diff --git a/packages/coding-agent/CHANGELOG.md b/packages/coding-agent/CHANGELOG.md
index 7eca501e..f4b4b858 100644
--- a/packages/coding-agent/CHANGELOG.md
+++ b/packages/coding-agent/CHANGELOG.md
@@ -15,6 +15,7 @@
   - `queuedMessageCount` → `pendingMessageCount`
   - `getQueuedMessages()` → `getSteeringMessages()` and `getFollowUpMessages()`
   - `clearQueue()` now returns `{ steering: string[], followUp: string[] }`
+  - `hasQueuedMessages()` → `hasPendingMessages()`
 - **Hook API signature changed**: `pi.sendMessage()` second parameter changed from `triggerTurn?: boolean` to `options?: { triggerTurn?, deliverAs? }`. Use `deliverAs: "followUp"` for follow-up delivery. Affects both hooks and internal `sendHookMessage()` method.
 - **RPC API changes**:
   - `queue_message` command → `steer` and `follow_up` commands
@@ -25,6 +26,7 @@
 ### Added
 
 - Alt+Enter keybind to queue follow-up messages while agent is streaming
+- `Theme` and `ThemeColor` types now exported for hooks using `ctx.ui.custom()`
 - Terminal window title now displays "pi - dirname" to identify which project session you're in ([#407](https://github.com/badlogic/pi-mono/pull/407) by [@kaofelix](https://github.com/kaofelix))
 
 ### Fixed
diff --git a/packages/coding-agent/README.md b/packages/coding-agent/README.md
index 352cd4cb..b72dd4fd 100644
--- a/packages/coding-agent/README.md
+++ b/packages/coding-agent/README.md
@@ -188,7 +188,7 @@ The agent reads, writes, and edits files, and executes commands via bash.
 
 | Command | Description |
 |---------|-------------|
-| `/settings` | Open settings menu (thinking, theme, queue mode, toggles) |
+| `/settings` | Open settings menu (thinking, theme, message delivery modes, toggles) |
 | `/model` | Switch models mid-session (fuzzy search, arrow keys, Enter to select) |
 | `/export [file]` | Export session to self-contained HTML |
 | `/share` | Upload session as secret GitHub gist, get shareable URL (requires `gh` CLI) |
@@ -214,7 +214,11 @@ The agent reads, writes, and edits files, and executes commands via bash.
 
 **Multi-line paste:** Pasted content is collapsed to `[paste #N <lines> lines]` but sent in full.
 
-**Message queuing:** Submit messages while the agent is working. They queue and process based on queue mode (configurable via `/settings`). Press Escape to abort and restore queued messages to editor.
+**Message queuing:** Submit messages while the agent is working:
+- **Enter** queues a *steering* message, delivered after current tool execution (interrupts remaining tools)
+- **Alt+Enter** queues a *follow-up* message, delivered only after the agent finishes all work
+
+Both modes are configurable via `/settings`: "one-at-a-time" delivers messages one by one waiting for responses, "all" delivers all queued messages at once. Press Escape to abort and restore queued messages to editor.
 
 ### Keyboard Shortcuts
 
@@ -499,7 +503,8 @@ Global `~/.pi/agent/settings.json` stores persistent preferences:
   "defaultModel": "claude-sonnet-4-20250514",
   "defaultThinkingLevel": "medium",
   "enabledModels": ["anthropic/*", "*gpt*", "gemini-2.5-pro:high"],
-  "queueMode": "one-at-a-time",
+  "steeringMode": "one-at-a-time",
+  "followUpMode": "one-at-a-time",
   "shellPath": "C:\\path\\to\\bash.exe",
   "hideThinkingBlock": false,
   "collapseChangelog": false,
@@ -531,7 +536,8 @@ Global `~/.pi/agent/settings.json` stores persistent preferences:
 | `defaultModel` | Default model ID | - |
 | `defaultThinkingLevel` | Thinking level: `off`, `minimal`, `low`, `medium`, `high`, `xhigh` | - |
 | `enabledModels` | Model patterns for cycling. Supports glob patterns (`github-copilot/*`, `*sonnet*`) and fuzzy matching. Same as `--models` CLI flag | - |
-| `queueMode` | Message queue mode: `all` or `one-at-a-time` | `one-at-a-time` |
+| `steeringMode` | Steering message delivery: `all` or `one-at-a-time` | `one-at-a-time` |
+| `followUpMode` | Follow-up message delivery: `all` or `one-at-a-time` | `one-at-a-time` |
 | `shellPath` | Custom bash path (Windows) | auto-detected |
 | `hideThinkingBlock` | Hide thinking blocks in output (Ctrl+T to toggle) | `false` |
 | `collapseChangelog` | Show condensed changelog after update | `false` |
@@ -689,7 +695,13 @@ export default function (pi: HookAPI) {
 
 **Sending messages from hooks:**
 
-Use `pi.sendMessage(message, triggerTurn?)` to inject messages into the session. Messages are persisted as `CustomMessageEntry` and sent to the LLM. If the agent is streaming, the message is queued; otherwise a new agent loop starts if `triggerTurn` is true.
+Use `pi.sendMessage(message, options?)` to inject messages into the session. Messages are persisted as `CustomMessageEntry` and sent to the LLM.
+
+Options:
+- `triggerTurn`: If true and agent is idle, starts a new agent turn. Default: false.
+- `deliverAs`: When agent is streaming, controls delivery timing:
+  - `"steer"` (default): Delivered after current tool execution, interrupts remaining tools.
+  - `"followUp"`: Delivered only after agent finishes all work.
 
 ```typescript
 import * as fs from "node:fs";
diff --git a/packages/coding-agent/docs/hooks.md b/packages/coding-agent/docs/hooks.md
index c5cc9fab..7313bd48 100644
--- a/packages/coding-agent/docs/hooks.md
+++ b/packages/coding-agent/docs/hooks.md
@@ -565,13 +565,13 @@ Abort the current agent operation (fire-and-forget, does not wait):
 await ctx.abort();
 ```
 
-### ctx.hasQueuedMessages()
+### ctx.hasPendingMessages()
 
-Check if there are messages queued (user typed while agent was streaming):
+Check if there are messages pending (user typed while agent was streaming):
 
 ```typescript
-if (ctx.hasQueuedMessages()) {
-  // Skip interactive prompt, let queued message take over
+if (ctx.hasPendingMessages()) {
+  // Skip interactive prompt, let pending messages take over
   return;
 }
 ```
@@ -638,7 +638,7 @@ const result = await ctx.navigateTree("entry-id-456", {
 
 Subscribe to events. See [Events](#events) for all event types.
 
-### pi.sendMessage(message, triggerTurn?)
+### pi.sendMessage(message, options?)
 
 Inject a message into the session. Creates a `CustomMessageEntry` that participates in the LLM context.
 
@@ -648,12 +648,17 @@ pi.sendMessage({
   content: "Message text",    // string or (TextContent | ImageContent)[]
   display: true,              // Show in TUI
   details: { ... },           // Optional metadata (not sent to LLM)
-}, triggerTurn);              // If true, triggers LLM response
+}, {
+  triggerTurn: true,          // If true and agent is idle, triggers LLM response
+  deliverAs: "steer",         // "steer" (default) or "followUp" when agent is streaming
+});
 ```
 
 **Storage and timing:**
 - The message is appended to the session file immediately as a `CustomMessageEntry`
-- If the agent is currently streaming, the message is queued and appended after the current turn
+- If the agent is currently streaming:
+  - `deliverAs: "steer"` (default): Delivered after current tool execution, interrupts remaining tools
+  - `deliverAs: "followUp"`: Delivered only after agent finishes all work
 - If `triggerTurn` is true and the agent is idle, a new agent loop starts
 
 **LLM context:**
@@ -700,7 +705,7 @@ pi.registerCommand("stats", {
 
 For long-running commands (e.g., LLM calls), use `ctx.ui.custom()` with a loader. See [examples/hooks/qna.ts](../examples/hooks/qna.ts).
 
-To trigger LLM after command, call `pi.sendMessage(..., true)`.
+To trigger LLM after command, call `pi.sendMessage(..., { triggerTurn: true })`.
 
 ### pi.registerMessageRenderer(customType, renderer)
 
diff --git a/packages/coding-agent/src/modes/interactive/components/settings-selector.ts b/packages/coding-agent/src/modes/interactive/components/settings-selector.ts
index 9538aebf..8bb9ac4e 100644
--- a/packages/coding-agent/src/modes/interactive/components/settings-selector.ts
+++ b/packages/coding-agent/src/modes/interactive/components/settings-selector.ts
@@ -131,14 +131,16 @@ export class SettingsSelectorComponent extends Container {
 			{
 				id: "steering-mode",
 				label: "Steering mode",
-				description: "How to deliver steering messages (Enter while streaming)",
+				description:
+					"Enter while streaming queues steering messages. 'one-at-a-time': deliver one, wait for response. 'all': deliver all at once.",
 				currentValue: config.steeringMode,
 				values: ["one-at-a-time", "all"],
 			},
 			{
 				id: "follow-up-mode",
 				label: "Follow-up mode",
-				description: "How to deliver follow-up messages (queued until agent finishes)",
+				description:
+					"Alt+Enter queues follow-up messages until agent stops. 'one-at-a-time': deliver one, wait for response. 'all': deliver all at once.",
 				currentValue: config.followUpMode,
 				values: ["one-at-a-time", "all"],
 			},