feat(openrouter): extract reasoning tokens and reasoning_details from responses.#954
Open
pocketarc wants to merge 1 commit intoprism-php:mainfrom
Open
feat(openrouter): extract reasoning tokens and reasoning_details from responses.#954pocketarc wants to merge 1 commit intoprism-php:mainfrom
pocketarc wants to merge 1 commit intoprism-php:mainfrom
Conversation
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
At the moment, the OpenRouter provider discards reasoning content from non-streaming responses. Streaming handles plaintext reasoning deltas, but
reasoning,reasoning_details, andthoughtTokenswere all lost in non-streaming mode. Structured reasoning metadata (reasoning_details) was ignored everywhere.I've added an
ExtractsReasoningtrait for non-streaming extraction, anOpenRouterStreamStateto trackreasoning_detailsduring streaming, updatedMessageMapto preserve reasoning across tool-calling turns, updated the documentation, and included tests.I also verified with real API calls against Claude, GPT-5, Gemini, and DeepSeek R1.