feat: CPU reasoner bake-off for Qwen3.5-9B vs Bonsai (#25)
Tests / Test (push) Skipped
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 1f9bdb0bf6
commit b317968a4c
13 changed files with 717 additions and 3 deletions
+9 -1
View File
@@ -78,4 +78,12 @@ fetches Zig + libs (`bin/cgo/zig`). Index/write is still `bin/kb/index`
`bin/brain/serve.go` exposes the same `internal/httpapi.Ops` table as OpenAPI
(`GET /openapi.json`) and MCP (`POST /mcp` JSON-RPC `tools/list` +
`tools/call`). Tool names match paths: `search`, `get`, `stats`, `audit`.
Agents should use these endpoints instead of shebang CLIs.
Agents should use these endpoints instead of shebang CLIs.
## Reasoner (D18)
Pluggable OpenAI-compatible URL. RAM: `Qwen/Qwen3.5-9B`. Quality:
`prism-ml/Bonsai-27B-gguf` or `Qwen/Qwen3.6-27B`. No official Qwen3.6-9B.
CPU sidecar: compose profile `reasoner` (`OLLAMA_NUM_GPU=0`,
`127.0.0.1:11435`). Bake-off: `bin/reasoner/bakeoff.go`. Weights stay out
of the 2dph image. See [docs/reasoner.md](reasoner.md).