diff --git a/cecli/website/docs/config/tui.md b/cecli/website/docs/config/tui.md
@@ -15,6 +15,21 @@ The TUI is the default in recent versions of Cecli and on older versions it can
 cecli ... --tui
 ```
 
+## Non-TUI Mode
+
+Pass `--no-tui` (or set `tui: false`) to run the plain terminal interface
+instead of the full-screen TUI. In this mode:
+
+- Input is read from stdin and re-prompted after each turn.
+- Confirmation prompts are read from the terminal.
+- Input and confirmations pushed by an external driver are also honored: the
+  [WebSocket/ACP server](api.html) and the AgentService wake path push onto the
+  coder's input queue, so a headless or server-driven session can answer prompts
+  with no terminal attached.
+
+Both modes consume the same per-coder input queue, so prompt handling is
+consistent whether or not the TUI is running.
+
 ## Configuration
 
 The TUI can be configured directly in the relevant config.json file or with JSON in the command line arguments:

diff --git a/cecli/website/docs/scripting.md b/cecli/website/docs/scripting.md
@@ -24,6 +24,12 @@ for FILE in *.py ; do
 done
 ```
 
+> **Note:** `--message` (`-m`) and `--message-file` (`-f`) are **one-shot**.
+> Cecli sends the message, lets the model act on it, then exits. There is no
+> follow-up prompt in this mode, so an instruction that ends by asking you a
+> question has nowhere to collect your answer. Pass `--yes` for fully
+> non-interactive runs, or use one of the multi-turn routes below.
+
 Use `cecli --help` to see all the [command line options](config/options.html), but these are useful for scripting:
 
 ```
@@ -50,6 +56,23 @@ Use `cecli --help` to see all the [command line options](config/options.html), b
                       [env var: CECLI_COMMIT]
 ```
 
+### Multi-turn input
+
+Run cecli without `--message` and it stays up for a back-and-forth session. Where
+your input comes from depends on the mode:
+
+- **TUI** (`tui: true`, the default): type into the chat input box.
+- **Non-TUI** (`--no-tui`, or `tui: false`): input is read from stdin and
+  re-prompted after every turn. Questions and confirmation prompts from the
+  agent are answered at the terminal prompt.
+- **Programmatic**: an external driver pushes `{"text": ...}` (and
+  `{"confirmed": ...}` for yes/no confirmations) onto the coder's input queue.
+  The [WebSocket/ACP server](config/api.html) and the AgentService wake path use
+  this route.
+
+Both input paths consume the same per-coder queue, so a headless or
+server-driven session can answer prompts with no terminal attached.
+
 
 ## Python