Fix missing reasoningEffort telemetry for Claude models#308325
Open
kevin-m-kent wants to merge 1 commit intomicrosoft:mainfrom
Open
Fix missing reasoningEffort telemetry for Claude models#308325kevin-m-kent wants to merge 1 commit intomicrosoft:mainfrom
kevin-m-kent wants to merge 1 commit intomicrosoft:mainfrom
Conversation
Contributor
There was a problem hiding this comment.
Pull request overview
Fixes missing reasoningEffort telemetry for Claude (Messages API) requests by falling back to requestBody.output_config?.effort when requestBody.reasoning?.effort is not present, ensuring consistent telemetry across API paths.
Changes:
- Add
requestBody.reasoning?.effort ?? requestBody.output_config?.effortfallback forresponse.successtelemetry. - Add the same fallback for
response.errortelemetry.
Show a summary per file
| File | Description |
|---|---|
| extensions/copilot/src/extension/prompt/node/chatMLFetcherTelemetry.ts | Ensures reasoningEffort is recorded for both Responses API and Messages API request shapes in success/error telemetry events. |
Copilot's findings
- Files reviewed: 1/1 changed files
- Comments generated: 0
bhavyaus
force-pushed
the
kevin-m-kent/fix-claude-reasoning-effort-telemetry
branch
from
d23eaed to
a27793f
Compare
bhavyaus
force-pushed
the
kevin-m-kent/fix-claude-reasoning-effort-telemetry
branch
from
a27793f to
8a2d8f9
Compare
The reasoningEffort telemetry property on response.success and response.error events was only reading from requestBody.reasoning?.effort (Responses API / OpenAI), missing Claude models which set effort via requestBody.output_config?.effort (Messages API). This adds a fallback to output_config.effort so both events capture the reasoning effort level regardless of which API path is used. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
bhavyaus
force-pushed
the
kevin-m-kent/fix-claude-reasoning-effort-telemetry
branch
from
8a2d8f9 to
02e33fd
Compare
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.
Problem
The
reasoningEfforttelemetry property onresponse.successandresponse.errorevents was only reading fromrequestBody.reasoning?.effort, which is set by the Responses API path (OpenAI models).Claude models use the Messages API path, which sets effort via
requestBody.output_config?.effortinstead. As a result, reasoning effort was silently missing from telemetry for all Claude model requests.Fix
Added a fallback:
requestBody.reasoning?.effort ?? requestBody.output_config?.efforton bothresponse.successandresponse.errortelemetry events so the effort level is captured regardless of which API path is used.Impact
response.success— now logsreasoningEffortfor Claude modelsresponse.error— now logsreasoningEffortfor Claude modelsreasoning.effortpath is checked first)Note: Identical fix also raised for vscode-copilot-chat in microsoft/vscode-copilot-chat#5041