feat: auto-update via settings

1 files changed, 19 insertions, 0 deletions

diff --git a/README.md b/README.md
index 5638aec..597a723 100644
--- a/README.md
+++ b/README.md
@@ -64,6 +64,25 @@ Voxtral TTS, Fish Speech, and more — see
 an NVIDIA GPU; one model is hosted per server process, so the Generate
 form's Model pick decides which server boots.
 
+## Updating
+
+Run `Configure Backends > Update Generator` in the hub: it fetches the
+latest code and moves the checkout to the remote's default branch (the
+same fetch + hard-reset flow the backend checkouts use), then asks you to
+restart so the new code loads. Nothing you generate or download is at risk
+— `input/`, `output/`, `voices/`, `app/envs/`, model weights, and logs are
+untracked and outside the reset's reach — and **locally modified tracked
+files are preserved**: `app/converter/config.py` (your settings) and any
+other file you edited are written back after the update, with a notice
+when upstream changed them too (merge new options by hand in that case).
+A dirty checkout asks before proceeding; an up-to-date checkout skips the
+reset entirely.
+
+After the generator itself updates, run **Update Backends** to refresh the
+backend packages (`pip -U` / git + rebuild). When a release changes an
+update's requirements, the next launch re-checks the app venv
+automatically; backend venvs follow their own wizards.
+
 ## CLI Options
 
 Without `--api-url` the CLI manages the server itself, just like the TUI: it starts the selected backend's managed instance (installed via the TUI), converts, and stops it again. A server already running at the configured endpoint is used as-is and left running when the run ends. `--api-url` points at an external server instead, and never touches server state.