Private
Public Access
0
0

fix(ai_client): move openai_compatible imports to local scope; fix startup_speedup invariant

The follow-up track's tool-loop refactor moved
'from src.openai_compatible import send_openai_compatible,
 OpenAICompatibleRequest, NormalizedResponse' to MODULE level
in src/ai_client.py. This violates the startup_speedup_20260606
invariant: heavy SDKs must not be loaded at module level because
ai_client.py is on the main thread's import chain.

src/openai_compatible.py line 5 does 'from openai import
OpenAIError, ...', so any import from it triggers the openai SDK
to load. test_ai_client_does_not_import_openai_at_module_level
guards this invariant and was failing.

Fix: move the imports back to local scope inside the function
bodies that need them:
- _default_send closure inside run_with_tool_loop
  (imports send_openai_compatible)
- _send_grok (imports OpenAICompatibleRequest)
- _send_minimax (imports OpenAICompatibleRequest)
- _send_llama (imports OpenAICompatibleRequest)
- _send_gemini_cli (imports OpenAICompatibleRequest + NormalizedResponse)

Test patches: tests that previously patched
'src.ai_client.send_openai_compatible' now patch
'src.openai_compatible.send_openai_compatible' (the actual
import source). _execute_tool_calls_concurrently patches
unchanged (it's defined in src/ai_client.py itself).

Green confirmed: 62 vendor + tool + import-isolation tests
pass. 0 regressions.
This commit is contained in:
2026-06-11 16:15:49 -04:00
parent 4748d13490
commit 9ddfa98133
3 changed files with 22 additions and 16 deletions
+1 -1
View File
@@ -30,7 +30,7 @@ def test_run_with_tool_loop_calls_request_builder_each_round() -> None:
def builder(round_idx: int) -> OpenAICompatibleRequest:
builder_calls.append(round_idx)
return OpenAICompatibleRequest(messages=[{"role": "user", "content": f"round={round_idx}"}], model="m")
with patch("src.ai_client.send_openai_compatible", side_effect=[tool_response, final]), \
with patch("src.openai_compatible.send_openai_compatible", side_effect=[tool_response, final]), \
patch("src.ai_client._execute_tool_calls_concurrently", return_value=[("noop", "c1", "r", "")]):
result = run_with_tool_loop(
client, builder, capabilities=caps,