Hans Heinemann 60576fbf2f fix: remove hardcoded max_tokens/temperature from _dispatch_via_llm ...

Both values are now sourced from team.yaml (models.default_max_tokens and
models.default_temperature) via the adapter's __init__, eliminating the
last hardcoded magic numbers. Callers can still override per-call via
context dict if needed.

2026-03-15 21:43:01 -04:00

27 KiB

Raw Blame History

View Raw