decolua 11e6004fcb fix: correct finish_reason for tool calls in OpenAI Responses translator ...

Apply fix from PR #354 by @tannk4w to properly signal tool_calls finish_reason
when model emits tool calls, allowing OpenAI-compatible clients to continue with
tool result processing instead of stopping prematurely.

Refactored finish_reason logic into computeFinishReason() helper to eliminate
duplication and improve maintainability across flush and completion paths.

Co-authored-by: tannk4w <tannk@tmi-soft.vn>

Thanks to @tannk4w, @trungtq2799, @quanhavn, and @East-rayyy for the thorough
review and improvement suggestions on the original PR.

Made-with: Cursor

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

..

helpers

fix: inject placeholder message when Responses API input[] is empty (closes #389) (#419)

2026-03-27 10:51:02 +07:00

request

fix: map OpenAI image_url data URLs to Ollama images[] (closes #427) (#432)

2026-03-27 10:48:18 +07:00

response

fix: correct finish_reason for tool calls in OpenAI Responses translator

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

formats.js

fix: strip functionCall/functionResponse id and synthetic thoughtSignature for Vertex AI (closes #388) (#414)

2026-03-27 10:46:47 +07:00

index.js

fix: strip functionCall/functionResponse id and synthetic thoughtSignature for Vertex AI (closes #388) (#414)

2026-03-27 10:46:47 +07:00