next-ai-draw-io

mirror of https://github.com/DayuanJiang/next-ai-draw-io.git synced 2026-09-02 01:20:23 +08:00

Files

Octopus c60e3930a3 fix: use createDeepSeek for kimi provider to handle reasoning_content in multi-turn conversations (fixes #824 ) (#825 )

Kimi thinking models (e.g. kimi-k2.6) return reasoning_content in their
responses. The previous createOpenAI-based implementation silently ignored
this field, so reasoning was never captured or replayed in subsequent turns.
Switching to createDeepSeek (which natively understands reasoning_content)
ensures that reasoning context is preserved across conversation turns,
resolving the "cannot interact a second time" error with Kimi k2.6.

This mirrors the existing doubao provider pattern, which already uses
createDeepSeek for kimi-based models routed through Doubao.

Co-authored-by: octo-patch <octo-patch@github.com>

2026-05-15 14:02:26 +09:00

ai-providers.test.ts

fix: use createDeepSeek for kimi provider to handle reasoning_content in multi-turn conversations (fixes #824 ) (#825 )

2026-05-15 14:02:26 +09:00

cached-responses.test.ts

test: add Vitest and Playwright testing infrastructure (#512 )

2026-01-05 01:37:32 +09:00

chat-helpers.test.ts

test: add Vitest and Playwright testing infrastructure (#512 )

2026-01-05 01:37:32 +09:00

diagram-validator.test.ts

Add VLM-based diagram validation (#602 )