fix: adjust GLM-4.6-turbo max output tokens to prevent context limit errors#8822

Merged

mrubens merged 4 commits intomainfrom

fix/glm-4.6-turbo-max-tokens

Oct 25, 2025

Commits on Oct 25, 2025

fix: adjust GLM-4.6-turbo max output tokens to 40k
roomote
committed
fix: enforce centralized 20% output-token cap for OpenAI-compatible providers (Chutes)\n\nRoot cause: BaseOpenAiCompatibleProvider sent model.info.maxTokens directly, bypassing getModelMaxOutputTok…
roomote
committed
test: align Z AI tests with centralized 20% output-token cap\n\nUpdate zai.spec to expect clamped max_tokens (min(model.maxTokens, ceil(contextWindow*0.2))) for OpenAI-compatible requests.
roomote
committed
revert: undo fc04a3a3d6524459fd5a31e27b8e7fc9e71ebf3c change to GLM-4.6-turbo maxTokens; restore 202752 in types; rely on centralized 20% cap at request time
roomote
committed