This repository was archived by the owner on May 20, 2026. It is now read-only.
Fix missing reasoningEffort telemetry for Claude models#5041
Closed
kevin-m-kent wants to merge 1 commit into
Closed
Fix missing reasoningEffort telemetry for Claude models#5041kevin-m-kent wants to merge 1 commit into
kevin-m-kent wants to merge 1 commit into
Conversation
The reasoningEffort telemetry property 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 response.success and response.error events capture the reasoning effort level regardless of which API path is used. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Contributor
There was a problem hiding this comment.
Pull request overview
Adds missing telemetry capture for reasoning effort when using Claude/Anthropic models via the Messages API, aligning telemetry across OpenAI Responses API and Anthropic Messages API request shapes.
Changes:
- Update
response.successtelemetry to fall back torequestBody.output_config?.effortwhenrequestBody.reasoning?.effortis absent. - Update
response.errortelemetry with the same fallback so failures also record reasoning effort.
Show a summary per file
| File | Description |
|---|---|
| src/extension/prompt/node/chatMLFetcherTelemetry.ts | Adds output_config.effort fallback so reasoningEffort telemetry is recorded for Claude/Messages API requests. |
Copilot's findings
- Files reviewed: 1/1 changed files
- Comments generated: 0
Contributor
Author
|
Closing in favor of the vscode repo version: microsoft/vscode#308325 |
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 subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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)