feat(runtime_context): pass Request to extension point (EVO-1626 followup)

[marcelogorutuba]

Summary

• Adds an optional request argument to run_agent / StandardRunner.run_agent and threads it from the chat/a2a routes down to the runtime_context extension-point call site.
• At the call site, prefer request over metadata so consumers that resolve the tenant from X-Evo-Tenant-Id actually see the header. Falls back to metadata when no request is provided (internal callers, tests).
• Community default is unchanged — the no-op impl ignores its argument either way.

Why

Before this patch, runtime_context.current_context_id(metadata) was called with metadata=None on every chat/a2a request, so the enterprise consumer in evo-enterprise-licensing-python (EVO-1626) had no way to observe X-Evo-Tenant-Id end-to-end.

Validation

• Syntax check on all 4 touched files passes (ast.parse).
• The only EP call site (src/services/adk/runners/standard_runner.py:101) keeps a single-line behavior change behind the existing log line.

Changed Files

• src/services/adk/runners/standard_runner.py
• src/services/adk/agent_runner.py
• src/api/chat_routes.py
• src/api/a2a_routes.py

Linked Issue

• EVO-1626 (followup; functional wiring for the consumer shipped in evolution-foundation/evo-enterprise-licensing-python#1)

Summary by Sourcery

Thread the incoming request object through agent execution so the runtime context extension point can use it when resolving context IDs.

Bug Fixes:

• Allow runtime context resolution to access request headers such as tenant ID by passing the request into the extension point.

Enhancements:

• Extend agent runner and standard runner signatures to accept an optional request parameter and prefer it over metadata when resolving runtime context IDs.

[sourcery-ai]

Reviewer's guide (collapsed on small PRs)

Reviewer's Guide

Threads an optional request object from the chat and A2A API routes through the agent runner into the StandardRunner, and uses it as the primary input to the runtime_context extension point, falling back to metadata when no request is provided.

Sequence diagram for passing request to runtime_context extension point

sequenceDiagram
    actor Client
    participant ChatRoutes as chat_routes
    participant A2aRoutes as a2a_routes
    participant AgentRunner as agent_runner
    participant StandardRunner as StandardRunner
    participant RuntimeContext as runtime_context

    Client->>ChatRoutes: chat(request)
    ChatRoutes->>AgentRunner: run_agent(db, session_id, files, metadata, user_id, request)
    AgentRunner->>StandardRunner: run_agent(db, session_id, files, metadata, user_id, request)
    StandardRunner->>RuntimeContext: current_context_id(request)

    Client->>A2aRoutes: handle_message_send(request)
    A2aRoutes->>AgentRunner: run_agent(db, session_id, files, metadata, user_id, request)
    AgentRunner->>StandardRunner: run_agent(db, session_id, files, metadata, user_id, request)

    alt request is None
        StandardRunner->>RuntimeContext: current_context_id(metadata)
    end

Loading

File-Level Changes

Change	Details	Files
Add optional request parameter to agent execution APIs and thread it through to the StandardRunner.	Extend run_agent function signature to accept an optional request argument. Pass the request argument from the API route handlers into run_agent. Propagate the request argument from run_agent to StandardRunner.run_agent.	src/services/adk/agent_runner.py src/api/a2a_routes.py src/api/chat_routes.py src/services/adk/runners/standard_runner.py
Use request as the preferred input for runtime_context.current_context_id, falling back to metadata.	Update StandardRunner.run_agent to pass request to runtime_context.current_context_id when available. Retain existing behavior for callers that do not supply a request by falling back to metadata.	src/services/adk/runners/standard_runner.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.

[sourcery-ai]

Hey - I've left some high level feedback:

• Consider tightening the type for the new request parameter (e.g., Request or Optional[Request]) instead of Any in run_agent and StandardRunner.run_agent so downstream consumers get better type safety and editor support.
• To reflect that request can be omitted, it may be clearer to type it as Optional[...] = None rather than Any = None in both the function signatures and any related call sites.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- Consider tightening the type for the new `request` parameter (e.g., `Request` or `Optional[Request]`) instead of `Any` in `run_agent` and `StandardRunner.run_agent` so downstream consumers get better type safety and editor support.
- To reflect that `request` can be omitted, it may be clearer to type it as `Optional[...] = None` rather than `Any = None` in both the function signatures and any related call sites.

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}