Files
zeekay e89a3fbf2f router: learned heads wired through the one Policy seam (ROUTER_HEADS)
The learned routing head is now a first-class hanzo-router primitive, and
exactly one Policy type reaches the serve seam. The featurizer moves from the
enso crate into hanzo-router (featurize.rs); heads.rs adds the serve-time
scorer (bilinear W + arm profiles). Policy grows `learned`: mounted, route()
scores arms x^T W p minus the SLO penalty; empty, the rule-based walk. The
PREFER table (a-priori per-task arm preferences, ported from the live eval
harness) ships as prefer() -- the preference-aware default.

hanzo-server-core resolves one deployment_policy(): ROUTER_HEADS=<bundle>
mounts the head (Policy::load_heads), unset keeps prefer(). Reversible by one
env var. Seam test proves the wired path routes per the head and diverges from
the rule-based default on the same prompt + pool.

router-fit (renamed from enso-fit) emits the serve bundle next to --out.
Fitted on 2981 real eval events (gpqa_diamond + livecodebench, prompt text
included so fit-time features match serve-time): held-out decision quality
(prompt-level splits, 8 seeds) head 0.9215+-0.011 vs rule-based 0.9162+-0.007
vs best-single-arm 0.9215 (gpt-5.5) vs oracle 0.9402. Bundle + regen docs in
hanzo-router/heads/. The enso crate remains the offline learner only; its
Policy never reaches the seam.
2026-07-18 00:03:00 -07:00
..

Router heads — the learned routing policy

router.heads.json is the serve bundle the engine mounts via ROUTER_HEADS=<path> (loaded by hanzo_router::Policy::load_heads at startup; unset = the rule-based prefer() policy). One Policy type either way.

Fit from eval events (per-prompt, per-arm outcomes with real prompt text):

cargo run --release -p hanzo-router-retrain --bin router-fit -- \
  --events <events.jsonl> --out heads.safetensors --gamma 0.1

which writes the servable heads.heads.json next to --out. Current bundle: 2981 events (gpqa_diamond + livecodebench, 373 prompts x 8 arms), gamma 0.1 picked by held-out decision quality (mean realized correctness of the chosen arm, prompt-level splits, 8 seeds): head 0.9215 +- 0.011 vs rule-based 0.9162 +- 0.007 vs best-single-arm 0.9215 (gpt-5.5) vs oracle 0.9402.