Files
EvoScientist/tests
m4 b2e28249fd fix(model-registry): inject async safe clients and split ollama transports
Review fixes for the Task 3 contract layer:

- build_chat_model now accepts http_async_client alongside http_client
  (at least one required) and wires it into ChatOpenAI
  (http_async_client), ChatAnthropic (seeded _async_client), and
  ChatOllama (async_client_kwargs transport), closing the unsafe
  default-async-client gap.
- ChatOllama safe transports move from the shared client_kwargs to
  sync_client_kwargs/async_client_kwargs; langchain-ollama merges shared
  kwargs into both clients, which poisoned the async client with a sync
  transport and crashed ainvoke.
- Unsupported parameters now actually execute the contract-declared
  normalizer (reject_non_auto) instead of a hardcoded raise, with a
  fallback rejection if a normalizer would let a value through.
- build_chat_model rejects overlapping client_options/request_options
  keys instead of silently overwriting.
2026-07-20 22:40:33 +08:00
..
2026-01-29 17:39:50 +00:00
2026-06-16 09:14:29 +02:00
2026-03-24 18:13:42 +00:00