frank-large: ship HALOGEN_VERBOSE=1 for permanent startup evidence

Verbose engine logging is the vendor's first-line evidence for load,
allocation and admission questions; shipping it on means an incident
report already carries the full startup account instead of needing a
restart-into-debug. HALOGEN_DMALLOC_LOG stays off (every alloc >64MB is
steady-state noise on a shared host). Doc updated with the rootless
podman-logs-vs-journalctl retrieval note.

dankclaw/frank-large/quadlet/frank-large.container

@@ -97,6 +97,13 @@ Environment=HALOGEN_KV_SLOTS=4
 Environment=HALOGEN_HOST_RESERVE_GIB=24
 # Image input (the sidecar ships inside the weights repo).
 Environment=HALOGEN_VISION_TOWER=1
+# Verbose engine logging: the vendor's first-line evidence for load,
+# allocation and admission questions. Shipping it on means an incident report
+# already has the full startup account instead of needing a restart-into-debug.
+# HALOGEN_DMALLOC_LOG is deliberately NOT set — it logs every allocation
+# over 64 MB, which is steady-state noise here; raise it only for a live
+# OOM hunt.
+Environment=HALOGEN_VERBOSE=1
 # Required by the image: the engine maps the checkpoint and registers it with
 # the GPU in place, which needs host IPC and an unconfined seccomp profile.
 PodmanArgs=--ipc=host --security-opt seccomp=unconfined

serverAppConfigs-docs/LLM/halogen-flash-server.md

@@ -83,6 +83,7 @@ upstream's defaults:
 | `HALOGEN_HOST_RESERVE_GIB` | `24` | RAM kept for the n-gram table the engine reads through the page cache — above upstream's 20 because a dozen containers share this host |
 | `HALOGEN_VISION_TOWER` | `1` | image input; the fleet's only image path since [[frank-npu]] was retired |
 | `HALOGEN_DOWNLOAD` | `peonist-ai/halogen-qwen3.8-flash-next` | first-start fetch |
+| `HALOGEN_VERBOSE` | `1` | verbose engine logging — the fullest startup account, on permanently so an incident report needs no restart-into-debug |
 
 Everything else is upstream's default, deliberately: prompt cache mode `2`
 (two entries per conversation — end-of-system-prompt and end-of-history — which
@@ -210,14 +211,22 @@ it stays unhealthy by design.
 | both the engine and a co-tenant stall for minutes at full CPU | the pinned-trunk trade; see Memory model |
 | `free`, `MemAvailable`, Grafana all wrong by ~68 GiB | expected — locked weights are counted as reclaimable |
 
-`HALOGEN_VERBOSE=1` and `HALOGEN_DMALLOC_LOG=1` print the fullest startup
+`HALOGEN_VERBOSE=1` ships in the unit, so the fullest startup account is
-account and every allocation over 64 MB; both are the vendor's suggested
+already in the log when something goes wrong. `HALOGEN_DMALLOC_LOG` is
-evidence to attach to a report. The two lines worth grepping first:
+deliberately **not** set: it logs every allocation over 64 MB, which is
+steady-state noise on a shared host — raise it only for a live OOM report.
+The lines worth grepping first:
 
 ```bash
 podman logs frank-large 2>&1 | grep -E '^(dmalloc|kv pool):'
 ```
 
+Retrieval: `podman logs frank-large` covers the **current** instance only —
+the Quadlet runs `--replace --rm`, so everything before the last recreate is
+gone from the container log. `journalctl --user -u frank-large.service` is
+the durable record. Both are rootless: `sudo podman logs frank-large` looks
+in root's storage and answers "no such container".
+
 ## Rollback
 
 The llama.cpp era is intact: the STRIX payload stays at