mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-22 00:13:08 +00:00
add64e8e2a
# Problem The current inline provider appends the user provided instructions to messages as a system prompt, but the returned response object does not contain the instructions field (as specified in the OpenAI responses spec). # What does this PR do? This pull request adds the instruction field to the response object definition and updates the inline provider. It also ensures that instructions from previous response is not carried over to the next response (as specified in the openAI spec). Closes #[3566](https://github.com/llamastack/llama-stack/issues/3566) ## Test Plan - Tested manually for change in model response w.r.t supplied instructions field. - Added unit test to check that the instructions from previous response is not carried over to the next response. - Added integration tests to check instructions parameter in the returned response object. - Added new recordings for the integration tests. --------- Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
59 lines
2.3 KiB
JSON
Generated
59 lines
2.3 KiB
JSON
Generated
{
|
|
"test_id": "tests/integration/agents/test_agents.py::test_custom_tool_infinite_loop[ollama/llama3.2:3b-instruct-fp16]",
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://0.0.0.0:11434/v1/v1/chat/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "llama-guard3:1b",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "Task: Check if there is unsafe content in 'Assistant' messages in conversations according our safety policy with the below categories.\n\n<BEGIN UNSAFE CONTENT CATEGORIES>\nS1: Violent Crimes.\nS2: Non-Violent Crimes.\nS3: Sex Crimes.\nS4: Child Exploitation.\nS5: Defamation.\nS6: Specialized Advice.\nS7: Privacy.\nS8: Intellectual Property.\nS9: Indiscriminate Weapons.\nS10: Hate.\nS11: Self-Harm.\nS12: Sexual Content.\nS13: Elections.\nS14: Code Interpreter Abuse.\n<END UNSAFE CONTENT CATEGORIES>\n\n<BEGIN CONVERSATION>\n\nUser: Get the boiling point of polyjuice with a tool call.\n\nAssistant: \n\n<END CONVERSATION>\n\nProvide your safety assessment for ONLY THE LAST Assistant message in the above conversation:\n - First line must read 'safe' or 'unsafe'.\n - If unsafe, a second line must include a comma-separated list of violated categories."
|
|
}
|
|
],
|
|
"stream": false,
|
|
"temperature": 0.0
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "llama-guard3:1b"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
|
"__data__": {
|
|
"id": "rec-6da760645fe2",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "stop",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"message": {
|
|
"content": "safe",
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"annotations": null,
|
|
"audio": null,
|
|
"function_call": null,
|
|
"tool_calls": null
|
|
}
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "llama-guard3:1b",
|
|
"object": "chat.completion",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": {
|
|
"completion_tokens": 2,
|
|
"prompt_tokens": 399,
|
|
"total_tokens": 401,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
}
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
},
|
|
"id_normalization_mapping": {}
|
|
}
|