Diego Rodrigues de Sa e Souza 50da54484e fix: downgrade adaptive thinking and gate context-1m beta on model eligibility (#10119) (#10481) ...

* fix(sse): downgrade adaptive thinking and gate context-1m beta on model eligibility (#10119)

* fix(sse): thread resolved model into DefaultExecutor's anthropic-beta merge (#10119)

DefaultExecutor.buildHeaders() merged the client-negotiated anthropic-beta
header without ever passing the resolved target model into
mergeClientAnthropicBeta(), so the context-1m-2025-08-07 eligibility gate
added earlier in this PR could not see which model a combo/fallback had
actually routed to at this call site. buildHeaders() now accepts an
optional model parameter (mirroring BaseExecutor.buildHeaders' existing
signature and the pattern already used by grok-cli.ts/qoder.ts) and
forwards it through, so an ineligible model target (e.g. Haiku) has the
beta dropped instead of forwarded blind.

Restores a CHANGELOG bullet (PR #10366) that a prior merge auto-resolve
had dropped from this branch.

---------

Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com>

2026-08-18 10:50:49 -03:00

..

openai-responses

fix(kiro): preserve GPT-5.6 Max reasoning via Responses (#9163)

2026-08-05 21:44:02 -03:00

openai-to-claude

fix(translator): resolve the Claude thinking output cap with the routed provider (#10139) (#10238)

2026-08-13 07:53:52 -03:00

openai-to-gemini

fix(translator): restore original tool name casing in Gemini response translators (#9568)

2026-08-06 22:55:50 -03:00

openai-to-kiro

fix(kiro): preserve GPT-5.6 Max reasoning via Responses (#9163)

2026-08-05 21:44:02 -03:00

antigravity-to-openai.ts

feat(mitm): add Antigravity reasoning-effort overrides (#7228)

2026-07-17 10:40:14 -03:00

claude-to-gemini.ts

fix(translator): restore TitleCase tool names on the Claude to Gemini path (#9993)

2026-08-11 09:52:40 -03:00

claude-to-openai.ts

fix(translator): pass output_config.effort=max through verbatim (#9053)

2026-08-04 10:06:18 -03:00

gemini-to-openai.ts

fix(translator): preserve Gemini thought parts as reasoning_content on the OpenAI bridge (#7206)

2026-07-17 10:39:32 -03:00

openai-responses.ts

fix(reasoning): preserve and replay assistant turns (#10045)

2026-08-13 07:52:12 -03:00

openai-to-claude.ts

fix: downgrade adaptive thinking and gate context-1m beta on model eligibility (#10119) (#10481)

2026-08-18 10:50:49 -03:00

openai-to-cursor.ts

feat(cursor): vision (image_url) input + tool-commit/output-constraint enhancements (#3104)

2026-06-03 18:24:41 -03:00

openai-to-gemini.ts

fix(antigravity): ban-safety hardening — bounded onboarding retries, gate thought-signature bypass sentinel (#9939)

2026-08-10 03:39:39 -03:00

openai-to-kiro.ts

fix(kiro): keep interleaved tool results grouped without dropping assistant text (#8903) (#8931)

2026-08-07 20:52:13 -03:00