feat: add orchestrator shadow observability

This commit is contained in:
john
2026-07-24 21:44:21 +08:00
parent 24336d0178
commit 3e57f85d3a
18 changed files with 992 additions and 9 deletions
+19
View File
@@ -48,6 +48,18 @@ Phase 2 adds:
- live health probing from memindadm;
- a separate Colima/Compose deployment artifact.
Phase 2.5 adds a Memind-owned Shadow observability projection:
- success/failure totals and rates;
- P50/P95 observation latency;
- Native terminal status beside the Shadow result;
- recent failure codes and messages;
- per-run LangGraph checkpoint and node-event inspection through the versioned
remote API.
The projection reads `h5_agent_run_events` from the Memind control plane.
LangGraph still has no access to Memind business tables.
The default memindadm mode remains `off`. Canary and Active routing are not
wired to the LangGraph executor in Phase 2. Native Agent Run remains the sole
executor, including in Shadow mode.
@@ -84,6 +96,13 @@ MEMIND_ORCHESTRATOR_CHECKPOINT_MODE=memory pnpm dev:orchestrator
The service binds to `127.0.0.1:8093` by default. Configure the same URL and
service token in Portal, then enable `shadow` in `/ops/admin/orchestrator`.
memindadm exposes the projection through:
```text
GET /admin-api/orchestrator/shadow-runs
GET /admin-api/orchestrator/shadow-runs/:runId
```
## Colima deployment
Colima is the recommended first container host on macOS because this service and