mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-14 14:27:58 +00:00
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
113 lines
2.9 KiB
JSON
113 lines
2.9 KiB
JSON
{
|
|
"test_id": "tests/integration/inference/test_tools_with_schemas.py::TestEdgeCases::test_multiple_tools_with_different_schemas[txt=ollama/llama3.2:3b-instruct-fp16]",
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://0.0.0.0:11434/v1/v1/chat/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "Use one of the available tools"
|
|
}
|
|
],
|
|
"tools": [
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "simple",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"x": {
|
|
"type": "string"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "complex",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"data": {
|
|
"$ref": "#/$defs/Complex"
|
|
}
|
|
},
|
|
"$defs": {
|
|
"Complex": {
|
|
"type": "object",
|
|
"properties": {
|
|
"nested": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "number"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "with_output",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"input": {
|
|
"type": "string"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
]
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "llama3.2:3b-instruct-fp16"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
|
"__data__": {
|
|
"id": "rec-12ea4e4a2705",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "stop",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"message": {
|
|
"content": "{\"name\":\"complex\",\"parameters\":{}\"}}",
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"annotations": null,
|
|
"audio": null,
|
|
"function_call": null,
|
|
"tool_calls": null
|
|
}
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": {
|
|
"completion_tokens": 10,
|
|
"prompt_tokens": 246,
|
|
"total_tokens": 256,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
}
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|