fjiaandCursor 411a589781 fix(claude-to-openai): handle OpenAI-format responses in non-streaming path ...

Some providers (e.g. xiaomi-tokenplan -claude models) return OpenAI-format
responses even when request was translated to Claude. Early-return now detects
choices[]. Also strip reasoning_content only when content is non-empty so
thinking models keep their only output.

Closes #1836

Co-authored-by: Cursor <cursoragent@cursor.com>

2026-06-17 09:43:58 +07:00

..

chatCore

fix(claude-to-openai): handle OpenAI-format responses in non-streaming path

2026-06-17 09:43:58 +07:00

embeddingProviders

refactor(open-sse): B1 consolidate media endpoint URLs into registry

2026-06-14 13:58:12 +07:00

fetch

Enhance token refresh functionality across multiple executors

2026-04-28 17:28:57 +07:00

imageProviders

refactor(open-sse): B1 consolidate media endpoint URLs into registry

2026-06-14 13:58:12 +07:00

search

refactor(open-sse): B1 consolidate media endpoint URLs into registry

2026-06-14 13:58:12 +07:00

ttsProviders

refactor(registry): B2 migrate to LiteLLM-style schema — unified models[] with kind field

2026-06-14 14:32:59 +07:00

chatCore.js

Refactor

2026-06-15 18:18:04 +07:00

embeddingsCore.js

Feat : Skills

2026-05-04 11:29:02 +07:00

imageGenerationCore.js

Add Cloudflare Workers AI image generation (#973)

2026-05-09 09:53:39 +07:00

responsesHandler.js

refactor(open-sse): translator DRY + schema enums, bug fixes, dead code cleanup

2026-06-14 18:49:38 +07:00

sttCore.js

refactor(open-sse): remove reverse coupling open-sse -> src (E2)

2026-06-13 16:35:07 +07:00

ttsCore.js

feat: add STT support, Gemini TTS, and expand usage tracking

2026-05-05 10:32:59 +07:00