fix: background-delivery ground rules — the dock is the source of truth, delivered content shows the moment it persists

The owner's three-part test of the context-injection flow surfaced
timing/visibility bugs, fixed as standing ground rules for ALL background
processes (owner rules, 2026-09-15):

1. THE JOB STARTS AT SEND. triggerGraphContext moves from onFinish to
   right after the write-ahead persist in handleChatRequest: its only
   input is the first typed message (the topic), just made durable — so
   embedding + cosine scan run CONCURRENT with the prober's turn and
   the dock blob appears the moment the session starts, not after turn
   one finishes. Extraction stays at onFinish (it needs answers
   accumulated DURING the turn).

2. DELIVERED CONTENT SHOWS MID-TURN. Steers inserted server-side
   (claimed at turn start, persisted write-ahead) used to wait for the
   next turn's completion to appear — the full record sync mid-stream
   is forbidden (it breaks the SDK's in-place continuation merge), so
   adoption was deferred to idle. New append-only seam: core
   mergeAdopted() inserts the record's new message ids in canonical
   order (in-flight streaming tail kept last) and never rewrites a
   local message; any other shape bails to the full-sync-at-idle net.
   Wired at three points, no new standing polls:
   - turn-start window: three bounded record fetches (400ms/1s/2s)
     after a send catch the claimed steer while the turn streams;
     self-terminating, survives the submitted->streaming flip.
   - jobs-poll settle: mid-turn settles adopt append-only NOW, the
     owed full sync still runs at idle.
   - wake-adoption poll: each tick adopts persisted wake content, so
     steers show at the wake turn's START, not its finish.
   The dock stays honest with zero gap: jobs hold "running" while
   queued behind a pending question ("delivering context"), then flip
   done at claim/delivery — visible from start to delivery, and the
   turn-start nudge (useActivity().refresh) clears it within ~150ms.

3. THE MARKER IS CLICKABLE (observability). The knowledge-context
   SystemLine becomes GraphContextMarker: quiet line, popover with the
   delivered propositions IN DELIVERY ORDER (most similar first — the
   order the budget filled), each with its folded understanding level;
   Esc / outside pointerdown close. The part data was already the audit
   trail — now it's readable at the seam where it landed.

Tests: mergeAdopted unit pins (6), marker render pins (3) — 468/468,
tsc, eslint, build all green; live-smoked end-to-end: blob at send,
marker at t+500ms mid-turn, popover order + levels, instant dock clear.

components/activity-dock.tsx

@@ -110,6 +110,15 @@ export function ActivityProvider({ children }: { children: React.ReactNode }) {
 	return <ActivityContext.Provider value={{ feed, refresh }}>{children}</ActivityContext.Provider>;
 }
 
+/** The activity feed seam for the rest of the shell: the dock's data +
+ *  its refresh nudge. The chat page nudges on turn start (owner ground
+ *  rules, 2026-09-15): a background process that starts at send — the
+ *  knowledge-context injection — must be visible in the dock the moment
+ *  it begins, without the dock polling faster while idle. */
+export function useActivity(): { feed: ActivityFeed; refresh: () => void } {
+	return useContext(ActivityContext);
+}
+
 // ─── Pure presentation helpers (exported for tests) ──────────────────────────
 
 /** One dock blob: the unified view of a job or an extraction run. */

components/chat.tsx

@@ -21,8 +21,9 @@ import { SubagentSteerCard } from "@/components/artifacts/steer-card";
 import { Composer } from "@/components/composer";
 import { JobsContext } from "@/components/jobs-context";
 import { StatsBar } from "@/components/stats-bar";
-import { graphContextOfMessage, type ChatSettings } from "@/src/core";
-import { formatTokens } from "@/components/usage-format";
+import { GraphContextMarker } from "@/components/graph-context-marker";
+import { useActivity } from "@/components/activity-dock";
+import { mergeAdopted, type ChatSettings } from "@/src/core";
 import { PlanBlock, PlanPopup, latestTree } from "@/components/plan-block";
 import { PlanMarginalia } from "@/components/plan-window";
 import { WaypointsIcon } from "lucide-react";
@@ -82,16 +83,6 @@ const useIsoLayoutEffect = typeof window === "undefined" ? useEffect : useLayout
 
 /** A wake-pipeline steer message: user-role delivery whose metadata marks it
  * as a sub-agent result — rendered as an artifact card, never a bubble. */
-/** The knowledge-context card's one-liner: the numbers the observability
- *  doctrine wants visible at the seam — tokens and proposition count
- *  (parse-don't-cast; a malformed part still renders a quiet generic line). */
-function graphContextLine(message: { parts: ReadonlyArray<{ type: string; data?: unknown }> }): string {
-	const data = graphContextOfMessage(message);
-	return data
-		? `Knowledge context — ~${formatTokens(data.tokens)} · ${data.propositions.length} propositions`
-		: "Knowledge context";
-}
-
 /** The quiet system line (custom-message scheme rendering): centered, muted,
  *  small — the transcript's voice for events that are not speech (wake
  *  scaffolding, the learner's plan verdict). */
@@ -235,6 +226,73 @@ export function Chat({
 		}
 	}, [chatId, setMessages, sendMessage, status]);
 
+	// ── Append-only record adoption (owner ground rules, 2026-09-15) ──
+	// Content delivered into the record server-side — the knowledge-context
+	// block, sub-agent artifacts, abort notes — must become visible the
+	// moment it persists, mid-turn included: it sits between messages, and
+	// nothing about a running turn should hide it. The full snapshot sync
+	// mid-stream is forbidden (it breaks the SDK's in-place continuation
+	// merge — the stale-snapshot lesson), so adoption here is APPEND-ONLY
+	// (core mergeAdopted): insert the record's new ids in their canonical
+	// order, never rewrite a local one, keep the in-flight tail last. The
+	// full syncFromServer stays the net at idle (reorder, plan blocks, turns).
+	const messagesRef = useRef(messages);
+	messagesRef.current = messages;
+	const adoptAppendOnly = useCallback(async () => {
+		try {
+			const res = await fetch(`/api/chats/${chatId}`);
+			if (!res.ok) return;
+			const record = (await res.json()) as { messages?: TeacherUIMessage[] };
+			if (!Array.isArray(record.messages)) return;
+			const merged = mergeAdopted(messagesRef.current, record.messages);
+			if (merged) setMessages(merged);
+		} catch {
+			/* transient — the idle full sync is the net */
+		}
+	}, [chatId, setMessages]);
+
+	// Turn-start window: the server inserts claimed steers right after our
+	// outgoing message, BEFORE the stream produces anything — so a bounded,
+	// self-terminating window of three record fetches (400ms/1s/2s) catches
+	// the insert and shows the marker during the turn, then stops. No
+	// standing poll — the window exists only for these seconds. The same
+	// instant nudges the activity feed: the knowledge-context job starts at
+	// send (server-side), and the dock must say so immediately.
+	const { refresh: refreshActivity } = useActivity();
+	const turnStartStatusRef = useRef(status);
+	// The window must survive the submitted→streaming flip (the stream starts
+	// in well under 400ms), so the timers are guarded by this ref — dropped at
+	// unmount, left alone otherwise: the window self-terminates after 2s.
+	const adoptionWindowOpenRef = useRef(false);
+	const turnStartTimerRefs = useRef<ReturnType<typeof setTimeout>[]>([]);
+	useEffect(() => {
+		const was = turnStartStatusRef.current;
+		turnStartStatusRef.current = status;
+		if (was === "submitted" || status !== "submitted") return;
+		// A turn just started (status flipped ready → submitted): open the
+		// bounded adoption window and nudge the dock's feed.
+		refreshActivity();
+		adoptionWindowOpenRef.current = true;
+		const timers = [400, 1000, 2000].map((ms) =>
+			setTimeout(() => {
+				if (adoptionWindowOpenRef.current) void adoptAppendOnly();
+			}, ms),
+		);
+		// Deliberately no cleanup here: this effect re-runs on every status
+		// flip, which would cancel the window at submitted→streaming.
+		timers.forEach((t) => {
+			turnStartTimerRefs.current.push(t);
+		});
+	}, [status, adoptAppendOnly, refreshActivity]);
+	useEffect(() => {
+		const timers = turnStartTimerRefs;
+		return () => {
+			adoptionWindowOpenRef.current = false;
+			timers.current.forEach(clearTimeout);
+			timers.current = [];
+		};
+	}, []);
+
 	// The live plan popup (wave 4): opened by any transcript plan block, the
 	// top-bar plan chip, and the dock band's marginalia.
 	const [planOpen, setPlanOpen] = useState(false);
@@ -422,14 +480,18 @@ export function Chat({
 					const prev = jobStatusRef.current.get(j.id);
 					if (prev === "running" && j.status !== "running") {
 						// The record is only guaranteed complete when no turn is in
-					// flight — locally or server-side. A coalesced settle fires
-					// mid-turn by design; adopt the record on the first idle tick.
+						// flight — locally or server-side (a coalesced settle fires
+						// mid-turn by design), so the FULL sync waits for idle.
+						// Ground rule (2026-09-15): delivered content shows
+						// immediately anyway — adopt append-only NOW; the idle
+						// sync still settles the record properly.
 						if (localStreamRef.current || data.turnInFlight === true) {
 							pendingSyncRef.current = true;
+							void adoptAppendOnly();
 						} else {
 							void syncFromServer();
+						}
 					}
-				}
 					jobStatusRef.current.set(j.id, j.status);
 				}
 				if (
@@ -455,7 +517,7 @@ export function Chat({
 			cancelled = true;
 			clearInterval(timer);
 		};
-	}, [pollMs, jobPartCount, chatId, syncFromServer]);
+	}, [pollMs, jobPartCount, chatId, syncFromServer, adoptAppendOnly]);
 
 	// Re-attach after mid-turn navigation (the key fix): poll the record until
 	// the orphaned turn finishes (turnInFlight flips false server-side in
@@ -470,10 +532,24 @@ export function Chat({
 			if (cancelled) return;
 			try {
 				const res = await fetch(`/api/chats/${chatId}`);
-				if (res.ok && !((await res.json()) as { turnInFlight?: boolean }).turnInFlight) {
-					setTurnInFlight(false);
-					void syncFromServer();
-					return;
+				if (res.ok) {
+					const record = (await res.json()) as {
+						turnInFlight?: boolean;
+						messages?: TeacherUIMessage[];
+					};
+					// Ground rule (2026-09-15): steer content persisted by the
+					// wake shows NOW, at the wake turn's start — not at its
+					// finish. Append-only is safe here: no local stream runs
+					// under a server-side wake turn.
+					if (Array.isArray(record.messages)) {
+						const merged = mergeAdopted(messagesRef.current, record.messages);
+						if (merged) setMessages(merged);
+					}
+					if (!record.turnInFlight) {
+						setTurnInFlight(false);
+						void syncFromServer();
+						return;
+					}
 				}
 			} catch {
 				/* transient network hiccup — keep polling */
@@ -553,11 +629,11 @@ export function Chat({
 									<SubagentSteerCard key={m.id || `m-${mi}`} message={m} />
 								) : m.role === "user" && m.parts.some((p) => p.type === "data-graph-context") ? (
 								// The prior-knowledge injection's delivery (vision-context-injection.md):
-								// quiet system line, the numbers only — the block itself was for the
-								// model (adapter flattening); the part data stays the audit trail.
-								<SystemLine key={m.id || `m-${mi}`} testId="graph-context">
-									{graphContextLine(m)}
-								</SystemLine>
+								// a quiet, CLICKABLE line (owner observability ask, 2026-09-15) —
+								// the popover shows which propositions were delivered, in delivery
+								// order; the block itself was for the model (adapter flattening),
+								// the part data is the audit trail this reads from.
+								<GraphContextMarker key={m.id || `m-${mi}`} message={m} />
 							) : m.role === "user" && m.parts.some((p) => p.type === "data-probe-handoff") ? (
 								// The probe→teach handoff wake (custom-message scheme): quiet
 								// system line, never a user bubble — the wake is scaffolding,

components/graph-context-marker.tsx

@@ -0,0 +1,104 @@
+"use client";
+
+import { useEffect, useRef, useState, type ReactNode } from "react";
+import { BookOpenIcon } from "lucide-react";
+import { graphContextOfMessage, type GraphContextData } from "@/src/core";
+import { formatTokens } from "@/components/usage-format";
+
+/**
+ * The knowledge-context delivery marker (vision-context-injection.md): the
+ * quiet transcript line for the injected prior-knowledge block — CLICKABLE
+ * (owner observability ask, 2026-09-15): the popover shows exactly which
+ * propositions were delivered, IN DELIVERY ORDER (most similar first —
+ * the order the selection filled the budget), each with its folded current
+ * understanding level. The record part is the audit trail; this makes it
+ * readable at the seam where it landed.
+ *
+ * Same quiet-line discipline as the SystemLine family (centered, muted,
+ * small); same popover discipline as the stats-detail (close on outside
+ * pointerdown + Escape, anchored below the marker).
+ */
+export function GraphContextMarker({
+	message,
+	testId = "graph-context",
+}: {
+	/** The steer message (marker-only user message). */
+	message: { parts: ReadonlyArray<{ type: string; data?: unknown }> };
+	testId?: string;
+}) {
+	const [open, setOpen] = useState(false);
+	const data = graphContextOfMessage(message);
+	const ref = useRef<HTMLDivElement>(null);
+
+	useEffect(() => {
+		if (!open) return;
+		const onPointerDown = (e: PointerEvent) => {
+			if (ref.current && !ref.current.contains(e.target as Node)) setOpen(false);
+		};
+		const onKeyDown = (e: KeyboardEvent) => {
+			if (e.key === "Escape") setOpen(false);
+		};
+		document.addEventListener("pointerdown", onPointerDown);
+		document.addEventListener("keydown", onKeyDown);
+		return () => {
+			document.removeEventListener("pointerdown", onPointerDown);
+			document.removeEventListener("keydown", onKeyDown);
+		};
+	}, [open]);
+
+	const summary = data
+		? `Knowledge context — ~${formatTokens(data.tokens)} · ${data.propositions.length} propositions`
+		: "Knowledge context";
+
+	return (
+		<div ref={ref} data-testid={testId} className="relative flex items-center justify-center py-1">
+			<button
+				type="button"
+				onClick={() => setOpen((o) => !o)}
+				aria-expanded={open}
+				title="What was delivered — the propositions, in delivery order"
+				className="flex items-center justify-center gap-1.5 text-xs text-muted-foreground transition-colors hover:text-foreground"
+			>
+				<BookOpenIcon className="size-3" />
+				{summary}
+			</button>
+			{open && data && <GraphContextList data={data} />}
+		</div>
+	);
+}
+
+/** The popover body — exported for render tests. Delivery order preserved. */
+export function GraphContextList({ data }: { data: GraphContextData }): ReactNode {
+	return (
+		<div
+			data-testid="graph-context-list"
+			className="absolute top-full left-1/2 z-40 mt-1.5 w-[36rem] max-w-[80vw] -translate-x-1/2 rounded-xl border bg-card p-3 text-xs shadow-xl"
+		>
+			<div className="mb-1 flex items-baseline justify-between gap-2">
+				<span className="font-medium uppercase tracking-wide text-muted-foreground">
+					Prior knowledge delivered
+				</span>
+				<span className="tabular-nums text-muted-foreground">
+					~{formatTokens(data.tokens)} tok of {data.budget} budget
+				</span>
+			</div>
+			<p className="mb-2 text-muted-foreground">
+				Most similar first — the order the budget filled. The tags are your current
+				understanding level for each proposition.
+			</p>
+			<ol className="flex max-h-72 flex-col gap-1.5 overflow-y-auto">
+				{data.propositions.map((p, i) => (
+					<li key={p.id} className="flex items-baseline gap-2">
+						<span className="shrink-0 tabular-nums text-muted-foreground">{i + 1}.</span>
+						{p.level && (
+							<span className="shrink-0 rounded bg-foreground/10 px-1 py-0.5 text-xxs text-muted-foreground">
+								{p.level}
+							</span>
+						)}
+						<span className="min-w-0 flex-1">{p.statement}</span>
+					</li>
+				))}
+			</ol>
+		</div>
+	);
+}