llama-stack-mirror/tests/integration/recordings/responses/168daab89068.json
Tami Takamiya 65f7b81e98
Some checks failed
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 0s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 17s
Python Package Build Test / build (3.12) (push) Failing after 17s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 19s
Unit Tests / unit-tests (3.13) (push) Failing after 15s
Vector IO Integration Tests / test-matrix (push) Failing after 20s
Test External API and Providers / test-external (venv) (push) Failing after 3s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 19s
Python Package Build Test / build (3.13) (push) Failing after 16s
Unit Tests / unit-tests (3.12) (push) Failing after 16s
API Conformance Tests / check-schema-compatibility (push) Successful in 25s
UI Tests / ui-tests (22) (push) Successful in 50s
Pre-commit / pre-commit (push) Successful in 1m16s
feat: Add items and title to ToolParameter/ToolParamDefinition (#3003)
# What does this PR do?
<!-- Provide a short summary of what this PR does and why. Link to
relevant issues if applicable. -->
Add items and title to ToolParameter/ToolParamDefinition. Adding items
will resolve the issue that occurs with Gemini LLM when an MCP tool has
array-type properties.

<!-- If resolving an issue, uncomment and update the line below -->
<!-- Closes #[issue-number] -->

## Test Plan
<!-- Describe the tests you ran to verify your changes with result
summaries. *Provide clear instructions so the plan can be easily
re-executed.* -->
Unite test cases will be added.

---------

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Kai Wu <kaiwu@meta.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
2025-09-27 11:35:29 -07:00

167 lines
7.3 KiB
JSON

{
"request": {
"method": "POST",
"url": "http://localhost:11434/api/generate",
"headers": {},
"body": {
"model": "llama3.2:3b-instruct-fp16",
"raw": true,
"prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are a helpful assistant. You have access to functions, but you should only use them if they are required.\nYou are an expert in composing functions. You are given a question and a set of possible functions.\nBased on the question, you may or may not need to make one function/tool call to achieve the purpose.\n\nIf you decide to invoke any of the function(s), you MUST put it in the format of [func_name1(params_name1=params_value1, params_name2=params_value2...), func_name2(params)]\nIf you decide to invoke a function, you SHOULD NOT include any other text in the response. besides the function call in the above format.\nFor a boolean parameter, be sure to use `True` or `False` (capitalized) for the value.\n\n\nHere is a list of functions in JSON format that you can invoke.\n\n[\n {\n \"name\": \"greet_everyone\",\n \"description\": \"\",\n \"parameters\": {\n \"type\": \"dict\",\n \"required\": [\"url\"],\n \"properties\": {\n \"url\": {\n \"type\": \"string\",\n \"description\": \"\"\n }\n }\n }\n },\n {\n \"name\": \"get_boiling_point\",\n \"description\": \"\n Returns the boiling point of a liquid in Celsius or Fahrenheit.\n\n :param liquid_name: The name of the liquid\n :param celsius: Whether to return the boiling point in Celsius\n :return: The boiling point of the liquid in Celcius or Fahrenheit\n \",\n \"parameters\": {\n \"type\": \"dict\",\n \"required\": [\"liquid_name\"],\n \"properties\": {\n \"liquid_name\": {\n \"type\": \"string\",\n \"description\": \"\"\n },\n \"celsius\": {\n \"type\": \"boolean\",\n \"description\": \"\",\n \"default\": \"True\"\n }\n }\n }\n }\n]\n\nYou can answer general questions or invoke tools when necessary.\nIn addition to tool calls, you should also augment your responses by using the tool outputs.\nYou are a helpful assistant.<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nSay hi to the world. Use tools to do so.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n[greet_everyone(url=\"world\")]<|eot_id|><|start_header_id|>ipython<|end_header_id|>\n\nHello, world!<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"options": {
"temperature": 0.0
},
"stream": true
},
"endpoint": "/api/generate",
"model": "llama3.2:3b-instruct-fp16"
},
"response": {
"body": [
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-09-27T18:05:56.663224Z",
"done": false,
"done_reason": null,
"total_duration": null,
"load_duration": null,
"prompt_eval_count": null,
"prompt_eval_duration": null,
"eval_count": null,
"eval_duration": null,
"response": "How",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-09-27T18:05:56.706706Z",
"done": false,
"done_reason": null,
"total_duration": null,
"load_duration": null,
"prompt_eval_count": null,
"prompt_eval_duration": null,
"eval_count": null,
"eval_duration": null,
"response": " can",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-09-27T18:05:56.751075Z",
"done": false,
"done_reason": null,
"total_duration": null,
"load_duration": null,
"prompt_eval_count": null,
"prompt_eval_duration": null,
"eval_count": null,
"eval_duration": null,
"response": " I",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-09-27T18:05:56.794187Z",
"done": false,
"done_reason": null,
"total_duration": null,
"load_duration": null,
"prompt_eval_count": null,
"prompt_eval_duration": null,
"eval_count": null,
"eval_duration": null,
"response": " assist",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-09-27T18:05:56.837831Z",
"done": false,
"done_reason": null,
"total_duration": null,
"load_duration": null,
"prompt_eval_count": null,
"prompt_eval_duration": null,
"eval_count": null,
"eval_duration": null,
"response": " you",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-09-27T18:05:56.879926Z",
"done": false,
"done_reason": null,
"total_duration": null,
"load_duration": null,
"prompt_eval_count": null,
"prompt_eval_duration": null,
"eval_count": null,
"eval_duration": null,
"response": " further",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-09-27T18:05:56.92182Z",
"done": false,
"done_reason": null,
"total_duration": null,
"load_duration": null,
"prompt_eval_count": null,
"prompt_eval_duration": null,
"eval_count": null,
"eval_duration": null,
"response": "?",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-09-27T18:05:56.963339Z",
"done": true,
"done_reason": "stop",
"total_duration": 492973041,
"load_duration": 103979375,
"prompt_eval_count": 482,
"prompt_eval_duration": 87032041,
"eval_count": 8,
"eval_duration": 300586375,
"response": "",
"thinking": null,
"context": null
}
}
],
"is_streaming": true
}
}