mateclaw/mateclaw-server/src/main
matevip 4898b79d49 fix(agent): strip tool_choice="auto" so strict OpenAI-compatible servers accept the request
Some self-hosted OpenAI-compatible serving frameworks return a 400 Bad Request
with a generic Pydantic "body=None / Field required" error when the outbound
request carries tool_choice="auto" but the server was launched without an
auto-tool-choice opt-in flag. The error message hides the real cause: the
request is rejected at validation time before the body is parsed, so the
upstream client sees only the generic body-missing error.

Per the OpenAI spec, omitting tool_choice when tools is non-empty is
functionally equivalent to "auto" — the server defaults to auto-pick.
Adding a stripAutoToolChoice patcher to the buildOpenAiApi chain:

- changes nothing on compliant servers (OpenAI / DashScope / DeepSeek / Kimi
  default to auto when tools are present)
- unblocks strict OpenAI-compatible self-hosted endpoints

Explicit values other than "auto" ({"none", "required", or a function
descriptor}) are passed through unchanged.

Run on both chatCompletionEntity and chatCompletionStream paths so both
buffered and streaming calls benefit.
2026-04-27 20:35:24 +08:00
..
java/vip/mate fix(agent): strip tool_choice="auto" so strict OpenAI-compatible servers accept the request 2026-04-27 20:35:24 +08:00
resources refactor(bootstrap): drop legacy tools-sync.sql in favor of per-tool Flyway migrations 2026-04-27 14:00:08 +08:00