feat(tests): implement test isolation for inference recordings (#3681)

Uses test_id in request hashes and test-scoped subdirectories to prevent
cross-test contamination. Model list endpoints exclude test_id to enable
merging recordings from different servers.

Additionally, this PR adds a `record-if-missing` mode (which we will use
instead of `record` which records everything) which is very useful.

🤖 Co-authored with [Claude Code](https://claude.com/claude-code)

---------

Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
Ashwin Bharambe 2025-10-04 11:34:18 -07:00 committed by GitHub
parent f176196fba
commit 045a0c1d57
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
428 changed files with 85345 additions and 104330 deletions

View file

@ -0,0 +1,59 @@
{
"test_id": "tests/integration/providers/nvidia/test_datastore.py::test_register_and_unregister[nvidia]",
"request": {
"method": "POST",
"url": "http://localhost:11434/api/ps",
"headers": {},
"body": {},
"endpoint": "/api/ps",
"model": ""
},
"response": {
"body": {
"__type__": "ollama._types.ProcessResponse",
"__data__": {
"models": [
{
"model": "all-minilm:l6-v2",
"name": "all-minilm:l6-v2",
"digest": "1b226e2802dbb772b5fc32a58f103ca1804ef7501331012de126ab22f67475ef",
"expires_at": "2025-10-03T21:21:14.509335-07:00",
"size": 585846784,
"size_vram": 585846784,
"details": {
"parent_model": "",
"format": "gguf",
"family": "bert",
"families": [
"bert"
],
"parameter_size": "23M",
"quantization_level": "F16"
},
"context_length": 256
},
{
"model": "llama3.2:3b-instruct-fp16",
"name": "llama3.2:3b-instruct-fp16",
"digest": "195a8c01d91ec3cb1e0aad4624a51f2602c51fa7d96110f8ab5a20c84081804d",
"expires_at": "2025-10-03T21:20:56.787737-07:00",
"size": 7919570944,
"size_vram": 7919570944,
"details": {
"parent_model": "",
"format": "gguf",
"family": "llama",
"families": [
"llama"
],
"parameter_size": "3.2B",
"quantization_level": "F16"
},
"context_length": 4096
}
]
}
},
"is_streaming": false
}
}

View file

@ -0,0 +1,59 @@
{
"test_id": "tests/integration/providers/test_providers.py::TestProviders::test_providers",
"request": {
"method": "POST",
"url": "http://localhost:11434/api/ps",
"headers": {},
"body": {},
"endpoint": "/api/ps",
"model": ""
},
"response": {
"body": {
"__type__": "ollama._types.ProcessResponse",
"__data__": {
"models": [
{
"model": "all-minilm:l6-v2",
"name": "all-minilm:l6-v2",
"digest": "1b226e2802dbb772b5fc32a58f103ca1804ef7501331012de126ab22f67475ef",
"expires_at": "2025-10-03T21:21:14.509335-07:00",
"size": 585846784,
"size_vram": 585846784,
"details": {
"parent_model": "",
"format": "gguf",
"family": "bert",
"families": [
"bert"
],
"parameter_size": "23M",
"quantization_level": "F16"
},
"context_length": 256
},
{
"model": "llama3.2:3b-instruct-fp16",
"name": "llama3.2:3b-instruct-fp16",
"digest": "195a8c01d91ec3cb1e0aad4624a51f2602c51fa7d96110f8ab5a20c84081804d",
"expires_at": "2025-10-03T21:20:56.787737-07:00",
"size": 7919570944,
"size_vram": 7919570944,
"details": {
"parent_model": "",
"format": "gguf",
"family": "llama",
"families": [
"llama"
],
"parameter_size": "3.2B",
"quantization_level": "F16"
},
"context_length": 4096
}
]
}
},
"is_streaming": false
}
}