Alvis 3ae1cefbd4 WeatherTool: fetch open-meteo directly, skip LLM for fast tool replies ...

- Replace SearXNG search with direct open-meteo.com API call (no key needed)
- WeatherTool now returns a ready-to-deliver reply string
- agent.py: short-circuit router+LLM when fast tools return a result (tier=fast)
- router.py: fast tool match no longer triggers light reply generation

Weather latency: 105-190s → ~1s

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-03-15 09:42:55 +00:00

.claude/rules

Restructure CLAUDE.md per official Claude Code recommendations

2026-03-13 07:19:09 +00:00

grammy

wiki search people tested pipeline

2026-03-05 11:22:34 +00:00

openmemory

Split CLAUDE.md per official Claude Code recommendations

2026-03-13 07:15:51 +00:00

routecheck

Split CLAUDE.md per official Claude Code recommendations

2026-03-13 07:15:51 +00:00

tests

Add real-time query handling: pre-search enrichment + routing fix

2026-03-13 05:08:08 +00:00

.gitignore

Integrate Bifrost LLM gateway, add test suite, implement memory pipeline

2026-03-12 13:50:12 +00:00

agent_factory.py

Integrate Bifrost LLM gateway, add test suite, implement memory pipeline

2026-03-12 13:50:12 +00:00

agent.py

WeatherTool: fetch open-meteo directly, skip LLM for fast tool replies

2026-03-15 09:42:55 +00:00

ARCHITECTURE.md

Update docs: fast tools, routecheck service, commute tool

2026-03-13 07:10:30 +00:00

bifrost-config.json

Integrate Bifrost LLM gateway, add test suite, implement memory pipeline

2026-03-12 13:50:12 +00:00

channels.py

wiki search people tested pipeline

2026-03-05 11:22:34 +00:00

CLAUDE.md

Restructure CLAUDE.md per official Claude Code recommendations

2026-03-13 07:19:09 +00:00

cli.py

Add Rich token streaming: server SSE + CLI live display + CLI container

2026-03-12 17:26:52 +00:00

docker-compose.yml

Add routecheck service and CommuteTool fast tool

2026-03-13 07:08:48 +00:00

Dockerfile

Add routecheck service and CommuteTool fast tool

2026-03-13 07:08:48 +00:00

Dockerfile.cli

Add Rich token streaming: server SSE + CLI live display + CLI container

2026-03-12 17:26:52 +00:00

fast_tools.py

WeatherTool: fetch open-meteo directly, skip LLM for fast tool replies

2026-03-15 09:42:55 +00:00

hello_world.py

wiki search people tested pipeline

2026-03-05 11:22:34 +00:00

langgraph.md

wiki search people tested pipeline

2026-03-05 11:22:34 +00:00

potential-directions.md

Switch extraction model to qwen2.5:1.5b, fix mem0migrations dims, update tests

2026-02-23 05:11:29 +00:00

pytest.ini

Integrate Bifrost LLM gateway, add test suite, implement memory pipeline

2026-03-12 13:50:12 +00:00

reasoning.md

wiki search people tested pipeline

2026-03-05 11:22:34 +00:00

router.py

WeatherTool: fetch open-meteo directly, skip LLM for fast tool replies

2026-03-15 09:42:55 +00:00

vram_manager.py

Add three-tier model routing with VRAM management and benchmark suite

2026-02-28 17:54:51 +00:00

wiki_research.py

wiki search people tested pipeline

2026-03-05 11:22:34 +00:00

Description

Persistent AI assistant (Telegram, GPU, memory)

493 KiB

Languages

Python 98.9%

JavaScript 0.7%

Dockerfile 0.4%