docs+AGENTS: model ids officially frank-archon/frank-dragoon/frank-zealot (services keep old names)

This commit is contained in:
Frank
2026-10-08 17:16:21 -07:00
parent a30ac9457a
commit 98f11a19c1
3 changed files with 23 additions and 4 deletions
+8 -4
View File
@@ -286,9 +286,13 @@ deletes the unit file from `/etc/systemd/system/`, not just the symlink.
The harness reaches the fleet through `.omp/agent/models.yml` in the
operator's home — `/home/blank/.omp/agent/models.yml` on the dev box, which is
where the harness runs; there is no copy on the servers. Each provider is one
HOST:PORT; each model `id` is the served alias: `frank-primary` →
`192.168.0.235:7770`, `frank-large` → `192.168.0.143:7770`, `frank-secondary` →
`modelRoles`.
HOST:PORT; each model `id` is the served alias. **Official model ids are
the StarCraft unit names (2026-10-08):** `frank-archon` →
`192.168.0.235:7770`, `frank-dragoon` → `192.168.0.143:7770`,
`frank-zealot` → `192.168.0.143:7771` (was `frank-primary`, `frank-large`,
`frank-secondary` — the SERVICES, units, scripts, env files and runbooks
keep the old names; the rename is model ids in `models.yml`/`config.yml`
and the homepage model cards). `modelRoles`.
Resolution rules: the default model resolves as a `defaultProvider` +
`defaultModel` pair (the provider must serve the model); a subagent override
@@ -475,7 +479,7 @@ carry over: ≥256 px probe images or the model answers "video", and only the
OpenAI `image_url` content part reaches the model.
**Compaction hub**: `models.yml` routes `compactionModel` for
`frank-primary`, `frank-large` and `frank-secondary` here — 200,704 is the
`frank-archon`, `frank-dragoon` and `frank-zealot` (the 3090 endpoint) here — 200,704 is the
only window in the fleet that fits a worst-case compaction input (~170k
tokens). With `--parallel 2` a compaction request no longer serializes behind
a live generation (the Gemma4 era's `--parallel 1` law).