Fix anthropic thinking#1718
Draft
eformat wants to merge 13 commits intovllm-project:mainfrom
Draft
Conversation
✅ Deploy Preview for vllm-semantic-router ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
Contributor
✅ Supply Chain Security Report — All Clear
Scanned at |
Signed-off-by: Mike Hepburn <eformat@gmail.com>
Signed-off-by: Mike Hepburn <eformat@gmail.com>
eformat
force-pushed
the
fix-anthropic-thinking
branch
from
68938bc to
966e49f
Compare
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
…c routing Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
…election When a client specifies a specific model (not "auto"), the decision engine returns an empty selectedModel. This caused llm_model_requests_total to record model="unknown". Fall back to originalModel for the metric label. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Purpose
Adds anthropic reasoning / thinking token support to golang server.
Test Plan
Testing using claude models in vertex, local hosted models with vllm-sr. Config is here:
https://github.com/eformat/vllm-sr-claude/blob/main/vllm-sr-config.yaml
Test Result
can now correctly see thinking tokens from claude models sonnet, opus.
{"level":"info","ts":"2026-04-05T22:43:31.547","caller":"client.go:180","msg":"Raw Anthropic response (7123 bytes): {\"model\":\"claude-sonnet-4-6\",\"id\":\"msg_vrtx_012AR97qvoL7RoMLcB7PpiJz\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[{\"type\":\"thinking\",\"thinking\":\"The user wants an analysis of recursion - why it can be both elegant and dangerous. Let me provide a thorough, well-structured analysis covering both sides.\",\"signature\":\"EtwC..."}```