feat(tests): auto-merge all model list responses and unify recordings (#3320)

One needed to specify record-replay related environment variables for
running integration tests. We could not use defaults because integration
tests could be run against Ollama instances which could be running
different models. For example, text vs vision tests needed separate
instances of Ollama because a single instance typically cannot serve
both of these models if you assume the standard CI worker configuration
on Github. As a result, `client.list()` as returned by the Ollama client
would be different between these runs and we'd end up overwriting
responses.

This PR "solves" it by adding a small amount of complexity -- we store
model list responses specially, keyed by the hashes of the models they
return. At replay time, we merge all of them and pretend that we have
the union of all models available.

## Test Plan

Re-recorded all the tests using `scripts/integration-tests.sh
--inference-mode record`, including the vision tests.

tests/integration/recordings/responses/140187e305dc.json

@@ -1,7 +1,7 @@
 {
   "request": {
     "method": "POST",
-    "url": "http://localhost:11434/v1/v1/chat/completions",
+    "url": "http://0.0.0.0:11434/v1/v1/chat/completions",
     "headers": {},
     "body": {
       "model": "llama3.2:3b-instruct-fp16",
@@ -20,14 +20,14 @@
     "body": {
       "__type__": "openai.types.chat.chat_completion.ChatCompletion",
       "__data__": {
-        "id": "chatcmpl-876",
+        "id": "chatcmpl-974",
         "choices": [
           {
             "finish_reason": "stop",
             "index": 0,
             "logprobs": null,
             "message": {
-              "content": "I'm afraid I don't have a built-in ability to directly interface with or \"test\" OpenAI models, including the original GPT-1 model. However, I can explain how you might approach this task:\n\nThe OpenAI GPT-1 is a large transformer-based language model that was trained on a massive dataset of text and achieved state-of-the-art results in various natural language processing tasks.\n\nTo test or evaluate the performance of a model like GPT-1, you would typically follow these steps:\n\n1. **Get access to the OpenAI API**: The OpenAI API provides a way for developers to interact with the GPT-1 model programmatically. You can sign up for an API key on the OpenAI website.\n2. **Choose a testing platform or environment**: You'll need a compute platform that supports the necessary algorithms and data structures to run inference on the GPT-1 model. Some popular options include AWS, Google Cloud, or Azure Compute Virtual Machines.\n3. **Prepare your test input data**: This will involve creating text inputs in the format expected by the OpenAI API (i.e., a JSON object containing the text to be processed).\n4. **Use the OpenAI Python library or SDK**: The OpenAI Python library provides an easy-to-use interface for interacting with the GPT-1 model through the API.\n\nHere's some example code that demonstrates how you might use the OpenAI Flask API to test a single input:\n\n```python\nfrom flask import Flask, request, jsonify\nimport json\n\napp = Flask(__name__)\n\n@ app . route ( '/ /gpt-en ', ' Text ', methods = ['POST'])\ndef gpt_en () -> Json :\n    data = request . get_json ()\n    if not data or \"message\" in ( data ):\n        return None , 400 , { ' error' : \"Input must be a text string.\" }\n    response = []\n    while True:\n        message = \"\"\n        for token in data [\"input\"]:\n            response_text = f\"{data['prompt']} {token}\"\n            data[\"input\"] = [response_text]\n            new_response = gpt_en()(data)\n            if all([not item or not isinstance(item, dict) for item in new_response]):\n             break\n\n        message = json . dumps ({}\"text\": response_text})\n        response.append(message)\n\n    return jsonify ({\"output\": response}), 200 , {}\n\nif __name__ == \"__main__\":\n   app.run(debug=True)\n```\n\n5. **Evaluate the output**: Once you have processed your test input data using the GPT-1 model, you can evaluate the accuracy of the generated responses.\n\nKeep in mind that this is just a basic example to illustrate how you might approach testing the OpenAI GPT-1 model.",
+              "content": "I'm happy to help you test the OpenAI API, however I can not access the API.\n\nInstead why don't we follow these steps:\n\n*   Check documentation\n*   Contact support\n*   Reach out to their community forum. \n\nLet me know if I can be of any additional assistance",
               "refusal": null,
               "role": "assistant",
               "annotations": null,
@@ -37,15 +37,15 @@
             }
           }
         ],
-        "created": 1754510050,
+        "created": 1756921202,
         "model": "llama3.2:3b-instruct-fp16",
         "object": "chat.completion",
         "service_tier": null,
         "system_fingerprint": "fp_ollama",
         "usage": {
-          "completion_tokens": 567,
+          "completion_tokens": 61,
           "prompt_tokens": 31,
-          "total_tokens": 598,
+          "total_tokens": 92,
           "completion_tokens_details": null,
           "prompt_tokens_details": null
         }