Feat: board redraft loop (#139)

* feat(board): expose board review brief + guard approve-and-start

Slice 1 of the board-informed intake re-draft loop (backend foundation):

- JournalService.board_review_brief(task_id): the PO + Head of Marketing
  DECISION_LOG entries for a task, oldest-first, each tagged with author —
  the board's review as structured data.
- GET /api/tasks/{task_id}/board-review (PM-or-above) backing the CEO's
  approval/redraft surface, so the real board analysis is readable instead
  of a placeholder; BoardReviewEntry response schema.
- Guard: approve_and_start now refuses a board task whose review is not
  complete (service invariant + precise BOARD_REVIEW_INCOMPLETE at the route).
  Previously only the UI hid the button; the backend let an early/rogue call
  hand the task to Main PM mid-review.

Tests: brief filtering/ordering + endpoint (200/404) + the two guard paths.

* feat(panel): show real board review at the approve gate + live refresh

Slice 1 frontend of the board-informed intake re-draft loop:

- tasksApi.getBoardReview + useBoardReview hook consume GET
  /tasks/{id}/board-review.
- The Approve & Start dialog now renders the actual Product Owner + Head of
  Marketing notes (markdown) instead of a static placeholder, so the CEO reads
  the board's analysis before approving.
- C2: useTask polls (4s) while a task is still on the board with an
  incomplete review, so the Approve & Start button appears as soon as the
  board finishes — there is no per-task websocket. Polling stops once
  board_review_complete flips.

* feat(intake): board-informed re-draft loop (backend, cold path)

Slice 2 of the re-draft loop:

- update_live_draft: apply a board-informed re-draft to the EXISTING task in
  place (title/description/acceptance_criteria) — never a duplicate — then route
  it: 'main_pm' hands it to the Main PM via approve_and_start; 'board' clears
  board_review_complete for another review round.
- confirm route branches on task_id → update_live_draft vs confirm_live_draft;
  LiveConfirmRequest.task_id added (scope taken from the task, not required).
- POST /live/re-interview/{task_id} (PM-or-above): spawns a fresh intake session
  seeded with the current draft + the board brief (compose_redraft_message),
  scoped to the task's product/project. The cold path + Slice-3 fallback.
- format_board_briefing / compose_redraft_message helpers.

Tests: pure helpers + update_live_draft (main_pm hand-off, re-board reset,
missing-task).

* feat(panel): board-informed re-draft entry + prompter re-draft guidance

Slice 2 panel of the re-draft loop:

- 'Re-draft with board feedback' button on a board-reviewed task detail →
  /prompter?redraft=<taskId>.
- usePrompter.startRedraft(taskId): calls POST /prompter/live/re-interview/{id},
  scopes the chat to the task, and streams the re-draft; redraftTaskId is
  threaded (persisted across reload) so confirm carries task_id and updates the
  existing task in place rather than creating a duplicate.
- prompterLiveApi.reInterview; ConfirmPayload.task_id.
- Prompter role prompt: a 'Re-drafting after board review' section so the agent
  revises the included draft from the board brief instead of starting over.

Panel verified by CI (no local node_modules).

* feat(intake): keep-alive re-draft — park the intake agent during board review

Slice 3 of the re-draft loop (in-context fidelity; cold path is the fallback):

- Registry: LiveIntakeSession.task_id + park(session_id, task_id) (keep alive
  instead of reaping) + find_by_task() for board-completion injection.
- Confirm: the board route (first pass) PARKS the intake agent instead of
  reaping, so it keeps the whole interview in context.
- Orchestrator: on board-review completion, inject the synthesized board brief
  into the parked session (_inject_board_brief_into_parked_intake) so the
  resident prompter re-drafts in-context. No-op when nothing is parked (the
  container died / a new intake replaced it) — the cold /re-interview path
  covers that. No reaper change needed (an idle parked session spends no tokens
  and the budget sweep is the only agent-stopping sweep).
- Panel: confirm(board) keeps the chat alive (parked, redraftTaskId set) with a
  notice; the injected revised draft arrives over the existing stream to approve.

Tests: registry park/find_by_task/closed-ignored. Container delivery + the full
panel parked flow need live (container-runtime) verification.

---------

Co-authored-by: Renn F <rennf93@users.noreply.github.com>

panel/src/components/tasks/approve-and-start-button.tsx

@@ -3,6 +3,8 @@
 import { useState } from "react";
 import { useMutation, useQueryClient } from "@tanstack/react-query";
 import { tasksApi } from "@/lib/api";
+import { useBoardReview } from "@/hooks/use-tasks";
+import { Markdown } from "@/components/ui/markdown";
 import { Button } from "@/components/ui/button";
 import {
   Dialog,
@@ -22,10 +24,22 @@ interface ApproveAndStartButtonProps {
   task: Task;
 }
 
+function roleLabel(role: string): string {
+  if (role === "product_owner") return "Product Owner";
+  if (role === "head_marketing") return "Head of Marketing";
+  return role;
+}
+
 export function ApproveAndStartButton({ task }: ApproveAndStartButtonProps) {
   const queryClient = useQueryClient();
   const [open, setOpen] = useState(false);
   const [notes, setNotes] = useState("");
+  // Fetch the board's actual review only while the dialog is open, so the CEO
+  // reads the PO + Head of Marketing analysis before approving.
+  const { data: boardReview = [], isLoading: boardLoading } = useBoardReview(
+    task.id,
+    open,
+  );
 
   const approveAndStartMutation = useMutation({
     mutationFn: ({ taskId, notes }: { taskId: string; notes: string }) =>
@@ -78,11 +92,39 @@ export function ApproveAndStartButton({ task }: ApproveAndStartButtonProps) {
             </DialogDescription>
           </DialogHeader>
 
+          <div className="space-y-2">
+            <Label>Board review (Product Owner &amp; Head of Marketing)</Label>
+            {boardLoading ? (
+              <p className="text-xs text-muted-foreground">
+                Loading board review…
+              </p>
+            ) : boardReview.length === 0 ? (
+              <p className="text-xs text-muted-foreground">
+                No board review recorded for this task yet.
+              </p>
+            ) : (
+              <div className="max-h-72 space-y-3 overflow-y-auto rounded-md border p-3">
+                {boardReview.map((entry) => (
+                  <div
+                    key={entry.timestamp ?? `${entry.author}-${entry.title}`}
+                    className="space-y-1"
+                  >
+                    <span className="inline-block rounded-full bg-primary/10 px-2 py-0.5 text-xs font-medium text-primary">
+                      {roleLabel(entry.author_role)}
+                    </span>
+                    <div className="text-sm font-medium">{entry.title}</div>
+                    <Markdown compact>{entry.content}</Markdown>
+                  </div>
+                ))}
+              </div>
+            )}
+          </div>
+
           <div className="space-y-2">
             <Label htmlFor="approve-and-start-notes">Approval notes (required)</Label>
             <Textarea
               id="approve-and-start-notes"
-              placeholder="Board review complete; requirements are clear. Build it..."
+              placeholder="Board review read; requirements are clear. Build it..."
               value={notes}
               onChange={(e) => setNotes(e.target.value)}
               rows={3}