Phase 0 go-live polish: hands-off incremental sync + refresh action

- backend/ingest/sync_scheduler.py: periodic incremental-sync loop (every
  CRM_INGEST_SYNC_INTERVAL_MIN min); resilient, --once for testing.
- start9/0.4: "Refresh search index" action (incremental sync.py); entrypoint
  launches the scheduler as a background process when Spark/Qdrant are set;
  CRM_INGEST_SYNC_INTERVAL_MIN env; pre-release note on fastembed/mcp pins.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Keysat
2026-06-05 09:36:06 -05:00
parent f357c23c75
commit 6be2e40f54
6 changed files with 298 additions and 19 deletions
+8
View File
@@ -38,6 +38,14 @@ RUN apt-get update \
# (backend/ingest/sparse.py auto-detects it).
# * mcp — MCP Python SDK, only needed to run backend/mcp/server.py.
# Everything else server.py needs is stdlib.
#
# ⚠️ PRE-RELEASE — VERIFY THESE PINS BUILD ON BOTH ARCHES BEFORE RELEASE ⚠️
# fastembed==0.4.2 and mcp==1.2.0 were pinned best-effort and have NOT been
# confirmed to build on both x86_64 AND aarch64 (StartOS runs arm64). fastembed
# in particular pulls onnxruntime (no wheel on some arches → source build) and
# downloads a model on first use. Build the image on aarch64 and run the ingest
# once to confirm before cutting a release. See INGEST_PACKAGING.md "Pre-release
# checks". Do not bump these without re-verifying on both arches.
RUN pip install --no-cache-dir \
cryptography==42.0.5 \
fastembed==0.4.2 \