thienpvandCursor 288940960a fix(translator): clamp thinking effort max->xhigh for OpenAI format (#2466) ...

Claude Code sends reasoning_effort "max" (its top level); OpenAI enum caps
at "xhigh" and rejects "max" with HTTP 400 "max effort not support".
applyFormat case "openai" now clamps "max"->"xhigh" before assigning
body.reasoning_effort; other levels pass through unchanged.

Add regression test covering client output_config.effort, direct
reasoning_effort, passthrough of xhigh/high, and budget_tokens capping.

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

2026-07-09 15:13:24 +07:00

..

concerns

fix(translator): clamp thinking effort max->xhigh for OpenAI format (#2466)

2026-07-09 15:13:24 +07:00

formats

fix(claude): reconcile max_tokens vs thinking budget and lift per-model ceiling (#2381)

2026-07-05 17:38:16 +07:00

request

fix(antigravity): align provider fingerprint with IDE Desktop 2.1.1 (#2389)

2026-07-08 10:17:47 +07:00

response

feat(usage): track cached tokens + correct input/output/cache cost (#2209)

2026-07-03 15:18:27 +07:00

schema

Refactor

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

formats.js

feat: add CommandCode provider support

2026-05-07 23:01:33 +07:00

index.js

fix(alicode): preserve cache_control for DashScope providers (#2069)

2026-06-29 15:29:49 +07:00