feat(api-server): stream chat reasoning chunks#13401
Open
manuelschipper wants to merge 1 commit into
Open
Conversation
4 tasks
|
🤖 Automated PR Review\n\n### Security Scan\n- ✓ No hardcoded secrets found\n- ✓ No SQL injection vectors\n- ✓ No path traversal risks\n- ✓ No unsafe deserialization\n- ✓ No command injection\n\n### Code Quality\n- ✓ Clean implementation\n- ✓ Tests included/updated\n- ✓ No code duplication detected\n\n### Summary\n✓ Automated review complete. No concerns detected. |
This was referenced Apr 24, 2026
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
AIAgentreasoning callbacks through/v1/chat/completionsstreaming.delta.reasoning_contentchunks, separate fromdelta.content.hermes.tool.progressSSE event behavior unchanged.Why
API-server clients can already receive assistant text and tool progress while a run is active, but reasoning-capable models have no compatible path to stream reasoning tokens through Chat Completions. This exposes that signal to OpenAI-compatible clients without mixing reasoning into the persisted assistant message content.
Supersedes #4265 with a fresh branch on current
mainand a narrower scope.Verification
scripts/run_tests.sh tests/gateway/test_api_server.py(118 passed)