## Summary
- When the copilot model responds with both text content AND a
long-running tool call (e.g., `create_agent`), the streaming code
created two separate consecutive assistant messages — one with text, one
with `tool_calls`. This caused Anthropic's API to reject with
`"unexpected tool_use_id found in tool_result blocks"` because the
`tool_result` couldn't find a matching `tool_use` in the immediately
preceding assistant message.
- Added a defensive merge of consecutive assistant messages in
`to_openai_messages()` (fixes existing corrupt sessions too)
- Fixed `_yield_tool_call` to add tool_calls to the existing
current-turn assistant message instead of creating a new one
- Changed `accumulated_tool_calls` assignment to use `extend` to prevent
overwriting tool_calls added by long-running tool flow
## Test plan
- [x] All 23 chat feature tests pass (`backend/api/features/chat/`)
- [x] All 44 prompt utility tests pass (`backend/util/prompt_test.py`)
- [x] All pre-commit hooks pass (ruff, isort, black, pyright)
- [ ] Manual test: create an agent via copilot, then ask a follow-up
question — should no longer get 400 error
<!-- greptile_comment -->
<h2>Greptile Overview</h2>
<details><summary><h3>Greptile Summary</h3></summary>
Fixes a critical bug where long-running tool calls (like `create_agent`)
caused Anthropic API 400 errors due to split assistant messages. The fix
ensures tool calls are added to the existing assistant message instead
of creating new ones, and adds a defensive merge function to repair any
existing corrupt sessions.
**Key changes:**
- Added `_merge_consecutive_assistant_messages()` to defensively merge
split assistant messages in `to_openai_messages()`
- Modified `_yield_tool_call()` to append tool calls to the current-turn
assistant message instead of creating a new one
- Changed `accumulated_tool_calls` from assignment to `extend` to
preserve tool calls already added by long-running tool flow
**Impact:** Resolves the issue where users received 400 errors after
creating agents via copilot and asking follow-up questions.
</details>
<details><summary><h3>Confidence Score: 4/5</h3></summary>
- Safe to merge with minor verification recommended
- The changes are well-targeted and solve a real API compatibility
issue. The logic is sound: searching backwards for the current assistant
message is correct, and using `extend` instead of assignment prevents
overwriting. The defensive merge in `to_openai_messages()` also fixes
existing corrupt sessions. All existing tests pass according to the PR
description.
- No files require special attention - changes are localized and
defensive
</details>
<details><summary><h3>Sequence Diagram</h3></summary>
```mermaid
sequenceDiagram
participant User
participant StreamAPI as stream_chat_completion
participant Chunks as _stream_chat_chunks
participant ToolCall as _yield_tool_call
participant Session as ChatSession
User->>StreamAPI: Send message
StreamAPI->>Chunks: Stream chat chunks
alt Text + Long-running tool call
Chunks->>StreamAPI: Text delta (content)
StreamAPI->>Session: Append assistant message with content
Chunks->>ToolCall: Tool call detected
Note over ToolCall: OLD: Created new assistant message<br/>NEW: Appends to existing assistant
ToolCall->>Session: Search backwards for current assistant
ToolCall->>Session: Append tool_call to existing message
ToolCall->>Session: Add pending tool result
end
StreamAPI->>StreamAPI: Merge accumulated_tool_calls
Note over StreamAPI: Use extend (not assign)<br/>to preserve existing tool_calls
StreamAPI->>Session: to_openai_messages()
Session->>Session: _merge_consecutive_assistant_messages()
Note over Session: Defensive: Merges any split<br/>assistant messages
Session-->>StreamAPI: Merged messages
StreamAPI->>User: Return response
```
</details>
<!-- greptile_other_comments_section -->
<!-- /greptile_comment -->
## Problem
The agent builder (LLM) misinterprets the HumanInTheLoop block outputs.
It thinks `approved_data` and `rejected_data` will yield status strings
like "APPROVED" or "REJECTED" instead of understanding that the actual
input data passes through.
This leads to unnecessary complexity - the agent builder adds comparison
blocks to check for status strings that don't exist.
## Solution
Enriched the block docstring and all input/output field descriptions to
make it explicit that:
1. The output is the actual data itself, not a status string
2. The routing is determined by which output pin fires
3. How to use the block correctly (connect downstream blocks to
appropriate output pins)
## Changes
- Updated block docstring with clear "How it works" and "Example usage"
sections
- Enhanced `data` input description to explain data flow
- Enhanced `name` input description for reviewer context
- Enhanced `approved_data` output to explicitly state it's NOT a status
string
- Enhanced `rejected_data` output to explicitly state it's NOT a status
string
- Enhanced `review_message` output for clarity
## Testing
Documentation-only change to schema descriptions. No functional changes.
Fixes SECRT-1930
<!-- greptile_comment -->
<h2>Greptile Overview</h2>
<details><summary><h3>Greptile Summary</h3></summary>
Enhanced documentation for the `HumanInTheLoopBlock` to clarify how
output pins work. The key improvement explicitly states that output pins
(`approved_data` and `rejected_data`) yield the actual input data, not
status strings like "APPROVED" or "REJECTED". This prevents the agent
builder (LLM) from misinterpreting the block's behavior and adding
unnecessary comparison blocks.
**Key changes:**
- Added "How it works" and "Example usage" sections to the block
docstring
- Clarified that routing is determined by which output pin fires, not by
comparing output values
- Enhanced all input/output field descriptions with explicit data flow
explanations
- Emphasized that downstream blocks should be connected to the
appropriate output pin based on desired workflow path
This is a documentation-only change with no functional modifications to
the code logic.
</details>
<details><summary><h3>Confidence Score: 5/5</h3></summary>
- This PR is safe to merge with no risk
- Documentation-only change that accurately reflects the existing code
behavior. No functional changes, no runtime impact, and the enhanced
descriptions correctly explain how the block outputs work based on
verification of the implementation code.
- No files require special attention
</details>
<!-- greptile_other_comments_section -->
<!-- /greptile_comment -->
Co-authored-by: Zamil Majdy <zamil.majdy@agpt.co>
## Changes 🏗️
<img width="800" height="621" alt="Screenshot 2026-02-11 at 19 32 39"
src="https://github.com/user-attachments/assets/e97be1a7-972e-4ae0-8dfa-6ade63cf287b"
/>
When the BE API has an error, prevent it from leaking into the stream
and instead handle it gracefully via toast.
## Checklist 📋
### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Run the app locally and trust the changes
<!-- greptile_comment -->
<h2>Greptile Overview</h2>
<details><summary><h3>Greptile Summary</h3></summary>
This PR fixes an issue where backend API stream errors were leaking into
the chat prompt instead of being handled gracefully. The fix involves
both backend and frontend changes to ensure error events conform to the
AI SDK's strict schema.
**Key Changes:**
- **Backend (`response_model.py`)**: Added custom `to_sse()` method for
`StreamError` that only emits `type` and `errorText` fields, stripping
extra fields like `code` and `details` that cause AI SDK validation
failures
- **Backend (`prompt.py`)**: Added validation step after context
compression to remove orphaned tool responses without matching tool
calls, preventing "unexpected tool_use_id" API errors
- **Frontend (`route.ts`)**: Implemented SSE stream normalization with
`normalizeSSEStream()` and `normalizeSSEEvent()` functions to strip
non-conforming fields from error events before they reach the AI SDK
- **Frontend (`ChatMessagesContainer.tsx`)**: Added toast notifications
for errors and improved error display UI with deduplication logic
The changes ensure a clean separation between internal error metadata
(useful for logging/debugging) and the strict schema required by the AI
SDK on the frontend.
</details>
<details><summary><h3>Confidence Score: 4/5</h3></summary>
- This PR is safe to merge with low risk
- The changes are well-structured and address a specific bug with proper
error handling. The dual-layer approach (backend filtering in `to_sse()`
+ frontend normalization) provides defense-in-depth. However, the lack
of automated tests for the new error normalization logic and the
potential for edge cases in SSE parsing prevent a perfect score.
- Pay close attention to
`autogpt_platform/frontend/src/app/api/chat/sessions/[sessionId]/stream/route.ts`
- the SSE normalization logic should be tested with various error
scenarios
</details>
<details><summary><h3>Sequence Diagram</h3></summary>
```mermaid
sequenceDiagram
participant User
participant Frontend as ChatMessagesContainer
participant Proxy as /api/chat/.../stream
participant Backend as Backend API
participant AISDK as AI SDK
User->>Frontend: Send message
Frontend->>Proxy: POST with message
Proxy->>Backend: Forward request with auth
Backend->>Backend: Process message
alt Success Path
Backend->>Proxy: SSE stream (text-delta, etc.)
Proxy->>Proxy: normalizeSSEStream (pass through)
Proxy->>AISDK: Forward SSE events
AISDK->>Frontend: Update messages
Frontend->>User: Display response
else Error Path
Backend->>Backend: StreamError.to_sse()
Note over Backend: Only emit {type, errorText}
Backend->>Proxy: SSE error event
Proxy->>Proxy: normalizeSSEEvent()
Note over Proxy: Strip extra fields (code, details)
Proxy->>AISDK: {type: "error", errorText: "..."}
AISDK->>Frontend: error state updated
Frontend->>Frontend: Toast notification (deduplicated)
Frontend->>User: Show error UI + toast
end
```
</details>
<!-- greptile_other_comments_section -->
<!-- /greptile_comment -->
---------
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
Co-authored-by: Otto-AGPT <otto@agpt.co>
### Changes 🏗️
Added `min-w-0` class to the ContentCard component in the ToolAccordion
to prevent content overflow issues. This CSS fix ensures that the card
properly respects its container width constraints and allows text
truncation to work correctly when content is too wide.
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Verified that tool content displays correctly in the accordion
- [x] Confirmed that long content properly truncates instead of
overflowing
- [x] Tested with various screen sizes to ensure responsive behavior
#### For configuration changes:
- [x] `.env.default` is updated or already compatible with my changes
- [x] `docker-compose.yml` is updated or already compatible with my
changes
<!-- greptile_comment -->
<h2>Greptile Overview</h2>
<details><summary><h3>Greptile Summary</h3></summary>
Added `min-w-0` class to `ContentCard` component to fix text truncation
overflow in grid layouts. This is a standard CSS fix that allows grid
items to shrink below their content size, enabling `truncate` classes on
child elements (`ContentCardTitle`, `ContentCardSubtitle`) to work
correctly. The fix follows the same pattern already used in
`ContentCardHeader` (line 54) and `ToolAccordion` (line 54).
</details>
<details><summary><h3>Confidence Score: 5/5</h3></summary>
- Safe to merge with no risk
- Single-line CSS fix that addresses a well-known flexbox/grid layout
issue. The change follows existing patterns in the codebase and is
thoroughly tested. No logic changes, no breaking changes, no side
effects.
- No files require special attention
</details>
<!-- greptile_other_comments_section -->
<!-- /greptile_comment -->
## Summary
Blocks marked `disabled=True` (like BlockInstallationBlock) were not
being checked during graph validation, allowing them to be used via
direct API calls despite being hidden from the UI.
This adds a security check in `_validate_graph_get_errors()` to reject
any graph containing disabled blocks.
## Security Advisory
GHSA-4crw-9p35-9x54
## Linear
SECRT-1927
## Changes
- Added `block.disabled` check in graph validation (6 lines)
## Testing
- Graphs with disabled blocks → rejected with clear error message
- Graphs with valid blocks → unchanged behavior
<!-- greptile_comment -->
<h2>Greptile Overview</h2>
<details><summary><h3>Greptile Summary</h3></summary>
Adds critical security validation to prevent execution of disabled
blocks (like `BlockInstallationBlock`) via direct API calls. The fix
validates that `block.disabled` is `False` during graph validation in
`_validate_graph_get_errors()` on line 747-750, ensuring disabled blocks
are rejected before graph creation or execution. This closes a
vulnerability where blocks marked disabled in the UI could still be used
through API endpoints.
</details>
<details><summary><h3>Confidence Score: 5/5</h3></summary>
- This PR is safe to merge and addresses a critical security
vulnerability
- The fix is minimal (6 lines), correctly placed in the validation flow,
includes clear security context (GHSA reference), and follows existing
validation patterns. The check is positioned after block existence
validation and before input validation, ensuring disabled blocks are
caught early in both graph creation and execution paths.
- No files require special attention
</details>
<!-- greptile_other_comments_section -->
<!-- /greptile_comment -->
---------
Co-authored-by: Nicholas Tindle <nicholas.tindle@agpt.co>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
### Changes
- Removed `defaultExpanded` prop from `ToolAccordion` in CreateAgent,
EditAgent, RunAgent, and RunBlock components to streamline the code and
improve readability.
### Impact
- This refactor enhances maintainability by reducing complexity in the
component structure while preserving existing functionality.
### Changes 🏗️
- Removed conditional expansion logic from all tool components
- Simplified ToolAccordion implementation across all affected components
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Create and run agents with various tools to verify accordion
behavior works correctly
- [x] Verify that UI components expand and collapse as expected
- [x] Test with different output types to ensure proper rendering
---------
Co-authored-by: Ubbe <hi@ubbe.dev>
Co-authored-by: Lluis Agusti <hi@llu.lu>
## Summary
Enables Anthropic's extended thinking feature for Claude models in
CoPilot via OpenRouter. This keeps the model's chain-of-thought
reasoning internal rather than outputting it to users.
## Problem
The CoPilot prompt was designed for a thinking agent (with
`<internal_reasoning>` tags), but extended thinking wasn't enabled on
the API side. This caused the model to output its reasoning as regular
text, leaking internal analysis to users.
## Solution
Added thinking configuration to the OpenRouter `extra_body` for
Anthropic models:
```python
extra_body["provider"] = {
"anthropic": {
"thinking": {
"type": "enabled",
"budget_tokens": config.thinking_budget_tokens,
}
}
}
```
## Configuration
New settings in `ChatConfig`:
| Setting | Default | Description |
|---------|---------|-------------|
| `thinking_enabled` | `True` | Enable extended thinking for Claude
models |
| `thinking_budget_tokens` | `10000` | Token budget for thinking
(1000-100000) |
## Changes
- `config.py`: Added `thinking_enabled` and `thinking_budget_tokens`
settings
- `service.py`: Added thinking config to all 3 places where `extra_body`
is built for LLM calls
## Testing
- Verify CoPilot responses no longer include internal reasoning text
- Check that Claude's extended thinking is working (should see thinking
tokens in usage)
- Confirm non-Anthropic models are unaffected
## Related
Discussion:
https://discord.com/channels/1126875755960336515/1126875756925046928/1470779843552612607
---------
Co-authored-by: Swifty <craigswift13@gmail.com>
These "is the user authenticated, and should they be?" checks should not
be spread across the codebase, it's complex enough as it is. :')
- Follow-up to #12050
### Changes 🏗️
- Revert "fix(frontend): copilot redirect logout (#12050)"
- Add `/copilot` to `PROTECTED_PAGES` in `@/lib/supabase/helpers`
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Trivial change, we know this works for other pages
Bumps the production-dependencies group in /autogpt_platform/backend
with 2 updates: [fastapi](https://github.com/fastapi/fastapi) and
[langfuse](https://github.com/langfuse/langfuse).
Updates `fastapi` from 0.128.5 to 0.128.6
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/fastapi/fastapi/releases">fastapi's
releases</a>.</em></p>
<blockquote>
<h2>0.128.6</h2>
<h3>Fixes</h3>
<ul>
<li>🐛 Fix <code>on_startup</code> and <code>on_shutdown</code>
parameters of <code>APIRouter</code>. PR <a
href="https://redirect.github.com/fastapi/fastapi/pull/14873">#14873</a>
by <a
href="https://github.com/YuriiMotov"><code>@YuriiMotov</code></a>.</li>
</ul>
<h3>Translations</h3>
<ul>
<li>🌐 Update translations for zh (update-outdated). PR <a
href="https://redirect.github.com/fastapi/fastapi/pull/14843">#14843</a>
by <a
href="https://github.com/tiangolo"><code>@tiangolo</code></a>.</li>
</ul>
<h3>Internal</h3>
<ul>
<li>✅ Fix parameterized tests with snapshots. PR <a
href="https://redirect.github.com/fastapi/fastapi/pull/14875">#14875</a>
by <a
href="https://github.com/YuriiMotov"><code>@YuriiMotov</code></a>.</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="fbca586c1d"><code>fbca586</code></a>
📝 Update release notes</li>
<li><a
href="4e879799dd"><code>4e87979</code></a>
📝 Update release notes</li>
<li><a
href="0a4033aeee"><code>0a4033a</code></a>
🔖 Release version 0.128.6</li>
<li><a
href="ed2512a5ec"><code>ed2512a</code></a>
🐛 Fix <code>on_startup</code> and <code>on_shutdown</code> parameters of
<code>APIRouter</code> (<a
href="https://redirect.github.com/fastapi/fastapi/issues/14873">#14873</a>)</li>
<li><a
href="0c0f6332e2"><code>0c0f633</code></a>
📝 Update release notes</li>
<li><a
href="227cb85a03"><code>227cb85</code></a>
✅ Fix parameterized tests with snapshots (<a
href="https://redirect.github.com/fastapi/fastapi/issues/14875">#14875</a>)</li>
<li><a
href="cd31576d57"><code>cd31576</code></a>
📝 Update release notes</li>
<li><a
href="376e108580"><code>376e108</code></a>
🌐 Update translations for zh (update-outdated) (<a
href="https://redirect.github.com/fastapi/fastapi/issues/14843">#14843</a>)</li>
<li>See full diff in <a
href="https://github.com/fastapi/fastapi/compare/0.128.5...0.128.6">compare
view</a></li>
</ul>
</details>
<br />
Updates `langfuse` from 3.13.0 to 3.14.1
<details>
<summary>Commits</summary>
<ul>
<li>See full diff in <a
href="https://github.com/langfuse/langfuse/commits">compare
view</a></li>
</ul>
</details>
<br />
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore <dependency name> major version` will close this
group update PR and stop Dependabot creating any more for the specific
dependency's major version (unless you unignore this specific
dependency's major version or upgrade to it yourself)
- `@dependabot ignore <dependency name> minor version` will close this
group update PR and stop Dependabot creating any more for the specific
dependency's minor version (unless you unignore this specific
dependency's minor version or upgrade to it yourself)
- `@dependabot ignore <dependency name>` will close this group update PR
and stop Dependabot creating any more for the specific dependency
(unless you unignore this specific dependency or upgrade to it yourself)
- `@dependabot unignore <dependency name>` will remove all of the ignore
conditions of the specified dependency
- `@dependabot unignore <dependency name> <ignore condition>` will
remove the ignore condition of the specified dependency and ignore
conditions
</details>
---------
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Zamil Majdy <zamil.majdy@agpt.co>
Co-authored-by: Otto <otto@agpt.co>
## Changes 🏗️
Redirect to `/login` if the user is not authenticated and tries to
access `/copilot`
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Run the app locally and tested
### Changes 🏗️
- Added AI SDK integration for chat streaming with proper message
handling
- Implemented custom to_sse method in StreamToolOutputAvailable to
exclude non-spec fields
- Modified stream_chat_completion to reuse message IDs for tool call
continuations
- Created new Copilot 2.0 UI with AI SDK React components
- Added streamdown and related packages for markdown rendering
- Built reusable conversation and message components for the chat
interface
- Added support for tool output display in the chat UI
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Start a new chat session and verify streaming works correctly
- [x] Test tool calls and verify they display properly in the UI
- [x] Verify message continuations don't create duplicate messages
- [x] Test markdown rendering with code blocks and other formatting
- [x] Verify the UI is responsive and scrolls correctly
#### For configuration changes:
- [x] `.env.default` is updated or already compatible with my changes
- [x] `docker-compose.yml` is updated or already compatible with my
changes
- [x] I have included a list of my configuration changes in the PR
description (under **Changes**)
---------
Co-authored-by: Lluis Agusti <hi@llu.lu>
Co-authored-by: Ubbe <hi@ubbe.dev>
Adds diagnostic logging when the `type vector does not exist` error
occurs in raw SQL queries.
## Problem
We're seeing intermittent "type vector does not exist" errors on
dev-behave ([Sentry
issue](https://significant-gravitas.sentry.io/issues/7205929979/)). The
pgvector extension should be in the search_path, but occasionally
queries fail to resolve the vector type.
## Solution
When a query fails with this specific error, we now log:
- `SHOW search_path` - what schemas are being searched
- `SELECT current_schema()` - the active schema
- `SELECT current_user, session_user, current_database()` - connection
context
This diagnostic info will help identify why the vector extension isn't
visible in certain cases.
## Changes
- Added `_log_vector_error_diagnostics()` helper function in
`backend/data/db.py`
- Wrapped SQL execution in try/except to catch and diagnose vector type
errors
- Original exception is re-raised after logging (no behavior change)
## Testing
This is observational/diagnostic code. It will be validated by waiting
for the error to occur naturally on dev and checking the logs.
## Rollout
Once we've captured diagnostic logs and identified the root cause, this
logging can be removed or reduced in verbosity.
[SECRT-1912: Investigate & eliminate chat session start
latency](https://linear.app/autogpt/issue/SECRT-1912)
### Changes 🏗️
- Add timing logs to `backend.api.features.chat` in `routes.py`,
`service.py`, and `stream_registry.py`
- Remove unneeded DB join in `create_chat_session`
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- CI checks
Fixes
[#11800](https://github.com/Significant-Gravitas/AutoGPT/issues/11800)
## Problem
The FileInput component crashed with `TypeError: e.startsWith is not a
function` when the value was an object (from external API) instead of a
string.
## Example Input Object
When using the external API
(`/external-api/v1/graphs/{id}/execute/{version}`), file inputs can be
passed as objects:
```json
{
"node_input": {
"input_image": {
"name": "image.jpeg",
"type": "image/jpeg",
"size": 131147,
"data": "/9j/4QAW..."
}
}
}
```
## Changes
- Updated `getFileLabelFromValue()` to handle object format: `{ name,
type, size, data }`
- Added type guards for string vs object values
- Graceful fallback for edge cases (null, undefined, empty object)
## Test cases verified
- Object with name: returns filename
- Object with type only: extracts and formats MIME type
- String data URI: parses correctly
- String file path: extracts extension
- Edge cases: returns "File" fallback
### Changes 🏗️
Fixes
[**AUTOGPT-SERVER-1TN**](https://autoagpt.sentry.io/issues/?query=AUTOGPT-SERVER-1TN)
(~39K events since Feb 2025) and related connection issues
**6JC/6JD/6JE/6JF** (~6K combined).
#### Problem
When the RabbitMQ TCP connection drops (network blip, server restart,
etc.):
1. `connect_robust` (aio_pika) automatically reconnects the underlying
AMQP connection
2. But `AsyncRabbitMQ._channel` still references the **old dead
channel**
3. `is_ready` checks `not self._channel.is_closed` — but the channel
object doesn't know the transport is gone
4. `publish_message` tries to use the stale channel →
`ChannelInvalidStateError: No active transport in channel`
5. `@func_retry` retries 5 times, but each retry hits the same stale
channel (it passes `is_ready`)
This means every connection drop generates errors until the process is
restarted.
#### Fix
**New `_ensure_channel()` helper** that resets stale channels before
reconnecting, so `connect()` creates a fresh one instead of
short-circuiting on `is_connected`.
**Explicit `ChannelInvalidStateError` handling in `publish_message`:**
1. First attempt uses `_ensure_channel()` (handles normal staleness)
2. If publish throws `ChannelInvalidStateError`, does a full reconnect
(resets both `_channel` and `_connection`) and retries once
3. `@func_retry` provides additional retry resilience on top
**Simplified `get_channel()`** to use the same resilient helper.
**1 file changed, 62 insertions, 24 deletions.**
#### Impact
- Eliminates ~39K `ChannelInvalidStateError` Sentry events
- RabbitMQ operations self-heal after connection drops without process
restart
- Related transport EOF errors (6JC/6JD/6JE/6JF) should also reduce
Filters out blocks that are unsuitable for standalone execution from
CoPilot's block search and execution. These blocks serve graph-specific
purposes and will either fail, hang, or confuse users when run outside
of a graph context.
**Important:** This does NOT affect the Builder UI which uses
`load_all_blocks()` directly.
### Changes 🏗️
- **find_block.py**: Added `EXCLUDED_BLOCK_TYPES` and
`EXCLUDED_BLOCK_IDS` constants, skip excluded blocks in search results
- **run_block.py**: Added execution guard that returns clear error
message for excluded blocks
- **content_handlers.py**: Added filtering to
`BlockHandler.get_missing_items()` and `get_stats()` to prevent indexing
excluded blocks
**Excluded by BlockType:**
| BlockType | Reason |
|-----------|--------|
| `INPUT` | Graph interface definition - data enters via chat, not graph
inputs |
| `OUTPUT` | Graph interface definition - data exits via chat, not graph
outputs |
| `WEBHOOK` | Wait for external events - would hang forever in CoPilot |
| `WEBHOOK_MANUAL` | Same as WEBHOOK |
| `NOTE` | Visual annotation only - no runtime behavior |
| `HUMAN_IN_THE_LOOP` | Pauses for human approval - CoPilot IS
human-in-the-loop |
| `AGENT` | AgentExecutorBlock requires graph context - use `run_agent`
tool instead |
**Excluded by ID:**
| Block | Reason |
|-------|--------|
| `SmartDecisionMakerBlock` | Dynamically discovers downstream blocks
via graph topology |
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [ ] Search for "input" in CoPilot - should NOT return AgentInputBlock
variants
- [ ] Search for "output" in CoPilot - should NOT return
AgentOutputBlock
- [ ] Search for "webhook" in CoPilot - should NOT return trigger blocks
- [ ] Search for "human" in CoPilot - should NOT return
HumanInTheLoopBlock
- [ ] Search for "decision" in CoPilot - should NOT return
SmartDecisionMakerBlock
- [ ] Verify functional blocks still appear (e.g., "email", "http",
"text")
- [ ] Verify Builder UI still shows ALL blocks (no regression)
#### For configuration changes:
- [x] `.env.default` is updated or already compatible with my changes
- [x] `docker-compose.yml` is updated or already compatible with my
changes
- [x] I have included a list of my configuration changes in the PR
description (under **Changes**)
No configuration changes required.
---
Resolves: [SECRT-1831](https://linear.app/autogpt/issue/SECRT-1831)
🤖 Generated with [Claude Code](https://claude.ai/code)
<!-- CURSOR_SUMMARY -->
---
> [!NOTE]
> **Low Risk**
> Behavior change is limited to CoPilot’s block discovery/execution
guards and is covered by new tests; main risk is inadvertently excluding
a block that should be runnable.
>
> **Overview**
> CoPilot now **filters out graph-only blocks** from `find_block`
results and prevents them from being executed via `run_block`, returning
a clear error when a user attempts to run an excluded block.
>
> `find_block` introduces explicit exclusion lists (by `BlockType` and a
specific block ID), over-fetches search results to maintain up to 10
usable matches after filtering, and adds debug logging when results are
reduced. New unit tests cover both the search filtering and the
`run_block` execution guard; a minor cleanup removes an unused `pytest`
import in `execution_queue_test.py`.
>
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
bc50755dcf. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: Nicholas Tindle <ntindle@users.noreply.github.com>
Co-authored-by: Otto <otto@agpt.co>
Bumps [react-window](https://github.com/bvaughn/react-window) and
[@types/react-window](https://github.com/DefinitelyTyped/DefinitelyTyped/tree/HEAD/types/react-window).
These dependencies needed to be updated together.
Updates `react-window` from 1.8.11 to 2.1.0
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/bvaughn/react-window/releases">react-window's
releases</a>.</em></p>
<blockquote>
<h2>2.1.0</h2>
<p>Improved ARIA support:</p>
<ul>
<li>Add better default ARIA attributes for outer
<code>HTMLDivElement</code></li>
<li>Add optional <code>ariaAttributes</code> prop to row and cell
renderers to simplify better ARIA attributes for user-rendered
cells</li>
<li>Remove intermediate <code>HTMLDivElement</code> from
<code>List</code> and <code>Grid</code>
<ul>
<li>This may enable more/better custom CSS styling</li>
<li>This may also enable adding an optional <code>children</code> prop
to <code>List</code> and <code>Grid</code> for e.g.
overlays/tooltips</li>
</ul>
</li>
<li>Add optional <code>tagName</code> prop; defaults to
<code>"div"</code> but can be changed to e.g.
<code>"ul"</code></li>
</ul>
<pre lang="tsx"><code>// Example of how to use new `ariaAttributes` prop
function RowComponent({
ariaAttributes,
index,
style,
...rest
}: RowComponentProps<object>) {
return (
<div style={style} {...ariaAttributes}>
...
</div>
);
}
</code></pre>
<p>Added optional <code>children</code> prop to better support edge
cases like sticky rows.</p>
<p>Minor changes to <code>onRowsRendered</code> and
<code>onCellsRendered</code> callbacks to make it easier to
differentiate between <em>visible</em> items and items rendered due to
overscan settings. These methods will now receive two params– the first
for <em>visible</em> rows and the second for <em>all</em> rows
(including overscan), e.g.:</p>
<pre lang="ts"><code>function onRowsRendered(
visibleRows: {
startIndex: number;
stopIndex: number;
},
allRows: {
startIndex: number;
stopIndex: number;
}
): void {
// ...
}
<p>function onCellsRendered(<br />
visibleCells: {<br />
columnStartIndex: number;<br />
columnStopIndex: number;<br />
rowStartIndex: number;<br />
rowStopIndex: number;<br />
</tr></table><br />
</code></pre></p>
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/bvaughn/react-window/blob/master/CHANGELOG.md">react-window's
changelog</a>.</em></p>
<blockquote>
<h2>2.1.0</h2>
<p>Improved ARIA support:</p>
<ul>
<li>Add better default ARIA attributes for outer
<code>HTMLDivElement</code></li>
<li>Add optional <code>ariaAttributes</code> prop to row and cell
renderers to simplify better ARIA attributes for user-rendered
cells</li>
<li>Remove intermediate <code>HTMLDivElement</code> from
<code>List</code> and <code>Grid</code>
<ul>
<li>This may enable more/better custom CSS styling</li>
<li>This may also enable adding an optional <code>children</code> prop
to <code>List</code> and <code>Grid</code> for e.g.
overlays/tooltips</li>
</ul>
</li>
<li>Add optional <code>tagName</code> prop; defaults to
<code>"div"</code> but can be changed to e.g.
<code>"ul"</code></li>
</ul>
<pre lang="tsx"><code>// Example of how to use new `ariaAttributes` prop
function RowComponent({
ariaAttributes,
index,
style,
...rest
}: RowComponentProps<object>) {
return (
<div style={style} {...ariaAttributes}>
...
</div>
);
}
</code></pre>
<p>Added optional <code>children</code> prop to better support edge
cases like sticky rows.</p>
<p>Minor changes to <code>onRowsRendered</code> and
<code>onCellsRendered</code> callbacks to make it easier to
differentiate between <em>visible</em> items and items rendered due to
overscan settings. These methods will now receive two params– the first
for <em>visible</em> rows and the second for <em>all</em> rows
(including overscan), e.g.:</p>
<pre lang="ts"><code>function onRowsRendered(
visibleRows: {
startIndex: number;
stopIndex: number;
},
allRows: {
startIndex: number;
stopIndex: number;
}
): void {
// ...
}
<p>function onCellsRendered(<br />
visibleCells: {<br />
columnStartIndex: number;<br />
columnStopIndex: number;<br />
rowStartIndex: number;<br />
</tr></table><br />
</code></pre></p>
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="1b6840ba35"><code>1b6840b</code></a>
Merge pull request <a
href="https://redirect.github.com/bvaughn/react-window/issues/836">#836</a>
from bvaughn/ARIA-roles</li>
<li><a
href="35f651b615"><code>35f651b</code></a>
Revert accidental change to docs example</li>
<li><a
href="8bce7f555b"><code>8bce7f5</code></a>
onRowsRendered/onCellsRendered separate visible and overscan items</li>
<li><a
href="9f1e8f2f0a"><code>9f1e8f2</code></a>
Support custom tagName for outer element and (optional) children</li>
<li><a
href="7f07ac33cb"><code>7f07ac3</code></a>
Improve ARIA attributes</li>
<li><a
href="7234ec3c09"><code>7234ec3</code></a>
Reduced network waterfalls between routes</li>
<li><a
href="5c431a294f"><code>5c431a2</code></a>
Stronger typing for doc website routes</li>
<li><a
href="c9349a4b7b"><code>c9349a4</code></a>
2.0.1 -> 2.0.2</li>
<li><a
href="6adc6c04a1"><code>6adc6c0</code></a>
Merge pull request <a
href="https://redirect.github.com/bvaughn/react-window/issues/832">#832</a>
from bvaughn/issues/831</li>
<li><a
href="bd562c5734"><code>bd562c5</code></a>
Add tests</li>
<li>Additional commits viewable in <a
href="https://github.com/bvaughn/react-window/compare/1.8.11...2.1.0">compare
view</a></li>
</ul>
</details>
<br />
Updates `@types/react-window` from 1.8.8 to 2.0.0
<details>
<summary>Commits</summary>
<ul>
<li>See full diff in <a
href="https://github.com/DefinitelyTyped/DefinitelyTyped/commits/HEAD/types/react-window">compare
view</a></li>
</ul>
</details>
<br />
You can trigger a rebase of this PR by commenting `@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
> **Note**
> Automatic rebases have been disabled on this pull request as it has
been open for over 30 days.
---------
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Nicholas Tindle <nicholas.tindle@agpt.co>
Co-authored-by: Nick Tindle <nick@ntindle.com>
Bumps the development-dependencies group with 3 updates in the
/autogpt_platform/backend directory:
[poethepoet](https://github.com/nat-n/poethepoet),
[pytest-watcher](https://github.com/olzhasar/pytest-watcher) and
[ruff](https://github.com/astral-sh/ruff).
Updates `poethepoet` from 0.37.0 to 0.40.0
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/nat-n/poethepoet/releases">poethepoet's
releases</a>.</em></p>
<blockquote>
<h2>0.40.0</h2>
<h2>Enhancements</h2>
<ul>
<li>Allow optional envfiles without warnings by <a
href="https://github.com/cnaples79"><code>@cnaples79</code></a> in <a
href="https://redirect.github.com/nat-n/poethepoet/pull/337">nat-n/poethepoet#337</a></li>
<li>Add support for the <code>capture_output</code> option in ref tasks
by <a href="https://github.com/kzrnm"><code>@kzrnm</code></a> in <a
href="https://redirect.github.com/nat-n/poethepoet/pull/343">nat-n/poethepoet#343</a></li>
<li>Set uv to quiet mode during shell completion to avoid console spam
by <a href="https://github.com/nat-n"><code>@nat-n</code></a> in <a
href="https://redirect.github.com/nat-n/poethepoet/pull/338">nat-n/poethepoet#338</a></li>
<li>Support <code>ignore_fail</code> on execution task types and ref
tasks by <a href="https://github.com/nat-n"><code>@nat-n</code></a> in
<a
href="https://redirect.github.com/nat-n/poethepoet/pull/347">nat-n/poethepoet#347</a></li>
<li>Add choices option to constrain named arguments by <a
href="https://github.com/nat-n"><code>@nat-n</code></a> in <a
href="https://redirect.github.com/nat-n/poethepoet/pull/348">nat-n/poethepoet#348</a></li>
</ul>
<h2>Fixes</h2>
<ul>
<li>Handle SIGHUP and SIGBREAK signals to stop tasks by <a
href="https://github.com/nat-n"><code>@nat-n</code></a> in <a
href="https://redirect.github.com/nat-n/poethepoet/pull/344">nat-n/poethepoet#344</a></li>
<li>Accept string for type name in global executor option by <a
href="https://github.com/kzrnm"><code>@kzrnm</code></a> in <a
href="https://redirect.github.com/nat-n/poethepoet/pull/340">nat-n/poethepoet#340</a></li>
</ul>
<h2>Code improvements</h2>
<ul>
<li>Modernize type annotations by <a
href="https://github.com/nat-n"><code>@nat-n</code></a> in <a
href="https://redirect.github.com/nat-n/poethepoet/pull/339">nat-n/poethepoet#339</a></li>
<li>Ensure test virtual environments are always cleaned up by <a
href="https://github.com/kzrnm"><code>@kzrnm</code></a> in <a
href="https://redirect.github.com/nat-n/poethepoet/pull/346">nat-n/poethepoet#346</a></li>
</ul>
<p><strong>Full Changelog</strong>: <a
href="https://github.com/nat-n/poethepoet/compare/v0.39.0...v0.40.0">https://github.com/nat-n/poethepoet/compare/v0.39.0...v0.40.0</a></p>
<h2>0.39.0</h2>
<h2>Enhancements</h2>
<ul>
<li>Add support for uv executor options by <a
href="https://github.com/rochacbruno"><code>@rochacbruno</code></a> and
<a href="https://github.com/nat-n"><code>@nat-n</code></a> in <a
href="https://redirect.github.com/nat-n/poethepoet/pull/327">nat-n/poethepoet#327</a>
<ul>
<li>feat: add <a
href="https://poethepoet.natn.io/global_options.html#uv-executor">various
options to the uv executor</a> to be passed to the uv run command</li>
<li>feat: allow task executor to be configure with just the type as a
string</li>
<li>feat executor options to be set at runtime via the new
--executor-opt cli global option</li>
<li>feat: allow inheritance of compatible executor options from global
to task to runtime</li>
<li>refactor: extend PoeOptions to support annotating config fields with
a config_name to parse, separate from the attribute name</li>
<li>refactor: some micro-optimizations to PoeOptions and
AnnotationType</li>
<li>doc: Add <a
href="https://poethepoet.natn.io/guides/tox_replacement_guide.html">guide
for replacing tox with poe + uv</a></li>
<li>doc: tidy up executor docs</li>
<li>doc: fix typo in doc for expr task</li>
<li>test: improve test coverage of PoeOptions</li>
<li>test: disable some test cases on windows that are too flaky</li>
</ul>
</li>
</ul>
<h2>New Contributors</h2>
<ul>
<li><a
href="https://github.com/rochacbruno"><code>@rochacbruno</code></a>
made their first contribution in <a
href="https://redirect.github.com/nat-n/poethepoet/pull/327">nat-n/poethepoet#327</a></li>
</ul>
<p><strong>Full Changelog</strong>: <a
href="https://github.com/nat-n/poethepoet/compare/v0.38.0...v0.39.0">https://github.com/nat-n/poethepoet/compare/v0.38.0...v0.39.0</a></p>
<h2>0.38.0</h2>
<h2>Enhancements</h2>
<ul>
<li>feat: Add parallel task type by <a
href="https://github.com/nat-n"><code>@nat-n</code></a> in <a
href="https://redirect.github.com/nat-n/poethepoet/pull/323">nat-n/poethepoet#323</a></li>
</ul>
<h2>Breaking changes</h2>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="0a7247d8f7"><code>0a7247d</code></a>
Bump version to 0.40.0</li>
<li><a
href="312e74a5be"><code>312e74a</code></a>
feat: Add choices option to constrain named arguments (<a
href="https://redirect.github.com/nat-n/poethepoet/issues/348">#348</a>)</li>
<li><a
href="5e0b3e5590"><code>5e0b3e5</code></a>
feat: support ignore_fail on execution task types and ref tasks (<a
href="https://redirect.github.com/nat-n/poethepoet/issues/347">#347</a>)</li>
<li><a
href="a3c97e1e94"><code>a3c97e1</code></a>
test: ensure the test virtual environment is always removed (<a
href="https://redirect.github.com/nat-n/poethepoet/issues/346">#346</a>)</li>
<li><a
href="bc04e2fe18"><code>bc04e2f</code></a>
feat: support <code>capture_output</code> on ref tasks (<a
href="https://redirect.github.com/nat-n/poethepoet/issues/343">#343</a>)</li>
<li><a
href="f7b82ef954"><code>f7b82ef</code></a>
fix: global executor option (<a
href="https://redirect.github.com/nat-n/poethepoet/issues/340">#340</a>)</li>
<li><a
href="8e7b1166a0"><code>8e7b116</code></a>
fix: handle SIGHUP and SIGBREAK signals to stop tasks (<a
href="https://redirect.github.com/nat-n/poethepoet/issues/344">#344</a>)</li>
<li><a
href="8e51f2b79f"><code>8e51f2b</code></a>
refactor: modernize type annotations (<a
href="https://redirect.github.com/nat-n/poethepoet/issues/339">#339</a>)</li>
<li><a
href="72a9225dac"><code>72a9225</code></a>
fix: set uv to quiet during shell completion (<a
href="https://redirect.github.com/nat-n/poethepoet/issues/338">#338</a>)</li>
<li><a
href="c6c7306276"><code>c6c7306</code></a>
feat: allow optional envfiles without warnings (<a
href="https://redirect.github.com/nat-n/poethepoet/issues/337">#337</a>)</li>
<li>Additional commits viewable in <a
href="https://github.com/nat-n/poethepoet/compare/v0.37.0...v0.40.0">compare
view</a></li>
</ul>
</details>
<br />
Updates `pytest-watcher` from 0.4.3 to 0.6.3
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/olzhasar/pytest-watcher/releases">pytest-watcher's
releases</a>.</em></p>
<blockquote>
<h2>v0.6.3</h2>
<h3>Features</h3>
<ul>
<li>Add debug mode activated with <code>PTW_DEBUG</code> environment
variable and improve log messages.</li>
</ul>
<h3>Bugfixes</h3>
<ul>
<li>Fix terminal flushing after menu and header prints.</li>
<li>Use monotonic clock for trigger detection to avoid misbehavior on
clock changes.</li>
</ul>
<h2>v0.6.2</h2>
<h3>Bugfixes</h3>
<ul>
<li>Allow specifying blank patterns via CLI</li>
<li>Fix duplicate command entries in menu</li>
</ul>
<h2>v0.6.1</h2>
<h3>Bugfixes</h3>
<ul>
<li>Trigger tests in interactive mode for carriage return character</li>
</ul>
<h3>Improved Documentation</h3>
<ul>
<li>Add contributing guide</li>
</ul>
<h3>Misc</h3>
<ul>
<li>Integrate <a
href="https://towncrier.readthedocs.io/en/stable/index.html">towncrier</a>
into the development process</li>
</ul>
<h2>v0.6.0</h2>
<h2>Features</h2>
<ul>
<li>Add <code>notify-on-failure</code> flag (and config option) to emit
BEL symbol on test suite failure.</li>
</ul>
<h2>Infrastructure</h2>
<ul>
<li>Migrate from poetry to uv.</li>
<li>Remove tox.</li>
</ul>
<h2>v0.5.0</h2>
<h2>Fixes</h2>
<ul>
<li>Merge arguments passed to the runner from config and CLI instead of
overriding.</li>
</ul>
<h2>Changes</h2>
<ul>
<li>Drop support for Python 3.7 & 3.8</li>
</ul>
</blockquote>
</details>
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/olzhasar/pytest-watcher/blob/master/CHANGELOG.md">pytest-watcher's
changelog</a>.</em></p>
<blockquote>
<h2><a
href="https://github.com/olzhasar/pytest-watcher/releases/tag/0.6.3">0.6.3</a>
- 2026-01-11</h2>
<h3>Features</h3>
<ul>
<li>Add debug mode activated with <code>PTW_DEBUG</code> environment
variable and improve log messages.</li>
</ul>
<h3>Bugfixes</h3>
<ul>
<li>Fix terminal flushing after menu and header prints.</li>
<li>Use monotonic clock for trigger detection to avoid misbehavior on
clock changes.</li>
</ul>
<h2><a
href="https://github.com/olzhasar/pytest-watcher/releases/tag/0.6.2">0.6.2</a>
- 2025-12-28</h2>
<h3>Bugfixes</h3>
<ul>
<li>Allow specifying blank patterns via CLI</li>
<li>Fix duplicate command entries in menu</li>
</ul>
<h2><a
href="https://github.com/olzhasar/pytest-watcher/releases/tag/0.6.1">0.6.1</a>
- 2025-12-26</h2>
<h3>Bugfixes</h3>
<ul>
<li>Trigger tests in interactive mode for carriage return character</li>
</ul>
<h3>Improved Documentation</h3>
<ul>
<li>Add contributing guide</li>
</ul>
<h3>Misc</h3>
<ul>
<li>Integrate <a
href="https://towncrier.readthedocs.io/en/stable/index.html">towncrier</a>
into the development process</li>
</ul>
<h2><a
href="https://github.com/olzhasar/pytest-watcher/releases/tag/0.6.0">0.6.0</a>
- 2025-12-22</h2>
<h3>Features</h3>
<ul>
<li>Add notify-on-failure flag (and config option) to emit BEL symbol on
test suite failure.</li>
</ul>
<h3>Infrastructure</h3>
<ul>
<li>Migrate from <code>poetry</code> to <code>uv</code>.</li>
<li>Remove <code>tox</code>.</li>
</ul>
<h2><a
href="https://github.com/olzhasar/pytest-watcher/releases/tag/0.5.0">0.5.0</a>
- 2025-12-21</h2>
<h3>Fixes</h3>
<ul>
<li>Merge arguments passed to the runner from config and CLI instead of
overriding.</li>
</ul>
<h3>Changes</h3>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="c52925b613"><code>c52925b</code></a>
release v0.6.3</li>
<li><a
href="23d49893f7"><code>23d4989</code></a>
Add debug mode. Improve log messages</li>
<li><a
href="e3dffa1cb3"><code>e3dffa1</code></a>
Fix terminal flushing after menu and header prints</li>
<li><a
href="0eeaf6080e"><code>0eeaf60</code></a>
Use monotonic clock for trigger detection</li>
<li><a
href="5ed9d0e262"><code>5ed9d0e</code></a>
Update CHANGELOG. Fix changelog_reader action</li>
<li><a
href="756f005f5d"><code>756f005</code></a>
release v0.6.2</li>
<li><a
href="902aa9e07b"><code>902aa9e</code></a>
Merge pull request <a
href="https://redirect.github.com/olzhasar/pytest-watcher/issues/51">#51</a>
from olzhasar/fix-duplicate-menu</li>
<li><a
href="e6b20d35b9"><code>e6b20d3</code></a>
Allow specifying empty patterns via CLI</li>
<li><a
href="2d522dabf9"><code>2d522da</code></a>
Fix duplicate menu entries</li>
<li><a
href="171e6f1282"><code>171e6f1</code></a>
Fix towncrier CHANGELOG versioning</li>
<li>Additional commits viewable in <a
href="https://github.com/olzhasar/pytest-watcher/compare/v0.4.3...v0.6.3">compare
view</a></li>
</ul>
</details>
<br />
Updates `ruff` from 0.14.14 to 0.15.0
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/astral-sh/ruff/releases">ruff's
releases</a>.</em></p>
<blockquote>
<h2>0.15.0</h2>
<h2>Release Notes</h2>
<p>Released on 2026-02-03.</p>
<p>Check out the <a href="https://astral.sh/blog/ruff-v0.15.0">blog
post</a> for a migration guide and overview of the changes!</p>
<h3>Breaking changes</h3>
<ul>
<li>
<p>Ruff now formats your code according to the 2026 style guide. See the
formatter section below or in the blog post for a detailed list of
changes.</p>
</li>
<li>
<p>The linter now supports block suppression comments. For example, to
suppress <code>N803</code> for all parameters in this function:</p>
<pre lang="python"><code># ruff: disable[N803]
def foo(
legacyArg1,
legacyArg2,
legacyArg3,
legacyArg4,
): ...
# ruff: enable[N803]
</code></pre>
<p>See the <a
href="https://docs.astral.sh/ruff/linter/#block-level">documentation</a>
for more details.</p>
</li>
<li>
<p>The <code>ruff:alpine</code> Docker image is now based on Alpine 3.23
(up from 3.21).</p>
</li>
<li>
<p>The <code>ruff:debian</code> and <code>ruff:debian-slim</code> Docker
images are now based on Debian 13 "Trixie" instead of Debian
12 "Bookworm."</p>
</li>
<li>
<p>Binaries for the <code>ppc64</code> (64-bit big-endian PowerPC)
architecture are no longer included in our releases. It should still be
possible to build Ruff manually for this platform, if needed.</p>
</li>
<li>
<p>Ruff now resolves all <code>extend</code>ed configuration files
before falling back on a default Python version.</p>
</li>
</ul>
<h3>Stabilization</h3>
<p>The following rules have been stabilized and are no longer in
preview:</p>
<ul>
<li><a
href="https://docs.astral.sh/ruff/rules/blocking-http-call-httpx-in-async-function"><code>blocking-http-call-httpx-in-async-function</code></a>
(<code>ASYNC212</code>)</li>
<li><a
href="https://docs.astral.sh/ruff/rules/blocking-path-method-in-async-function"><code>blocking-path-method-in-async-function</code></a>
(<code>ASYNC240</code>)</li>
<li><a
href="https://docs.astral.sh/ruff/rules/blocking-input-in-async-function"><code>blocking-input-in-async-function</code></a>
(<code>ASYNC250</code>)</li>
<li><a
href="https://docs.astral.sh/ruff/rules/map-without-explicit-strict"><code>map-without-explicit-strict</code></a>
(<code>B912</code>)</li>
<li><a
href="https://docs.astral.sh/ruff/rules/if-exp-instead-of-or-operator"><code>if-exp-instead-of-or-operator</code></a>
(<code>FURB110</code>)</li>
<li><a
href="https://docs.astral.sh/ruff/rules/single-item-membership-test"><code>single-item-membership-test</code></a>
(<code>FURB171</code>)</li>
<li><a
href="https://docs.astral.sh/ruff/rules/missing-maxsplit-arg"><code>missing-maxsplit-arg</code></a>
(<code>PLC0207</code>)</li>
<li><a
href="https://docs.astral.sh/ruff/rules/unnecessary-lambda"><code>unnecessary-lambda</code></a>
(<code>PLW0108</code>)</li>
<li><a
href="https://docs.astral.sh/ruff/rules/unnecessary-empty-iterable-within-deque-call"><code>unnecessary-empty-iterable-within-deque-call</code></a>
(<code>RUF037</code>)</li>
<li><a
href="https://docs.astral.sh/ruff/rules/in-empty-collection"><code>in-empty-collection</code></a>
(<code>RUF060</code>)</li>
<li><a
href="https://docs.astral.sh/ruff/rules/legacy-form-pytest-raises"><code>legacy-form-pytest-raises</code></a>
(<code>RUF061</code>)</li>
<li><a
href="https://docs.astral.sh/ruff/rules/non-octal-permissions"><code>non-octal-permissions</code></a>
(<code>RUF064</code>)</li>
</ul>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/astral-sh/ruff/blob/main/CHANGELOG.md">ruff's
changelog</a>.</em></p>
<blockquote>
<h2>0.15.0</h2>
<p>Released on 2026-02-03.</p>
<p>Check out the <a href="https://astral.sh/blog/ruff-v0.15.0">blog
post</a> for a migration
guide and overview of the changes!</p>
<h3>Breaking changes</h3>
<ul>
<li>
<p>Ruff now formats your code according to the 2026 style guide. See the
formatter section below or in the blog post for a detailed list of
changes.</p>
</li>
<li>
<p>The linter now supports block suppression comments. For example, to
suppress <code>N803</code> for all parameters in this function:</p>
<pre lang="python"><code># ruff: disable[N803]
def foo(
legacyArg1,
legacyArg2,
legacyArg3,
legacyArg4,
): ...
# ruff: enable[N803]
</code></pre>
<p>See the <a
href="https://docs.astral.sh/ruff/linter/#block-level">documentation</a>
for more details.</p>
</li>
<li>
<p>The <code>ruff:alpine</code> Docker image is now based on Alpine 3.23
(up from 3.21).</p>
</li>
<li>
<p>The <code>ruff:debian</code> and <code>ruff:debian-slim</code> Docker
images are now based on Debian 13 "Trixie" instead of Debian
12 "Bookworm."</p>
</li>
<li>
<p>Binaries for the <code>ppc64</code> (64-bit big-endian PowerPC)
architecture are no longer included in our releases. It should still be
possible to build Ruff manually for this platform, if needed.</p>
</li>
<li>
<p>Ruff now resolves all <code>extend</code>ed configuration files
before falling back on a default Python version.</p>
</li>
</ul>
<h3>Stabilization</h3>
<p>The following rules have been stabilized and are no longer in
preview:</p>
<ul>
<li><a
href="https://docs.astral.sh/ruff/rules/blocking-http-call-httpx-in-async-function"><code>blocking-http-call-httpx-in-async-function</code></a>
(<code>ASYNC212</code>)</li>
<li><a
href="https://docs.astral.sh/ruff/rules/blocking-path-method-in-async-function"><code>blocking-path-method-in-async-function</code></a>
(<code>ASYNC240</code>)</li>
<li><a
href="https://docs.astral.sh/ruff/rules/blocking-input-in-async-function"><code>blocking-input-in-async-function</code></a>
(<code>ASYNC250</code>)</li>
<li><a
href="https://docs.astral.sh/ruff/rules/map-without-explicit-strict"><code>map-without-explicit-strict</code></a>
(<code>B912</code>)</li>
<li><a
href="https://docs.astral.sh/ruff/rules/if-exp-instead-of-or-operator"><code>if-exp-instead-of-or-operator</code></a>
(<code>FURB110</code>)</li>
<li><a
href="https://docs.astral.sh/ruff/rules/single-item-membership-test"><code>single-item-membership-test</code></a>
(<code>FURB171</code>)</li>
</ul>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="ce5f7b6127"><code>ce5f7b6</code></a>
Bump 0.15.0 (<a
href="https://redirect.github.com/astral-sh/ruff/issues/23055">#23055</a>)</li>
<li><a
href="b4e40f539c"><code>b4e40f5</code></a>
[ty] Fix <code>__contains__</code> to respect descriptors (<a
href="https://redirect.github.com/astral-sh/ruff/issues/23056">#23056</a>)</li>
<li><a
href="848cb72dc1"><code>848cb72</code></a>
[ty] Fix narrowing of nonlocal variables with conditional assignments
(<a
href="https://redirect.github.com/astral-sh/ruff/issues/22966">#22966</a>)</li>
<li><a
href="da7f33af22"><code>da7f33a</code></a>
[ty] Add a diagnostic for <code>Final</code> without assignment (<a
href="https://redirect.github.com/astral-sh/ruff/issues/23001">#23001</a>)</li>
<li><a
href="e65f9a6b03"><code>e65f9a6</code></a>
Document markdown formatting feature (<a
href="https://redirect.github.com/astral-sh/ruff/issues/22990">#22990</a>)</li>
<li><a
href="c0c1b985c9"><code>c0c1b98</code></a>
Format markdown code blocks with line-by-line regex parse (<a
href="https://redirect.github.com/astral-sh/ruff/issues/22996">#22996</a>)</li>
<li><a
href="9f8f3e196b"><code>9f8f3e1</code></a>
Allow positional-only params with defaults in method overrides (<a
href="https://redirect.github.com/astral-sh/ruff/issues/23037">#23037</a>)</li>
<li><a
href="ef83810e11"><code>ef83810</code></a>
[ty] ecosystem-analyzer: Support bare git repositories (<a
href="https://redirect.github.com/astral-sh/ruff/issues/23054">#23054</a>)</li>
<li><a
href="54dfee4cb8"><code>54dfee4</code></a>
Customize where the <code>fix_title</code> sub-diagnostic appears (<a
href="https://redirect.github.com/astral-sh/ruff/issues/23044">#23044</a>)</li>
<li><a
href="b53460799b"><code>b534607</code></a>
2026 Ruff Formatter Style (<a
href="https://redirect.github.com/astral-sh/ruff/issues/22735">#22735</a>)</li>
<li>Additional commits viewable in <a
href="https://github.com/astral-sh/ruff/compare/0.14.14...0.15.0">compare
view</a></li>
</ul>
</details>
<br />
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore <dependency name> major version` will close this
group update PR and stop Dependabot creating any more for the specific
dependency's major version (unless you unignore this specific
dependency's major version or upgrade to it yourself)
- `@dependabot ignore <dependency name> minor version` will close this
group update PR and stop Dependabot creating any more for the specific
dependency's minor version (unless you unignore this specific
dependency's minor version or upgrade to it yourself)
- `@dependabot ignore <dependency name>` will close this group update PR
and stop Dependabot creating any more for the specific dependency
(unless you unignore this specific dependency or upgrade to it yourself)
- `@dependabot unignore <dependency name>` will remove all of the ignore
conditions of the specified dependency
- `@dependabot unignore <dependency name> <ignore condition>` will
remove the ignore condition of the specified dependency and ignore
conditions
</details>
---------
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Nick Tindle <nick@ntindle.com>
Co-authored-by: Nicholas Tindle <nicholas.tindle@agpt.co>
## Context
From PR #11796 review discussion. Files processed by the video blocks
(downloads, uploads, generated videos) should be scanned through ClamAV
for malware detection.
## Problem
`store_media_file()` in `backend/util/file.py` already scans:
- `workspace://` references
- Cloud storage paths
- Data URIs (`data:...`)
- HTTP/HTTPS URLs
**But local file paths were NOT scanned.** The `else` branch only
verified the file exists.
This gap affected video processing blocks (e.g., `LoopVideoBlock`,
`AddAudioToVideoBlock`) that:
1. Download/receive input media
2. Process it locally (loop, add audio, etc.)
3. Write output to temp directory
4. Call `store_media_file(output_filename, ...)` with a local path →
**skipped virus scanning**
## Solution
Added virus scanning to the local file path branch:
```python
# 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(...)
await scan_content_safe(local_content, filename=sanitized_file)
```
## Changes
- `backend/util/file.py` - Added ~7 lines to scan local files
(consistent with other input types)
- `backend/util/file_test.py` - Added 2 test cases for local file
scanning
## Risk Assessment
- **Low risk:** Single point of change, follows existing pattern
- **Backwards compatible:** No API changes
- **Fail-safe:** If scanning fails, file is rejected (existing behavior)
Closes SECRT-1904
Co-authored-by: Nicholas Tindle <nicholas.tindle@agpt.co>
Bumps [cryptography](https://github.com/pyca/cryptography) from 45.0.6
to 46.0.1.
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/pyca/cryptography/blob/main/CHANGELOG.rst">cryptography's
changelog</a>.</em></p>
<blockquote>
<p>46.0.1 - 2025-09-16</p>
<pre><code>
* Fixed an issue where users installing via ``pip`` on Python 3.14
development
versions would not properly install a dependency.
* Fixed an issue building the free-threaded macOS 3.14 wheels.
<p>.. _v46-0-0:</p>
<p>46.0.0 - 2025-09-16<br />
</code></pre></p>
<ul>
<li><strong>BACKWARDS INCOMPATIBLE:</strong> Support for Python 3.7 has
been removed.</li>
<li>Support for OpenSSL < 3.0 is deprecated and will be removed in
the next
release.</li>
<li>Support for <code>x86_64</code> macOS (including publishing wheels)
is deprecated
and will be removed in two releases. We will switch to publishing an
<code>arm64</code> only wheel for macOS.</li>
<li>Support for 32-bit Windows (including publishing wheels) is
deprecated
and will be removed in two releases. Users should move to a 64-bit
Python installation.</li>
<li>Updated Windows, macOS, and Linux wheels to be compiled with OpenSSL
3.5.3.</li>
<li>We now build <code>ppc64le</code> <code>manylinux</code> wheels and
publish them to PyPI.</li>
<li>We now build <code>win_arm64</code> (Windows on Arm) wheels and
publish them to PyPI.</li>
<li>Added support for free-threaded Python 3.14.</li>
<li>Removed the deprecated <code>get_attribute_for_oid</code> method on
:class:<code>~cryptography.x509.CertificateSigningRequest</code>. Users
should use
:meth:<code>~cryptography.x509.Attributes.get_attribute_for_oid</code>
instead.</li>
<li>Removed the deprecated <code>CAST5</code>, <code>SEED</code>,
<code>IDEA</code>, and <code>Blowfish</code>
classes from the cipher module. These are still available in
:doc:<code>/hazmat/decrepit/index</code>.</li>
<li>In X.509, when performing a PSS signature with a SHA-3 hash, it is
now
encoded with the official NIST SHA3 OID.</li>
</ul>
<p>.. _v45-0-7:</p>
<p>45.0.7 - 2025-09-01</p>
<pre><code>
* Added a function to support an upcoming ``pyOpenSSL`` release.
<p>.. _v45-0-6:<br />
</code></pre></p>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="e735cfc275"><code>e735cfc</code></a>
release 46.0.1 (<a
href="https://redirect.github.com/pyca/cryptography/issues/13450">#13450</a>)</li>
<li><a
href="4e457ffba4"><code>4e457ff</code></a>
Explicitly specify python in mac uv build invocation (<a
href="https://redirect.github.com/pyca/cryptography/issues/13447">#13447</a>)</li>
<li><a
href="2726efdb6d"><code>2726efd</code></a>
Depend on CFFI 2.0.0 or newer on Python > 3.8 (<a
href="https://redirect.github.com/pyca/cryptography/issues/13448">#13448</a>)</li>
<li><a
href="62230623d1"><code>6223062</code></a>
release 46.0.0 (<a
href="https://redirect.github.com/pyca/cryptography/issues/13446">#13446</a>)</li>
<li><a
href="563c4915b0"><code>563c491</code></a>
Update comment for pyopenssl-release tag (<a
href="https://redirect.github.com/pyca/cryptography/issues/13445">#13445</a>)</li>
<li><a
href="d2f6f7face"><code>d2f6f7f</code></a>
Bump downstream dependencies in CI (<a
href="https://redirect.github.com/pyca/cryptography/issues/13439">#13439</a>)</li>
<li><a
href="e7ab02bd67"><code>e7ab02b</code></a>
we'll ship this with 3.5.3 why not (<a
href="https://redirect.github.com/pyca/cryptography/issues/13442">#13442</a>)</li>
<li><a
href="0b68a4bffb"><code>0b68a4b</code></a>
Another pair of bump dependencies fix (<a
href="https://redirect.github.com/pyca/cryptography/issues/13444">#13444</a>)</li>
<li><a
href="e076d08ee4"><code>e076d08</code></a>
Attempt to fix commit message for bump downstreams (<a
href="https://redirect.github.com/pyca/cryptography/issues/13440">#13440</a>)</li>
<li><a
href="6835ce899e"><code>6835ce8</code></a>
Put correct version bounds for pyenchant in pins (<a
href="https://redirect.github.com/pyca/cryptography/issues/13441">#13441</a>)</li>
<li>Additional commits viewable in <a
href="https://github.com/pyca/cryptography/compare/45.0.6...46.0.1">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
You can trigger a rebase of this PR by commenting `@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
> **Note**
> Automatic rebases have been disabled on this pull request as it has
been open for over 30 days.
---------
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Nick Tindle <nick@ntindle.com>
<!-- Clearly explain the need for these changes: -->
The `ExecutionQueue` class was using `multiprocessing.Manager().Queue()`
which spawns a subprocess for inter-process communication. However,
analysis showed that `ExecutionQueue` is only accessed from threads
within the same process, not across processes. This caused:
- Unnecessary subprocess spawning per graph execution
- IPC overhead for every queue operation
- Potential resource leaks if Manager processes weren't properly cleaned
up
- Limited scalability when many graphs execute concurrently
### Changes
<!-- Concisely describe all of the changes made in this pull request:
-->
- Replaced `multiprocessing.Manager().Queue()` with `queue.Queue()` in
`ExecutionQueue` class
- Updated imports: removed `from multiprocessing import Manager` and
`from queue import Empty`, added `import queue`
- Updated exception handling from `except Empty:` to `except
queue.Empty:`
- Added comprehensive docstring explaining the bug and fix
**File changed:** `autogpt_platform/backend/backend/data/execution.py`
### Checklist
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
<!-- Put your test plan here: -->
- [x] Verified `ExecutionQueue` uses `queue.Queue` (not
`multiprocessing.Manager().Queue()`)
- [x] Tested all queue operations: `add()`, `get()`, `empty()`,
`get_or_none()`
- [x] Verified thread-safety with concurrent producer/consumer threads
(100 items)
- [x] Verified multi-producer/consumer scenario (3 producers, 2
consumers, 150 items)
- [x] Confirmed no subprocess spawning when creating multiple queues
- [x] Code passes Black formatting check
#### For configuration changes:
- [x] `.env.default` is updated or already compatible with my changes
- [x] `docker-compose.yml` is updated or already compatible with my
changes
- [x] I have included a list of my configuration changes in the PR
description (under **Changes**)
> No configuration changes required - this is a code-only fix with no
external API changes.
---------
Co-authored-by: Otto <otto@agpt.co>
Co-authored-by: Zamil Majdy <majdyz@users.noreply.github.com>
Co-authored-by: Zamil Majdy <zamil.majdy@agpt.co>
[SECRT-1896: Fix crazy `GET /api/graphs` latency (P95 =
107s)](https://linear.app/autogpt/issue/SECRT-1896)
These changes should decrease latency of this endpoint by ~~60-65%~~ a
lot.
### Changes 🏗️
- Make `Graph.credentials_input_schema` cheaper by avoiding constructing
a new `BlockSchema` subclass
- Strip down `GraphMeta` - drop all computed fields
- Replace with either `GraphModel` or `GraphModelWithoutNodes` wherever
those computed fields are used
- Simplify usage in `list_graphs_paginated` and
`fetch_graph_from_store_slug`
- Refactor and clarify relationships between the different graph models
- Split `BaseGraph` into `GraphBaseMeta` + `BaseGraph`
- Strip down `Graph` - move `credentials_input_schema` and
`aggregate_credentials_inputs` to `GraphModel`
- Refactor to eliminate double `aggregate_credentials_inputs()` call in
`credentials_input_schema` call tree
- Add `GraphModelWithoutNodes` (similar to current `GraphMeta`)
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] `GET /api/graphs` works as it should
- [x] Running a graph succeeds
- [x] Adding a sub-agent in the Builder works as it should
## Summary
Improves the auto-generated message format when users submit
clarification answers in the agent generator.
## Before
```
I have the answers to your questions:
keyword_1: User answer 1
keyword_2: User answer 2
Please proceed with creating the agent.
```
<img width="748" height="153" alt="image"
src="https://github.com/user-attachments/assets/7231aaab-8ea4-406b-ba31-fa2b6055b82d"
/>
## After
```
**Here are my answers:**
> What is the primary purpose?
User answer 1
> What is the target audience?
User answer 2
Please proceed with creating the agent.
```
<img width="619" height="352" alt="image"
src="https://github.com/user-attachments/assets/ef8c1fbf-fb60-4488-b51f-407c1b9e3e44"
/>
## Changes
- Use human-readable question text instead of machine-readable keywords
- Use blockquote format for questions (natural "quote and reply"
pattern)
- Use double newlines for proper Markdown paragraph breaks
- Iterate over `message.questions` array to preserve original question
order
- Move handler inside conditional block for proper TypeScript type
narrowing
## Why
- The old format was ugly and hard to read (raw keywords, no line
breaks)
- The new format uses a natural "quoting and replying" pattern
- Better readability for both users and the LLM (verified: backend does
NOT parse keywords)
## Linear Ticket
Fixes [SECRT-1822](https://linear.app/autogpt/issue/SECRT-1822)
## Testing
- [ ] Trigger agent creation that requires clarifying questions
- [ ] Fill out the form and submit
- [ ] Verify message appears with new blockquote format
- [ ] Verify questions appear in original order
- [ ] Verify agent generation proceeds correctly
Co-authored-by: Toran Bruce Richards <toran.richards@gmail.com>
## Summary
Adds virus scanning at the `WorkspaceManager.write_file()` layer for
defense in depth.
## Problem
Previously, virus scanning was only performed at entry points:
- `store_media_file()` in `backend/util/file.py`
- `WriteWorkspaceFileTool` in
`backend/api/features/chat/tools/workspace_files.py`
This created a trust boundary where any new caller of
`WorkspaceManager.write_file()` would need to remember to scan first.
## Solution
Add `scan_content_safe()` call directly in
`WorkspaceManager.write_file()` before persisting to storage. This
ensures all content is scanned regardless of the caller.
## Changes
- Added import for `scan_content_safe` from `backend.util.virus_scanner`
- Added virus scan call after file size validation, before storage
## Testing
Existing tests should pass. The scan is a no-op in test environments
where ClamAV isn't running.
Closes https://linear.app/autogpt/issue/OPEN-2993
<!-- CURSOR_SUMMARY -->
---
> [!NOTE]
> **Medium Risk**
> Introduces a new required async scan step in the workspace write path,
which can add latency or cause new failures if the scanner/ClamAV is
misconfigured or unavailable.
>
> **Overview**
> Adds a **defense-in-depth** virus scan to
`WorkspaceManager.write_file()` by invoking `scan_content_safe()` after
file-size validation and before any storage/database persistence.
>
> This centralizes scanning so any caller writing workspace files gets
the same malware check without relying on upstream entry points to
remember to scan.
>
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
0f5ac68b92. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
<!-- Clearly explain the need for these changes: -->
This PR adds general-purpose video editing blocks for the AutoGPT
Platform, enabling automated video production workflows like documentary
creation, marketing videos, tutorial assembly, and content repurposing.
### Changes 🏗️
<!-- Concisely describe all of the changes made in this pull request:
-->
**New blocks added in `backend/blocks/video/`:**
- `VideoDownloadBlock` - Download videos from URLs (YouTube, Vimeo, news
sites, direct links) using yt-dlp
- `VideoClipBlock` - Extract time segments from videos with start/end
time validation
- `VideoConcatBlock` - Merge multiple video clips with optional
transitions (none, crossfade, fade_black)
- `VideoTextOverlayBlock` - Add text overlays/captions with positioning
and timing options
- `VideoNarrationBlock` - Generate AI narration via ElevenLabs and mix
with video audio (replace, mix, or ducking modes)
**Dependencies required:**
- `yt-dlp` - For video downloading
- `moviepy` - For video editing operations
**Implementation details:**
- All blocks follow the SDK pattern with proper error handling and
exception chaining
- Proper resource cleanup in `finally` blocks to prevent memory leaks
- Input validation (e.g., end_time > start_time)
- Test mocks included for CI
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Blocks follow the SDK pattern with
`BlockSchemaInput`/`BlockSchemaOutput`
- [x] Resource cleanup is implemented in `finally` blocks
- [x] Exception chaining is properly implemented
- [x] Input validation is in place
- [x] Test mocks are provided for CI environments
#### For configuration changes:
- [ ] `.env.default` is updated or already compatible with my changes
- [x] `docker-compose.yml` is updated or already compatible with my
changes
- [ ] I have included a list of my configuration changes in the PR
description (under **Changes**)
N/A - No configuration changes required.
<!-- CURSOR_SUMMARY -->
---
> [!NOTE]
> **Medium Risk**
> Adds new multimedia blocks that invoke ffmpeg/MoviePy and introduces
new external dependencies (plus container packages), which can impact
runtime stability and resource usage; download/overlay blocks are
present but disabled due to sandbox/policy concerns.
>
> **Overview**
> Adds a new `backend.blocks.video` module with general-purpose video
workflow blocks (download, clip, concat w/ transitions, loop, add-audio,
text overlay, and ElevenLabs-powered narration), including shared
utilities for codec selection, filename cleanup, and an ffmpeg-based
chapter-strip workaround for MoviePy.
>
> Extends credentials/config to support ElevenLabs
(`ELEVENLABS_API_KEY`, provider enum, system credentials, and cost
config) and adds new dependencies (`elevenlabs`, `yt-dlp`) plus Docker
runtime packages (`ffmpeg`, `imagemagick`).
>
> Improves file/reference handling end-to-end by embedding MIME types in
`workspace://...#mime` outputs and updating frontend rendering to detect
video vs image from MIME fragments (and broaden supported audio/video
extensions), with optional enhanced output rendering behind a feature
flag in the legacy builder UI.
>
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
da7a44d794. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
---------
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: Nicholas Tindle <ntindle@users.noreply.github.com>
Co-authored-by: Otto <otto@agpt.co>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
## Summary
Adds support for Anthropic's newly released Claude Opus 4.6 model.
## Changes
- Added `claude-opus-4-6` to the `LlmModel` enum
- Added model metadata: 200K context window (1M beta), **128K max output
tokens**
- Added block cost config (same pricing tier as Opus 4.5: $5/MTok input,
$25/MTok output)
- Updated chat config default model to Claude Opus 4.6
## Model Details
From [Anthropic's
docs](https://docs.anthropic.com/en/docs/about-claude/models):
- **API ID:** `claude-opus-4-6`
- **Context window:** 200K tokens (1M beta)
- **Max output:** 128K tokens (up from 64K on Opus 4.5)
- **Extended thinking:** Yes
- **Adaptive thinking:** Yes (new, Opus 4.6 exclusive)
- **Knowledge cutoff:** May 2025 (reliable), Aug 2025 (training)
- **Pricing:** $5/MTok input, $25/MTok output (same as Opus 4.5)
---------
Co-authored-by: Toran Bruce Richards <toran.richards@gmail.com>
## Summary
Implements a `TextEncoderBlock` that encodes plain text into escape
sequences (the reverse of `TextDecoderBlock`).
## Changes
### Block Implementation
- Added `encoder_block.py` with `TextEncoderBlock` in
`autogpt_platform/backend/backend/blocks/`
- Uses `codecs.encode(text, "unicode_escape").decode("utf-8")` for
encoding
- Mirrors the structure and patterns of the existing `TextDecoderBlock`
- Categorised as `BlockCategory.TEXT`
### Documentation
- Added Text Encoder section to
`docs/integrations/block-integrations/text.md` (the auto-generated docs
file for TEXT category blocks)
- Expanded "How it works" with technical details on the encoding method,
validation, and edge cases
- Added 3 structured use cases per docs guidelines: JSON payload
preparation, Config/ENV generation, Snapshot fixtures
- Added Text Encoder to the overview table in
`docs/integrations/README.md`
- Removed standalone `encoder_block.md` (TEXT category blocks belong in
`text.md` per `CATEGORY_FILE_MAP` in `generate_block_docs.py`)
### Documentation Formatting (CodeRabbit feedback)
- Added blank lines around markdown tables (MD058)
- Added `text` language tags to fenced code blocks (MD040)
- Restructured use case section with bold headings per coding guidelines
## How Docs Were Synced
The `check-docs-sync` CI job runs `poetry run python
scripts/generate_block_docs.py --check` which expects blocks to be
documented in category-grouped files. Since `TextEncoderBlock` uses
`BlockCategory.TEXT`, the `CATEGORY_FILE_MAP` maps it to `text.md` — not
a standalone file. The block entry was added to `text.md` following the
exact format used by the generator (with `<!-- MANUAL -->` markers for
hand-written sections).
## Related Issue
Fixes#11111
---------
Co-authored-by: Otto <otto@agpt.co>
Co-authored-by: lif <19658300+majiayu000@users.noreply.github.com>
Co-authored-by: Aryan Kaul <134673289+aryancodes1@users.noreply.github.com>
Co-authored-by: Nicholas Tindle <nicholas.tindle@agpt.co>
Co-authored-by: Nick Tindle <nick@ntindle.com>
## Summary
When editing an agent via CoPilot's `edit_agent` tool, the code was
always creating a new `LibraryAgent` entry instead of updating the
existing one to point to the new graph version. This caused duplicate
agents to appear in the user's library.
## Changes
In `save_agent_to_library()`:
- When `is_update=True`, now checks if there's an existing library agent
for the graph using `get_library_agent_by_graph_id()`
- If found, uses `update_agent_version_in_library()` to update the
existing library agent to point to the new version
- Falls back to creating a new library agent if no existing one is found
(e.g., if editing a graph that wasn't added to library yet)
## Testing
- Verified lint/format checks pass
- Plan reviewed and approved by Staff Engineer Plan Reviewer agent
## Related
Fixes [SECRT-1857](https://linear.app/autogpt/issue/SECRT-1857)
---------
Co-authored-by: Zamil Majdy <zamil.majdy@agpt.co>
## Summary
- Add asymptotic progress bar that appears during long-running chat
tasks
- Progress bar shows after 10 seconds with "Working on it..." label and
percentage
- Uses half-life formula: ~50% at 30s, ~75% at 60s, ~87.5% at 90s, etc.
- Creates the classic "game loading bar" effect that never reaches 100%
https://github.com/user-attachments/assets/3c59289e-793c-4a08-b3fc-69e1eef28b1f
## Test plan
- [x] Start a chat that triggers agent generation
- [x] Wait 10+ seconds for the progress bar to appear
- [x] Verify progress bar is centered with label and percentage
- [x] Verify progress follows expected timing (~50% at 30s)
- [x] Verify progress bar disappears when task completes
---------
Co-authored-by: Otto <otto@agpt.co>
## Summary
- Add special UI prompt when agent is successfully created in chat
- Show "Agent Created Successfully" with agent name
- Provide two action buttons:
- **Run with example values**: Sends chat message asking AI to run with
placeholders
- **Run with my inputs**: Opens RunAgentModal for custom input
configuration
- After run/schedule, automatically send chat message with execution
details for AI monitoring
https://github.com/user-attachments/assets/b11e118c-de59-4b79-a629-8bd0d52d9161
## Test plan
- [x] Create an agent through chat
- [x] Verify "Agent Created Successfully" prompt appears
- [x] Click "Run with example values" - verify chat message is sent
- [x] Click "Run with my inputs" - verify RunAgentModal opens
- [x] Fill inputs and run - verify chat message with execution ID is
sent
- [x] Fill inputs and schedule - verify chat message with schedule
details is sent
---------
Co-authored-by: Otto <otto@agpt.co>
When users search for agents, guide them toward creating custom agents
if no results are found or after showing results. This improves user
engagement by offering a clear next step.
### Changes 🏗️
- Updated `agent_search.py` to add CTAs in search responses
- Added messaging to inform users they can create custom agents based on
their needs
- Applied to both "no results found" and "agents found" scenarios
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Search for agents in marketplace with matching results
- [x] Search for agents in marketplace with no results
- [x] Search for agents in library with matching results
- [x] Search for agents in library with no results
- [x] Verify CTA message appears in all cases
---------
Co-authored-by: Otto <otto@agpt.co>
In non-production environments, the chat service now fetches prompts
with the `latest` label instead of the default production-labeled
prompt. This makes it easier to test and iterate on prompt changes in
dev/staging without needing to promote them to production first.
### Changes 🏗️
- Updated `_get_system_prompt_template()` in chat service to pass
`label="latest"` when `app_env` is not `PRODUCTION`
- Production environments continue using the default behavior
(production-labeled prompts)
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Verified that in non-production environments, prompts with
`latest` label are fetched
- [x] Verified that production environments still use the default
(production) labeled prompts
Co-authored-by: Otto <otto@agpt.co>
## Summary
Fixes [SECRT-1889](https://linear.app/autogpt/issue/SECRT-1889): The
YouTube transcription block was yielding both `video_id` and `error`
when the transcript fetch failed.
## Problem
The block yielded `video_id` immediately upon extracting it from the
URL, before attempting to fetch the transcript. If the transcript fetch
failed, both outputs were present.
```python
# Before
video_id = self.extract_video_id(input_data.youtube_url)
yield "video_id", video_id # ← Yielded before transcript attempt
transcript = self.get_transcript(video_id, credentials) # ← Could fail here
```
## Solution
Wrap the entire operation in try/except and only yield outputs after all
operations succeed:
```python
# After
try:
video_id = self.extract_video_id(input_data.youtube_url)
transcript = self.get_transcript(video_id, credentials)
transcript_text = self.format_transcript(transcript=transcript)
# Only yield after all operations succeed
yield "video_id", video_id
yield "transcript", transcript_text
except Exception as e:
yield "error", str(e)
```
This follows the established pattern in other blocks (e.g.,
`ai_image_generator_block.py`).
## Testing
- All 10 unit tests pass (`test/blocks/test_youtube.py`)
- Lint/format checks pass
Co-authored-by: Toran Bruce Richards <toran.richards@gmail.com>
### Changes 🏗️
Fixes **AUTOGPT-SERVER-7JA** (123 events since Jan 27, 2026).
#### Problem
`StreamHeartbeat` was added to keep SSE connections alive during
long-running tool executions (yielded every 15s while waiting). However,
the main `stream_chat_completion` handler's `elif` chain didn't have a
case for it:
```
StreamTextStart → ✅ handled
StreamTextDelta → ✅ handled
StreamTextEnd → ✅ handled
StreamToolInputStart → ✅ handled
StreamToolInputAvailable → ✅ handled
StreamToolOutputAvailable → ✅ handled
StreamFinish → ✅ handled
StreamError → ✅ handled
StreamUsage → ✅ handled
StreamHeartbeat → ❌ fell through to 'Unknown chunk type' error
```
This meant every heartbeat during tool execution generated a Sentry
error instead of keeping the connection alive.
#### Fix
Add `StreamHeartbeat` to the `elif` chain and yield it through. The
route handler already calls `to_sse()` on all yielded chunks, and
`StreamHeartbeat.to_sse()` correctly returns `: heartbeat\n\n` (SSE
comment format, ignored by clients but keeps proxies/load balancers
happy).
**1 file changed, 3 insertions.**
## Summary
Fixes the flaky `test_block_credit_reset` test that was failing on
multiple PRs with `assert 0 == 1000`.
## Root Cause
The test calls `disable_test_user_transactions()` which sets `updatedAt`
to 35 days ago from the **actual current time**. It then mocks
`time_now` to January 1st.
**The bug**: If the test runs in early February, 35 days ago is January
— the **same month** as the mocked `time_now`. The credit refill logic
only triggers when the balance snapshot is from a *different* month, so
no refill happens and the balance stays at 0.
## Fix
After calling `disable_test_user_transactions()`, explicitly set
`updatedAt` to December of the previous year. This ensures it's always
in a different month than the mocked `month1` (January), regardless of
when the test runs.
## Testing
CI will verify the fix.
## Summary
Implements [SECRT-1880](https://linear.app/autogpt/issue/SECRT-1880) -
Improve Linear Search Block
## Changes
### Models (`models.py`)
- Added `State` model with `id`, `name`, and `type` fields for workflow
state information
- Added `state: State | None` field to `Issue` model
### API Client (`_api.py`)
- Updated `try_search_issues()` to:
- Add `max_results` parameter (default 10, was ~50) to reduce token
usage
- Add `team_id` parameter for team filtering
- Return `createdAt`, `state`, `project`, and `assignee` fields in
results
- Fixed `try_get_team_by_name()` to return descriptive error message
when team not found instead of crashing with `IndexError`
### Block (`issues.py`)
- Added `max_results` input parameter (1-100, default 10)
- Added `team_name` input parameter for optional team filtering
- Added `error` output field for graceful error handling
- Added categories (`PRODUCTIVITY`, `ISSUE_TRACKING`)
- Updated test fixtures to include new fields
## Breaking Changes
| Change | Before | After | Mitigation |
|--------|--------|-------|------------|
| Default result count | ~50 | 10 | Users can set `max_results` up to
100 if needed |
## Non-Breaking Changes
- `state` field added to `Issue` (optional, defaults to `None`)
- `max_results` param added (has default value)
- `team_name` param added (optional, defaults to `None`)
- `error` output added (follows established pattern from GitHub blocks)
## Testing
- [x] Format/lint checks pass
- [x] Unit test fixtures updated
Resolves SECRT-1880
---------
Co-authored-by: Toran Bruce Richards <toran.richards@gmail.com>
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: Toran Bruce Richards <Torantulino@users.noreply.github.com>
- Fixes [SECRT-1851: \[Copilot\] `run_agent` tool doesn't filter
host-scoped credentials](https://linear.app/autogpt/issue/SECRT-1851)
- Follow-up to #11881
### Changes 🏗️
- Filter host-scoped credentials for `run_agent` tool
- Tighten validation on host input field in `HostScopedCredentialsModal`
- Use netloc (w/ port) rather than just hostname (w/o port) as host
scope
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- Create graph that requires host-scoped credentials to work
- Create host-scoped credentials with a *different* host
- Try to have Copilot run the graph
- [x] -> no matching credentials available
- Create new credentials
- [x] -> works
---------
Co-authored-by: Nicholas Tindle <nicholas.tindle@agpt.co>
## Summary
Update the CoPilot homepage to shift from "what do you want to
automate?" to "tell me about your problems." This lowers the barrier to
engagement by letting users describe their work frustrations instead of
requiring them to identify automations themselves.
## Changes
| Element | Before | After |
|---------|--------|-------|
| Headline | "What do you want to automate?" | "Tell me about your work
— I'll find what to automate." |
| Placeholder | "You can search or just ask - e.g. 'create a blog post
outline'" | "What's your role and what eats up most of your day? e.g.
'I'm a real estate agent and I hate...'" |
| Button 1 | "Show me what I can automate" | "I don't know where to
start, just ask me stuff" |
| Button 2 | "Design a custom workflow" | "I do the same thing every
week and it's killing me" |
| Button 3 | "Help me with content creation" | "Help me find where I'm
wasting my time" |
| Container | max-w-2xl | max-w-3xl |
> **Note on container width:** The `max-w-2xl` → `max-w-3xl` change is
just to keep the longer headline on one line. This works but may not be
the ideal solution — @lluis-xai should advise on the proper approach.
## Why This Matters
The current UX assumes users know what they want to automate. In
reality, most users know what frustrates them but can't identify
automations. The current screen blocks Otto from starting the discovery
conversation that leads to useful recommendations.
## Files Changed
- `autogpt_platform/frontend/src/app/(platform)/copilot/page.tsx` —
headline, placeholder, container width
- `autogpt_platform/frontend/src/app/(platform)/copilot/helpers.ts` —
quick action button text
Resolves: [SECRT-1876](https://linear.app/autogpt/issue/SECRT-1876)
---------
Co-authored-by: Lluis Agusti <hi@llu.lu>
## Summary
Fixes a reflected cross-site scripting (XSS) vulnerability in the OAuth
callback route.
**Security Issue:**
https://github.com/Significant-Gravitas/AutoGPT/security/code-scanning/202
### Vulnerability
The OAuth callback route at
`frontend/src/app/(platform)/auth/integrations/oauth_callback/route.ts`
was writing user-controlled data directly into an HTML response without
proper sanitization. This allowed potential attackers to inject
malicious scripts via OAuth callback parameters.
### Fix
Added a `safeJsonStringify()` function that escapes characters that
could break out of the script context:
- `<` → `\u003c`
- `>` → `\u003e`
- `&` → `\u0026`
This prevents any user-provided values from being interpreted as
HTML/script content when embedded in the response.
### References
- [OWASP XSS Prevention Cheat
Sheet](https://cheatsheetseries.owasp.org/cheatsheets/Cross_Site_Scripting_Prevention_Cheat_Sheet.html)
- [CWE-79: Improper Neutralization of Input During Web Page
Generation](https://cwe.mitre.org/data/definitions/79.html)
## Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Verified the OAuth callback still functions correctly
- [x] Confirmed special characters in OAuth responses are properly
escaped
<!-- Clearly explain the need for these changes: -->
### Changes 🏗️
- Disable auto-opening Wallet for first time user and on credit increase
- Remove no longer needed `lastSeenCredits` state and storage
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Wallet doesn't open automatically
Fixes GHSA-rc89-6g7g-v5v7 / CVE-2026-22038
The logger.info() calls were explicitly logging API keys via
get_secret_value(), exposing credentials in plaintext logs.
Changes:
- Replace info-level credential logging with debug-level provider logging
- Remove all explicit secret value logging from observe/act/extract blocks
Co-authored-by: Otto <otto@agpt.co>
## Changes 🏗️
Adds Redis-based SSE reconnection support for long-running CoPilot
operations (like Agent Generator), enabling clients to reconnect and
resume receiving updates after disconnection.
### What this does:
- **Stream Registry** - Redis-backed task tracking with message
persistence via Redis Streams
- **SSE Reconnection** - Clients can reconnect to active tasks using
`task_id` and `last_message_id`
- **Duplicate Message Fix** - Filters out in-progress assistant messages
from session response when active stream exists
- **Completion Consumer** - Handles background task completion
notifications via Redis Streams
### Architecture:
```
1. User sends message → Backend creates task in Redis
2. SSE chunks written to Redis Stream for persistence
3. Client receives chunks via SSE subscription
4. If client disconnects → Task continues in background
5. Client reconnects → GET /sessions/{id} returns active_stream info
6. Client subscribes to /tasks/{task_id}/stream with last_message_id
7. Missed messages replayed from Redis Stream
```
### Key endpoints:
- `GET /sessions/{session_id}` - Returns `active_stream` info if task is
running
- `GET /tasks/{task_id}/stream?last_message_id=X` - SSE endpoint for
reconnection
- `GET /tasks/{task_id}` - Get task status
- `POST /operations/{op_id}/complete` - Webhook for external service
completion
### Duplicate message fix:
When `GET /sessions/{id}` detects an active stream:
1. Filters out the in-progress assistant message from response
2. Returns `last_message_id="0-0"` so client replays stream from
beginning
3. Client receives complete response only through SSE (single source of
truth)
### Frontend changes:
- Task persistence in localStorage for cross-tab reconnection
- Stream event dispatcher handles reconnection flow
- Deduplication logic prevents duplicate messages
### Testing:
- Manual testing of reconnection scenarios
- Verified duplicate message fix works correctly
## Related
- Resolves SSE timeout issues for Agent Generator
- Fixes duplicate message bug on reconnection
Zamil Majdy