phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-09 21:18:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge 8da9ff352c into 2838d5a20f

Browse source
This commit is contained in:
Ashwin Bharambe 2025-09-11 13:09:31 +02:00 • committed by GitHub
commit 736d734098
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
45 changed files with 25144 additions and 41 deletions
Download patch file Download diff file Expand all files Collapse all files

8
docs/source/contributing/testing/record-replay.md
View file

@ -58,7 +58,9 @@ 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(...)
```
@ -69,7 +71,7 @@ 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
```
@ -86,7 +88,7 @@ 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
```