Reconcile the deployed resident model documentation (V-407)

AGENTS.md

@@ -135,37 +135,41 @@ Russian recall — you may see many "clarify" responses).
 
 ## Qwen3 resident model for router + phraser
 
-The target daemon uses the locally trained Qwen3-1.7B checkpoint for both
-routing and phrasing. Training is Qwen3 Base → RU CPT → joint persona/router
-SFT → merged GGUF, and is still in flight (#122) — until it lands, the deployed
-resident model is stock **Qwen3.5-0.8B** (`Q4_K_M`), see `deploy/mavend.json`.
+The deployed resident model is stock **Qwen3-1.7B** (`UD-Q4_K_XL`), a Thinking
+variant at `n_ctx` 4096. `CLAUDE.md` carries the rule on which models qualify.
 Without a configured model, `StubPhraser` plus the classifier remain the
 deterministic floor.
 
-During training, use the runbook in
-`docs/plans/2026-07-18-qwen3-resident-training-eval.md`. After the decision gate
-and SFT pass, copy the merged GGUF into the mounted model directory and set:
+A locally trained Qwen3-1.7B checkpoint is still in flight (V-122). Training
+runs Qwen3 Base, then RU CPT, then joint persona and router SFT, then a merged
+GGUF. The
+runbook is `docs/plans/2026-07-18-qwen3-resident-training-eval.md`. After the
+decision gate and SFT pass, copy the merged GGUF into the mounted model
+directory and point `model_path` at it.
+
+**Configure in `deploy/mavend.json`.** This is the deployed `phraser` block:
 
 ```json
 "phraser": {
-  "model_path": "/opt/maven/models/llm/Qwen3-Maven-1.7B-Q8_0.gguf",
+  "model_path": "/opt/maven/models/llm/qwen3/Qwen3-1.7B-UD-Q4_K_XL.gguf",
   "bin_path": "llama-server",
   "n_gpu_layers": 99,
-  "n_ctx": 2048
+  "n_ctx": 4096,
+  "cache_ram_mib": 512,
+  "timeout": "60s"
 }
 ```
 
-**Configure in `deploy/mavend.json`** — the `phraser` block points at this
-model and the daemon spawns `llama-server` as a subprocess. The router and
-replier use the same llama-server via the shared `internal/llm` client.
+The daemon spawns `llama-server` as a subprocess. The router and replier reach
+that one server through the shared `internal/llm` client. Model files live in
+`/mnt/hdd1/llms`, bind-mounted over `models/llm/`, so a gguf sitting in the repo
+is loaded by nothing.
 
 Telegram tokens are read from `deploy/telegram.env` (gitignored), expanded
 via `${VAR}` in the JSON config.
 
-**Routing is Qwen-first** with classifier fallback. The LLM router runs
-after stage-0 (exact-match grammar) and before the classifier cascade. On any
-error or parse failure, the classifier handles the utterance — the turn never
-breaks on the model.
+The cascade order, and which stage may decline to the next, is in
+`docs/routing.md`. It is not restated here.
 
 ## Web UI conventions