Files
qwen3.5-122B-A10B-on-spark/runtime
Entrpi 72badaf39a serve: enable OpenAI auto tool-calling (qwen3_xml) + reasoning split by default
A forum user hit HTTP 400 "'auto' tool choice requires --enable-auto-tool-choice
and --tool-call-parser to be set" — the server shipped without tool-calling
enabled, which is exactly what agent/tool workloads (the whole point) need.

- serve.sh + mtp_serve.sh now pass --enable-auto-tool-choice --tool-call-parser
  qwen3_xml --reasoning-parser qwen3 by default (overridable/disable via
  TOOL_PARSER= / REASONING_PARSER=).
- Parser matters: Qwen3.5 emits the XML tool format
  (<function=name><parameter=k>v</parameter></function>), so hermes returns 200
  but with EMPTY tool_calls (the call lands in content). qwen3_xml parses it.
  Verified on the box: tool_choice=auto -> tool_calls=[get_weather {city:Paris}];
  plain chat unaffected; <think> -> reasoning_content.
- README: document tool-calling defaults + that the server binds 0.0.0.0
  (LAN-reachable at http://<spark-ip>:8000; no auth).
2026-06-24 23:08:31 +10:00
..