10.0"
 aiodns = "^3.5.0"
-anthropic = "^0.59.0"
+anthropic = "^0.79.0"
 apscheduler = "^3.11.1"
 autogpt-libs = { path = "../autogpt_libs", develop = true }
 bleach = { extras = ["css"], version = "^6.2.0" }
 click = "^8.2.0"
-cryptography = "^45.0"
+cryptography = "^46.0"
 discord-py = "^2.5.2"
 e2b-code-interpreter = "^1.5.2"
 elevenlabs = "^1.50.0"
-fastapi = "^0.116.1"
+fastapi = "^0.128.5"
 feedparser = "^6.0.11"
 flake8 = "^7.3.0"
 google-api-python-client = "^2.177.0"
@@ -35,10 +35,10 @@ jinja2 = "^3.1.6"
 jsonref = "^1.1.0"
 jsonschema = "^4.25.0"
 langfuse = "^3.11.0"
-launchdarkly-server-sdk = "^9.12.0"
+launchdarkly-server-sdk = "^9.14.1"
 mem0ai = "^0.1.115"
 moviepy = "^2.1.2"
-ollama = "^0.5.1"
+ollama = "^0.6.1"
 openai = "^1.97.1"
 orjson = "^3.10.0"
 pika = "^1.3.2"
@@ -48,16 +48,16 @@ postmarker = "^1.0"
 praw = "~7.8.1"
 prisma = "^0.15.0"
 rank-bm25 = "^0.2.2"
-prometheus-client = "^0.22.1"
+prometheus-client = "^0.24.1"
 prometheus-fastapi-instrumentator = "^7.0.0"
 psutil = "^7.0.0"
 psycopg2-binary = "^2.9.10"
-pydantic = { extras = ["email"], version = "^2.11.7" }
-pydantic-settings = "^2.10.1"
+pydantic = { extras = ["email"], version = "^2.12.5" }
+pydantic-settings = "^2.12.0"
 pytest = "^8.4.1"
 pytest-asyncio = "^1.1.0"
 python-dotenv = "^1.1.1"
-python-multipart = "^0.0.20"
+python-multipart = "^0.0.22"
 redis = "^6.2.0"
 regex = "^2025.9.18"
 replicate = "^1.0.6"
@@ -65,11 +65,11 @@ sentry-sdk = {extras = ["anthropic", "fastapi", "launchdarkly", "openai", "sqlal
 sqlalchemy = "^2.0.40"
 strenum = "^0.4.9"
 stripe = "^11.5.0"
-supabase = "2.17.0"
-tenacity = "^9.1.2"
+supabase = "2.27.3"
+tenacity = "^9.1.4"
 todoist-api-python = "^2.1.7"
 tweepy = "^4.16.0"
-uvicorn = { extras = ["standard"], version = "^0.35.0" }
+uvicorn = { extras = ["standard"], version = "^0.40.0" }
 websockets = "^15.0"
 youtube-transcript-api = "^1.2.1"
 yt-dlp = "2025.12.08"
@@ -77,7 +77,7 @@ zerobouncesdk = "^1.1.2"
 # NOTE: please insert new dependencies in their alphabetical location
 pytest-snapshot = "^0.9.0"
 aiofiles = "^24.1.0"
-tiktoken = "^0.9.0"
+tiktoken = "^0.12.0"
 aioclamd = "^1.0.0"
 setuptools = "^80.9.0"
 gcloud-aio-storage = "^9.5.0"
@@ -95,13 +95,13 @@ black = "^24.10.0"
 faker = "^38.2.0"
 httpx = "^0.28.1"
 isort = "^5.13.2"
-poethepoet = "^0.37.0"
+poethepoet = "^0.41.0"
 pre-commit = "^4.4.0"
 pyright = "^1.1.407"
 pytest-mock = "^3.15.1"
-pytest-watcher = "^0.4.2"
+pytest-watcher = "^0.6.3"
 requests = "^2.32.5"
-ruff = "^0.14.5"
+ruff = "^0.15.0"
 # NOTE: please insert new dependencies in their alphabetical location
 
 [build-system]

autogpt_platform/frontend/package.json

@@ -102,7 +102,7 @@
     "react-markdown": "9.0.3",
     "react-modal": "3.16.3",
     "react-shepherd": "6.1.9",
-    "react-window": "1.8.11",
+    "react-window": "2.2.0",
     "recharts": "3.3.0",
     "rehype-autolink-headings": "7.1.0",
     "rehype-highlight": "7.0.2",
@@ -140,7 +140,7 @@
     "@types/react": "18.3.17",
     "@types/react-dom": "18.3.5",
     "@types/react-modal": "3.16.3",
-    "@types/react-window": "1.8.8",
+    "@types/react-window": "2.0.0",
     "@vitejs/plugin-react": "5.1.2",
     "axe-playwright": "2.2.2",
     "chromatic": "13.3.3",

autogpt_platform/frontend/pnpm-lock.yaml

@@ -228,8 +228,8 @@ importers:
         specifier: 6.1.9
         version: 6.1.9(react-dom@18.3.1(react@18.3.1))(react@18.3.1)(typescript@5.9.3)
       react-window:
-        specifier: 1.8.11
-        version: 1.8.11(react-dom@18.3.1(react@18.3.1))(react@18.3.1)
+        specifier: 2.2.0
+        version: 2.2.0(react-dom@18.3.1(react@18.3.1))(react@18.3.1)
       recharts:
         specifier: 3.3.0
         version: 3.3.0(@types/react@18.3.17)(react-dom@18.3.1(react@18.3.1))(react-is@18.3.1)(react@18.3.1)(redux@5.0.1)
@@ -337,8 +337,8 @@ importers:
         specifier: 3.16.3
         version: 3.16.3
       '@types/react-window':
-        specifier: 1.8.8
-        version: 1.8.8
+        specifier: 2.0.0
+        version: 2.0.0(react-dom@18.3.1(react@18.3.1))(react@18.3.1)
       '@vitejs/plugin-react':
         specifier: 5.1.2
         version: 5.1.2(vite@7.3.1(@types/node@24.10.0)(jiti@2.6.1)(terser@5.44.1)(yaml@2.8.2))
@@ -3469,8 +3469,9 @@ packages:
   '@types/react-modal@3.16.3':
     resolution: {integrity: sha512-xXuGavyEGaFQDgBv4UVm8/ZsG+qxeQ7f77yNrW3n+1J6XAstUy5rYHeIHPh1KzsGc6IkCIdu6lQ2xWzu1jBTLg==}
 
-  '@types/react-window@1.8.8':
-    resolution: {integrity: sha512-8Ls660bHR1AUA2kuRvVG9D/4XpRC6wjAaPT9dil7Ckc76eP9TKWZwwmgfq8Q1LANX3QNDnoU4Zp48A3w+zK69Q==}
+  '@types/react-window@2.0.0':
+    resolution: {integrity: sha512-E8hMDtImEpMk1SjswSvqoSmYvk7GEtyVaTa/GJV++FdDNuMVVEzpAClyJ0nqeKYBrMkGiyH6M1+rPLM0Nu1exQ==}
+    deprecated: This is a stub types definition. react-window provides its own type definitions, so you do not need this installed.
 
   '@types/react@18.3.17':
     resolution: {integrity: sha512-opAQ5no6LqJNo9TqnxBKsgnkIYHozW9KSTlFVoSUJYh1Fl/sswkEoqIugRSm7tbh6pABtYjGAjW+GOS23j8qbw==}
@@ -5976,9 +5977,6 @@ packages:
     resolution: {integrity: sha512-UERzLsxzllchadvbPs5aolHh65ISpKpM+ccLbOJ8/vvpBKmAWf+la7dXFy7Mr0ySHbdHrFv5kGFCUHHe6GFEmw==}
     engines: {node: '>= 4.0.0'}
 
-  memoize-one@5.2.1:
-    resolution: {integrity: sha512-zYiwtZUcYyXKo/np96AGZAckk+FWWsUdJ3cHGGmld7+AhvcWmQyGCYUh1hc4Q/pkOhb65dQR/pqCyK0cOaHz4Q==}
-
   merge-stream@2.0.0:
     resolution: {integrity: sha512-abv/qOcuPfk3URPfDzmZU1LKmuw8kT+0nIHvKrKgFrwifol/doWcdA4ZqsWQ8ENrFKkd67Mfpo/LovbIUsbt3w==}
 
@@ -6891,12 +6889,11 @@ packages:
       '@types/react':
         optional: true
 
-  react-window@1.8.11:
-    resolution: {integrity: sha512-+SRbUVT2scadgFSWx+R1P754xHPEqvcfSfVX10QYg6POOz+WNgkN48pS+BtZNIMGiL1HYrSEiCkwsMS15QogEQ==}
-    engines: {node: '>8.0.0'}
+  react-window@2.2.0:
+    resolution: {integrity: sha512-Y2L7yonHq6K1pQA2P98wT5QdIsEcjBTB7T8o6Mub12hH9eYppXoYu6vgClmcjlh3zfNcW2UrXiJJJqDxUY7GVw==}
     peerDependencies:
-      react: ^15.0.0 || ^16.0.0 || ^17.0.0 || ^18.0.0 || ^19.0.0
-      react-dom: ^15.0.0 || ^16.0.0 || ^17.0.0 || ^18.0.0 || ^19.0.0
+      react: ^18.0.0 || ^19.0.0
+      react-dom: ^18.0.0 || ^19.0.0
 
   react@18.3.1:
     resolution: {integrity: sha512-wS+hAgJShR0KhEvPJArfuPVN1+Hz1t0Y6n5jLrGQbkb4urgPE/0Rve+1kMB1v/oWgHgm4WIcV+i7F2pTVj+2iQ==}
@@ -11603,9 +11600,12 @@ snapshots:
     dependencies:
       '@types/react': 18.3.17
 
-  '@types/react-window@1.8.8':
+  '@types/react-window@2.0.0(react-dom@18.3.1(react@18.3.1))(react@18.3.1)':
     dependencies:
-      '@types/react': 18.3.17
+      react-window: 2.2.0(react-dom@18.3.1(react@18.3.1))(react@18.3.1)
+    transitivePeerDependencies:
+      - react
+      - react-dom
 
   '@types/react@18.3.17':
     dependencies:
@@ -14545,8 +14545,6 @@ snapshots:
     dependencies:
       fs-monkey: 1.1.0
 
-  memoize-one@5.2.1: {}
-
   merge-stream@2.0.0: {}
 
   merge2@1.4.1: {}
@@ -15592,10 +15590,8 @@ snapshots:
     optionalDependencies:
       '@types/react': 18.3.17
 
-  react-window@1.8.11(react-dom@18.3.1(react@18.3.1))(react@18.3.1):
+  react-window@2.2.0(react-dom@18.3.1(react@18.3.1))(react@18.3.1):
     dependencies:
-      '@babel/runtime': 7.28.4
-      memoize-one: 5.2.1
       react: 18.3.1
       react-dom: 18.3.1(react@18.3.1)
 

autogpt_platform/frontend/src/app/api/openapi.json

@@ -12307,7 +12307,9 @@
             "title": "Location"
           },
           "msg": { "type": "string", "title": "Message" },
-          "type": { "type": "string", "title": "Error Type" }
+          "type": { "type": "string", "title": "Error Type" },
+          "input": { "title": "Input" },
+          "ctx": { "type": "object", "title": "Context" }
         },
         "type": "object",
         "required": ["loc", "msg", "type"],

autogpt_platform/frontend/src/components/atoms/FileInput/FileInput.tsx

@@ -104,7 +104,31 @@ export function FileInput(props: Props) {
     return false;
   }
 
-  const getFileLabelFromValue = (val: string) => {
+  const getFileLabelFromValue = (val: unknown): string => {
+    // Handle object format from external API: { name, type, size, data }
+    if (val && typeof val === "object") {
+      const obj = val as Record<string, unknown>;
+      if (typeof obj.name === "string") {
+        return getFileLabel(
+          obj.name,
+          typeof obj.type === "string" ? obj.type : "",
+        );
+      }
+      if (typeof obj.type === "string") {
+        const mimeParts = obj.type.split("/");
+        if (mimeParts.length > 1) {
+          return `${mimeParts[1].toUpperCase()} file`;
+        }
+        return `${obj.type} file`;
+      }
+      return "File";
+    }
+
+    // Handle string values (data URIs or file paths)
+    if (typeof val !== "string") {
+      return "File";
+    }
+
     if (val.startsWith("data:")) {
       const matches = val.match(/^data:([^;]+);/);
       if (matches?.[1]) {

autogpt_platform/frontend/src/components/contextual/GoogleDrivePicker/helpers.ts

@@ -4,9 +4,7 @@ import { loadScript } from "@/services/scripts/scripts";
 export async function loadGoogleAPIPicker(): Promise<void> {
   validateWindow();
 
-  await loadScript("https://apis.google.com/js/api.js", {
-    referrerPolicy: "no-referrer-when-downgrade",
-  });
+  await loadScript("https://apis.google.com/js/api.js");
 
   const googleAPI = window.gapi;
   if (!googleAPI) {
@@ -29,9 +27,7 @@ export async function loadGoogleIdentityServices(): Promise<void> {
     throw new Error("Google Identity Services cannot load on server");
   }
 
-  await loadScript("https://accounts.google.com/gsi/client", {
-    referrerPolicy: "no-referrer-when-downgrade",
-  });
+  await loadScript("https://accounts.google.com/gsi/client");
 
   const google = window.google;
   if (!google?.accounts?.oauth2) {

autogpt_platform/frontend/src/components/layout/Navbar/components/AgentActivityDropdown/components/ActivityDropdown/ActivityDropdown.tsx

@@ -4,7 +4,7 @@ import { Button } from "@/components/atoms/Button/Button";
 import { Input } from "@/components/atoms/Input/Input";
 import { Text } from "@/components/atoms/Text/Text";
 import { Bell, MagnifyingGlass, X } from "@phosphor-icons/react";
-import { FixedSizeList as List } from "react-window";
+import { List, type RowComponentProps } from "react-window";
 import { AgentExecutionWithInfo } from "../../helpers";
 import { ActivityItem } from "../ActivityItem";
 import styles from "./styles.module.css";
@@ -19,14 +19,16 @@ interface Props {
   recentFailures: AgentExecutionWithInfo[];
 }
 
-interface VirtualizedItemProps {
-  index: number;
-  style: React.CSSProperties;
-  data: AgentExecutionWithInfo[];
+interface ActivityRowProps {
+  executions: AgentExecutionWithInfo[];
 }
 
-function VirtualizedActivityItem({ index, style, data }: VirtualizedItemProps) {
-  const execution = data[index];
+function VirtualizedActivityItem({
+  index,
+  style,
+  executions,
+}: RowComponentProps<ActivityRowProps>) {
+  const execution = executions[index];
   return (
     <div style={style}>
       <ActivityItem execution={execution} />
@@ -129,14 +131,13 @@ export function ActivityDropdown({
       >
         {filteredExecutions.length > 0 ? (
           <List
-            height={listHeight}
-            width={320} // Match dropdown width (w-80 = 20rem = 320px)
-            itemCount={filteredExecutions.length}
-            itemSize={itemHeight}
-            itemData={filteredExecutions}
-          >
-            {VirtualizedActivityItem}
-          </List>
+            defaultHeight={listHeight}
+            rowCount={filteredExecutions.length}
+            rowHeight={itemHeight}
+            rowProps={{ executions: filteredExecutions }}
+            rowComponent={VirtualizedActivityItem}
+            style={{ width: 320, height: listHeight }}
+          />
         ) : (
           <div className="flex h-full flex-col items-center justify-center gap-5 pb-8 pt-6">
             <div className="mx-auto inline-flex flex-col items-center justify-center rounded-full bg-bgLightGrey p-6">