matt/meshai
1
0
Fork 0
mirror of https://github.com/zvx-echo6/meshai.git synced 2026-05-22 07:34:47 +02:00
Code Issues Projects Releases Packages Wiki Activity
meshai/meshai
History
K7ZVX 9674e94efb Phase 2.4: LLM-summarized digest with master toggle filter 
- Remove severity-based fork; tee pattern sends all events to both dispatcher and accumulator
- Add ToggleFilter before tee; drops events for disabled toggles
- Rework DigestAccumulator: event log instead of active/resolved tracking
- render_digest now async, calls LLM once per toggle with severity-ordered events
- Fallback to count-based summary when LLM unavailable
- Add TogglesConfig to config.py for master toggle settings
- Update scheduler to await async render_digest
- 75 tests passing

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-05-15 02:37:12 +00:00
..
backends fix: Remove hard-coded token limits on LLM responses 2026-05-05 22:06:50 +00:00
cli feat: Full alert engine — 17 conditions, scaling cooldown, per-condition TUI toggles 2026-05-06 05:39:11 +00:00
commands build: normalize all line endings to LF 2026-05-14 22:43:06 +00:00
dashboard build: normalize all line endings to LF 2026-05-14 22:43:06 +00:00
env build: normalize all line endings to LF 2026-05-14 22:43:06 +00:00
notifications Phase 2.4: LLM-summarized digest with master toggle filter 2026-05-15 02:37:12 +00:00
scripts build: normalize all line endings to LF 2026-05-14 22:43:06 +00:00
sources build: normalize all line endings to LF 2026-05-14 22:43:06 +00:00
__init__.py
__main__.py
alert_engine.py refactor: simplify severity to 3 levels (routine/priority/immediate) 2026-05-13 19:05:50 -06:00
chunker.py feat: ACK-based message delivery, markdown stripping, prompt fixes 2026-05-06 04:17:44 +00:00
config.py Phase 2.4: LLM-summarized digest with master toggle filter 2026-05-15 02:37:12 +00:00
config_loader.py build: normalize all line endings to LF 2026-05-14 22:43:06 +00:00
connector.py fix: node_id int handling in connector + rule stats data path 2026-05-13 19:27:04 -06:00
context.py Add passive mesh context awareness — observe channel traffic, inject into LLM prompts 2026-02-24 22:02:42 +00:00
geo.py build: normalize all line endings to LF 2026-05-14 22:43:06 +00:00
history.py Support unlimited message history when max_messages_per_user is 0 2026-02-24 07:03:15 +00:00
knowledge.py build: normalize all line endings to LF 2026-05-14 22:43:06 +00:00
main.py feat(config): split monolithic config + extract secrets 2026-05-14 15:14:12 +00:00
memory.py
mesh_data_store.py fix: notification system improvements and threshold corrections 2026-05-14 06:03:51 +00:00
mesh_health.py fix: notification system improvements and threshold corrections 2026-05-14 06:03:51 +00:00
mesh_models.py feat: Feeder-level gateway awareness from /api/packets_seen 2026-05-05 19:55:23 +00:00
mesh_reporter.py fix: notification system improvements and threshold corrections 2026-05-14 06:03:51 +00:00
mesh_sources.py build: normalize all line endings to LF 2026-05-14 22:43:06 +00:00
meshmonitor.py build: normalize all line endings to LF 2026-05-14 22:43:06 +00:00
responder.py fix: Switch to delay-based delivery — wantAck firmware retries cause duplicates 2026-05-07 21:50:09 +00:00
router.py build: normalize all line endings to LF 2026-05-14 22:43:06 +00:00
subscriptions.py build: normalize all line endings to LF 2026-05-14 22:43:06 +00:00