docs(vault): the embedding lane has a consumer, and two shapes that bite

open-notebook's embedding default now points at qwen3-embedding-0.6b on frank-dragoon's XDNA2 lane, proven through the app's own paths (model test 1024 dims, worker 'Successfully embedded', vector search ranking two unrelated notes 0.659/0.292 and 0.906/0.318). Records the two app-side traps: defaults store the model ID and a name is accepted then fails in the worker, and POST /api/embed 500s on an upstream RecordID typing bug after the vector is already written. frank-dragoon's lane section moves from 'off until the mount fix' to armed-and-serving with the boot-ledger contract and the measured idle RSS; the page's stale 'not on dankclaw_default' reachability claims are retired.

serverAppConfigs-docs/LLM/frank-dragoon.md

@@ -10,7 +10,7 @@ tags:
   - gfx1151
   - halogen
   - endpoint
-timestamp: 2026-10-18
+timestamp: 2026-10-19
 ---
 
 # frank-dragoon — halogen-flash-server 0.16.2, native v2 abliterated (Dankclaw iGPU)
@@ -236,9 +236,8 @@ Embedding contract on that lane: `POST /v1/embeddings`, `model: "qwen3-embedding
 `check_embedding_ctx_length=False`.
 
 Four host prerequisites, each refused **by name** in the serve script and mirrored in `deploy_llm_dragoon` — a
-precondition that surfaces as an engine crash-loop is a gate that was never written. All four are satisfied on this
-box as of 2026-10-19; the endpoint still runs with the lane **off** until that day's mount fix merges, and the first
-armed boot's evidence lands here with it:
+precondition that surfaces as an engine crash-loop is a gate that was never written. All four are satisfied and the
+lane is **armed and serving** since 2026-10-19 (`HALOGEN_NPU_MODELS=qwen3-embedding-0.6b`):
 
 1. `--device /dev/accel/accel0` **and** a node the container's namespace can open. `/dev/accel/accel0` is
    `root:render 0660` and a rootless namespace maps exactly one uid/gid, so the engine's own first words are
@@ -270,11 +269,14 @@ armed boot's evidence lands here with it:
    unset, so the container opens no outbound connection; `scripts/download-frank-dragoon-npu.sh` pins every file by
    size and sha256 against the catalog and the payload mount carries the tree in.
 
-Price: the programs and their weights sit in host RAM beside the 62.9 GiB of locked weights ("a few GB in all" for
-the default set; ~1.1 GiB for `embeddinggemma-2`), and **the Flash model decodes slower while the NPU works** — same
-memory bus, same power budget. Under this page's RAM law the question is pool versus n-gram table, so read the boot
-ledger after the first NPU boot instead of modelling it. If the lane is opened, prefer **0.18.8 or newer**: that
-release budgets NPU memory before asking for it, fixing kernel errors from several NPU models under a concurrent mix
+Armed, the boot ledger reads (`/home/dank/logs/frank_dragoon.log`, 2026-10-19): the GPU fabric clock is held at its top level (2000 MHz) **before** the NPU starts; `/dev/accel/accel0` is `crw-rw-rw- nobody:nogroup` under driver `amdxdna` with the distro XRT and its NPU plugin; the program arrives as `15 files checked against this image's record`; then `npu_api: qwen3-embedding-0.6b (embeddings) on the NPU engine at 127.0.0.1:8740 (buckets u0…u9; inputs up to 4096 tokens)` and `up to 64 passes queued … up to 7200 s`. Callers never see `:8740` — the lane answers on the same `:8731` as the Flash model and a request picks the engine by its `model` field, so `/v1/models` lists `frank-dragoon` **and** `qwen3-embedding-0.6b`. The fleet's consumer is open-notebook's embedding default ([[Open Notebook]]); that page owns the app-side shapes (the URL guard, defaults-by-id, the `/api/embed` 500 that still writes the vector).
+
+Price: the programs and their weights sit in host RAM beside the locked weights ("a few GB in all" for the default
+set; ~1.1 GiB for `embeddinggemma-2`), and **the Flash model decodes slower while the NPU works** — same memory bus,
+same power budget. Measured 2026-10-19 with one program armed and the endpoint idle, the whole container holds
+**1.55 GiB** of host RSS (`podman stats`), so this lane is not what the RAM law above is negotiating against; a
+multi-model set is where that question returns. If the lane is widened, prefer **0.18.8 or newer**: that release
+budgets NPU memory before asking for it, fixing kernel errors from several NPU models under a concurrent mix
 **on the stock kernel driver** — the driver this box runs.
 
 ## Files