## Summary
- Routes Claude Agent SDK API calls through OpenRouter via
`ANTHROPIC_BASE_URL` / `ANTHROPIC_AUTH_TOKEN` env vars, enabling
per-call token and cost tracking on the OpenRouter dashboard
- Adds `sdk_model` and `sdk_max_budget_usd` config fields for
SDK-specific model selection and budget control
- Emits `StreamUsage` from SDK `ResultMessage` so the frontend receives
token counts, and persists usage to `session.usage`
- Fixes Langfuse tracing to use the configured model name instead of a
hardcoded default
- Updates Anthropic fallback to use `config.api_key` / `config.base_url`
(OpenRouter routing) instead of raw `ANTHROPIC_API_KEY` env var
## Test plan
- [ ] Deploy and send a CoPilot message — verify the API call appears on
the OpenRouter dashboard
- [ ] Check Langfuse trace shows correct model name (e.g.
`claude-opus-4.6` not hardcoded `claude-sonnet-4-20250514`)
- [ ] Verify frontend receives `StreamUsage` with `promptTokens` /
`completionTokens` values
- [ ] Set `CHAT_SDK_MAX_BUDGET_USD` and verify budget is respected
- [ ] Test fallback path (without `claude-agent-sdk` installed) still
works via OpenRouter
<!-- greptile_comment -->
<h2>Greptile Overview</h2>
<details><summary><h3>Greptile Summary</h3></summary>
Routes Claude Agent SDK API calls through OpenRouter for enhanced
observability and cost tracking. The PR enables per-call token tracking
on the OpenRouter dashboard by configuring the SDK to use
`ANTHROPIC_BASE_URL` and `ANTHROPIC_AUTH_TOKEN` environment variables
derived from the chat configuration.
Key changes:
- Added `sdk_model` and `sdk_max_budget_usd` configuration fields for
SDK-specific control
- Implemented automatic model name resolution that strips OpenRouter
provider prefixes
- Updated SDK client initialization to route through OpenRouter with
proper environment variables
- Emits `StreamUsage` events from SDK `ResultMessage` for frontend token
visibility
- Persists usage data to `session.usage` for historical tracking
- Fixed Langfuse tracing to use the configured model name instead of
hardcoded defaults
- Updated fallback path to use OpenRouter routing instead of direct
Anthropic API
</details>
<details><summary><h3>Confidence Score: 4/5</h3></summary>
- Safe to merge with minor observations - the implementation is solid
and the changes are well-structured
- The code quality is high with proper error handling, clear separation
of concerns, and good defensive coding practices. The changes integrate
cleanly with existing patterns. Minor observations include missing
validation for sdk_max_budget_usd and a potential edge case in model
name resolution, but these don't block merging
- No files require special attention - all changes follow existing
patterns and maintain consistency
</details>
<details><summary><h3>Sequence Diagram</h3></summary>
```mermaid
sequenceDiagram
participant Frontend
participant Backend
participant SDK as Claude Agent SDK
participant OpenRouter
participant Anthropic
participant Langfuse
Frontend->>Backend: POST /chat/completions
Backend->>Backend: Load config (api_key, base_url)
Backend->>Backend: Resolve SDK model (strip OpenRouter prefix)
Backend->>Backend: Build SDK env vars (ANTHROPIC_BASE_URL, ANTHROPIC_AUTH_TOKEN)
Backend->>Langfuse: Initialize TracedSession with model name
Backend->>SDK: ClaudeSDKClient(model, env, max_budget_usd)
SDK->>SDK: Use ANTHROPIC_BASE_URL from env
SDK->>OpenRouter: POST /messages (via configured base_url)
OpenRouter->>Anthropic: Forward request with routing
Anthropic-->>OpenRouter: Stream response chunks
OpenRouter-->>SDK: Stream response with usage data
loop For each SDK message
SDK-->>Backend: AssistantMessage/UserMessage/ResultMessage
Backend->>Langfuse: log_sdk_message()
Backend->>Backend: SDKResponseAdapter.convert_message()
Backend->>Backend: Extract usage from ResultMessage
Backend->>Backend: Persist Usage to session.usage
Backend-->>Frontend: StreamUsage(promptTokens, completionTokens)
Backend-->>Frontend: StreamTextDelta/StreamToolInput/etc
end
Backend->>Langfuse: Log final generation with model name
Backend->>Backend: Save session with usage data
Backend-->>Frontend: StreamFinish
```
</details>
<!-- greptile_other_comments_section -->
<!-- /greptile_comment -->
I'm getting circular import issues because there is a lot of
cross-importing between `backend.data`, `backend.blocks`, and other
modules. This change reduces block-related cross-imports and thus risk
of breaking circular imports.
### Changes 🏗️
- Strip down `backend.data.block`
- Move `Block` base class and related class/enum defs to
`backend.blocks._base`
- Move `is_block_auth_configured` to `backend.blocks._utils`
- Move `get_blocks()`, `get_io_block_ids()` etc. to `backend.blocks`
(`__init__.py`)
- Update imports everywhere
- Remove unused and poorly typed `Block.create()`
- Change usages from `block_cls.create()` to `block_cls()`
- Improve typing of `load_all_blocks` and `get_blocks`
- Move cross-import of `backend.api.features.library.model` from
`backend/data/__init__.py` to `backend/data/integrations.py`
- Remove deprecated attribute `NodeModel.webhook`
- Re-generate OpenAPI spec and fix frontend usage
- Eliminate module-level `backend.blocks` import from `blocks/agent.py`
- Eliminate module-level `backend.data.execution` and
`backend.executor.manager` imports from `blocks/helpers/review.py`
- Replace `BlockInput` with `GraphInput` for graph inputs
### 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 static type-checking + tests should be sufficient for this
Replace the read-modify-write pattern in stream_chat_post with an
atomic append_and_save_message helper that acquires the session lock
before re-fetching and appending. This prevents message loss when
concurrent requests modify the same session.
- Create tracing.py with TracedSession context manager
- Automatically trace user messages, SDK messages, and results
- Capture tool calls with input/output and timing
- Log usage and cost from SDK ResultMessage
- No-op when Langfuse not configured (zero overhead)
- Clean integration into service.py via context manager
- Add empty check after session_id sanitization
- Add assertion for defense-in-depth
- Add explicit '..' traversal check in cleanup
- Replace glob with os.listdir to avoid glob injection
- Add validation that project_dir stays under ~/.claude/projects
- Add warning logs for rejected paths
Addresses CodeQL alert about uncontrolled data in path expression
- Use json.dumps instead of str() for more predictable pattern matching
- Log warning when SDK not available and security hooks are disabled
Addresses CodeRabbit review feedback
- Extract command name (jq, grep, etc.) from Bash tool input
- Display 'jq completed' instead of 'Bash completed'
- Add ripgrep and tree to Dockerfile (match ALLOWED_BASH_COMMANDS)
- Add sdk_max_buffer_size config option (default 10MB, was 1MB)
- Pass max_buffer_size to ClaudeAgentOptions to prevent crashes on large tool outputs
- Install jq in Dockerfile for JSON processing capabilities
Fixes AUTOGPT-SERVER-7V2
## 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 -->
The SDK CLI truncates large tool results (writing them to disk),
which breaks frontend widget rendering (e.g., find_block's block
list cards). Stash the full MCP tool output before the SDK sees it,
then use the stash in the response adapter so the frontend always
receives the complete JSON for proper widget parsing.
The Vercel AI SDK frontend renders tool widgets based on tool name
(e.g. "tool-find_block", "tool-run_agent"). The SDK sends tool names
with the MCP prefix (mcp__copilot__find_block) which didn't match
any frontend switch case, causing tool execution to be invisible.
Strip the mcp__copilot__ prefix in the response adapter so tool events
reach the correct frontend widget handlers.
Move these tools from fully-blocked to workspace-scoped: they are now
allowed when the file path stays within the SDK working directory
(/tmp/copilot-<session>/) or the tool-results directory
(~/.claude/projects/…/tool-results/). This enables the SDK's built-in
oversized tool result handling and workspace file operations.
- Add _validate_workspace_path() with normpath-based path validation
- Pass sdk_cwd from service.py into create_security_hooks()
- Add 20 unit tests covering allowed/denied paths, traversal attacks
The non-SDK path emits step boundaries (StartStep/FinishStep) around
each LLM turn and tool cycle. The SDK adapter was missing these,
causing the frontend to lack visual step framing for tool calls.
Now the SDK adapter emits:
- StreamStartStep after init and before each new LLM turn
- StreamFinishStep after tool results and before final finish
## 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>
## 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>
Routes.py already publishes a StreamStart before calling the service.
The SDK path filters the duplicate internally, but the non-SDK path
did not, causing two StreamStart events to reach the frontend.
CodeQL doesn't recognize re.sub as a path sanitizer. Switch to the
os.path.normpath + startswith prefix check pattern that CodeQL's
taint model explicitly recognizes as breaking the taint chain.
- Use session-specific temp dir (/tmp/copilot-{session_id}) as SDK cwd
to prevent concurrent sessions from deleting each other's tool-result
files during cleanup
- Move _cleanup_sdk_tool_results() to outer finally block so it runs
even when the outer except Exception fires
- Clean up the temp cwd directory after each session
- Remove unnecessary inner try/finally nesting
- Fix message accumulation bug: reset has_appended_assistant when
creating new post-tool assistant message to prevent lost text deltas
- Fix hardcoded model in anthropic_fallback.py: use config.model instead
of hardcoded "claude-sonnet-4-20250514"
- Fix _SDK_TOOL_RESULTS_DIR using hardcoded /root/ path: use expanduser
- Remove unused create_strict_security_hooks (~75 lines)
- Remove unused create_heartbeat/create_usage from response adapter
- Remove unused RAW_TOOL_NAMES from tool_adapter
- Extract _MAX_TOOL_ITERATIONS constant from magic number
- Remove broken --resume/session file approach (CLI v2.1.38 can't load
>2 message session files) and delete session_file.py + tests
- Embed prior conversation turns as <conversation_history> context in
the user message for multi-turn memory
- Add context compaction using shared compress_context() from prompt.py
with LLM summarization + truncation fallback for long conversations
- Reuse _build_system_prompt and _generate_session_title from parent
service.py instead of duplicating (gains Langfuse prompt support)
- Add has_conversation_history param to _build_system_prompt to avoid
greeting on multi-turn conversations
- Fix _SDK_TOOL_RESULTS_GLOB from hardcoded /root/ to expanduser ~/
The CLI resolves symlinks when computing its project directory (e.g.
/tmp -> /private/tmp on macOS), so our session file writes must use
the resolved path to match. Also adds cwd to ClaudeAgentOptions and
debug logging for SDK messages.
## 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>
Replace broken AsyncIterable approach (CLI rejects assistant-type stdin
messages) with JSONL session files written to the CLI's storage directory.
This enables --resume to load full user+assistant context with turn-level
compaction support for long conversations.
Replace duck typing (class name checks, getattr) with isinstance() using
SDK-exported dataclasses. Replace file-based --resume with AsyncIterable
message injection for conversation history, eliminating disk I/O. Add 15
unit tests for the response adapter.
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>
- Skip BLOCKED_TOOLS check for tools with mcp__copilot__ prefix since they
are already sandboxed by tool_adapter (fixes Read tool being blocked)
- Fall back to session.messages for title generation when message=None
### 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>
The Claude Agent SDK saves tool results exceeding its token limit to
files and instructs the agent to read them back with a Read tool. Our
MCP server didn't have this tool, breaking the agent on large results
like run_block output (117K+ chars).
Changes:
- Add a Read tool to the MCP server (restricted to /root/.claude/)
- Register it in COPILOT_TOOL_NAMES so the SDK can use it
- Add safety-net truncation at 500K chars for extreme cases
- Clean up SDK tool-result files after each client session
When run_ai_generation() or event_generator() encounter errors, they
were only publishing StreamFinish without a preceding StreamError. The
frontend treats finish-without-error as normal completion, leaving the
user with an apparently stuck/empty response requiring a page refresh.
