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

Browse Source

- Three-tier routing: light (router answers directly ~3s), medium (qwen3:4b
  + tools ~60s), complex (/think prefix → qwen3:8b + subagents ~140s)
- Router: qwen2.5:1.5b, temp=0, regex pre-classifier + raw-text LLM classify
- VRAMManager: explicit flush/poll/prewarm to prevent Ollama CPU-spill bug
- agent_factory: build_medium_agent and build_complex_agent using deepagents
  (TodoListMiddleware + SubAgentMiddleware with research/memory subagents)
- Fix: split Telegram replies >4000 chars into multiple messages
- Benchmark: 30 questions (easy/medium/hard) — 10/10/10 verified passing
  easy→light, medium→medium, hard→complex with VRAM flush confirmed

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

...

This commit is contained in:

Alvis

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

parent ff20f8942d

commit 09a93c661e

8 changed files with 1400 additions and 308 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

999

adolf/test_pipeline.py

File diff suppressed because it is too large Load Diff