fix: derive LLM provider from adapter, not config

Remove redundant models.provider from team.yaml. Each adapter knows its
own provider key — AnthropicAdapter always looks up 'anthropic' in the
capability_map. This avoids a footgun where adapters.llm and models.provider
could disagree.

Future adapters (OpenAIAdapter, OllamaAdapter) will hardcode their own key
the same way.
This commit is contained in:
2026-03-15 23:47:52 -04:00
parent 60576fbf2f
commit bd96a83069
2 changed files with 9 additions and 7 deletions

View File

@@ -10,7 +10,6 @@ adapters:
runtime: openclaw
models:
provider: anthropic
default_max_tokens: 4096
default_temperature: 0
capability_map: