story-kit: done 290_story_show_agent_output_stream_in_expanded_work_item_detail_panel

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

.story_kit/README.md

@@ -18,7 +18,7 @@ When you start a new session with this project:
    This returns the full tool catalog (create stories, spawn agents, record tests, manage worktrees, etc.). Familiarize yourself with the available tools before proceeding. These tools allow you to directly manipulate the workflow and spawn subsidiary agents without manual file manipulation.
 2. **Read Context:** Check `.story_kit/specs/00_CONTEXT.md` for high-level project goals.
 3. **Read Stack:** Check `.story_kit/specs/tech/STACK.md` for technical constraints and patterns.
-4. **Check Work Items:** Look at `.story_kit/work/1_upcoming/` and `.story_kit/work/2_current/` to see what work is pending.
+4. **Check Work Items:** Look at `.story_kit/work/1_backlog/` and `.story_kit/work/2_current/` to see what work is pending.
 
 
 ---
@@ -52,7 +52,7 @@ project_root/
   ├── README.md          # This document
   ├── project.toml       # Agent configuration (roles, models, prompts)
   ├── work/              # Unified work item pipeline (stories, bugs, spikes)
-  │   ├── 1_upcoming/    # New work items awaiting implementation
+  │   ├── 1_backlog/    # New work items awaiting implementation
   │   ├── 2_current/     # Work in progress
   │   ├── 3_qa/          # QA review
   │   ├── 4_merge/       # Ready to merge to master
@@ -78,7 +78,7 @@ All work items (stories, bugs, spikes) live in the same `work/` pipeline. Items
 
 Items move through stages by moving the file between directories:
 
-`1_upcoming` → `2_current` → `3_qa` → `4_merge` → `5_done` → `6_archived`
+`1_backlog` → `2_current` → `3_qa` → `4_merge` → `5_done` → `6_archived`
 
 Items in `5_done` are auto-swept to `6_archived` after 4 hours by the server.
 
@@ -87,7 +87,7 @@ Items in `5_done` are auto-swept to `6_archived` after 4 hours by the server.
 The server watches `.story_kit/work/` for changes. When a file is created, moved, or modified, the watcher auto-commits with a deterministic message and broadcasts a WebSocket notification to the frontend. This means:
 
 *   MCP tools only need to write/move files — the watcher handles git commits
-*   IDE drag-and-drop works (drag a story from `1_upcoming/` to `2_current/`)
+*   IDE drag-and-drop works (drag a story from `1_backlog/` to `2_current/`)
 *   The frontend updates automatically without manual refresh
 
 ---
@@ -156,7 +156,7 @@ Not everything needs to be a full story. Simple bugs can skip the story process:
 *   Performance issues with known fixes
 
 ### Bug Process
-1.  **Document Bug:** Create a bug file in `work/1_upcoming/` named `{id}_bug_{slug}.md` with:
+1.  **Document Bug:** Create a bug file in `work/1_backlog/` named `{id}_bug_{slug}.md` with:
     *   **Symptom:** What the user observes
     *   **Root Cause:** Technical explanation (if known)
     *   **Reproduction Steps:** How to trigger the bug
@@ -186,7 +186,7 @@ Not everything needs a story or bug fix. Spikes are time-boxed investigations to
 *   Need to validate performance constraints
 
 ### Spike Process
-1.  **Document Spike:** Create a spike file in `work/1_upcoming/` named `{id}_spike_{slug}.md` with:
+1.  **Document Spike:** Create a spike file in `work/1_backlog/` named `{id}_spike_{slug}.md` with:
     *   **Question:** What you need to answer
     *   **Hypothesis:** What you expect to be true
     *   **Timebox:** Strict limit for the research
@@ -209,7 +209,7 @@ When the LLM context window fills up (or the chat gets slow/confused):
 1.  **Stop Coding.**
 2.  **Instruction:** Tell the user to open a new chat.
 3.  **Handoff:** The only context the new LLM needs is in the `specs/` folder and `.mcp.json`.
-    *   *Prompt for New Session:* "I am working on Project X. Read `.mcp.json` to discover available tools, then read `specs/00_CONTEXT.md` and `specs/tech/STACK.md`. Then look at `work/1_upcoming/` and `work/2_current/` to see what is pending."
+    *   *Prompt for New Session:* "I am working on Project X. Read `.mcp.json` to discover available tools, then read `specs/00_CONTEXT.md` and `specs/tech/STACK.md`. Then look at `work/1_backlog/` and `work/2_current/` to see what is pending."
 
 
 ---
@@ -221,7 +221,7 @@ If a user hands you this document and says "Apply this process to my project":
 1.  **Check for MCP Tools:** Look for `.mcp.json` in the project root. If it exists, you have programmatic access to workflow tools and agent spawning capabilities.
 2.  **Analyze the Request:** Ask for the high-level goal ("What are we building?") and the tech preferences ("Rust or Python?").
 3.  **Git Check:** Check if the directory is a git repository (`git status`). If not, run `git init`.
-4.  **Scaffold:** Run commands to create the `work/` and `specs/` folders with the 6-stage pipeline (`work/1_upcoming/` through `work/6_archived/`).
+4.  **Scaffold:** Run commands to create the `work/` and `specs/` folders with the 6-stage pipeline (`work/1_backlog/` through `work/6_archived/`).
 5.  **Draft Context:** Write `specs/00_CONTEXT.md` based on the user's answer.
 6.  **Draft Stack:** Write `specs/tech/STACK.md` based on best practices for that language.
 7.  **Wait:** Ask the user for "Story #1".

.story_kit/bot.toml.example

@@ -13,3 +13,7 @@ enabled = false
 
 # Maximum conversation turns to remember per room (default: 20).
 # history_size = 20
+
+# Rooms where the bot responds to all messages (not just addressed ones).
+# This list is updated automatically when users toggle ambient mode at runtime.
+# ambient_rooms = ["!roomid:example.com"]

.story_kit/project.toml

@@ -34,7 +34,7 @@ You have these tools via the story-kit MCP server:
 ## Your Workflow
 1. Read CLAUDE.md and .story_kit/README.md to understand the project and dev process
 2. Read the story file from .story_kit/work/ to understand requirements
-3. Move it to work/2_current/ if it is in work/1_upcoming/
+3. Move it to work/2_current/ if it is in work/1_backlog/
 4. Start coder-1 on the story: call start_agent with story_id="{{story_id}}" and agent_name="coder-1"
 5. Wait for completion: call wait_for_agent with story_id="{{story_id}}" and agent_name="coder-1". The server automatically runs acceptance gates (cargo clippy + tests) when the coder process exits. wait_for_agent returns when the coder reaches a terminal state.
 6. Check the result: inspect the "completion" field in the wait_for_agent response — if gates_passed is true, the work is done; if false, review the gate_output and decide whether to start a fresh coder.
@@ -102,7 +102,7 @@ Read CLAUDE.md first, then .story_kit/README.md to understand the dev process.
   - URL to visit in the browser
   - Things to check in the UI
   - curl commands to exercise relevant API endpoints
-- Kill the test server when done: `pkill -f story-kit || true`
+- Kill the test server when done: `pkill -f 'target.*story-kit' || true` (NEVER use `pkill -f story-kit` — it kills the vite dev server)
 
 ### 4. Produce Structured Report
 Print your QA report to stdout before your process exits. The server will automatically run acceptance gates. Use this format:
@@ -179,7 +179,7 @@ Read CLAUDE.md first, then .story_kit/README.md to understand the dev process.
   - URL to visit in the browser
   - Things to check in the UI
   - curl commands to exercise relevant API endpoints
-- Kill the test server when done: `pkill -f story-kit || true`
+- Kill the test server when done: `pkill -f 'target.*story-kit' || true` (NEVER use `pkill -f story-kit` — it kills the vite dev server)
 
 ### 4. Produce Structured Report
 Print your QA report to stdout before your process exits. The server will automatically run acceptance gates. Use this format:

.story_kit/work/1_backlog/280_story_long_running_supervisor_agent_with_periodic_pipeline_polling.md

@@ -21,6 +21,10 @@ As a project owner, I want a long-running supervisor agent (opus) that automatic
 - [ ] Polling interval is configurable in project.toml (e.g. supervisor_poll_interval_secs = 30)
 - [ ] Supervisor logs persistent/recurring problems to `.story_kit/problems.md` with timestamp, description, and frequency — humans review this file periodically to create stories for systemic issues
 
+## Notes
+
+- **2026-03-18**: Moved back to current from merge. Previous attempt went through the full pipeline but the squash-merge produced an empty diff — no code was actually implemented. Needs a real implementation.
+
 ## Out of Scope
 
 - Supervisor accepting or merging stories to master (human job)

.story_kit/work/1_backlog/292_story_show_server_logs_in_web_ui.md

@@ -0,0 +1,21 @@
+---
+name: "Show server logs in web UI"
+---
+
+# Story 292: Show server logs in web UI
+
+## User Story
+
+As a project owner using the web UI, I want to see live server logs in the interface, so that I can debug agent behavior and pipeline issues without needing terminal access.
+
+## Acceptance Criteria
+
+- [ ] Web UI has a server logs panel accessible from the main interface
+- [ ] Logs stream in real-time via WebSocket or SSE
+- [ ] Logs can be filtered by keyword (same as get_server_logs MCP tool's filter param)
+- [ ] Log entries show timestamp and severity level
+- [ ] Panel doesn't interfere with the existing pipeline board and work item views
+
+## Out of Scope
+
+- TBD

.story_kit/work/5_done/247_story_human_qa_gate_with_rejection_flow.md

@@ -1,25 +0,0 @@
----
-name: "Human QA gate with rejection flow"
----
-
-# Story 247: Human QA gate with rejection flow
-
-## User Story
-
-As the project owner, I want stories to require my manual approval after machine QA before they can be merged, so that features that compile and pass tests but do not actually work correctly are caught before reaching master.
-
-## Acceptance Criteria
-
-- [ ] Story files support a manual_qa front matter field (defaults to true)
-- [ ] After machine QA passes in 3_qa, stories with manual_qa: true wait for human approval before moving to 4_merge
-- [ ] The UI shows a clear way to launch the app from the worktree for manual testing (single button click), with automatic port conflict handling via .story_kit_port
-- [ ] Frontend and backend are pre-compiled during machine QA so the app is ready to run instantly for manual testing
-- [ ] Only one QA app instance runs at a time — do not automatically spin up multiple instances
-- [ ] Human can approve a story from 3_qa to move it to 4_merge
-- [ ] Human can reject a story from 3_qa back to 2_current with notes about what is broken
-- [ ] Rejection notes are written into the story file so the coder can see what needs fixing
-- [ ] Stories with manual_qa: false skip the human gate and proceed directly from machine QA to 4_merge
-
-## Out of Scope
-
-- TBD

.story_kit/work/5_done/273_story_matrix_bot_sends_typing_indicator_while_waiting_for_claude_response.md

@@ -15,6 +15,10 @@ As a user chatting with the Matrix bot, I want to see a typing indicator in Elem
 - [ ] Typing indicator is cleared on error so it doesn't get stuck
 - [ ] No visible delay between sending a message and seeing the typing indicator
 
+## Notes
+
+- **2026-03-18**: Moved back to current from done. Previous attempt went through the full pipeline but merged with an empty diff — no typing indicator code was actually implemented. Needs a real implementation this time.
+
 ## Out of Scope
 
 - TBD

.story_kit/work/5_done/282_story_matrix_bot_ambient_mode_toggle_via_chat_command.md

@@ -0,0 +1,24 @@
+---
+name: "Matrix bot ambient mode toggle via chat command"
+---
+
+# Story 282: Matrix bot ambient mode toggle via chat command
+
+## User Story
+
+As a user chatting with Timmy in a Matrix room, I want to toggle between "addressed mode" (bot only responds when mentioned by name) and "ambient mode" (bot responds to all messages) via a chat command, so that I don't have to @-mention the bot on every message when I'm the only one around.
+
+## Acceptance Criteria
+
+- [ ] Matrix bot defaults to addressed mode — only forwards messages containing the bot's name to Claude
+- [ ] Chat command "{bot_name} ambient on" switches to ambient mode — bot forwards all room messages to Claude (bot name comes from display_name in bot.toml)
+- [ ] Chat command "{bot_name} ambient off" switches back to addressed mode
+- [ ] Mode is persisted per-room in bot.toml so it survives bot restarts
+- [ ] bot.toml.example includes the ambient_mode setting with a comment explaining it
+- [ ] Bot confirms the mode switch with a short response in chat
+- [ ] When other users join or are active, user can flip back to addressed mode to avoid noise
+- [ ] Ambient mode applies per-room (not globally across all rooms)
+
+## Out of Scope
+
+- TBD

.story_kit/work/5_done/283_bug_pipeline_does_not_check_manual_qa_flag_before_advancing_from_qa_to_merge.md

@@ -0,0 +1,30 @@
+---
+name: "Pipeline does not check manual_qa flag before advancing from QA to merge"
+---
+
+# Bug 283: Pipeline does not check manual_qa flag before advancing from QA to merge
+
+## Description
+
+Story 247 added the manual_qa front matter field and the MCP tooling to set it, but the pipeline in pool.rs never actually checks the flag. After QA passes gates and coverage, stories move straight to merge regardless of manual_qa setting.
+
+## How to Reproduce
+
+1. Create a story with manual_qa: true in front matter
+2. Let it go through the coder and QA stages
+3. Observe that it moves directly to merge without waiting for human approval
+
+## Actual Result
+
+Stories always advance from QA to merge automatically, ignoring the manual_qa flag.
+
+## Expected Result
+
+Stories with manual_qa: true should pause after QA passes and wait for human approval before moving to merge. Stories with manual_qa: false (the default) should advance automatically as they do now.
+
+## Acceptance Criteria
+
+- [ ] Pipeline checks manual_qa front matter field after QA gates pass
+- [ ] manual_qa defaults to false — stories advance automatically unless explicitly opted in
+- [ ] Stories with manual_qa: true wait in 3_qa for human approval via accept_story or the UI
+- [ ] Stories with manual_qa: false proceed directly from QA to merge as before

.story_kit/work/5_done/284_story_matrix_bot_status_command_shows_pipeline_and_agent_availability.md

@@ -0,0 +1,22 @@
+---
+name: "Matrix bot status command shows pipeline and agent availability"
+---
+
+# Story 284: Matrix bot status command shows pipeline and agent availability
+
+## User Story
+
+As a user in a Matrix room, I want to type "{bot_name} status" and get a formatted summary of the full pipeline (upcoming through done) with agent assignments, plus which agents are currently free, so that I can check project status without leaving chat.
+
+## Acceptance Criteria
+
+- [ ] Chat command "{bot_name} status" triggers a pipeline status display (bot name comes from display_name in bot.toml)
+- [ ] Output shows all stages: upcoming, current, qa, merge, done — with story names and IDs
+- [ ] Each active story shows its assigned agent name and model
+- [ ] Output includes a section showing which agents are free (not currently assigned to any story)
+- [ ] Response is formatted for readability in Matrix (monospace or markdown as appropriate)
+- [ ] Command is handled at the bot level — does not require a full Claude invocation
+
+## Out of Scope
+
+- TBD

.story_kit/work/5_done/285_story_matrix_bot_help_command_lists_available_bot_commands.md

@@ -0,0 +1,25 @@
+---
+name: "Matrix bot help command lists available bot commands"
+---
+
+# Story 285: Matrix bot help command lists available bot commands
+
+## User Story
+
+As a user in a Matrix room, I want to type "{bot_name} help" and get a list of all available bot commands with brief descriptions, so that I can discover what the bot can do without having to ask or remember.
+
+## Acceptance Criteria
+
+- [ ] Chat command "{bot_name} help" displays a list of all available bot-level commands (bot name comes from display_name in bot.toml)
+- [ ] Each command is shown with a short description of what it does
+- [ ] Help output is formatted for readability in Matrix
+- [ ] Help command is handled at the bot level — does not require a full Claude invocation
+- [ ] Help list automatically includes new commands as they are added (driven by a registry or similar, not a hardcoded string)
+
+## Notes
+
+- **2026-03-18**: Moved back to current from done. Previous attempt committed code directly to master (commit a32cfbd) instead of the worktree, and the help command is not functional in the running server. Needs a clean implementation this time.
+
+## Out of Scope
+
+- TBD

.story_kit/work/5_done/286_story_server_self_rebuild_and_restart_via_mcp_tool.md

@@ -0,0 +1,22 @@
+---
+name: "Server self-rebuild and restart via MCP tool"
+---
+
+# Story 286: Server self-rebuild and restart via MCP tool
+
+## User Story
+
+As a project owner away from my terminal, I want to tell the bot to restart the server so that it picks up new code changes, without needing physical access to the machine.
+
+## Acceptance Criteria
+
+- [ ] MCP tool `rebuild_and_restart` triggers a cargo build of the server
+- [ ] If the build fails, server stays up and returns the build error
+- [ ] If the build succeeds, server re-execs itself with the new binary using std::os::unix::process::CommandExt::exec()
+- [ ] Server logs the restart so it's traceable
+- [ ] Matrix bot reconnects automatically after the server comes back up
+- [ ] Running agents are gracefully stopped before re-exec
+
+## Out of Scope
+
+- TBD

.story_kit/work/5_done/287_story_rename_upcoming_pipeline_stage_to_backlog.md

@@ -0,0 +1,22 @@
+---
+name: "Rename upcoming pipeline stage to backlog"
+---
+
+# Story 287: Rename upcoming pipeline stage to backlog
+
+## User Story
+
+As a project owner, I want the "upcoming" pipeline stage renamed to "backlog" throughout the codebase, UI, and directory structure, so that the terminology better reflects that these items are not necessarily coming up next.
+
+## Acceptance Criteria
+
+- [ ] Directory renamed from 1_upcoming to 1_backlog
+- [ ] All server code references updated (watcher, lifecycle, MCP tools, workflow, etc.)
+- [ ] Frontend UI labels updated
+- [ ] MCP tool descriptions and outputs use "backlog" instead of "upcoming"
+- [ ] Existing story/bug files moved to the new directory
+- [ ] Git commit messages use "backlog" for new items going forward
+
+## Out of Scope
+
+- TBD

.story_kit/work/5_done/288_bug_ambient_mode_state_lost_on_server_restart.md

@@ -0,0 +1,29 @@
+---
+name: "Ambient mode state lost on server restart"
+---
+
+# Bug 288: Ambient mode state lost on server restart
+
+## Description
+
+Story 282 implemented ambient mode toggle but only in-memory. The acceptance criterion requiring persistence in bot.toml was not implemented. Every server restart (including rebuild_and_restart) clears ambient mode for all rooms.
+
+## How to Reproduce
+
+1. Type "timmy ambient on" — get confirmation
+2. Restart server (or rebuild_and_restart)
+3. Send unaddressed message — bot ignores it, ambient mode is gone
+
+## Actual Result
+
+Ambient mode state is lost on server restart.
+
+## Expected Result
+
+Ambient mode per-room state is persisted in bot.toml and restored on startup.
+
+## Acceptance Criteria
+
+- [ ] Ambient mode per-room state is saved to bot.toml when toggled
+- [ ] Ambient mode state is restored from bot.toml on server startup
+- [ ] bot.toml.example includes the ambient_rooms setting with a comment

.story_kit/work/5_done/289_bug_rebuild_and_restart_mcp_tool_does_not_rebuild.md

@@ -0,0 +1,28 @@
+---
+name: "rebuild_and_restart MCP tool does not rebuild"
+agent: coder-opus
+---
+
+# Bug 289: rebuild_and_restart MCP tool does not rebuild
+
+## Description
+
+The rebuild_and_restart MCP tool re-execs the server binary but does not run cargo build first. It restarts with the old binary, so code changes are not picked up.
+
+## How to Reproduce
+
+1. Make a code change to the server
+2. Call rebuild_and_restart via MCP
+3. Observe the server restarts but the code change is not reflected
+
+## Actual Result
+
+Server re-execs with the old binary. Code changes are not compiled.
+
+## Expected Result
+
+Server runs cargo build --release (or cargo build) before re-execing, so the new binary includes the latest code changes.
+
+## Acceptance Criteria
+
+- [ ] Bug is fixed and verified

.story_kit/work/5_done/290_story_show_agent_output_stream_in_expanded_work_item_detail_panel.md

@@ -0,0 +1,22 @@
+---
+name: "Remove agent thinking traces from agents sidebar"
+---
+
+# Story 290: Remove agent thinking traces from agents sidebar
+
+## User Story
+
+As a user viewing an expanded work item in the web UI, I want to see the live agent output stream (thinking traces, tool calls, progress) for the agent working on that story, so that I can monitor progress in context rather than in the agents sidebar.
+
+## Acceptance Criteria
+
+- [ ] Agent thinking traces are removed from the agents sidebar panel — they should only appear in the work item detail panel (which already has SSE streaming wired up in `WorkItemDetailPanel.tsx`)
+
+## Notes
+
+The detail panel (`WorkItemDetailPanel.tsx`) already has agent log streaming implemented — SSE subscription, real-time output, status badges, etc. The only remaining work is removing the thinking traces from the agents sidebar (`AgentPanel.tsx` or similar) so they don't appear in both places.
+
+## Out of Scope
+
+- Replacing the agents sidebar entirely — it still shows agent names, status, and assignments
+- Historical agent output (only live stream while agent is running)

.story_kit/work/6_archived/276_story_detect_and_log_when_root_mcp_json_port_is_modified.md

@@ -0,0 +1,17 @@
+---
+name: "Detect and log when root .mcp.json port is modified"
+---
+
+# Story 276: Detect and log when root .mcp.json port is modified
+
+## User Story
+
+As a ..., I want ..., so that ...
+
+## Acceptance Criteria
+
+- [ ] TODO
+
+## Out of Scope
+
+- TBD

Cargo.lock

@@ -3997,7 +3997,7 @@ checksum = "6ce2be8dc25455e1f91df71bfa12ad37d7af1092ae736f3a6cd0e37bc7810596"
 
 [[package]]
 name = "story-kit"
-version = "0.2.0"
+version = "0.3.1"
 dependencies = [
  "async-stream",
  "async-trait",

frontend/src/api/client.test.ts

@@ -262,7 +262,7 @@ describe("ChatWebSocket", () => {
 
 		// Server pushes pipeline_state on fresh connection
 		const freshState = {
-			upcoming: [{ story_id: "1_story_test", name: "Test", error: null }],
+			backlog: [{ story_id: "1_story_test", name: "Test", error: null }],
 			current: [],
 			qa: [],
 			merge: [],

frontend/src/api/client.ts

@@ -36,7 +36,7 @@ export interface PipelineStageItem {
 }
 
 export interface PipelineState {
-	upcoming: PipelineStageItem[];
+	backlog: PipelineStageItem[];
 	current: PipelineStageItem[];
 	qa: PipelineStageItem[];
 	merge: PipelineStageItem[];
@@ -50,7 +50,7 @@ export type WsResponse =
 	| { type: "error"; message: string }
 	| {
 			type: "pipeline_state";
-			upcoming: PipelineStageItem[];
+			backlog: PipelineStageItem[];
 			current: PipelineStageItem[];
 			qa: PipelineStageItem[];
 			merge: PipelineStageItem[];
@@ -398,7 +398,7 @@ export class ChatWebSocket {
 				if (data.type === "error") this.onError?.(data.message);
 				if (data.type === "pipeline_state")
 					this.onPipelineState?.({
-						upcoming: data.upcoming,
+						backlog: data.backlog,
 						current: data.current,
 						qa: data.qa,
 						merge: data.merge,

frontend/src/components/AgentPanel.test.tsx

@@ -213,7 +213,7 @@ describe("RosterBadge availability state", () => {
 	});
 });
 
-describe("Thinking traces hidden from agent stream UI", () => {
+describe("Agent output not shown in sidebar (story 290)", () => {
 	beforeAll(() => {
 		Element.prototype.scrollIntoView = vi.fn();
 	});
@@ -224,7 +224,51 @@ describe("Thinking traces hidden from agent stream UI", () => {
 		mockedSubscribeAgentStream.mockReturnValue(() => {});
 	});
 
-	// AC1: thinking block is never rendered even when thinking events arrive
+	// AC1: output events do not appear in the agents sidebar
+	it("does not render agent output when output event arrives", async () => {
+		let emitEvent: ((e: AgentEvent) => void) | null = null;
+		mockedSubscribeAgentStream.mockImplementation(
+			(_storyId, _agentName, onEvent) => {
+				emitEvent = onEvent;
+				return () => {};
+			},
+		);
+
+		const agentList: AgentInfo[] = [
+			{
+				story_id: "290_output",
+				agent_name: "coder-1",
+				status: "running",
+				session_id: null,
+				worktree_path: "/tmp/wt",
+				base_branch: "master",
+				log_session_id: null,
+			},
+		];
+		mockedAgents.listAgents.mockResolvedValue(agentList);
+
+		const { container } = render(<AgentPanel />);
+		await screen.findByTestId("roster-badge-coder-1");
+
+		await act(async () => {
+			emitEvent?.({
+				type: "output",
+				story_id: "290_output",
+				agent_name: "coder-1",
+				text: "doing some work...",
+			});
+		});
+
+		// No output elements in the sidebar
+		expect(
+			container.querySelector('[data-testid^="agent-output-"]'),
+		).not.toBeInTheDocument();
+		expect(
+			container.querySelector('[data-testid^="agent-stream-"]'),
+		).not.toBeInTheDocument();
+	});
+
+	// AC1: thinking events do not appear in the agents sidebar
 	it("does not render thinking block when thinking event arrives", async () => {
 		let emitEvent: ((e: AgentEvent) => void) | null = null;
 		mockedSubscribeAgentStream.mockImplementation(
@@ -236,7 +280,7 @@ describe("Thinking traces hidden from agent stream UI", () => {
 
 		const agentList: AgentInfo[] = [
 			{
-				story_id: "218_thinking",
+				story_id: "290_thinking",
 				agent_name: "coder-1",
 				status: "running",
 				session_id: null,
@@ -253,109 +297,16 @@ describe("Thinking traces hidden from agent stream UI", () => {
 		await act(async () => {
 			emitEvent?.({
 				type: "thinking",
-				story_id: "218_thinking",
+				story_id: "290_thinking",
 				agent_name: "coder-1",
 				text: "Let me consider the problem carefully...",
 			});
 		});
 
-		// AC1: thinking block must not be present
+		// No thinking block or output in sidebar
 		expect(screen.queryByTestId("thinking-block")).not.toBeInTheDocument();
-	});
+		expect(
-
+			screen.queryByText("Let me consider the problem carefully..."),
-	// AC2: after thinking events, only regular output is rendered
+		).not.toBeInTheDocument();
-	it("renders regular output but not thinking block when both arrive", async () => {
-		let emitEvent: ((e: AgentEvent) => void) | null = null;
-		mockedSubscribeAgentStream.mockImplementation(
-			(_storyId, _agentName, onEvent) => {
-				emitEvent = onEvent;
-				return () => {};
-			},
-		);
-
-		const agentList: AgentInfo[] = [
-			{
-				story_id: "218_output",
-				agent_name: "coder-1",
-				status: "running",
-				session_id: null,
-				worktree_path: "/tmp/wt",
-				base_branch: "master",
-				log_session_id: null,
-			},
-		];
-		mockedAgents.listAgents.mockResolvedValue(agentList);
-
-		render(<AgentPanel />);
-		await screen.findByTestId("roster-badge-coder-1");
-
-		// Thinking event — must be ignored visually
-		await act(async () => {
-			emitEvent?.({
-				type: "thinking",
-				story_id: "218_output",
-				agent_name: "coder-1",
-				text: "thinking deeply",
-			});
-		});
-
-		// AC3: output event still renders correctly (no regression)
-		await act(async () => {
-			emitEvent?.({
-				type: "output",
-				story_id: "218_output",
-				agent_name: "coder-1",
-				text: "Here is the result.",
-			});
-		});
-
-		// AC1: no thinking block
-		expect(screen.queryByTestId("thinking-block")).not.toBeInTheDocument();
-
-		// AC2+AC3: output area renders the text but NOT thinking text
-		const outputArea = screen.getByTestId("agent-output-coder-1");
-		expect(outputArea).toBeInTheDocument();
-		expect(outputArea.textContent).toContain("Here is the result.");
-		expect(outputArea.textContent).not.toContain("thinking deeply");
-	});
-
-	// AC3: output-only event stream (no thinking) still works
-	it("renders output event text without a thinking block", async () => {
-		let emitEvent: ((e: AgentEvent) => void) | null = null;
-		mockedSubscribeAgentStream.mockImplementation(
-			(_storyId, _agentName, onEvent) => {
-				emitEvent = onEvent;
-				return () => {};
-			},
-		);
-
-		const agentList: AgentInfo[] = [
-			{
-				story_id: "218_noThink",
-				agent_name: "coder-1",
-				status: "running",
-				session_id: null,
-				worktree_path: "/tmp/wt",
-				base_branch: "master",
-				log_session_id: null,
-			},
-		];
-		mockedAgents.listAgents.mockResolvedValue(agentList);
-
-		render(<AgentPanel />);
-		await screen.findByTestId("roster-badge-coder-1");
-
-		await act(async () => {
-			emitEvent?.({
-				type: "output",
-				story_id: "218_noThink",
-				agent_name: "coder-1",
-				text: "plain output line",
-			});
-		});
-
-		expect(screen.queryByTestId("thinking-block")).not.toBeInTheDocument();
-		const outputArea = screen.getByTestId("agent-output-coder-1");
-		expect(outputArea.textContent).toContain("plain output line");
 	});
 });

frontend/src/components/AgentPanel.tsx

@@ -13,7 +13,6 @@ const { useCallback, useEffect, useRef, useState } = React;
 interface AgentState {
 	agentName: string;
 	status: AgentStatusValue;
-	log: string[];
 	sessionId: string | null;
 	worktreePath: string | null;
 	baseBranch: string | null;
@@ -120,7 +119,6 @@ export function AgentPanel({
 					const current = prev[key] ?? {
 						agentName,
 						status: "pending" as AgentStatusValue,
-						log: [],
 						sessionId: null,
 						worktreePath: null,
 						baseBranch: null,
@@ -144,14 +142,6 @@ export function AgentPanel({
 								},
 							};
 						}
-						case "output":
-							return {
-								...prev,
-								[key]: {
-									...current,
-									log: [...current.log, event.text ?? ""],
-								},
-							};
 						case "done":
 							return {
 								...prev,
@@ -168,17 +158,12 @@ export function AgentPanel({
 								[key]: {
 									...current,
 									status: "failed",
-									log: [
-										...current.log,
-										`[ERROR] ${event.message ?? "Unknown error"}`,
-									],
 									terminalAt: current.terminalAt ?? Date.now(),
 								},
 							};
-						case "thinking":
-							// Thinking traces are internal model state — never display them.
-							return prev;
 						default:
+							// output, thinking, and other events are not displayed in the sidebar.
+							// Agent output streams appear in the work item detail panel instead.
 							return prev;
 					}
 				});
@@ -204,7 +189,6 @@ export function AgentPanel({
 					agentMap[key] = {
 						agentName: a.agent_name,
 						status: a.status,
-						log: [],
 						sessionId: a.session_id,
 						worktreePath: a.worktree_path,
 						baseBranch: a.base_branch,
@@ -261,9 +245,6 @@ export function AgentPanel({
 		}
 	};
 
-	// Agents that have streaming content to show
-	const activeAgents = Object.values(agents).filter((a) => a.log.length > 0);
-
 	return (
 		<div
 			style={{
@@ -420,35 +401,6 @@ export function AgentPanel({
 				</div>
 			)}
 
-			{/* Per-agent streaming output */}
-			{activeAgents.map((agent) => (
-				<div
-					key={`stream-${agent.agentName}`}
-					data-testid={`agent-stream-${agent.agentName}`}
-					style={{
-						display: "flex",
-						flexDirection: "column",
-						gap: "4px",
-					}}
-				>
-					{agent.log.length > 0 && (
-						<div
-							data-testid={`agent-output-${agent.agentName}`}
-							style={{
-								fontSize: "0.8em",
-								fontFamily: "monospace",
-								color: "#ccc",
-								whiteSpace: "pre-wrap",
-								wordBreak: "break-word",
-								lineHeight: "1.5",
-							}}
-						>
-							{agent.log.join("")}
-						</div>
-					)}
-				</div>
-			))}
-
 			{actionError && (
 				<div
 					style={{

frontend/src/components/Chat.test.tsx

@@ -631,7 +631,10 @@ describe("Chat localStorage persistence (Story 145)", () => {
 
 		// Verify sendChat was called with ALL prior messages + the new one
 		expect(lastSendChatArgs).not.toBeNull();
-		const args = lastSendChatArgs as unknown as { messages: Message[]; config: unknown };
+		const args = lastSendChatArgs as unknown as {
+			messages: Message[];
+			config: unknown;
+		};
 		expect(args.messages).toHaveLength(3);
 		expect(args.messages[0]).toEqual({
 			role: "user",
@@ -1350,7 +1353,14 @@ describe("Bug 264: Claude Code session ID persisted across browser refresh", ()
 
 		expect(lastSendChatArgs).not.toBeNull();
 		expect(
-			((lastSendChatArgs as unknown as { messages: Message[]; config: unknown })?.config as Record<string, unknown>).session_id,
+			(
+				(
+					lastSendChatArgs as unknown as {
+						messages: Message[];
+						config: unknown;
+					}
+				)?.config as Record<string, unknown>
+			).session_id,
 		).toBe("persisted-session-xyz");
 	});
 

frontend/src/components/Chat.tsx

@@ -165,7 +165,7 @@ export function Chat({ projectPath, onCloseProject }: ChatProps) {
 	const [apiKeyInput, setApiKeyInput] = useState("");
 	const [hasAnthropicKey, setHasAnthropicKey] = useState(false);
 	const [pipeline, setPipeline] = useState<PipelineState>({
-		upcoming: [],
+		backlog: [],
 		current: [],
 		qa: [],
 		merge: [],
@@ -1017,8 +1017,8 @@ export function Chat({ projectPath, onCloseProject }: ChatProps) {
 									onItemClick={(item) => setSelectedWorkItemId(item.story_id)}
 								/>
 								<StagePanel
-									title="Upcoming"
+									title="Backlog"
-									items={pipeline.upcoming}
+									items={pipeline.backlog}
 									onItemClick={(item) => setSelectedWorkItemId(item.story_id)}
 								/>
 							</>

frontend/src/components/ChatInput.tsx

@@ -1,7 +1,14 @@
 import * as React from "react";
 import { api } from "../api/client";
 
-const { forwardRef, useCallback, useEffect, useImperativeHandle, useRef, useState } = React;
+const {
+	forwardRef,
+	useCallback,
+	useEffect,
+	useImperativeHandle,
+	useRef,
+	useState,
+} = React;
 
 export interface ChatInputHandle {
 	appendToInput(text: string): void;
@@ -131,10 +138,13 @@ export const ChatInput = forwardRef<ChatInputHandle, ChatInputProps>(
 		}, []);
 
 		// Compute filtered files for current picker query
-		const filteredFiles = pickerQuery !== null
+		const filteredFiles =
+			pickerQuery !== null
 				? projectFiles
 						.filter((f) => fuzzyMatch(f, pickerQuery))
-				.sort((a, b) => fuzzyScore(a, pickerQuery) - fuzzyScore(b, pickerQuery))
+						.sort(
+							(a, b) => fuzzyScore(a, pickerQuery) - fuzzyScore(b, pickerQuery),
+						)
 						.slice(0, 10)
 				: [];
 
@@ -177,7 +187,10 @@ export const ChatInput = forwardRef<ChatInputHandle, ChatInputProps>(
 
 					// Lazily load files on first trigger
 					if (projectFiles.length === 0) {
-						api.listProjectFiles().then(setProjectFiles).catch(() => {});
+						api
+							.listProjectFiles()
+							.then(setProjectFiles)
+							.catch(() => {});
 					}
 				} else {
 					if (pickerQuery !== null) dismissPicker();
@@ -191,7 +204,9 @@ export const ChatInput = forwardRef<ChatInputHandle, ChatInputProps>(
 				if (pickerQuery !== null && filteredFiles.length > 0) {
 					if (e.key === "ArrowDown") {
 						e.preventDefault();
-						setPickerSelectedIndex((i) => Math.min(i + 1, filteredFiles.length - 1));
+						setPickerSelectedIndex((i) =>
+							Math.min(i + 1, filteredFiles.length - 1),
+						);
 						return;
 					}
 					if (e.key === "ArrowUp") {
@@ -220,7 +235,13 @@ export const ChatInput = forwardRef<ChatInputHandle, ChatInputProps>(
 					handleSubmit();
 				}
 			},
-			[pickerQuery, filteredFiles, pickerSelectedIndex, selectFile, dismissPicker],
+			[
+				pickerQuery,
+				filteredFiles,
+				pickerSelectedIndex,
+				selectFile,
+				dismissPicker,
+			],
 		);
 
 		const handleSubmit = () => {

frontend/src/components/LozengeFlyContext.test.tsx

@@ -9,7 +9,7 @@ import { StagePanel } from "./StagePanel";
 
 function makePipeline(overrides: Partial<PipelineState> = {}): PipelineState {
 	return {
-		upcoming: [],
+		backlog: [],
 		current: [],
 		qa: [],
 		merge: [],

frontend/src/components/LozengeFlyContext.tsx

@@ -115,7 +115,7 @@ export function LozengeFlyProvider({
 	const assignedAgentNames = useMemo(() => {
 		const names = new Set<string>();
 		for (const item of [
-			...pipeline.upcoming,
+			...pipeline.backlog,
 			...pipeline.current,
 			...pipeline.qa,
 			...pipeline.merge,
@@ -165,13 +165,13 @@ export function LozengeFlyProvider({
 
 		const prev = prevPipelineRef.current;
 		const allPrev = [
-			...prev.upcoming,
+			...prev.backlog,
 			...prev.current,
 			...prev.qa,
 			...prev.merge,
 		];
 		const allCurr = [
-			...pipeline.upcoming,
+			...pipeline.backlog,
 			...pipeline.current,
 			...pipeline.qa,
 			...pipeline.merge,

frontend/src/components/WorkItemDetailPanel.tsx

@@ -8,7 +8,7 @@ import { api } from "../api/client";
 const { useEffect, useRef, useState } = React;
 
 const STAGE_LABELS: Record<string, string> = {
-	upcoming: "Upcoming",
+	backlog: "Backlog",
 	current: "Current",
 	qa: "QA",
 	merge: "To Merge",
@@ -420,10 +420,34 @@ export function WorkItemDetailPanel({
 					}}
 				>
 					{/* Agent Logs section */}
+					{!agentInfo && (
 						<div
-						data-testid={
+							data-testid="placeholder-agent-logs"
-							agentInfo ? "agent-logs-section" : "placeholder-agent-logs"
+							style={{
-						}
+								border: "1px solid #2a2a2a",
+								borderRadius: "8px",
+								padding: "10px 12px",
+								background: "#161616",
+							}}
+						>
+							<div
+								style={{
+									fontWeight: 600,
+									fontSize: "0.8em",
+									color: "#555",
+									marginBottom: "4px",
+								}}
+							>
+								Agent Logs
+							</div>
+							<div style={{ fontSize: "0.75em", color: "#444" }}>
+								Coming soon
+							</div>
+						</div>
+					)}
+					{agentInfo && (
+						<div
+							data-testid="agent-logs-section"
 							style={{
 								border: "1px solid #2a2a2a",
 								borderRadius: "8px",
@@ -436,19 +460,19 @@ export function WorkItemDetailPanel({
 									display: "flex",
 									alignItems: "center",
 									justifyContent: "space-between",
-								marginBottom: agentInfo ? "6px" : "4px",
+									marginBottom: "6px",
 								}}
 							>
 								<div
 									style={{
 										fontWeight: 600,
 										fontSize: "0.8em",
-									color: agentInfo ? "#888" : "#555",
+										color: "#888",
 									}}
 								>
 									Agent Logs
 								</div>
-							{agentInfo && agentStatus && (
+								{agentStatus && (
 									<div
 										data-testid="agent-status-badge"
 										style={{
@@ -461,7 +485,7 @@ export function WorkItemDetailPanel({
 									</div>
 								)}
 							</div>
-						{agentInfo && agentLog.length > 0 ? (
+							{agentLog.length > 0 ? (
 								<div
 									data-testid="agent-log-output"
 									style={{
@@ -477,18 +501,15 @@ export function WorkItemDetailPanel({
 								>
 									{agentLog.join("")}
 								</div>
-						) : agentInfo ? (
+							) : (
 								<div style={{ fontSize: "0.75em", color: "#444" }}>
 									{agentStatus === "running" || agentStatus === "pending"
 										? "Waiting for output..."
 										: "No output."}
 								</div>
-						) : (
-							<div style={{ fontSize: "0.75em", color: "#444" }}>
-								Coming soon
-							</div>
 							)}
 						</div>
+					)}
 
 					{/* Placeholder sections for future content */}
 					{(

server/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "story-kit"
-version = "0.3.0"
+version = "0.3.1"
 edition = "2024"
 build = "build.rs"
 

server/src/agents/lifecycle.rs

@@ -16,9 +16,9 @@ pub(super) fn item_type_from_id(item_id: &str) -> &'static str {
     }
 }
 
-/// Return the source directory path for a work item (always work/1_upcoming/).
+/// Return the source directory path for a work item (always work/1_backlog/).
 fn item_source_dir(project_root: &Path, _item_id: &str) -> PathBuf {
-    project_root.join(".story_kit").join("work").join("1_upcoming")
+    project_root.join(".story_kit").join("work").join("1_backlog")
 }
 
 /// Return the done directory path for a work item (always work/5_done/).
@@ -26,10 +26,10 @@ fn item_archive_dir(project_root: &Path, _item_id: &str) -> PathBuf {
     project_root.join(".story_kit").join("work").join("5_done")
 }
 
-/// Move a work item (story, bug, or spike) from `work/1_upcoming/` to `work/2_current/`.
+/// Move a work item (story, bug, or spike) from `work/1_backlog/` to `work/2_current/`.
 ///
 /// Idempotent: if the item is already in `2_current/`, returns Ok without committing.
-/// If the item is not found in `1_upcoming/`, logs a warning and returns Ok.
+/// If the item is not found in `1_backlog/`, logs a warning and returns Ok.
 pub fn move_story_to_current(project_root: &Path, story_id: &str) -> Result<(), String> {
     let sk = project_root.join(".story_kit").join("work");
     let current_dir = sk.join("2_current");
@@ -219,16 +219,16 @@ pub fn move_story_to_qa(project_root: &Path, story_id: &str) -> Result<(), Strin
     Ok(())
 }
 
-/// Move a bug from `work/2_current/` or `work/1_upcoming/` to `work/5_done/` and auto-commit.
+/// Move a bug from `work/2_current/` or `work/1_backlog/` to `work/5_done/` and auto-commit.
 ///
 /// * If the bug is in `2_current/`, it is moved to `5_done/` and committed.
-/// * If the bug is still in `1_upcoming/` (never started), it is moved directly to `5_done/`.
+/// * If the bug is still in `1_backlog/` (never started), it is moved directly to `5_done/`.
 /// * If the bug is already in `5_done/`, this is a no-op (idempotent).
 /// * If the bug is not found anywhere, an error is returned.
 pub fn close_bug_to_archive(project_root: &Path, bug_id: &str) -> Result<(), String> {
     let sk = project_root.join(".story_kit").join("work");
     let current_path = sk.join("2_current").join(format!("{bug_id}.md"));
-    let upcoming_path = sk.join("1_upcoming").join(format!("{bug_id}.md"));
+    let backlog_path = sk.join("1_backlog").join(format!("{bug_id}.md"));
     let archive_dir = item_archive_dir(project_root, bug_id);
     let archive_path = archive_dir.join(format!("{bug_id}.md"));
 
@@ -238,11 +238,11 @@ pub fn close_bug_to_archive(project_root: &Path, bug_id: &str) -> Result<(), Str
 
     let source_path = if current_path.exists() {
         current_path.clone()
-    } else if upcoming_path.exists() {
+    } else if backlog_path.exists() {
-        upcoming_path.clone()
+        backlog_path.clone()
     } else {
         return Err(format!(
-            "Bug '{bug_id}' not found in work/2_current/ or work/1_upcoming/. Cannot close bug."
+            "Bug '{bug_id}' not found in work/2_current/ or work/1_backlog/. Cannot close bug."
         ));
     };
 
@@ -269,15 +269,15 @@ mod tests {
         use std::fs;
         let tmp = tempfile::tempdir().unwrap();
         let root = tmp.path();
-        let upcoming = root.join(".story_kit/work/1_upcoming");
+        let backlog = root.join(".story_kit/work/1_backlog");
         let current = root.join(".story_kit/work/2_current");
-        fs::create_dir_all(&upcoming).unwrap();
+        fs::create_dir_all(&backlog).unwrap();
         fs::create_dir_all(&current).unwrap();
-        fs::write(upcoming.join("10_story_foo.md"), "test").unwrap();
+        fs::write(backlog.join("10_story_foo.md"), "test").unwrap();
 
         move_story_to_current(root, "10_story_foo").unwrap();
 
-        assert!(!upcoming.join("10_story_foo.md").exists());
+        assert!(!backlog.join("10_story_foo.md").exists());
         assert!(current.join("10_story_foo.md").exists());
     }
 
@@ -295,25 +295,25 @@ mod tests {
     }
 
     #[test]
-    fn move_story_to_current_noop_when_not_in_upcoming() {
+    fn move_story_to_current_noop_when_not_in_backlog() {
         let tmp = tempfile::tempdir().unwrap();
         assert!(move_story_to_current(tmp.path(), "99_missing").is_ok());
     }
 
     #[test]
-    fn move_bug_to_current_moves_from_upcoming() {
+    fn move_bug_to_current_moves_from_backlog() {
         use std::fs;
         let tmp = tempfile::tempdir().unwrap();
         let root = tmp.path();
-        let upcoming = root.join(".story_kit/work/1_upcoming");
+        let backlog = root.join(".story_kit/work/1_backlog");
         let current = root.join(".story_kit/work/2_current");
-        fs::create_dir_all(&upcoming).unwrap();
+        fs::create_dir_all(&backlog).unwrap();
         fs::create_dir_all(&current).unwrap();
-        fs::write(upcoming.join("1_bug_test.md"), "# Bug 1\n").unwrap();
+        fs::write(backlog.join("1_bug_test.md"), "# Bug 1\n").unwrap();
 
         move_story_to_current(root, "1_bug_test").unwrap();
 
-        assert!(!upcoming.join("1_bug_test.md").exists());
+        assert!(!backlog.join("1_bug_test.md").exists());
         assert!(current.join("1_bug_test.md").exists());
     }
 
@@ -335,17 +335,17 @@ mod tests {
     }
 
     #[test]
-    fn close_bug_moves_from_upcoming_when_not_started() {
+    fn close_bug_moves_from_backlog_when_not_started() {
         use std::fs;
         let tmp = tempfile::tempdir().unwrap();
         let root = tmp.path();
-        let upcoming = root.join(".story_kit/work/1_upcoming");
+        let backlog = root.join(".story_kit/work/1_backlog");
-        fs::create_dir_all(&upcoming).unwrap();
+        fs::create_dir_all(&backlog).unwrap();
-        fs::write(upcoming.join("3_bug_test.md"), "# Bug 3\n").unwrap();
+        fs::write(backlog.join("3_bug_test.md"), "# Bug 3\n").unwrap();
 
         close_bug_to_archive(root, "3_bug_test").unwrap();
 
-        assert!(!upcoming.join("3_bug_test.md").exists());
+        assert!(!backlog.join("3_bug_test.md").exists());
         assert!(root.join(".story_kit/work/5_done/3_bug_test.md").exists());
     }
 

server/src/agents/pool.rs

@@ -212,7 +212,7 @@ impl AgentPool {
         let event_log: Arc<Mutex<Vec<AgentEvent>>> = Arc::new(Mutex::new(Vec::new()));
         let log_session_id = uuid::Uuid::new_v4().to_string();
 
-        // Move story from upcoming/ to current/ before checking agent
+        // Move story from backlog/ to current/ before checking agent
         // availability so that auto_assign_available_work can pick it up even
         // when all coders are currently busy (story 203).  This is idempotent:
         // if the story is already in 2_current/ or a later stage, the call is
@@ -1430,7 +1430,7 @@ impl AgentPool {
     ///
     /// Scans `work/2_current/`, `work/3_qa/`, and `work/4_merge/` for items that have no
     /// active agent and assigns the first free agent of the appropriate role. Items in
-    /// `work/1_upcoming/` are never auto-started.
+    /// `work/1_backlog/` are never auto-started.
     ///
     /// Respects the configured agent roster: the maximum number of concurrently active agents
     /// per role is bounded by the count of agents of that role defined in `project.toml`.
@@ -1603,7 +1603,7 @@ impl AgentPool {
             // Determine which active stage the story is in.
             let stage_dir = match find_active_story_stage(project_root, story_id) {
                 Some(s) => s,
-                None => continue, // Not in any active stage (upcoming/archived or unknown).
+                None => continue, // Not in any active stage (backlog/archived or unknown).
             };
 
             // 4_merge/ is left for auto_assign to handle with a fresh mergemaster.
@@ -2728,8 +2728,8 @@ mod tests {
         fs::write(current.join("173_story_test.md"), "test").unwrap();
         // Ensure 3_qa/ exists for the move target
         fs::create_dir_all(root.join(".story_kit/work/3_qa")).unwrap();
-        // Ensure 1_upcoming/ exists (start_agent calls move_story_to_current)
+        // Ensure 1_backlog/ exists (start_agent calls move_story_to_current)
-        fs::create_dir_all(root.join(".story_kit/work/1_upcoming")).unwrap();
+        fs::create_dir_all(root.join(".story_kit/work/1_backlog")).unwrap();
 
         // Write a project.toml with a qa agent so start_agent can resolve it.
         fs::create_dir_all(root.join(".story_kit")).unwrap();
@@ -3498,14 +3498,14 @@ stage = "coder"
     }
 
     /// Story 203: when all coders are busy the story file must be moved from
-    /// 1_upcoming/ to 2_current/ so that auto_assign_available_work can pick
+    /// 1_backlog/ to 2_current/ so that auto_assign_available_work can pick
     /// it up once a coder finishes.
     #[tokio::test]
     async fn start_agent_moves_story_to_current_when_coders_busy() {
         let tmp = tempfile::tempdir().unwrap();
         let sk = tmp.path().join(".story_kit");
-        let upcoming = sk.join("work/1_upcoming");
+        let backlog = sk.join("work/1_backlog");
-        std::fs::create_dir_all(&upcoming).unwrap();
+        std::fs::create_dir_all(&backlog).unwrap();
         std::fs::write(
             sk.join("project.toml"),
             r#"
@@ -3515,9 +3515,9 @@ stage = "coder"
 "#,
         )
         .unwrap();
-        // Place the story in 1_upcoming/.
+        // Place the story in 1_backlog/.
         std::fs::write(
-            upcoming.join("story-3.md"),
+            backlog.join("story-3.md"),
             "---\nname: Story 3\n---\n",
         )
         .unwrap();
@@ -3547,10 +3547,10 @@ stage = "coder"
             current_path.exists(),
             "story should be in 2_current/ after busy error, but was not"
         );
-        let upcoming_path = upcoming.join("story-3.md");
+        let backlog_path = backlog.join("story-3.md");
         assert!(
-            !upcoming_path.exists(),
+            !backlog_path.exists(),
-            "story should no longer be in 1_upcoming/"
+            "story should no longer be in 1_backlog/"
         );
     }
 
@@ -3774,7 +3774,7 @@ stage = "coder"
 
         // Create the story in upcoming so `move_story_to_current` succeeds,
         // but do NOT init a git repo — `create_worktree` will fail in the spawn.
-        let upcoming = root.join(".story_kit/work/1_upcoming");
+        let upcoming = root.join(".story_kit/work/1_backlog");
         fs::create_dir_all(&upcoming).unwrap();
         fs::write(
             upcoming.join("50_story_test.md"),
@@ -3924,7 +3924,7 @@ stage = "coder"
         let root = tmp.path().to_path_buf();
 
         let sk_dir = root.join(".story_kit");
-        fs::create_dir_all(sk_dir.join("work/1_upcoming")).unwrap();
+        fs::create_dir_all(sk_dir.join("work/1_backlog")).unwrap();
         fs::write(
             root.join(".story_kit/project.toml"),
             "[[agent]]\nname = \"coder-1\"\n",
@@ -3933,12 +3933,12 @@ stage = "coder"
         // Both stories must exist in upcoming so move_story_to_current can run
         // (only the winner reaches that point, but we set both up defensively).
         fs::write(
-            root.join(".story_kit/work/1_upcoming/86_story_foo.md"),
+            root.join(".story_kit/work/1_backlog/86_story_foo.md"),
             "---\nname: Foo\n---\n",
         )
         .unwrap();
         fs::write(
-            root.join(".story_kit/work/1_upcoming/130_story_bar.md"),
+            root.join(".story_kit/work/1_backlog/130_story_bar.md"),
             "---\nname: Bar\n---\n",
         )
         .unwrap();
@@ -4138,14 +4138,14 @@ stage = "coder"
         let root = tmp.path();
 
         let sk_dir = root.join(".story_kit");
-        fs::create_dir_all(sk_dir.join("work/1_upcoming")).unwrap();
+        fs::create_dir_all(sk_dir.join("work/1_backlog")).unwrap();
         fs::write(
             root.join(".story_kit/project.toml"),
             "[[agent]]\nname = \"coder-1\"\n\n[[agent]]\nname = \"coder-2\"\n",
         )
         .unwrap();
         fs::write(
-            root.join(".story_kit/work/1_upcoming/99_story_baz.md"),
+            root.join(".story_kit/work/1_backlog/99_story_baz.md"),
             "---\nname: Baz\n---\n",
         )
         .unwrap();

server/src/http/agents.rs

@@ -339,7 +339,7 @@ impl AgentsApi {
             .map_err(bad_request)?;
 
         let stages = [
-            ("1_upcoming", "upcoming"),
+            ("1_backlog", "backlog"),
             ("2_current", "current"),
             ("3_qa", "qa"),
             ("4_merge", "merge"),
@@ -809,12 +809,12 @@ allowed_tools = ["Read", "Bash"]
     }
 
     #[tokio::test]
-    async fn get_work_item_content_returns_content_from_upcoming() {
+    async fn get_work_item_content_returns_content_from_backlog() {
         let tmp = TempDir::new().unwrap();
         let root = tmp.path();
-        make_stage_dir(root, "1_upcoming");
+        make_stage_dir(root, "1_backlog");
         std::fs::write(
-            root.join(".story_kit/work/1_upcoming/42_story_foo.md"),
+            root.join(".story_kit/work/1_backlog/42_story_foo.md"),
             "---\nname: \"Foo Story\"\n---\n\n# Story 42: Foo Story\n\nSome content.",
         )
         .unwrap();
@@ -828,7 +828,7 @@ allowed_tools = ["Read", "Bash"]
             .unwrap()
             .0;
         assert!(result.content.contains("Some content."));
-        assert_eq!(result.stage, "upcoming");
+        assert_eq!(result.stage, "backlog");
         assert_eq!(result.name, Some("Foo Story".to_string()));
     }
 
@@ -1113,7 +1113,7 @@ allowed_tools = ["Read", "Bash"]
         let tmp = TempDir::new().unwrap();
         let root = tmp.path().to_path_buf();
         // Create work dirs including 2_current for the story file.
-        for stage in &["1_upcoming", "2_current", "5_done", "6_archived"] {
+        for stage in &["1_backlog", "2_current", "5_done", "6_archived"] {
             std::fs::create_dir_all(root.join(".story_kit").join("work").join(stage)).unwrap();
         }
 

server/src/http/mcp.rs

@@ -1,4 +1,4 @@
-use crate::agents::{close_bug_to_archive, feature_branch_has_unmerged_changes, move_story_to_archived, move_story_to_merge, move_story_to_qa, PipelineStage};
+use crate::agents::{close_bug_to_archive, feature_branch_has_unmerged_changes, move_story_to_archived, move_story_to_merge, move_story_to_qa, AgentStatus, PipelineStage};
 use crate::config::ProjectConfig;
 use crate::log_buffer;
 use crate::slog;
@@ -672,7 +672,7 @@ fn handle_tools_list(id: Option<Value>) -> JsonRpcResponse {
                 },
                 {
                     "name": "create_spike",
-                    "description": "Create a spike file in .story_kit/work/1_upcoming/ with a deterministic filename and YAML front matter. Returns the spike_id.",
+                    "description": "Create a spike file in .story_kit/work/1_backlog/ with a deterministic filename and YAML front matter. Returns the spike_id.",
                     "inputSchema": {
                         "type": "object",
                         "properties": {
@@ -690,7 +690,7 @@ fn handle_tools_list(id: Option<Value>) -> JsonRpcResponse {
                 },
                 {
                     "name": "create_bug",
-                    "description": "Create a bug file in work/1_upcoming/ with a deterministic filename and auto-commit to master. Returns the bug_id.",
+                    "description": "Create a bug file in work/1_backlog/ with a deterministic filename and auto-commit to master. Returns the bug_id.",
                     "inputSchema": {
                         "type": "object",
                         "properties": {
@@ -725,7 +725,7 @@ fn handle_tools_list(id: Option<Value>) -> JsonRpcResponse {
                 },
                 {
                     "name": "list_bugs",
-                    "description": "List all open bugs in work/1_upcoming/ matching the _bug_ naming convention.",
+                    "description": "List all open bugs in work/1_backlog/ matching the _bug_ naming convention.",
                     "inputSchema": {
                         "type": "object",
                         "properties": {}
@@ -733,7 +733,7 @@ fn handle_tools_list(id: Option<Value>) -> JsonRpcResponse {
                 },
                 {
                     "name": "create_refactor",
-                    "description": "Create a refactor work item in work/1_upcoming/ with a deterministic filename and YAML front matter. Returns the refactor_id.",
+                    "description": "Create a refactor work item in work/1_backlog/ with a deterministic filename and YAML front matter. Returns the refactor_id.",
                     "inputSchema": {
                         "type": "object",
                         "properties": {
@@ -756,7 +756,7 @@ fn handle_tools_list(id: Option<Value>) -> JsonRpcResponse {
                 },
                 {
                     "name": "list_refactors",
-                    "description": "List all open refactors in work/1_upcoming/ matching the _refactor_ naming convention.",
+                    "description": "List all open refactors in work/1_backlog/ matching the _refactor_ naming convention.",
                     "inputSchema": {
                         "type": "object",
                         "properties": {}
@@ -764,7 +764,7 @@ fn handle_tools_list(id: Option<Value>) -> JsonRpcResponse {
                 },
                 {
                     "name": "close_bug",
-                    "description": "Archive a bug from work/2_current/ or work/1_upcoming/ to work/5_done/ and auto-commit to master.",
+                    "description": "Archive a bug from work/2_current/ or work/1_backlog/ to work/5_done/ and auto-commit to master.",
                     "inputSchema": {
                         "type": "object",
                         "properties": {
@@ -891,6 +891,14 @@ fn handle_tools_list(id: Option<Value>) -> JsonRpcResponse {
                         }
                     }
                 },
+                {
+                    "name": "rebuild_and_restart",
+                    "description": "Rebuild the server binary from source and re-exec with the new binary. Gracefully stops all running agents before restart. If the build fails, the server stays up and returns the build error.",
+                    "inputSchema": {
+                        "type": "object",
+                        "properties": {}
+                    }
+                },
                 {
                     "name": "prompt_permission",
                     "description": "Present a permission request to the user via the web UI. Used by Claude Code's --permission-prompt-tool to delegate permission decisions to the frontend dialog. Returns on approval; returns an error on denial.",
@@ -975,6 +983,8 @@ async fn handle_tools_call(
         "get_pipeline_status" => tool_get_pipeline_status(ctx),
         // Diagnostics
         "get_server_logs" => tool_get_server_logs(&args),
+        // Server lifecycle
+        "rebuild_and_restart" => tool_rebuild_and_restart(ctx).await,
         // Permission bridge (Claude Code → frontend dialog)
         "prompt_permission" => tool_prompt_permission(&args, ctx).await,
         _ => Err(format!("Unknown tool: {tool_name}")),
@@ -1012,7 +1022,7 @@ fn tool_create_story(args: &Value, ctx: &AppContext) -> Result<String, String> {
         .get("acceptance_criteria")
         .and_then(|v| serde_json::from_value(v.clone()).ok());
     // Spike 61: write the file only — the filesystem watcher detects the new
-    // .md file in work/1_upcoming/ and auto-commits with a deterministic message.
+    // .md file in work/1_backlog/ and auto-commits with a deterministic message.
     let commit = false;
 
     let root = ctx.state.get_project_root()?;
@@ -1081,16 +1091,16 @@ fn tool_get_pipeline_status(ctx: &AppContext) -> Result<String, String> {
     active.extend(map_items(&state.merge, "merge"));
     active.extend(map_items(&state.done, "done"));
 
-    let upcoming: Vec<Value> = state
+    let backlog: Vec<Value> = state
-        .upcoming
+        .backlog
         .iter()
         .map(|s| json!({ "story_id": s.story_id, "name": s.name }))
         .collect();
 
     serde_json::to_string_pretty(&json!({
         "active": active,
-        "upcoming": upcoming,
+        "backlog": backlog,
-        "upcoming_count": upcoming.len(),
+        "backlog_count": backlog.len(),
     }))
     .map_err(|e| format!("Serialization error: {e}"))
 }
@@ -2108,6 +2118,100 @@ fn add_permission_rule(project_root: &std::path::Path, rule: &str) -> Result<(),
     Ok(())
 }
 
+/// Rebuild the server binary and re-exec.
+///
+/// 1. Gracefully stops all running agents (kills PTY children).
+/// 2. Runs `cargo build [-p story-kit]` from the workspace root, matching
+///    the current build profile (debug or release).
+/// 3. If the build fails, returns the build error (server stays up).
+/// 4. If the build succeeds, re-execs the process with the new binary via
+///    `std::os::unix::process::CommandExt::exec()`.
+async fn tool_rebuild_and_restart(ctx: &AppContext) -> Result<String, String> {
+    slog!("[rebuild] Rebuild and restart requested via MCP tool");
+
+    // 1. Gracefully stop all running agents.
+    let running_agents = ctx.agents.list_agents().unwrap_or_default();
+    let running_count = running_agents
+        .iter()
+        .filter(|a| a.status == AgentStatus::Running)
+        .count();
+    if running_count > 0 {
+        slog!("[rebuild] Stopping {running_count} running agent(s) before rebuild");
+    }
+    ctx.agents.kill_all_children();
+
+    // 2. Find the workspace root (parent of the server binary's source).
+    //    CARGO_MANIFEST_DIR at compile time points to the `server/` crate;
+    //    the workspace root is its parent.
+    let manifest_dir = std::path::Path::new(env!("CARGO_MANIFEST_DIR"));
+    let workspace_root = manifest_dir
+        .parent()
+        .ok_or_else(|| "Cannot determine workspace root from CARGO_MANIFEST_DIR".to_string())?;
+
+    slog!(
+        "[rebuild] Building server from workspace root: {}",
+        workspace_root.display()
+    );
+
+    // 3. Build the server binary, matching the current build profile so the
+    //    re-exec via current_exe() picks up the new binary.
+    let build_args: Vec<&str> = if cfg!(debug_assertions) {
+        vec!["build", "-p", "story-kit"]
+    } else {
+        vec!["build", "--release", "-p", "story-kit"]
+    };
+    slog!("[rebuild] cargo {}", build_args.join(" "));
+    let output = tokio::task::spawn_blocking({
+        let workspace_root = workspace_root.to_path_buf();
+        move || {
+            std::process::Command::new("cargo")
+                .args(&build_args)
+                .current_dir(&workspace_root)
+                .output()
+        }
+    })
+    .await
+    .map_err(|e| format!("Build task panicked: {e}"))?
+    .map_err(|e| format!("Failed to run cargo build: {e}"))?;
+
+    if !output.status.success() {
+        let stderr = String::from_utf8_lossy(&output.stderr);
+        slog!("[rebuild] Build failed:\n{stderr}");
+        return Err(format!("Build failed:\n{stderr}"));
+    }
+
+    slog!("[rebuild] Build succeeded, re-execing with new binary");
+
+    // 4. Re-exec with the new binary.
+    //    Collect current argv so we preserve any CLI arguments (e.g. project path).
+    let current_exe = std::env::current_exe()
+        .map_err(|e| format!("Cannot determine current executable: {e}"))?;
+    let args: Vec<String> = std::env::args().collect();
+
+    // Remove the port file before re-exec so the new process can write its own.
+    if let Ok(root) = ctx.state.get_project_root() {
+        let port_file = root.join(".story_kit_port");
+        if port_file.exists() {
+            let _ = std::fs::remove_file(&port_file);
+        }
+    }
+    // Also check cwd for port file.
+    let cwd_port_file = std::path::Path::new(".story_kit_port");
+    if cwd_port_file.exists() {
+        let _ = std::fs::remove_file(cwd_port_file);
+    }
+
+    // Use exec() to replace the current process.
+    // This never returns on success.
+    use std::os::unix::process::CommandExt;
+    let err = std::process::Command::new(&current_exe)
+        .args(&args[1..])
+        .exec();
+
+    // If we get here, exec() failed.
+    Err(format!("Failed to exec new binary: {err}"))
+}
+
 /// MCP tool called by Claude Code via `--permission-prompt-tool`.
 ///
 /// Forwards the permission request through the shared channel to the active
@@ -2282,7 +2386,8 @@ mod tests {
         assert!(names.contains(&"get_server_logs"));
         assert!(names.contains(&"prompt_permission"));
         assert!(names.contains(&"get_pipeline_status"));
-        assert_eq!(tools.len(), 35);
+        assert!(names.contains(&"rebuild_and_restart"));
+        assert_eq!(tools.len(), 36);
     }
 
     #[test]
@@ -2355,7 +2460,7 @@ mod tests {
         let root = tmp.path();
 
         for (stage, id, name) in &[
-            ("1_upcoming", "10_story_upcoming", "Upcoming Story"),
+            ("1_backlog", "10_story_upcoming", "Upcoming Story"),
             ("2_current", "20_story_current", "Current Story"),
             ("3_qa", "30_story_qa", "QA Story"),
             ("4_merge", "40_story_merge", "Merge Story"),
@@ -2384,11 +2489,11 @@ mod tests {
         assert!(stages.contains(&"merge"));
         assert!(stages.contains(&"done"));
 
-        // Upcoming backlog
+        // Backlog
-        let upcoming = parsed["upcoming"].as_array().unwrap();
+        let backlog = parsed["backlog"].as_array().unwrap();
-        assert_eq!(upcoming.len(), 1);
+        assert_eq!(backlog.len(), 1);
-        assert_eq!(upcoming[0]["story_id"], "10_story_upcoming");
+        assert_eq!(backlog[0]["story_id"], "10_story_upcoming");
-        assert_eq!(parsed["upcoming_count"], 1);
+        assert_eq!(parsed["backlog_count"], 1);
     }
 
     #[test]
@@ -2704,8 +2809,8 @@ mod tests {
         let t = tool.unwrap();
         let desc = t["description"].as_str().unwrap();
         assert!(
-            desc.contains("work/1_upcoming/"),
+            desc.contains("work/1_backlog/"),
-            "create_bug description should reference work/1_upcoming/, got: {desc}"
+            "create_bug description should reference work/1_backlog/, got: {desc}"
         );
         assert!(
             !desc.contains(".story_kit/bugs"),
@@ -2729,8 +2834,8 @@ mod tests {
         let t = tool.unwrap();
         let desc = t["description"].as_str().unwrap();
         assert!(
-            desc.contains("work/1_upcoming/"),
+            desc.contains("work/1_backlog/"),
-            "list_bugs description should reference work/1_upcoming/, got: {desc}"
+            "list_bugs description should reference work/1_backlog/, got: {desc}"
         );
         assert!(
             !desc.contains(".story_kit/bugs"),
@@ -2814,7 +2919,7 @@ mod tests {
         assert!(result.contains("1_bug_login_crash"));
         let bug_file = tmp
             .path()
-            .join(".story_kit/work/1_upcoming/1_bug_login_crash.md");
+            .join(".story_kit/work/1_backlog/1_bug_login_crash.md");
         assert!(bug_file.exists());
     }
 
@@ -2830,15 +2935,15 @@ mod tests {
     #[test]
     fn tool_list_bugs_returns_open_bugs() {
         let tmp = tempfile::tempdir().unwrap();
-        let upcoming_dir = tmp.path().join(".story_kit/work/1_upcoming");
+        let backlog_dir = tmp.path().join(".story_kit/work/1_backlog");
-        std::fs::create_dir_all(&upcoming_dir).unwrap();
+        std::fs::create_dir_all(&backlog_dir).unwrap();
         std::fs::write(
-            upcoming_dir.join("1_bug_crash.md"),
+            backlog_dir.join("1_bug_crash.md"),
             "# Bug 1: App Crash\n",
         )
         .unwrap();
         std::fs::write(
-            upcoming_dir.join("2_bug_typo.md"),
+            backlog_dir.join("2_bug_typo.md"),
             "# Bug 2: Typo in Header\n",
         )
         .unwrap();
@@ -2866,9 +2971,9 @@ mod tests {
     fn tool_close_bug_moves_to_archive() {
         let tmp = tempfile::tempdir().unwrap();
         setup_git_repo_in(tmp.path());
-        let upcoming_dir = tmp.path().join(".story_kit/work/1_upcoming");
+        let backlog_dir = tmp.path().join(".story_kit/work/1_backlog");
-        std::fs::create_dir_all(&upcoming_dir).unwrap();
+        std::fs::create_dir_all(&backlog_dir).unwrap();
-        let bug_file = upcoming_dir.join("1_bug_crash.md");
+        let bug_file = backlog_dir.join("1_bug_crash.md");
         std::fs::write(&bug_file, "# Bug 1: Crash\n").unwrap();
         // Stage the file so it's tracked
         std::process::Command::new("git")
@@ -2938,7 +3043,7 @@ mod tests {
         assert!(result.contains("1_spike_compare_encoders"));
         let spike_file = tmp
             .path()
-            .join(".story_kit/work/1_upcoming/1_spike_compare_encoders.md");
+            .join(".story_kit/work/1_backlog/1_spike_compare_encoders.md");
         assert!(spike_file.exists());
         let contents = std::fs::read_to_string(&spike_file).unwrap();
         assert!(contents.starts_with("---\nname: \"Compare Encoders\"\n---"));
@@ -2953,7 +3058,7 @@ mod tests {
         let result = tool_create_spike(&json!({"name": "My Spike"}), &ctx).unwrap();
         assert!(result.contains("1_spike_my_spike"));
 
-        let spike_file = tmp.path().join(".story_kit/work/1_upcoming/1_spike_my_spike.md");
+        let spike_file = tmp.path().join(".story_kit/work/1_backlog/1_spike_my_spike.md");
         assert!(spike_file.exists());
         let contents = std::fs::read_to_string(&spike_file).unwrap();
         assert!(contents.starts_with("---\nname: \"My Spike\"\n---"));
@@ -4169,4 +4274,56 @@ stage = "coder"
         assert_eq!(servers.len(), 1);
         assert_eq!(servers[0], "story-kit");
     }
+
+    // ── rebuild_and_restart ──────────────────────────────────────────
+
+    #[test]
+    fn rebuild_and_restart_in_tools_list() {
+        let resp = handle_tools_list(Some(json!(1)));
+        let tools = resp.result.unwrap()["tools"].as_array().unwrap().clone();
+        let tool = tools.iter().find(|t| t["name"] == "rebuild_and_restart");
+        assert!(
+            tool.is_some(),
+            "rebuild_and_restart missing from tools list"
+        );
+        let t = tool.unwrap();
+        assert!(t["description"].as_str().unwrap().contains("Rebuild"));
+        assert!(t["inputSchema"].is_object());
+    }
+
+    #[tokio::test]
+    async fn rebuild_and_restart_kills_agents_before_build() {
+        // Verify that calling rebuild_and_restart on an empty pool doesn't
+        // panic and proceeds to the build step. We can't test exec() in a
+        // unit test, but we can verify the build attempt happens.
+        let tmp = tempfile::tempdir().unwrap();
+        let ctx = test_ctx(tmp.path());
+
+        // The build will succeed (we're running in the real workspace) and
+        // then exec() will be called — which would replace our test process.
+        // So we only test that the function *runs* without panicking up to
+        // the agent-kill step. We do this by checking the pool is empty.
+        assert_eq!(ctx.agents.list_agents().unwrap().len(), 0);
+        ctx.agents.kill_all_children(); // should not panic on empty pool
+    }
+
+    #[test]
+    fn rebuild_uses_matching_build_profile() {
+        // The build must use the same profile (debug/release) as the running
+        // binary, otherwise cargo build outputs to a different target dir and
+        // current_exe() still points at the old binary.
+        let build_args: Vec<&str> = if cfg!(debug_assertions) {
+            vec!["build", "-p", "story-kit"]
+        } else {
+            vec!["build", "--release", "-p", "story-kit"]
+        };
+
+        // Tests always run in debug mode, so --release must NOT be present.
+        assert!(
+            !build_args.contains(&"--release"),
+            "In debug builds, rebuild must not pass --release (would put \
+             the binary in target/release/ while current_exe() points to \
+             target/debug/)"
+        );
+    }
 }

server/src/http/workflow.rs

@@ -35,7 +35,7 @@ pub struct StoryValidationResult {
 /// Full pipeline state across all stages.
 #[derive(Clone, Debug, Serialize)]
 pub struct PipelineState {
-    pub upcoming: Vec<UpcomingStory>,
+    pub backlog: Vec<UpcomingStory>,
     pub current: Vec<UpcomingStory>,
     pub qa: Vec<UpcomingStory>,
     pub merge: Vec<UpcomingStory>,
@@ -46,7 +46,7 @@ pub struct PipelineState {
 pub fn load_pipeline_state(ctx: &AppContext) -> Result<PipelineState, String> {
     let agent_map = build_active_agent_map(ctx);
     Ok(PipelineState {
-        upcoming: load_stage_items(ctx, "1_upcoming", &HashMap::new())?,
+        backlog: load_stage_items(ctx, "1_backlog", &HashMap::new())?,
         current: load_stage_items(ctx, "2_current", &agent_map)?,
         qa: load_stage_items(ctx, "3_qa", &agent_map)?,
         merge: load_stage_items(ctx, "4_merge", &agent_map)?,
@@ -130,7 +130,7 @@ fn load_stage_items(
 }
 
 pub fn load_upcoming_stories(ctx: &AppContext) -> Result<Vec<UpcomingStory>, String> {
-    load_stage_items(ctx, "1_upcoming", &HashMap::new())
+    load_stage_items(ctx, "1_backlog", &HashMap::new())
 }
 
 /// Shared create-story logic used by both the OpenApi and MCP handlers.
@@ -152,11 +152,11 @@ pub fn create_story_file(
     }
 
     let filename = format!("{story_number}_story_{slug}.md");
-    let upcoming_dir = root.join(".story_kit").join("work").join("1_upcoming");
+    let backlog_dir = root.join(".story_kit").join("work").join("1_backlog");
-    fs::create_dir_all(&upcoming_dir)
+    fs::create_dir_all(&backlog_dir)
-        .map_err(|e| format!("Failed to create upcoming directory: {e}"))?;
+        .map_err(|e| format!("Failed to create backlog directory: {e}"))?;
 
-    let filepath = upcoming_dir.join(&filename);
+    let filepath = backlog_dir.join(&filename);
     if filepath.exists() {
         return Err(format!("Story file already exists: {filename}"));
     }
@@ -206,7 +206,7 @@ pub fn create_story_file(
 
 // ── Bug file helpers ──────────────────────────────────────────────
 
-/// Create a bug file in `work/1_upcoming/` with a deterministic filename and auto-commit.
+/// Create a bug file in `work/1_backlog/` with a deterministic filename and auto-commit.
 ///
 /// Returns the bug_id (e.g. `"4_bug_login_crash"`).
 pub fn create_bug_file(
@@ -226,9 +226,9 @@ pub fn create_bug_file(
     }
 
     let filename = format!("{bug_number}_bug_{slug}.md");
-    let bugs_dir = root.join(".story_kit").join("work").join("1_upcoming");
+    let bugs_dir = root.join(".story_kit").join("work").join("1_backlog");
     fs::create_dir_all(&bugs_dir)
-        .map_err(|e| format!("Failed to create upcoming directory: {e}"))?;
+        .map_err(|e| format!("Failed to create backlog directory: {e}"))?;
 
     let filepath = bugs_dir.join(&filename);
     if filepath.exists() {
@@ -276,7 +276,7 @@ pub fn create_bug_file(
 
 // ── Spike file helpers ────────────────────────────────────────────
 
-/// Create a spike file in `work/1_upcoming/` with a deterministic filename.
+/// Create a spike file in `work/1_backlog/` with a deterministic filename.
 ///
 /// Returns the spike_id (e.g. `"4_spike_filesystem_watcher_architecture"`).
 pub fn create_spike_file(
@@ -292,11 +292,11 @@ pub fn create_spike_file(
     }
 
     let filename = format!("{spike_number}_spike_{slug}.md");
-    let upcoming_dir = root.join(".story_kit").join("work").join("1_upcoming");
+    let backlog_dir = root.join(".story_kit").join("work").join("1_backlog");
-    fs::create_dir_all(&upcoming_dir)
+    fs::create_dir_all(&backlog_dir)
-        .map_err(|e| format!("Failed to create upcoming directory: {e}"))?;
+        .map_err(|e| format!("Failed to create backlog directory: {e}"))?;
 
-    let filepath = upcoming_dir.join(&filename);
+    let filepath = backlog_dir.join(&filename);
     if filepath.exists() {
         return Err(format!("Spike file already exists: {filename}"));
     }
@@ -338,7 +338,7 @@ pub fn create_spike_file(
     Ok(spike_id)
 }
 
-/// Create a refactor work item file in `work/1_upcoming/`.
+/// Create a refactor work item file in `work/1_backlog/`.
 ///
 /// Returns the refactor_id (e.g. `"5_refactor_split_agents_rs"`).
 pub fn create_refactor_file(
@@ -355,11 +355,11 @@ pub fn create_refactor_file(
     }
 
     let filename = format!("{refactor_number}_refactor_{slug}.md");
-    let upcoming_dir = root.join(".story_kit").join("work").join("1_upcoming");
+    let backlog_dir = root.join(".story_kit").join("work").join("1_backlog");
-    fs::create_dir_all(&upcoming_dir)
+    fs::create_dir_all(&backlog_dir)
-        .map_err(|e| format!("Failed to create upcoming directory: {e}"))?;
+        .map_err(|e| format!("Failed to create backlog directory: {e}"))?;
 
-    let filepath = upcoming_dir.join(&filename);
+    let filepath = backlog_dir.join(&filename);
     if filepath.exists() {
         return Err(format!("Refactor file already exists: {filename}"));
     }
@@ -427,18 +427,18 @@ fn extract_bug_name(path: &Path) -> Option<String> {
     None
 }
 
-/// List all open bugs — files in `work/1_upcoming/` matching the `_bug_` naming pattern.
+/// List all open bugs — files in `work/1_backlog/` matching the `_bug_` naming pattern.
 ///
 /// Returns a sorted list of `(bug_id, name)` pairs.
 pub fn list_bug_files(root: &Path) -> Result<Vec<(String, String)>, String> {
-    let upcoming_dir = root.join(".story_kit").join("work").join("1_upcoming");
+    let backlog_dir = root.join(".story_kit").join("work").join("1_backlog");
-    if !upcoming_dir.exists() {
+    if !backlog_dir.exists() {
         return Ok(Vec::new());
     }
 
     let mut bugs = Vec::new();
     for entry in
-        fs::read_dir(&upcoming_dir).map_err(|e| format!("Failed to read upcoming directory: {e}"))?
+        fs::read_dir(&backlog_dir).map_err(|e| format!("Failed to read backlog directory: {e}"))?
     {
         let entry = entry.map_err(|e| format!("Failed to read entry: {e}"))?;
         let path = entry.path();
@@ -477,18 +477,18 @@ fn is_refactor_item(stem: &str) -> bool {
     after_num.starts_with("_refactor_")
 }
 
-/// List all open refactors — files in `work/1_upcoming/` matching the `_refactor_` naming pattern.
+/// List all open refactors — files in `work/1_backlog/` matching the `_refactor_` naming pattern.
 ///
 /// Returns a sorted list of `(refactor_id, name)` pairs.
 pub fn list_refactor_files(root: &Path) -> Result<Vec<(String, String)>, String> {
-    let upcoming_dir = root.join(".story_kit").join("work").join("1_upcoming");
+    let backlog_dir = root.join(".story_kit").join("work").join("1_backlog");
-    if !upcoming_dir.exists() {
+    if !backlog_dir.exists() {
         return Ok(Vec::new());
     }
 
     let mut refactors = Vec::new();
-    for entry in fs::read_dir(&upcoming_dir)
+    for entry in fs::read_dir(&backlog_dir)
-        .map_err(|e| format!("Failed to read upcoming directory: {e}"))?
+        .map_err(|e| format!("Failed to read backlog directory: {e}"))?
     {
         let entry = entry.map_err(|e| format!("Failed to read entry: {e}"))?;
         let path = entry.path();
@@ -525,11 +525,11 @@ pub fn list_refactor_files(root: &Path) -> Result<Vec<(String, String)>, String>
 
 /// Locate a work item file by searching all active pipeline stages.
 ///
-/// Searches in priority order: 2_current, 1_upcoming, 3_qa, 4_merge, 5_done, 6_archived.
+/// Searches in priority order: 2_current, 1_backlog, 3_qa, 4_merge, 5_done, 6_archived.
 fn find_story_file(project_root: &Path, story_id: &str) -> Result<PathBuf, String> {
     let filename = format!("{story_id}.md");
     let sk = project_root.join(".story_kit").join("work");
-    for stage in &["2_current", "1_upcoming", "3_qa", "4_merge", "5_done", "6_archived"] {
+    for stage in &["2_current", "1_backlog", "3_qa", "4_merge", "5_done", "6_archived"] {
         let path = sk.join(stage).join(&filename);
         if path.exists() {
             return Ok(path);
@@ -778,7 +778,7 @@ fn next_item_number(root: &std::path::Path) -> Result<u32, String> {
     let work_base = root.join(".story_kit").join("work");
     let mut max_num: u32 = 0;
 
-    for subdir in &["1_upcoming", "2_current", "3_qa", "4_merge", "5_done", "6_archived"] {
+    for subdir in &["1_backlog", "2_current", "3_qa", "4_merge", "5_done", "6_archived"] {
         let dir = work_base.join(subdir);
         if !dir.exists() {
             continue;
@@ -973,10 +973,10 @@ pub fn validate_story_dirs(
 ) -> Result<Vec<StoryValidationResult>, String> {
     let mut results = Vec::new();
 
-    // Directories to validate: work/2_current/ + work/1_upcoming/
+    // Directories to validate: work/2_current/ + work/1_backlog/
     let dirs_to_validate: Vec<PathBuf> = vec![
         root.join(".story_kit").join("work").join("2_current"),
-        root.join(".story_kit").join("work").join("1_upcoming"),
+        root.join(".story_kit").join("work").join("1_backlog"),
     ];
 
     for dir in &dirs_to_validate {
@@ -1042,7 +1042,7 @@ mod tests {
         let root = tmp.path().to_path_buf();
 
         for (stage, id) in &[
-            ("1_upcoming", "10_story_upcoming"),
+            ("1_backlog", "10_story_upcoming"),
             ("2_current", "20_story_current"),
             ("3_qa", "30_story_qa"),
             ("4_merge", "40_story_merge"),
@@ -1060,8 +1060,8 @@ mod tests {
         let ctx = crate::http::context::AppContext::new_test(root);
         let state = load_pipeline_state(&ctx).unwrap();
 
-        assert_eq!(state.upcoming.len(), 1);
+        assert_eq!(state.backlog.len(), 1);
-        assert_eq!(state.upcoming[0].story_id, "10_story_upcoming");
+        assert_eq!(state.backlog[0].story_id, "10_story_upcoming");
 
         assert_eq!(state.current.len(), 1);
         assert_eq!(state.current[0].story_id, "20_story_current");
@@ -1164,15 +1164,15 @@ mod tests {
     #[test]
     fn load_upcoming_parses_metadata() {
         let tmp = tempfile::tempdir().unwrap();
-        let upcoming = tmp.path().join(".story_kit/work/1_upcoming");
+        let backlog = tmp.path().join(".story_kit/work/1_backlog");
-        fs::create_dir_all(&upcoming).unwrap();
+        fs::create_dir_all(&backlog).unwrap();
         fs::write(
-            upcoming.join("31_story_view_upcoming.md"),
+            backlog.join("31_story_view_upcoming.md"),
             "---\nname: View Upcoming\n---\n# Story\n",
         )
         .unwrap();
         fs::write(
-            upcoming.join("32_story_worktree.md"),
+            backlog.join("32_story_worktree.md"),
             "---\nname: Worktree Orchestration\n---\n# Story\n",
         )
         .unwrap();
@@ -1189,11 +1189,11 @@ mod tests {
     #[test]
     fn load_upcoming_skips_non_md_files() {
         let tmp = tempfile::tempdir().unwrap();
-        let upcoming = tmp.path().join(".story_kit/work/1_upcoming");
+        let backlog = tmp.path().join(".story_kit/work/1_backlog");
-        fs::create_dir_all(&upcoming).unwrap();
+        fs::create_dir_all(&backlog).unwrap();
-        fs::write(upcoming.join(".gitkeep"), "").unwrap();
+        fs::write(backlog.join(".gitkeep"), "").unwrap();
         fs::write(
-            upcoming.join("31_story_example.md"),
+            backlog.join("31_story_example.md"),
             "---\nname: A Story\n---\n",
         )
         .unwrap();
@@ -1208,16 +1208,16 @@ mod tests {
     fn validate_story_dirs_valid_files() {
         let tmp = tempfile::tempdir().unwrap();
         let current = tmp.path().join(".story_kit/work/2_current");
-        let upcoming = tmp.path().join(".story_kit/work/1_upcoming");
+        let backlog = tmp.path().join(".story_kit/work/1_backlog");
         fs::create_dir_all(&current).unwrap();
-        fs::create_dir_all(&upcoming).unwrap();
+        fs::create_dir_all(&backlog).unwrap();
         fs::write(
             current.join("28_story_todos.md"),
             "---\nname: Show TODOs\n---\n# Story\n",
         )
         .unwrap();
         fs::write(
-            upcoming.join("36_story_front_matter.md"),
+            backlog.join("36_story_front_matter.md"),
             "---\nname: Enforce Front Matter\n---\n# Story\n",
         )
         .unwrap();
@@ -1302,7 +1302,7 @@ mod tests {
     #[test]
     fn next_item_number_empty_dirs() {
         let tmp = tempfile::tempdir().unwrap();
-        let base = tmp.path().join(".story_kit/work/1_upcoming");
+        let base = tmp.path().join(".story_kit/work/1_backlog");
         fs::create_dir_all(&base).unwrap();
         assert_eq!(next_item_number(tmp.path()).unwrap(), 1);
     }
@@ -1310,13 +1310,13 @@ mod tests {
     #[test]
     fn next_item_number_scans_all_dirs() {
         let tmp = tempfile::tempdir().unwrap();
-        let upcoming = tmp.path().join(".story_kit/work/1_upcoming");
+        let backlog = tmp.path().join(".story_kit/work/1_backlog");
         let current = tmp.path().join(".story_kit/work/2_current");
         let archived = tmp.path().join(".story_kit/work/5_done");
-        fs::create_dir_all(&upcoming).unwrap();
+        fs::create_dir_all(&backlog).unwrap();
         fs::create_dir_all(&current).unwrap();
         fs::create_dir_all(&archived).unwrap();
-        fs::write(upcoming.join("10_story_foo.md"), "").unwrap();
+        fs::write(backlog.join("10_story_foo.md"), "").unwrap();
         fs::write(current.join("20_story_bar.md"), "").unwrap();
         fs::write(archived.join("15_story_baz.md"), "").unwrap();
         assert_eq!(next_item_number(tmp.path()).unwrap(), 21);
@@ -1334,9 +1334,9 @@ mod tests {
     #[test]
     fn create_story_writes_correct_content() {
         let tmp = tempfile::tempdir().unwrap();
-        let upcoming = tmp.path().join(".story_kit/work/1_upcoming");
+        let backlog = tmp.path().join(".story_kit/work/1_backlog");
-        fs::create_dir_all(&upcoming).unwrap();
+        fs::create_dir_all(&backlog).unwrap();
-        fs::write(upcoming.join("36_story_existing.md"), "").unwrap();
+        fs::write(backlog.join("36_story_existing.md"), "").unwrap();
 
         let number = next_item_number(tmp.path()).unwrap();
         assert_eq!(number, 37);
@@ -1345,7 +1345,7 @@ mod tests {
         assert_eq!(slug, "my_new_feature");
 
         let filename = format!("{number}_{slug}.md");
-        let filepath = upcoming.join(&filename);
+        let filepath = backlog.join(&filename);
 
         let mut content = String::new();
         content.push_str("---\n");
@@ -1377,10 +1377,10 @@ mod tests {
         let result = create_story_file(tmp.path(), name, None, None, false);
         assert!(result.is_ok(), "create_story_file failed: {result:?}");
 
-        let upcoming = tmp.path().join(".story_kit/work/1_upcoming");
+        let backlog = tmp.path().join(".story_kit/work/1_backlog");
         let story_id = result.unwrap();
         let filename = format!("{story_id}.md");
-        let contents = fs::read_to_string(upcoming.join(&filename)).unwrap();
+        let contents = fs::read_to_string(backlog.join(&filename)).unwrap();
 
         let meta = parse_front_matter(&contents).expect("front matter should be valid YAML");
         assert_eq!(meta.name.as_deref(), Some(name));
@@ -1389,10 +1389,10 @@ mod tests {
     #[test]
     fn create_story_rejects_duplicate() {
         let tmp = tempfile::tempdir().unwrap();
-        let upcoming = tmp.path().join(".story_kit/work/1_upcoming");
+        let backlog = tmp.path().join(".story_kit/work/1_backlog");
-        fs::create_dir_all(&upcoming).unwrap();
+        fs::create_dir_all(&backlog).unwrap();
 
-        let filepath = upcoming.join("1_story_my_feature.md");
+        let filepath = backlog.join("1_story_my_feature.md");
         fs::write(&filepath, "existing").unwrap();
 
         // Simulate the check
@@ -1511,17 +1511,17 @@ mod tests {
     }
 
     #[test]
-    fn find_story_file_searches_current_then_upcoming() {
+    fn find_story_file_searches_current_then_backlog() {
         let tmp = tempfile::tempdir().unwrap();
         let current = tmp.path().join(".story_kit/work/2_current");
-        let upcoming = tmp.path().join(".story_kit/work/1_upcoming");
+        let backlog = tmp.path().join(".story_kit/work/1_backlog");
         fs::create_dir_all(&current).unwrap();
-        fs::create_dir_all(&upcoming).unwrap();
+        fs::create_dir_all(&backlog).unwrap();
 
-        // Only in upcoming
+        // Only in backlog
-        fs::write(upcoming.join("6_test.md"), "").unwrap();
+        fs::write(backlog.join("6_test.md"), "").unwrap();
         let found = find_story_file(tmp.path(), "6_test").unwrap();
-        assert!(found.ends_with("1_upcoming/6_test.md") || found.ends_with("1_upcoming\\6_test.md"));
+        assert!(found.ends_with("1_backlog/6_test.md") || found.ends_with("1_backlog\\6_test.md"));
 
         // Also in current — current should win
         fs::write(current.join("6_test.md"), "").unwrap();
@@ -1724,19 +1724,19 @@ mod tests {
     #[test]
     fn next_item_number_increments_from_existing_bugs() {
         let tmp = tempfile::tempdir().unwrap();
-        let upcoming = tmp.path().join(".story_kit/work/1_upcoming");
+        let backlog = tmp.path().join(".story_kit/work/1_backlog");
-        fs::create_dir_all(&upcoming).unwrap();
+        fs::create_dir_all(&backlog).unwrap();
-        fs::write(upcoming.join("1_bug_crash.md"), "").unwrap();
+        fs::write(backlog.join("1_bug_crash.md"), "").unwrap();
-        fs::write(upcoming.join("3_bug_another.md"), "").unwrap();
+        fs::write(backlog.join("3_bug_another.md"), "").unwrap();
         assert_eq!(next_item_number(tmp.path()).unwrap(), 4);
     }
 
     #[test]
     fn next_item_number_scans_archived_too() {
         let tmp = tempfile::tempdir().unwrap();
-        let upcoming = tmp.path().join(".story_kit/work/1_upcoming");
+        let backlog = tmp.path().join(".story_kit/work/1_backlog");
         let archived = tmp.path().join(".story_kit/work/5_done");
-        fs::create_dir_all(&upcoming).unwrap();
+        fs::create_dir_all(&backlog).unwrap();
         fs::create_dir_all(&archived).unwrap();
         fs::write(archived.join("5_bug_old.md"), "").unwrap();
         assert_eq!(next_item_number(tmp.path()).unwrap(), 6);
@@ -1752,11 +1752,11 @@ mod tests {
     #[test]
     fn list_bug_files_excludes_archive_subdir() {
         let tmp = tempfile::tempdir().unwrap();
-        let upcoming_dir = tmp.path().join(".story_kit/work/1_upcoming");
+        let backlog_dir = tmp.path().join(".story_kit/work/1_backlog");
         let archived_dir = tmp.path().join(".story_kit/work/5_done");
-        fs::create_dir_all(&upcoming_dir).unwrap();
+        fs::create_dir_all(&backlog_dir).unwrap();
         fs::create_dir_all(&archived_dir).unwrap();
-        fs::write(upcoming_dir.join("1_bug_open.md"), "# Bug 1: Open Bug\n").unwrap();
+        fs::write(backlog_dir.join("1_bug_open.md"), "# Bug 1: Open Bug\n").unwrap();
         fs::write(archived_dir.join("2_bug_closed.md"), "# Bug 2: Closed Bug\n").unwrap();
 
         let result = list_bug_files(tmp.path()).unwrap();
@@ -1768,11 +1768,11 @@ mod tests {
     #[test]
     fn list_bug_files_sorted_by_id() {
         let tmp = tempfile::tempdir().unwrap();
-        let upcoming_dir = tmp.path().join(".story_kit/work/1_upcoming");
+        let backlog_dir = tmp.path().join(".story_kit/work/1_backlog");
-        fs::create_dir_all(&upcoming_dir).unwrap();
+        fs::create_dir_all(&backlog_dir).unwrap();
-        fs::write(upcoming_dir.join("3_bug_third.md"), "# Bug 3: Third\n").unwrap();
+        fs::write(backlog_dir.join("3_bug_third.md"), "# Bug 3: Third\n").unwrap();
-        fs::write(upcoming_dir.join("1_bug_first.md"), "# Bug 1: First\n").unwrap();
+        fs::write(backlog_dir.join("1_bug_first.md"), "# Bug 1: First\n").unwrap();
-        fs::write(upcoming_dir.join("2_bug_second.md"), "# Bug 2: Second\n").unwrap();
+        fs::write(backlog_dir.join("2_bug_second.md"), "# Bug 2: Second\n").unwrap();
 
         let result = list_bug_files(tmp.path()).unwrap();
         assert_eq!(result.len(), 3);
@@ -1810,7 +1810,7 @@ mod tests {
 
         let filepath = tmp
             .path()
-            .join(".story_kit/work/1_upcoming/1_bug_login_crash.md");
+            .join(".story_kit/work/1_backlog/1_bug_login_crash.md");
         assert!(filepath.exists());
         let contents = fs::read_to_string(&filepath).unwrap();
         assert!(
@@ -1854,7 +1854,7 @@ mod tests {
         )
         .unwrap();
 
-        let filepath = tmp.path().join(".story_kit/work/1_upcoming/1_bug_some_bug.md");
+        let filepath = tmp.path().join(".story_kit/work/1_backlog/1_bug_some_bug.md");
         let contents = fs::read_to_string(&filepath).unwrap();
         assert!(
             contents.starts_with("---\nname: \"Some Bug\"\n---"),
@@ -1876,7 +1876,7 @@ mod tests {
 
         let filepath = tmp
             .path()
-            .join(".story_kit/work/1_upcoming/1_spike_filesystem_watcher_architecture.md");
+            .join(".story_kit/work/1_backlog/1_spike_filesystem_watcher_architecture.md");
         assert!(filepath.exists());
         let contents = fs::read_to_string(&filepath).unwrap();
         assert!(
@@ -1900,7 +1900,7 @@ mod tests {
         create_spike_file(tmp.path(), "FS Watcher Spike", Some(description)).unwrap();
 
         let filepath =
-            tmp.path().join(".story_kit/work/1_upcoming/1_spike_fs_watcher_spike.md");
+            tmp.path().join(".story_kit/work/1_backlog/1_spike_fs_watcher_spike.md");
         let contents = fs::read_to_string(&filepath).unwrap();
         assert!(contents.contains(description));
     }
@@ -1910,7 +1910,7 @@ mod tests {
         let tmp = tempfile::tempdir().unwrap();
         create_spike_file(tmp.path(), "My Spike", None).unwrap();
 
-        let filepath = tmp.path().join(".story_kit/work/1_upcoming/1_spike_my_spike.md");
+        let filepath = tmp.path().join(".story_kit/work/1_backlog/1_spike_my_spike.md");
         let contents = fs::read_to_string(&filepath).unwrap();
         // Should have placeholder TBD in Question section
         assert!(contents.contains("## Question\n\n- TBD\n"));
@@ -1931,10 +1931,10 @@ mod tests {
         let result = create_spike_file(tmp.path(), name, None);
         assert!(result.is_ok(), "create_spike_file failed: {result:?}");
 
-        let upcoming = tmp.path().join(".story_kit/work/1_upcoming");
+        let backlog = tmp.path().join(".story_kit/work/1_backlog");
         let spike_id = result.unwrap();
         let filename = format!("{spike_id}.md");
-        let contents = fs::read_to_string(upcoming.join(&filename)).unwrap();
+        let contents = fs::read_to_string(backlog.join(&filename)).unwrap();
 
         let meta = parse_front_matter(&contents).expect("front matter should be valid YAML");
         assert_eq!(meta.name.as_deref(), Some(name));
@@ -1943,9 +1943,9 @@ mod tests {
     #[test]
     fn create_spike_file_increments_from_existing_items() {
         let tmp = tempfile::tempdir().unwrap();
-        let upcoming = tmp.path().join(".story_kit/work/1_upcoming");
+        let backlog = tmp.path().join(".story_kit/work/1_backlog");
-        fs::create_dir_all(&upcoming).unwrap();
+        fs::create_dir_all(&backlog).unwrap();
-        fs::write(upcoming.join("5_story_existing.md"), "").unwrap();
+        fs::write(backlog.join("5_story_existing.md"), "").unwrap();
 
         let spike_id = create_spike_file(tmp.path(), "My Spike", None).unwrap();
         assert!(spike_id.starts_with("6_spike_"), "expected spike number 6, got: {spike_id}");

server/src/http/ws.rs

@@ -79,7 +79,7 @@ enum WsResponse {
     },
     /// Full pipeline state pushed on connect and after every work-item watcher event.
     PipelineState {
-        upcoming: Vec<crate::http::workflow::UpcomingStory>,
+        backlog: Vec<crate::http::workflow::UpcomingStory>,
         current: Vec<crate::http::workflow::UpcomingStory>,
         qa: Vec<crate::http::workflow::UpcomingStory>,
         merge: Vec<crate::http::workflow::UpcomingStory>,
@@ -160,7 +160,7 @@ impl From<WatcherEvent> for Option<WsResponse> {
 impl From<PipelineState> for WsResponse {
     fn from(s: PipelineState) -> Self {
         WsResponse::PipelineState {
-            upcoming: s.upcoming,
+            backlog: s.backlog,
             current: s.current,
             qa: s.qa,
             merge: s.merge,
@@ -695,7 +695,7 @@ mod tests {
             agent: None,
         };
         let resp = WsResponse::PipelineState {
-            upcoming: vec![story],
+            backlog: vec![story],
             current: vec![],
             qa: vec![],
             merge: vec![],
@@ -703,8 +703,8 @@ mod tests {
         };
         let json = serde_json::to_value(&resp).unwrap();
         assert_eq!(json["type"], "pipeline_state");
-        assert_eq!(json["upcoming"].as_array().unwrap().len(), 1);
+        assert_eq!(json["backlog"].as_array().unwrap().len(), 1);
-        assert_eq!(json["upcoming"][0]["story_id"], "10_story_test");
+        assert_eq!(json["backlog"][0]["story_id"], "10_story_test");
         assert!(json["current"].as_array().unwrap().is_empty());
         assert!(json["done"].as_array().unwrap().is_empty());
     }
@@ -824,7 +824,7 @@ mod tests {
     #[test]
     fn pipeline_state_converts_to_ws_response() {
         let state = PipelineState {
-            upcoming: vec![UpcomingStory {
+            backlog: vec![UpcomingStory {
                 story_id: "1_story_a".to_string(),
                 name: Some("Story A".to_string()),
                 error: None,
@@ -851,8 +851,8 @@ mod tests {
         let resp: WsResponse = state.into();
         let json = serde_json::to_value(&resp).unwrap();
         assert_eq!(json["type"], "pipeline_state");
-        assert_eq!(json["upcoming"].as_array().unwrap().len(), 1);
+        assert_eq!(json["backlog"].as_array().unwrap().len(), 1);
-        assert_eq!(json["upcoming"][0]["story_id"], "1_story_a");
+        assert_eq!(json["backlog"][0]["story_id"], "1_story_a");
         assert_eq!(json["current"].as_array().unwrap().len(), 1);
         assert_eq!(json["current"][0]["story_id"], "2_story_b");
         assert!(json["qa"].as_array().unwrap().is_empty());
@@ -864,7 +864,7 @@ mod tests {
     #[test]
     fn empty_pipeline_state_converts_to_ws_response() {
         let state = PipelineState {
-            upcoming: vec![],
+            backlog: vec![],
             current: vec![],
             qa: vec![],
             merge: vec![],
@@ -873,7 +873,7 @@ mod tests {
         let resp: WsResponse = state.into();
         let json = serde_json::to_value(&resp).unwrap();
         assert_eq!(json["type"], "pipeline_state");
-        assert!(json["upcoming"].as_array().unwrap().is_empty());
+        assert!(json["backlog"].as_array().unwrap().is_empty());
         assert!(json["current"].as_array().unwrap().is_empty());
         assert!(json["qa"].as_array().unwrap().is_empty());
         assert!(json["merge"].as_array().unwrap().is_empty());
@@ -991,7 +991,7 @@ mod tests {
     #[test]
     fn pipeline_state_with_agent_converts_correctly() {
         let state = PipelineState {
-            upcoming: vec![],
+            backlog: vec![],
             current: vec![UpcomingStory {
                 story_id: "10_story_x".to_string(),
                 name: Some("Story X".to_string()),
@@ -1046,7 +1046,7 @@ mod tests {
         let root = tmp.path().to_path_buf();
 
         // Create minimal pipeline dirs so load_pipeline_state succeeds.
-        for stage in &["1_upcoming", "2_current", "3_qa", "4_merge"] {
+        for stage in &["1_backlog", "2_current", "3_qa", "4_merge"] {
             std::fs::create_dir_all(root.join(".story_kit").join("work").join(stage)).unwrap();
         }
 
@@ -1155,7 +1155,7 @@ mod tests {
 
         assert_eq!(initial["type"], "pipeline_state");
         // All stages should be empty arrays since no .md files were created.
-        assert!(initial["upcoming"].as_array().unwrap().is_empty());
+        assert!(initial["backlog"].as_array().unwrap().is_empty());
         assert!(initial["current"].as_array().unwrap().is_empty());
         assert!(initial["qa"].as_array().unwrap().is_empty());
         assert!(initial["merge"].as_array().unwrap().is_empty());

server/src/io/fs.rs

@@ -409,7 +409,7 @@ fn scaffold_story_kit(root: &Path) -> Result<(), String> {
 
     // Create the work/ pipeline directories, each with a .gitkeep so empty dirs survive git clone
     let work_stages = [
-        "1_upcoming",
+        "1_backlog",
         "2_current",
         "3_qa",
         "4_merge",
@@ -1085,7 +1085,7 @@ mod tests {
         let dir = tempdir().unwrap();
         scaffold_story_kit(dir.path()).unwrap();
 
-        let stages = ["1_upcoming", "2_current", "3_qa", "4_merge", "5_done", "6_archived"];
+        let stages = ["1_backlog", "2_current", "3_qa", "4_merge", "5_done", "6_archived"];
         for stage in &stages {
             let path = dir.path().join(".story_kit/work").join(stage);
             assert!(path.is_dir(), "work/{} should be a directory", stage);

server/src/io/watcher.rs

@@ -78,7 +78,7 @@ pub fn is_config_file(path: &Path, git_root: &Path) -> bool {
 /// Map a pipeline directory name to a (action, commit-message-prefix) pair.
 fn stage_metadata(stage: &str, item_id: &str) -> Option<(&'static str, String)> {
     let (action, prefix) = match stage {
-        "1_upcoming" => ("create", format!("story-kit: create {item_id}")),
+        "1_backlog" => ("create", format!("story-kit: create {item_id}")),
         "2_current"  => ("start",  format!("story-kit: start {item_id}")),
         "3_qa"       => ("qa",     format!("story-kit: queue {item_id} for QA")),
         "4_merge"    => ("merge",  format!("story-kit: queue {item_id} for merge")),
@@ -111,7 +111,7 @@ fn stage_for_path(path: &Path) -> Option<String> {
         .parent()
         .and_then(|p| p.file_name())
         .and_then(|n| n.to_str())?;
-    matches!(stage, "1_upcoming" | "2_current" | "3_qa" | "4_merge" | "5_done" | "6_archived")
+    matches!(stage, "1_backlog" | "2_current" | "3_qa" | "4_merge" | "5_done" | "6_archived")
         .then(|| stage.to_string())
 }
 
@@ -159,7 +159,7 @@ fn git_add_work_and_commit(git_root: &Path, message: &str) -> Result<bool, Strin
 /// Intermediate stages (current, qa, merge, done) are transient pipeline state
 /// that don't need to be committed — they're only relevant while the server is
 /// running and are broadcast to WebSocket clients for real-time UI updates.
-const COMMIT_WORTHY_STAGES: &[&str] = &["1_upcoming", "5_done", "6_archived"];
+const COMMIT_WORTHY_STAGES: &[&str] = &["1_backlog", "5_done", "6_archived"];
 
 /// Return `true` if changes in `stage` should be committed to git.
 fn should_commit_stage(stage: &str) -> bool {
@@ -172,7 +172,7 @@ fn should_commit_stage(stage: &str) -> bool {
 /// (they represent the destination of a move or a new file). Deletions are
 /// captured by `git add -A .story_kit/work/` automatically.
 ///
-/// Only terminal stages (`1_upcoming` and `6_archived`) trigger git commits.
+/// Only terminal stages (`1_backlog` and `6_archived`) trigger git commits.
 /// All stages broadcast a [`WatcherEvent`] so the frontend stays in sync.
 fn flush_pending(
     pending: &HashMap<PathBuf, String>,
@@ -574,13 +574,13 @@ mod tests {
     fn flush_pending_commits_and_broadcasts_for_terminal_stage() {
         let tmp = TempDir::new().unwrap();
         init_git_repo(tmp.path());
-        let stage_dir = make_stage_dir(tmp.path(), "1_upcoming");
+        let stage_dir = make_stage_dir(tmp.path(), "1_backlog");
         let story_path = stage_dir.join("42_story_foo.md");
         fs::write(&story_path, "---\nname: test\n---\n").unwrap();
 
         let (tx, mut rx) = tokio::sync::broadcast::channel(16);
         let mut pending = HashMap::new();
-        pending.insert(story_path, "1_upcoming".to_string());
+        pending.insert(story_path, "1_backlog".to_string());
 
         flush_pending(&pending, tmp.path(), &tx);
 
@@ -592,7 +592,7 @@ mod tests {
                 action,
                 commit_msg,
             } => {
-                assert_eq!(stage, "1_upcoming");
+                assert_eq!(stage, "1_backlog");
                 assert_eq!(item_id, "42_story_foo");
                 assert_eq!(action, "create");
                 assert_eq!(commit_msg, "story-kit: create 42_story_foo");
@@ -660,7 +660,7 @@ mod tests {
     #[test]
     fn flush_pending_broadcasts_for_all_pipeline_stages() {
         let stages = [
-            ("1_upcoming", "create", "story-kit: create 10_story_x"),
+            ("1_backlog", "create", "story-kit: create 10_story_x"),
             ("3_qa", "qa", "story-kit: queue 10_story_x for QA"),
             ("4_merge", "merge", "story-kit: queue 10_story_x for merge"),
             ("5_done", "done", "story-kit: done 10_story_x"),
@@ -792,10 +792,10 @@ mod tests {
     }
 
     #[test]
-    fn flush_pending_clears_merge_failure_when_moving_to_upcoming() {
+    fn flush_pending_clears_merge_failure_when_moving_to_backlog() {
         let tmp = TempDir::new().unwrap();
         init_git_repo(tmp.path());
-        let stage_dir = make_stage_dir(tmp.path(), "1_upcoming");
+        let stage_dir = make_stage_dir(tmp.path(), "1_backlog");
         let story_path = stage_dir.join("51_story_reset.md");
         fs::write(
             &story_path,
@@ -805,14 +805,14 @@ mod tests {
 
         let (tx, _rx) = tokio::sync::broadcast::channel(16);
         let mut pending = HashMap::new();
-        pending.insert(story_path.clone(), "1_upcoming".to_string());
+        pending.insert(story_path.clone(), "1_backlog".to_string());
 
         flush_pending(&pending, tmp.path(), &tx);
 
         let contents = fs::read_to_string(&story_path).unwrap();
         assert!(
             !contents.contains("merge_failure"),
-            "merge_failure should be stripped when story lands in 1_upcoming"
+            "merge_failure should be stripped when story lands in 1_backlog"
         );
     }
 
@@ -937,7 +937,7 @@ mod tests {
     #[test]
     fn should_commit_stage_only_for_terminal_stages() {
         // Terminal stages — should commit.
-        assert!(should_commit_stage("1_upcoming"));
+        assert!(should_commit_stage("1_backlog"));
         assert!(should_commit_stage("5_done"));
         assert!(should_commit_stage("6_archived"));
         // Intermediate stages — broadcast-only, no commit.

server/src/llm/providers/claude_code.rs

@@ -150,7 +150,7 @@ fn run_pty_session(
     user_message: &str,
     cwd: &str,
     resume_session_id: Option<&str>,
-    system_prompt: Option<&str>,
+    _system_prompt: Option<&str>,
     cancelled: Arc<AtomicBool>,
     token_tx: tokio::sync::mpsc::UnboundedSender<String>,
     thinking_tx: tokio::sync::mpsc::UnboundedSender<String>,
@@ -189,10 +189,8 @@ fn run_pty_session(
     // a tool requires user approval, instead of using PTY stdin/stdout.
     cmd.arg("--permission-prompt-tool");
     cmd.arg("mcp__story-kit__prompt_permission");
-    if let Some(sys) = system_prompt {
+    // Note: --system is not a valid Claude Code CLI flag. System-level
-        cmd.arg("--system");
+    // instructions (like bot name) are prepended to the user prompt instead.
-        cmd.arg(sys);
-    }
     cmd.cwd(cwd);
     // Keep TERM reasonable but disable color
     cmd.env("NO_COLOR", "1");

server/src/main.rs

@@ -196,7 +196,7 @@ async fn main() -> Result<(), std::io::Error> {
     // Optional Matrix bot: connect to the homeserver and start listening for
     // messages if `.story_kit/bot.toml` is present and enabled.
     if let Some(ref root) = startup_root {
-        matrix::spawn_bot(root, watcher_tx_for_bot, perm_rx_for_bot);
+        matrix::spawn_bot(root, watcher_tx_for_bot, perm_rx_for_bot, Arc::clone(&startup_agents));
     }
 
     // On startup:

server/src/matrix/bot.rs

@@ -1,3 +1,5 @@
+use crate::agents::{AgentPool, AgentStatus};
+use crate::config::ProjectConfig;
 use crate::http::context::{PermissionDecision, PermissionForward};
 use crate::llm::providers::claude_code::{ClaudeCodeProvider, ClaudeCodeResult};
 use crate::slog;
@@ -30,7 +32,7 @@ use matrix_sdk::encryption::verification::{
 };
 use matrix_sdk::ruma::events::key::verification::request::ToDeviceKeyVerificationRequestEvent;
 
-use super::config::BotConfig;
+use super::config::{BotConfig, save_ambient_rooms};
 
 // ---------------------------------------------------------------------------
 // Conversation history types
@@ -165,6 +167,189 @@ pub struct BotContext {
     /// The name the bot uses to refer to itself. Derived from `display_name`
     /// in bot.toml; defaults to "Assistant" when unset.
     pub bot_name: String,
+    /// Set of room IDs where ambient mode is active.  In ambient mode the bot
+    /// responds to all messages rather than only addressed ones.  This is
+    /// in-memory only — the state does not survive a bot restart.
+    pub ambient_rooms: Arc<TokioMutex<HashSet<OwnedRoomId>>>,
+    /// Agent pool for checking agent availability.
+    pub agents: Arc<AgentPool>,
+}
+
+// ---------------------------------------------------------------------------
+// Startup announcement
+// ---------------------------------------------------------------------------
+
+/// Format the startup greeting the bot sends to each room when it comes online.
+///
+/// Uses the bot's configured display name so the message reads naturally
+/// (e.g. "Timmy is online.").
+pub fn format_startup_announcement(bot_name: &str) -> String {
+    format!("{bot_name} is online.")
+}
+
+// ---------------------------------------------------------------------------
+// Command extraction
+// ---------------------------------------------------------------------------
+
+/// Extract the command portion from a bot-addressed message.
+///
+/// Strips the leading bot mention (full Matrix user ID, `@localpart`, or
+/// display name) plus any trailing punctuation (`,`, `:`) and whitespace,
+/// then returns the remainder in lowercase. Returns `None` when no
+/// recognized mention prefix is found in the message.
+pub fn extract_command(body: &str, bot_name: &str, bot_user_id: &OwnedUserId) -> Option<String> {
+    let full_id = bot_user_id.as_str().to_lowercase();
+    let at_localpart = format!("@{}", bot_user_id.localpart().to_lowercase());
+    let bot_name_lower = bot_name.to_lowercase();
+    let body_lower = body.trim().to_lowercase();
+
+    let stripped = if let Some(s) = body_lower.strip_prefix(&full_id) {
+        s
+    } else if let Some(s) = body_lower.strip_prefix(&at_localpart) {
+        // Guard against matching a longer @mention (e.g. "@timmybot" vs "@timmy").
+        let next = s.chars().next();
+        if next.is_some_and(|c| c.is_alphanumeric() || c == '-' || c == '_') {
+            return None;
+        }
+        s
+    } else if let Some(s) = body_lower.strip_prefix(&bot_name_lower) {
+        // Guard against matching a longer display-name prefix.
+        let next = s.chars().next();
+        if next.is_some_and(|c| c.is_alphanumeric() || c == '-' || c == '_') {
+            return None;
+        }
+        s
+    } else {
+        return None;
+    };
+
+    // Strip leading separators (`,`, `:`) and whitespace after the mention.
+    let cmd = stripped.trim_start_matches(|c: char| c == ':' || c == ',' || c.is_whitespace());
+    Some(cmd.trim().to_string())
+}
+
+// ---------------------------------------------------------------------------
+// Pipeline status formatter
+// ---------------------------------------------------------------------------
+
+/// Read all story IDs and names from a pipeline stage directory.
+fn read_stage_items(
+    project_root: &std::path::Path,
+    stage_dir: &str,
+) -> Vec<(String, Option<String>)> {
+    let dir = project_root
+        .join(".story_kit")
+        .join("work")
+        .join(stage_dir);
+    if !dir.exists() {
+        return Vec::new();
+    }
+    let mut items = Vec::new();
+    if let Ok(entries) = std::fs::read_dir(&dir) {
+        for entry in entries.flatten() {
+            let path = entry.path();
+            if path.extension().and_then(|e| e.to_str()) != Some("md") {
+                continue;
+            }
+            if let Some(stem) = path.file_stem().and_then(|s| s.to_str()) {
+                let name = std::fs::read_to_string(&path)
+                    .ok()
+                    .and_then(|contents| {
+                        crate::io::story_metadata::parse_front_matter(&contents)
+                            .ok()
+                            .and_then(|m| m.name)
+                    });
+                items.push((stem.to_string(), name));
+            }
+        }
+    }
+    items.sort_by(|a, b| a.0.cmp(&b.0));
+    items
+}
+
+/// Build the full pipeline status text formatted for Matrix (markdown).
+pub fn build_pipeline_status(project_root: &std::path::Path, agents: &AgentPool) -> String {
+    // Build a map from story_id → active AgentInfo for quick lookup.
+    let active_agents = agents.list_agents().unwrap_or_default();
+    let active_map: std::collections::HashMap<String, &crate::agents::AgentInfo> = active_agents
+        .iter()
+        .filter(|a| matches!(a.status, AgentStatus::Running | AgentStatus::Pending))
+        .map(|a| (a.story_id.clone(), a))
+        .collect();
+
+    let config = ProjectConfig::load(project_root).ok();
+
+    let mut out = String::from("**Pipeline Status**\n\n");
+
+    let stages = [
+        ("1_upcoming", "Upcoming"),
+        ("2_current", "In Progress"),
+        ("3_qa", "QA"),
+        ("4_merge", "Merge"),
+        ("5_done", "Done"),
+    ];
+
+    for (dir, label) in &stages {
+        let items = read_stage_items(project_root, dir);
+        let count = items.len();
+        out.push_str(&format!("**{label}** ({count})\n"));
+        if items.is_empty() {
+            out.push_str("  *(none)*\n");
+        } else {
+            for (story_id, name) in &items {
+                let display = match name {
+                    Some(n) => format!("{story_id} — {n}"),
+                    None => story_id.clone(),
+                };
+                if let Some(agent) = active_map.get(story_id) {
+                    let model_str = config
+                        .as_ref()
+                        .and_then(|cfg| cfg.find_agent(&agent.agent_name))
+                        .and_then(|ac| ac.model.as_deref())
+                        .unwrap_or("?");
+                    out.push_str(&format!(
+                        "  • {display} — {} ({}) [{}]\n",
+                        agent.agent_name, model_str, agent.status
+                    ));
+                } else {
+                    out.push_str(&format!("  • {display}\n"));
+                }
+            }
+        }
+        out.push('\n');
+    }
+
+    // Free agents: configured agents not currently running or pending.
+    out.push_str("**Free Agents**\n");
+    if let Some(cfg) = &config {
+        let busy_names: std::collections::HashSet<String> = active_agents
+            .iter()
+            .filter(|a| matches!(a.status, AgentStatus::Running | AgentStatus::Pending))
+            .map(|a| a.agent_name.clone())
+            .collect();
+
+        let free: Vec<String> = cfg
+            .agent
+            .iter()
+            .filter(|a| !busy_names.contains(&a.name))
+            .map(|a| match &a.model {
+                Some(m) => format!("{} ({})", a.name, m),
+                None => a.name.clone(),
+            })
+            .collect();
+
+        if free.is_empty() {
+            out.push_str("  *(none — all agents busy)*\n");
+        } else {
+            for name in &free {
+                out.push_str(&format!("  • {name}\n"));
+            }
+        }
+    } else {
+        out.push_str("  *(no agent config found)*\n");
+    }
+
+    out
 }
 
 // ---------------------------------------------------------------------------
@@ -179,6 +364,7 @@ pub async fn run_bot(
     project_root: PathBuf,
     watcher_rx: tokio::sync::broadcast::Receiver<crate::io::watcher::WatcherEvent>,
     perm_rx: Arc<TokioMutex<mpsc::UnboundedReceiver<PermissionForward>>>,
+    agents: Arc<AgentPool>,
 ) -> Result<(), String> {
     let store_path = project_root.join(".story_kit").join("matrix_store");
     let client = Client::builder()
@@ -305,10 +491,11 @@ pub async fn run_bot(
         target_room_ids
     );
 
-    // Clone values needed by the notification listener before they are moved
+    // Clone values needed by the notification listener and startup announcement
-    // into BotContext.
+    // before they are moved into BotContext.
     let notif_room_ids = target_room_ids.clone();
     let notif_project_root = project_root.clone();
+    let announce_room_ids = target_room_ids.clone();
 
     let persisted = load_history(&project_root);
     slog!(
@@ -316,10 +503,26 @@ pub async fn run_bot(
         persisted.len()
     );
 
+    // Restore persisted ambient rooms from config, ignoring any that are not
+    // in the configured target_room_ids to avoid stale entries.
+    let persisted_ambient: HashSet<OwnedRoomId> = config
+        .ambient_rooms
+        .iter()
+        .filter_map(|s| s.parse::<OwnedRoomId>().ok())
+        .collect();
+    if !persisted_ambient.is_empty() {
+        slog!(
+            "[matrix-bot] Restored ambient mode for {} room(s): {:?}",
+            persisted_ambient.len(),
+            persisted_ambient
+        );
+    }
+
     let bot_name = config
         .display_name
         .clone()
         .unwrap_or_else(|| "Assistant".to_string());
+    let announce_bot_name = bot_name.clone();
 
     let ctx = BotContext {
         bot_user_id,
@@ -333,6 +536,8 @@ pub async fn run_bot(
         pending_perm_replies: Arc::new(TokioMutex::new(HashMap::new())),
         permission_timeout_secs: config.permission_timeout_secs,
         bot_name,
+        ambient_rooms: Arc::new(TokioMutex::new(persisted_ambient)),
+        agents,
     };
 
     slog!("[matrix-bot] Cryptographic identity verification is always ON — commands from unencrypted rooms or unverified devices are rejected");
@@ -351,6 +556,23 @@ pub async fn run_bot(
         notif_project_root,
     );
 
+    // Send a startup announcement to each configured room so users know the
+    // bot is online.  This runs once per process start — the sync loop handles
+    // reconnects internally so this code is never reached again on a network
+    // blip or sync resumption.
+    let announce_msg = format_startup_announcement(&announce_bot_name);
+    slog!("[matrix-bot] Sending startup announcement: {announce_msg}");
+    for room_id in &announce_room_ids {
+        if let Some(room) = client.get_room(room_id) {
+            let content = RoomMessageEventContent::text_plain(announce_msg.clone());
+            if let Err(e) = room.send(content).await {
+                slog!("[matrix-bot] Failed to send startup announcement to {room_id}: {e}");
+            }
+        } else {
+            slog!("[matrix-bot] Room {room_id} not found in client state, skipping announcement");
+        }
+    }
+
     slog!("[matrix-bot] Starting Matrix sync loop");
 
     // This blocks until the connection is terminated or an error occurs.
@@ -432,6 +654,50 @@ fn contains_word(haystack: &str, needle: &str) -> bool {
     false
 }
 
+/// Parse an ambient-mode toggle command from a message body.
+///
+/// Recognises the following (case-insensitive) forms, with or without a
+/// leading bot mention:
+///
+/// - `@botname ambient on`  / `@botname:server ambient on`
+/// - `botname ambient on`
+/// - `ambient on`
+///
+/// and the `off` variants.
+///
+/// Returns `Some(true)` for "ambient on", `Some(false)` for "ambient off",
+/// and `None` when the body is not an ambient mode command.
+pub fn parse_ambient_command(
+    body: &str,
+    bot_user_id: &OwnedUserId,
+    bot_name: &str,
+) -> Option<bool> {
+    let lower = body.trim().to_ascii_lowercase();
+    let display_lower = bot_name.to_ascii_lowercase();
+    let localpart_lower = bot_user_id.localpart().to_ascii_lowercase();
+
+    // Strip a leading @mention (handles "@localpart" and "@localpart:server").
+    let rest = if let Some(after_at) = lower.strip_prefix('@') {
+        // Skip everything up to the first whitespace (the full mention token).
+        let word_end = after_at
+            .find(char::is_whitespace)
+            .unwrap_or(after_at.len());
+        after_at[word_end..].trim()
+    } else if let Some(after) = lower.strip_prefix(display_lower.as_str()) {
+        after.trim()
+    } else if let Some(after) = lower.strip_prefix(localpart_lower.as_str()) {
+        after.trim()
+    } else {
+        lower.as_str()
+    };
+
+    match rest {
+        "ambient on" => Some(true),
+        "ambient off" => Some(false),
+        _ => None,
+    }
+}
+
 /// Returns `true` if the message's `relates_to` field references an event that
 /// the bot previously sent (i.e. the message is a reply or thread-reply to a
 /// bot message).
@@ -635,11 +901,14 @@ async fn on_room_message(
         _ => return,
     };
 
-    // Only respond when the bot is directly addressed (mentioned by name/ID)
+    // Only respond when the bot is directly addressed (mentioned by name/ID),
-    // or when the message is a reply to one of the bot's own messages.
+    // when the message is a reply to one of the bot's own messages, or when
-    if !mentions_bot(&body, formatted_body.as_deref(), &ctx.bot_user_id)
+    // ambient mode is enabled for this room.
-        && !is_reply_to_bot(ev.content.relates_to.as_ref(), &ctx.bot_sent_event_ids).await
+    let is_addressed = mentions_bot(&body, formatted_body.as_deref(), &ctx.bot_user_id)
-    {
+        || is_reply_to_bot(ev.content.relates_to.as_ref(), &ctx.bot_sent_event_ids).await;
+    let is_ambient = ctx.ambient_rooms.lock().await.contains(&incoming_room_id);
+
+    if !is_addressed && !is_ambient {
         slog!(
             "[matrix-bot] Ignoring unaddressed message from {}",
             ev.sender
@@ -708,10 +977,67 @@ async fn on_room_message(
         }
     }
 
+    // Check for ambient mode toggle commands.  Commands are only recognised
+    // from addressed messages so they can't be accidentally triggered by
+    // ambient-mode traffic from other users.
+    let ambient_cmd = is_addressed
+        .then(|| parse_ambient_command(&body, &ctx.bot_user_id, &ctx.bot_name))
+        .flatten();
+    if let Some(enable) = ambient_cmd {
+        let ambient_room_ids: Vec<String> = {
+            let mut ambient = ctx.ambient_rooms.lock().await;
+            if enable {
+                ambient.insert(incoming_room_id.clone());
+            } else {
+                ambient.remove(&incoming_room_id);
+            }
+            ambient.iter().map(|r| r.to_string()).collect()
+        }; // lock released before the async send below
+
+        // Persist updated ambient rooms to bot.toml so the state survives restarts.
+        save_ambient_rooms(&ctx.project_root, &ambient_room_ids);
+
+        let confirmation = if enable {
+            "Ambient mode on. I'll respond to all messages in this room."
+        } else {
+            "Ambient mode off. I'll only respond when mentioned."
+        };
+        let html = markdown_to_html(confirmation);
+        if let Ok(resp) = room
+            .send(RoomMessageEventContent::text_html(confirmation, html))
+            .await
+        {
+            ctx.bot_sent_event_ids.lock().await.insert(resp.event_id);
+        }
+        slog!(
+            "[matrix-bot] Ambient mode {} for room {}",
+            if enable { "enabled" } else { "disabled" },
+            incoming_room_id
+        );
+        return;
+    }
+
     let sender = ev.sender.to_string();
     let user_message = body;
     slog!("[matrix-bot] Message from {sender}: {user_message}");
 
+    // Check for bot-level commands (e.g. "help") before invoking the LLM.
+    if let Some(response) = super::commands::try_handle_command(
+        &ctx.bot_name,
+        ctx.bot_user_id.as_str(),
+        &user_message,
+    ) {
+        slog!("[matrix-bot] Handled bot command from {sender}");
+        let html = markdown_to_html(&response);
+        if let Ok(resp) = room
+            .send(RoomMessageEventContent::text_html(response, html))
+            .await
+        {
+            ctx.bot_sent_event_ids.lock().await.insert(resp.event_id);
+        }
+        return;
+    }
+
     // Spawn a separate task so the Matrix sync loop is not blocked while we
     // wait for the LLM response (which can take several seconds).
     tokio::spawn(async move {
@@ -736,6 +1062,22 @@ async fn handle_message(
     sender: String,
     user_message: String,
 ) {
+    // Handle built-in commands before invoking Claude.
+    if let Some(cmd) = extract_command(&user_message, &ctx.bot_name, &ctx.bot_user_id)
+        && cmd == "status"
+    {
+        let project_root = ctx.project_root.clone();
+        let status_text = build_pipeline_status(&project_root, &ctx.agents);
+        let html = markdown_to_html(&status_text);
+        if let Ok(resp) = room
+            .send(RoomMessageEventContent::text_html(status_text, html))
+            .await
+        {
+            ctx.bot_sent_event_ids.lock().await.insert(resp.event_id);
+        }
+        return;
+    }
+
     // Look up the room's existing Claude Code session ID (if any) so we can
     // resume the conversation with structured API messages instead of
     // flattening history into a text prefix.
@@ -748,11 +1090,10 @@ async fn handle_message(
 
     // The prompt is just the current message with sender attribution.
     // Prior conversation context is carried by the Claude Code session.
-    let prompt = format_user_prompt(&sender, &user_message);
-
     let bot_name = &ctx.bot_name;
-    let system_prompt = format!(
+    let prompt = format!(
-        "Your name is {bot_name}. Refer to yourself as {bot_name}, not Claude."
+        "[Your name is {bot_name}. Refer to yourself as {bot_name}, not Claude.]\n\n{}",
+        format_user_prompt(&sender, &user_message)
     );
 
     let provider = ClaudeCodeProvider::new();
@@ -792,7 +1133,7 @@ async fn handle_message(
         &prompt,
         &project_root_str,
         resume_session_id.as_deref(),
-        Some(&system_prompt),
+        None,
         &mut cancel_rx,
         move |token| {
             let mut buf = buffer_for_callback.lock().unwrap();
@@ -1221,6 +1562,8 @@ mod tests {
             pending_perm_replies: Arc::new(TokioMutex::new(HashMap::new())),
             permission_timeout_secs: 120,
             bot_name: "Assistant".to_string(),
+            ambient_rooms: Arc::new(TokioMutex::new(HashSet::new())),
+            agents: Arc::new(AgentPool::new_test(3000)),
         };
         // Clone must work (required by Matrix SDK event handler injection).
         let _cloned = ctx.clone();
@@ -1664,6 +2007,127 @@ mod tests {
         assert!(is_permission_approval("\tyes\n"));
     }
 
+    // -- format_startup_announcement ----------------------------------------
+
+    #[test]
+    fn startup_announcement_uses_bot_name() {
+        assert_eq!(format_startup_announcement("Timmy"), "Timmy is online.");
+    }
+
+    #[test]
+    fn startup_announcement_uses_configured_display_name_not_hardcoded() {
+        assert_eq!(format_startup_announcement("HAL"), "HAL is online.");
+        assert_eq!(format_startup_announcement("Assistant"), "Assistant is online.");
+    }
+
+    // -- extract_command (status trigger) ------------------------------------
+
+    #[test]
+    fn extract_command_returns_status_for_bot_name_prefix() {
+        let uid = make_user_id("@assistant:example.com");
+        let result = extract_command("Assistant status", "Assistant", &uid);
+        assert_eq!(result.as_deref(), Some("status"));
+    }
+
+    #[test]
+    fn extract_command_returns_status_for_at_localpart_prefix() {
+        let uid = make_user_id("@assistant:example.com");
+        let result = extract_command("@assistant status", "Assistant", &uid);
+        assert_eq!(result.as_deref(), Some("status"));
+    }
+
+    #[test]
+    fn extract_command_returns_status_for_full_id_prefix() {
+        let uid = make_user_id("@assistant:example.com");
+        let result = extract_command("@assistant:example.com status", "Assistant", &uid);
+        assert_eq!(result.as_deref(), Some("status"));
+    }
+
+    #[test]
+    fn extract_command_returns_none_when_no_bot_mention() {
+        let uid = make_user_id("@assistant:example.com");
+        let result = extract_command("status", "Assistant", &uid);
+        assert!(result.is_none());
+    }
+
+    #[test]
+    fn extract_command_handles_punctuation_after_mention() {
+        let uid = make_user_id("@assistant:example.com");
+        let result = extract_command("@assistant: status", "Assistant", &uid);
+        assert_eq!(result.as_deref(), Some("status"));
+    }
+
+    // -- build_pipeline_status -----------------------------------------------
+
+    fn write_story_file(dir: &std::path::Path, stage: &str, filename: &str, name: &str) {
+        let stage_dir = dir.join(".story_kit").join("work").join(stage);
+        std::fs::create_dir_all(&stage_dir).unwrap();
+        let content = format!("---\nname: \"{name}\"\n---\n\n# {name}\n");
+        std::fs::write(stage_dir.join(filename), content).unwrap();
+    }
+
+    #[test]
+    fn build_pipeline_status_includes_all_stages() {
+        let dir = tempfile::tempdir().unwrap();
+        let pool = AgentPool::new_test(3001);
+        let out = build_pipeline_status(dir.path(), &pool);
+
+        assert!(out.contains("Upcoming"), "missing Upcoming: {out}");
+        assert!(out.contains("In Progress"), "missing In Progress: {out}");
+        assert!(out.contains("QA"), "missing QA: {out}");
+        assert!(out.contains("Merge"), "missing Merge: {out}");
+        assert!(out.contains("Done"), "missing Done: {out}");
+    }
+
+    #[test]
+    fn build_pipeline_status_shows_story_id_and_name() {
+        let dir = tempfile::tempdir().unwrap();
+        write_story_file(
+            dir.path(),
+            "1_upcoming",
+            "42_story_do_something.md",
+            "Do Something",
+        );
+        let pool = AgentPool::new_test(3001);
+        let out = build_pipeline_status(dir.path(), &pool);
+
+        assert!(
+            out.contains("42_story_do_something"),
+            "missing story id: {out}"
+        );
+        assert!(out.contains("Do Something"), "missing story name: {out}");
+    }
+
+    #[test]
+    fn build_pipeline_status_includes_free_agents_section() {
+        let dir = tempfile::tempdir().unwrap();
+        let pool = AgentPool::new_test(3001);
+        let out = build_pipeline_status(dir.path(), &pool);
+
+        assert!(out.contains("Free Agents"), "missing Free Agents section: {out}");
+    }
+
+    #[test]
+    fn build_pipeline_status_uses_markdown_bold_headings() {
+        let dir = tempfile::tempdir().unwrap();
+        let pool = AgentPool::new_test(3001);
+        let out = build_pipeline_status(dir.path(), &pool);
+
+        // Stages and headers should use markdown bold (**text**).
+        assert!(out.contains("**Pipeline Status**"), "missing bold title: {out}");
+        assert!(out.contains("**Upcoming**"), "stage should use bold: {out}");
+    }
+
+    #[test]
+    fn build_pipeline_status_shows_none_for_empty_stages() {
+        let dir = tempfile::tempdir().unwrap();
+        let pool = AgentPool::new_test(3001);
+        let out = build_pipeline_status(dir.path(), &pool);
+
+        // Empty stages show *(none)*
+        assert!(out.contains("*(none)*"), "expected none marker: {out}");
+    }
+
     // -- bot_name / system prompt -------------------------------------------
 
     #[test]
@@ -1687,4 +2151,97 @@ mod tests {
         assert_eq!(resolve_bot_name(None), "Assistant");
         assert_eq!(resolve_bot_name(Some("Timmy".to_string())), "Timmy");
     }
+
+    // -- parse_ambient_command ------------------------------------------------
+
+    #[test]
+    fn ambient_command_on_with_at_mention() {
+        let uid = make_user_id("@timmy:homeserver.local");
+        assert_eq!(parse_ambient_command("@timmy ambient on", &uid, "Timmy"), Some(true));
+    }
+
+    #[test]
+    fn ambient_command_off_with_at_mention() {
+        let uid = make_user_id("@timmy:homeserver.local");
+        assert_eq!(parse_ambient_command("@timmy ambient off", &uid, "Timmy"), Some(false));
+    }
+
+    #[test]
+    fn ambient_command_on_with_full_user_id() {
+        let uid = make_user_id("@timmy:homeserver.local");
+        assert_eq!(
+            parse_ambient_command("@timmy:homeserver.local ambient on", &uid, "Timmy"),
+            Some(true)
+        );
+    }
+
+    #[test]
+    fn ambient_command_on_with_display_name() {
+        let uid = make_user_id("@timmy:homeserver.local");
+        assert_eq!(parse_ambient_command("timmy ambient on", &uid, "Timmy"), Some(true));
+    }
+
+    #[test]
+    fn ambient_command_off_with_display_name() {
+        let uid = make_user_id("@timmy:homeserver.local");
+        assert_eq!(parse_ambient_command("timmy ambient off", &uid, "Timmy"), Some(false));
+    }
+
+    #[test]
+    fn ambient_command_on_bare() {
+        // "ambient on" without any bot mention is also recognised.
+        let uid = make_user_id("@timmy:homeserver.local");
+        assert_eq!(parse_ambient_command("ambient on", &uid, "Timmy"), Some(true));
+    }
+
+    #[test]
+    fn ambient_command_off_bare() {
+        let uid = make_user_id("@timmy:homeserver.local");
+        assert_eq!(parse_ambient_command("ambient off", &uid, "Timmy"), Some(false));
+    }
+
+    #[test]
+    fn ambient_command_case_insensitive() {
+        let uid = make_user_id("@timmy:homeserver.local");
+        assert_eq!(parse_ambient_command("@Timmy AMBIENT ON", &uid, "Timmy"), Some(true));
+        assert_eq!(parse_ambient_command("TIMMY AMBIENT OFF", &uid, "Timmy"), Some(false));
+    }
+
+    #[test]
+    fn ambient_command_unrelated_message_returns_none() {
+        let uid = make_user_id("@timmy:homeserver.local");
+        assert_eq!(parse_ambient_command("@timmy what is the status?", &uid, "Timmy"), None);
+        assert_eq!(parse_ambient_command("hello there", &uid, "Timmy"), None);
+        assert_eq!(parse_ambient_command("ambient", &uid, "Timmy"), None);
+    }
+
+    // -- ambient mode state ---------------------------------------------------
+
+    #[tokio::test]
+    async fn ambient_rooms_defaults_to_empty() {
+        let ambient_rooms: Arc<TokioMutex<HashSet<OwnedRoomId>>> =
+            Arc::new(TokioMutex::new(HashSet::new()));
+        let room_id: OwnedRoomId = "!room:example.com".parse().unwrap();
+        assert!(!ambient_rooms.lock().await.contains(&room_id));
+    }
+
+    #[tokio::test]
+    async fn ambient_mode_can_be_toggled_per_room() {
+        let ambient_rooms: Arc<TokioMutex<HashSet<OwnedRoomId>>> =
+            Arc::new(TokioMutex::new(HashSet::new()));
+        let room_a: OwnedRoomId = "!room_a:example.com".parse().unwrap();
+        let room_b: OwnedRoomId = "!room_b:example.com".parse().unwrap();
+
+        // Enable ambient mode for room_a only.
+        ambient_rooms.lock().await.insert(room_a.clone());
+
+        let guard = ambient_rooms.lock().await;
+        assert!(guard.contains(&room_a), "room_a should be in ambient mode");
+        assert!(!guard.contains(&room_b), "room_b should NOT be in ambient mode");
+        drop(guard);
+
+        // Disable ambient mode for room_a.
+        ambient_rooms.lock().await.remove(&room_a);
+        assert!(!ambient_rooms.lock().await.contains(&room_a), "room_a ambient mode should be off");
+    }
 }

server/src/matrix/commands.rs

@@ -0,0 +1,318 @@
+//! Bot-level command registry for the Matrix bot.
+//!
+//! Commands registered here are handled directly by the bot without invoking
+//! the LLM. The registry is the single source of truth — the `help` command
+//! iterates it automatically so new commands appear in the help output as soon
+//! as they are added.
+
+/// A bot-level command that is handled without LLM invocation.
+pub struct BotCommand {
+    /// The command keyword (e.g., `"help"`). Always lowercase.
+    pub name: &'static str,
+    /// Short description shown in help output.
+    pub description: &'static str,
+    /// Handler that produces the response text (Markdown).
+    pub handler: fn(&CommandContext) -> String,
+}
+
+/// Context passed to command handlers.
+pub struct CommandContext<'a> {
+    /// The bot's display name (e.g., "Timmy").
+    pub bot_name: &'a str,
+    /// Any text after the command keyword, trimmed.
+    #[allow(dead_code)]
+    pub args: &'a str,
+}
+
+/// Returns the full list of registered bot commands.
+///
+/// Add new commands here — they will automatically appear in `help` output.
+pub fn commands() -> &'static [BotCommand] {
+    &[BotCommand {
+        name: "help",
+        description: "Show this list of available commands",
+        handler: handle_help,
+    }]
+}
+
+/// Try to match a user message against a registered bot command.
+///
+/// The message is expected to be the raw body text from Matrix (e.g.,
+/// `"@timmy help"`). The bot mention prefix is stripped before matching.
+///
+/// Returns `Some(response)` if a command matched, `None` otherwise (the
+/// caller should fall through to the LLM).
+pub fn try_handle_command(
+    bot_name: &str,
+    bot_user_id: &str,
+    message: &str,
+) -> Option<String> {
+    let command_text = strip_bot_mention(message, bot_name, bot_user_id);
+    let trimmed = command_text.trim();
+    if trimmed.is_empty() {
+        return None;
+    }
+
+    let (cmd_name, args) = match trimmed.split_once(char::is_whitespace) {
+        Some((c, a)) => (c, a.trim()),
+        None => (trimmed, ""),
+    };
+    let cmd_lower = cmd_name.to_ascii_lowercase();
+
+    let ctx = CommandContext {
+        bot_name,
+        args,
+    };
+
+    commands()
+        .iter()
+        .find(|c| c.name == cmd_lower)
+        .map(|c| (c.handler)(&ctx))
+}
+
+/// Strip the bot mention prefix from a raw message body.
+///
+/// Handles these forms (case-insensitive where applicable):
+/// - `@bot_localpart:server.com rest` → `rest`
+/// - `@bot_localpart rest` → `rest`
+/// - `DisplayName rest` → `rest`
+fn strip_bot_mention<'a>(message: &'a str, bot_name: &str, bot_user_id: &str) -> &'a str {
+    let trimmed = message.trim();
+
+    // Try full Matrix user ID (e.g. "@timmy:homeserver.local")
+    if let Some(rest) = strip_prefix_ci(trimmed, bot_user_id) {
+        return rest;
+    }
+
+    // Try @localpart (e.g. "@timmy")
+    if let Some(localpart) = bot_user_id.split(':').next()
+        && let Some(rest) = strip_prefix_ci(trimmed, localpart)
+    {
+        return rest;
+    }
+
+    // Try display name (e.g. "Timmy")
+    if let Some(rest) = strip_prefix_ci(trimmed, bot_name) {
+        return rest;
+    }
+
+    trimmed
+}
+
+/// Case-insensitive prefix strip that also requires the match to end at a
+/// word boundary (whitespace, punctuation, or end-of-string).
+fn strip_prefix_ci<'a>(text: &'a str, prefix: &str) -> Option<&'a str> {
+    if text.len() < prefix.len() {
+        return None;
+    }
+    if !text[..prefix.len()].eq_ignore_ascii_case(prefix) {
+        return None;
+    }
+    let rest = &text[prefix.len()..];
+    // Must be at end or followed by non-alphanumeric
+    match rest.chars().next() {
+        None => Some(rest), // exact match, empty remainder
+        Some(c) if c.is_alphanumeric() || c == '-' || c == '_' => None, // not a word boundary
+        _ => Some(rest),
+    }
+}
+
+// ---------------------------------------------------------------------------
+// Built-in command handlers
+// ---------------------------------------------------------------------------
+
+fn handle_help(ctx: &CommandContext) -> String {
+    let mut output = format!("**{} Commands**\n\n", ctx.bot_name);
+    for cmd in commands() {
+        output.push_str(&format!("- **{}** — {}\n", cmd.name, cmd.description));
+    }
+    output
+}
+
+// ---------------------------------------------------------------------------
+// Tests
+// ---------------------------------------------------------------------------
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    // -- strip_bot_mention --------------------------------------------------
+
+    #[test]
+    fn strip_mention_full_user_id() {
+        let rest = strip_bot_mention(
+            "@timmy:homeserver.local help",
+            "Timmy",
+            "@timmy:homeserver.local",
+        );
+        assert_eq!(rest.trim(), "help");
+    }
+
+    #[test]
+    fn strip_mention_localpart() {
+        let rest = strip_bot_mention("@timmy help me", "Timmy", "@timmy:homeserver.local");
+        assert_eq!(rest.trim(), "help me");
+    }
+
+    #[test]
+    fn strip_mention_display_name() {
+        let rest = strip_bot_mention("Timmy help", "Timmy", "@timmy:homeserver.local");
+        assert_eq!(rest.trim(), "help");
+    }
+
+    #[test]
+    fn strip_mention_display_name_case_insensitive() {
+        let rest = strip_bot_mention("timmy help", "Timmy", "@timmy:homeserver.local");
+        assert_eq!(rest.trim(), "help");
+    }
+
+    #[test]
+    fn strip_mention_no_match_returns_original() {
+        let rest = strip_bot_mention("hello world", "Timmy", "@timmy:homeserver.local");
+        assert_eq!(rest, "hello world");
+    }
+
+    #[test]
+    fn strip_mention_does_not_match_longer_name() {
+        // "@timmybot" should NOT match "@timmy"
+        let rest = strip_bot_mention("@timmybot help", "Timmy", "@timmy:homeserver.local");
+        assert_eq!(rest, "@timmybot help");
+    }
+
+    #[test]
+    fn strip_mention_comma_after_name() {
+        let rest = strip_bot_mention("@timmy, help", "Timmy", "@timmy:homeserver.local");
+        assert_eq!(rest.trim().trim_start_matches(',').trim(), "help");
+    }
+
+    // -- try_handle_command -------------------------------------------------
+
+    #[test]
+    fn help_command_matches() {
+        let result = try_handle_command("Timmy", "@timmy:homeserver.local", "@timmy help");
+        assert!(result.is_some(), "help command should match");
+    }
+
+    #[test]
+    fn help_command_case_insensitive() {
+        let result = try_handle_command("Timmy", "@timmy:homeserver.local", "@timmy HELP");
+        assert!(result.is_some(), "HELP should match case-insensitively");
+    }
+
+    #[test]
+    fn unknown_command_returns_none() {
+        let result = try_handle_command(
+            "Timmy",
+            "@timmy:homeserver.local",
+            "@timmy what is the weather?",
+        );
+        assert!(result.is_none(), "non-command should return None");
+    }
+
+    #[test]
+    fn help_output_contains_all_commands() {
+        let result = try_handle_command("Timmy", "@timmy:homeserver.local", "@timmy help");
+        let output = result.unwrap();
+        for cmd in commands() {
+            assert!(
+                output.contains(cmd.name),
+                "help output must include command '{}'",
+                cmd.name
+            );
+            assert!(
+                output.contains(cmd.description),
+                "help output must include description for '{}'",
+                cmd.name
+            );
+        }
+    }
+
+    #[test]
+    fn help_output_uses_bot_name() {
+        let result = try_handle_command("HAL", "@hal:example.com", "@hal help");
+        let output = result.unwrap();
+        assert!(
+            output.contains("HAL Commands"),
+            "help output should use bot name: {output}"
+        );
+    }
+
+    #[test]
+    fn help_output_formatted_as_markdown() {
+        let result = try_handle_command("Timmy", "@timmy:homeserver.local", "@timmy help");
+        let output = result.unwrap();
+        assert!(
+            output.contains("**help**"),
+            "command name should be bold: {output}"
+        );
+        assert!(
+            output.contains("- **"),
+            "commands should be in a list: {output}"
+        );
+    }
+
+    #[test]
+    fn empty_message_after_mention_returns_none() {
+        let result = try_handle_command("Timmy", "@timmy:homeserver.local", "@timmy");
+        assert!(
+            result.is_none(),
+            "bare mention with no command should fall through to LLM"
+        );
+    }
+
+    // -- strip_prefix_ci ----------------------------------------------------
+
+    #[test]
+    fn strip_prefix_ci_basic() {
+        assert_eq!(strip_prefix_ci("Hello world", "hello"), Some(" world"));
+    }
+
+    #[test]
+    fn strip_prefix_ci_no_match() {
+        assert_eq!(strip_prefix_ci("goodbye", "hello"), None);
+    }
+
+    #[test]
+    fn strip_prefix_ci_word_boundary_required() {
+        assert_eq!(strip_prefix_ci("helloworld", "hello"), None);
+    }
+
+    #[test]
+    fn strip_prefix_ci_exact_match() {
+        assert_eq!(strip_prefix_ci("hello", "hello"), Some(""));
+    }
+
+    // -- commands registry --------------------------------------------------
+
+    #[test]
+    fn commands_registry_is_not_empty() {
+        assert!(
+            !commands().is_empty(),
+            "command registry must contain at least one command"
+        );
+    }
+
+    #[test]
+    fn all_command_names_are_lowercase() {
+        for cmd in commands() {
+            assert_eq!(
+                cmd.name,
+                cmd.name.to_ascii_lowercase(),
+                "command name '{}' must be lowercase",
+                cmd.name
+            );
+        }
+    }
+
+    #[test]
+    fn all_commands_have_descriptions() {
+        for cmd in commands() {
+            assert!(
+                !cmd.description.is_empty(),
+                "command '{}' must have a description",
+                cmd.name
+            );
+        }
+    }
+}

server/src/matrix/config.rs

@@ -53,6 +53,11 @@ pub struct BotConfig {
     /// If unset, the bot falls back to "Assistant".
     #[serde(default)]
     pub display_name: Option<String>,
+    /// Room IDs where ambient mode is active (bot responds to all messages).
+    /// Updated at runtime when the user toggles ambient mode — do not edit
+    /// manually while the bot is running.
+    #[serde(default)]
+    pub ambient_rooms: Vec<String>,
 }
 
 impl BotConfig {
@@ -97,6 +102,46 @@ impl BotConfig {
     }
 }
 
+/// Persist the current set of ambient room IDs back to `bot.toml`.
+///
+/// Reads the existing file as a TOML document, updates the `ambient_rooms`
+/// array, and writes the result back.  Errors are logged but not propagated
+/// so a persistence failure never interrupts the bot's message handling.
+pub fn save_ambient_rooms(project_root: &Path, room_ids: &[String]) {
+    let path = project_root.join(".story_kit").join("bot.toml");
+    let content = match std::fs::read_to_string(&path) {
+        Ok(c) => c,
+        Err(e) => {
+            eprintln!("[matrix-bot] save_ambient_rooms: failed to read bot.toml: {e}");
+            return;
+        }
+    };
+    let mut doc: toml::Value = match toml::from_str(&content) {
+        Ok(v) => v,
+        Err(e) => {
+            eprintln!("[matrix-bot] save_ambient_rooms: failed to parse bot.toml: {e}");
+            return;
+        }
+    };
+    if let toml::Value::Table(ref mut t) = doc {
+        let arr = toml::Value::Array(
+            room_ids
+                .iter()
+                .map(|s| toml::Value::String(s.clone()))
+                .collect(),
+        );
+        t.insert("ambient_rooms".to_string(), arr);
+    }
+    match toml::to_string_pretty(&doc) {
+        Ok(new_content) => {
+            if let Err(e) = std::fs::write(&path, new_content) {
+                eprintln!("[matrix-bot] save_ambient_rooms: failed to write bot.toml: {e}");
+            }
+        }
+        Err(e) => eprintln!("[matrix-bot] save_ambient_rooms: failed to serialise bot.toml: {e}"),
+    }
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;
@@ -378,4 +423,90 @@ require_verified_devices = true
             "bot.toml with legacy require_verified_devices key must still load"
         );
     }
+
+    #[test]
+    fn load_reads_ambient_rooms() {
+        let tmp = tempfile::tempdir().unwrap();
+        let sk = tmp.path().join(".story_kit");
+        fs::create_dir_all(&sk).unwrap();
+        fs::write(
+            sk.join("bot.toml"),
+            r#"
+homeserver = "https://matrix.example.com"
+username = "@bot:example.com"
+password = "secret"
+room_ids = ["!abc:example.com"]
+enabled = true
+ambient_rooms = ["!abc:example.com"]
+"#,
+        )
+        .unwrap();
+        let config = BotConfig::load(tmp.path()).unwrap();
+        assert_eq!(config.ambient_rooms, vec!["!abc:example.com"]);
+    }
+
+    #[test]
+    fn load_ambient_rooms_defaults_to_empty_when_absent() {
+        let tmp = tempfile::tempdir().unwrap();
+        let sk = tmp.path().join(".story_kit");
+        fs::create_dir_all(&sk).unwrap();
+        fs::write(
+            sk.join("bot.toml"),
+            r#"
+homeserver = "https://matrix.example.com"
+username = "@bot:example.com"
+password = "secret"
+room_ids = ["!abc:example.com"]
+enabled = true
+"#,
+        )
+        .unwrap();
+        let config = BotConfig::load(tmp.path()).unwrap();
+        assert!(config.ambient_rooms.is_empty());
+    }
+
+    #[test]
+    fn save_ambient_rooms_persists_to_bot_toml() {
+        let tmp = tempfile::tempdir().unwrap();
+        let sk = tmp.path().join(".story_kit");
+        fs::create_dir_all(&sk).unwrap();
+        fs::write(
+            sk.join("bot.toml"),
+            r#"homeserver = "https://matrix.example.com"
+username = "@bot:example.com"
+password = "secret"
+room_ids = ["!abc:example.com"]
+enabled = true
+"#,
+        )
+        .unwrap();
+
+        save_ambient_rooms(tmp.path(), &["!abc:example.com".to_string()]);
+
+        let config = BotConfig::load(tmp.path()).unwrap();
+        assert_eq!(config.ambient_rooms, vec!["!abc:example.com"]);
+    }
+
+    #[test]
+    fn save_ambient_rooms_clears_when_empty() {
+        let tmp = tempfile::tempdir().unwrap();
+        let sk = tmp.path().join(".story_kit");
+        fs::create_dir_all(&sk).unwrap();
+        fs::write(
+            sk.join("bot.toml"),
+            r#"homeserver = "https://matrix.example.com"
+username = "@bot:example.com"
+password = "secret"
+room_ids = ["!abc:example.com"]
+enabled = true
+ambient_rooms = ["!abc:example.com"]
+"#,
+        )
+        .unwrap();
+
+        save_ambient_rooms(tmp.path(), &[]);
+
+        let config = BotConfig::load(tmp.path()).unwrap();
+        assert!(config.ambient_rooms.is_empty());
+    }
 }

server/src/matrix/mod.rs

@@ -16,11 +16,13 @@
 //! `bot.toml`. Each room maintains its own independent conversation history.
 
 mod bot;
+pub mod commands;
 mod config;
 pub mod notifications;
 
 pub use config::BotConfig;
 
+use crate::agents::AgentPool;
 use crate::http::context::PermissionForward;
 use crate::io::watcher::WatcherEvent;
 use std::path::Path;
@@ -46,6 +48,7 @@ pub fn spawn_bot(
     project_root: &Path,
     watcher_tx: broadcast::Sender<WatcherEvent>,
     perm_rx: Arc<TokioMutex<mpsc::UnboundedReceiver<PermissionForward>>>,
+    agents: Arc<AgentPool>,
 ) {
     let config = match BotConfig::load(project_root) {
         Some(c) => c,
@@ -64,7 +67,7 @@ pub fn spawn_bot(
     let root = project_root.to_path_buf();
     let watcher_rx = watcher_tx.subscribe();
     tokio::spawn(async move {
-        if let Err(e) = bot::run_bot(config, root, watcher_rx, perm_rx).await {
+        if let Err(e) = bot::run_bot(config, root, watcher_rx, perm_rx, agents).await {
             crate::slog!("[matrix-bot] Fatal error: {e}");
         }
     });

server/src/matrix/notifications.rs

@@ -15,7 +15,7 @@ use tokio::sync::broadcast;
 /// Human-readable display name for a pipeline stage directory.
 pub fn stage_display_name(stage: &str) -> &'static str {
     match stage {
-        "1_upcoming" => "Upcoming",
+        "1_backlog" => "Backlog",
         "2_current" => "Current",
         "3_qa" => "QA",
         "4_merge" => "Merge",
@@ -27,11 +27,11 @@ pub fn stage_display_name(stage: &str) -> &'static str {
 
 /// Infer the previous pipeline stage for a given destination stage.
 ///
-/// Returns `None` for `1_upcoming` since items are created there (not
+/// Returns `None` for `1_backlog` since items are created there (not
 /// transitioned from another stage).
 pub fn inferred_from_stage(to_stage: &str) -> Option<&'static str> {
     match to_stage {
-        "2_current" => Some("Upcoming"),
+        "2_current" => Some("Backlog"),
         "3_qa" => Some("Current"),
         "4_merge" => Some("QA"),
         "5_done" => Some("Merge"),
@@ -195,7 +195,7 @@ mod tests {
 
     #[test]
     fn stage_display_name_maps_all_known_stages() {
-        assert_eq!(stage_display_name("1_upcoming"), "Upcoming");
+        assert_eq!(stage_display_name("1_backlog"), "Backlog");
         assert_eq!(stage_display_name("2_current"), "Current");
         assert_eq!(stage_display_name("3_qa"), "QA");
         assert_eq!(stage_display_name("4_merge"), "Merge");
@@ -208,7 +208,7 @@ mod tests {
 
     #[test]
     fn inferred_from_stage_returns_previous_stage() {
-        assert_eq!(inferred_from_stage("2_current"), Some("Upcoming"));
+        assert_eq!(inferred_from_stage("2_current"), Some("Backlog"));
         assert_eq!(inferred_from_stage("3_qa"), Some("Current"));
         assert_eq!(inferred_from_stage("4_merge"), Some("QA"));
         assert_eq!(inferred_from_stage("5_done"), Some("Merge"));
@@ -216,8 +216,8 @@ mod tests {
     }
 
     #[test]
-    fn inferred_from_stage_returns_none_for_upcoming() {
+    fn inferred_from_stage_returns_none_for_backlog() {
-        assert_eq!(inferred_from_stage("1_upcoming"), None);
+        assert_eq!(inferred_from_stage("1_backlog"), None);
     }
 
     #[test]