mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-14 22:33:48 +00:00
79bed44b04
Propagate test IDs from client to server via HTTP headers to maintain proper test isolation when running with server-based stack configs. Without this, recorded/replayed inference requests in server mode would leak across tests. Changes: - Patch client _prepare_request to inject test ID into provider data header - Sync test context from provider data on server side before storage operations - Set LLAMA_STACK_TEST_STACK_CONFIG_TYPE env var based on stack config - Configure console width for cleaner log output in CI - Add SQLITE_STORE_DIR temp directory for test data isolation
39 lines
992 B
JSON
39 lines
992 B
JSON
{
|
|
"test_id": null,
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://localhost:11434/api/ps",
|
|
"headers": {},
|
|
"body": {},
|
|
"endpoint": "/api/ps",
|
|
"model": ""
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "ollama._types.ProcessResponse",
|
|
"__data__": {
|
|
"models": [
|
|
{
|
|
"model": "llama3.2-vision:11b",
|
|
"name": "llama3.2-vision:11b",
|
|
"digest": "6f2f9757ae97e8a3f8ea33d6adb2b11d93d9a35bef277cd2c0b1b5af8e8d0b1e",
|
|
"expires_at": "2025-10-08T12:40:47.430429-07:00",
|
|
"size": 11765236384,
|
|
"size_vram": 11765236384,
|
|
"details": {
|
|
"parent_model": "",
|
|
"format": "gguf",
|
|
"family": "mllama",
|
|
"families": [
|
|
"mllama"
|
|
],
|
|
"parameter_size": "10.7B",
|
|
"quantization_level": "Q4_K_M"
|
|
}
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|