887a3af84fd97582a73f589c0196e3a0cf4f09f9
4
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 whqreza
|
887a3af84f |
refactor(monitoring): move grafana into the main compose stack
Owner request: one 'docker compose up -d' should bring the whole system up —
no separate monitoring project to start for the dashboards.
- docker-compose.yml: grafana service (procurement-grafana, loopback :3001,
default+shared networks, obs datasource env) + grafana_data volume;
provisioning and dashboard JSONs stay in ./monitoring/grafana/ (no file
moves, provisioning unchanged)
- docker-compose.prod.yml: GRAFANA_ADMIN_PASSWORD forced via the existing
${VAR:?} pattern (local keeps a lenient default, prod refuses defaults)
- monitoring/docker-compose.monitoring.yml: grafana service + volume removed
(no name/port conflict); glitchtip/prometheus/loki stay server-side as before
- docs updated: grafana restarts on app deploys are harmless (settings live
in the volume); SSH-tunnel posture unchanged
Verified locally: both compose files validate; 'docker compose up -d' starts
all 10 services incl. procurement-grafana; BotPostgres datasource health OK;
all 3 dashboards provisioned in the fresh volume; monitoring compose no
longer contains grafana; old monitoring-grafana container removed; port
still loopback-only.
|
||
|
whqreza
|
cb621ca5d0 |
feat(monitoring): multi-model dashboard v2.1 — tabs, per-model records, voice playback + MinIO dual-write
Problem: the dashboard was Jev-centric; NLU/arbiter/fallback DeepSeek, STT
providers and the audio-enhancer were barely visible, and stored texts/voices
had no real access path.
Bot (additive; reply path untouched):
- nlu.result now records latency_ms + the DeepSeek usage tokens
- matching.arbitration/fallback.result fill the model + latency_ms columns
(payload unchanged; SQL coalesces column/payload so old rows still count)
- storage.py: MinIO dual-write layer — every voice (raw + denoised) and user
attachment is mirrored fire-and-forget into bucket bot-media; the blocking
minio SDK runs via asyncio.to_thread (senior-engineer review) so the event
loop is never stalled; empty MINIO_* env = layer off; bucket auto-created
- requirements: minio>=7.2
Backend (admin-gated, read-only):
- GET /bot-metrics/models — one record per model (jev, deepseek-nlu,
deepseek-arbiter, deepseek-fallback, audio-enhancer + dynamic per-provider
STT) with calls/ok-rate/p50/p95/tokens/last-seen + version-drift vs the pin
- GET /bot-metrics/models/{id}/daily — per-model daily calls/fails/tokens/p50
- GET /bot-metrics/stages — every stage tagged with its Persian pipeline
section (صوت/درک پیام/تطبیق/ابهام و انتخاب/پیشنویس)
- /traces now carries input_kind + a 120-char text excerpt (consensus →
input.text → first STT transcript)
- media serving: POST /media-url mints a short-lived HMAC URL (audio/a tags
cannot send Authorization); GET /media streams from MinIO bot-media with
the read-only ./bot/data mount as fallback for pre-MinIO files; hard ref
validation (voices|attachments only, no .., extension whitelist)
- router exempted from the global Bearer dependency (files.py pattern) —
every endpoint keeps its own require_role('admin')
Frontend /bot-monitor (RTL, recharts):
- four tabs: نمای کلی / مدلها (records table + per-model expandable daily
charts: calls/fails, tokens, p50) / بخشها (sections grouped) / پیامها
- message drawer rebuilt: inline <audio controls> for raw + denoised voice,
download links, every STT transcript + consensus side-by-side, user
attachments, then the event timeline
- terminology: «ترس» → «پروندهی پیام» with tooltips + a one-line legend
Grafana: bot-observability gains a «کارکرد مدلها» table (stage→model
mapping for legacy rows); the explorer gains a message text column.
Seed: real (tiny) ogg files written + mirrored to MinIO, NLU usage tokens,
column-level model/latency on matching events.
Verified locally: /models returns all 7 records incl. per-STT and NLU tokens;
media 200 via signed URL (MinIO) and 401 without; ../ and .py rejected (400);
disk fallback serves a legacy file; pm-role 403 on every new endpoint;
bucket auto-created with 14 mirrored objects; tsc + vite build clean;
Grafana re-provisions 24 panels.
|
||
|
whqreza
|
0adadd2cf8 |
feat(monitoring): bot observability dashboards — Grafana + Persian RTL ERP page
Grafana (full use of the existing monitoring/ stack, per OSS policy):
- datasources.yml: BotPostgres (uid bot-postgres) over the shared network;
grafana service joins 'shared' + carries the datasource env
- db_init.py: idempotent read-only role obs_reader (USAGE on schema public +
SELECT on bot_traces/bot_trace_events; skipped when
OBS_READER_PASSWORD empty; ALTER ROLE for rotation) + composite index
ix_bot_trace_events_stage_time (stage, created_at DESC) — senior-engineer
review applied with the column-name fix (event_type -> stage); (trace_id)
already covered by the existing (trace_id, created_at) index
- dashboards/bot-observability.json: KPI row (real traffic, events, Jev/
fallback errors, Jev p95, tokens, commits, archive guard), events/day,
per-stage p50/p95, mention statuses (arbiter+fallback aggregates + legacy
rows), DeepSeek arbiter actions, tokens/day, model-drift vs jev-1.13.0,
user-choice A/B, STT + audio.enhance health, archive size guard
- dashboards/bot-trace-explorer.json: trace table + full event drill-down
via the trace_id variable
ERP page (admin-only, Persian RTL, recharts@^3 for React 19):
- backend bot_metrics.py: read-only require_role('admin') endpoints
(summary/routing/quality/jev/stt/traces + trace detail); aggregates count
real traffic only (calibration/demo/chat_id=0 excluded)
- frontend BotMonitorPage at /bot-monitor (KPI cards, daily events,
status donut, arbiter actions, user-choice A/B, STT/enhance tables,
stage latency, tokens chart, traces table + detail drawer with payload
viewer); entry link from the admin panel; MobileTabBar hidden there
- api.ts: typed botMetrics client section
Tooling/docs:
- tools/seed_observability_demo.py: deterministic demo traces (source='demo',
every current pipeline stage incl. audio.enhance/jev.failure/arbitration/
fallback/user choices) — excluded from real-traffic aggregates
- monitoring/README.md + bot/docs/DEPLOY-AND-MONITORING.md: setup, seed and
rollback notes; alerts deliberately deferred (owner decision 2026-10-24)
Verified locally: obs_reader SELECT ok / INSERT denied; panels' SQL run as
obs_reader with data; datasource health OK; both dashboards survive a grafana
restart; endpoints 200 as admin and 403 without role; tsc + vite build clean;
page renders in-browser (admin session); bot startup provisions role+index.
|
||
|
whqreza
|
b44816aa98 |
feat(bot): phase-7 monitoring digest + deploy checklist
- tools/monitor.py: weekly SQL digest over bot_traces/bot_trace_events — pipeline funnel, Jev health (failures/latency/tokens/model drift vs pinned jev-1.13.0), user-choice quality proxy (Jev↔user A/B), difflib fallback volume, STT provider health, and the plan-§4.5 archive guard (>5GB or >100k events/month -> «archive, do not delete» session); real-traffic only by default (calibration/test traces excluded, --include-calibration shows all); writes markdown to data/reports/; --check exits 1 on warnings - docs/DEPLOY-AND-MONITORING.md: deploy checklist — server env vars (TypeSafe key via Coolify env or bot/.env), recreate-not-restart for new mounts, single-Bale-poller rule, smoke tests per plan §7.12, one-env rollback (JEV_ENABLED/OBS_ENABLED=false); bot server deployment deliberately stays an owner decision (no service added to the Coolify compose) |