feat: implement step tracking and event streaming

[codegen-sh]

This PR implements step tracking and event streaming for the Codegen API server. Key features:

1. Step Tracking

   • Extracts step information from task.result and task.summary
   • Tracks step numbers and progress
   • Only sends updates when steps change

2. Event Streaming

   • Uses Server-Sent Events (SSE) for real-time updates
   • Includes step information in events
   • Adds heartbeat events every 5 seconds
   • Proper event formatting with data: prefix

3. Timeout Handling

   • Extended timeout to 30 minutes
   • Configurable via max_retries
   • Proper cleanup for long-running tasks

4. Comprehensive Testing

   • Unit tests for all endpoints
   • Tests for step tracking
   • Tests for timeout handling
   • Tests for event streaming

5. Documentation

   • Added detailed README
   • API endpoint documentation
   • Event format documentation
   • Environment variable documentation

Example event format:

{
    "status": "in_progress",
    "task_id": "123",
    "timestamp": "2025-06-12T14:58:40Z",
    "current_step": "Analyzing repository structure",
    "step_number": 1
}

The implementation has been tested and validated to work with the Codegen SDK. All tests pass and the code is ready for review.

---

💻 View my work • About Codegen

Summary by Sourcery

Implement a FastAPI-based Codegen API server featuring real-time step tracking and SSE event streaming, extended timeouts, and comprehensive documentation and tests

New Features:

• Provide FastAPI server with /run, /status, and /events endpoints for Codegen tasks
• Stream real-time task progress via Server-Sent Events including step tracking and heartbeat events
• Support configurable long-running task timeouts (default 30 minutes) with proper cleanup on timeout or completion

Build:

• Add requirements.txt with dependencies for the API server and testing

Documentation:

• Revise README to document installation, environment variables, usage, API endpoints, event format, timeouts, and heartbeats

Tests:

• Add unit tests for API endpoints, streaming events, step tracking, timeout handling, and task monitoring

[sourcery-ai]

Reviewer's Guide

Introduces a FastAPI-based backend that runs Codegen agent tasks, streams real-time step-wise progress via SSE with heartbeats, handles extended timeouts and cleanup, and includes corresponding docs and tests.

Sequence diagram for task execution and event streaming

sequenceDiagram
    actor Client
    participant FastAPI Server
    participant Codegen SDK

    Client->>FastAPI Server: POST /run (prompt)
    activate FastAPI Server
    FastAPI Server->>Codegen SDK: agent.run(prompt)
    activate Codegen SDK
    Codegen SDK-->>FastAPI Server: task object
    deactivate Codegen SDK
    Note right of FastAPI Server: Creates AgentCallback, spawns monitor_task()
    FastAPI Server-->>Client: 200 OK (task_id)
    deactivate FastAPI Server

    Client->>FastAPI Server: GET /events/{task_id}
    activate FastAPI Server
    Note right of FastAPI Server: Returns StreamingResponse from callback.get_events()

    loop Background Monitoring & Streaming
        FastAPI Server->>Codegen SDK: task.refresh()
        activate Codegen SDK
        Codegen SDK-->>FastAPI Server: Updated task status
        deactivate Codegen SDK

        alt Step/Status Changed
            FastAPI Server->>FastAPI Server: callback.on_status_change()
            FastAPI Server-->>Client: data: {"status": "in_progress", "current_step": "...", ...}
        else Timeout with no new events
            FastAPI Server-->>Client: : heartbeat
        end
    end

    FastAPI Server->>Codegen SDK: task.refresh()
    activate Codegen SDK
    Codegen SDK-->>FastAPI Server: Task completed
    deactivate Codegen SDK
    FastAPI Server->>FastAPI Server: callback.on_status_change("completed", ...)
    FastAPI Server-->>Client: data: {"status": "completed", ...}
    FastAPI Server-->>Client: data: [DONE]
    deactivate FastAPI Server

Loading

File-Level Changes

Change	Details	Files
Event streaming via Server-Sent Events with heartbeat support	Implemented AgentCallback.get_events to yield formatted SSE messages and periodic heartbeats Configured StreamingResponse on /events endpoint with media type text/event-stream Ensured proper SSE formatting using “data:” prefix and [DONE] sentinel	backend/api.py
Step tracking and progress updates	Extract current_step from task.result or task.summary and increment step_number Track and compare last_step to only send updates on change Augmented on_status_change to include step_info in SSE payloads	backend/api.py
Extended timeout handling and task cleanup	Set max_retries to 900 for a 30-minute timeout with 2-second polling Emit failure event on timeout and mark callback.completed Remove tasks from active_tasks store in monitor_task finally block	backend/api.py
New FastAPI endpoints for task management	Added POST /run to start an agent task and spawn monitor_task Added GET /status for synchronous task status and result retrieval Configured CORS middleware for cross-origin access	backend/api.py
Updated documentation and dependencies	Expanded README with installation, environment variables, usage, event format, timeouts Added requirements.txt pinning FastAPI, uvicorn, pydantic, Codegen SDK, pytest Reorganized badges and sections for clarity	README.md requirements.txt
Added comprehensive unit and integration tests	Created tests for /run, /status, /events endpoints using TestClient and mocks Tested monitor_task logic for completion, timeout, and step tracking Utilized pytest-asyncio for async event streaming scenarios	tests/test_api.py

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[korbit-ai]

By default, I don't review pull requests opened by bots. If you would like me to review this pull request anyway, you can request a review via the /korbit-review command in a comment.

[coderabbitai]

Important

Review skipped

Bot user detected.

To trigger a single review, invoke the @coderabbitai review command.

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

---

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

• Review comments: Directly reply to a review comment made by CodeRabbit. Example:
  • I pushed a fix in commit <commit_id>, please review it.
  • Explain this complex logic.
  • Open a follow-up GitHub issue for this discussion.
• Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
  • @coderabbitai explain this code block.
  • @coderabbitai modularize this function.
• PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
  • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
  • @coderabbitai read src/utils.ts and explain its main purpose.
  • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
  • @coderabbitai help me debug CodeRabbit configuration file.

Support

Need help? Join our Discord community for assistance with any issues or questions.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

• @coderabbitai pause to pause the reviews on a PR.
• @coderabbitai resume to resume the paused reviews.
• @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
• @coderabbitai full review to do a full review from scratch and review all the files again.
• @coderabbitai summary to regenerate the summary of the PR.
• @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
• @coderabbitai resolve resolve all the CodeRabbit review comments.
• @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
• @coderabbitai help to get help.

Other keywords and placeholders

• Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
• Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
• Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

• You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
• Please see the configuration documentation for more information.
• If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

• Visit our Documentation for detailed information on how to use CodeRabbit.
• Join our Discord Community to get help, request features, and share feedback.
• Follow us on X/Twitter for updates and announcements.