chore: docker, config, delivery sinks, dialogue, and agent docs

- Dockerfile: multi-stage build with CGO_ENABLED=0, embedder model copy,
  non-root user, healthcheck, and /data volume.
- docker-compose.yml: mavend + mavweb services with shared volume, health
  checks, and restart policy.
- .gitignore: ignore models/llm/*.gguf, deploy/telegram.env, tmp artifacts.
- deploy/mavend.json: add LLM, phraser, voice sections (embedder, model
  paths, wake sensitivity). Add telegram token env-var expansion.
- deploy/telegram.env.example: template for telegram bot token.
- internal/config/config.go: add LLM config struct, voice config struct
  (embedder, llama, wake sensitivity), telegram token loading.
- telegramsink: add chat intent delivery support alongside existing types.
- voicesink: skip empty payloads in delivery.
- dialogue/session: add chat intent to anaphora resolution, test coverage.
- AGENTS.md: update with LLM embedder, LFM model download/configure steps,
  new UI conventions.
- REARCH.md: architecture research document.
- cmd/mavend/main.go: wire LLM config, phraser, embedder, telegram config,
  WebAuthn, IPC event/routine handlers, and reactive notes.

AGENTS.md

@@ -74,6 +74,38 @@ sudo cp onnxruntime-linux-x64-1.15.1/lib/libonnxruntime.so* /usr/local/lib/
 Without the embedder block, the daemon uses `HashEmbedder` (works, but weak on
 Russian recall — you may see many "clarify" responses).
 
+## LFM model for router + phraser
+
+The daemon uses a single resident LFM (sub-1B) for both routing (intent
+classification + slot extraction) and phrasing (nudges, reminders, reactive
+replies). Without it, the `StubPhraser` + `HashEmbedder` classifier are used
+— deterministic but stiff (canned confirmations, weak Russian recall).
+
+**Download the model** (GGUF, ~780 MB):
+
+```sh
+make download-llm
+```
+
+Or manually:
+
+```sh
+curl -sL "https://huggingface.co/lfm/LFM2.5-1.2B-Instruct-GGUF/resolve/main/LFM2.5-1.2B-Instruct-Q4_K_M.gguf" \
+  -o models/llm/LFM2.5-1.2B-Instruct-Q4_K_M.gguf
+```
+
+**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.
+
+Telegram tokens are read from `deploy/telegram.env` (gitignored), expanded
+via `${VAR}` in the JSON config.
+
+**Routing is now LFM-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.
+
 ## Web UI conventions
 
 - All server-rendered pages share `cmd/mavweb/static/ui.css` (served at