@a-t-h-i/bot-lobby 0.6.5 → 0.6.6

package/README.md

@@ -2,7 +2,7 @@
 
 A [Pi](https://pi.dev) extension that turns Pi into a multi-agent software team.
 
-![The bot-lobby status scene: the oracle orchestrating DEV, DESIGN, RESEARCH and QA through a task's plan](https://raw.githubusercontent.com/a-t-h-i/bot-lobby/main/docs/gallery.png)
+![The Lobby tab: your conversation with the oracle, the activity log of every agent, and their latest thoughts](https://raw.githubusercontent.com/a-t-h-i/bot-lobby/main/docs/gallery.png)
 
 `/bot-lobby <request>` (or a request typed in the lobby) starts a task, unless
 one agent can simply do it: then it goes to the [quick-fix agent](#quick-fix-or-the-team).
@@ -16,6 +16,10 @@ The rule: **LLMs decide, the engine enforces.** Agents propose; the
 extension validates every state change, permission and approval through one
 `orchestrate` tool.
 
+The oracle is meant to be your most capable model; the agents can be smaller
+and cheaper ones. So it never assumes they are as capable as it is: it makes
+every decision itself and [briefs each agent in full](#briefing-the-agents).
+
 ## Install
 
 ```bash
@@ -35,7 +39,7 @@ tool names.
 
 1. `/bot-lobby add a login page` — starts a task; the lobby opens.
 2. Answer the Master's questions, then approve its proposal.
-3. Watch the agents work in the lobby (`alt+l` shows or hides it).
+3. Follow the agents in the lobby (`alt+l` shows or hides it): what they do, and what they think.
 
 `/bot-lobby settings` sets each agent's model, thinking level, time limit and
 extra instructions.
@@ -129,6 +133,30 @@ passwords, payments, migrations, production, personal data), or **unclear**
 - The track shows in the lobby's activity log, the task's details on the
   Tasks tab, and `/bot-lobby status`.
 
+### Briefing the agents
+
+Every agent may run on a smaller, cheaper model than the oracle's, one that
+follows instructions well but does not infer intent. So the oracle writes
+each delegation (`implement`, `scout`, `research`) as a self-contained brief
+and settles every design and architecture decision itself first:
+
+- **Goal**, the exact **Files**, numbered **What to do** with names, shapes
+  and values, the **Contracts** shared with other agents (repeated in full in
+  each brief), **Constraints**, **Done when** (checkable criteria and the
+  commands to run) and **If stuck**.
+- Plan steps are written to the same standard, so a brief is the plan step
+  made explicit, never a new decision.
+- Every agent is told to follow its brief and the approved plan exactly, use
+  the given names letter for letter, and report what does not match instead of
+  guessing. Workers end their report with a **Brief Check**: each "Done when"
+  item, met or not, with evidence.
+- The oracle holds each report to its brief. Drift, a skipped criterion or a
+  guessed choice comes back as a fix step with a more explicit brief.
+- The engine backs it up: a delegation that names nothing concrete (or a long
+  one with no done criteria) is sent back to the oracle once before any agent
+  starts. Sending the same text again goes through, so a short task that is
+  complete as written is never stuck. `workflow.briefCheck: false` turns it off.
+
 ### The full workflow
 
 - **Scouts** (read-only) investigate the domains the request touches.
@@ -188,16 +216,54 @@ everything. `workflow.freshContext: false` in the config turns this off.
 ## The lobby
 
 A full-screen view with a prompt at the bottom that talks to whatever tab is
-open. `alt+h` lists every key.
+open. `alt+h` lists every key. It is text only: no animations, just the
+conversation, the activity log and the thoughts, and a one-line status in Pi's
+footer.
 
 | Tab | What it is |
 | --- | --- |
-| **1 Lobby** | The task's status, your conversation with the oracle, an activity log of every tool call, and each agent's latest thought |
+| **1 Lobby** | Your conversation with the oracle, an activity log of every agent's steps, and each agent's latest thought |
 | **2 Tasks** | Every task and saved plan as a checklist. `s` starts a plan in a new session, `h` here; `c` comments on a plan; `a` archives, `d` deletes |
 | **3 Plan** | Plan a task with a panel of agents before building it (below) |
 | **4 Quick fix** | One agent makes a change right away, beside any running task; requests the oracle [routes here](#quick-fix-or-the-team) show up too |
 | **5 Metrics** | Run time, success rate, tokens and cost per model and agent |
 
+### Lobby
+
+![The Lobby tab](https://raw.githubusercontent.com/a-t-h-i/bot-lobby/main/docs/gallery.png)
+
+Your conversation with the oracle on the left, the activity log of every
+agent's steps on the right, and the agents' latest thoughts below. `alt+c`,
+`alt+a` and `alt+k` hide any of the three; the prompt steers the running turn.
+
+### Tasks
+
+![The Tasks tab](https://raw.githubusercontent.com/a-t-h-i/bot-lobby/main/docs/lobby-tasks.png)
+
+Every task as a checklist, with its track, plan progress, the approved plan
+and your comments on it.
+
+### Plan
+
+![The Plan tab](https://raw.githubusercontent.com/a-t-h-i/bot-lobby/main/docs/lobby-plan.png)
+
+The panel's questions, with recommended options, on the left; the draft plan
+on the right. See [Planning](#planning).
+
+### Quick fix
+
+![The Quick fix tab](https://raw.githubusercontent.com/a-t-h-i/bot-lobby/main/docs/lobby-quickfix.png)
+
+One agent's jobs, each with its live steps, the files it edited and its
+report. See [Quick fix or the team](#quick-fix-or-the-team).
+
+### Metrics
+
+![The Metrics tab](https://raw.githubusercontent.com/a-t-h-i/bot-lobby/main/docs/lobby-metrics.png)
+
+Run time, success rate, cost and tokens per model and agent, so you can see
+which cheaper models hold up.
+
 Common keys: `tab` switches tabs, `esc` browses (arrows, single-key
 commands), `ctrl+f` searches, `ctrl+s` saves the plan, `alt+o` browses
 sessions, `alt+n` starts a task in a new session, `alt+s` opens settings.
@@ -336,7 +402,7 @@ the result.
   "scout": { "model": "anthropic/claude-haiku-4-5-20251001", "timeoutMs": 480000 },
   "planner": { "thinking": "high", "timeoutMs": 300000 },
   "lobby": { "planningPanel": ["backend", "designer", "qa", "researcher"], "maxPlanningRounds": 5 },
-  "workflow": { "maxReviewIterations": 2, "maxParallelWorkers": 3, "stallTimeoutMs": 300000, "wrapUpAt": 0.75, "taskBudgetMinutes": 0, "fastTrack": true, "routeQuickFixes": true },
+  "workflow": { "maxReviewIterations": 2, "maxParallelWorkers": 3, "stallTimeoutMs": 300000, "wrapUpAt": 0.75, "taskBudgetMinutes": 0, "fastTrack": true, "briefCheck": true, "routeQuickFixes": true },
   "classifier": { "enabled": false, "provider": "auto", "effort": { "cheapModel": "inherit" } }
 }
 ```

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@a-t-h-i/bot-lobby",
-  "version": "0.6.5",
+  "version": "0.6.6",
   "description": "Structured multi-agent software engineering orchestrator for Pi",
   "type": "module",
   "license": "Apache-2.0",

package/prompts/global.md

@@ -15,6 +15,24 @@ Perform your assigned responsibility precisely and remain within your domain.
 - Do not invent requirements; ask when they are genuinely ambiguous.
 - Report conclusions, evidence, decisions, findings and blockers concisely.
 
+## Following your brief
+
+The Master that instructs you plans the work and knows the whole task; you may
+be a smaller model that sees only your part. Your brief and the approved plan
+are your authority, so:
+
+- Read the whole brief and the plan before acting, and do exactly what it
+  says, in its order. Do not add features, refactors or "improvements", and do
+  not skip steps because they look unnecessary.
+- Use the names, paths, shapes and wording the brief gives you, letter for
+  letter. Where it leaves a detail open, choose the simplest option that
+  follows the existing code, and say what you chose in your report.
+- Never guess at something that matters (a contract, a file that is not there,
+  a conflict between the brief and the code). Stop that part, finish the rest,
+  and report it under Blockers or Pushback with what you found.
+- Check your own work against the brief's "Done when" list before you report,
+  criterion by criterion, and say honestly which are met and which are not.
+
 ## Hard rules
 
 - Do not add dependencies without approval.

package/prompts/master.md

@@ -155,12 +155,81 @@ each `implement` task with its step number (`Step 3: ...`, or `Steps 3-4: ...`
 when one delegation covers several) so the user's checklist tracks progress
 exactly.
 
+## Briefing the agents
+
+You are usually a far more capable model than the agents you delegate to. Scouts,
+workers, the researcher and the reviewer may run on smaller, cheaper models
+that follow instructions well but do not infer intent, fill gaps sensibly or
+know what you know. Never assume they are as capable as you. Whatever you leave
+unsaid, they will guess, and a wrong guess costs a whole agent run. Your plan
+and every brief are how your goal reaches the code, so write them for a
+capable but literal reader who has read nothing but the brief and the
+repository.
+
+Every `implement` task (each assignment in a parallel batch), `scout` and
+`research` instruction is a self-contained brief with these parts, in this order:
+
+1. **Goal** — the outcome this step must produce and how it serves the user's
+   request and the approved plan, in one or two sentences. Name the step
+   number(s).
+2. **Files** — the exact paths to create or change, and the ones to leave
+   alone. When you do not know a path, say what to search for and where.
+3. **What to do** — numbered, concrete actions in the order to do them: names
+   of functions, components, endpoints, fields, types, CSS classes, strings,
+   values. Give the exact signature, shape or wording wherever it matters.
+   Write "use X", not "use a suitable library"; when a choice is left to the
+   agent, say which options are allowed and how to pick.
+4. **Contracts** — everything this step shares with another domain or step:
+   API shapes, status codes, error format, event names, shared types, data
+   formats, file locations. State them in full in every brief that touches
+   them; an agent never sees another agent's brief.
+5. **Constraints** — what it must not do: no new dependencies, no other files,
+   no refactors, no changed behavior outside the step, no restyling of code
+   it does not own. Repeat the user's explicit requirements that apply.
+6. **Done when** — a checklist of observable, checkable criteria (behaviors,
+   exact commands to run and what they should print, files that must exist),
+   including what to verify and how, with `timeout`. The agent must be able to
+   tell for itself whether it has finished.
+7. **If stuck** — what to do when something does not match the brief (a file is
+   missing, a name differs, two instructions conflict): stop that part, do not
+   invent a workaround, and report it under Blockers or Pushback with what it
+   found. Ask nothing you can answer yourself: settle it in the brief.
+
+Rules for the brief:
+
+- Decide first, delegate second. Every design, architecture and product
+  decision belongs to you; make it and write down the result. A brief must not
+  contain "consider", "as appropriate", "if needed", "etc.", "similar to",
+  "handle edge cases" or "make it look good" without the specifics. List the
+  edge cases; describe the look in concrete terms (layout, sizes, colors,
+  states).
+- Say the obvious. Repeat what you already told an earlier agent, include the
+  conventions to follow and point to an existing file to imitate by path.
+- One step, one purpose, small enough to hold in mind: a handful of files and
+  a few actions. Split anything larger into consecutive steps in the same
+  `implement` call rather than leaving the agent to sequence it. Prefer more
+  explicit detail to fewer, larger chunks.
+- The plan's steps are written to the same standard: each step names its
+  files, its actions and its done criteria, so the brief is the step made
+  explicit, never a new decision.
+- Scout and research instructions ask specific questions with the answer
+  format you want (paths, names, versions, yes/no plus evidence), and say what
+  you will do with the answer.
+
+When a report comes back, hold it to the brief: check each **Done when**
+criterion against the report's `## Brief Check`, the diff and the repository.
+Drift, a skipped criterion or a guessed choice is a fix step with a corrected,
+even more explicit brief that quotes the exact gap — not a reason to accept the
+work, and not a reason to redo it yourself. Keep every agent on your plan: if
+the code no longer matches it, say which step it deviates from and restore it.
+
 ## Speed
 
 Every delegation costs a full agent run, so keep the loop short:
 
-- Delegate fewer, larger chunks: one `implement` per domain covering its
-  consecutive steps (`Steps 2-4: ...`) rather than one call per step.
+- Delegate fewer calls, not vaguer ones: one `implement` per domain covering
+  its consecutive steps (`Steps 2-4: ...`) rather than one call per step, each
+  step still briefed in full (see Briefing the agents).
 - When steps for different domains are independent, run them together with
   `implement` `assignments` (one entry per domain). Workers then share files
   through the file desk: they claim files, queue for busy ones, and hand them

package/prompts/worker.md

@@ -19,7 +19,9 @@ them.
 
 ## Implementation
 
-- Follow the approved plan.
+- Follow the approved plan and your brief exactly: they are the Master's
+  decisions. Do not substitute your own design, rename things, or widen the
+  step. If the code contradicts the brief, do not improvise: report it.
 - Follow domain boundaries.
 
 If you need a new dependency, or you believe a significant architectural
@@ -73,7 +75,10 @@ repository at the same time, and files are checked out like physical documents:
 
 ## Before handoff
 
-- Inspect the actual diff.
+- Go through the brief's "Done when" list one criterion at a time and record
+  each in `## Brief Check` as `- criterion — met|not met — evidence`.
+- Inspect the actual diff: it must contain what the brief asked for and
+  nothing else.
 - Verify tests.
 - Update the temporary task scratchpad.
 - Report concise results.

package/src/ask/dialog.ts

@@ -83,7 +83,17 @@ export class AskDialog implements Component {
  * cannot draw the questionnaire. Without any UI nobody can answer: the
  * result says the questions were put away.
  */
-export const askUser: Asker = async (questions, ctx, signal, from) => {
+export const askUser: Asker = (questions, ctx, signal, from) => {
+  // A model may call the tool several times in one turn; pi runs them in parallel, and overlays opened together hide each other. One at a time.
+  const next = asking.then(() => (signal?.aborted ? { answers: [], cancelled: true } : askNow(questions, ctx, signal, from)));
+  asking = next.then(() => undefined, () => undefined);
+  return next;
+};
+
+/** Tail of the questions waiting their turn. */
+let asking: Promise<void> = Promise.resolve();
+
+const askNow: Asker = async (questions, ctx, signal, from) => {
   if (!ctx.hasUI || questions.length === 0) return { answers: [], cancelled: true };
   if ((ctx as { mode?: string }).mode === "rpc") return dialogAsker(questions, ctx, signal, from);
   // Option images are read before the questionnaire opens, so drawing it never waits on the disk.

package/src/index.ts

@@ -21,7 +21,7 @@ export default function (pi: ExtensionAPI): void {
   // Before the lifecycle, so a task that ended while the oracle was idle is closed before it builds the next turn's prompt.
   registerFreshContext(pi, CONFIG_DIR_NAME);
   registerLifecycle(pi, CONFIG_DIR_NAME);
-  // After the lifecycle, so the lobby opens over a task the widget state already knows.
+  // After the lifecycle, so the lobby opens over a task the status already knows.
   registerLobbyEvents(pi, CONFIG_DIR_NAME);
   registerOwner(pi, CONFIG_DIR_NAME);
   onTransition((task) => pingTransition(task));

package/src/lobby/feed.ts

@@ -2,7 +2,7 @@
  * What the lobby narrates: an activity log of plain-words tool steps from the
  * Master and every subagent, a single place for thoughts, and the conversation
  * with the Master stripped of tool rows and thinking. Bounded ring buffers in
- * one module-level store (like the zen widget state), so every event source can
+ * one module-level store (like the task state in ui.ts), so every event source can
  * write without a reference to the lobby, and the lobby repaints on `version`.
  */
 import type { AgentRun } from "../schemas/findings.ts";

package/src/lobby/keys.ts

@@ -17,7 +17,6 @@ export const LOBBY_ACTIONS = {
   toggleAuto: { key: "alt+g", help: "auto mode: the oracle drives the task to completion without asking" },
   nextTab: { key: "tab", help: "next tab" },
   prevTab: { key: "shift+tab", help: "previous tab" },
-  toggleScene: { key: "alt+z", help: "show or hide the oracle and agent animations" },
   toggleConversation: { key: "alt+c", help: "show or hide the conversation" },
   toggleActivity: { key: "alt+a", help: "show or hide the activity log" },
   toggleThinking: { key: "alt+k", help: "show or hide thinking" },

package/src/lobby/runtime.ts

@@ -20,8 +20,7 @@ import { archiveTask as archiveTaskOnDisk, deleteTask as deleteTaskOnDisk, listA
 import { discardPlannedTask, listPlannedTasks, type PlannedTask } from "../state/backlog.ts";
 import { appendMetrics, readClassifierMetrics, readMetrics, type MetricStatus } from "../state/metrics.ts";
 import { describeToolCall } from "../pi/activity.ts";
-import { applyStatus, currentZenTask, isMinimized, onMinimizeChange, onRunUpdates, persistedRuns, setMinimized, setWidgetSuppressor, ZenScene, zenSnapshot } from "../pi/ui.ts";
-import { panelLines } from "../pi/zen.ts";
+import { applyStatus, currentZenTask, isMinimized, onMinimizeChange, onRunUpdates, setMinimized, taskSnapshot } from "../pi/ui.ts";
 import { shortTitle } from "../text.ts";
 import { isSubagentProcess } from "../pi/quiet.ts";
 import { modelRef, resolveLobbyProfile, resolvePanelProfile } from "../pi/model-support.ts";
@@ -43,7 +42,6 @@ import { LobbyView, type LiveSession, type LobbyHost, type SwitchTarget, type Ta
 import { lobbyTheme } from "./theme.ts";
 import { deliverComments, onOwnerEvent, setAuto } from "../pi/owner.ts";
 import { openEntrySettings, openSettings } from "../pi/settings-ui.ts";
-import { budgetClock } from "../state/budget.ts";
 
 export const ANCHOR_KEY = "bot-lobby-anchor";
 export { deliverComments };
@@ -59,7 +57,6 @@ interface Runtime {
   visible: boolean;
   /** Stepped aside while pi shows a dialog. */
   asideForPrompt: boolean;
-  scene: ZenScene;
   quickfix: QuickFixQueue;
   planner?: PlanningSession;
   issues: IssuesState;
@@ -426,13 +423,6 @@ function deleteTask(state: Runtime, taskId: string, where: "list" | "archive"):
   return `deleted ${taskId} for good`;
 }
 
-/** A task's status box without animations, for a session other than this window's. */
-function taskScene(state: Runtime, task: Task, width: number, height: number): string[] {
-  const now = Date.now();
-  const time = budgetClock(state.root, state.configDir, task.id, now);
-  return panelLines(task, persistedRuns(task), now, false, { width, rows: Math.floor(height / 0.75), still: true, theme: state.ctx.ui.theme, ...(time ? { time } : {}) });
-}
-
 function seatProfile(state: Runtime, member: PanelMember) {
   return resolvePanelProfile(loadConfig(), member, {
     lookup: modelLookup(state.ctx),
@@ -518,15 +508,9 @@ function host(state: Runtime, tui: TUI): LobbyHost {
     theme: () => lobbyTheme(state.ctx.ui.theme),
     sessionId: () => state.ctx.sessionManager.getSessionId(),
     zen: () => {
-      const snapshot = zenSnapshot();
+      const snapshot = taskSnapshot();
       return { ...(snapshot.task ? { task: snapshot.task } : {}), runs: snapshot.runs };
     },
-    // The scene's height budget is 3/4 of the rows it is given.
-    scene: (width, height, animated) => state.scene.lines(width, Math.floor(height / 0.75), state.ctx.ui.theme, Date.now(), !animated),
-    advanceScene: (now) => {
-      state.scene.advance(now);
-      return state.scene.delay(now);
-    },
     feed: lobbyFeed,
     masterBusy: () => !state.ctx.isIdle(),
     tasks: () => peekTasks(state.root, state.configDir),
@@ -577,7 +561,6 @@ function host(state: Runtime, tui: TUI): LobbyHost {
     sessionChat: (sessionId) => chats.chat(sessionId),
     hasOlderChat: (sessionId) => chats.hasOlder(sessionId),
     chatHistory: (sessionId) => chatHistory(state, sessionId),
-    taskScene: (task, width, height) => taskScene(state, task, width, height),
     requestRender: () => tui.requestRender(),
   };
 }
@@ -716,7 +699,6 @@ function shutdown(): void {
   state.planner?.cancel();
   state.view?.dispose();
   state.handle?.hide();
-  setWidgetSuppressor(() => false);
   onRunUpdates(undefined);
   onMinimizeChange(undefined);
 }
@@ -755,7 +737,6 @@ export function initLobby(pi: ExtensionAPI, ctx: ExtensionContext, configDir: st
     asking: false,
     mouse: false,
     inSettings: false,
-    scene: new ZenScene(),
     quickfix: undefined as unknown as QuickFixQueue,
     issues: new IssuesState(execCommand, ctx.cwd, rerender),
   };
@@ -781,7 +762,6 @@ export function initLobby(pi: ExtensionAPI, ctx: ExtensionContext, configDir: st
   // Only the newest messages are kept; the feed learns whether earlier ones exist, and loads them when scrolled to.
   lobbyFeed.seedChat(chatFromEntries(ctx.sessionManager.getBranch(), Number.POSITIVE_INFINITY));
   state.unsubscribeFeed = lobbyFeed.onChange(rerender);
-  setWidgetSuppressor(() => runtime?.visible === true);
   onRunUpdates((runs) => lobbyFeed.runs(runs));
   onMinimizeChange((value) => {
     if (value) hideLobby();

package/src/lobby/tabs/home.ts

@@ -1,9 +1,8 @@
 /**
- * The Lobby tab: the zen scene of this session's task on top (the oracle
- * and agent animations, or just their status when animations are off), then the
+ * The Lobby tab: the status of this session's task on top, then the
  * conversation with the oracle (text only, no tool rows, no thinking), the
  * activity log of plain-words steps from every agent, and the one place where
- * thoughts show up. Pure: the scene arrives as a callback, the clock as `now`.
+ * thoughts show up. Pure: the clock arrives as `now`.
  */
 import { textWidth } from "../../width.ts";
 import type { Task } from "../../schemas/task.ts";
@@ -18,8 +17,6 @@ export type HomePane = (typeof HOME_PANES)[number];
 
 export interface HomeInput {
   task?: Task;
-  /** Draws the zen scene into at most `height` lines, animated or still; absent when no task is active. */
-  scene?: (width: number, height: number, animated: boolean) => string[];
   chat: readonly ChatEntry[];
   /** The oracle's reply while it streams. */
   liveReply?: string;
@@ -48,8 +45,6 @@ export interface HomeInput {
   keys?: Record<LobbyPanel, string>;
   /** Another session is shown: its name titles the conversation. */
   title?: string;
-  /** The scene is another session's still status (no animations to toggle). */
-  stillScene?: boolean;
   /** What the empty conversation says instead of the default (a session starting, say). */
   emptyNote?: string;
   /** What the empty activity log says instead of "No activity yet.". */
@@ -60,11 +55,6 @@ export interface HomeInput {
 
 /** Wide terminals put the conversation and the activity log side by side. */
 export const HOME_COLUMNS_MIN = 100;
-/** Most lines the scene may take, and its share of the body; the still status needs far fewer. */
-const SCENE_SHARE = 0.45;
-const MAX_SCENE = 36;
-const MAX_STILL = 10;
-
 const SOURCE_COLORS: Record<string, LobbyColor> = {
   MASTER: "accent",
   DEV: "success",
@@ -490,31 +480,6 @@ function thinkingContent(input: HomeInput, thoughts: readonly ThoughtEntry[], wi
   return whole([paint(theme, "dim", input.query ? `No thought matches "${input.query}".` : "Thoughts from the oracle and every agent appear here, and only here.")]);
 }
 
-/**
- * The scene: with animations off (the `animations` panel, off by default)
- * only the task's status box, what the agents are doing and the checklist;
- * with them on, the animated oracle and agents too. Its first line names the
- * key that toggles the animations.
- */
-function sceneLines(input: HomeInput, width: number, height: number, theme?: LobbyTheme): string[] {
-  if (!input.task || !input.scene) return [];
-  const animated = input.panels.animations && !input.stillScene;
-  const budget = Math.min(animated ? MAX_SCENE : MAX_STILL, Math.floor(height * SCENE_SHARE));
-  if (budget < (animated ? 6 : 4)) return [];
-  const lines = input.scene(width, budget, animated).slice(0, budget);
-  const note = input.keys && !input.stillScene ? `${input.keys.animations} ${animated ? "hides" : "shows"} animations` : undefined;
-  return keyNote(lines, width, note, theme);
-}
-
-/** `note` at the right end of the first line, dimmed, when it fits beside what is there. */
-function keyNote(lines: readonly string[], width: number, note: string | undefined, theme?: LobbyTheme): string[] {
-  const first = lines[0];
-  if (!note || first === undefined) return [...lines];
-  const gap = width - textWidth(first) - textWidth(note) - 1;
-  if (gap < 2) return [...lines];
-  return [`${first}${" ".repeat(gap)}${paint(theme, "dim", note)}`, ...lines.slice(1)];
-}
-
 function hiddenHint(input: HomeInput, width: number, height: number, theme?: LobbyTheme): string[] {
   const keys = input.keys;
   const text = keys
@@ -536,12 +501,11 @@ export function renderHome(input: HomeInput, width: number, height: number, them
   if (height <= 0) return [];
   const { panels } = input;
   const feed = filterFeed(input);
-  const scene = sceneLines(input, width, height, theme);
-  const rest = height - scene.length;
+  const rest = height;
   const showMain = panels.conversation || panels.activity;
   const thinkHeight = !panels.thinking ? 0 : !showMain ? rest : rest >= 18 ? Math.max(5, Math.floor(rest * 0.25)) : rest >= 10 ? 4 : 0;
   const main = rest - thinkHeight;
-  if (!showMain && !panels.thinking) return fill([...scene, ...hiddenHint(input, width, rest, theme)], height, width);
+  if (!showMain && !panels.thinking) return fill(hiddenHint(input, width, rest, theme), height, width);
   const matches = (count: number) => `${count} match${count === 1 ? "" : "es"}`;
   /**
    * One scrollable pane: only the lines it shows are drawn — its newest, or
@@ -563,7 +527,7 @@ export function renderHome(input: HomeInput, width: number, height: number, them
   const thought = currentThought(feed.thoughts);
   const thinkingNote = thought ? `${thought.source} · ${thought.live ? "thinking" : since(input.now - thought.at)}` : input.keys?.thinking;
   const thinkingBox = pane("thinking", "Thinking", thinkingNote, (inner, need, anchor) => thinkingContent(input, feed.thoughts, inner, need, anchor, theme));
-  const top = scene.length;
+  const top = 0;
   let body: string[] = [];
   if (main > 0 && panels.conversation && panels.activity) {
     if (width >= HOME_COLUMNS_MIN) {
@@ -576,5 +540,5 @@ export function renderHome(input: HomeInput, width: number, height: number, them
   } else if (main > 0 && panels.conversation) body = chatBox(top, 0, width, main);
   else if (main > 0 && panels.activity) body = activityBox(top, 0, width, main);
   const think = thinkHeight >= 3 ? thinkingBox(top + main, 0, width, thinkHeight) : [];
-  return fill([...scene, ...fill(body, main), ...think], height, width);
+  return fill([...fill(body, main), ...think], height, width);
 }

package/src/lobby/tabs/tasks.ts

@@ -7,7 +7,7 @@
 import { TERMINAL_STATES, taskRequest, type Task } from "../../schemas/task.ts";
 import type { PlannedTask } from "../../state/backlog.ts";
 import type { PlanComment } from "../../state/comments.ts";
-import { planChecklist } from "../../pi/zen.ts";
+import { planChecklist } from "../../pi/plan-checklist.ts";
 import { persistedRuns } from "../../pi/ui.ts";
 import { describeRun, runFromLog } from "../../pi/run-summary.ts";
 import { pendingApprovals } from "../../workflow/approvals.ts";

package/src/lobby/view.ts

@@ -54,8 +54,8 @@ const PROMPT_FIRST: ReadonlySet<TabId> = new Set(["lobby", "plan", "quickfix"]);
 export type LobbyMode = "type" | "browse";
 
 /** What each pane toggle is called in notices and help. */
-const PANEL_NAMES: Record<LobbyPanel, string> = { animations: "oracle and agent animations", conversation: "conversation", activity: "activity log", thinking: "thinking" };
-const PANEL_ACTIONS: Record<LobbyPanel, LobbyAction> = { animations: "toggleScene", conversation: "toggleConversation", activity: "toggleActivity", thinking: "toggleThinking" };
+const PANEL_NAMES: Record<LobbyPanel, string> = { conversation: "conversation", activity: "activity log", thinking: "thinking" };
+const PANEL_ACTIONS: Record<LobbyPanel, LobbyAction> = { conversation: "toggleConversation", activity: "toggleActivity", thinking: "toggleThinking" };
 
 /**
  * Which session the Lobby tab shows and talks to: this window, one it started
@@ -125,12 +125,8 @@ export interface LobbyHost {
   rows(): number;
   theme(): LobbyTheme;
   sessionId(): string | undefined;
-  /** This session's active task and its runs, as the zen widget sees them. */
+  /** This session's active task and its runs, as the lobby reads them. */
   zen(): { task?: Task; runs: readonly AgentRun[] };
-  /** Draw the zen scene into at most `height` lines: animated, or only the task's status when `animated` is false. */
-  scene(width: number, height: number, animated: boolean): string[];
-  /** Advance the scene's clock; returns the delay it wants until the next step. */
-  advanceScene(now: number): number;
   feed: LobbyFeed;
   masterBusy(): boolean;
   tasks(): Task[];
@@ -199,14 +195,12 @@ export interface LobbyHost {
   hasOlderChat(sessionId: string): boolean;
   /** A session's whole conversation, oldest first: this window's (no id) or another's; loaded only while scrolled back to it. */
   chatHistory(sessionId?: string): readonly ChatEntry[];
-  /** A task's status without animations, for a session other than this window's. */
-  taskScene(task: Task, width: number, height: number): string[];
   profileLabel(kind: LobbyAgentKind): string;
   requestRender(): void;
   now?(): number;
 }
 
-/** Live work speeds the clock up so spinners and the scene move. */
+/** Live work speeds the clock up so spinners move. */
 export const LIVE_MS = 250;
 export const IDLE_MS = 1000;
 /** How often task and metrics data is reread from disk while the lobby is open. */
@@ -424,16 +418,13 @@ export class LobbyView implements Component, Focusable {
       || Boolean(zen.task && !zen.task.paused && !TERMINAL_STATES.includes(zen.task.state));
   }
 
-  /** One clock step: advance the scene, reread data when due, repaint. */
+  /** One clock step: reread data when due, repaint. */
   private step(): void {
     if (!this.running) return;
-    const now = this.now();
     this.tick += 1;
-    let delay = this.isLive() ? LIVE_MS : IDLE_MS;
-    if (this.tab === "lobby" && this.panels.animations && this.host.zen().task) delay = Math.min(delay, this.host.advanceScene(now));
     this.refreshData(false);
     this.host.requestRender();
-    this.schedule(delay);
+    this.schedule(this.isLive() ? LIVE_MS : IDLE_MS);
   }
 
   /** Reread tasks, plans, comments and metrics from disk (throttled unless forced). */
@@ -675,8 +666,6 @@ export class LobbyView implements Component, Focusable {
         return this.cycleTab(1);
       case "prevTab":
         return this.cycleTab(-1);
-      case "toggleScene":
-        return this.togglePanel("animations");
       case "toggleConversation":
         return this.togglePanel("conversation");
       case "toggleActivity":
@@ -2295,7 +2284,7 @@ export class LobbyView implements Component, Focusable {
     if (entry.view.kind !== "here") return this.otherSessionBody(entry, width, height, theme, now);
     const talk = this.conversationFor(entry);
     return renderHome({
-      ...(zen.task ? { task: zen.task, scene: (w: number, h: number, animated: boolean) => this.host.scene(w, h, animated) } : {}),
+      ...(zen.task ? { task: zen.task } : {}),
       chat: talk.chat,
       ...(talk.older ? { olderNote: OLDER_NOTE } : {}),
       ...(feed.reply ? { liveReply: feed.reply } : {}),
@@ -2313,7 +2302,6 @@ export class LobbyView implements Component, Focusable {
       panels: this.panels,
       ...(query ? { query } : {}),
       keys: {
-        animations: keyLabel(this.keys.toggleScene),
         conversation: keyLabel(this.keys.toggleConversation),
         activity: keyLabel(this.keys.toggleActivity),
         thinking: keyLabel(this.keys.toggleThinking),
@@ -2323,8 +2311,7 @@ export class LobbyView implements Component, Focusable {
 
   /**
    * Another session on the Lobby tab: a background session's live feed, or an
-   * other terminal's conversation read from its session file; the task's
-   * status sits on top without animations.
+   * other terminal's conversation read from its session file.
    */
   private otherSessionBody(entry: SessionEntry, width: number, height: number, theme: LobbyTheme, now: number): string[] {
     const session = this.viewedSession();
@@ -2332,7 +2319,7 @@ export class LobbyView implements Component, Focusable {
     const task = entry.task;
     const query = this.query();
     const common = {
-      ...(task ? { task, scene: (w: number, h: number) => this.host.taskScene(task, w, h), stillScene: true } : {}),
+      ...(task ? { task } : {}),
       others: 0,
       pending: 0,
       offsets: this.homeOffsets,
@@ -2345,7 +2332,6 @@ export class LobbyView implements Component, Focusable {
       ...(query ? { query } : {}),
       title: entry.name,
       keys: {
-        animations: keyLabel(this.keys.toggleScene),
         conversation: keyLabel(this.keys.toggleConversation),
         activity: keyLabel(this.keys.toggleActivity),
         thinking: keyLabel(this.keys.toggleThinking),