Merge pull request #506 from timkjr/fix/split-pane-scroll-history

fix(split-pane): let a Shell Pane B's scroll-up reach tmux history
This commit is contained in:
Codeman maintainer
2026-10-01 11:09:26 +02:00
4 changed files with 683 additions and 16 deletions
+502 -10
View File
@@ -11,17 +11,31 @@
// refresh arriving mid-replay is now coalesced into ONE trailing re-run rather
// than dropped, because the in-flight fetch may predate the drop the new frame
// reports and no further frame comes to correct stale content.
//
// The last block covers the scroll-to-top history pull: a burst of output leaves
// a shell pane's xterm with about one screen of scrollback while tmux holds every
// line, and Pane B (a separate xterm from the primary pane) never went back to
// ask. See _maybeLoadMoreHistory / _pullHistory in terminal-split.js.
import { readFileSync } from 'node:fs';
import { resolve } from 'node:path';
import vm from 'node:vm';
import { beforeEach, describe, expect, it, vi } from 'vitest';
const TERMINAL_CHUNK_SIZE = 32 * 1024;
const TERMINAL_TAIL_SIZE = 1024 * 1024;
/** The pane's `performance.now()`, so frame arrival vs. capture time is set by hand, not raced. */
let clock = 0;
type FakeTerminal = {
write: ReturnType<typeof vi.fn>;
clear: ReturnType<typeof vi.fn>;
dispose: ReturnType<typeof vi.fn>;
scrollToLine: ReturnType<typeof vi.fn>;
scrollToTop: ReturnType<typeof vi.fn>;
cols: number;
rows: number;
options: { scrollback: number };
buffer: { active: { type: string; viewportY: number; length: number } };
};
type FakeSocket = {
onopen: unknown;
@@ -36,43 +50,79 @@ type PaneUnderTest = {
_destroyed: boolean;
_bufferLoading: boolean;
_bufferRefreshPending: boolean;
_historyPullAt: number;
_historyPullUseless: boolean;
_liveQueue: unknown[] | null;
_onWheel: unknown;
_wsClosed: boolean;
detachedSessions: Set<string> | undefined;
destroy(): void;
_loadBuffer(): Promise<void>;
_refreshBuffer(): void;
_maybeLoadMoreHistory(): void;
_pullHistory(): Promise<void>;
_onLiveOutput(data: string): void;
_onLiveClear(): void;
_installWheelListener(): void;
_writeDisconnectedMarker(): void;
};
const fetchMock = vi.fn();
/** requestAnimationFrame stand-in: chunked writes queue here and are drained by hand. */
const rafQueue: Array<() => void> = [];
const SOURCE = readFileSync(resolve(import.meta.dirname, '../src/web/public/terminal-split.js'), 'utf8');
function loadSplitTerminalPane() {
const dir = resolve(import.meta.dirname, '../src/web/public');
const src = readFileSync(resolve(dir, 'terminal-split.js'), 'utf8');
const context = vm.createContext({
console: { ...console, log: vi.fn(), warn: vi.fn(), error: vi.fn() },
window: {},
// The primary pane's row estimator, reduced to a line count: the pull only
// compares it with the pane's own row count.
window: {
app: { _estimateReplayRows: (text: string) => text.split('\n').length },
AbortSignal: { timeout: (ms: number) => ({ timeoutMs: ms }) },
},
performance: { now: () => clock },
fetch: (...args: unknown[]) => fetchMock(...args),
requestAnimationFrame: (fn: () => void) => rafQueue.push(fn),
// The constants.js globals the module reads at call time.
TERMINAL_CHUNK_SIZE,
TERMINAL_TAIL_SIZE: 1024 * 1024,
TERMINAL_TAIL_SIZE,
});
// The module's tail patches CodemanApp.prototype; nothing on it runs here.
vm.runInContext(`class CodemanApp { _onSessionDeleted() {} selectSession() {} }\n${src}`, context);
vm.runInContext(`class CodemanApp { _onSessionDeleted() {} selectSession() {} }\n${SOURCE}`, context);
return (context.window as { SplitTerminalPane: new (id: string, mount: unknown, opts?: object) => PaneUnderTest })
.SplitTerminalPane;
}
const SplitTerminalPane = loadSplitTerminalPane();
function makePane(mode = 'claude'): PaneUnderTest & { terminal: FakeTerminal } {
const pane = new SplitTerminalPane('s1', {}, { mode });
pane.terminal = { write: vi.fn(), clear: vi.fn(), dispose: vi.fn() };
function makePane(
mode = 'claude',
mount: unknown = {},
opts: { detachedSessions?: Set<string> } = {}
): PaneUnderTest & { terminal: FakeTerminal } {
const pane = new SplitTerminalPane('s1', mount, { mode, ...opts });
pane.terminal = {
// xterm invokes a write's callback once everything before it is parsed.
write: vi.fn((_data: string, done?: () => void) => done?.()),
clear: vi.fn(),
dispose: vi.fn(),
scrollToLine: vi.fn(),
scrollToTop: vi.fn(),
cols: 80,
rows: 30,
// xterm keeps at most `scrollback + rows` rows; small here so a test can fill it.
options: { scrollback: 1000 },
// A pane sitting at the top of a 40-row buffer on the normal screen.
buffer: { active: { type: 'normal', viewportY: 0, length: 40 } },
};
return pane as PaneUnderTest & { terminal: FakeTerminal };
}
function jsonResponse(terminalBuffer: string) {
return { json: async () => ({ data: { terminalBuffer } }) };
const rowsOf = (n: number) => Array.from({ length: n }, (_, i) => `line ${i}`).join('\n');
function jsonResponse(terminalBuffer: string, extra: Record<string, unknown> = {}) {
return { json: async () => ({ data: { terminalBuffer, ...extra } }) };
}
function deferred<T>() {
@@ -89,6 +139,7 @@ const settle = () => new Promise((r) => setTimeout(r, 0));
beforeEach(() => {
fetchMock.mockReset();
rafQueue.length = 0;
clock = 0;
});
describe('SplitTerminalPane.destroy()', () => {
@@ -232,3 +283,444 @@ describe('SplitTerminalPane server-refresh single-flight', () => {
expect(pane.terminal.write).toHaveBeenCalledWith('back');
});
});
describe('SplitTerminalPane scroll-to-top history pull', () => {
it('a shell pane at the top pulls a bounded window of full history and replays it', async () => {
const pane = makePane('shell');
const term = pane.terminal;
// The replay grows the buffer once xterm has parsed it (the empty write's callback).
term.write.mockImplementation((data: string, done?: () => void) => {
if (data === '' && done) term.buffer.active.length = 140;
done?.();
});
fetchMock.mockResolvedValueOnce(jsonResponse(rowsOf(100)));
pane._maybeLoadMoreHistory();
await settle();
// With a deadline: live output is held for as long as the pull runs, so a
// request that never answers would freeze the pane.
expect(fetchMock).toHaveBeenCalledWith(`/api/sessions/s1/terminal?full=1&tail=${TERMINAL_TAIL_SIZE}`, {
signal: { timeoutMs: 10_000 },
});
expect(term.write).toHaveBeenCalledWith('\x1bc');
expect(term.write).toHaveBeenCalledWith(rowsOf(100));
// What was row 0 is now 100 rows down (140 - 40): the reader keeps their
// place with the recovered history above it, instead of being dropped at the bottom.
expect(term.scrollToLine).toHaveBeenCalledWith(100);
expect(pane._bufferLoading).toBe(false);
expect(pane._liveQueue).toBeNull();
});
it('does nothing away from the top, for other modes, or on the alternate screen', async () => {
const midScroll = makePane('shell');
midScroll.terminal.buffer.active.viewportY = 12;
midScroll._maybeLoadMoreHistory();
// A repaint-mode agent CLI keeps no tmux history to recover.
makePane('claude')._maybeLoadMoreHistory();
// nano/vim/less own the wheel; their screen is not scrollback.
const fullScreenApp = makePane('shell');
fullScreenApp.terminal.buffer.active.type = 'alternate';
fullScreenApp._maybeLoadMoreHistory();
await settle();
expect(fetchMock).not.toHaveBeenCalled();
});
it('stands aside for a detached session, mirroring _sendResize()', async () => {
// A detached session's own window already owns its PTY size and
// scrollback (buildSplitPickerSessions() already refuses to open one).
const pane = makePane('shell', {}, { detachedSessions: new Set(['s1']) });
pane._maybeLoadMoreHistory();
await settle();
expect(fetchMock).not.toHaveBeenCalled();
});
it('a flick fires once: overlapping triggers are dropped, then the cooldown holds', async () => {
const pane = makePane('shell');
const response = deferred<ReturnType<typeof jsonResponse>>();
fetchMock.mockReturnValueOnce(response.promise);
pane._maybeLoadMoreHistory();
const startedAt = pane._historyPullAt;
// The cooldown is cleared between triggers on purpose, so that only the
// in-flight guard can be what drops the overlapping ones.
pane._historyPullAt = 0;
pane._maybeLoadMoreHistory();
pane._historyPullAt = 0;
pane._maybeLoadMoreHistory();
expect(fetchMock).toHaveBeenCalledTimes(1);
pane._historyPullAt = startedAt;
response.resolve(jsonResponse(rowsOf(100)));
await settle();
expect(pane._bufferLoading).toBe(false);
// Nothing in flight any more, so now it is the 4s cooldown alone.
pane._maybeLoadMoreHistory();
await settle();
expect(fetchMock).toHaveBeenCalledTimes(1);
// Once the cooldown lapses a later scroll-to-top may pull again.
fetchMock.mockResolvedValueOnce(jsonResponse(rowsOf(100)));
pane._historyPullAt = Date.now() - 5000;
pane._maybeLoadMoreHistory();
await settle();
expect(fetchMock).toHaveBeenCalledTimes(2);
});
it('a window the pane already holds in full is not rewritten, and is not latched as useless', async () => {
const pane = makePane('shell');
fetchMock.mockResolvedValueOnce(jsonResponse(rowsOf(30)));
pane._maybeLoadMoreHistory();
await settle();
// A reset+rewrite here would jump the viewport for no new rows.
expect(pane.terminal.write).not.toHaveBeenCalledWith('\x1bc');
expect(pane.terminal.scrollToLine).not.toHaveBeenCalled();
expect(pane.terminal.scrollToTop).not.toHaveBeenCalled();
// The next burst can put more history in tmux than the pane has.
expect(pane._historyPullUseless).toBe(false);
expect(pane._bufferLoading).toBe(false);
});
it('refuses a downgrade, keeping the 4s cooldown when the window is all of tmux history', async () => {
const pane = makePane('shell');
pane.terminal.buffer.active.length = 500;
fetchMock.mockResolvedValueOnce(jsonResponse(rowsOf(5)));
pane._maybeLoadMoreHistory();
await settle();
expect(pane.terminal.write).not.toHaveBeenCalledWith('\x1bc');
// Untruncated: tmux has nothing older, but the next burst can add history.
expect(pane._historyPullUseless).toBe(false);
});
it('a truncated window that fits in the pane backs off for a minute', async () => {
// Every ask costs the server a capture-pane of the WHOLE history (`tail` is
// cut after the capture), and a window cut at the tail size can never reach
// anything older than what the pane already shows.
const pane = makePane('shell');
pane.terminal.buffer.active.length = 500;
// Within a screen of what the pane holds, so the old downgrade guard never
// latched it: only the truncated-skip rule can back this off.
fetchMock.mockResolvedValueOnce(jsonResponse(rowsOf(480), { truncated: true, truncationReason: 'tail' }));
pane._maybeLoadMoreHistory();
await settle();
expect(pane.terminal.write).not.toHaveBeenCalledWith('\x1bc');
expect(pane._historyPullUseless).toBe(true);
// Inside the 60s back-off, well past the normal 4s cooldown.
pane._historyPullAt = Date.now() - 10_000;
pane._maybeLoadMoreHistory();
await settle();
expect(fetchMock).toHaveBeenCalledTimes(1);
});
it('a pane already at its scrollback cap skips the window and backs off for a minute', async () => {
// A 1 MiB window of short lines can carry more rows than xterm will ever hold
// (`scrollback + rows`), so `incoming <= rows held` never comes true and every
// scroll-to-top would reset and re-parse it.
const pane = makePane('shell');
pane.terminal.buffer.active.length = 1030;
fetchMock.mockResolvedValueOnce(jsonResponse(rowsOf(5000)));
pane._maybeLoadMoreHistory();
await settle();
expect(pane.terminal.write).not.toHaveBeenCalledWith('\x1bc');
expect(pane.terminal.write).not.toHaveBeenCalledWith(rowsOf(5000));
expect(pane._historyPullUseless).toBe(true);
});
it('a successful replay clears the one-minute back-off', async () => {
const pane = makePane('shell');
pane._historyPullUseless = true;
fetchMock.mockResolvedValueOnce(jsonResponse(rowsOf(100), { truncated: true, truncationReason: 'tail' }));
void pane._pullHistory();
await settle();
expect(pane.terminal.write).toHaveBeenCalledWith(rowsOf(100));
expect(pane._historyPullUseless).toBe(false);
});
it('holds live output during the replay and replays only what arrived after the capture', async () => {
const pane = makePane('shell');
const term = pane.terminal;
const response = deferred<ReturnType<typeof jsonResponse>>();
fetchMock.mockReturnValueOnce(response.promise);
pane._maybeLoadMoreHistory();
expect(pane._liveQueue).toEqual([]);
// Arrives before the response does: it is IN the capture already.
clock = 1;
pane._onLiveOutput('early');
expect(term.write).not.toHaveBeenCalledWith('early');
await settle();
// 200 rows (more than the pane holds, so it replays) of 400 columns each:
// three chunks, which leaves the replay mid-write once the fetch lands.
const bigReplay = Array.from({ length: 200 }, () => 'y'.repeat(400)).join('\n');
expect(bigReplay.length).toBeGreaterThan(TERMINAL_CHUNK_SIZE * 2);
clock = 2; // the response arrives: this is the cutoff
response.resolve(jsonResponse(bigReplay));
await settle();
expect(rafQueue).toHaveLength(1);
// Arrives while the snapshot is still being written: must not land under it.
clock = 3;
pane._onLiveOutput('late');
expect(term.write).not.toHaveBeenCalledWith('late');
rafQueue.shift()!();
rafQueue.shift()!();
await settle();
const written = term.write.mock.calls.map((call) => call[0]);
expect(written).not.toContain('early');
expect(written.at(-1)).toBe('late');
expect(pane._liveQueue).toBeNull();
expect(pane._bufferLoading).toBe(false);
});
it('writes every held frame when the pull ends without replaying', async () => {
const pane = makePane('shell');
const response = deferred<ReturnType<typeof jsonResponse>>();
fetchMock.mockReturnValueOnce(response.promise);
pane._maybeLoadMoreHistory();
pane._onLiveOutput('held');
await settle();
response.resolve(jsonResponse(rowsOf(30))); // nothing to gain: no replay
await settle();
// Nothing replaced the terminal, so the frame is news even though it
// arrived before the response did.
expect(pane.terminal.write).toHaveBeenCalledWith('held');
});
it('a failed fetch releases the flag and the queue, so live output flows again', async () => {
const pane = makePane('shell');
fetchMock.mockRejectedValueOnce(new Error('offline'));
pane._maybeLoadMoreHistory();
pane._onLiveOutput('held');
await settle();
expect(pane._bufferLoading).toBe(false);
expect(pane._liveQueue).toBeNull();
expect(pane.terminal.write).toHaveBeenCalledWith('held');
pane._onLiveOutput('after');
expect(pane.terminal.write).toHaveBeenLastCalledWith('after');
});
it('a refresh frame during the pull runs once behind it', async () => {
const pane = makePane('shell');
const response = deferred<ReturnType<typeof jsonResponse>>();
fetchMock.mockReturnValueOnce(response.promise).mockResolvedValueOnce(jsonResponse('refreshed'));
pane._maybeLoadMoreHistory();
pane._refreshBuffer();
expect(pane.terminal.clear).not.toHaveBeenCalled();
expect(pane._bufferRefreshPending).toBe(true);
response.resolve(jsonResponse(rowsOf(30)));
await settle();
expect(pane.terminal.clear).toHaveBeenCalledTimes(1);
expect(fetchMock).toHaveBeenCalledTimes(2);
expect(pane.terminal.write).toHaveBeenCalledWith('refreshed');
});
it('a clear frame during the pull is queued in order, never applied under the replay', async () => {
const pane = makePane('shell');
const term = pane.terminal;
const order: string[] = [];
term.write.mockImplementation((data: string, done?: () => void) => {
order.push(`write:${data}`);
done?.();
});
term.clear.mockImplementation(() => order.push('clear'));
const response = deferred<ReturnType<typeof jsonResponse>>();
fetchMock.mockReturnValueOnce(response.promise);
pane._maybeLoadMoreHistory();
pane._onLiveOutput('before');
pane._onLiveClear();
pane._onLiveOutput('after');
// Held: clearing now would wipe a half-written snapshot.
expect(order).toEqual([]);
response.resolve(jsonResponse(rowsOf(30))); // nothing to gain: no replay
await settle();
expect(order).toEqual(['write:before', 'clear', 'write:after']);
expect(pane._liveQueue).toBeNull();
// With nothing in flight a clear frame applies straight away.
pane._onLiveClear();
expect(order.at(-1)).toBe('clear');
});
it('a clear that arrived before the capture is not replayed after it', async () => {
const pane = makePane('shell');
const term = pane.terminal;
const response = deferred<ReturnType<typeof jsonResponse>>();
fetchMock.mockReturnValueOnce(response.promise);
pane._maybeLoadMoreHistory();
clock = 1;
pane._onLiveClear(); // already reflected in the capture
clock = 2;
response.resolve(jsonResponse(rowsOf(100)));
await settle();
expect(term.write).toHaveBeenCalledWith('\x1bc');
expect(term.clear).not.toHaveBeenCalled();
});
it('destroy() mid-pull leaves nothing running and nothing written to the dead terminal', async () => {
const pane = makePane('shell');
const term = pane.terminal;
const response = deferred<ReturnType<typeof jsonResponse>>();
fetchMock.mockReturnValueOnce(response.promise);
pane._maybeLoadMoreHistory();
pane._onLiveOutput('held');
pane.destroy();
response.resolve(jsonResponse(rowsOf(100)));
await settle();
expect(pane._bufferLoading).toBe(false);
expect(pane._liveQueue).toBeNull();
expect(pane.terminal).toBeNull();
expect(term.write).not.toHaveBeenCalledWith('\x1bc');
expect(term.write).not.toHaveBeenCalledWith('held');
});
it('a pull whose request is aborted (the deadline) frees the pane', async () => {
const pane = makePane('shell');
fetchMock.mockRejectedValueOnce(new Error('The operation timed out'));
pane._maybeLoadMoreHistory();
pane._onLiveOutput('held');
await settle();
expect(pane._bufferLoading).toBe(false);
expect(pane._liveQueue).toBeNull();
expect(pane.terminal.write).toHaveBeenCalledWith('held');
});
it('the wheel listener is capture-phase, and only a wheel UP can trigger a pull', async () => {
const mount = { addEventListener: vi.fn(), removeEventListener: vi.fn() };
const pane = makePane('shell', mount);
fetchMock.mockResolvedValue(jsonResponse(rowsOf(100)));
pane._installWheelListener();
// Capture phase: xterm's own wheel handler stopPropagation()s the events it
// consumes, so a bubbling listener would never fire while the pane still has
// scrollback to scroll, and the pull would work only from the exact top row.
const [type, listener, options] = mount.addEventListener.mock.calls[0];
expect(type).toBe('wheel');
expect(options).toEqual({ capture: true, passive: true });
listener({ deltaY: 120 }); // wheel down
listener({ deltaY: 0 });
await settle();
expect(fetchMock).not.toHaveBeenCalled();
listener({ deltaY: -120 }); // wheel up, at the top
await settle();
expect(fetchMock).toHaveBeenCalledTimes(1);
});
it('destroy() detaches exactly the wheel listener it registered', () => {
const mount = { addEventListener: vi.fn(), removeEventListener: vi.fn() };
const pane = makePane('shell', mount);
pane._installWheelListener();
const registered = mount.addEventListener.mock.calls[0][1];
pane.destroy();
expect(mount.removeEventListener).toHaveBeenCalledWith('wheel', registered, { capture: true });
expect(pane._onWheel).toBeNull();
});
it('connect() installs the wheel listener (static guard)', () => {
// connect() needs a whole xterm to run, so its wiring is pinned by source
// rather than executed; the listener's behaviour is exercised above.
const connect = SOURCE.slice(SOURCE.indexOf('async connect()'), SOURCE.indexOf('async _loadBuffer()'));
expect(connect).toContain('this._installWheelListener();');
expect(connect).toContain('this._onLiveClear();');
expect(connect).not.toContain('this.terminal.clear();');
});
it('re-stamps the disconnected marker after a replay if the socket closed before the pull started', async () => {
// onclose already wrote the marker once; a replay's own `\x1bc` would wipe
// it and paint a fresh, current-looking history while onData keeps
// silently dropping every keystroke on the dead socket.
const pane = makePane('shell');
pane._wsClosed = true;
fetchMock.mockResolvedValueOnce(jsonResponse(rowsOf(100)));
void pane._pullHistory();
await settle();
const marker = expect.stringContaining('Pane B disconnected');
const writes = pane.terminal.write.mock.calls.map((c) => c[0]);
expect(writes.at(-1)).toEqual(expect.stringMatching(/Pane B disconnected/));
expect(pane.terminal.write).toHaveBeenCalledWith(marker);
});
it('re-stamps the disconnected marker after a replay if the socket closes mid-fetch', async () => {
// The other order Ark0N's review called out: the close lands while the
// capture is in flight, so the HTTP pull still succeeds (a Codeman
// restart drops the WS while the tmux session, and so the pull, survives).
const pane = makePane('shell');
const response = deferred<ReturnType<typeof jsonResponse>>();
fetchMock.mockReturnValueOnce(response.promise);
const pull = pane._pullHistory();
pane._wsClosed = true; // the close arrives mid-fetch, before the response
response.resolve(jsonResponse(rowsOf(100)));
await pull;
expect(pane.terminal.write.mock.calls.at(-1)?.[0]).toEqual(expect.stringMatching(/Pane B disconnected/));
});
it('does not re-stamp the marker when the socket is still open', async () => {
const pane = makePane('shell');
fetchMock.mockResolvedValueOnce(jsonResponse(rowsOf(100)));
void pane._pullHistory();
await settle();
for (const call of pane.terminal.write.mock.calls) {
expect(call[0]).toEqual(expect.not.stringMatching(/Pane B disconnected/));
}
});
it('does not re-stamp the marker when the pull never replayed (skip/downgrade path)', async () => {
// Nothing erased the marker in this path, so re-stamping it would be a
// second, redundant write.
const pane = makePane('shell');
pane._wsClosed = true;
fetchMock.mockResolvedValueOnce(jsonResponse(rowsOf(30))); // held in full already: no replay
void pane._pullHistory();
await settle();
expect(pane.terminal.write).not.toHaveBeenCalled();
});
});