- Add build_distance() method to MeshReporter
- Uses _haversine_km() for GPS distance calculation
- Formats output with both km and miles
- Handles missing nodes or GPS positions gracefully
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add max_response_tokens config (8192) to LLMConfig
- Use config value in router.py instead of hardcoded 500
- Update base.py default from 300 to 8192
- Lets LLM generate full responses; chunker handles size limits
Fixes truncated responses like Here are three nodes in the freq
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
These methods were called by commands/health.py and main.py but missing
from mesh_reporter.py, causing crashes on !health and !region commands.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Added hops_away to Connectivity section in node detail
- Added nearest infra distance after Position in node detail
- Added distance from reference infra to single-gw client listings
- Added _haversine_km and _format_distance helper functions
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Single-gateway nodes now display "via {source_name}" to indicate
which data source they depend on. This helps identify coverage gaps
and understand node visibility.
Adds source info to:
- Tier 1 region summary (infra and client nodes)
- Node distribution section (infrastructure nodes)
- Region detail view (single gateway list)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Coverage:
- Single-gateway infra nodes named as critical risks per region
- Client single-gw nodes counted but not individually named
- Mesh-wide single-gw infra summary
Monitoring rules by node type:
- Infrastructure: full detail - battery, offline, coverage, neighbors, hardware
- Clients causing problems: named - high util, top senders
- Clients otherwise: counted per region, not individually tracked
- POWER breakdown now infra-only
Commands:
- Removed hardcoded command list from config.py system_prompt
- Dynamic command list in router.py from dispatcher (only enabled commands)
- MeshMonitor commands no longer listed as MeshAI commands
- !help overhaul: grouped by category, per-command detailed help
- LLM explicitly told to only mention listed commands
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Tier 1 now includes:
- Every infrastructure node BY NAME per region with status/battery/util/gateways
- Problem nodes section: offline infra, critical battery, high util, coverage risks
- Per-region coverage with gateway counts and single-gw counts
- Environmental data per region
- All 5 pillars with weights
- Expanded recommendations with specifics (10 max, up from 5)
- LLM prompt simplified: data speaks for itself
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Added CRITICAL instruction to keep sentences under 150 chars
- Chunker now splits long sentences at word boundaries instead of truncating
- No words lost when splitting
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Line 763: REGION_CONTEXT.get() → self._region_context() (same method used elsewhere)
- Deleted _CITY_TO_REGION hardcoded dict
- Scope detection now uses config aliases/cities from RegionAnchor
- Fixed Sun Valley/Ketchum geography (was Central ID, should be South Central ID)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Extended RegionAnchor with local_name, description, aliases, cities
- Moved region geographic context from hardcoded Python to config.yaml
- Added 7-day stale node purge in _do_refresh (556 → 267 nodes)
- Fixed coverage lookup: str(node_num) → node_num (int key)
- Added bidirectional neighbor lookup for better region assignment
- Dynamic geography building in router from config
- Reporter reads region context from config instead of hardcoded dict
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Magic Valley, Treasure Valley, Panhandle, Dixie — local names in all output
- Southern Idaho correctly maps to Magic Valley, not lumped with Boise/IF
- Unlocated nodes excluded from coverage gap recommendations
- LLM response rules override brevity for mesh questions
- Node detail shows region with local context
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
NodeHealth is gone. MeshHealth.nodes is now dict[int, UnifiedNode].
Reporter reads all fields from UnifiedNode: coverage, environment,
neighbors, hw_model — everything available without cross-referencing.
This eliminates the entire category of field missing on NodeHealth bugs.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Update HealthScore with coverage pillar (20% weight)
- Adjust weights: Infra 30%, Util 25%, Coverage 20%, Behavior 15%, Power 10%
- Add coverage metrics: avg_gateways, single_gw_count, full_count
- Add health score fields to UnifiedNode for direct sync
- compute() now syncs scores back to UnifiedNode objects
- Coverage scoring penalizes single-gateway nodes
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Health engine stores node IDs as decimal strings, but UnifiedNode.node_num
is an integer. The lookup health.nodes.get(n.node_num) was failing, causing
all nodes to show as Unlocated. Fixed by converting to string first.
- Show per-region coverage stats in tier1 summary
- List single-gateway nodes in region detail
- Add coverage status to node detail view
- Add coverage gap recommendations
Replaces broken per-packet gateway sampling with node-level source counting.
Each Meshview/MeshMonitor source represents a gateway view of the mesh.
If a node is seen by N sources, its packets are reaching N gateways.
- Removed _sample_gateway_coverage() (required non-existent API)
- Rewrote _enrich_deliverability() to use node.sources count
- Per-node: avg_gateways, max_gateways, source_reach, deliverability_score
- Mesh-wide: avg 4.16 gateways/node with 7 sources
- Fixed edge.timestamp -> edge.last_seen in get_all_edges()
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add hasattr check for fetch_recent_packets in gateway sampling
- Add get_all_nodes(), get_all_telemetry(), get_all_packets(), get_all_edges() methods
- These methods return data in dict format expected by mesh_health.py
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Create subscriptions.py with SubscriptionManager class for SQLite storage
- Add subscribe.py commands: !sub, !unsub, !mysubs with aliases
- Update dispatcher.py to register subscription commands
- Modify main.py with scheduler tick (60s) and _check_scheduled_subs()
- Add build_node_compact() and build_region_compact() to mesh_reporter.py
- Support daily, weekly, and alerts subscription types
- Support mesh, region, and node scope filtering
- 5-minute matching window for schedule tolerance
- Dedup via last_sent tracking
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Removed SNR-required filter from !neighbors command
- Show all infra neighbors, add signal quality when available
- Enrich edges with SNR from traceroute snrTowards/snrBack data
- Fallback: use node-level SNR for edges without traceroute data
- Sort by SNR when available, alphabetically otherwise
Co-Authored-By: Claude <noreply@anthropic.com>
Root cause: health engine keyed nodes by database row IDs instead of
Meshtastic node numbers. Packets and telemetry could never match.
Fixed:
- Store _node_num on all normalized nodes (mesh_sources.py)
- Key health engine node dict by _node_num (mesh_health.py)
- Fix packet field names: from_node not from/fromId
- Fix telemetry parsing: handle telemetryType/value structure
- Increase packet/telemetry fetch limits for 24h coverage
- Fix utilization formula to compute actual airtime percentage
- router.py: Fixed region scope detection to match longest region name first
- router.py: Added region abbreviations (SCID, SWID, etc.) for quick matching
- router.py: Added city name mapping (Boise -> South Western ID, etc.)
- router.py: Fixed node longname matching (case-insensitive substring)
- router.py: Added follow-up message context tracking (_user_mesh_context)
- router.py: Added more mesh keywords (noisy, traffic, packets, etc.)
- mesh_reporter.py: Added disambiguation for duplicate shortnames in region detail
- mesh_health.py: Added util_data_available flag to track packet data presence
- mesh_health.py: Passes has_packet_data through score computation
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add _normalize_node() function to mesh_sources.py that standardizes:
- Role field: Map integer enums to string names using correct Meshtastic
protobuf values (0=CLIENT, 1=CLIENT_MUTE, 2=ROUTER, 3=ROUTER_CLIENT,
11=ROUTER_LATE, etc.). Now detects 18 infrastructure nodes.
- GPS fields: Check latitude/longitude, then last_lat/last_long (Meshview
scaled integers), then lat/lon. Filter out invalid 0,0 coordinates.
Now 238 nodes with GPS (was 201).
- Timestamps: Normalize to last_heard as epoch seconds. Handle
microseconds (last_seen_us), milliseconds, and seconds formats.
Now 527 nodes with timestamps (was 0).
- Hardware model: Prefer string hw_model over integer hwModel.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
New files:
- mesh_reporter.py: MeshReporter class for prompt injection
- build_tier1_summary(): ~500-800 token mesh health summary
- build_region_detail(): Detailed region breakdown
- build_node_detail(): Single node info with recommendations
- build_recommendations(): Optimization suggestions
- build_lora_compact(): Short format for LoRa messages
- list_regions_compact(): Region list with scores
- commands/health.py: !health and !region commands
- !health: Quick mesh summary (no LLM)
- !region [name]: Region info or list all regions
Modified files:
- router.py: Mesh question detection and prompt injection
- _is_mesh_question(): Keyword/phrase matching
- _detect_mesh_scope(): Node/region/mesh scope detection
- Inject Tier 1/2 data for mesh questions
- Add mesh awareness instructions to LLM
- main.py: Create MeshReporter, pass to dispatcher/router
- commands/dispatcher.py: Register health/region commands
- mesh_health.py: Fix role type (int -> str)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add _extract_node_num() helper to normalize node IDs across formats
- Add _normalize_edge_key() helper for undirected edge deduplication
- Update get_all_nodes() to deduplicate by nodeNum with _sources field
- Update get_all_edges() to deduplicate by sorted (from, to) tuple
- Update get_all_telemetry() to deduplicate by (nodeNum, timestamp)
- Add get_dedup_stats() method for raw vs dedup counts
- Add get_stats_by_source() method for per-source statistics
- Change _source field to _sources (list) for multi-source tracking
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
10 regions covering Idaho and Utah:
- Northern ID (Coeur d alene)
- Central ID (Salmon)
- South Western ID (Boise)
- South Central ID (Twin Falls)
- South Eastern ID (Idaho Falls)
- Northern UT (Ogden)
- Central UT (Salt Lake City)
- Eastern UT (Vernal)
- Western UT (Tooele)
- Southern UT (St. George)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Nodes without GPS can be assigned to a region based on their
neighbors. Uses edge data to build neighbor graph, then assigns
unlocated nodes to the most common region among their neighbors.
Iterates until no more assignments possible.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Regions are now user-defined anchor points (name + lat/lon)
- Nodes assigned to nearest region, no distance limits
- Removed auto-naming and region_labels/infra_overrides
- Added Idaho region defaults in TUI
- Simpler, deterministic, user-controlled
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- last_lat/last_long are scaled integers (divide by 1e7)
- last_seen_us is in microseconds (divide by 1e6)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Meshview API returns {"nodes": [...]} and {"edges": [...]} wrapper
dicts, not raw lists. Added _extract_list() helper to unwrap.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds MeshAI/x.x User-Agent for good API citizenship and easier
traffic identification by Meshview/MeshMonitor operators.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implements mesh intelligence with geo clustering, four-pillar health scoring,
and auto-naming regions from GPS data.
New: geo.py, mesh_health.py
Modified: config.py, main.py, router.py, configurator.py, config.example.yaml
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add MeshviewSource class for fetching nodes, edges, stats from Meshview API
- Add MeshMonitorDataSource class for fetching nodes, channels, telemetry,
traceroutes, network stats, topology, packets, solar from MeshMonitor API
- Add MeshSourceManager for managing multiple sources with aggregation
- Add MeshSourceConfig dataclass and mesh_sources list to config
- Integrate source_manager into main.py with periodic refresh
- Add source_manager parameter to MessageRouter (for future Phase 3)
- Add Mesh Sources TUI menu with add/edit/remove/test functionality
- Update config.example.yaml with mesh_sources section
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add MeshMonitor Integration section with features and configuration
- Add credit line in Features list
- Link to github.com/Yeraze/meshmonitor
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Build system prompt dynamically using bot.name and bot.owner from config
- Reorder prompt: identity -> static prompt -> MeshMonitor (conditional) -> mesh context
- MeshMonitor description only injected when meshmonitor.enabled is true
- Update default system_prompt to static parts only (commands, architecture, rules)
- Fix meshmonitor.py to handle trigger arrays (not just strings)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
