feat: CPU reasoner bake-off for Qwen3.5-9B vs Bonsai (#25)
Tests / Test (push) Failing after 5s
Tests / Release (semver) (push) Skipped

Measure OpenAI tool_calls (search/get/audit) on a CPU Ollama sidecar
instead of gating D18 on GPU or PicoClaw. Weights stay out of the image.
This commit is contained in:
2026-08-13 23:19:51 +01:00
committed by GitHub
co-authored by GitHub
parent e393cc6a99
commit bb272d7416
13 changed files with 717 additions and 3 deletions
+1
View File
@@ -158,6 +158,7 @@ Docker (optional, cached model + var volumes):
docker compose up -d brain # API (Zig CGO serve :8630)
docker compose --profile index run --rm index # Python Ladybug rebuild
docker compose --profile picoclaw up brain-mcp # MCP on 127.0.0.1:8630
docker compose --profile reasoner up -d reasoner # CPU Ollama 127.0.0.1:11435
docker compose up brain-watch # auto re-index on change
```