Initial Open-SWE-Traces cleanup pipeline

tests/test_client.py

@@ -0,0 +1,71 @@
+"""Tests for API request compatibility and structured-response validation."""
+
+from __future__ import annotations
+
+import json
+
+import httpx
+
+from swe_data_processing.client import GLMClient
+from swe_data_processing.config import Settings
+
+
+def test_client_parses_fenced_json_and_never_sends_key_in_body() -> None:
+    captured_body = {}
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        captured_body.update(json.loads(request.content))
+        assert request.headers["authorization"] == "Bearer test-secret"
+        return httpx.Response(
+            200,
+            headers={"x-request-id": "request-123"},
+            json={
+                "choices": [
+                    {"message": {"role": "assistant", "content": "```json\n{\"status\":\"ok\"}\n```"}}
+                ],
+                "usage": {"total_tokens": 10},
+            },
+        )
+
+    schema = {
+        "type": "object",
+        "additionalProperties": False,
+        "required": ["status"],
+        "properties": {"status": {"const": "ok"}},
+    }
+    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={"ping": True}, schema=schema)
+
+    assert response.data == {"status": "ok"}
+    assert response.request_id == "request-123"
+    assert response.usage == {"total_tokens": 10}
+    assert "test-secret" not in json.dumps(captured_body)
+    assert captured_body["model"] == "glm-5.2"
+
+
+def test_client_falls_back_when_vendor_extensions_are_rejected() -> None:
+    calls = []
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        body = json.loads(request.content)
+        calls.append(body)
+        if len(calls) == 1:
+            return httpx.Response(400, json={"error": {"message": "unknown parameter: thinking"}})
+        return httpx.Response(
+            200,
+            json={"choices": [{"message": {"content": "{\"status\":\"ok\"}"}}]},
+        )
+
+    schema = {
+        "type": "object",
+        "required": ["status"],
+        "properties": {"status": {"const": "ok"}},
+    }
+    settings = Settings(api_key="test-secret", max_retries=2)
+    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