feat(ci): use replay mode, setup ollama if specific label exists on PR (#2955)

This PR makes setting up Ollama optional for CI. By default, we use
`replay` mode for inference requests and use the stored results from the
`tests/integration/recordings/` directory.

Every so often, users will update tests which will need us to re-record.
To do this, we check for the existence of a label `re-record-tests` on
the PR. If detected,
- ollama is spun up
- inference mode is set to record
- after the tests are done, if any new changes are detected, they are
pushed back to the PR

## Test Plan

This is GitHub CI. Gotta test it live.

tests/integration/recordings/responses/4a3a4447b16b.json

@@ -14,7 +14,7 @@
         "models": [
           {
             "model": "nomic-embed-text:latest",
-            "modified_at": "2025-07-29T14:55:45.755906-07:00",
+            "modified_at": "2025-07-29T16:46:26.304701-07:00",
             "digest": "0a109f422b47e3a30ba2b10eca18548e944e8a23073ee3f3e947efcf3c45e59f",
             "size": 274302450,
             "details": {