Skip to content

fix(ai): normalize OpenAI stream edge cases and add inline think parsing control#245

Merged
GCWing merged 2 commits intoGCWing:mainfrom
wsp1911:main
Mar 24, 2026
Merged

fix(ai): normalize OpenAI stream edge cases and add inline think parsing control#245
GCWing merged 2 commits intoGCWing:mainfrom
wsp1911:main

Conversation

@wsp1911
Copy link
Copy Markdown
Collaborator

@wsp1911 wsp1911 commented Mar 24, 2026

  • filter redundant trailing OpenAI tool-call chunks that repeat an existing tool id without new data
  • parse OpenAI-compatible ... text chunks into streaming reasoning content at the handler layer
  • add a model-level advanced setting to explicitly enable inline think parsing, defaulting to disabled
  • wire the new setting through backend config, AI client, frontend model configuration, and onboarding defaults
  • hide the preserved thinking toggle from the advanced settings UI while keeping existing config compatibility
  • add tests covering inline think parsing, disabled passthrough behavior, and OpenAI stream edge cases

wsp1911 added 2 commits March 23, 2026 21:38
…ing control

- filter redundant trailing OpenAI tool-call chunks that repeat an existing tool id without new data
- parse OpenAI-compatible `<think>...</think>` text chunks into streaming reasoning content at the handler layer
- add a model-level advanced setting to explicitly enable inline think parsing, defaulting to disabled
- wire the new setting through backend config, AI client, frontend model configuration, and onboarding defaults
- hide the preserved thinking toggle from the advanced settings UI while keeping existing config compatibility
- add tests covering inline think parsing, disabled passthrough behavior, and OpenAI stream edge cases
@GCWing GCWing merged commit 56c4c19 into GCWing:main Mar 24, 2026
4 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants