trentuna/candle-annotator
8
0
Fork 0
Code Issues Pull requests Releases Packages Activity Actions

fix(ml): add _model_swap_lock to prediction reads for thread-safe model access

Browse source 
In /predict and /predict/batch endpoints, grab the model reference under
_model_swap_lock before running inference. Inference itself runs outside
the lock (using a local variable) to avoid blocking model swaps during
potentially slow computation.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Marko Djordjevic 2026-02-18 11:26:33 +01:00
parent ff15adc847
commit b9beea1574
2 changed files with 56 additions and 34 deletions
Download patch file Download diff file Expand all files Collapse all files

2
openspec/changes/code-review-fix/tasks.md
View file

@ -43,7 +43,7 @@
- [x] 5.1 `[sonnet]` Replace `error.message` / traceback details with generic `"Internal server error"` in FastAPI exception handlers at lines 640, 778, 1091, 1134, 1199, 1296 of `services/ml/app/main.py`
- [x] 5.2 `[opus]` Add SHA256 model integrity check: create `models/checksums.sha256` manifest, verify hash before `joblib.load()` in `services/ml/app/main.py:266`
- [ ] 5.3 `[sonnet]` Add `_model_swap_lock` to prediction reads (not just writes) in `services/ml/app/main.py` for thread-safe model access
- [x] 5.3 `[sonnet]` Add `_model_swap_lock` to prediction reads (not just writes) in `services/ml/app/main.py` for thread-safe model access
- [ ] 5.4 `[sonnet]` Add date range validation (max 1 year) to `POST /predict/batch` in `services/ml/app/main.py`
- [ ] 5.5 `[sonnet]` Add candle time-sort validation/auto-sort to `POST /predict` in `services/ml/app/main.py`
- [ ] 5.6 `[sonnet]` Implement real health checks: `SELECT 1` for PostgreSQL, MLflow API ping in `services/ml/app/main.py:396-409`