From b734eb96bf0af267fdfbef85df51940ca0b4e8c7 Mon Sep 17 00:00:00 2001
From: Adam Malczewski <github@tradam.dev>
Date: Tue, 2 Jun 2026 13:08:36 +0900
Subject: feat: persist per-tab token/cache usage across reload

Persist usage as invisible type:"usage" chunk rows (side channel):
- core: add "usage" ChunkType + UsageData; exclude usage rows from
  getChunksForTab/getTotalChunkCount; add getUsageStatsForTab aggregate
  (exported from barrel); defensive skip in groupRowsToMessages.
- api: agent-manager accumulates per-attempt usageRows and flushes them in
  the same atomic appendChunks call as the turn's content (discarded on a
  superseded fallback attempt). GET /tabs enriches rows with usageStats.
- frontend: hydrateFromBackend seeds cacheStats from usageStats (reload only;
  no re-seed on statuses reconnect, so no double-count with live events).

Tests: core DB-backed usage persistence/aggregate; api usage-row-per-event +
fallback discard; routes GET /tabs usageStats; frontend hydrate seed +
no-double-count + live-accumulation-after-seed. 495 -> 509 passing.
---
 packages/api/src/agent-manager.ts | 27 +++++++++++++++++++++++++--
 packages/api/src/routes/tabs.ts   |  6 +++++-
 2 files changed, 30 insertions(+), 3 deletions(-)

(limited to 'packages/api/src')

diff --git a/packages/api/src/agent-manager.ts b/packages/api/src/agent-manager.ts
index 5a0ffdf..1db9a04 100644
--- a/packages/api/src/agent-manager.ts
+++ b/packages/api/src/agent-manager.ts
@@ -54,6 +54,7 @@ import {
 	TaskList,
 	toAvailableSubagents,
 	toAvailableUserAgents,
+	type UsageData,
 	validateConfig,
 } from "@dispatch/core";
 import type { PermissionManager } from "./permission-manager.js";
@@ -1477,6 +1478,10 @@ export class AgentManager {
 			// turn (text / thinking / tool-batch / error / system), folded from
 			// the stream via the shared `appendEventToChunks` helper.
 			const chunks: Chunk[] = [];
+			// Per-attempt usage accumulator. Reset each fallback attempt so a
+			// superseded (rate-limited) attempt's usage is discarded alongside its
+			// `chunks`. One `usage` event → one UsageData row.
+			const usageRows: UsageData[] = [];
 			const assistantId = crypto.randomUUID();
 			let assistantPersisted = false;
 			tabAgent.currentChunks = chunks;
@@ -1487,8 +1492,17 @@ export class AgentManager {
 			// `tool-batch` into separate `tool_call` + `tool_result` rows and
 			// tags every row with `turn_id` + derived `step`.
 			const flushAssistant = (): void => {
-				if (assistantPersisted || chunks.length === 0) return;
-				appendChunks(tabId, explodeTurn(turnId, chunks));
+				if (assistantPersisted) return;
+				// Append usage as extra drafts in the SAME appendChunks call as the
+				// turn's content rows: one atomic write, one fsync, contiguous seqs.
+				// Usage rows are an invisible side channel (excluded from
+				// getChunksForTab); `step` is cosmetic for usage (never grouped).
+				const drafts = explodeTurn(turnId, chunks);
+				for (const u of usageRows) {
+					drafts.push({ turnId, step: 0, role: "assistant", type: "usage", data: u });
+				}
+				if (drafts.length === 0) return;
+				appendChunks(tabId, drafts);
 				assistantPersisted = true;
 			};
 
@@ -1542,6 +1556,15 @@ export class AgentManager {
 						allOutput += event.delta;
 					}
 
+					// Capture per-step usage as a side-channel row to persist with the
+					// turn (one row per `usage` event). The live `this.emit(event)`
+					// above still drives in-session accumulation; this is the reload-
+					// persistence path. `appendEventToChunks` intentionally ignores
+					// `usage`, so it never becomes message content.
+					if (event.type === "usage") {
+						usageRows.push({ ...event.usage });
+					}
+
 					// Route every content-bearing event through the shared helper.
 					// `appendEventToChunks` ignores lifecycle events (status / done
 					// / task-list-update / tab-created / message-* / etc), so it's
diff --git a/packages/api/src/routes/tabs.ts b/packages/api/src/routes/tabs.ts
index b1e9659..f52ee99 100644
--- a/packages/api/src/routes/tabs.ts
+++ b/packages/api/src/routes/tabs.ts
@@ -6,6 +6,7 @@ import {
 	getSetting,
 	getTab,
 	getTotalChunkCount,
+	getUsageStatsForTab,
 	groupRowsToMessages,
 	listOpenTabs,
 	setSetting,
@@ -27,7 +28,10 @@ export function setTabsAgentManager(
 }
 
 tabsRoutes.get("/", (c) => {
-	const tabs = listOpenTabs();
+	// Enrich each tab with its persisted usage aggregate so the frontend can
+	// seed `cacheStats` on reload without an extra round-trip. N small indexed
+	// queries — fine for tab counts.
+	const tabs = listOpenTabs().map((t) => ({ ...t, usageStats: getUsageStatsForTab(t.id) }));
 	return c.json({ tabs });
 });
 
-- 
cgit v1.2.3