Abhishek Divekar cda583114f fix(command-code): cap max_tokens per model using registry maxOutputTokens (#4518) ...

clampMaxTokens now uses the per-model maxOutputTokens from REGISTRY['command-code'] as the upper bound (falls back to MAX_COMMAND_CODE_TOKENS), so GLM-5.x stops being rejected for max_tokens > 131072. Rebuilt onto release/v3.8.33 (passthrough block from the PR base is already present via #2986); 3 tests added.

Integrated into release/v3.8.33.

2026-06-21 12:33:25 -03:00

14 KiB

Raw Blame History

View Raw