feat(test): record agents, safety and vector_io integration tests (#2952)

Continue to build on top of
https://github.com/meta-llama/llama-stack/pull/2941

## Test Plan

Run server with `LLAMA_STACK_TEST_INFERENCE_MODE=record` and then run
the integration tests with `--stack-config=server:starter`. Then restart
the server with `LLAMA_STACK_TEST_INFERENCE_MODE=replay` and re-run the
tests. Verify that no request hit Ollama at any point.
This commit is contained in:
Ashwin Bharambe 2025-07-29 14:02:14 -07:00 committed by GitHub
parent 2d1ab3ca55
commit 072d20a124
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
59 changed files with 22727 additions and 9 deletions

View file

@ -0,0 +1,366 @@
{
"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\": \"get_boiling_point\",\n \"description\": \"Returns the boiling point of a liquid in Celcius or Fahrenheit.\",\n \"parameters\": {\n \"type\": \"dict\",\n \"required\": [\"liquid_name\"],\n \"properties\": {\n \"liquid_name\": {\n \"type\": \"str\",\n \"description\": \"The name of the liquid\"\n },\n \"celcius\": {\n \"type\": \"bool\",\n \"description\": \"Whether to return the boiling point in Celcius\",\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 Always respond with tool calls no matter what. <|eot_id|><|start_header_id|>user<|end_header_id|>\n\nGet the boiling point of polyjuice with a tool call.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
"options": {
"temperature": 0.0001,
"top_p": 0.9
},
"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": "2025-07-29T20:04:11.730544Z",
"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": "2025-07-29T20:04:11.776362Z",
"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": "2025-07-29T20:04:11.818895Z",
"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": "2025-07-29T20:04:11.861401Z",
"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": "2025-07-29T20:04:11.904334Z",
"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": "2025-07-29T20:04:11.946942Z",
"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": "2025-07-29T20:04:11.988807Z",
"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": "2025-07-29T20:04:12.030657Z",
"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": "2025-07-29T20:04:12.072804Z",
"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": "2025-07-29T20:04:12.115051Z",
"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": "2025-07-29T20:04:12.157568Z",
"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": "2025-07-29T20:04:12.200298Z",
"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": "2025-07-29T20:04:12.243723Z",
"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": "2025-07-29T20:04:12.286287Z",
"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": " cel",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T20:04:12.329284Z",
"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": "ci",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T20:04:12.371308Z",
"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": "us",
"thinking": null,
"context": null
}
},
{
"__type__": "ollama._types.GenerateResponse",
"__data__": {
"model": "llama3.2:3b-instruct-fp16",
"created_at": "2025-07-29T20:04:12.413286Z",
"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": "2025-07-29T20:04:12.455335Z",
"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": "2025-07-29T20:04:12.497365Z",
"done": true,
"done_reason": "stop",
"total_duration": 1007895792,
"load_duration": 128942250,
"prompt_eval_count": 376,
"prompt_eval_duration": 109187542,
"eval_count": 19,
"eval_duration": 768957125,
"response": "",
"thinking": null,
"context": null
}
}
],
"is_streaming": true
}
}