feat(tests): record responses for evals and telemetry tests

tests/integration/recordings/responses/ae1c22f18ecc.json

@@ -0,0 +1,39 @@
+{
+  "request": {
+    "method": "POST",
+    "url": "http://localhost:11434/api/generate",
+    "headers": {},
+    "body": {
+      "model": "llama3.2:3b-instruct-fp16",
+      "raw": true,
+      "prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nTest trace 0<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
+      "options": {
+        "temperature": 0.0
+      },
+      "stream": false
+    },
+    "endpoint": "/api/generate",
+    "model": "llama3.2:3b-instruct-fp16"
+  },
+  "response": {
+    "body": {
+      "__type__": "ollama._types.GenerateResponse",
+      "__data__": {
+        "model": "llama3.2:3b-instruct-fp16",
+        "created_at": "2025-07-29T21:56:47.06444Z",
+        "done": true,
+        "done_reason": "stop",
+        "total_duration": 2620252041,
+        "load_duration": 196706333,
+        "prompt_eval_count": 20,
+        "prompt_eval_duration": 70100292,
+        "eval_count": 58,
+        "eval_duration": 2352865167,
+        "response": "I'm happy to help you with your test, but I don't see what kind of test we are testing. Could you please provide more context or clarify what kind of test you would like me to perform? Is it a programming test, a language proficiency test, or something else?",
+        "thinking": null,
+        "context": null
+      }
+    },
+    "is_streaming": false
+  }
+}