* fix(mcp): delegate tool carries the collision surface the B1a gate demands

TASK_AT_DELEGATE (5fc85419) requires intends_to_touch on code delegations,
but the MCP delegate tool never gained the parameter — PMs were rejected
with incomplete_input and could never comply (live fleet-wide delegation
wall, 2026-07-02). Adds intends_to_touch / adds_migration / touches_shared /
depends_on to the tool and forwards them; parity test locks the invariant.

* fix(git): assembly-integrity guard accepts squash-merged children

git cherry patch-matches each child commit individually, so a squash merge
(N patches -> one commit, new patch-id) read as 'work missing' and the #11
guard refused every legitimate submit_up (live 2026-07-02: S6 cell, three
squash-merged children at the branch tip). A parent commit carrying the
child's [taskid8] prefix now proves the child landed; children with no
marker stay flagged — the original incident the guard exists for.

* fix(git): diff head prefers origin when the local ref is behind it

Assembled branches advance on ORIGIN as child PRs squash-merge on GitHub,
but _resolve_head_ref preferred the inspecting clone's parked local ref —
the PR-gate reviewer's evidence diff was built from a pre-merge snapshot
and re-flagged work that had already landed (two false pr_fail verdicts
on the S6 cell PR, live 2026-07-02). When both refs exist and the local
ref is strictly behind origin, resolve to origin/<branch>; local-ahead
(unpushed) and diverged refs keep priority, single-ref cases unchanged.

* test(mcp): plan-gate fields must be tool parameters (parity class lock)

Extends the delegate parity test to every choreographer plan-depth gate:
a gate that can reject with missing=[field] must name only fields the
corresponding MCP tool can send, else the agent can never comply.

* perf(api): wire TaskSummaryResponse into a bounded /tasks/summary route

The panel fetched /api/tasks unbounded and full-fat — 2MB per refresh
measured live (2026-07-02), ~21KB/task, and the trimmed
TaskSummaryResponse was dead code. /tasks/summary returns exactly the
fields list views render (~50x lighter); the status-only branch of
/tasks now honors its limit, and the eleven unbounded task list routes
are capped.

* perf(panel): kill the per-page request flood and fat payloads

Every page load funneled ~85 default-prefetch RSC requests + 665KB of
images + the 2MB task list through the browser's six HTTP/1.1
connections — real data calls queued ~2s before being sent (measured
via Playwright resource timing, 2026-07-02).

- prefetch={false} on all 59 Links (sidebar, task rows, kanban cards,
  list rows) — ~85 requests/refresh down to a handful
- icon/apple-icon/logo resized to render size: 665KB -> 54KB; unused
  219KB PNG removed
- task list fetches the trimmed /tasks/summary (2MB -> ~100KB),
  normalized into the Task shape so list consumers keep their types
- ReactQueryDevtools rendered only in development

* fix(api): Annotated limit defaults so direct-call tests get real ints

Query(...) positional defaults arrive as Query objects when a route
function is invoked outside the HTTP layer (integration tests call
handlers directly) and broke the new [:limit] slices.

* fix(api,panel): summary carries completed_at + board_review_complete

The metrics page computes velocity client-side from completed_at and the
CEO approval queue gates on board_review_complete — both were nulled by
the summary normalizer, so Completed Today/Week read 0 against 63 real
completions and approved-board tasks could vanish from the queue. The
queue also renders quick_context, so it fetches the full list (small,
status-scoped) via tasksApi.listFull instead of the summary.

* fix(runtime): spawn manifest workspace_path follows the task's project

_build_manifest_for_agent hardcoded the roboco project workspace for
every agent; a guard-core task's manifest claimed /data/workspaces/roboco
while the container cwd sat in the task worktree. The manifest now takes
the same _resolve_workspace_cwd the container -w uses — one resolver,
both surfaces agree by construction.

* fix(runtime): respawn breaker catches status ping-pong loops

Any status CHANGE fully reset the strike counter, so a blocked <->
in_progress oscillation — which changes status on every spawn while
advancing nothing — never tripped the gate (live 2026-07-02: 8 spawns
over two hours). A status never seen on the (agent, task) still fully
resets; a REVISITED status gets a bounded reset budget mirroring
tracing_resets, after which strikes accrue and the gate fires.

* fix(runtime): unassigned-QA dispatch spawns without pre-claiming

The transitioning pre-claim moved awaiting_qa -> claimed before the QA
agent existed; the spawned agent's claim_review/pass_review both demand
awaiting_qa, so it bounced twice and unclaimed (live 2026-07-02,
ba7b751c). Matches _spawn_assigned_qa and the external-PR reviewer
dispatch: no pre-claim, the agent claims itself via claim_review.

* fix(tests): narrow await_args before kwargs access (mypy union-attr)

* Minor upgrades

* fix(policy): team-match gate gains org-wide exemption; resume/unblock/activate now team-matched

needs_team_match sat in its permissive fallback since shipping (no
caller supplied Context.agent_team) and three PM verbs opted out
entirely — a misrouted frontend cell PM blocked, escalated, and held a
backend task through exactly that gap (live 2026-07-02). Org-wide roles
(main_pm, board, CEO, PR reviewer) are exempt so escalation handling
and root-PR gating keep working; cell-scoped roles are now enforced
wherever the caller supplies the team.

---------

Co-authored-by: Renn F <rennf93@users.noreply.github.com>
This commit is contained in:
Renzo F
2026-07-02 15:36:49 +02:00
committed by GitHub
co-authored by Renn F
parent cfde4369b1
commit 0f1ed3cc6a
58 changed files with 1246 additions and 105 deletions
@@ -66,7 +66,7 @@ export function ActiveBlockersPanel({
) : (
<div className="space-y-3">
{blockedTasks.map((task) => (
<Link key={task.id} href={"/tasks/" + task.id}>
<Link key={task.id} href={"/tasks/" + task.id} prefetch={false}>
<div className="flex items-start gap-3 p-3 rounded-lg border border-red-200 bg-red-50 hover:bg-red-100 dark:border-red-900 dark:bg-red-950 dark:hover:bg-red-900 transition-colors">
<span className="text-lg">\uD83D\uDD34</span>
<div className="flex-1 min-w-0">
@@ -91,7 +91,7 @@ export function ActiveBlockersPanel({
</div>
)}
<div className="mt-4 pt-3 border-t">
<Link href="/tasks?status=blocked">
<Link href="/tasks?status=blocked" prefetch={false}>
<Button variant="ghost" size="sm" className="w-full">
View All Blocked
<ArrowRight className="h-4 w-4 ml-2" />
@@ -98,7 +98,7 @@ export function AuditorAlertsPanel({
</div>
)}
<div className="mt-4 pt-3 border-t">
<Link href="/auditor">
<Link href="/auditor" prefetch={false}>
<Button variant="ghost" size="sm" className="w-full">
View All Flags
<ArrowRight className="h-4 w-4 ml-2" />
@@ -65,7 +65,9 @@ export function CeoApprovalQueue({ className }: CeoApprovalQueueProps) {
const { data: startTasks } = useQuery({
queryKey: ["tasks", "awaiting-approve-start"],
queryFn: async () => {
const pending = await tasksApi.list({ status: TaskStatus.PENDING });
// Full-fat fetch: this card renders quick_context, which the trimmed
// summary list deliberately omits. The PENDING set is small.
const pending = await tasksApi.listFull({ status: TaskStatus.PENDING });
return pending.filter(
(t) => t.board_review_complete === true && t.team !== Team.MAIN_PM,
);
@@ -219,6 +221,7 @@ export function CeoApprovalQueue({ className }: CeoApprovalQueueProps) {
<Badge variant="outline">{task.team}</Badge>
</div>
<Link
prefetch={false}
href={`/tasks/${task.id}`}
className="font-medium hover:underline line-clamp-1"
>
@@ -231,7 +234,7 @@ export function CeoApprovalQueue({ className }: CeoApprovalQueueProps) {
)}
</div>
<div className="flex items-center gap-2 ml-4 flex-shrink-0">
<Link href={`/tasks/${task.id}`}>
<Link href={`/tasks/${task.id}`} prefetch={false}>
<Button variant="ghost" size="sm">
<FileText className="h-4 w-4" />
</Button>
@@ -348,6 +351,7 @@ export function CeoApprovalQueue({ className }: CeoApprovalQueueProps) {
</p>
)}
<Link
prefetch={false}
href={`/tasks/${selectedTask.id}`}
target="_blank"
className="text-sm text-primary flex items-center gap-1 mt-2 hover:underline"
@@ -76,7 +76,7 @@ export function CommandCenter() {
<RefreshCw className="h-4 w-4 mr-2" />
Refresh
</Button>
<Link href="/settings">
<Link href="/settings" prefetch={false}>
<Button variant="ghost" size="icon">
<Settings className="h-5 w-5" />
</Button>
@@ -166,6 +166,7 @@ export function PrReviewQueue({ className }: PrReviewQueueProps) {
<div className="flex-1 min-w-0">
<div className="flex items-center gap-2">
<Link
prefetch={false}
href={`/tasks/${task.id}`}
className="font-medium hover:underline line-clamp-1"
>
@@ -202,7 +203,11 @@ export function PrReviewQueue({ className }: PrReviewQueueProps) {
)}
</div>
<div className="flex items-center gap-2 ml-4 flex-shrink-0">
<Link href={`/tasks/${task.id}`} title="Review details">
<Link
href={`/tasks/${task.id}`}
title="Review details"
prefetch={false}
>
<Button variant="ghost" size="sm">
<FileText className="h-4 w-4" />
</Button>
@@ -17,42 +17,42 @@ export function QuickActionsBar() {
<div className="flex flex-wrap gap-3">
<CreateTaskDialog />
<Link href="/agents">
<Link href="/agents" prefetch={false}>
<Button variant="outline">
<Users className="h-4 w-4 mr-2" />
Spawn Agent
</Button>
</Link>
<Link href="/prompter">
<Link href="/prompter" prefetch={false}>
<Button variant="outline">
<Sparkles className="h-4 w-4 mr-2" />
Task Intake
</Button>
</Link>
<Link href="/business?tab=secretary">
<Link href="/business?tab=secretary" prefetch={false}>
<Button variant="outline">
<Bot className="h-4 w-4 mr-2" />
Secretary
</Button>
</Link>
<Link href="/communications">
<Link href="/communications" prefetch={false}>
<Button variant="outline">
<Megaphone className="h-4 w-4 mr-2" />
Broadcast Message
</Button>
</Link>
<Link href="/journals">
<Link href="/journals" prefetch={false}>
<Button variant="outline">
<BookOpen className="h-4 w-4 mr-2" />
View Journals
</Button>
</Link>
<Link href="/auditor">
<Link href="/auditor" prefetch={false}>
<Button variant="outline">
<Shield className="h-4 w-4 mr-2" />
Auditor Report
@@ -47,7 +47,7 @@ export function RecentActivityFeed({
</ScrollArea>
)}
<div className="mt-4 pt-3 border-t">
<Link href="/notifications">
<Link href="/notifications" prefetch={false}>
<Button variant="ghost" size="sm" className="w-full">
View Full Activity
<ArrowRight className="h-4 w-4 ml-2" />
@@ -55,6 +55,7 @@ export function ScorecardOverviewPanel() {
Performance
</CardTitle>
<Link
prefetch={false}
href="/metrics?tab=scorecards"
className="text-muted-foreground hover:text-foreground flex items-center gap-1 text-xs"
>
@@ -25,7 +25,7 @@ function OnDemandAgentCard({
description: string;
}) {
return (
<Link href={href} className="block">
<Link href={href} className="block" prefetch={false}>
<div className="rounded-lg border bg-card p-4 hover:bg-accent/50 transition-colors h-full flex flex-col gap-2">
<div className="flex items-center gap-2">
<Icon className="h-4 w-4 text-muted-foreground" />