phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-11 05:38:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(tests): make inference_recorder into api_recorder (include tool_invoke) (#3403)

Browse source 
Renames `inference_recorder.py` to `api_recorder.py` and extends it to
support recording/replaying tool invocations in addition to inference
calls.

This allows us to record web-search, etc. tool calls and thereafter
apply recordings for `tests/integration/responses`

## Test Plan

```
export OPENAI_API_KEY=...
export TAVILY_SEARCH_API_KEY=...

./scripts/integration-tests.sh --stack-config ci-tests \
   --suite responses --inference-mode record-if-missing
```
This commit is contained in:
Ashwin Bharambe 2025-10-09 14:27:51 -07:00 • committed by GitHub
parent 26fd5dbd34
commit f50ce11a3b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
284 changed files with 296191 additions and 631 deletions
Download patch file Download diff file Expand all files Collapse all files

8
docs/docs/contributing/testing/record-replay.mdx
View file

@ -68,7 +68,9 @@ recordings/
Direct API calls with no recording or replay:
```python
with inference_recording(mode=InferenceMode.LIVE):
from llama_stack.testing.api_recorder import api_recording, APIRecordingMode
with api_recording(mode=APIRecordingMode.LIVE):
response = await client.chat.completions.create(...)
```
@ -79,7 +81,7 @@ Use for initial development and debugging against real APIs.
Captures API interactions while passing through real responses:
```python
with inference_recording(mode=InferenceMode.RECORD, storage_dir="./recordings"):
with api_recording(mode=APIRecordingMode.RECORD, storage_dir="./recordings"):
response = await client.chat.completions.create(...)
# Real API call made, response captured AND returned
```
@ -96,7 +98,7 @@ The recording process:
Returns stored responses instead of making API calls:
```python
with inference_recording(mode=InferenceMode.REPLAY, storage_dir="./recordings"):
with api_recording(mode=APIRecordingMode.REPLAY, storage_dir="./recordings"):
response = await client.chat.completions.create(...)
# No API call made, cached response returned instantly
```