fix(auxiliary): honor api_mode in auxiliary client (#6800)
The auxiliary client always calls client.chat.completions.create(),
ignoring the api_mode config flag. This breaks codex-family models
(e.g. gpt-5.3-codex) on direct OpenAI API keys, which need the
/v1/responses endpoint.
Changes:
- Expand _resolve_task_provider_model to return api_mode (5-tuple)
- Read api_mode from auxiliary.{task}.api_mode config and env vars
(AUXILIARY_{TASK}_API_MODE)
- Pass api_mode through _get_cached_client to resolve_provider_client
- Add _needs_codex_wrap/_wrap_if_needed helpers that wrap plain OpenAI
clients in CodexAuxiliaryClient when api_mode=codex_responses or
when auto-detection finds api.openai.com + codex model pattern
- Apply wrapping at all custom endpoint, named custom provider, and
API-key provider return paths
- Update test mocks for the new 5-tuple return format
Users can now set:
auxiliary:
compression:
model: gpt-5.3-codex
base_url: https://api.openai.com/v1
api_mode: codex_responses
Closes #6800
This commit is contained in:
@@ -1136,7 +1136,7 @@ class TestCallLlmPaymentFallback:
|
||||
with patch("agent.auxiliary_client._get_cached_client",
|
||||
return_value=(primary_client, "google/gemini-3-flash-preview")), \
|
||||
patch("agent.auxiliary_client._resolve_task_provider_model",
|
||||
return_value=("openrouter", "google/gemini-3-flash-preview", None, None)), \
|
||||
return_value=("openrouter", "google/gemini-3-flash-preview", None, None, None)), \
|
||||
patch("agent.auxiliary_client._try_payment_fallback",
|
||||
return_value=(fallback_client, "gpt-5.2-codex", "openai-codex")) as mock_fb:
|
||||
result = call_llm(
|
||||
@@ -1162,7 +1162,7 @@ class TestCallLlmPaymentFallback:
|
||||
with patch("agent.auxiliary_client._get_cached_client",
|
||||
return_value=(primary_client, "google/gemini-3-flash-preview")), \
|
||||
patch("agent.auxiliary_client._resolve_task_provider_model",
|
||||
return_value=("openrouter", "google/gemini-3-flash-preview", None, None)):
|
||||
return_value=("openrouter", "google/gemini-3-flash-preview", None, None, None)):
|
||||
with pytest.raises(Exception, match="Internal Server Error"):
|
||||
call_llm(
|
||||
task="compression",
|
||||
@@ -1179,7 +1179,7 @@ class TestCallLlmPaymentFallback:
|
||||
with patch("agent.auxiliary_client._get_cached_client",
|
||||
return_value=(primary_client, "google/gemini-3-flash-preview")), \
|
||||
patch("agent.auxiliary_client._resolve_task_provider_model",
|
||||
return_value=("openrouter", "google/gemini-3-flash-preview", None, None)), \
|
||||
return_value=("openrouter", "google/gemini-3-flash-preview", None, None, None)), \
|
||||
patch("agent.auxiliary_client._try_payment_fallback",
|
||||
return_value=(None, None, "")):
|
||||
with pytest.raises(Exception, match="insufficient credits"):
|
||||
|
||||
Reference in New Issue
Block a user