Mario Zechner 8df22faedf fix(ai): ensure maxTokens > thinkingBudget for Claude thinking models ...

Claude requires max_tokens > thinking.budget_tokens. When caller specifies
a small maxTokens (e.g. compaction with ~13k tokens) and reasoning is enabled
with high budget (16k tokens), the constraint was violated.

Fix: In mapOptionsForApi, add thinkingBudget on top of caller's maxTokens
(capped at model.maxTokens). If still not enough room, reduce thinkingBudget
to leave space for output.

Applied to both anthropic-messages and google-gemini-cli APIs.

Also adds test utilities for OAuth credential resolution and tests for
compaction with thinking models.

fixes #413

2026-01-03 02:45:30 +01:00

6.5 KiB

Raw Blame History

View Raw