feat(compaction): conversation compacting + auto-compact threshold

Consume the compaction handoff ([email protected], [email protected]).
Re-pinned file: deps + re-mirrored .dispatch/*.reference.md.

- New 'Compaction' sidebar view (CompactionView.svelte):
  - 'Compact now' button → POST /conversations/:id/compact (loading indicator
    + result: 'N messages summarized, M kept')
  - Auto-compact threshold number input → GET/PUT
    /conversations/:id/compact-threshold (0 = disabled, default 350000)
  - Re-mounts per conversation via {#key}
- App store: compactNow() + compactThreshold reactive state +
  setCompactThreshold(), seeded on focus change (like reasoning-effort + cwd)
- conversation.compacted WS handler: reloads the SAME conversation's history
  (ID unchanged — old history forked to an archive, not a tab switch)
- WS adapter parses newConversationId field on ConversationCompactedMessage
- conformance guards + tests cover the new type

686 tests green.

6 files changed, 328 insertions, 4 deletions

diff --git a/src/adapters/ws/logic.ts b/src/adapters/ws/logic.ts
index 53955f8..b11c5c4 100644
--- a/src/adapters/ws/logic.ts
+++ b/src/adapters/ws/logic.ts
@@ -136,11 +136,13 @@ export function parseServerMessage(data: string): WsServerMessage | null {
 		}
 		case "conversation.compacted": {
 			if (typeof parsed.conversationId !== "string") return null;
+			if (typeof parsed.newConversationId !== "string") return null;
 			if (typeof parsed.messagesSummarized !== "number") return null;
 			if (typeof parsed.messagesKept !== "number") return null;
 			const msg: ConversationCompactedMessage = {
 				type: "conversation.compacted",
 				conversationId: parsed.conversationId,
+				newConversationId: parsed.newConversationId,
 				messagesSummarized: parsed.messagesSummarized,
 				messagesKept: parsed.messagesKept,
 			};
diff --git a/src/app/App.svelte b/src/app/App.svelte
index e065759..350db49 100644
--- a/src/app/App.svelte
+++ b/src/app/App.svelte
@@ -10,11 +10,14 @@
 	} from "../features/cache-warming";
 	import {
 		ChatView,
+		CompactionView,
 		Composer,
 		manifest as chatManifest,
 		ModelSelector,
 		ReasoningEffortSelector,
+		type CompactNowResult,
 		type ReasoningEffortSaveResult,
+		type SaveCompactThresholdResult,
 	} from "../features/chat";
 	import { manifest as conversationCacheManifest } from "../features/conversation-cache";
 	import { manifest as markdownManifest } from "../features/markdown";
@@ -65,11 +68,20 @@
 		{ id: "extensions", label: "Extensions" },
 		{ id: "cache-warming", label: "Cache Warming" },
 		{ id: "tasks", label: "Tasks" },
+		{ id: "compaction", label: "Compaction" },
 		{ id: "settings", label: "Settings" },
 	] as const;
 
-	// Default sidebar layout: Model, Language Servers, Extensions, Cache Warming, Tasks, Settings.
-	const initialViews = ["model", "lsp", "extensions", "cache-warming", "tasks", "settings"] as const;
+	// Default sidebar layout: Model, Language Servers, Extensions, Cache Warming, Tasks, Compaction, Settings.
+	const initialViews = [
+		"model",
+		"lsp",
+		"extensions",
+		"cache-warming",
+		"tasks",
+		"compaction",
+		"settings",
+	] as const;
 
 	// Frontend module list for the "Loaded Modules" view, AGGREGATED from each
 	// feature's public `manifest` export so it can't drift from what's actually
@@ -211,6 +223,29 @@
 			: { ok: false, error: result.error };
 	}
 
+	// Adapt the store's compact result to the compaction view's port.
+	async function compactNow(): Promise<CompactNowResult | null> {
+		const result = await store.compactNow();
+		if (result === null) return null;
+		return result.ok
+			? {
+					ok: true,
+					messagesSummarized: result.response.messagesSummarized,
+					messagesKept: result.response.messagesKept,
+				}
+			: { ok: false, error: result.error };
+	}
+
+	async function saveCompactThreshold(
+		threshold: number,
+	): Promise<SaveCompactThresholdResult | null> {
+		const result = await store.setCompactThreshold(threshold);
+		if (result === null) return null;
+		return result.ok
+			? { ok: true, threshold: result.threshold }
+			: { ok: false, error: result.error };
+	}
+
 	// Adapt the store's chat-limit result to the settings feature's port. On a
 	// raise the active chat refills (prepends older history); preserve the
 	// reader's viewport over the prepend (the manual analogue of CSS scroll
@@ -426,6 +461,16 @@
 				<p class="text-xs opacity-60">No tasks yet.</p>
 			{/if}
 		{/key}
+	{:else if kind === "compaction"}
+		<!-- Re-mount per conversation so the threshold + feedback can't bleed across tabs. -->
+		{#key store.currentConversationId}
+			<CompactionView
+				threshold={store.compactThreshold}
+				canCompact={store.activeConversationId !== null}
+				{compactNow}
+				saveThreshold={saveCompactThreshold}
+			/>
+		{/key}
 	{:else if kind === "settings"}
 		<!-- FE-local settings. Not conversation-scoped (no {#key}: the chat limit is
 		     global), so the field stays mounted across tab switches. -->
diff --git a/src/app/store.svelte.ts b/src/app/store.svelte.ts
index 6fd8e5e..1359fcd 100644
--- a/src/app/store.svelte.ts
+++ b/src/app/store.svelte.ts
@@ -1,6 +1,8 @@
 import type {
 	ChatDeltaMessage,
 	ChatErrorMessage,
+	CompactResponse,
+	CompactThresholdResponse,
 	ConversationCompactedMessage,
 	ConversationHistoryResponse,
 	ConversationListResponse,
@@ -12,6 +14,7 @@ import type {
 	ModelsResponse,
 	ReasoningEffort,
 	ReasoningEffortResponse,
+	SetCompactThresholdRequest,
 	SetCwdRequest,
 	SetReasoningEffortRequest,
 	WarmRequest,
@@ -65,6 +68,16 @@ export type ReasoningEffortResult =
 	| { readonly ok: true; readonly reasoningEffort: ReasoningEffort }
 	| { readonly ok: false; readonly error: string };
 
+/** Outcome of `POST /conversations/:id/compact` (manual compaction). */
+export type CompactResult =
+	| { readonly ok: true; readonly response: CompactResponse }
+	| { readonly ok: false; readonly error: string };
+
+/** Outcome of `PUT /conversations/:id/compact-threshold`. */
+export type CompactThresholdResult =
+	| { readonly ok: true; readonly threshold: number }
+	| { readonly ok: false; readonly error: string };
+
 /** Outcome of persisting a chat-limit setting (localStorage; FE-local). */
 export type ChatLimitResult =
 	| { readonly ok: true; readonly chatLimit: number }
@@ -123,6 +136,24 @@ export interface AppStore {
 	 */
 	setReasoningEffort(level: ReasoningEffort): Promise<ReasoningEffortResult | null>;
 	/**
+	 * Manually trigger conversation compaction (`POST /conversations/:id/compact`).
+	 * Summarizes old messages + retains the most recent N. Returns null when no
+	 * conversation is focused (a draft has nothing to compact).
+	 */
+	compactNow(keepLastN?: number): Promise<CompactResult | null>;
+	/**
+	 * The workspace conversation's auto-compact threshold (tokens). `0` = disabled
+	 * (manual only); a positive number = auto-compact triggers when the last
+	 * turn's input tokens exceed it. Seeded from the backend on focus change.
+	 */
+	readonly compactThreshold: number | null;
+	/**
+	 * Persist the workspace conversation's auto-compact threshold
+	 * (`PUT /conversations/:id/compact-threshold`). `0` disables; any positive
+	 * number enables. Works for a draft too (its id survives promotion).
+	 */
+	setCompactThreshold(threshold: number): Promise<CompactThresholdResult | null>;
+	/**
 	 * Fetch the workspace conversation's language-server status (`GET /conversations/:id/lsp`).
 	 * The backend lazily spawns servers, so this may take a moment on the first call for a cwd.
 	 */
@@ -317,6 +348,26 @@ export function createAppStore(opts?: CreateAppStoreOptions): AppStore {
 		}
 	}
 
+	// The workspace conversation's auto-compact threshold. Seeded from the
+	// backend on focus change; null = not yet fetched. 0 = disabled.
+	let compactThreshold = $state<number | null>(null);
+
+	/** Refetch the workspace conversation's compact threshold (works for a draft too). */
+	async function refreshCompactThreshold(): Promise<void> {
+		const id = workspaceConversationId();
+		compactThreshold = null;
+		try {
+			const res = await fetchImpl(
+				`${httpBase}/conversations/${encodeURIComponent(id)}/compact-threshold`,
+			);
+			if (!res.ok) return;
+			const data = (await res.json()) as CompactThresholdResponse;
+			if (workspaceConversationId() === id) compactThreshold = data.threshold;
+		} catch {
+			// Non-fatal: a threshold fetch failure just leaves null.
+		}
+	}
+
 	function getActiveChat(): ChatStore {
 		const activeId = tabsStore.activeConversationId;
 		if (activeId === null) {
@@ -481,6 +532,7 @@ export function createAppStore(opts?: CreateAppStoreOptions): AppStore {
 		syncSubscriptions();
 		void refreshCwd();
 		void refreshReasoningEffort();
+		void refreshCompactThreshold();
 	}
 
 	// Conversation lifecycle status (backend-owned, pushed via WS +
@@ -562,8 +614,9 @@ export function createAppStore(opts?: CreateAppStoreOptions): AppStore {
 			}
 		},
 		onConversationCompacted(msg: ConversationCompactedMessage): void {
-			// The conversation's history was summarized — reload it from the server.
-			// Dispose the old store (stale cache) + create a fresh one + load.
+			// Compaction keeps the conversation ID — the old full history is forked
+			// to an archive (newConversationId). Just reload the same conversation's
+			// history (dispose stale store + cache + re-fetch).
 			const cid = msg.conversationId;
 			const wasActive = tabsStore.activeConversationId === cid;
 			const store = chatStores.get(cid);
@@ -650,6 +703,7 @@ export function createAppStore(opts?: CreateAppStoreOptions): AppStore {
 	refreshActiveChat();
 	void refreshCwd();
 	void refreshReasoningEffort();
+	void refreshCompactThreshold();
 
 	// Fetch the authoritative open-conversation list from the backend (cross-
 	// device tab sync). Merges with the localStorage-restored tabs: opens new
@@ -692,6 +746,9 @@ export function createAppStore(opts?: CreateAppStoreOptions): AppStore {
 		get reasoningEffort(): ReasoningEffort | null {
 			return reasoningEffort;
 		},
+		get compactThreshold(): number | null {
+			return compactThreshold;
+		},
 		get chatLimit(): number {
 			return chatLimit;
 		},
@@ -730,6 +787,7 @@ export function createAppStore(opts?: CreateAppStoreOptions): AppStore {
 				syncSubscriptions();
 				void refreshCwd();
 				void refreshReasoningEffort();
+				void refreshCompactThreshold();
 				// Now send on the promoted store
 				chatStores.get(conversationId)?.send(text);
 			} else {
@@ -766,6 +824,7 @@ export function createAppStore(opts?: CreateAppStoreOptions): AppStore {
 			syncSubscriptions();
 			void refreshCwd();
 			void refreshReasoningEffort();
+			void refreshCompactThreshold();
 		},
 
 		selectTab(conversationId: string): void {
@@ -778,6 +837,7 @@ export function createAppStore(opts?: CreateAppStoreOptions): AppStore {
 			syncSubscriptions();
 			void refreshCwd();
 			void refreshReasoningEffort();
+			void refreshCompactThreshold();
 		},
 
 		closeTab(conversationId: string): void {
@@ -874,6 +934,67 @@ export function createAppStore(opts?: CreateAppStoreOptions): AppStore {
 			}
 		},
 
+		async compactNow(keepLastN?: number): Promise<CompactResult | null> {
+			const conversationId = tabsStore.activeConversationId;
+			if (conversationId === null) return null;
+			const body: Record<string, unknown> = {};
+			if (keepLastN !== undefined) body.keepLastN = keepLastN;
+			try {
+				const res = await fetchImpl(
+					`${httpBase}/conversations/${encodeURIComponent(conversationId)}/compact`,
+					{
+						method: "POST",
+						headers: { "content-type": "application/json" },
+						body: JSON.stringify(body),
+					},
+				);
+				if (!res.ok) {
+					const errBody = (await res.json().catch(() => null)) as { error?: string } | null;
+					return {
+						ok: false,
+						error: errBody?.error ?? `Compact failed (HTTP ${res.status})`,
+					};
+				}
+				const data = (await res.json()) as CompactResponse;
+				return { ok: true, response: data };
+			} catch (err) {
+				return {
+					ok: false,
+					error: err instanceof Error ? err.message : "Compact request failed",
+				};
+			}
+		},
+
+		async setCompactThreshold(threshold: number): Promise<CompactThresholdResult | null> {
+			const id = workspaceConversationId();
+			const body: SetCompactThresholdRequest = { threshold };
+			try {
+				const res = await fetchImpl(
+					`${httpBase}/conversations/${encodeURIComponent(id)}/compact-threshold`,
+					{
+						method: "PUT",
+						headers: { "content-type": "application/json" },
+						body: JSON.stringify(body),
+					},
+				);
+				if (!res.ok) {
+					const errBody = (await res.json().catch(() => null)) as { error?: string } | null;
+					return {
+						ok: false,
+						error: errBody?.error ?? `Set compact threshold failed (HTTP ${res.status})`,
+					};
+				}
+				const data = (await res.json()) as CompactThresholdResponse;
+				if (workspaceConversationId() === id) compactThreshold = data.threshold;
+				return { ok: true, threshold: data.threshold };
+			} catch (err) {
+				return {
+					ok: false,
+					error: err instanceof Error ? err.message : "Set compact threshold request failed",
+				};
+			}
+		},
+
 		async setChatLimit(limit: number): Promise<ChatLimitResult> {
 			const next = normalizeChatLimit(limit);
 			chatLimitStore.save(next);
diff --git a/src/core/wire/conformance.test.ts b/src/core/wire/conformance.test.ts
index 58cba3a..c50cbf4 100644
--- a/src/core/wire/conformance.test.ts
+++ b/src/core/wire/conformance.test.ts
@@ -148,6 +148,7 @@ describe("classifies every WsServerMessage type", () => {
 			{
 				type: "conversation.compacted" as const,
 				conversationId: "c1",
+				newConversationId: "c2",
 				messagesSummarized: 10,
 				messagesKept: 5,
 			},
diff --git a/src/features/chat/index.ts b/src/features/chat/index.ts
index 9b94392..9c65cd4 100644
--- a/src/features/chat/index.ts
+++ b/src/features/chat/index.ts
@@ -17,6 +17,8 @@ export {
 export type { ChatStore, ChatStoreDependencies } from "./store.svelte";
 export { createChatStore } from "./store.svelte";
 export { default as ChatView } from "./ui/ChatView.svelte";
+export type { CompactNowResult, SaveCompactThresholdResult } from "./ui/CompactionView.svelte";
+export { default as CompactionView } from "./ui/CompactionView.svelte";
 export { default as Composer } from "./ui/Composer.svelte";
 export { default as ModelSelector } from "./ui/ModelSelector.svelte";
 export { default as ReasoningEffortSelector } from "./ui/ReasoningEffortSelector.svelte";
diff --git a/src/features/chat/ui/CompactionView.svelte b/src/features/chat/ui/CompactionView.svelte
new file mode 100644
index 0000000..ce2a0a0
--- /dev/null
+++ b/src/features/chat/ui/CompactionView.svelte
@@ -0,0 +1,153 @@
+<script lang="ts">
+	export type CompactNowResult =
+		| { readonly ok: true; readonly messagesSummarized: number; readonly messagesKept: number }
+		| { readonly ok: false; readonly error: string };
+
+	export type SaveCompactThresholdResult =
+		| { readonly ok: true; readonly threshold: number }
+		| { readonly ok: false; readonly error: string };
+
+	let {
+		threshold,
+		canCompact,
+		compactNow,
+		saveThreshold,
+	}: {
+		/** The conversation's auto-compact threshold, or null when not yet fetched. 0 = disabled. */
+		threshold: number | null;
+		/** Whether a real conversation is focused (a draft has nothing to compact). */
+		canCompact: boolean;
+		compactNow: () => Promise<CompactNowResult | null>;
+		saveThreshold: (threshold: number) => Promise<SaveCompactThresholdResult | null>;
+	} = $props();
+
+	const DEFAULT_THRESHOLD = 350000;
+
+	let compacting = $state(false);
+	let compactError = $state<string | null>(null);
+	let compactResult = $state<{ summarized: number; kept: number } | null>(null);
+
+	let thresholdInput = $state("");
+	let savingThreshold = $state(false);
+	let thresholdError = $state<string | null>(null);
+	let thresholdSaved = $state(false);
+
+	// Sync the input from the prop when it changes (focus switch / initial load).
+	let lastThreshold = $state<number | null>(null);
+	$effect(() => {
+		if (threshold !== lastThreshold) {
+			lastThreshold = threshold;
+			thresholdInput = threshold !== null ? String(threshold) : "";
+			thresholdError = null;
+			thresholdSaved = false;
+		}
+	});
+
+	const thresholdLabel = $derived(
+		threshold == null
+			? "Loading…"
+			: threshold === 0
+				? "Disabled (manual only)"
+				: threshold === DEFAULT_THRESHOLD
+					? `${threshold.toLocaleString("en-US")} (default)`
+					: threshold.toLocaleString("en-US"),
+	);
+
+	async function handleCompact() {
+		if (compacting || !canCompact) return;
+		compacting = true;
+		compactError = null;
+		compactResult = null;
+		const result = await compactNow();
+		compacting = false;
+		if (result === null) return;
+		if (result.ok) {
+			compactResult = { summarized: result.messagesSummarized, kept: result.messagesKept };
+		} else {
+			compactError = result.error;
+		}
+	}
+
+	async function handleSaveThreshold() {
+		const value = Number.parseInt(thresholdInput, 10);
+		if (Number.isNaN(value) || value < 0) {
+			thresholdError = "Must be a non-negative number";
+			return;
+		}
+		savingThreshold = true;
+		thresholdError = null;
+		thresholdSaved = false;
+		const result = await saveThreshold(value);
+		savingThreshold = false;
+		if (result === null) return;
+		if (result.ok) {
+			thresholdSaved = true;
+		} else {
+			thresholdError = result.error;
+		}
+	}
+</script>
+
+<div class="flex flex-col gap-3">
+	<!-- Manual compaction -->
+	<section class="flex flex-col gap-1">
+		<span class="text-xs font-semibold uppercase opacity-60">Manual compaction</span>
+		<button
+			type="button"
+			class="btn btn-sm btn-outline"
+			disabled={!canCompact || compacting}
+			onclick={handleCompact}
+		>
+			{#if compacting}
+				<span class="loading loading-spinner loading-xs"></span>
+				Compacting…
+			{:else}
+				Compact now
+			{/if}
+		</button>
+		{#if !canCompact}
+			<p class="text-xs opacity-60">Open or start a conversation to compact its history.</p>
+		{:else if compactError}
+			<p class="text-xs text-error">{compactError}</p>
+		{:else if compactResult}
+			<p class="text-xs text-success">
+				Compacted — {compactResult.summarized} messages summarized, {compactResult.kept} kept.
+			</p>
+		{:else}
+			<p class="text-xs opacity-50">
+				Summarizes old messages into a system summary + retains the most recent messages.
+			</p>
+		{/if}
+	</section>
+
+	<!-- Auto-compact threshold -->
+	<section class="flex flex-col gap-1">
+		<span class="text-xs font-semibold uppercase opacity-60">Auto-compact threshold</span>
+		<div class="flex items-center gap-2">
+			<input
+				type="number"
+				class="input input-bordered input-sm w-32"
+				min="0"
+				placeholder={DEFAULT_THRESHOLD.toLocaleString("en-US")}
+				value={thresholdInput}
+				disabled={savingThreshold}
+				onchange={handleSaveThreshold}
+				aria-label="Compact threshold (tokens)"
+			/>
+			<span class="text-xs opacity-60">tokens</span>
+			{#if savingThreshold}
+				<span class="loading loading-spinner loading-xs"></span>
+			{/if}
+		</div>
+		<p class="text-xs opacity-50">
+			Current: {thresholdLabel}
+			<br />
+			0 disables auto-compact. Default is {DEFAULT_THRESHOLD.toLocaleString("en-US")}.
+		</p>
+		{#if thresholdError}
+			<p class="text-xs text-error">{thresholdError}</p>
+		{:else if thresholdSaved}
+			<p class="text-xs text-success">Saved.</p>
+		{/if}
+	</section>
+</div>