Four-part implementation:
- Part 1: TLE cache handler subscribes central.sat.tle.>, upserts latest-wins
on epoch, 14-day staleness exclusion at read time (tle_handler.py)
- Part 2: SGP4 pass predictor with 30s step propagation, ECI→topocentric
look angles, grouped into PassInfo objects (pass_predictor.py)
- Part 3: ZCTA centroid CSV vendored (33,144 ZIPs), lazy-loaded for
ZIP→lat/lon lookup with no runtime network dependency
- Part 4: !satpass command with three forms: bare (adapter_config defaults),
name/NORAD ID, ZIP code observer. Location chain: GPS→ZIP→ask.
Reply formatted as 'ISS 09:36-09:43 MDT max 64deg SW->NE'
Schema v16→v17 (sat_tles table). sgp4>=2.22 added to requirements.
24 new tests covering TLE upsert/staleness, pass prediction reference,
ZCTA lookup, command routing, location chain, and reply format.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
First per-adapter content formatter in the meshai-side central_normalizer library (per Central response to schema-divergence + nearest-town reports). state_511_atis (94% of Idaho 511 work-zone traffic) now produces clean wire strings like "🚧 SH-55, near McCall: both directions, emergency repairs" instead of the previous "🚧 ROADS: Work Zone, US-ID. routine -- roadwork".
Implementation: nearest_town(lat, lon) calls Photon directly at 100.64.0.24:2322/reverse with osm_tag=place + client-side filter for city/town/village/hamlet (Navi passthrough route documented in Central response does not exist on current Navi instance). H3-cell-7 LRU cache. Town fallback chain: _enriched.geocoder.city -> nearest_town(coords) -> drop segment. Composer bypass via event.data["_meshai_precomposed"] flag -- renderer owns full wire string for normalized events. SB->S route normalization. distance<1mi -> "near X".
Tests: 535 passed (was 511, +24 net). Synthetic probe over 25 bucket-B + 8 fixture envelopes confirmed 23/25 + 8/8 produce clean output; 2/25 fell back to None (drop segment) on Photon index gaps near Boise/Cascade. Matt eyeballed and approved.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- FastAPI runs in MeshAI asyncio loop (no separate process)
- REST API: /api/status, /api/health, /api/nodes, /api/edges,
/api/regions, /api/sources, /api/config, /api/alerts
- WebSocket at /ws/live pushes health updates and alerts
- Config CRUD: GET/PUT per section with validation and save
- DashboardConfig with port/host in config.yaml
Features:
- Multi-backend LLM support (OpenAI, Anthropic, Google)
- Rolling summary memory for token optimization (~70-80% reduction)
- Per-user conversation history with SQLite persistence
- Bang commands (!help, !ping, !reset, !status, !weather)
- Meshtastic integration via serial or TCP
- Message chunking for mesh network constraints (150 char limit)
- Rate limiting to prevent network congestion
- Rich TUI configurator
- Docker support
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
