Commit Graph
2 Commits
Author SHA1 Message Date
Frank 33396d2daa feat(frank-dragoon): halogen-flash-server 0.16.2 -> 0.18.20, NPU lane re-pinned
The engine pin moves to the newest vendor release (0.18.20, image built
2026-10-30). The payload lock is the gate this deploy has to pass: the v2
.hgn loads only in the flash-server line, so /health plus the boot ledger
decide, and the rollback is the 0c61bf84 digest on the same env line.

0.18.20's NPU catalog is NOT the 0.16.2 one: it names 14 device programs
(u0..u13) and an 8,495,512 B consts.hnpb where 0.16.2 had 10 and 5,086,496 B,
and the entrypoint verifies size+sha256 for every staged file before it
starts. HALOGEN_NPU_MODELS names qwen3-embedding-0.6b, so the staging set is
re-pinned to revision 8fd44c9f with the new block — bumping the engine alone
would refuse the boot on the NPU lane.
2026-10-30 15:13:19 -07:00
Frank e36f6a732c frank-dragoon: promote the A/B verification harness into the repo
The three artifacts that produced the native-vs-swift15 verdict, so the next
payload swap starts from instruments instead of ad-hoc scripts:

  census-frank-dragoon.sh — the engine's own checkpoint tools (verify/ppl/niah)
    over BOTH payloads under one knob set; the pool stays 524288 deliberately
    because the ppl pass scores 297,053 ids as two 262,144-token sequences.
  battery-frank-dragoon.py — behavior battery against the live service: refusal
    census, thinking-token census, tool-call turns, the red-PNG vision probe,
    needle-in-haystack, decode/prefill/prompt-cache rates; discards the
    post-boot warmup request and records the engine's 400 body (which names the
    exact token overage) instead of dying on it.
  trial-frank-dragoon.sh — the guarded candidate window: fetch gate, verify,
    stop+mask, census, boot through a transient FRANK_DRAGOON_ENV_FILE drop-in,
    battery, trap-guarded restore.
2026-10-17 22:18:00 -07:00