Add API retries and concurrent batch processing

tests/test_client.py

@@ -5,6 +5,7 @@ from __future__ import annotations
 import json
 
 import httpx
+import pytest
 
 from swe_data_processing.client import GLMClient
 from swe_data_processing.config import Settings
@@ -33,7 +34,7 @@ def test_client_parses_fenced_json_and_never_sends_key_in_body() -> None:
         "required": ["status"],
         "properties": {"status": {"const": "ok"}},
     }
-    settings = Settings(api_key="test-secret", max_retries=1)
+    settings = Settings(api_key="test-secret", max_retries=0)
     with GLMClient(settings, transport=httpx.MockTransport(handler)) as client:
         response = client.invoke_json(system_prompt="Return JSON.", payload={"ping": True}, schema=schema)
 
@@ -62,10 +63,41 @@ def test_client_falls_back_when_vendor_extensions_are_rejected() -> None:
         "required": ["status"],
         "properties": {"status": {"const": "ok"}},
     }
-    settings = Settings(api_key="test-secret", max_retries=2)
+    settings = Settings(api_key="test-secret", max_retries=1)
     with GLMClient(settings, transport=httpx.MockTransport(handler)) as client:
         response = client.invoke_json(system_prompt="Return JSON.", payload={}, schema=schema)
 
     assert "thinking" in calls[0]
     assert "thinking" not in calls[1]
     assert response.compatibility_fallback_used is True
+
+
+def test_client_retries_five_failures_before_succeeding(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    """Five retryable failures are followed by a sixth and final attempt."""
+
+    calls = 0
+
+    def handler(_: httpx.Request) -> httpx.Response:
+        nonlocal calls
+        calls += 1
+        if calls <= 5:
+            return httpx.Response(503, json={"error": {"message": "temporarily unavailable"}})
+        return httpx.Response(
+            200,
+            json={"choices": [{"message": {"content": "{\"status\":\"ok\"}"}}]},
+        )
+
+    monkeypatch.setattr("swe_data_processing.client.time.sleep", lambda _: None)
+    schema = {
+        "type": "object",
+        "required": ["status"],
+        "properties": {"status": {"const": "ok"}},
+    }
+    settings = Settings(api_key="test-secret", max_retries=5)
+    with GLMClient(settings, transport=httpx.MockTransport(handler)) as client:
+        response = client.invoke_json(system_prompt="Return JSON.", payload={}, schema=schema)
+
+    assert calls == 6
+    assert response.data == {"status": "ok"}