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

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

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
}
}