feat(nh3-dev): repoint Hermes at gen-large on the LiteLLM gateway

Operator ruled the repoint; Miranda moves off the paid z.ai Coding Plan
onto free local compute. model.default gen-large, provider custom,
base_url http://10.250.50.70:4000/v1. Verified by a real turn rather than
by config: hermes status reports gen-large / Custom endpoint and a
completion through /v1/chat/completions returns 660 tokens. The
openrouter/nous credit warnings cleared with it.

Records the landmine found on the way: CUSTOM_API_KEY and
HERMES_CUSTOM_API_KEY are inert for bare provider: custom — they bind only
a named custom_providers entry through its key_env. Without model.api_key
the request ships the placeholder no-key-required and LiteLLM 401s inside
the response body while hermes status still reports a healthy gen-large /
Custom endpoint, so status alone cannot verify this change.

Also notes that nh3-dev/hermes/api-server-key must not be rotated until
SVOS splits its HS256 signing key off the shared value.

servers/nh3-dev/README.md

@@ -36,15 +36,32 @@ local Bash already executes here — no SSH-to-self needed for non-privileged wo
   is what SVOS's `_hermes_roster` derives its required-config line from —
   narrowing does not blind it. Becomes `[svos_miranda]` once SVOS's plugin lands
   in `$HERMES_HOME/plugins/`.
-- ⚠ **Hermes model resolution is NOT the free local gateway.** `model.default`
-  says `anthropic/claude-opus-4.6` and `model.base_url` says openrouter, but
-  `provider: auto` plus a lone `zai` credential in `auth.json` resolves Miranda
-  to **GLM-5.3 over the paid z.ai Coding Plan**
-  (`https://api.z.ai/api/coding/paas/v4`). Nothing under `~/.hermes` references
-  the LiteLLM gateway at all. Raised 2026-09-14 by svos-dev, who reports the
-  operator believes Miranda runs on `gen-large` (free local). `gen-large` does
-  exist on LiteLLM. **Unresolved — do not repoint without the operator**, the
-  premise is his to confirm.
+- **Hermes model backend → `gen-large` on the fleet LiteLLM gateway** (free local
+  compute), set 2026-09-14 per operator ruling. Until then `model.default` said
+  `anthropic/claude-opus-4.6` with `model.base_url` at openrouter, but
+  `provider: auto` plus a lone `zai` credential in `auth.json` silently resolved
+  Miranda to **GLM-5.3 on the paid z.ai Coding Plan** — three settings that had
+  to be read together before the real answer fell out. Now
+  `default: gen-large` / `provider: custom` / `base_url:
+  http://10.250.50.70:4000/v1`, verified by a real turn (`hermes status` →
+  `gen-large` / `Custom endpoint`, plus a 660-token completion through
+  `/v1/chat/completions`). The openrouter/nous credit warnings cleared with it.
+  ⚠ **`CUSTOM_API_KEY` / `HERMES_CUSTOM_API_KEY` are INERT for bare
+  `provider: "custom"`** — they only bind a *named* `custom_providers:` entry via
+  its `key_env`. Set `model.api_key` in `config.yaml` instead; its only env
+  fallback is the legacy name `OPENROUTER_API_KEY`. Get this wrong and the
+  request ships the placeholder `no-key-required`, LiteLLM 401s **inside the
+  response body**, and `hermes status` still reports a perfectly healthy
+  `gen-large` / `Custom endpoint` — so status alone cannot verify this change,
+  only a real completion can. The `zai` credential is still in `auth.json`,
+  present and unused; `provider: custom` is explicit so it is not a candidate,
+  and `hermes fallback list` is empty, so there is no degraded-mode route that
+  quietly re-bills z.ai. Miranda fails rather than fails over if LiteLLM is down.
+- ⚠ **Do not rotate `nh3-dev/hermes/api-server-key` yet.** SVOS currently reuses
+  that value as the HS256 signing key on its Bifrost wall, so a rotation would
+  401 every Miranda tool call. svos-dev is splitting theirs off (operator-
+  approved 2026-09-14) and will confirm when it lands; rotation is safe after
+  that, not before.
 - **bloom_music dev** — `~/development/bloom_music`; its `web/` test harness uses
   Playwright headless Chromium for OSMD browser-geometry assertions.
 - **The Booth** — ephemeral media drop board (`:8090`, `booth.service`), from