feat: Wire A2A inter-agent messaging into orchestrator + API#45
Merged
groupthinking merged 1 commit intomainfrom Feb 28, 2026
Merged
feat: Wire A2A inter-agent messaging into orchestrator + API#45groupthinking merged 1 commit intomainfrom
groupthinking merged 1 commit intomainfrom
Conversation
- Add A2AContextMessage dataclass to AgentOrchestrator for lightweight inter-agent context sharing during parallel task execution - Auto-broadcast agent results to peer agents after parallel execution - Add send_a2a_message() and get_a2a_log() methods to orchestrator - Add POST /api/v1/agents/a2a/send endpoint for frontend-to-agent messaging - Add GET /api/v1/agents/a2a/log endpoint to query message history - Extend frontend agentService with sendA2AMessage() and getA2ALog() Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Contributor
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Contributor
Summary of ChangesHello, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request significantly enhances the multi-agent system by introducing robust Agent-to-Agent (A2A) communication capabilities. It allows agents to share context and information seamlessly after parallel execution, and provides programmatic interfaces for sending and logging these inter-agent messages. This integration paves the way for more sophisticated and collaborative agent behaviors. Highlights
Changelog
Activity
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request effectively wires up the A2A inter-agent messaging framework, adding new API endpoints and integrating context sharing into the agent orchestrator. The changes are logical and well-structured. My review focuses on improving adherence to the repository's style guide, ensuring consistency with existing patterns like dependency injection, and addressing a potential memory leak in the message logging implementation. Overall, these are solid additions that enhance the agent framework's capabilities.
Comment on lines
+1230
to
+1232
| async def send_a2a_message( | ||
| body: dict[str, Any] = {}, | ||
| ): |
Contributor
There was a problem hiding this comment.
The function signature uses dict[str, Any] for the request body, which violates the style guide's requirement for "strict type hinting". Using a Pydantic model provides automatic validation, better API documentation, and improved type safety.
You should define a A2ASendMessageRequest model in models.py and use it here. For example:
# In models.py
from pydantic import BaseModel, Field
# ...
class A2ASendMessageRequest(BaseModel):
sender: Optional[str] = "frontend"
recipient: str
content: dict[str, Any] = Field(default_factory=dict)
conversation_id: Optional[str] = NoneThen, you can update the function signature and body to use this model, which also allows you to remove the manual validation for recipient.
Suggested change
| async def send_a2a_message( | |
| body: dict[str, Any] = {}, | |
| ): | |
| async def send_a2a_message( | |
| body: A2ASendMessageRequest, # Define this Pydantic model in models.py | |
| ): |
References
- The function uses
dict[str, Any]for the request body instead of a strictly typed Pydantic model, which is required by the coding standards. (link)
| self.logger = logging.getLogger("agent_orchestrator") | ||
| self._agents: dict[str, BaseAgent] = {} | ||
| self._agent_types: dict[str, type[BaseAgent]] = {} | ||
| self._a2a_log: list[A2AContextMessage] = [] |
Contributor
There was a problem hiding this comment.
The _a2a_log is an in-memory list that is appended to but never cleared or capped. In a long-running process, this will lead to unbounded memory growth and eventually cause performance issues or crashes. To prevent this, you should use a capped collection, such as collections.deque with a maxlen.
You'll need to from collections import deque.
Suggested change
| self._a2a_log: list[A2AContextMessage] = [] | |
| self._a2a_log: "deque[A2AContextMessage]" = deque(maxlen=1000) # Using a capped collection |
| if not recipient: | ||
| raise HTTPException(status_code=400, detail="recipient is required") | ||
|
|
||
| orch = AgentOrchestrator() |
Contributor
There was a problem hiding this comment.
AgentOrchestrator is instantiated directly. This endpoint should use the existing dependency injection pattern (Depends(get_agent_orchestrator_service)) to ensure it uses the shared global instance and maintains consistency with other endpoints. Please add orch: AgentOrchestrator = Depends(get_agent_orchestrator_service) to the function signature and remove this line.
| limit: int = 50, | ||
| ): | ||
| """Return recent A2A inter-agent messages.""" | ||
| orch = AgentOrchestrator() |
Contributor
There was a problem hiding this comment.
AgentOrchestrator is instantiated directly. This endpoint should use the existing dependency injection pattern (Depends(get_agent_orchestrator_service)) to ensure it uses the shared global instance and maintains consistency with other endpoints. Please add orch: AgentOrchestrator = Depends(get_agent_orchestrator_service) to the function signature and remove this line.
Comment on lines
+331
to
+349
| def get_a2a_log( | ||
| self, | ||
| conversation_id: str | None = None, | ||
| limit: int = 50, | ||
| ) -> list[dict[str, Any]]: | ||
| """Return recent A2A messages, optionally filtered by conversation.""" | ||
| msgs = self._a2a_log | ||
| if conversation_id: | ||
| msgs = [m for m in msgs if m.conversation_id == conversation_id] | ||
| return [ | ||
| { | ||
| "sender": m.sender, | ||
| "recipient": m.recipient, | ||
| "content": m.content, | ||
| "conversation_id": m.conversation_id, | ||
| "timestamp": m.timestamp, | ||
| } | ||
| for m in msgs[-limit:] | ||
| ] |
Contributor
There was a problem hiding this comment.
This function can be improved for type safety and robustness:
- Return Type: Returning
list[dict[str, Any]]is not strictly typed. You can returnlist[A2AContextMessage]directly, as FastAPI can serialize dataclasses. This aligns better with the style guide's emphasis on strict typing. - Slicing with Deque: If
_a2a_logis converted to adequeto prevent memory leaks (as suggested in another comment), themsgs[-limit:]slice will fail when noconversation_idis provided. Deques do not support negative slicing.
Here's a revised implementation that addresses both points and is robust for both list and deque.
def get_a2a_log(
self,
conversation_id: str | None = None,
limit: int = 50,
) -> list[A2AContextMessage]:
"""Return recent A2A messages, optionally filtered by conversation."""
if conversation_id:
# Filtering creates a list, so negative slicing is safe here.
return [m for m in self._a2a_log if m.conversation_id == conversation_id][-limit:]
# If self._a2a_log is a deque, convert to list for slicing.
# This is safe but could be optimized for very large deques if performance is critical.
return list(self._a2a_log)[-limit:]References
- The function returns a
list[dict[str, Any]]which is not strictly typed. The suggestion improves this by returning a list of strongly-typedA2AContextMessageobjects. (link)
Contributor
There was a problem hiding this comment.
Pull request overview
This PR connects A2A-style inter-agent messaging to the agent orchestrator, exposes that functionality via new API v1 endpoints, and adds corresponding frontend service methods to send messages and fetch logs.
Changes:
- Added an in-orchestrator A2A message log plus helper methods to send messages and query the log.
- Added
/api/v1/agents/a2a/sendand/api/v1/agents/a2a/logendpoints for sending and inspecting A2A messages. - Added frontend
agentServicemethods to call the new A2A endpoints.
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 5 comments.
| File | Description |
|---|---|
src/youtube_extension/services/agents/adapters/agent_orchestrator.py |
Introduces A2A message dataclass, in-memory A2A log, and “broadcast” logging after parallel execution. |
src/youtube_extension/backend/api/v1/router.py |
Adds A2A send/log endpoints under the Agents tag. |
apps/web/src/lib/services/agent-service.ts |
Adds sendA2AMessage and getA2ALog client helpers for the new endpoints. |
Comment on lines
+1242
to
+1248
| orch = AgentOrchestrator() | ||
| msg = await orch.send_a2a_message( | ||
| sender=sender, | ||
| recipient=recipient, | ||
| content=content, | ||
| conversation_id=conversation_id, | ||
| ) |
There was a problem hiding this comment.
send_a2a_message/get_a2a_log create a fresh AgentOrchestrator() per request, which bypasses the app’s orchestrator singleton from get_agent_orchestrator_service() (and therefore has no registered agent types and an empty _a2a_log). This makes message delivery/log retrieval effectively non-functional across requests. Use the DI-provided orchestrator (e.g., orch: AgentOrchestrator = Depends(get_agent_orchestrator_service)) instead of instantiating a new one here.
Comment on lines
+1231
to
+1233
| body: dict[str, Any] = {}, | ||
| ): | ||
| """Send a context-share or tool-request message between agents.""" |
There was a problem hiding this comment.
Avoid using a mutable default for the request body (body: dict[str, Any] = {}), as it is shared at function definition time and can lead to surprising behavior. Prefer a required Pydantic model (recommended) or at least body: dict[str, Any] | None = None with body = body or {} inside.
Suggested change
| body: dict[str, Any] = {}, | |
| ): | |
| """Send a context-share or tool-request message between agents.""" | |
| body: dict[str, Any] | None = None, | |
| ): | |
| """Send a context-share or tool-request message between agents.""" | |
| body = body or {} |
Comment on lines
+200
to
+212
| # A2A context sharing: broadcast each agent's output to all others | ||
| if orchestration_result.success and len(orchestration_result.results) > 1: | ||
| conv_id = str(uuid.uuid4()) | ||
| for sender_name, sender_result in orchestration_result.results.items(): | ||
| for recipient_name in orchestration_result.results: | ||
| if recipient_name != sender_name: | ||
| msg = A2AContextMessage( | ||
| sender=sender_name, | ||
| recipient=recipient_name, | ||
| content={"type": "context_share", "output": sender_result.output}, | ||
| conversation_id=conv_id, | ||
| ) | ||
| self._a2a_log.append(msg) |
There was a problem hiding this comment.
The “A2A context sharing” block only appends messages to _a2a_log; it doesn’t actually deliver them to recipient agents. Since none of the agents (and not even BaseAgent) define receive_context, this code currently cannot share context as described. Consider either (1) calling send_a2a_message(...) for each sender/recipient pair (and defining a receive_context contract on BaseAgent), or (2) renaming/commenting this as logging-only if that’s the intent.
Comment on lines
60
to
+63
| self.logger = logging.getLogger("agent_orchestrator") | ||
| self._agents: dict[str, BaseAgent] = {} | ||
| self._agent_types: dict[str, type[BaseAgent]] = {} | ||
| self._a2a_log: list[A2AContextMessage] = [] |
There was a problem hiding this comment.
_a2a_log is an in-memory list with no retention policy, and the broadcast path stores each agent’s full output for every sender/recipient pair. With a long-lived orchestrator singleton this can grow unbounded and retain large payloads (transcripts, etc.). Consider capping the log (e.g., deque with maxlen), truncating/storing summaries, or making logging opt-in via config.
Comment on lines
+1224
to
+1268
| @router.post( | ||
| "/agents/a2a/send", | ||
| response_model=ApiResponse, | ||
| summary="Send an A2A message between agents", | ||
| tags=["Agents"], | ||
| ) | ||
| async def send_a2a_message( | ||
| body: dict[str, Any] = {}, | ||
| ): | ||
| """Send a context-share or tool-request message between agents.""" | ||
| sender = body.get("sender", "frontend") | ||
| recipient = body.get("recipient") | ||
| content = body.get("content", {}) | ||
| conversation_id = body.get("conversation_id") | ||
|
|
||
| if not recipient: | ||
| raise HTTPException(status_code=400, detail="recipient is required") | ||
|
|
||
| orch = AgentOrchestrator() | ||
| msg = await orch.send_a2a_message( | ||
| sender=sender, | ||
| recipient=recipient, | ||
| content=content, | ||
| conversation_id=conversation_id, | ||
| ) | ||
| return ApiResponse.success({ | ||
| "conversation_id": msg.conversation_id, | ||
| "timestamp": msg.timestamp, | ||
| }) | ||
|
|
||
|
|
||
| @router.get( | ||
| "/agents/a2a/log", | ||
| response_model=ApiResponse, | ||
| summary="Get A2A message log", | ||
| tags=["Agents"], | ||
| ) | ||
| async def get_a2a_log( | ||
| conversation_id: Optional[str] = None, | ||
| limit: int = 50, | ||
| ): | ||
| """Return recent A2A inter-agent messages.""" | ||
| orch = AgentOrchestrator() | ||
| log = orch.get_a2a_log(conversation_id=conversation_id, limit=limit) | ||
| return ApiResponse.success({"messages": log, "count": len(log)}) |
There was a problem hiding this comment.
New A2A endpoints and orchestrator behavior are introduced here, but there are no accompanying tests. There are already unit tests covering API v1 models and orchestrator behavior in tests/; adding tests for /api/v1/agents/a2a/send, /api/v1/agents/a2a/log, and the expected context-sharing/logging semantics would help prevent regressions and keep coverage in line with repo expectations.
![sentry[bot]](https://avatars.githubusercontent.com/in/12637?s=60&v=4){kind=small}
| self.logger = logging.getLogger("agent_orchestrator") | ||
| self._agents: dict[str, BaseAgent] = {} | ||
| self._agent_types: dict[str, type[BaseAgent]] = {} | ||
| self._a2a_log: list[A2AContextMessage] = [] |
There was a problem hiding this comment.
Bug: The _a2a_log list in the singleton AgentOrchestrator is appended to without any cleanup mechanism, causing it to grow indefinitely and risk a memory leak.
Severity: HIGH
Suggested Fix
Implement a retention policy for the _a2a_log. A simple approach is to cap its size using a collections.deque with a maxlen or by manually trimming the list after each append to ensure it does not exceed a predefined limit.
Prompt for AI Agent
Review the code at the location below. A potential bug has been identified by an AI
agent.
Verify if this is a real issue. If it is, propose a fix; if not, explain why it's not
valid.
Location: src/youtube_extension/services/agents/adapters/agent_orchestrator.py#L63
Potential issue: The `_a2a_log` list within the `AgentOrchestrator` class accumulates
`A2AContextMessage` objects from agent-to-agent communications. Because the
`AgentOrchestrator` is instantiated as a long-lived singleton, this log grows
indefinitely without any clearing or trimming mechanism. In a production environment
with continuous operation, this unbounded growth will lead to excessive memory
consumption, eventually causing the service to crash with an out-of-memory error.
Did we get this right? 👍 / 👎 to inform future reviews.
groupthinking
added a commit
that referenced
this pull request
Mar 4, 2026
…51) * feat: Initialize PGLite v17 database data files for the dataconnect project. * feat: enable automatic outline generation for Gemini Code Assist in VS Code settings. * feat: Add NotebookLM integration with a new processor and `analyze_video_with_notebooklm` MCP tool. * feat: Add NotebookLM profile data and an ingestion test. * chore: Update and add generated browser profile files for notebooklm development. * Update `notebooklm_chrome_profile` internal state and add architectural context documentation and video asset. * feat: Add various knowledge prototypes for MCP servers and universal automation, archive numerous scripts and documentation, and update local browser profile data. * chore: Add generated browser profile cache and data for notebooklm. * Update notebooklm Chrome profile preferences, cache, and session data. * feat: Update NotebookLM Chrome profile with new cache, preferences, and service worker data. * feat: Add generated Chrome profile cache and code cache files and update associated profile data. * Update `notebooklm` Chrome profile cache, code cache, GPU cache, and safe browsing data. * chore(deps): bump the npm_and_yarn group across 4 directories with 5 updates Bumps the npm_and_yarn group with 3 updates in the / directory: [ajv](https://github.com/ajv-validator/ajv), [hono](https://github.com/honojs/hono) and [qs](https://github.com/ljharb/qs). Bumps the npm_and_yarn group with 3 updates in the /docs/knowledge_prototypes/mcp-servers/fetch-mcp directory: [@modelcontextprotocol/sdk](https://github.com/modelcontextprotocol/typescript-sdk), [ajv](https://github.com/ajv-validator/ajv) and [hono](https://github.com/honojs/hono). Bumps the npm_and_yarn group with 1 update in the /scripts/archive/software-on-demand directory: [ajv](https://github.com/ajv-validator/ajv). Bumps the npm_and_yarn group with 2 updates in the /scripts/archive/supabase_cleanup directory: [next](https://github.com/vercel/next.js) and [qs](https://github.com/ljharb/qs). Updates `ajv` from 8.17.1 to 8.18.0 - [Release notes](https://github.com/ajv-validator/ajv/releases) - [Commits](ajv-validator/ajv@v8.17.1...v8.18.0) Updates `hono` from 4.11.7 to 4.12.1 - [Release notes](https://github.com/honojs/hono/releases) - [Commits](honojs/hono@v4.11.7...v4.12.1) Updates `qs` from 6.14.1 to 6.15.0 - [Changelog](https://github.com/ljharb/qs/blob/main/CHANGELOG.md) - [Commits](ljharb/qs@v6.14.1...v6.15.0) Updates `@modelcontextprotocol/sdk` from 1.25.2 to 1.26.0 - [Release notes](https://github.com/modelcontextprotocol/typescript-sdk/releases) - [Commits](modelcontextprotocol/typescript-sdk@v1.25.2...v1.26.0) Updates `ajv` from 8.17.1 to 8.18.0 - [Release notes](https://github.com/ajv-validator/ajv/releases) - [Commits](ajv-validator/ajv@v8.17.1...v8.18.0) Updates `hono` from 4.11.5 to 4.12.1 - [Release notes](https://github.com/honojs/hono/releases) - [Commits](honojs/hono@v4.11.7...v4.12.1) Updates `qs` from 6.14.1 to 6.15.0 - [Changelog](https://github.com/ljharb/qs/blob/main/CHANGELOG.md) - [Commits](ljharb/qs@v6.14.1...v6.15.0) Updates `ajv` from 8.17.1 to 8.18.0 - [Release notes](https://github.com/ajv-validator/ajv/releases) - [Commits](ajv-validator/ajv@v8.17.1...v8.18.0) Updates `next` from 15.4.10 to 15.5.10 - [Release notes](https://github.com/vercel/next.js/releases) - [Changelog](https://github.com/vercel/next.js/blob/canary/release.js) - [Commits](vercel/next.js@v15.4.10...v15.5.10) Updates `qs` from 6.14.1 to 6.15.0 - [Changelog](https://github.com/ljharb/qs/blob/main/CHANGELOG.md) - [Commits](ljharb/qs@v6.14.1...v6.15.0) --- updated-dependencies: - dependency-name: ajv dependency-version: 8.18.0 dependency-type: indirect dependency-group: npm_and_yarn - dependency-name: hono dependency-version: 4.12.1 dependency-type: indirect dependency-group: npm_and_yarn - dependency-name: qs dependency-version: 6.15.0 dependency-type: indirect dependency-group: npm_and_yarn - dependency-name: "@modelcontextprotocol/sdk" dependency-version: 1.26.0 dependency-type: direct:production dependency-group: npm_and_yarn - dependency-name: ajv dependency-version: 8.18.0 dependency-type: indirect dependency-group: npm_and_yarn - dependency-name: hono dependency-version: 4.12.1 dependency-type: indirect dependency-group: npm_and_yarn - dependency-name: qs dependency-version: 6.15.0 dependency-type: indirect dependency-group: npm_and_yarn - dependency-name: ajv dependency-version: 8.18.0 dependency-type: direct:production dependency-group: npm_and_yarn - dependency-name: next dependency-version: 15.5.10 dependency-type: direct:production dependency-group: npm_and_yarn - dependency-name: qs dependency-version: 6.15.0 dependency-type: indirect dependency-group: npm_and_yarn ... Signed-off-by: dependabot[bot] <support@github.com> * chore(deps): bump minimatch Bumps the npm_and_yarn group with 1 update in the /scripts/archive/supabase_cleanup directory: [minimatch](https://github.com/isaacs/minimatch). Updates `minimatch` from 3.1.2 to 3.1.4 - [Changelog](https://github.com/isaacs/minimatch/blob/main/changelog.md) - [Commits](isaacs/minimatch@v3.1.2...v3.1.4) --- updated-dependencies: - dependency-name: minimatch dependency-version: 3.1.4 dependency-type: indirect dependency-group: npm_and_yarn ... Signed-off-by: dependabot[bot] <support@github.com> * chore(deps): bump the npm_and_yarn group across 2 directories with 1 update Bumps the npm_and_yarn group with 1 update in the / directory: [hono](https://github.com/honojs/hono). Bumps the npm_and_yarn group with 1 update in the /docs/knowledge_prototypes/mcp-servers/fetch-mcp directory: [hono](https://github.com/honojs/hono). Updates `hono` from 4.12.1 to 4.12.2 - [Release notes](https://github.com/honojs/hono/releases) - [Commits](honojs/hono@v4.12.1...v4.12.2) Updates `hono` from 4.12.1 to 4.12.2 - [Release notes](https://github.com/honojs/hono/releases) - [Commits](honojs/hono@v4.12.1...v4.12.2) --- updated-dependencies: - dependency-name: hono dependency-version: 4.12.2 dependency-type: indirect dependency-group: npm_and_yarn - dependency-name: hono dependency-version: 4.12.2 dependency-type: indirect dependency-group: npm_and_yarn ... Signed-off-by: dependabot[bot] <support@github.com> * feat: enable frontend-only video ingestion pipeline for Vercel deployment The core pipeline previously required the Python backend to be running. When deployed to Vercel (https://v0-uvai.vercel.app/), the backend is unavailable, causing all video analysis to fail immediately. Changes: - /api/video: Falls back to frontend-only pipeline (transcribe + extract) when the Python backend is unreachable, with 15s timeout - /api/transcribe: Adds Gemini fallback when OpenAI is unavailable, plus 8s timeout on backend probe to avoid hanging on Vercel - layout.tsx: Loads Google Fonts via <link> instead of next/font/google to avoid build failures in offline/sandboxed CI environments - page.tsx: Replace example URLs with technical content (3Blue1Brown neural networks, Karpathy LLM intro) instead of rick roll / zoo videos - gemini_service.py: Gate Vertex AI import behind GOOGLE_CLOUD_PROJECT env var to prevent 30s+ hangs on the GCE metadata probe - agent_gap_analyzer.py: Fix f-string backslash syntax errors (Python 3.11) https://claude.ai/code/session_015Pd3a6hinTenCNrPRGiZqE * Potential fix for code scanning alert no. 4518: Server-side request forgery Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com> * Initial plan * Potential fix for code scanning alert no. 4517: Server-side request forgery Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com> * Initial plan * Fix review feedback: timeout cleanup, transcript_segments shape, ENABLE_VERTEX_AI boolean parsing Co-authored-by: groupthinking <154503486+groupthinking@users.noreply.github.com> * fix: clearTimeout in finally blocks, transcript_segments shape, ENABLE_VERTEX_AI boolean parsing Co-authored-by: groupthinking <154503486+groupthinking@users.noreply.github.com> * Update src/youtube_extension/services/ai/gemini_service.py Co-authored-by: vercel[bot] <35613825+vercel[bot]@users.noreply.github.com> * Update apps/web/src/app/api/video/route.ts Co-authored-by: vercel[bot] <35613825+vercel[bot]@users.noreply.github.com> * Update apps/web/src/app/api/video/route.ts Co-authored-by: vercel[bot] <35613825+vercel[bot]@users.noreply.github.com> * Initial plan * Initial plan * Fix: move clearTimeout into .finally() to prevent timer leaks on fetch abort/error Co-authored-by: groupthinking <154503486+groupthinking@users.noreply.github.com> * Fix clearTimeout not called in finally blocks for AbortController timeouts Co-authored-by: groupthinking <154503486+groupthinking@users.noreply.github.com> * Fix: Relative URLs in server-side fetch calls fail in production - fetch('/api/transcribe') and fetch('/api/extract-events') use relative URLs which don't resolve correctly in server-side Next.js code on production deployments like Vercel. This commit fixes the issue reported at apps/web/src/app/api/video/route.ts:101 ## Bug Analysis **Why it happens:** In Next.js API routes running on the server (Node.js runtime), the `fetch()` API requires absolute URLs. Unlike browsers which have an implicit base URL (the current origin), server-side code has no context for resolving relative URLs like `/api/transcribe`. The Node.js fetch implementation will fail to resolve these relative paths, resulting in TypeError or connection errors. **When it manifests:** - **Development (localhost:3000)**: Works accidentally because the request URL contains the host - **Production (Vercel)**: Fails because the relative URL cannot be resolved to a valid absolute URL without proper host context **What impact it has:** The frontend-only pipeline fallback (Strategy 2) in lines 101-132 is completely broken in production. When the backend is unavailable (common on Vercel), the code attempts to use `/api/transcribe` and `/api/extract-events` serverless functions but fails due to unresolvable relative URLs. This causes the entire video analysis endpoint to fail when the backend is unavailable. ## Fix Explanation **Changes made:** 1. Added a `getBaseUrl(request: Request)` helper function that extracts the absolute base URL from the incoming request object using `new URL(request.url)` 2. Updated line 108: `fetch('/api/transcribe', ...)` → `fetch(`${baseUrl}/api/transcribe`, ...)` 3. Updated line 127: `fetch('/api/extract-events', ...)` → `fetch(`${baseUrl}/api/extract-events`, ...)` **Why it solves the issue:** - The incoming `request` object contains the full URL including protocol and host - By constructing an absolute URL from the request, we ensure the fetch calls work in both development and production - This approach is more reliable than environment variables because it uses the actual request context, handling reverse proxies and different deployment configurations correctly Co-authored-by: Vercel <vercel[bot]@users.noreply.github.com> Co-authored-by: groupthinking <garveyht@gmail.com> * Initial plan * chore(deps): bump the npm_and_yarn group across 1 directory with 1 update Bumps the npm_and_yarn group with 1 update in the /docs/knowledge_prototypes/mcp-servers/fetch-mcp directory: [minimatch](https://github.com/isaacs/minimatch). Updates `minimatch` from 3.1.2 to 3.1.5 - [Changelog](https://github.com/isaacs/minimatch/blob/main/changelog.md) - [Commits](isaacs/minimatch@v3.1.2...v3.1.5) Updates `minimatch` from 5.1.6 to 5.1.9 - [Changelog](https://github.com/isaacs/minimatch/blob/main/changelog.md) - [Commits](isaacs/minimatch@v3.1.2...v3.1.5) --- updated-dependencies: - dependency-name: minimatch dependency-version: 3.1.5 dependency-type: indirect dependency-group: npm_and_yarn - dependency-name: minimatch dependency-version: 5.1.9 dependency-type: indirect dependency-group: npm_and_yarn ... Signed-off-by: dependabot[bot] <support@github.com> * fix: validate BACKEND_URL before using it Skip backend calls entirely when BACKEND_URL is not configured or contains an invalid value (like a literal ${...} template string). This prevents URL parse errors on Vercel where the env var may not be set. https://claude.ai/code/session_015Pd3a6hinTenCNrPRGiZqE * fix: resolve embeddings package build errors (#41) - Create stub types for Firebase Data Connect SDK in src/dataconnect-generated/ - Fix import path from ../dataconnect-generated to ./dataconnect-generated (rootDir constraint) - Add explicit type assertions for JSON responses (predictions, access_token) - All 6 TypeScript errors resolved, clean build verified Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * feat: Gemini SDK upgrade + VideoPack schema alignment (#43) * chore: Update generated Chrome profile cache and session data for notebooklm. * chore: refresh notebooklm Chrome profile data, including Safe Browsing lists, caches, and session files. * Update local application cache and database files within the NotebookLM Chrome profile. * chore: update Chrome profile cache and Safe Browsing data files. * feat: upgrade Gemini to @google/genai SDK with structured output, search grounding, video URL processing, and extend VideoPack schema - Upgrade extract-events/route.ts from @google/generative-ai to @google/genai - Add Gemini responseSchema with Type system for structured output enforcement - Add Google Search grounding (googleSearch tool) to Gemini calls - Upgrade transcribe/route.ts to @google/genai with direct YouTube URL processing via fileData - Add Gemini video URL fallback chain: direct video → text+search → other strategies - Extend VideoPackV0 schema with Chapter, CodeCue, Task models - Update versioning shim for new fields - Export new types from videopack __init__ Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * feat: wire CloudEvents pipeline + Chrome Built-in AI fallback (#44) - Add TypeScript CloudEvents publisher (apps/web/src/lib/cloudevents.ts) emitting standardized events at each video processing stage - Wire CloudEvents into /api/video route (both backend + frontend strategies) - Wire CloudEvents into FastAPI backend router (process_video_v1 endpoint) - Add Chrome Built-in AI service (Prompt API + Summarizer API) for on-device client-side transcript analysis when API keys are unavailable - Add useBuiltInAI React hook for component integration - Add .next/ to .gitignore Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * feat: wire A2A inter-agent messaging into orchestrator + API (#45) - Add A2AContextMessage dataclass to AgentOrchestrator for lightweight inter-agent context sharing during parallel task execution - Auto-broadcast agent results to peer agents after parallel execution - Add send_a2a_message() and get_a2a_log() methods to orchestrator - Add POST /api/v1/agents/a2a/send endpoint for frontend-to-agent messaging - Add GET /api/v1/agents/a2a/log endpoint to query message history - Extend frontend agentService with sendA2AMessage() and getA2ALog() Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * feat: add LiteRT-LM setup script and update README (#46) - Add setup.sh to download lit CLI binary and .litertlm model - Support macOS arm64 and x86_64 architectures - Auto-generate .env with LIT_BINARY_PATH and LIT_MODEL_PATH - Add .gitignore for bin/, models/, .env - Update README with Quick Setup section Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * feat: implement Gemini agentic video analysis with Google Search grounding (#47) - Create gemini-video-analyzer.ts: single Gemini call with googleSearch tool for transcript extraction AND event analysis (PK=998 pattern) - Add youtube-metadata.ts: scrapes title, description, chapters from YouTube without API key - Update /api/video: Gemini agentic analysis as primary strategy, transcribe→extract chain as fallback - Fix /api/transcribe: remove broken fileData.fileUri, use Gemini Google Search grounding as primary, add metadata context, filter garbage OpenAI results - Fix /api/extract-events: accept videoUrl without requiring transcript, direct Gemini analysis via Google Search when no transcript available Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * fix: support Vertex_AI_API_KEY as Gemini key fallback Create shared gemini-client.ts that resolves API key from: GEMINI_API_KEY → GOOGLE_API_KEY → Vertex_AI_API_KEY All API routes now use the shared client instead of hardcoding process.env.GEMINI_API_KEY. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * fix: use Vertex AI Express Mode for Vertex_AI_API_KEY When only Vertex_AI_API_KEY is set (no GEMINI_API_KEY), the client now initializes in Vertex AI mode with vertexai: true + apiKey. Uses project uvai-730bb and us-central1 as defaults. Also added GOOGLE_CLOUD_PROJECT env var to Vercel. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * fix: Vertex AI Express Mode compatibility — remove responseSchema+googleSearch conflict (#48) Vertex AI does not support controlled generation (responseSchema) combined with the googleSearch tool. This caused 400 errors on every Gemini call. Changes: - gemini-client.ts: Prioritize Vertex_AI_API_KEY, support GOOGLE_GENAI_USE_VERTEXAI env var - gemini-video-analyzer.ts: Remove responseSchema, enforce JSON via prompt instructions - extract-events/route.ts: Same fix for extractWithGemini and inline Gemini calls - Strip markdown code fences from responses before JSON parsing Tested end-to-end with Vertex AI Express Mode key against multiple YouTube videos. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * fix: restore full PK=998 pattern — responseSchema + googleSearch + gemini-3-pro-preview (#49) The previous fix (PR #48) was a shortcut — it removed responseSchema when the real issue was using gemini-2.5-flash which doesn't support responseSchema + googleSearch together on Vertex AI. gemini-3-pro-preview DOES support the combination. This commit restores the exact PK=998 pattern: - gemini-video-analyzer.ts: Restored responseSchema with Type system, responseMimeType, e22Snippets field, model → gemini-3-pro-preview - extract-events/route.ts: Restored geminiResponseSchema, Type import, responseMimeType, model → gemini-3-pro-preview - transcribe/route.ts: model → gemini-3-pro-preview Tested with Vertex AI Express Mode key on two YouTube videos. Both return structured JSON with events, transcript, actions, codeMapping, cloudService, e22Snippets, architectureCode, ingestScript. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * feat: end-to-end pipeline — YouTube URL to deployed software (#50) - Add /api/pipeline route for full end-to-end pipeline (video analysis → code generation → GitHub repo → Vercel deploy) - Add deployPipeline() action to dashboard store with stage tracking - Add 🚀 Deploy button to dashboard alongside Analyze - Show pipeline results (live URL, GitHub repo, framework) in video cards - Fix deployment_manager import path in video_processing_service - Wire pipeline to backend /api/v1/video-to-software endpoint - Fallback to Gemini-only analysis when no backend available Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * fix: add writable directories to Docker image for deployment pipeline Create /app/generated_projects, /app/youtube_processed_videos, and /tmp/uvai_data directories in Dockerfile to fix permission denied errors in the deployment and video processing pipeline on Railway. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * fix: security hardening, video-specific codegen, API consistency - CORS: replace wildcard/glob with explicit allowed origins in both entry points - Rate limiting: enable 60 req/min with 15 burst on backend - API auth: add optional X-API-Key middleware for pipeline endpoints - Codegen: generate video-specific HTML/CSS/JS from analysis output - API: accept both 'url' and 'video_url' via Pydantic alias - Deploy: fix Vercel REST API payload format (gitSource instead of gitRepository) Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * fix: Vercel deployment returning empty live_url Root causes fixed: - Case mismatch in _poll_deployment_status: compared lowercased status against uppercase success_statuses list, so READY was never matched - Vercel API returns bare domain URLs without https:// prefix; added _ensure_https() to normalize them - Poll requests were missing auth headers, causing 401 failures - _deploy_files_directly fallback returned fake simulated URLs that masked real failures; removed in favor of proper error reporting - _generate_deployment_urls only returned URLs from 'success' status deployments, discarding useful fallback URLs from failed deployments Improvements: - On API failure (permissions, plan limits), return a Vercel import URL the user can click to deploy manually instead of an empty string - Support VERCEL_ORG_ID team scoping on deploy and poll endpoints - Use readyState field (Vercel v13 API) for initial status check - Add 'canceled' to failure status list in poll loop - Poll failures are now non-fatal; initial URL is used as fallback Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * fix: harden slim entry point — CORS, rate limiting, auth, security headers - Add uvaiio.vercel.app to CORS allowed origins - Add slowapi rate limiting (60 req/min) - Add API key auth middleware (optional via EVENTRELAY_API_KEY) - Add security headers (X-Content-Type-Options, X-Frame-Options, X-XSS-Protection) - Fixes production gap where slim main.py had none of the backend/main.py protections Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * fix: resolve Pydantic Config/model_config conflict breaking Railway deploy The VideoToSoftwareRequest model had both 'model_config = ConfigDict(...)' and 'class Config:' which Pydantic v2 rejects. Merged into single model_config. This was causing the v1 router to fail loading, making /api/v1/health return 404. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com> Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: vercel[bot] <35613825+vercel[bot]@users.noreply.github.com> Co-authored-by: Vercel <vercel[bot]@users.noreply.github.com> Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Connect A2A framework to agent orchestrator. Adds inter-agent context sharing after parallel execution, A2A send/log API endpoints, and frontend service methods.