jay77721 dc6c0e5de5 fix: drop max_tokens from generic OpenAI-compatible request builder (#17857) ...

## Summary

The generic `buildRequestBody` in `internal/entity/models/base_model.go`
unconditionally forwarded `ChatConfig.MaxTokens` as `"max_tokens"` for
every OpenAI-compatible provider.

Providers that need a different token field already delete or override
it after the call (e.g. Xiaomi uses `max_completion_tokens`, Replicate
uses `max_new_tokens`). This change stops setting `max_tokens` in the
shared builder so it only forwards the parameters common across
providers, and each provider remains free to set its own token limit
field.

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

2026-08-05 19:31:12 +08:00

26 KiB

Raw Blame History

View Raw