fix(test): exorcise the sidebar-agent ghost from the test suite

browse/src/sidebar-agent.ts was deleted in the v1.14 sidebar refactor, but the
test suite kept testing it for 48 versions. Nothing noticed because the free
suite runs in no CI job and Bun-era module-load errors were suppressed in the
Windows shard runner via an exclusion pattern whose own comment documented the
breakage ('broken on every platform since v1.14 ... exit 0').

- Delete sidebar-security.test.ts + security-source-contracts.test.ts: crashed
  at module load (unguarded readFileSync of the deleted file); per-assertion
  triage confirmed every SERVER_SRC pin targeted the deleted chat prompt
  builder (zero hits in today's server.ts) — nothing to port.
- Delete sidebar-integration.test.ts: 11 of 13 tests exercised deleted
  endpoints (/sidebar-command queue, /sidebar-agent/event, chat buffer); the 2
  passing tests pinned only the blanket auth gate, covered by
  server-auth.test.ts + dual-listener.test.ts.
- Delete test/skill-e2e-sidebar.test.ts: E2E for the deleted queue flow.
- sidebar-ux.test.ts 1,669 -> 830 lines: 20 dead-chat describes + 15 dead
  tests removed (incl. 10 vacuous passes asserting on empty indexOf slices);
  2 stale pins on LIVE features fixed (content.js typed-catch CSSOM fallback,
  arrow-hint window widened). 95 pass / 0 fail.
- sidebar-tabs.test.ts: both failures were stale pins, not regressions —
  forceRestart's deliberate ws.close(4001) and the terminal-agent spawn that
  moved into spawnTerminalAgent() (identity-based kill refactor). 28 pass.
- touchfiles.ts: drop the three sidebar E2E entries from BOTH maps
  (E2E_TOUCHFILES + E2E_TIERS) — they pointed diff-selection at the deleted
  file, so those tests were unreachable by any diff.
- test-free-shards.ts: remove the now-dead sidebar-agent exclusion pattern.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-08-14 15:59:19 -07:00
co-authored by Claude Fable 5
parent 05be4dbb8a
commit cd4490e515
8 changed files with 34 additions and 1981 deletions
+21 -864
View File
@@ -1,10 +1,14 @@
/**
* Tests for sidebar UX changes:
* - System prompt does not bake in page URL (navigation fix)
* - --resume is never used (stale context fix)
* - /sidebar-chat response includes agentStatus
* - Sidebar HTML has updated banner, placeholder, stop button
* - Narration instructions present in system prompt
* Tests for sidebar UX invariants that survived the chat-tab rip:
* - Browser tab bar HTML/CSS + browser-manager tab sync plumbing
* - Inspector message allowlist + CSP fallback basic picker
* - Cleanup/screenshot toolbar buttons + deterministic cleanup heuristics
* - Welcome page, sidebar auto-open, arrow hint signal chain
* - Connection auth race, startup fast-retry, debug visibility
*
* The chat-queue pipeline (sidebar-agent.ts, /sidebar-command,
* /sidebar-chat, chat bubbles) is gone — its tests were pruned with it.
* See sidebar-tabs.test.ts for the invariants locking that removal.
*/
import { describe, test, expect } from 'bun:test';
@@ -13,361 +17,8 @@ import * as path from 'path';
const ROOT = path.resolve(__dirname, '..');
// ─── System prompt tests (server.ts spawnClaude) ─────────────────
describe('sidebar system prompt (server.ts)', () => {
const serverSrc = fs.readFileSync(path.join(ROOT, 'src', 'server.ts'), 'utf-8');
test('system prompt does not bake in page URL', () => {
// The old prompt had: `The user is currently viewing: ${pageUrl}`
// The new prompt should NOT contain this pattern
// Extract the systemPrompt array from spawnClaude
const promptSection = serverSrc.slice(
serverSrc.indexOf('const systemPrompt = ['),
serverSrc.indexOf("].join('\\n');", serverSrc.indexOf('const systemPrompt = [')) + 15,
);
expect(promptSection).not.toContain('currently viewing');
expect(promptSection).not.toContain('${pageUrl}');
});
test('system prompt tells agent to check URL before acting', () => {
const promptSection = serverSrc.slice(
serverSrc.indexOf('const systemPrompt = ['),
serverSrc.indexOf("].join('\\n');", serverSrc.indexOf('const systemPrompt = [')) + 15,
);
expect(promptSection).toContain('NEVER');
expect(promptSection).toContain('navigate back');
expect(promptSection).toContain('NEVER assume');
expect(promptSection).toContain('url`');
});
test('system prompt includes conciseness and stop instructions', () => {
const promptSection = serverSrc.slice(
serverSrc.indexOf('const systemPrompt = ['),
serverSrc.indexOf("].join('\\n');", serverSrc.indexOf('const systemPrompt = [')) + 15,
);
expect(promptSection).toContain('CONCISE');
expect(promptSection).toContain('STOP');
});
test('--resume is never used in spawnClaude args', () => {
// Extract the spawnClaude function
const fnStart = serverSrc.indexOf('function spawnClaude(');
const fnEnd = serverSrc.indexOf('\nfunction ', fnStart + 1);
const fnBody = serverSrc.slice(fnStart, fnEnd);
// Should not push --resume to args
expect(fnBody).not.toContain("'--resume'");
expect(fnBody).not.toContain('"--resume"');
});
test('system prompt includes inspect and style commands', () => {
const promptSection = serverSrc.slice(
serverSrc.indexOf('const systemPrompt = ['),
serverSrc.indexOf("].join('\\n');", serverSrc.indexOf('const systemPrompt = [')) + 15,
);
expect(promptSection).toContain('inspect');
expect(promptSection).toContain('style');
expect(promptSection).toContain('cleanup');
});
});
// ─── /sidebar-chat response includes agentStatus ─────────────────
describe('/sidebar-chat agentStatus', () => {
const serverSrc = fs.readFileSync(path.join(ROOT, 'src', 'server.ts'), 'utf-8');
test('sidebar-chat response includes agentStatus field', () => {
// Find the GET /sidebar-chat handler — look for the data response, not the auth error
const handlerStart = serverSrc.indexOf("url.pathname === '/sidebar-chat'");
// Find the response that returns entries + total (skip the auth error response)
const entriesResponse = serverSrc.indexOf('{ entries, total', handlerStart);
expect(entriesResponse).toBeGreaterThan(handlerStart);
const responseLine = serverSrc.slice(entriesResponse, entriesResponse + 100);
expect(responseLine).toContain('agentStatus');
});
});
// ─── Sidebar HTML tests ──────────────────────────────────────────
describe('sidebar HTML (sidepanel.html)', () => {
const html = fs.readFileSync(path.join(ROOT, '..', 'extension', 'sidepanel.html'), 'utf-8');
test('banner says "Browser co-pilot" not "Standalone mode"', () => {
expect(html).toContain('Browser co-pilot');
expect(html).not.toContain('Standalone mode');
});
test('input placeholder says "Ask about this page"', () => {
expect(html).toContain('Ask about this page');
expect(html).not.toContain('Message Claude Code');
});
test('stop button exists with id stop-agent-btn', () => {
expect(html).toContain('id="stop-agent-btn"');
expect(html).toContain('class="stop-btn"');
});
test('stop button is hidden by default', () => {
// The stop button should have style="display: none;" initially
const stopBtnMatch = html.match(/id="stop-agent-btn"[^>]*/);
expect(stopBtnMatch).not.toBeNull();
expect(stopBtnMatch![0]).toContain('display: none');
});
});
// ─── Sidebar JS tests ───────────────────────────────────────────
describe('sidebar JS (sidepanel.js)', () => {
const js = fs.readFileSync(path.join(ROOT, '..', 'extension', 'sidepanel.js'), 'utf-8');
test('stopAgent function exists', () => {
expect(js).toContain('async function stopAgent()');
});
test('stopAgent calls /sidebar-agent/stop endpoint', () => {
expect(js).toContain('/sidebar-agent/stop');
});
test('stop button click handler is wired up', () => {
expect(js).toContain("getElementById('stop-agent-btn')");
expect(js).toContain('stopAgent');
});
test('updateStopButton function exists', () => {
expect(js).toContain('function updateStopButton(');
});
test('agent_start shows stop button', () => {
// Find the agent_start handler and verify it calls updateStopButton(true)
const startHandler = js.slice(
js.indexOf("entry.type === 'agent_start'"),
js.indexOf("entry.type === 'agent_done'"),
);
expect(startHandler).toContain('updateStopButton(true)');
});
test('agent_done hides stop button', () => {
const doneHandler = js.slice(
js.indexOf("entry.type === 'agent_done'"),
js.indexOf("entry.type === 'agent_error'"),
);
expect(doneHandler).toContain('updateStopButton(false)');
});
test('agent_error hides stop button', () => {
const errorIdx = js.indexOf("entry.type === 'agent_error'");
const errorHandler = js.slice(errorIdx, errorIdx + 500);
expect(errorHandler).toContain('updateStopButton(false)');
});
test('orphaned thinking cleanup checks agentStatus from server', () => {
// After polling, if agentStatus !== processing, thinking dots are removed
expect(js).toContain("data.agentStatus !== 'processing'");
});
test('orphaned thinking cleanup removes thinking dots silently', () => {
// Thinking dots are removed when agent is idle — no "(session ended)"
// notice, which was removed as noisy false-positive UX
expect(js).toContain('thinking.remove()');
});
test('sendMessage renders user bubble + thinking dots optimistically', () => {
// sendMessage should create user bubble and agent-thinking BEFORE the server responds
const sendFn = js.slice(js.indexOf('async function sendMessage()'), js.indexOf('async function sendMessage()') + 2000);
expect(sendFn).toContain('chat-bubble user');
expect(sendFn).toContain('agent-thinking');
expect(sendFn).toContain('lastOptimisticMsg');
});
test('fast polling during agent execution (300ms), slow when idle (1000ms)', () => {
expect(js).toContain('FAST_POLL_MS');
expect(js).toContain('SLOW_POLL_MS');
expect(js).toContain('startFastPoll');
expect(js).toContain('stopFastPoll');
// Fast = 300ms
expect(js).toContain('300');
// Slow = 1000ms
expect(js).toContain('1000');
});
test('agent_done calls stopFastPoll', () => {
const doneHandler = js.slice(
js.indexOf("entry.type === 'agent_done'"),
js.indexOf("entry.type === 'agent_error'"),
);
expect(doneHandler).toContain('stopFastPoll');
});
test('duplicate user bubble prevention via lastOptimisticMsg', () => {
expect(js).toContain('lastOptimisticMsg');
// When polled message matches optimistic, skip rendering
expect(js).toContain('lastOptimisticMsg === entry.message');
});
});
// ─── Sidebar agent queue poll (sidebar-agent.ts) ─────────────────
describe('sidebar agent queue poll (sidebar-agent.ts)', () => {
const agentSrc = fs.readFileSync(path.join(ROOT, 'src', 'sidebar-agent.ts'), 'utf-8');
test('queue poll interval is 200ms or less for fast TTFO', () => {
const match = agentSrc.match(/const POLL_MS\s*=\s*(\d+)/);
expect(match).not.toBeNull();
const pollMs = parseInt(match![1], 10);
expect(pollMs).toBeLessThanOrEqual(200);
});
});
// ─── System prompt size (TTFO optimization) ──────────────────────
describe('system prompt size', () => {
const serverSrc = fs.readFileSync(path.join(ROOT, 'src', 'server.ts'), 'utf-8');
test('system prompt is compact (under 30 lines)', () => {
const start = serverSrc.indexOf('const systemPrompt = [');
const end = serverSrc.indexOf("].join('\\n');", start);
const promptBlock = serverSrc.slice(start, end);
const lines = promptBlock.split('\n').length;
// Compact prompt = fewer input tokens = faster first response
// Higher limit accommodates security lines (prompt injection defense, allowed commands)
expect(lines).toBeLessThan(30);
});
test('system prompt does not contain verbose narration examples', () => {
// We trimmed examples to reduce token count. The agent gets the
// instruction to narrate, not 6 examples of how.
const start = serverSrc.indexOf('const systemPrompt = [');
const end = serverSrc.indexOf("].join('\\n');", start);
const promptBlock = serverSrc.slice(start, end);
expect(promptBlock).not.toContain('Examples of good narration');
expect(promptBlock).not.toContain('I can see a login form');
});
});
// ─── TTFO latency chain invariants ──────────────────────────────
describe('TTFO latency chain', () => {
const js = fs.readFileSync(path.join(ROOT, '..', 'extension', 'sidepanel.js'), 'utf-8');
const agentSrc = fs.readFileSync(path.join(ROOT, 'src', 'sidebar-agent.ts'), 'utf-8');
test('optimistic render happens BEFORE chrome.runtime.sendMessage', () => {
// In sendMessage(), the bubble + thinking dots must be created
// before the async POST to the server
const sendFn = js.slice(
js.indexOf('async function sendMessage()'),
js.indexOf('async function sendMessage()') + 3000,
);
const optimisticIdx = sendFn.indexOf('agent-thinking');
const sendIdx = sendFn.indexOf('chrome.runtime.sendMessage');
expect(optimisticIdx).toBeGreaterThan(0);
expect(sendIdx).toBeGreaterThan(0);
expect(optimisticIdx).toBeLessThan(sendIdx);
});
test('sendMessage calls startFastPoll before server request', () => {
const sendFn = js.slice(
js.indexOf('async function sendMessage()'),
js.indexOf('async function sendMessage()') + 3000,
);
const fastPollIdx = sendFn.indexOf('startFastPoll');
const sendIdx = sendFn.indexOf('chrome.runtime.sendMessage');
expect(fastPollIdx).toBeGreaterThan(0);
expect(fastPollIdx).toBeLessThan(sendIdx);
});
test('agent_start from server does not duplicate thinking dots', () => {
// When we already showed dots optimistically, agent_start from
// the poll should skip creating a second set
const startHandler = js.slice(
js.indexOf("entry.type === 'agent_start'"),
js.indexOf("entry.type === 'agent_done'"),
);
expect(startHandler).toContain('agent-thinking');
// Should check if thinking already exists and skip
expect(startHandler).toContain("getElementById('agent-thinking')");
});
test('FAST_POLL_MS is strictly less than SLOW_POLL_MS', () => {
const fastMatch = js.match(/FAST_POLL_MS\s*=\s*(\d+)/);
const slowMatch = js.match(/SLOW_POLL_MS\s*=\s*(\d+)/);
expect(fastMatch).not.toBeNull();
expect(slowMatch).not.toBeNull();
expect(parseInt(fastMatch![1], 10)).toBeLessThan(parseInt(slowMatch![1], 10));
});
test('stopAgent also calls stopFastPoll', () => {
const stopFn = js.slice(
js.indexOf('async function stopAgent()'),
js.indexOf('async function stopAgent()') + 1000,
);
expect(stopFn).toContain('stopFastPoll');
});
});
// ─── Browser tab bar ────────────────────────────────────────────
describe('browser tab bar (server.ts)', () => {
const serverSrc = fs.readFileSync(path.join(ROOT, 'src', 'server.ts'), 'utf-8');
test('/sidebar-tabs endpoint exists', () => {
expect(serverSrc).toContain("/sidebar-tabs'");
expect(serverSrc).toContain('getTabListWithTitles');
});
test('/sidebar-tabs/switch endpoint exists', () => {
expect(serverSrc).toContain("/sidebar-tabs/switch'");
expect(serverSrc).toContain('switchTab');
});
test('/sidebar-tabs requires auth', () => {
// Find the handler and verify auth check
const handlerIdx = serverSrc.indexOf("/sidebar-tabs'");
const handlerBlock = serverSrc.slice(handlerIdx, handlerIdx + 300);
expect(handlerBlock).toContain('validateAuth');
});
});
describe('browser tab bar (sidepanel.js)', () => {
const js = fs.readFileSync(path.join(ROOT, '..', 'extension', 'sidepanel.js'), 'utf-8');
test('pollTabs function exists and calls /sidebar-tabs', () => {
expect(js).toContain('async function pollTabs()');
expect(js).toContain('/sidebar-tabs');
});
test('renderTabBar function exists', () => {
expect(js).toContain('function renderTabBar(tabs)');
});
test('tab bar hidden when only 1 tab', () => {
const renderFn = js.slice(
js.indexOf('function renderTabBar('),
js.indexOf('function renderTabBar(') + 600,
);
expect(renderFn).toContain('tabs.length <= 1');
expect(renderFn).toContain("display = 'none'");
});
test('switchBrowserTab calls /sidebar-tabs/switch', () => {
expect(js).toContain('async function switchBrowserTab(');
expect(js).toContain('/sidebar-tabs/switch');
});
test('tab polling interval is set on connection', () => {
expect(js).toContain('tabPollInterval');
expect(js).toContain('setInterval(pollTabs');
});
test('tab polling cleaned up on disconnect', () => {
expect(js).toContain('clearInterval(tabPollInterval)');
});
test('only re-renders when tabs change (diff check)', () => {
expect(js).toContain('lastTabJson');
expect(js).toContain('json === lastTabJson');
});
});
describe('browser tab bar (sidepanel.html)', () => {
const html = fs.readFileSync(path.join(ROOT, '..', 'extension', 'sidepanel.html'), 'utf-8');
@@ -438,46 +89,12 @@ describe('browser→sidebar tab sync', () => {
expect(fn).toContain('this.pages.size <= 1');
});
test('/sidebar-tabs reads activeUrl param and calls syncActiveTabByUrl', () => {
const handler = serverSrc.slice(
serverSrc.indexOf("/sidebar-tabs'"),
serverSrc.indexOf("/sidebar-tabs'") + 700,
);
expect(handler).toContain("get('activeUrl')");
expect(handler).toContain('syncActiveTabByUrl');
});
test('/sidebar-command syncs activeTabUrl BEFORE reading tabId', () => {
// The server must call syncActiveTabByUrl before getActiveTabId
// so the agent targets the correct tab
const cmdIdx = serverSrc.indexOf("url.pathname === '/sidebar-command'");
const handler = serverSrc.slice(cmdIdx, cmdIdx + 1200);
const syncIdx = handler.indexOf('syncActiveTabByUrl');
const getIdIdx = handler.indexOf('getActiveTabId');
expect(syncIdx).toBeGreaterThan(0);
expect(getIdIdx).toBeGreaterThan(syncIdx); // sync happens BEFORE reading ID
});
test('background.js listens for chrome.tabs.onActivated', () => {
const bgSrc = fs.readFileSync(path.join(ROOT, '..', 'extension', 'background.js'), 'utf-8');
expect(bgSrc).toContain('chrome.tabs.onActivated.addListener');
expect(bgSrc).toContain('browserTabActivated');
});
test('sidepanel handles browserTabActivated message instantly', () => {
expect(js).toContain("msg.type === 'browserTabActivated'");
// Should call switchChatTab for instant context swap
expect(js).toContain('switchChatTab');
});
test('pollTabs sends Chrome active tab URL to server', () => {
const pollFn = js.slice(
js.indexOf('async function pollTabs()'),
js.indexOf('async function pollTabs()') + 800,
);
expect(pollFn).toContain('chrome.tabs.query');
expect(pollFn).toContain('activeUrl=');
});
});
describe('browser tab bar (sidepanel.css)', () => {
@@ -507,138 +124,6 @@ describe('browser tab bar (sidepanel.css)', () => {
});
});
// ─── Event relay (processAgentEvent) ────────────────────────────
describe('processAgentEvent handles sidebar-agent event types', () => {
const serverSrc = fs.readFileSync(path.join(ROOT, 'src', 'server.ts'), 'utf-8');
// Extract processAgentEvent function body
const fnStart = serverSrc.indexOf('function processAgentEvent(');
const fnEnd = serverSrc.indexOf('\nfunction ', fnStart + 1);
const fnBody = serverSrc.slice(fnStart, fnEnd > fnStart ? fnEnd : fnStart + 2000);
test('handles tool_use events directly (not raw Claude stream format)', () => {
// Must handle { type: 'tool_use', tool, input } from sidebar-agent
expect(fnBody).toContain("event.type === 'tool_use'");
expect(fnBody).toContain('event.tool');
expect(fnBody).toContain('event.input');
});
test('handles text_delta events directly', () => {
expect(fnBody).toContain("event.type === 'text_delta'");
expect(fnBody).toContain('event.text');
});
test('handles text events directly', () => {
expect(fnBody).toContain("event.type === 'text'");
});
test('handles result events', () => {
expect(fnBody).toContain("event.type === 'result'");
});
test('handles agent_error events', () => {
expect(fnBody).toContain("event.type === 'agent_error'");
expect(fnBody).toContain('event.error');
});
test('does NOT re-parse raw Claude stream events (no content_block_start)', () => {
// sidebar-agent.ts already transforms these. Server should not duplicate.
expect(fnBody).not.toContain('content_block_start');
expect(fnBody).not.toContain('content_block_delta');
expect(fnBody).not.toContain("event.type === 'assistant'");
});
test('all event types call addChatEntry with role: agent', () => {
// Every addChatEntry in processAgentEvent should have role: 'agent'
const addCalls = fnBody.match(/addChatEntry\(\{[^}]+\}\)/g) || [];
for (const call of addCalls) {
expect(call).toContain("role: 'agent'");
}
});
});
// ─── Per-tab chat context ────────────────────────────────────────
describe('per-tab chat context (server.ts)', () => {
const serverSrc = fs.readFileSync(path.join(ROOT, 'src', 'server.ts'), 'utf-8');
test('/sidebar-chat accepts tabId query param', () => {
const handler = serverSrc.slice(
serverSrc.indexOf("/sidebar-chat'"),
serverSrc.indexOf("/sidebar-chat'") + 600,
);
expect(handler).toContain('tabId');
});
test('addChatEntry takes a tabId parameter', () => {
// addChatEntry should route entries to the correct tab's buffer
expect(serverSrc).toContain('tabId');
// Look for tabId in addChatEntry function
const fnIdx = serverSrc.indexOf('function addChatEntry(');
if (fnIdx > -1) {
const fnBody = serverSrc.slice(fnIdx, fnIdx + 300);
expect(fnBody).toContain('tabId');
}
});
test('spawnClaude passes active tab ID to queue entry', () => {
const spawnFn = serverSrc.slice(
serverSrc.indexOf('function spawnClaude('),
serverSrc.indexOf('\nfunction ', serverSrc.indexOf('function spawnClaude(') + 1),
);
expect(spawnFn).toContain('tabId');
});
test('tab isolation uses BROWSE_TAB env var instead of system prompt hack', () => {
const agentSrc = fs.readFileSync(path.join(ROOT, 'src', 'sidebar-agent.ts'), 'utf-8');
// Agent passes BROWSE_TAB env var to claude (not a system prompt instruction)
expect(agentSrc).toContain('BROWSE_TAB');
// Server handleCommand reads tabId from body and pins to that tab
expect(serverSrc).toContain('savedTabId');
expect(serverSrc).toContain('switchTab(tabId)');
});
});
describe('per-tab chat context (sidepanel.js)', () => {
const js = fs.readFileSync(path.join(ROOT, '..', 'extension', 'sidepanel.js'), 'utf-8');
test('tracks activeTabId for chat context', () => {
expect(js).toContain('activeTabId');
});
test('pollChat sends tabId to server', () => {
const pollFn = js.slice(
js.indexOf('async function pollChat()'),
js.indexOf('async function pollChat()') + 600,
);
expect(pollFn).toContain('tabId');
});
test('switching tabs swaps displayed chat', () => {
// When tab changes, old chat is saved and new tab's chat is shown
expect(js).toContain('switchChatTab');
});
test('switchChatTab saves current tab DOM and restores new tab', () => {
const fn = js.slice(
js.indexOf('function switchChatTab('),
js.indexOf('function switchChatTab(') + 800,
);
expect(fn).toContain('chatDomByTab');
expect(fn).toContain('createDocumentFragment');
});
test('sendMessage includes tabId in message', () => {
const sendFn = js.slice(
js.indexOf('async function sendMessage()'),
js.indexOf('async function sendMessage()') + 2000,
);
expect(sendFn).toContain('tabId');
expect(sendFn).toContain('sidebarActiveTabId');
});
});
// ─── Sidebar CSS tests ──────────────────────────────────────────
describe('sidebar CSS (sidepanel.css)', () => {
@@ -712,10 +197,13 @@ describe('CSP fallback basic picker', () => {
expect(contentSrc).toContain('getBoundingClientRect()');
});
test('content.js contains CSSOM iteration with cross-origin try/catch', () => {
test('content.js contains CSSOM iteration tolerating cross-origin sheets', () => {
expect(contentSrc).toContain('document.styleSheets');
expect(contentSrc).toContain('cssRules');
expect(contentSrc).toContain('cross-origin');
// Cross-origin sheets throw DOMException on cssRules access — the
// iteration swallows exactly that (typed catch), nothing broader.
expect(contentSrc).toContain('same-origin only');
expect(contentSrc).toContain('instanceof DOMException');
});
test('content.js saves and restores outline on elements', () => {
@@ -772,31 +260,10 @@ describe('cleanup and screenshot buttons', () => {
expect(html).toContain('quick-actions');
});
test('cleanup button sends smart prompt to sidebar agent (not just deterministic selectors)', () => {
// Should use /sidebar-command endpoint (agent-based) not just /command (deterministic)
const cleanupFn = js.slice(
js.indexOf('async function runCleanup('),
js.indexOf('async function runScreenshot('),
);
expect(cleanupFn).toContain('sidebar-command');
expect(cleanupFn).toContain('cleanupPrompt');
// Should include both deterministic first pass AND agent snapshot analysis
expect(cleanupFn).toContain('cleanup --all');
expect(cleanupFn).toContain('snapshot -i');
// Should instruct agent to KEEP site branding
expect(cleanupFn).toContain('KEEP');
expect(cleanupFn).toContain('header/masthead/logo');
});
test('sidepanel.js screenshot handler POSTs to /command with screenshot', () => {
expect(js).toContain("command: 'screenshot'");
});
test('sidepanel.js has notification rendering for type notification', () => {
expect(js).toContain("entry.type === 'notification'");
expect(js).toContain('chat-notification');
});
test('sidepanel.css contains inspector-action-btn styles', () => {
expect(css).toContain('.inspector-action-btn');
expect(css).toContain('.inspector-action-btn.loading');
@@ -941,69 +408,12 @@ describe('chat toolbar buttons disabled state', () => {
});
});
// ─── Chat message dedup ─────────────────────────────────────────
// ─── No focus stealing (switchTab bringToFront) ─────────────────
describe('chat message dedup (prevents repeat rendering)', () => {
const js = fs.readFileSync(path.join(ROOT, '..', 'extension', 'sidepanel.js'), 'utf-8');
test('renderedEntryIds Set exists for dedup tracking', () => {
expect(js).toContain('const renderedEntryIds = new Set()');
});
test('addChatEntry checks entry.id against renderedEntryIds', () => {
const addFn = js.slice(
js.indexOf('function addChatEntry(entry)'),
js.indexOf('\n // User messages', js.indexOf('function addChatEntry(entry)')),
);
expect(addFn).toContain('renderedEntryIds.has(entry.id)');
expect(addFn).toContain('renderedEntryIds.add(entry.id)');
// Should return early (skip) if already rendered
expect(addFn).toContain('return');
});
test('addChatEntry skips dedup for entries without id (local notifications)', () => {
const addFn = js.slice(
js.indexOf('function addChatEntry(entry)'),
js.indexOf('\n // User messages', js.indexOf('function addChatEntry(entry)')),
);
// Should only check dedup when entry.id is defined
expect(addFn).toContain('entry.id !== undefined');
});
test('clear chat resets renderedEntryIds', () => {
expect(js).toContain('renderedEntryIds.clear()');
});
});
// ─── Agent conciseness and focus stealing ───────────────────────
describe('sidebar agent conciseness + no focus stealing', () => {
describe('no focus stealing (switchTab bringToFront)', () => {
const serverSrc = fs.readFileSync(path.join(ROOT, 'src', 'server.ts'), 'utf-8');
const bmSrc = fs.readFileSync(path.join(ROOT, 'src', 'browser-manager.ts'), 'utf-8');
test('system prompt tells agent to STOP when task is done', () => {
const promptSection = serverSrc.slice(
serverSrc.indexOf('const systemPrompt = ['),
serverSrc.indexOf("].join('\\n');", serverSrc.indexOf('const systemPrompt = [')),
);
expect(promptSection).toContain('STOP');
expect(promptSection).toContain('CONCISE');
expect(promptSection).toContain('Do NOT keep exploring');
});
test('sidebar agent auto-routes model based on message type', () => {
// Model router exists and defaults to opus for analysis tasks
expect(serverSrc).toContain('function pickSidebarModel(');
expect(serverSrc).toContain("return 'opus'");
expect(serverSrc).toContain("return 'sonnet'");
// spawnClaude uses the router, not a hardcoded model
const spawnFn = serverSrc.slice(
serverSrc.indexOf('function spawnClaude('),
serverSrc.indexOf('\nfunction ', serverSrc.indexOf('function spawnClaude(') + 1),
);
expect(spawnFn).toContain('pickSidebarModel(userMessage)');
});
test('switchTab has bringToFront option', () => {
expect(bmSrc).toContain('bringToFront?: boolean');
expect(bmSrc).toContain('bringToFront !== false');
@@ -1028,17 +438,6 @@ describe('LLM-based cleanup (smart agent cleanup)', () => {
const js = fs.readFileSync(path.join(ROOT, '..', 'extension', 'sidepanel.js'), 'utf-8');
const wcSrc = fs.readFileSync(path.join(ROOT, 'src', 'write-commands.ts'), 'utf-8');
test('cleanup button uses /sidebar-command not /command', () => {
const cleanupFn = js.slice(
js.indexOf('async function runCleanup('),
js.indexOf('async function runScreenshot('),
);
// Should POST to sidebar-command (agent) not /command (deterministic)
expect(cleanupFn).toContain('/sidebar-command');
// Should NOT directly call the cleanup command endpoint
expect(cleanupFn).not.toMatch(/fetch.*\/command['"]/);
});
test('cleanup prompt includes deterministic first pass', () => {
const cleanupFn = js.slice(
js.indexOf('async function runCleanup('),
@@ -1048,72 +447,6 @@ describe('LLM-based cleanup (smart agent cleanup)', () => {
expect(cleanupFn).toContain('cleanup --all');
});
test('cleanup prompt instructs agent to snapshot and analyze', () => {
const cleanupFn = js.slice(
js.indexOf('async function runCleanup('),
js.indexOf('async function runScreenshot('),
);
// Agent should take a snapshot to see what deterministic pass missed
expect(cleanupFn).toContain('snapshot -i');
// Agent should analyze what remains
expect(cleanupFn).toContain('identify remaining non-content');
});
test('cleanup prompt lists specific clutter categories for agent', () => {
const cleanupFn = js.slice(
js.indexOf('async function runCleanup('),
js.indexOf('async function runScreenshot('),
);
// Should guide the agent on what to look for
expect(cleanupFn).toContain('Ad placeholder');
expect(cleanupFn).toContain('ADVERTISEMENT');
expect(cleanupFn).toContain('Cookie');
expect(cleanupFn).toContain('Audio/podcast');
expect(cleanupFn).toContain('Sidebar widget');
expect(cleanupFn).toContain('Social share');
expect(cleanupFn).toContain('Floating chat');
});
test('cleanup prompt instructs agent to preserve site identity', () => {
const cleanupFn = js.slice(
js.indexOf('async function runCleanup('),
js.indexOf('async function runScreenshot('),
);
// Must keep the site looking like itself
expect(cleanupFn).toContain('KEEP');
expect(cleanupFn).toContain('header/masthead/logo');
expect(cleanupFn).toContain('article headline');
expect(cleanupFn).toContain('article body');
expect(cleanupFn).toContain('author byline');
});
test('cleanup prompt instructs agent to unlock scrolling', () => {
const cleanupFn = js.slice(
js.indexOf('async function runCleanup('),
js.indexOf('async function runScreenshot('),
);
expect(cleanupFn).toContain('unlock scrolling');
expect(cleanupFn).toContain('overflow');
});
test('cleanup prompt instructs agent to use $B eval for removal', () => {
const cleanupFn = js.slice(
js.indexOf('async function runCleanup('),
js.indexOf('async function runScreenshot('),
);
// Agent should use $B eval to hide elements via JavaScript
expect(cleanupFn).toContain('$B eval');
expect(cleanupFn).toContain("display=");
});
test('cleanup shows notification while agent works', () => {
const cleanupFn = js.slice(
js.indexOf('async function runCleanup('),
js.indexOf('async function runScreenshot('),
);
expect(cleanupFn).toContain('agent is analyzing');
});
test('cleanup removes loading state after short delay (agent is async)', () => {
const cleanupFn = js.slice(
js.indexOf('async function runCleanup('),
@@ -1343,10 +676,12 @@ describe('sidebar arrow hint hide flow (4-step signal chain)', () => {
// Step 1: sidepanel sends sidebarOpened when connected
test('step 1: sidepanel sends sidebarOpened message on connect', () => {
expect(spSrc).toContain("{ type: 'sidebarOpened' }");
// Should be in updateConnection, after setConnState('connected')
// Should be in updateConnection, after setConnState('connected').
// Window is 1500 chars — the function grew bootstrap-global exports
// for sidepanel-terminal.js ahead of the sidebarOpened send.
const connectFn = spSrc.slice(
spSrc.indexOf('function updateConnection('),
spSrc.indexOf('function updateConnection(') + 800,
spSrc.indexOf('function updateConnection(') + 1500,
);
expect(connectFn).toContain('sidebarOpened');
});
@@ -1463,131 +798,6 @@ describe('sidebar debug visibility when stuck', () => {
});
});
describe('BROWSE_NO_AUTOSTART (sidebar headless prevention)', () => {
const cliSrc = fs.readFileSync(path.join(ROOT, 'src', 'cli.ts'), 'utf-8');
const agentSrc = fs.readFileSync(path.join(ROOT, 'src', 'sidebar-agent.ts'), 'utf-8');
test('cli.ts checks BROWSE_NO_AUTOSTART before starting a new server', () => {
// ensureServer must check this env var BEFORE calling startServer()
const ensureServerFn = cliSrc.slice(
cliSrc.indexOf('async function ensureServer()'),
cliSrc.indexOf('async function startServer()'),
);
expect(ensureServerFn).toContain('BROWSE_NO_AUTOSTART');
expect(ensureServerFn).toContain('process.exit(1)');
});
test('cli.ts shows actionable error message when BROWSE_NO_AUTOSTART blocks', () => {
expect(cliSrc).toContain('/open-gstack-browser');
expect(cliSrc).toContain('BROWSE_NO_AUTOSTART is set');
});
test('sidebar-agent.ts sets BROWSE_NO_AUTOSTART=1', () => {
expect(agentSrc).toContain("BROWSE_NO_AUTOSTART: '1'");
});
test('sidebar-agent.ts sets BROWSE_PORT for headed server reuse', () => {
expect(agentSrc).toContain('BROWSE_PORT');
});
test('BROWSE_NO_AUTOSTART check happens before lock acquisition', () => {
// The guard must be BEFORE the lock acquisition. If it's after,
// we'd acquire a lock and then exit, leaving a stale lock file.
const ensureServerStart = cliSrc.indexOf('async function ensureServer()');
const noAutoStart = cliSrc.indexOf('BROWSE_NO_AUTOSTART', ensureServerStart);
const lockAcquisition = cliSrc.indexOf('Acquire lock', ensureServerStart);
expect(noAutoStart).toBeGreaterThan(0);
expect(lockAcquisition).toBeGreaterThan(0);
expect(noAutoStart).toBeLessThan(lockAcquisition);
});
});
// ─── Tool-result file filtering (sidebar-agent.ts) ──────────────
describe('sidebar-agent hides internal tool-result reads', () => {
const agentSrc = fs.readFileSync(path.join(ROOT, 'src', 'sidebar-agent.ts'), 'utf-8');
test('describeToolCall returns empty for tool-results paths', () => {
expect(agentSrc).toContain("input.file_path.includes('/tool-results/')");
});
test('describeToolCall returns empty for .claude/projects paths', () => {
expect(agentSrc).toContain("input.file_path.includes('/.claude/projects/')");
});
test('empty description causes early return (no event sent)', () => {
// describeToolCall returns '' for internal reads, which means
// summarizeToolInput returns '', which means event.input is ''
const readHandler = agentSrc.slice(
agentSrc.indexOf("if (tool === 'Read'"),
agentSrc.indexOf("if (tool === 'Edit'"),
);
expect(readHandler).toContain("return ''");
});
});
// ─── Sidebar skips empty tool_use entries (sidepanel.js) ────────
describe('sidebar skips empty tool_use descriptions', () => {
const js = fs.readFileSync(path.join(ROOT, '..', 'extension', 'sidepanel.js'), 'utf-8');
test('tool_use with no input returns early', () => {
const toolUseHandler = js.slice(
js.indexOf("entry.type === 'tool_use'"),
js.indexOf("entry.type === 'tool_use'") + 400,
);
expect(toolUseHandler).toContain("if (!toolInput) return");
});
});
// ─── Tool calls collapse into "See reasoning" on agent_done ─────
describe('tool calls collapse into reasoning disclosure', () => {
const js = fs.readFileSync(path.join(ROOT, '..', 'extension', 'sidepanel.js'), 'utf-8');
const css = fs.readFileSync(path.join(ROOT, '..', 'extension', 'sidepanel.css'), 'utf-8');
test('agent_done wraps tool calls in <details> element', () => {
const doneHandler = js.slice(
js.indexOf("entry.type === 'agent_done'"),
js.indexOf("entry.type === 'agent_done'") + 1200,
);
expect(doneHandler).toContain("createElement('details')");
expect(doneHandler).toContain('agent-reasoning');
});
test('disclosure summary shows step count', () => {
const doneHandler = js.slice(
js.indexOf("entry.type === 'agent_done'"),
js.indexOf("entry.type === 'agent_done'") + 1200,
);
expect(doneHandler).toContain('See reasoning');
expect(doneHandler).toContain('tools.length');
});
test('disclosure inserts before text response', () => {
const doneHandler = js.slice(
js.indexOf("entry.type === 'agent_done'"),
js.indexOf("entry.type === 'agent_done'") + 1200,
);
// Tool calls should appear before the text answer, not after
expect(doneHandler).toContain("querySelector('.agent-text')");
expect(doneHandler).toContain('insertBefore(details, textEl)');
});
test('CSS styles the reasoning disclosure', () => {
expect(css).toContain('.agent-reasoning');
expect(css).toContain('.agent-reasoning summary');
// Starts collapsed (no [open] by default)
expect(css).toContain('.agent-reasoning[open]');
});
test('disclosure uses custom triangle markers', () => {
// No default list-style, custom ▶/▼ via ::before
expect(css).toContain('list-style: none');
expect(css).toMatch(/agent-reasoning summary::before/);
});
});
// ─── Idle timeout disabled in headed mode (server.ts) ───────────
//
// The original 'idle check skips in headed mode' string-grep test was deleted
@@ -1597,33 +807,6 @@ describe('tool calls collapse into reasoning disclosure', () => {
// 'idle timer + onDisconnect dual-instance fix' describe block, which
// exercises the headed/headless/tunnel branches of idleCheckTick directly.
describe('idle timeout behavior (server.ts)', () => {
const serverSrc = fs.readFileSync(path.join(ROOT, 'src', 'server.ts'), 'utf-8');
test('sidebar-command resets idle timer', () => {
const sidebarCmd = serverSrc.slice(
serverSrc.indexOf("url.pathname === '/sidebar-command'"),
serverSrc.indexOf("url.pathname === '/sidebar-command'") + 300,
);
expect(sidebarCmd).toContain('resetIdleTimer');
});
});
// ─── Shutdown kills sidebar-agent daemon (server.ts) ────────────
describe('shutdown cleanup (server.ts)', () => {
const serverSrc = fs.readFileSync(path.join(ROOT, 'src', 'server.ts'), 'utf-8');
test('shutdown kills sidebar-agent daemon process', () => {
const shutdownFn = serverSrc.slice(
serverSrc.indexOf('async function shutdown()'),
serverSrc.indexOf('async function shutdown()') + 800,
);
expect(shutdownFn).toContain('sidebar-agent');
expect(shutdownFn).toContain('pkill');
});
});
// ─── Cookie button in sidebar footer ────────────────────────────
describe('cookie import button (sidebar)', () => {
@@ -1641,29 +824,3 @@ describe('cookie import button (sidebar)', () => {
});
});
// ─── Model routing (server.ts) ──────────────────────────────────
describe('sidebar model routing (server.ts)', () => {
const serverSrc = fs.readFileSync(path.join(ROOT, 'src', 'server.ts'), 'utf-8');
test('pickSidebarModel routes actions to sonnet', () => {
expect(serverSrc).toContain("return 'sonnet'");
});
test('pickSidebarModel routes analysis to opus', () => {
expect(serverSrc).toContain("return 'opus'");
});
test('analysis words override action verbs', () => {
// ANALYSIS_WORDS check comes before ACTION_PATTERNS
const routerFn = serverSrc.slice(
serverSrc.indexOf('function pickSidebarModel('),
serverSrc.indexOf('function pickSidebarModel(') + 600,
);
const analysisCheck = routerFn.indexOf('ANALYSIS_WORDS');
const actionCheck = routerFn.indexOf('ACTION_PATTERNS');
expect(analysisCheck).toBeGreaterThan(0);
expect(actionCheck).toBeGreaterThan(0);
expect(analysisCheck).toBeLessThan(actionCheck);
});
});