phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-12 04:50:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(ci): use replay mode, setup ollama if specific label exists on PR (#2955)

Browse source 
This PR makes setting up Ollama optional for CI. By default, we use
`replay` mode for inference requests and use the stored results from the
`tests/integration/recordings/` directory.

Every so often, users will update tests which will need us to re-record.
To do this, we check for the existence of a label `re-record-tests` on
the PR. If detected,
- ollama is spun up
- inference mode is set to record
- after the tests are done, if any new changes are detected, they are
pushed back to the PR

## Test Plan

This is GitHub CI. Gotta test it live.
This commit is contained in:
Ashwin Bharambe 2025-07-29 16:50:26 -07:00 • committed by GitHub
parent 0ac503ec0d
commit b237df8f18
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
11 changed files with 1519 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

BIN
tests/integration/recordings/index.sqlite
View file

Binary file not shown.

167
tests/integration/recordings/responses/0ff78129bb3a.json Normal file
View file

@ -0,0 +1,167 @@
{
"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\": \"\nReturns 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\", \"celsius\"],\n \"properties\": {\n \"liquid_name\": {\n \"type\": \"string\",\n \"description\": \"\"\n },\n \"celsius\": {\n \"type\": \"boolean\",\n \"description\": \"\"\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": "2025-07-29T23:26:18.143606Z",
"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": "2025-07-29T23:26:18.186151Z",
"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": "2025-07-29T23:26:18.229036Z",
"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": "2025-07-29T23:26:18.271516Z",
"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": "2025-07-29T23:26:18.316272Z",
"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": "2025-07-29T23:26:18.361005Z",
"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": "2025-07-29T23:26:18.404689Z",
"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": "2025-07-29T23:26:18.447699Z",
"done": true,
"done_reason": "stop",
"total_duration": 456939083,
"load_duration": 79653292,
"prompt_eval_count": 471,
"prompt_eval_duration": 71724667,
"eval_count": 8,
"eval_duration": 304859000,
"response": "",
"thinking": null,
"context": null
}
}
],
"is_streaming": true
}
}

185
tests/integration/recordings/responses/4597743bcd2a.json Normal file
View file

@ -0,0 +1,185 @@
{
"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\": \"\nReturns 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\", \"celsius\"],\n \"properties\": {\n \"liquid_name\": {\n \"type\": \"string\",\n \"description\": \"\"\n },\n \"celsius\": {\n \"type\": \"boolean\",\n \"description\": \"\"\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",
"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": "2025-07-29T23:26:17.476678Z",
"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": "[g",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:26:17.520346Z",
"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": "reet",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:26:17.563375Z",
"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": "_every",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:26:17.606256Z",
"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": "one",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:26:17.649215Z",
"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": "(url",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:26:17.692049Z",
"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": "2025-07-29T23:26:17.734316Z",
"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": "world",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:26:17.776615Z",
"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": "2025-07-29T23:26:17.819266Z",
"done": true,
"done_reason": "stop",
"total_duration": 5629478417,
"load_duration": 4092162625,
"prompt_eval_count": 448,
"prompt_eval_duration": 1191158583,
"eval_count": 9,
"eval_duration": 343915792,
"response": "",
"thinking": null,
"context": null
}
}
],
"is_streaming": true
}
}

2
tests/integration/recordings/responses/4a3a4447b16b.json
View file

@ -14,7 +14,7 @@
"models": [
{
"model": "nomic-embed-text:latest",
"modified_at": "2025-07-29T14:55:45.755906-07:00",
"modified_at": "2025-07-29T16:46:26.304701-07:00",
"digest": "0a109f422b47e3a30ba2b10eca18548e944e8a23073ee3f3e947efcf3c45e59f",
"size": 274302450,
"details": {

347
tests/integration/recordings/responses/9c28ec9ac338.json Normal file
View file

@ -0,0 +1,347 @@
{
"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\", \"celsius\"],\n \"properties\": {\n \"liquid_name\": {\n \"type\": \"string\",\n \"description\": \"\"\n },\n \"celsius\": {\n \"type\": \"boolean\",\n \"description\": \"\"\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\nHow can I assist you further?<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nWhat is the boiling point of polyjuice? Use tools to answer.<|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": "2025-07-29T23:46:36.316207Z",
"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": "2025-07-29T23:46:36.358611Z",
"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": "get",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:46:36.401272Z",
"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": "_bo",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:46:36.444321Z",
"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": "iling",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:46:36.48795Z",
"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": "_point",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:46:36.530158Z",
"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": "2025-07-29T23:46:36.573318Z",
"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": "liquid",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:46:36.616297Z",
"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": "_name",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:46:36.659527Z",
"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": "2025-07-29T23:46:36.702422Z",
"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": "poly",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:46:36.745894Z",
"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": "ju",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:46:36.788811Z",
"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": "ice",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:46:36.831618Z",
"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": "2025-07-29T23:46:36.874469Z",
"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": " c",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:46:36.917372Z",
"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": "elsius",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:46:36.960558Z",
"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": "=True",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:46:37.004223Z",
"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": "2025-07-29T23:46:37.046563Z",
"done": true,
"done_reason": "stop",
"total_duration": 845522667,
"load_duration": 47784875,
"prompt_eval_count": 511,
"prompt_eval_duration": 66135292,
"eval_count": 18,
"eval_duration": 730999291,
"response": "",
"thinking": null,
"context": null
}
}
],
"is_streaming": true
}
}

167
tests/integration/recordings/responses/bd356b27a085.json Normal file
View file

@ -0,0 +1,167 @@
{
"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\", \"celsius\"],\n \"properties\": {\n \"liquid_name\": {\n \"type\": \"string\",\n \"description\": \"\"\n },\n \"celsius\": {\n \"type\": \"boolean\",\n \"description\": \"\"\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": "2025-07-29T23:46:35.850399Z",
"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": "2025-07-29T23:46:35.89419Z",
"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": "2025-07-29T23:46:35.938049Z",
"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": "2025-07-29T23:46:35.980392Z",
"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": "2025-07-29T23:46:36.023004Z",
"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": "2025-07-29T23:46:36.065467Z",
"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": "2025-07-29T23:46:36.108189Z",
"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": "2025-07-29T23:46:36.150902Z",
"done": true,
"done_reason": "stop",
"total_duration": 468910417,
"load_duration": 93969000,
"prompt_eval_count": 479,
"prompt_eval_duration": 72596750,
"eval_count": 8,
"eval_duration": 301590375,
"response": "",
"thinking": null,
"context": null
}
}
],
"is_streaming": true
}
}

347
tests/integration/recordings/responses/c7582fa7c2c4.json Normal file
View file

@ -0,0 +1,347 @@
{
"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\": \"\nReturns 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\", \"celsius\"],\n \"properties\": {\n \"liquid_name\": {\n \"type\": \"string\",\n \"description\": \"\"\n },\n \"celsius\": {\n \"type\": \"boolean\",\n \"description\": \"\"\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\nHow can I assist you further?<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nWhat is the boiling point of polyjuice? Use tools to answer.<|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": "2025-07-29T23:26:18.64197Z",
"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": "2025-07-29T23:26:18.687885Z",
"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": "get",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:26:18.73112Z",
"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": "_bo",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:26:18.774191Z",
"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": "iling",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:26:18.816695Z",
"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": "_point",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:26:18.859121Z",
"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": "2025-07-29T23:26:18.901585Z",
"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": "liquid",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:26:18.943788Z",
"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": "_name",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:26:18.986429Z",
"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": "2025-07-29T23:26:19.029894Z",
"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": "poly",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:26:19.073113Z",
"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": "ju",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:26:19.116671Z",
"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": "ice",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:26:19.159456Z",
"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": "2025-07-29T23:26:19.203354Z",
"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": " c",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:26:19.246192Z",
"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": "elsius",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:26:19.290499Z",
"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": "=True",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:26:19.334562Z",
"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": "2025-07-29T23:26:19.380415Z",
"done": true,
"done_reason": "stop",
"total_duration": 881889250,
"load_duration": 69966916,
"prompt_eval_count": 503,
"prompt_eval_duration": 70368167,
"eval_count": 18,
"eval_duration": 740885458,
"response": "",
"thinking": null,
"context": null
}
}
],
"is_streaming": true
}
}

185
tests/integration/recordings/responses/ef757a75ed08.json Normal file
View file

@ -0,0 +1,185 @@
{
"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\", \"celsius\"],\n \"properties\": {\n \"liquid_name\": {\n \"type\": \"string\",\n \"description\": \"\"\n },\n \"celsius\": {\n \"type\": \"boolean\",\n \"description\": \"\"\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",
"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": "2025-07-29T23:46:35.212563Z",
"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": "[g",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:46:35.254896Z",
"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": "reet",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:46:35.297152Z",
"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": "_every",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:46:35.339477Z",
"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": "one",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:46:35.382245Z",
"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": "(url",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:46:35.423387Z",
"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": "2025-07-29T23:46:35.465286Z",
"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": "world",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T23:46:35.507249Z",
"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": "2025-07-29T23:46:35.549072Z",
"done": true,
"done_reason": "stop",
"total_duration": 5519843458,
"load_duration": 4110366375,
"prompt_eval_count": 456,
"prompt_eval_duration": 1070783708,
"eval_count": 9,
"eval_duration": 337120750,
"response": "",
"thinking": null,
"context": null
}
}
],
"is_streaming": true
}
}

59
tests/integration/recordings/responses/f3c3afbd9b7e.json Normal file
View file

@ -0,0 +1,59 @@
{
"request": {
"method": "POST",
"url": "http://localhost:11434/api/generate",
"headers": {},
"body": {
"model": "llama3.2:1b",
"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\": \"\nReturns 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\", \"celsius\"],\n \"properties\": {\n \"liquid_name\": {\n \"type\": \"string\",\n \"description\": \"\"\n },\n \"celsius\": {\n \"type\": \"boolean\",\n \"description\": \"\"\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",
"options": {
"temperature": 0.0
},
"stream": true
},
"endpoint": "/api/generate",
"model": "llama3.2:1b"
},
"response": {
"body": [
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:1b",
"created_at": "2025-07-29T23:23:09.553247Z",
"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": "Hi",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:1b",
"created_at": "2025-07-29T23:23:09.564069Z",
"done": true,
"done_reason": "stop",
"total_duration": 2125493250,
"load_duration": 1610279708,
"prompt_eval_count": 448,
"prompt_eval_duration": 502413125,
"eval_count": 2,
"eval_duration": 11573709,
"response": "",
"thinking": null,
"context": null
}
}
],
"is_streaming": true
}
}

11
tests/integration/tool_runtime/test_mcp.py
View file

@ -10,7 +10,6 @@ import pytest
from llama_stack_client import Agent
from llama_stack import LlamaStackAsLibraryClient
from llama_stack.apis.models import ModelType
from llama_stack.distribution.datatypes import AuthenticationRequiredError
AUTH_TOKEN = "test-token"
@ -24,7 +23,7 @@ def mcp_server():
yield mcp_server_info
def test_mcp_invocation(llama_stack_client, mcp_server):
def test_mcp_invocation(llama_stack_client, text_model_id, mcp_server):
if not isinstance(llama_stack_client, LlamaStackAsLibraryClient):
pytest.skip("The local MCP server only reliably reachable from library client.")
@ -69,14 +68,10 @@ def test_mcp_invocation(llama_stack_client, mcp_server):
assert content[0].type == "text"
assert content[0].text == "Hello, world!"
models = [
m for m in llama_stack_client.models.list() if m.model_type == ModelType.llm and "guard" not in m.identifier
]
model_id = models[0].identifier
print(f"Using model: {model_id}")
print(f"Using model: {text_model_id}")
agent = Agent(
client=llama_stack_client,
model=model_id,
model=text_model_id,
instructions="You are a helpful assistant.",
tools=[test_toolgroup_id],
)