3 people 46e6c01a01 fix(claude): reconcile max_tokens vs thinking budget and lift per-model ceiling (#2381) ...

On the translated OpenAI->Claude path, adjustMaxTokens capped max_tokens
before applyThinking set thinking.budget_tokens, so max-effort budget
(128000) could exceed a 64k-clamped max_tokens -> Anthropic 400.
prepareClaudeRequest now reconciles after the budget is known: prefer
raising max_tokens, only shrink budget when it meets/exceeds the ceiling.

Also lift the global 64000 cap: the ceiling is now the model's real
maxOutput, so high-output models (fable/mythos, opus-4.8/sonnet-4.6) get
their full budget. adjustMaxTokens gains an optional ceiling arg (default
unchanged, callers untouched); openai-to-claude passes the model maxOutput.

Native Claude Code passthrough is unaffected.

Co-Authored-By: Claude <noreply@anthropic.com>
Co-authored-by: Cursor <cursoragent@cursor.com>

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

..

claude.js

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

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

gemini.js

fix(antigravity): strip 'deprecated' from tool schemas before Gemini

2026-06-29 15:28:02 +07:00

maxTokens.js

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

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

openai.js

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

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

responsesApi.js

refactor(open-sse): translator DRY + schema enums, bug fixes, dead code cleanup

2026-06-14 18:49:38 +07:00