diff --git a/AGENTS.md b/AGENTS.md
index 983c67f..8c53483 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -69,7 +69,7 @@ crash recovery, images both ways), and the usage screen.
 names a host, `session::transport` turns that into an `ssh host …`
 invocation, and the driver never learns which it got.
 
-**Phase 4 (llama.cpp) works on the server side** (2026-08-28). Models are
+**Phase 4 (llama.cpp) works end to end, phone included** (2026-08-28). Models are
 browsed and downloaded from HuggingFace (`models.rs`, resumable and
 verified), and `session::llama` runs one through `llama-server`, talking
 to its OpenAI-compatible streaming endpoint. Two things about it are
@@ -77,10 +77,23 @@ deliberate and easy to undo by accident: the conversation is rebuilt from
 the **transcript** rather than kept in the driver, because driver memory
 is invisible to a second device; and a llama session is refused on an ssh
 host, because the model is reached over HTTP and forwarding that port is
-not built. No app screen yet — models are driven through the routes.
+not built.
 
-What is left is the models UI, and real-phone/WireGuard bring-up, which is
-operational rather than code.
+Models are browsed, downloaded and deleted from the app, and a llama
+session picks one of them plus a context size and temperature. Setups —
+machines, each carrying what it can run — are added, renamed, re-probed
+and removed from the app too; providers are **discovered by asking the
+machine**, never typed, so the enrolled token cannot introduce a command.
+
+What is left is real-phone/WireGuard bring-up, which is operational rather
+than code.
+
+**`command -v` follows PATH under a non-interactive ssh session**, which is
+not the PATH a login shell shows, so a binary somewhere unusual is
+invisible to discovery — llama.cpp unpacked into `~/.local/opt` needs a
+symlink into `~/.local/bin` before a setup finds it. The escape hatch for
+anything odder is editing `config.ron` on the backend, which is
+deliberately the one authority the phone does not have.
 
 **Testing llama.cpp here:** the prebuilt CPU build lives outside the repo
 at `~/.local/opt/llama.cpp` (the 15 MB `ubuntu-x64` release asset — no