Files
Codeman/test/mocks/mock-session.ts
T
JD 71a51df2e2 feat(sessions): keep an idle session's prompt cache warm with a guarded keep-alive turn
Claude Code lets a subscription's one-hour prompt cache expire after an hour idle, and the first turn back re-writes the whole conversation at the cache-write rate; nearly every gap over an hour goes cold, while the saving is concentrated in gaps of one to four hours. Codeman now sends one short keep-alive turn five minutes before the expiry Claude Code reports on its statusline, so the next real prompt still reads the conversation from cache, and stops two hours (configurable) after the last real prompt.

Codeman owns the idle policy for these sessions, as agreed in Discussion #554: a launch with keep-warm on also carries idleCompaction: false in its one --settings JSON, so Claude Code's own idle compaction cannot replace the conversation with a summary a minute before the nudge. It is decided once per launch (keep-warm on, the statusLine exporter injected, Claude Code 2.1.290 or newer, an unknown version fails closed like --name), recorded on the mux record, and picked up by any relaunch; a launch with keep-warm off is byte-identical. A session switched on after launch is kept warm best-effort and the readout says so.

Every guard lives in one pure rulebook: the opt-in (an agent-spawned session does not inherit the app default), a launch that reports cache state, a warm 1h cache with enough tokens at stake and no compaction this gap, a live pane, no usage-limit pause, no respawn, Ralph, task or waiting agent, idle, no open dialog, an empty composer and no recent keystroke. The nudge is a submit and moves lastSubmitAt, which the response viewer's conversation correlation needs; the cap counts from its own persisted lastRealPromptAt instead. Read My Mind drops the exact nudge text, and the turn's stop hook and idle prompt open pre-acknowledged so nothing alerts. The last cache report and the clock survive a restart, so the timer re-arms.
2026-10-18 15:19:08 -04:00

510 lines
16 KiB
TypeScript

/**
* Shared MockSession for tests that need terminal simulation.
* Used by respawn, route, and subagent tests.
*/
import { EventEmitter } from 'node:events';
import { vi } from 'vitest';
import type {
KeepWarmStatus,
PromptCacheStatus,
SessionAttachmentHistoryItem,
SessionStatus,
SessionRemote,
} from '../../src/types.js';
/**
* Enhanced mock session for testing RespawnController.
* Extends the existing MockSession pattern with additional utilities.
*/
export class MockSession extends EventEmitter {
id: string;
workingDir: string = '/tmp/test-workdir';
/**
* Mirrors `Session.remote` — set to a `SessionRemote` to model a remote-SSH case,
* whose `workingDir` is an absolute path on ANOTHER host. File routes must read it
* over ssh instead of with local `fs` (#415).
*/
remote?: SessionRemote;
/** Mirrors Session.attachmentHistory (the attachment panel's source of truth). */
attachmentHistory: SessionAttachmentHistoryItem[] = [];
/** Mirrors Session.getAttachmentHistoryForPersist(). */
getAttachmentHistoryForPersist(): SessionAttachmentHistoryItem[] {
return this.attachmentHistory;
}
/**
* The REAL union, deliberately. This used to be `'idle' | 'working'`, and
* `'working'` is not a `SessionStatus` at all — so `signalForStatus()` fell to its
* `default: null` branch in every route test and the busy / stopped / error halves
* of the immediate-resolve mapping had zero coverage while appearing to be tested.
*/
status: SessionStatus = 'idle';
/** `null` once the PTY is gone (or before it has ever started) — see `pid` in Session. */
pid: number | null = 12345;
isWorking: boolean = false;
/**
* Mirrors Session.watching — what the pane's footer says is still running in the
* background. An idle prompt from such a session opens acknowledged, so the routes
* need to be able to set it.
*/
watching: string | null = null;
/** Mirrors Session.promptCache / setPromptCache (fed by POST /api/status-telemetry). */
promptCache: PromptCacheStatus | null = null;
setPromptCache(status: PromptCacheStatus): boolean {
const changed = JSON.stringify(status) !== JSON.stringify(this.promptCache);
this.promptCache = status;
return changed;
}
/** Mirrors the prompt-cache keep-warm surface on Session (prompt-cache-keepwarm.ts). */
keepAliveTurnActive = false;
keepWarmEnabled: boolean | undefined = undefined;
setKeepWarmEnabled(enabled: boolean | undefined): void {
this.keepWarmEnabled = enabled;
}
keepWarm: KeepWarmStatus | null = null;
setKeepWarmStatus(status: KeepWarmStatus): boolean {
const changed = JSON.stringify(status) !== JSON.stringify(this.keepWarm);
this.keepWarm = status;
return changed;
}
private _activeChildProcesses: { pid: number; command: string }[] = [];
ralphTracker: null = null;
writeBuffer: string[] = [];
terminalBuffer: string = '';
/** Mirrors Session.lastSubmitAt — the response viewer credits history entries by it. */
lastSubmitAt: number = 0;
/** Mirrors Session.claudeSessionId — the conversation the viewer reads. */
claudeSessionId: string | null = null;
/** Mirrors Session.claudeSessionIdIsFirstHand — set only by a hook adoption. */
claudeSessionIdIsFirstHand: boolean = false;
/** Mirrors Session.claudeSessionChain — oldest first, current last. */
claudeSessionChain: string[] = [];
/** Mirrors Session.adoptClaudeSessionId, including the first-hand chain rule. */
adoptClaudeSessionId(newId: string, options: { firstHand?: boolean } = {}): void {
if (!newId) return;
if (options.firstHand) {
this.claudeSessionIdIsFirstHand = true;
if (this.claudeSessionChain[this.claudeSessionChain.length - 1] !== newId) {
const existing = this.claudeSessionChain.indexOf(newId);
if (existing !== -1) this.claudeSessionChain.splice(existing, 1);
this.claudeSessionChain.push(newId);
}
}
if (newId === this.claudeSessionId) return;
this.claudeSessionId = newId;
}
/** Mirrors Session.markPromptSubmitted; records the hook's prompt text it was handed. */
submittedPrompts: Array<string | undefined> = [];
markPromptSubmitted(prompt?: string): void {
this.submittedPrompts.push(prompt);
this.lastSubmitAt = Date.now();
}
/** Mirrors Session.trackUserInput (the send-key route feeds it around the write path). */
trackUserInput(_data: string): void {}
private _muxName: string | null = null;
constructor(id: string = 'mock-session-id') {
super();
this.id = id;
this._muxName = `codeman-test-${id.slice(0, 8)}`;
}
/**
* Set to simulate a session whose PTY is gone: both write paths report failure,
* which is the state in which input used to disappear silently.
*/
failWrites = false;
/** Direct PTY write (used by session.write()). Mirrors the real boolean return. */
write(data: string): boolean {
if (this.failWrites) return false;
this.writeBuffer.push(data);
return true;
}
/** Write via mux (used by respawn controller) */
async writeViaMux(data: string): Promise<boolean> {
if (this.failWrites) return false;
this.writeBuffer.push(data);
return true;
}
/**
* Mirrors `Session.reattachRemote()` — the COD-108 transport re-establish that
* the wake-on-LAN flow calls once a sleeping host is back. Defaults to success;
* set `reattachRemote.mockResolvedValue(false)` to model a pane that could not
* be respawned.
*/
reattachRemote = vi.fn(async (): Promise<boolean> => true);
/** Exactly-once input dedup — mirrors Session.shouldApplyInput so route tests
* exercising the reliable-delivery path behave like production. */
private _appliedInputSeq = new Map<string, number>();
forgetInputSeq(clientId: string, seq: number): void {
if (this._appliedInputSeq.get(clientId) === seq) this._appliedInputSeq.set(clientId, seq - 1);
}
shouldApplyInput(clientId: string, seq: number): boolean {
const last = this._appliedInputSeq.get(clientId);
if (last !== undefined && seq <= last) return false;
this._appliedInputSeq.set(clientId, seq);
return true;
}
/** Get the last written data */
get lastWrite(): string | undefined {
return this.writeBuffer[this.writeBuffer.length - 1];
}
/** Clear the write buffer */
clearWriteBuffer(): void {
this.writeBuffer = [];
}
/** Check if a specific command was written */
hasWritten(pattern: string | RegExp): boolean {
return this.writeBuffer.some((data) => (typeof pattern === 'string' ? data.includes(pattern) : pattern.test(data)));
}
// ========== Terminal Output Simulation ==========
/** Simulate raw terminal output */
simulateTerminalOutput(data: string): void {
this.terminalBuffer += data;
this.emit('terminal', data);
}
/** Simulate prompt appearing (legacy fallback signal) */
simulatePrompt(): void {
this.simulateTerminalOutput('\u276f ');
this.status = 'idle';
this.emit('idle');
}
/** Simulate ready state with definitive indicator (legacy) */
simulateReady(): void {
this.simulateTerminalOutput('\u21b5 send');
this.status = 'idle';
this.emit('idle');
}
/**
* Simulate completion message (primary idle detection in Claude Code 2024+).
* This triggers the multi-layer detection flow.
*/
simulateCompletionMessage(duration: string = '2m 46s'): void {
this.simulateTerminalOutput(`\u273b Worked for ${duration}`);
this.status = 'idle';
}
/** Simulate working state with spinner */
simulateWorking(text: string = 'Thinking'): void {
this.simulateTerminalOutput(`${text}... \u280b`);
// 'busy' is what the real Session sets while a turn is in flight; the old
// 'working' here was the event name, not a status value.
this.status = 'busy';
this.emit('working');
}
/** Simulate /clear completion */
simulateClearComplete(): void {
this.simulateTerminalOutput('conversation cleared');
setTimeout(() => this.simulateCompletionMessage(), 50);
}
/** Simulate /init completion */
simulateInitComplete(): void {
this.simulateTerminalOutput('Analyzing CLAUDE.md...');
setTimeout(() => this.simulateCompletionMessage(), 100);
}
/**
* Simulate plan mode approval prompt.
* This triggers auto-accept detection.
*/
simulatePlanModePrompt(): void {
this.simulateTerminalOutput(
'Would you like to proceed with this plan?\n' + '\u276f 1. Yes\n' + ' 2. No\n' + ' 3. Type your own\n'
);
}
/**
* Simulate elicitation dialog (AskUserQuestion).
* This should block auto-accept.
*/
simulateElicitationDialog(): void {
this.simulateTerminalOutput('What would you like to name the new file?\n' + '> ');
}
/** Simulate token count display */
simulateTokenCount(tokens: number | string): void {
const formatted =
typeof tokens === 'number' ? (tokens >= 1000 ? `${(tokens / 1000).toFixed(1)}k` : String(tokens)) : tokens;
this.simulateTerminalOutput(`${formatted} tokens used`);
}
/** Simulate ANSI escape codes */
simulateAnsiOutput(text: string, color: 'green' | 'red' | 'blue' = 'green'): void {
const codes: Record<string, string> = {
green: '\x1b[32m',
red: '\x1b[31m',
blue: '\x1b[34m',
};
this.simulateTerminalOutput(`${codes[color]}${text}\x1b[0m`);
}
/** Clear terminal buffer */
clearTerminalBuffer(): void {
this.terminalBuffer = '';
}
// ========== Session Lifecycle ==========
/** Simulate session closing */
close(): void {
this.emit('exit', 0);
this.removeAllListeners();
}
/** Get mux name (for mux-based operations) */
get muxName(): string | null {
return this._muxName;
}
/**
* Mirrors `Session.usesMux`. True by default because that is the normal
* configuration, and it is what makes a route's pane-liveness probe reachable:
* `session.pid` is the tmux ATTACH CLIENT, so a mux-backed session's worker can be
* dead while `pid` is still a live number.
*/
usesMux: boolean = true;
/** Check for active child processes (mock returns configurable list) */
getActiveChildProcesses(): { pid: number; command: string }[] {
return this._activeChildProcesses;
}
/** Set active child processes for testing */
setActiveChildProcesses(processes: { pid: number; command: string }[]): void {
this._activeChildProcesses = processes;
}
// ========== Route-test conveniences ==========
/** Session display name */
name: string = 'test-session';
/** Session color tag */
color: string = 'default';
/** CLI mode */
mode: string = 'claude';
/** Text output buffer (stripped of ANSI) */
textOutput: string = '';
/** Structured messages */
messages: unknown[] = [];
/** Error buffer */
errorBuffer: string = '';
/** Ralph loop state */
ralphLoopState: Record<string, unknown> | null = null;
/** Ralph todo items */
ralphTodos: unknown[] = [];
/** Ralph todo statistics */
ralphTodoStats: Record<string, unknown> = {};
/** Currently active tools */
activeTools: unknown[] = [];
/** Token tracking */
inputTokens: number = 0;
outputTokens: number = 0;
totalCost: number = 0;
/** Terminal buffer byte length */
get terminalBufferLength(): number {
return this.terminalBuffer.length;
}
/** Return a state-like object for route handlers */
toState(): Record<string, unknown> {
return {
id: this.id,
workingDir: this.workingDir,
status: this.status,
name: this.name,
color: this.color,
mode: this.mode,
muxName: this._muxName,
pinned: this.pinned || undefined,
pinnedAt: this.pinned ? (this.pinnedAt ?? undefined) : undefined,
};
}
/** Auto-resume on usage limit (token pause control) */
autoResumeEnabled: boolean = false;
autoResumeAt: number | null = null;
isLimitPaused: boolean = false;
setAutoResume = vi.fn((enabled: boolean) => {
this.autoResumeEnabled = enabled;
if (!enabled) this.autoResumeAt = null;
});
/** Pin state (COD-139) */
pinned: boolean = false;
pinnedAt: number | null = null;
setPinned = vi.fn((pinned: boolean) => {
this.pinned = pinned;
this.pinnedAt = pinned ? Date.now() : null;
});
/** Check if session is busy */
isBusy = vi.fn(() => false);
/** Set session color */
setColor = vi.fn((c: string) => {
this.color = c;
});
/** Custom Model Endpoint Profiles (docs/custom-model-endpoints-plan.md) */
customModel: { endpointId: string; modelId: string; label?: string } | undefined = undefined;
remote: unknown = undefined;
docker: unknown = undefined;
private _mockCustomModel:
| {
endpointId: string;
modelId: string;
label?: string;
envKeys: string[];
configDir?: string;
launchModel?: string;
}
| undefined;
setCustomModel = vi.fn(
(
next:
| {
endpointId: string;
modelId: string;
label?: string;
envKeys: string[];
configDir?: string;
launchModel?: string;
}
| undefined,
_envOverrides?: Record<string, string>
): { removedEnvKeys: string[]; previousConfigDir: string | undefined } => {
const previous = this._mockCustomModel;
this._mockCustomModel = next;
this.customModel = next ? { endpointId: next.endpointId, modelId: next.modelId, label: next.label } : undefined;
return { removedEnvKeys: previous?.envKeys ?? [], previousConfigDir: previous?.configDir };
}
);
restartCli = vi.fn(async () => true);
getCustomModelForPersist = vi.fn(() => this._mockCustomModel);
/** Mirrors Session.noteReportedModel: the statusline route records the CLI's model. */
reportedModel: { model: string; source: 'statusline' | 'screen' } | null = null;
noteReportedModel = vi.fn((source: 'statusline' | 'screen', raw: unknown): boolean => {
if (typeof raw !== 'string' || !raw.trim()) return false;
if (this.reportedModel?.model === raw && this.reportedModel.source === source) return false;
this.reportedModel = { model: raw, source };
return true;
});
/** Stub for sendInput */
sendInput = vi.fn();
/** Stub for resize */
resize = vi.fn();
/** Stubs for the desktop sizing claims used by resize arbitration */
claimDesktopSizing = vi.fn();
releaseDesktopSizing = vi.fn();
noteDesktopActivity = vi.fn();
/** Stub for runPrompt */
runPrompt = vi.fn(async () => {});
/** Stub for startInteractive */
startInteractive = vi.fn(async () => {});
/** Stub for resetRespawnBreaker (COD-118) */
resetRespawnBreaker = vi.fn();
/** Stub for startShell */
startShell = vi.fn(async () => {});
/** Stub for compact */
compact = vi.fn();
/** Stub for getTextOutput */
getTextOutput = vi.fn(() => '');
/** Stub for getMessages */
getMessages = vi.fn(() => []);
}
/**
* Generate realistic terminal output for testing.
* Must match the patterns used in MockSession's simulate* methods.
*/
export const terminalOutputs = {
/** Standard completion message */
completion(duration: string = '2m 46s'): string {
return `\n\u273b Worked for ${duration}\n 123.4k tokens used\n`;
},
/** Working spinner output */
working(activity: string = 'Thinking'): string {
return `${activity}... \u280b`;
},
/** Plan mode prompt */
planMode(question: string = 'Would you like to proceed?'): string {
return [`\n${question}\n`, '\u276f 1. Yes\n', ' 2. No\n', ' 3. Type your own\n'].join('');
},
/** Prompt character */
prompt(): string {
return '\n\u276f ';
},
/** Token count display */
tokens(count: number): string {
const formatted =
count >= 1000000
? `${(count / 1000000).toFixed(1)}M`
: count >= 1000
? `${(count / 1000).toFixed(1)}k`
: String(count);
return ` ${formatted} tokens\n`;
},
/** Large output for buffer testing */
largeOutput(sizeKb: number = 100): string {
const baseText = 'Lorem ipsum dolor sit amet. '.repeat(100);
const repetitions = Math.ceil((sizeKb * 1024) / baseText.length);
return baseText.repeat(repetitions).slice(0, sizeKb * 1024);
},
/** ANSI colored output */
ansiColored(text: string): string {
return `\x1b[32m${text}\x1b[0m`;
},
};
/**
* Convenience factory.
*/
export function createMockSession(id?: string): MockSession {
return new MockSession(id);
}