fix(ci, tests): ensure uv environments in CI are kosher, record tests (#3193)

I started this PR trying to unbreak a newly broken test
`test_agent_name`. This test was broken all along but did not show up
because during testing we were pulling the "non-updated" llama stack
client. See this comment:
https://github.com/llamastack/llama-stack/pull/3119#discussion_r2270988205

While fixing this, I encountered a large amount of badness in our CI
workflow definitions.

- We weren't passing `LLAMA_STACK_DIR` or `LLAMA_STACK_CLIENT_DIR`
overrides to `llama stack build` at all in some cases.
- Even when we did, we used `uv run` liberally. The first thing `uv run`
does is "syncs" the project environment. This means, it is going to undo
any mutations we might have done ourselves. But we make many mutations
in our CI runners to these environments. The most important of which is
why `llama stack build` where we install distro dependencies. As a
result, when you tried to run the integration tests, you would see old,
strange versions.


## Test Plan

Re-record using:

```
sh scripts/integration-tests.sh --stack-config ci-tests \
  --provider ollama --test-pattern test_agent_name --inference-mode record
```

Then re-run with `--inference-mode replay`. But: 

Eventually, this test turned out to be quite flaky for telemetry
reasons. I haven't investigated it for now and just disabled it sadly
since we have a release to push out.

tests/integration/recordings/responses/731824c54461.json

@@ -0,0 +1,203 @@
+{
+  "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\nYou are a helpful assistant<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nGive me a sentence that contains the word: hello<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
+      "options": {
+        "temperature": 0.0
+      },
+      "stream": true
+    },
+    "endpoint": "/api/generate",
+    "model": "llama3.2:3b-instruct-fp16"
+  },
+  "response": {
+    "body": [
+      {
+        "__type__": "ollama._types.GenerateResponse",
+        "__data__": {
+          "model": "llama3.2:3b-instruct-fp16",
+          "created_at": "2025-08-18T19:47:58.267146Z",
+          "done": false,
+          "done_reason": null,
+          "total_duration": null,
+          "load_duration": null,
+          "prompt_eval_count": null,
+          "prompt_eval_duration": null,
+          "eval_count": null,
+          "eval_duration": null,
+          "response": "Hello",
+          "thinking": null,
+          "context": null
+        }
+      },
+      {
+        "__type__": "ollama._types.GenerateResponse",
+        "__data__": {
+          "model": "llama3.2:3b-instruct-fp16",
+          "created_at": "2025-08-18T19:47:58.309006Z",
+          "done": false,
+          "done_reason": null,
+          "total_duration": null,
+          "load_duration": null,
+          "prompt_eval_count": null,
+          "prompt_eval_duration": null,
+          "eval_count": null,
+          "eval_duration": null,
+          "response": ",",
+          "thinking": null,
+          "context": null
+        }
+      },
+      {
+        "__type__": "ollama._types.GenerateResponse",
+        "__data__": {
+          "model": "llama3.2:3b-instruct-fp16",
+          "created_at": "2025-08-18T19:47:58.351179Z",
+          "done": false,
+          "done_reason": null,
+          "total_duration": null,
+          "load_duration": null,
+          "prompt_eval_count": null,
+          "prompt_eval_duration": null,
+          "eval_count": null,
+          "eval_duration": null,
+          "response": " how",
+          "thinking": null,
+          "context": null
+        }
+      },
+      {
+        "__type__": "ollama._types.GenerateResponse",
+        "__data__": {
+          "model": "llama3.2:3b-instruct-fp16",
+          "created_at": "2025-08-18T19:47:58.393262Z",
+          "done": false,
+          "done_reason": null,
+          "total_duration": null,
+          "load_duration": null,
+          "prompt_eval_count": null,
+          "prompt_eval_duration": null,
+          "eval_count": null,
+          "eval_duration": null,
+          "response": " can",
+          "thinking": null,
+          "context": null
+        }
+      },
+      {
+        "__type__": "ollama._types.GenerateResponse",
+        "__data__": {
+          "model": "llama3.2:3b-instruct-fp16",
+          "created_at": "2025-08-18T19:47:58.436079Z",
+          "done": false,
+          "done_reason": null,
+          "total_duration": null,
+          "load_duration": null,
+          "prompt_eval_count": null,
+          "prompt_eval_duration": null,
+          "eval_count": null,
+          "eval_duration": null,
+          "response": " I",
+          "thinking": null,
+          "context": null
+        }
+      },
+      {
+        "__type__": "ollama._types.GenerateResponse",
+        "__data__": {
+          "model": "llama3.2:3b-instruct-fp16",
+          "created_at": "2025-08-18T19:47:58.478393Z",
+          "done": false,
+          "done_reason": null,
+          "total_duration": null,
+          "load_duration": null,
+          "prompt_eval_count": null,
+          "prompt_eval_duration": null,
+          "eval_count": null,
+          "eval_duration": null,
+          "response": " assist",
+          "thinking": null,
+          "context": null
+        }
+      },
+      {
+        "__type__": "ollama._types.GenerateResponse",
+        "__data__": {
+          "model": "llama3.2:3b-instruct-fp16",
+          "created_at": "2025-08-18T19:47:58.520608Z",
+          "done": false,
+          "done_reason": null,
+          "total_duration": null,
+          "load_duration": null,
+          "prompt_eval_count": null,
+          "prompt_eval_duration": null,
+          "eval_count": null,
+          "eval_duration": null,
+          "response": " you",
+          "thinking": null,
+          "context": null
+        }
+      },
+      {
+        "__type__": "ollama._types.GenerateResponse",
+        "__data__": {
+          "model": "llama3.2:3b-instruct-fp16",
+          "created_at": "2025-08-18T19:47:58.562885Z",
+          "done": false,
+          "done_reason": null,
+          "total_duration": null,
+          "load_duration": null,
+          "prompt_eval_count": null,
+          "prompt_eval_duration": null,
+          "eval_count": null,
+          "eval_duration": null,
+          "response": " today",
+          "thinking": null,
+          "context": null
+        }
+      },
+      {
+        "__type__": "ollama._types.GenerateResponse",
+        "__data__": {
+          "model": "llama3.2:3b-instruct-fp16",
+          "created_at": "2025-08-18T19:47:58.604683Z",
+          "done": false,
+          "done_reason": null,
+          "total_duration": null,
+          "load_duration": null,
+          "prompt_eval_count": null,
+          "prompt_eval_duration": null,
+          "eval_count": null,
+          "eval_duration": null,
+          "response": "?",
+          "thinking": null,
+          "context": null
+        }
+      },
+      {
+        "__type__": "ollama._types.GenerateResponse",
+        "__data__": {
+          "model": "llama3.2:3b-instruct-fp16",
+          "created_at": "2025-08-18T19:47:58.646586Z",
+          "done": true,
+          "done_reason": "stop",
+          "total_duration": 1011323917,
+          "load_duration": 76575458,
+          "prompt_eval_count": 31,
+          "prompt_eval_duration": 553259250,
+          "eval_count": 10,
+          "eval_duration": 380302792,
+          "response": "",
+          "thinking": null,
+          "context": null
+        }
+      }
+    ],
+    "is_streaming": true
+  }
+}