feat(tests): record responses for evals and telemetry tests (#2954)

Continuing with https://github.com/meta-llama/llama-stack/pull/2952

This also includes a "fix" to inference store related tests so that we
pull a large number of inference responses from the DB so as to always
find the one we just wrote.

tests/integration/recordings/responses/44fb9cf5875f.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 1<|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": "2025-07-29T21:56:49.398099Z",
+        "done": true,
+        "done_reason": "stop",
+        "total_duration": 2251794875,
+        "load_duration": 108848667,
+        "prompt_eval_count": 20,
+        "prompt_eval_duration": 82008917,
+        "eval_count": 51,
+        "eval_duration": 2060141416,
+        "response": "It seems like you're trying to test the system, but I'm not sure what specific functionality or feature you'd like to test. Could you please provide more context or clarify what you're looking for? I'll do my best to assist you!",
+        "thinking": null,
+        "context": null
+      }
+    },
+    "is_streaming": false
+  }
+}