kwanLeeFrmVi 054facb08b fix(gemini): preserve thoughtSignature via tool_call ID smuggling + fix ELOCKED mutex ...

- Encode thoughtSignature into tool_call.id using _TSIG_ delimiter and base64url
- Decode _TSIG_ on request to restore thoughtSignature for Gemini multi-turn thinking
- Track pendingThoughtSignature across parts for deferred signature attachment
- Add LocalMutex (2-layer locking) to prevent ELOCKED on concurrent DB access
- Increase lockfile retries from 5 to 15 for multi-process robustness
- Restore db.json seed on first run to prevent ENOENT on lockfile.lock
- Use process.env.BASE_URL fallback in models test route
- Remove gemini-3-flash-lite-preview from provider models

Co-authored-by: kwanLeeFrmVi <quanle96@outlook.com>
Closes #450

Made-with: Cursor

2026-03-30 16:57:28 +07:00

..

claude-to-openai.js

refactor(claude-to-openai): simplify usage token calculation and final chunk assembly

2026-03-09 17:18:49 +07:00

cursor-to-openai.js

feat(cursor): Add cursor Provider

2026-02-05 11:06:20 +07:00

gemini-to-openai.js

fix(gemini): preserve thoughtSignature via tool_call ID smuggling + fix ELOCKED mutex

2026-03-30 16:57:28 +07:00

kiro-to-openai.js

feat: Update response handling and logging for improved usage tracking

2026-02-03 10:22:43 +07:00

ollama-to-openai.js

feat(ollama): Enhance Ollama support by adding new models, updating API format handling, and integrating translation functionality.

2026-03-12 15:24:10 +07:00

openai-responses.js

fix: correct finish_reason for tool calls in OpenAI Responses translator

2026-03-28 14:45:07 +07:00

openai-to-antigravity.js

Fix Bug

2026-03-30 12:21:24 +07:00

openai-to-claude.js

feat: Update response handling and logging for improved usage tracking

2026-02-03 10:22:43 +07:00