chore: retire asset-engine (Prime 2026-10-17); kuma gains delete-by-name; FleetTools/bootstrap/catalog marked

docs/asset-engine/CATALOG-CONTRACT.md

@@ -1,5 +1,10 @@
 # services.yaml — contract for downstream consumers
 
+> **RETIRED 2026-10-17 (Prime).** asset-engine, this catalog's only consumer, is `compose down` on ana-docker.
+> The catalog is NOT maintained: every irv-ml1 endpoint in `services.yaml` still points at `10.100.79.3`, the wg0
+> lifeline that died at the 09-06 mesh cutover, and several of those ports now belong to other services. Kept as
+> the record and for a bring-back, which would need a full per-entry refresh first.
+
 `services.yaml` in this directory is the **canonical, versioned**
 description of the inference services this fleet exposes. It is a
 first-class artifact: external tools (the asset-engine UI is the

docs/fleettools/AGENT-BOOTSTRAP.md

@@ -17,7 +17,6 @@ their own:
 
 ```sh
 curl -s http://10.0.50.45:5100/api/services            # every fleet service, curated
-curl -s http://10.250.50.70:8200/api/v1/services       # inference seats + GPU state
 curl -s http://10.250.50.70:4000/v1/models             # the LLM roster (needs a key)
 ```
 

docs/fleettools/FLEETTOOLS.md

@@ -14,12 +14,11 @@ directory; that defeats the point.
 
 ## Rule zero: query live inventories, never a written list
 
-Three endpoints answer "what exists right now" better than any document, and they stay
+Two endpoints answer "what exists right now" better than any document, and they stay
 correct on their own. **Reach for these before asking anyone:**
 
 ```sh
 curl -s http://10.0.50.45:5100/api/services            # every fleet service, curated
-curl -s http://10.250.50.70:8200/api/v1/services       # inference seats + GPU state
 curl -s -H "Authorization: Bearer $KEY" \
         http://10.250.50.70:4000/v1/models             # the LLM roster (~40 models)
 ```
@@ -70,13 +69,13 @@ live contract for its API. Fetch it rather than trusting a transcription.
   ⚠ *The shared key CAN spend real vendor credits.*
   *Detail:* `/home/lkraven/development/eshpfi-management/docs/fleettools/litellm.md`
 
-- **Direct inference seats + Asset Engine** — the control plane at
-  `http://10.250.50.70:8200` enumerates seats, reads GPU state, and starts/stops them.
+- **Direct inference seats** — most sit behind the gateway; the GPU hosts and their traps.
+  (The Asset Engine control plane at `:8200` was RETIRED 2026-10-17.)
   *When:* the gateway does not expose what you need, or a seat is down.
   *Detail:* `/home/lkraven/development/eshpfi-management/docs/fleettools/inference.md`
 
 - **Speech (TTS/ASR)** — Breeze-TTS-2 is the fleet primary; Chatterbox-fast is the
-  low-latency chat front end; Speaches and Parakeet do ASR.
+  low-latency chat front end; Parakeet does ASR (`whisper-1` / `ext-stt` on the gateway).
   *When:* you need audio out of text, or text out of audio.
   *Detail:* `/home/lkraven/development/eshpfi-management/docs/fleettools/speech.md`
 

docs/fleettools/inference.md

@@ -1,4 +1,4 @@
-# Direct inference seats + the Asset Engine control plane
+# Direct inference seats
 
 Most seats are vLLM behind the LiteLLM gateway — prefer the gateway
 (`docs/fleettools/litellm.md`) unless you need something it does not expose.
@@ -8,30 +8,20 @@ Most seats are vLLM behind the LiteLLM gateway — prefer the gateway
 ```sh
 # every fleet service, curated, with hrefs and descriptions
 curl -s http://10.0.50.45:5100/api/services | python3 -m json.tool
-
-# the inference control plane: what exists, what is up, GPU state
-curl -s http://10.250.50.70:8200/api/v1/services
-curl -s http://10.250.50.70:8200/api/v1/gpus
+# the LLM roster
+curl -s -H "Authorization: Bearer $KEY" http://10.250.50.70:4000/v1/models
 ```
 
 Seats move between hosts and GPUs often enough that any transcribed table here would
 mislead within a month.
 
-## Asset Engine — `http://10.250.50.70:8200`
+## Asset Engine — RETIRED 2026-10-17
 
-Control plane over the PFI inference fleet. Can enumerate services, read GPU state,
-**start and stop seats**, submit jobs and fetch assets.
-
-```
-GET  /api/v1/services              GET  /api/v1/services/{id}/state
-POST /api/v1/services/{id}/start   POST /api/v1/services/{id}/stop
-GET  /api/v1/gpus                  POST /api/v1/jobs
-GET  /api/v1/assets/{id}/blob      GET  /api/v1/presets
-```
-
-⚠ **Liveness is keyed on the compose PROJECT name.** A seat reads OFFLINE unless the
-compose project name equals the catalog's `lifecycle.stack`. Pin `name: <stack>` in
-the compose file.
+The control plane at `http://10.250.50.70:8200` is gone (Prime). Its last job was 2026-08-02, and every
+catalog endpoint pointed at irv-ml1's dead wg0 address after the 09-06 mesh cutover. `docker compose
+down` on ana-docker; the DB, image, repo (`vh/asset-engine`) and catalog (`docs/asset-engine/`) are kept, so
+`docker compose up -d` in `/opt/docker/compose/asset-engine` brings it back. Start/stop a seat by hand
+(`docker compose up -d` / `stop` in its compose dir on the GPU host).
 
 ## GPU hosts
 

docs/fleettools/speech.md

@@ -33,7 +33,7 @@ the router cooldown** — list voices first.
 
 Retired, verified 2026-10-17: **Speaches** (irv-ml1 :8204 is now Breeze-TTS-2), the sherpa-onnx `parakeet` container
 on fv-ml1 (stopped; NeMo replaced it), and the asset-engine `parakeet` entry at `10.100.79.3:8765` (the dead wg0
-lifeline address). The first two's leftover containers were removed 2026-10-17 (images and compose dirs kept), so
+lifeline address; asset-engine itself was retired 2026-10-17). The first two's leftover containers were removed 2026-10-17 (images and compose dirs kept), so
 Homepage no longer lists them.
 
 ## Traps