|
|
|
@@ -0,0 +1,796 @@
|
|
|
|
|
import { afterEach, describe, expect, it, vi } from 'vitest';
|
|
|
|
|
|
|
|
|
|
interface FakeEntry {
|
|
|
|
|
type: string;
|
|
|
|
|
customType?: string;
|
|
|
|
|
data?: unknown;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
interface SentMessage {
|
|
|
|
|
message: {
|
|
|
|
|
customType: string;
|
|
|
|
|
content: string;
|
|
|
|
|
display: boolean;
|
|
|
|
|
};
|
|
|
|
|
options?: {
|
|
|
|
|
triggerTurn?: boolean;
|
|
|
|
|
deliverAs?: 'steer' | 'followUp' | 'nextTurn';
|
|
|
|
|
};
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
interface FakeContext {
|
|
|
|
|
cwd: string;
|
|
|
|
|
ui: {
|
|
|
|
|
notifications: Array<{ message: string; level?: string }>;
|
|
|
|
|
statuses: Map<string, string | undefined>;
|
|
|
|
|
notify(message: string, level?: string): void;
|
|
|
|
|
setStatus(key: string, value: string | undefined): void;
|
|
|
|
|
};
|
|
|
|
|
sessionManager: {
|
|
|
|
|
getBranch(): FakeEntry[];
|
|
|
|
|
};
|
|
|
|
|
isIdle(): boolean;
|
|
|
|
|
hasPendingMessages(): boolean;
|
|
|
|
|
abort(): void;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
type EventHandler = (
|
|
|
|
|
event: Record<string, unknown>,
|
|
|
|
|
context: FakeContext,
|
|
|
|
|
) => unknown | Promise<unknown>;
|
|
|
|
|
|
|
|
|
|
type CommandHandler = (args: string, context: FakeContext) => unknown | Promise<unknown>;
|
|
|
|
|
|
|
|
|
|
interface FakeToolResult {
|
|
|
|
|
content: Array<{ type: string; text: string }>;
|
|
|
|
|
details?: unknown;
|
|
|
|
|
terminate?: boolean;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
interface FakeTool {
|
|
|
|
|
name: string;
|
|
|
|
|
execute(
|
|
|
|
|
toolCallId: string,
|
|
|
|
|
params: Record<string, unknown>,
|
|
|
|
|
signal: AbortSignal | undefined,
|
|
|
|
|
onUpdate: undefined,
|
|
|
|
|
context: FakeContext,
|
|
|
|
|
): Promise<FakeToolResult>;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
interface GoalExtensionFactory {
|
|
|
|
|
(api: FakePiApi): void;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
interface GoalExtensionModule {
|
|
|
|
|
default: GoalExtensionFactory;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
interface FakePiApi {
|
|
|
|
|
on(event: string, handler: EventHandler): void;
|
|
|
|
|
registerCommand(name: string, options: { description: string; handler: CommandHandler }): void;
|
|
|
|
|
registerTool(tool: FakeTool): void;
|
|
|
|
|
appendEntry(customType: string, data?: unknown): void;
|
|
|
|
|
sendMessage(message: SentMessage['message'], options?: SentMessage['options']): void;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
function isGoalExtensionModule(value: unknown): value is GoalExtensionModule {
|
|
|
|
|
if (typeof value !== 'object' || value === null) return false;
|
|
|
|
|
return typeof Reflect.get(value, 'default') === 'function';
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
const goalExtensionUrl = new URL('../../framework/runtime/pi/goal-extension.ts', import.meta.url)
|
|
|
|
|
.href;
|
|
|
|
|
const importedGoalExtension: unknown = await import(goalExtensionUrl);
|
|
|
|
|
if (!isGoalExtensionModule(importedGoalExtension)) {
|
|
|
|
|
throw new Error('Pi goal extension must export a default registration function');
|
|
|
|
|
}
|
|
|
|
|
const registerGoalExtension = importedGoalExtension.default;
|
|
|
|
|
|
|
|
|
|
function isRecord(value: unknown): value is Record<string, unknown> {
|
|
|
|
|
return typeof value === 'object' && value !== null && !Array.isArray(value);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
class FakePi {
|
|
|
|
|
readonly handlers = new Map<string, EventHandler[]>();
|
|
|
|
|
readonly commands = new Map<string, CommandHandler>();
|
|
|
|
|
readonly tools = new Map<string, FakeTool>();
|
|
|
|
|
readonly entries: FakeEntry[] = [];
|
|
|
|
|
readonly sentMessages: SentMessage[] = [];
|
|
|
|
|
readonly notifications: Array<{ message: string; level?: string }> = [];
|
|
|
|
|
readonly statuses = new Map<string, string | undefined>();
|
|
|
|
|
branch: FakeEntry[] = [];
|
|
|
|
|
idle = true;
|
|
|
|
|
pending = false;
|
|
|
|
|
abortCount = 0;
|
|
|
|
|
|
|
|
|
|
readonly context: FakeContext = {
|
|
|
|
|
cwd: '/tmp/project',
|
|
|
|
|
ui: {
|
|
|
|
|
notifications: this.notifications,
|
|
|
|
|
statuses: this.statuses,
|
|
|
|
|
notify: (message: string, level?: string): void => {
|
|
|
|
|
this.notifications.push({ message, level });
|
|
|
|
|
},
|
|
|
|
|
setStatus: (key: string, value: string | undefined): void => {
|
|
|
|
|
this.statuses.set(key, value);
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
sessionManager: {
|
|
|
|
|
getBranch: (): FakeEntry[] => [...this.branch],
|
|
|
|
|
},
|
|
|
|
|
isIdle: (): boolean => this.idle,
|
|
|
|
|
hasPendingMessages: (): boolean => this.pending,
|
|
|
|
|
abort: (): void => {
|
|
|
|
|
this.abortCount += 1;
|
|
|
|
|
},
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
readonly api: FakePiApi = {
|
|
|
|
|
on: (event: string, handler: EventHandler): void => {
|
|
|
|
|
this.handlers.set(event, [...(this.handlers.get(event) ?? []), handler]);
|
|
|
|
|
},
|
|
|
|
|
registerCommand: (
|
|
|
|
|
name: string,
|
|
|
|
|
options: { description: string; handler: CommandHandler },
|
|
|
|
|
): void => {
|
|
|
|
|
this.commands.set(name, options.handler);
|
|
|
|
|
},
|
|
|
|
|
registerTool: (tool: FakeTool): void => {
|
|
|
|
|
this.tools.set(tool.name, tool);
|
|
|
|
|
},
|
|
|
|
|
appendEntry: (customType: string, data?: unknown): void => {
|
|
|
|
|
const entry: FakeEntry = { type: 'custom', customType, data };
|
|
|
|
|
this.entries.push(entry);
|
|
|
|
|
this.branch.push(entry);
|
|
|
|
|
},
|
|
|
|
|
sendMessage: (message: SentMessage['message'], options?: SentMessage['options']): void => {
|
|
|
|
|
this.sentMessages.push({ message, options });
|
|
|
|
|
},
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
constructor(initialBranch: FakeEntry[] = []) {
|
|
|
|
|
this.branch = [...initialBranch];
|
|
|
|
|
registerGoalExtension(this.api);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
async emit(event: string, value: Record<string, unknown> = {}): Promise<unknown[]> {
|
|
|
|
|
const results: unknown[] = [];
|
|
|
|
|
for (const handler of this.handlers.get(event) ?? []) {
|
|
|
|
|
results.push(await handler(value, this.context));
|
|
|
|
|
}
|
|
|
|
|
return results;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
async goal(args: string): Promise<void> {
|
|
|
|
|
const handler = this.commands.get('goal');
|
|
|
|
|
if (handler === undefined) throw new Error('/goal was not registered');
|
|
|
|
|
await handler(args, this.context);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
async report(params: Record<string, unknown>): Promise<FakeToolResult> {
|
|
|
|
|
const tool = this.tools.get('mosaic_goal_report');
|
|
|
|
|
if (tool === undefined) throw new Error('mosaic_goal_report was not registered');
|
|
|
|
|
return await tool.execute('goal-report-1', params, undefined, undefined, this.context);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
function latestGoalStateData(pi: FakePi): Record<string, unknown> {
|
|
|
|
|
for (let index = pi.entries.length - 1; index >= 0; index -= 1) {
|
|
|
|
|
const entry = pi.entries[index];
|
|
|
|
|
if (entry?.customType === 'mosaic-goal-state' && isRecord(entry.data)) return entry.data;
|
|
|
|
|
}
|
|
|
|
|
throw new Error('No persisted Mosaic goal state found');
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
function stateField(pi: FakePi, field: string): unknown {
|
|
|
|
|
return latestGoalStateData(pi)[field];
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
function activeGoalStatementFromContext(result: unknown): string {
|
|
|
|
|
if (!isRecord(result)) throw new Error('Context handler did not return an object');
|
|
|
|
|
const messages = result['messages'];
|
|
|
|
|
if (!Array.isArray(messages)) throw new Error('Context result did not include messages');
|
|
|
|
|
const goalMessage = messages.find(
|
|
|
|
|
(message: unknown): boolean =>
|
|
|
|
|
isRecord(message) && message['customType'] === 'mosaic-goal-context',
|
|
|
|
|
);
|
|
|
|
|
if (!isRecord(goalMessage) || typeof goalMessage['content'] !== 'string') {
|
|
|
|
|
throw new Error('Goal context message was not injected');
|
|
|
|
|
}
|
|
|
|
|
return goalMessage['content'];
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
afterEach(() => {
|
|
|
|
|
vi.useRealTimers();
|
|
|
|
|
vi.unstubAllEnvs();
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
describe('Mosaic Pi goal extension commands', () => {
|
|
|
|
|
it('shows help and handles controls safely when no goal exists', async () => {
|
|
|
|
|
const pi = new FakePi();
|
|
|
|
|
|
|
|
|
|
await pi.goal('');
|
|
|
|
|
expect(pi.notifications.at(-1)?.message).toContain('/goal set');
|
|
|
|
|
await pi.goal('status');
|
|
|
|
|
expect(pi.notifications.at(-1)?.message).toContain('No Mosaic goal is set');
|
|
|
|
|
|
|
|
|
|
for (const command of ['pause', 'resume', 'cancel']) {
|
|
|
|
|
await pi.goal(command);
|
|
|
|
|
expect(pi.notifications.at(-1)?.level).toBe('warning');
|
|
|
|
|
}
|
|
|
|
|
expect(pi.entries).toHaveLength(0);
|
|
|
|
|
expect(pi.sentMessages).toHaveLength(0);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('sets, reports, pauses, resumes, and cancels a bounded goal', async () => {
|
|
|
|
|
const pi = new FakePi();
|
|
|
|
|
|
|
|
|
|
await pi.goal('set Deliver the local goal extension with tests');
|
|
|
|
|
expect(stateField(pi, 'phase')).toBe('active');
|
|
|
|
|
expect(stateField(pi, 'statement')).toBe('Deliver the local goal extension with tests');
|
|
|
|
|
expect(pi.sentMessages).toHaveLength(1);
|
|
|
|
|
expect(pi.sentMessages[0]?.options?.triggerTurn).toBe(true);
|
|
|
|
|
|
|
|
|
|
await pi.goal('status');
|
|
|
|
|
expect(pi.notifications.at(-1)?.message).toContain('Deliver the local goal extension');
|
|
|
|
|
expect(pi.notifications.at(-1)?.message).toContain('active');
|
|
|
|
|
|
|
|
|
|
await pi.goal('pause');
|
|
|
|
|
expect(stateField(pi, 'phase')).toBe('paused');
|
|
|
|
|
pi.sentMessages.length = 0;
|
|
|
|
|
await pi.emit('agent_settled');
|
|
|
|
|
expect(pi.sentMessages).toHaveLength(0);
|
|
|
|
|
|
|
|
|
|
await pi.goal('resume');
|
|
|
|
|
expect(stateField(pi, 'phase')).toBe('active');
|
|
|
|
|
expect(pi.sentMessages).toHaveLength(1);
|
|
|
|
|
|
|
|
|
|
await pi.goal('cancel');
|
|
|
|
|
expect(stateField(pi, 'phase')).toBe('cancelled');
|
|
|
|
|
pi.sentMessages.length = 0;
|
|
|
|
|
await pi.emit('agent_settled');
|
|
|
|
|
expect(pi.sentMessages).toHaveLength(0);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('accepts /goal <statement> shorthand but refuses to replace an active goal', async () => {
|
|
|
|
|
const pi = new FakePi();
|
|
|
|
|
|
|
|
|
|
await pi.goal('First goal');
|
|
|
|
|
const firstGoalId = stateField(pi, 'goalId');
|
|
|
|
|
await pi.goal('set Second goal');
|
|
|
|
|
|
|
|
|
|
expect(stateField(pi, 'goalId')).toBe(firstGoalId);
|
|
|
|
|
expect(stateField(pi, 'statement')).toBe('First goal');
|
|
|
|
|
expect(pi.notifications.at(-1)?.level).toBe('warning');
|
|
|
|
|
expect(pi.notifications.at(-1)?.message).toContain('/goal cancel');
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('rejects invalid phase transitions, aborts busy work, and supports clear as cancel', async () => {
|
|
|
|
|
const pi = new FakePi();
|
|
|
|
|
await pi.goal('set Preserve transition safety');
|
|
|
|
|
|
|
|
|
|
await pi.goal('resume');
|
|
|
|
|
expect(pi.notifications.at(-1)?.message).toContain('cannot be resumed');
|
|
|
|
|
pi.idle = false;
|
|
|
|
|
await pi.goal('pause maintenance window');
|
|
|
|
|
expect(stateField(pi, 'stopReason')).toBe('maintenance window');
|
|
|
|
|
expect(pi.abortCount).toBe(1);
|
|
|
|
|
await pi.goal('pause');
|
|
|
|
|
expect(pi.notifications.at(-1)?.message).toContain('cannot be paused');
|
|
|
|
|
await pi.goal('clear');
|
|
|
|
|
expect(stateField(pi, 'phase')).toBe('cancelled');
|
|
|
|
|
expect(pi.abortCount).toBe(2);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('rejects empty and oversized goal statements without starting a run', async () => {
|
|
|
|
|
const pi = new FakePi();
|
|
|
|
|
|
|
|
|
|
await pi.goal('set');
|
|
|
|
|
await pi.goal(`set ${'x'.repeat(8_001)}`);
|
|
|
|
|
|
|
|
|
|
expect(pi.entries).toHaveLength(0);
|
|
|
|
|
expect(pi.sentMessages).toHaveLength(0);
|
|
|
|
|
expect(pi.notifications.at(-1)?.level).toBe('warning');
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
describe('Mosaic Pi goal lifecycle', () => {
|
|
|
|
|
it('injects one fresh active contract before every model context', async () => {
|
|
|
|
|
const pi = new FakePi();
|
|
|
|
|
await pi.goal('set Keep the agent oriented');
|
|
|
|
|
|
|
|
|
|
const existingGoalContext = {
|
|
|
|
|
role: 'custom',
|
|
|
|
|
customType: 'mosaic-goal-context',
|
|
|
|
|
content: 'stale',
|
|
|
|
|
};
|
|
|
|
|
const existingContinuation = {
|
|
|
|
|
role: 'custom',
|
|
|
|
|
customType: 'mosaic-goal-continuation',
|
|
|
|
|
content: 'stale continuation',
|
|
|
|
|
};
|
|
|
|
|
const first = await pi.emit('context', {
|
|
|
|
|
messages: [existingGoalContext, existingContinuation],
|
|
|
|
|
});
|
|
|
|
|
const second = await pi.emit('context', { messages: [] });
|
|
|
|
|
|
|
|
|
|
expect(activeGoalStatementFromContext(first[0])).toContain('Keep the agent oriented');
|
|
|
|
|
expect(activeGoalStatementFromContext(first[0])).toContain('mosaic_goal_report');
|
|
|
|
|
expect(activeGoalStatementFromContext(first[0])).not.toContain('stale');
|
|
|
|
|
if (!isRecord(first[0]) || !Array.isArray(first[0]['messages'])) {
|
|
|
|
|
throw new Error('Expected filtered context messages');
|
|
|
|
|
}
|
|
|
|
|
expect(first[0]['messages']).toHaveLength(1);
|
|
|
|
|
expect(activeGoalStatementFromContext(second[0])).toContain('Keep the agent oriented');
|
|
|
|
|
|
|
|
|
|
await pi.goal('cancel');
|
|
|
|
|
expect(
|
|
|
|
|
await pi.emit('context', {
|
|
|
|
|
messages: [existingGoalContext, existingContinuation],
|
|
|
|
|
}),
|
|
|
|
|
).toEqual([{ messages: [] }]);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('lets an existing busy run adopt the goal and waits behind a pending message', async () => {
|
|
|
|
|
const busy = new FakePi();
|
|
|
|
|
busy.idle = false;
|
|
|
|
|
await busy.goal('set Join the current run safely');
|
|
|
|
|
expect(busy.sentMessages).toHaveLength(0);
|
|
|
|
|
|
|
|
|
|
busy.pending = true;
|
|
|
|
|
await busy.emit('agent_settled');
|
|
|
|
|
expect(busy.sentMessages).toHaveLength(0);
|
|
|
|
|
busy.pending = false;
|
|
|
|
|
busy.idle = true;
|
|
|
|
|
await busy.emit('agent_settled');
|
|
|
|
|
expect(busy.sentMessages).toHaveLength(1);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('records every turn and continues once when an active run settles', async () => {
|
|
|
|
|
const pi = new FakePi();
|
|
|
|
|
await pi.goal('set Finish all acceptance criteria');
|
|
|
|
|
pi.sentMessages.length = 0;
|
|
|
|
|
|
|
|
|
|
await pi.emit('turn_end', { turnIndex: 0, message: {}, toolResults: [] });
|
|
|
|
|
expect(stateField(pi, 'turnCount')).toBe(1);
|
|
|
|
|
expect(stateField(pi, 'lastCheckSource')).toBe('turn');
|
|
|
|
|
|
|
|
|
|
await pi.emit('agent_settled');
|
|
|
|
|
await pi.emit('agent_settled');
|
|
|
|
|
expect(pi.sentMessages).toHaveLength(1);
|
|
|
|
|
expect(pi.sentMessages[0]?.message.content).toContain('Goal remains active');
|
|
|
|
|
|
|
|
|
|
await pi.emit('agent_start');
|
|
|
|
|
await pi.emit('agent_settled');
|
|
|
|
|
expect(pi.sentMessages).toHaveLength(2);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('requires two consecutive evidence-bearing achievement reports', async () => {
|
|
|
|
|
const pi = new FakePi();
|
|
|
|
|
await pi.goal('set Prove the feature works');
|
|
|
|
|
pi.sentMessages.length = 0;
|
|
|
|
|
|
|
|
|
|
const first = await pi.report({
|
|
|
|
|
status: 'achieved',
|
|
|
|
|
summary: 'Focused tests pass',
|
|
|
|
|
evidence: ['pnpm test: 12 passed'],
|
|
|
|
|
});
|
|
|
|
|
expect(first.terminate).toBe(true);
|
|
|
|
|
expect(stateField(pi, 'phase')).toBe('verifying');
|
|
|
|
|
expect(stateField(pi, 'verificationPasses')).toBe(1);
|
|
|
|
|
|
|
|
|
|
await pi.emit('agent_settled');
|
|
|
|
|
expect(pi.sentMessages).toHaveLength(1);
|
|
|
|
|
expect(pi.sentMessages[0]?.message.content).toContain('verification pass');
|
|
|
|
|
|
|
|
|
|
await pi.emit('agent_start');
|
|
|
|
|
const second = await pi.report({
|
|
|
|
|
status: 'achieved',
|
|
|
|
|
summary: 'Independent recheck confirms completion',
|
|
|
|
|
evidence: ['rerun: 12 passed', 'framework path verified'],
|
|
|
|
|
});
|
|
|
|
|
expect(second.terminate).toBe(true);
|
|
|
|
|
expect(stateField(pi, 'phase')).toBe('achieved');
|
|
|
|
|
expect(stateField(pi, 'verificationPasses')).toBe(2);
|
|
|
|
|
|
|
|
|
|
pi.sentMessages.length = 0;
|
|
|
|
|
await pi.emit('agent_settled');
|
|
|
|
|
expect(pi.sentMessages).toHaveLength(0);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('rejects malformed progress reports and reports submitted without an active goal', async () => {
|
|
|
|
|
const noGoal = new FakePi();
|
|
|
|
|
await expect(
|
|
|
|
|
noGoal.report({ status: 'continue', summary: 'work', evidence: [] }),
|
|
|
|
|
).rejects.toThrow(/No active Mosaic goal/);
|
|
|
|
|
|
|
|
|
|
const pi = new FakePi();
|
|
|
|
|
await pi.goal('set Validate report boundaries');
|
|
|
|
|
const invalidReports: Record<string, unknown>[] = [
|
|
|
|
|
{},
|
|
|
|
|
{ status: 'invalid', summary: 'work', evidence: [] },
|
|
|
|
|
{ status: 'continue', evidence: [] },
|
|
|
|
|
{ status: 'continue', summary: ' ', evidence: [] },
|
|
|
|
|
{ status: 'continue', summary: 'x'.repeat(2_001), evidence: [] },
|
|
|
|
|
{ status: 'continue', summary: 'work', evidence: 'not-an-array' },
|
|
|
|
|
{ status: 'continue', summary: 'work', evidence: Array.from({ length: 21 }, () => 'x') },
|
|
|
|
|
{ status: 'continue', summary: 'work', evidence: [4] },
|
|
|
|
|
{ status: 'continue', summary: 'work', evidence: [''] },
|
|
|
|
|
{ status: 'continue', summary: 'work', evidence: ['x'.repeat(1_001)] },
|
|
|
|
|
{ status: 'continue', summary: 'work', evidence: [], nextStep: 4 },
|
|
|
|
|
{ status: 'continue', summary: 'work', evidence: [], nextStep: ' ' },
|
|
|
|
|
{ status: 'continue', summary: 'work', evidence: [], nextStep: 'x'.repeat(2_001) },
|
|
|
|
|
];
|
|
|
|
|
for (const report of invalidReports) {
|
|
|
|
|
await expect(pi.report(report)).rejects.toThrow();
|
|
|
|
|
}
|
|
|
|
|
expect(stateField(pi, 'phase')).toBe('active');
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('rejects an achievement claim without evidence', async () => {
|
|
|
|
|
const pi = new FakePi();
|
|
|
|
|
await pi.goal('set Require evidence');
|
|
|
|
|
|
|
|
|
|
await expect(
|
|
|
|
|
pi.report({ status: 'achieved', summary: 'Trust me', evidence: [] }),
|
|
|
|
|
).rejects.toThrow(/evidence/i);
|
|
|
|
|
expect(stateField(pi, 'phase')).toBe('active');
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('redacts credential-shaped goal and report text before persistence or display', async () => {
|
|
|
|
|
const githubToken = `ghp_${'a'.repeat(32)}`;
|
|
|
|
|
const anthropicKey = `sk-ant-api03-${'b'.repeat(40)}`;
|
|
|
|
|
const bearerToken = 'header.payload.signature-canary';
|
|
|
|
|
const databaseUrl = 'postgresql://mosaic:[email protected]/mosaic';
|
|
|
|
|
const password = 'password-canary';
|
|
|
|
|
const pi = new FakePi();
|
|
|
|
|
|
|
|
|
|
await pi.goal(`set Rotate ${githubToken} without retaining it`);
|
|
|
|
|
const context = await pi.emit('context', { messages: [] });
|
|
|
|
|
expect(activeGoalStatementFromContext(context[0])).not.toContain(githubToken);
|
|
|
|
|
|
|
|
|
|
const result = await pi.report({
|
|
|
|
|
status: 'achieved',
|
|
|
|
|
summary: `Validated ${anthropicKey}`,
|
|
|
|
|
evidence: [`Authorization: Bearer ${bearerToken}`, `DATABASE_URL=${databaseUrl}`],
|
|
|
|
|
nextStep: `password=${password}`,
|
|
|
|
|
});
|
|
|
|
|
await pi.goal('status');
|
|
|
|
|
|
|
|
|
|
const persisted = JSON.stringify(latestGoalStateData(pi));
|
|
|
|
|
const displayed = pi.notifications.at(-1)?.message ?? '';
|
|
|
|
|
const toolOutput = JSON.stringify(result);
|
|
|
|
|
for (const secret of [githubToken, anthropicKey, bearerToken, databaseUrl, password]) {
|
|
|
|
|
expect(persisted).not.toContain(secret);
|
|
|
|
|
expect(displayed).not.toContain(secret);
|
|
|
|
|
expect(toolOutput).not.toContain(secret);
|
|
|
|
|
}
|
|
|
|
|
expect(persisted).toContain('[REDACTED-SECRET]');
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('preserves ordinary typed fields that resemble sensitive assignment names', async () => {
|
|
|
|
|
const typedFields = 'token: string, password: boolean, secret: false';
|
|
|
|
|
const pi = new FakePi();
|
|
|
|
|
|
|
|
|
|
await pi.goal(`set Preserve TypeScript fields: ${typedFields}`);
|
|
|
|
|
await pi.report({
|
|
|
|
|
status: 'continue',
|
|
|
|
|
summary: `Schema still contains ${typedFields}`,
|
|
|
|
|
evidence: [`interface Config { ${typedFields} }`],
|
|
|
|
|
nextStep: `Keep ${typedFields} unchanged`,
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
expect(stateField(pi, 'statement')).toContain(typedFields);
|
|
|
|
|
expect(JSON.stringify(stateField(pi, 'lastReport'))).toContain(typedFields);
|
|
|
|
|
expect(JSON.stringify(latestGoalStateData(pi))).not.toContain('[REDACTED-SECRET]');
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('stops autonomous continuation when the max-turn limit is reached', async () => {
|
|
|
|
|
vi.stubEnv('MOSAIC_GOAL_MAX_TURNS', '2');
|
|
|
|
|
const pi = new FakePi();
|
|
|
|
|
await pi.goal('set Bound this run');
|
|
|
|
|
pi.sentMessages.length = 0;
|
|
|
|
|
|
|
|
|
|
await pi.emit('turn_end', { turnIndex: 0, message: {}, toolResults: [] });
|
|
|
|
|
await pi.emit('turn_end', { turnIndex: 1, message: {}, toolResults: [] });
|
|
|
|
|
|
|
|
|
|
expect(stateField(pi, 'phase')).toBe('exhausted');
|
|
|
|
|
expect(pi.abortCount).toBe(1);
|
|
|
|
|
await pi.emit('agent_settled');
|
|
|
|
|
expect(pi.sentMessages).toHaveLength(0);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('resets the no-progress sequence when a continuation report changes', async () => {
|
|
|
|
|
const pi = new FakePi();
|
|
|
|
|
await pi.goal('set Track changing progress');
|
|
|
|
|
|
|
|
|
|
await pi.report({
|
|
|
|
|
status: 'continue',
|
|
|
|
|
summary: 'First checkpoint',
|
|
|
|
|
evidence: ['file A changed'],
|
|
|
|
|
nextStep: 'Run focused tests',
|
|
|
|
|
});
|
|
|
|
|
await pi.report({
|
|
|
|
|
status: 'continue',
|
|
|
|
|
summary: 'Second checkpoint',
|
|
|
|
|
evidence: ['focused tests passed'],
|
|
|
|
|
nextStep: 'Review the diff',
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
expect(stateField(pi, 'phase')).toBe('active');
|
|
|
|
|
expect(stateField(pi, 'noProgressReports')).toBe(1);
|
|
|
|
|
await pi.goal('status');
|
|
|
|
|
expect(pi.notifications.at(-1)?.message).toContain('Next step: Review the diff');
|
|
|
|
|
expect(pi.notifications.at(-1)?.message).toContain('focused tests passed');
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('stops after a bounded number of identical no-progress reports', async () => {
|
|
|
|
|
vi.stubEnv('MOSAIC_GOAL_MAX_NO_PROGRESS', '2');
|
|
|
|
|
const pi = new FakePi();
|
|
|
|
|
await pi.goal('set Detect stalled work');
|
|
|
|
|
|
|
|
|
|
const report = {
|
|
|
|
|
status: 'continue',
|
|
|
|
|
summary: 'No change yet',
|
|
|
|
|
evidence: ['same observation'],
|
|
|
|
|
nextStep: 'Try again',
|
|
|
|
|
};
|
|
|
|
|
await pi.report(report);
|
|
|
|
|
await pi.report(report);
|
|
|
|
|
|
|
|
|
|
expect(stateField(pi, 'phase')).toBe('exhausted');
|
|
|
|
|
expect(stateField(pi, 'noProgressReports')).toBe(2);
|
|
|
|
|
pi.sentMessages.length = 0;
|
|
|
|
|
await pi.emit('agent_settled');
|
|
|
|
|
expect(pi.sentMessages).toHaveLength(0);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('rejects a goal report mixed with another tool result in the same turn', async () => {
|
|
|
|
|
const pi = new FakePi();
|
|
|
|
|
await pi.goal('set Require a sole final report');
|
|
|
|
|
await pi.report({
|
|
|
|
|
status: 'achieved',
|
|
|
|
|
summary: 'Premature mixed claim',
|
|
|
|
|
evidence: ['one observation'],
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
await pi.emit('turn_end', {
|
|
|
|
|
turnIndex: 0,
|
|
|
|
|
message: {},
|
|
|
|
|
toolResults: [{ toolName: 'mosaic_goal_report' }, { toolName: 'read' }],
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
expect(stateField(pi, 'phase')).toBe('active');
|
|
|
|
|
expect(stateField(pi, 'verificationPasses')).toBe(0);
|
|
|
|
|
expect(stateField(pi, 'lastCheckOutcome')).toBe('mixed-goal-report-rejected');
|
|
|
|
|
expect(pi.notifications.at(-1)?.level).toBe('warning');
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('marks blocked reports terminal until the operator resumes', async () => {
|
|
|
|
|
const pi = new FakePi();
|
|
|
|
|
await pi.goal('set Stop on a real blocker');
|
|
|
|
|
|
|
|
|
|
await pi.report({
|
|
|
|
|
status: 'blocked',
|
|
|
|
|
summary: 'Missing required access',
|
|
|
|
|
evidence: ['provider returned 403'],
|
|
|
|
|
});
|
|
|
|
|
expect(stateField(pi, 'phase')).toBe('blocked');
|
|
|
|
|
|
|
|
|
|
pi.sentMessages.length = 0;
|
|
|
|
|
await pi.emit('agent_settled');
|
|
|
|
|
expect(pi.sentMessages).toHaveLength(0);
|
|
|
|
|
|
|
|
|
|
await pi.goal('resume');
|
|
|
|
|
expect(stateField(pi, 'phase')).toBe('active');
|
|
|
|
|
expect(stateField(pi, 'turnCount')).toBe(0);
|
|
|
|
|
expect(pi.sentMessages).toHaveLength(1);
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
describe('Mosaic Pi goal compaction and restoration', () => {
|
|
|
|
|
it('resets provisional verification and defers manual-compaction continuation until idle', async () => {
|
|
|
|
|
vi.useFakeTimers();
|
|
|
|
|
const pi = new FakePi();
|
|
|
|
|
await pi.goal('set Survive compaction');
|
|
|
|
|
await pi.report({
|
|
|
|
|
status: 'achieved',
|
|
|
|
|
summary: 'Initial claim',
|
|
|
|
|
evidence: ['focused test passed'],
|
|
|
|
|
});
|
|
|
|
|
expect(stateField(pi, 'phase')).toBe('verifying');
|
|
|
|
|
pi.sentMessages.length = 0;
|
|
|
|
|
|
|
|
|
|
await pi.emit('session_compact', { reason: 'manual', willRetry: false });
|
|
|
|
|
expect(stateField(pi, 'phase')).toBe('active');
|
|
|
|
|
expect(stateField(pi, 'verificationPasses')).toBe(0);
|
|
|
|
|
expect(stateField(pi, 'compactionCount')).toBe(1);
|
|
|
|
|
expect(stateField(pi, 'lastCheckSource')).toBe('compact');
|
|
|
|
|
expect(pi.sentMessages).toHaveLength(0);
|
|
|
|
|
|
|
|
|
|
await vi.runAllTimersAsync();
|
|
|
|
|
expect(pi.sentMessages).toHaveLength(1);
|
|
|
|
|
expect(pi.sentMessages[0]?.message.content).toContain('compaction');
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('does not re-enter an active automatic compaction and relies on the settled backstop', async () => {
|
|
|
|
|
vi.useFakeTimers();
|
|
|
|
|
const pi = new FakePi();
|
|
|
|
|
await pi.goal('set Avoid compaction races');
|
|
|
|
|
pi.sentMessages.length = 0;
|
|
|
|
|
pi.idle = false;
|
|
|
|
|
|
|
|
|
|
await pi.emit('session_compact', { reason: 'threshold', willRetry: false });
|
|
|
|
|
await vi.runAllTimersAsync();
|
|
|
|
|
expect(pi.sentMessages).toHaveLength(0);
|
|
|
|
|
|
|
|
|
|
pi.idle = true;
|
|
|
|
|
await pi.emit('agent_settled');
|
|
|
|
|
expect(pi.sentMessages).toHaveLength(1);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('restores branch-specific state on session start and tree navigation', async () => {
|
|
|
|
|
vi.useFakeTimers();
|
|
|
|
|
const source = new FakePi();
|
|
|
|
|
await source.goal('set Restore this exact branch goal');
|
|
|
|
|
const activeState = latestGoalStateData(source);
|
|
|
|
|
|
|
|
|
|
const restored = new FakePi([
|
|
|
|
|
{ type: 'custom', customType: 'mosaic-goal-state', data: activeState },
|
|
|
|
|
]);
|
|
|
|
|
await restored.emit('session_start', { reason: 'resume' });
|
|
|
|
|
expect(restored.statuses.get('mosaic-goal')).toContain('active');
|
|
|
|
|
const context = await restored.emit('context', { messages: [] });
|
|
|
|
|
expect(activeGoalStatementFromContext(context[0])).toContain('Restore this exact branch goal');
|
|
|
|
|
|
|
|
|
|
await restored.goal('pause');
|
|
|
|
|
const pausedState = latestGoalStateData(restored);
|
|
|
|
|
restored.branch = [{ type: 'custom', customType: 'mosaic-goal-state', data: pausedState }];
|
|
|
|
|
await restored.emit('session_tree', {});
|
|
|
|
|
await vi.runAllTimersAsync();
|
|
|
|
|
expect(stateField(restored, 'phase')).toBe('paused');
|
|
|
|
|
expect(restored.sentMessages).toHaveLength(0);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('restores only fully valid persisted states and ignores malformed entries', async () => {
|
|
|
|
|
vi.useFakeTimers();
|
|
|
|
|
const source = new FakePi();
|
|
|
|
|
await source.goal('set Validate persisted branch state');
|
|
|
|
|
await source.report({
|
|
|
|
|
status: 'continue',
|
|
|
|
|
summary: 'Valid report',
|
|
|
|
|
evidence: ['valid evidence'],
|
|
|
|
|
nextStep: 'Continue validation',
|
|
|
|
|
});
|
|
|
|
|
const valid = latestGoalStateData(source);
|
|
|
|
|
|
|
|
|
|
const validRestore = new FakePi([
|
|
|
|
|
{ type: 'custom', customType: 'mosaic-goal-state', data: valid },
|
|
|
|
|
]);
|
|
|
|
|
await validRestore.emit('session_start', { reason: 'resume' });
|
|
|
|
|
expect(stateField(validRestore, 'statement')).toBe('Validate persisted branch state');
|
|
|
|
|
await validRestore.emit('session_shutdown', { reason: 'reload' });
|
|
|
|
|
|
|
|
|
|
const validReport = latestGoalStateData(source)['lastReport'];
|
|
|
|
|
if (!isRecord(validReport)) throw new Error('Expected a valid persisted report fixture');
|
|
|
|
|
const integerFields = [
|
|
|
|
|
'turnCount',
|
|
|
|
|
'reportCount',
|
|
|
|
|
'verificationPasses',
|
|
|
|
|
'requiredVerificationPasses',
|
|
|
|
|
'noProgressReports',
|
|
|
|
|
'maxTurns',
|
|
|
|
|
'maxNoProgressReports',
|
|
|
|
|
'compactionCount',
|
|
|
|
|
];
|
|
|
|
|
const corruptions: Array<(state: Record<string, unknown>) => unknown> = [
|
|
|
|
|
(): unknown => null,
|
|
|
|
|
(state): unknown => ({ ...state, version: 99 }),
|
|
|
|
|
(state): unknown => ({ ...state, goalId: '' }),
|
|
|
|
|
(state): unknown => ({ ...state, statement: '' }),
|
|
|
|
|
(state): unknown => ({ ...state, statement: 'x'.repeat(8_001) }),
|
|
|
|
|
(state): unknown => ({ ...state, phase: 'unknown' }),
|
|
|
|
|
(state): unknown => ({ ...state, lastCheckSource: 'unknown' }),
|
|
|
|
|
(state): unknown => ({ ...state, startedAt: 4 }),
|
|
|
|
|
(state): unknown => ({ ...state, lastCheckAt: 4 }),
|
|
|
|
|
(state): unknown => ({ ...state, lastReport: null }),
|
|
|
|
|
(state): unknown => ({ ...state, lastProgressFingerprint: 4 }),
|
|
|
|
|
(state): unknown => ({ ...state, stopReason: 4 }),
|
|
|
|
|
...integerFields.map((field: string) => (state: Record<string, unknown>): unknown => ({
|
|
|
|
|
...state,
|
|
|
|
|
[field]: -1,
|
|
|
|
|
})),
|
|
|
|
|
];
|
|
|
|
|
|
|
|
|
|
corruptions.push(
|
|
|
|
|
(state: Record<string, unknown>): unknown => ({ ...state, maxTurns: 501 }),
|
|
|
|
|
(state: Record<string, unknown>): unknown => ({ ...state, maxNoProgressReports: 101 }),
|
|
|
|
|
(state: Record<string, unknown>): unknown => ({ ...state, requiredVerificationPasses: 3 }),
|
|
|
|
|
);
|
|
|
|
|
const reportCorruptions: Array<Record<string, unknown>> = [
|
|
|
|
|
{ ...validReport, status: 'bad' },
|
|
|
|
|
{ ...validReport, summary: '' },
|
|
|
|
|
{ ...validReport, evidence: 'bad' },
|
|
|
|
|
{ ...validReport, evidence: [4] },
|
|
|
|
|
{ ...validReport, fingerprint: '' },
|
|
|
|
|
{ ...validReport, reportedAt: '' },
|
|
|
|
|
{ ...validReport, nextStep: 4 },
|
|
|
|
|
];
|
|
|
|
|
for (const corruptReport of reportCorruptions) {
|
|
|
|
|
corruptions.push((state: Record<string, unknown>): unknown => ({
|
|
|
|
|
...state,
|
|
|
|
|
lastReport: corruptReport,
|
|
|
|
|
}));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
for (const corrupt of corruptions) {
|
|
|
|
|
const candidate = corrupt(structuredClone(valid));
|
|
|
|
|
const restored = new FakePi([
|
|
|
|
|
{ type: 'custom', customType: 'mosaic-goal-state', data: candidate },
|
|
|
|
|
]);
|
|
|
|
|
await restored.emit('session_start', { reason: 'resume' });
|
|
|
|
|
expect(restored.statuses.get('mosaic-goal')).toBeUndefined();
|
|
|
|
|
expect(await restored.emit('context', { messages: [] })).toEqual([undefined]);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
const failClosed = new FakePi([
|
|
|
|
|
{ type: 'custom', customType: 'mosaic-goal-state', data: valid },
|
|
|
|
|
{ type: 'custom', customType: 'mosaic-goal-state', data: { ...valid, version: 99 } },
|
|
|
|
|
]);
|
|
|
|
|
await failClosed.emit('session_start', { reason: 'resume' });
|
|
|
|
|
expect(failClosed.statuses.get('mosaic-goal')).toBeUndefined();
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('fails closed instead of reusing credential-bearing legacy branch state', async () => {
|
|
|
|
|
const source = new FakePi();
|
|
|
|
|
await source.goal('set Build a valid restore fixture');
|
|
|
|
|
const cleanState = latestGoalStateData(source);
|
|
|
|
|
const legacyState = structuredClone(cleanState);
|
|
|
|
|
legacyState['statement'] = `Legacy secret ghp_${'z'.repeat(32)}`;
|
|
|
|
|
|
|
|
|
|
const restored = new FakePi([
|
|
|
|
|
{ type: 'custom', customType: 'mosaic-goal-state', data: legacyState },
|
|
|
|
|
{ type: 'custom', customType: 'mosaic-goal-state', data: cleanState },
|
|
|
|
|
]);
|
|
|
|
|
await restored.emit('session_start', { reason: 'resume' });
|
|
|
|
|
|
|
|
|
|
expect(restored.statuses.get('mosaic-goal')).toBeUndefined();
|
|
|
|
|
expect(await restored.emit('context', { messages: [] })).toEqual([undefined]);
|
|
|
|
|
expect(restored.notifications.at(-1)?.level).toBe('warning');
|
|
|
|
|
expect(restored.notifications.at(-1)?.message).toContain('was not restored');
|
|
|
|
|
expect(restored.entries).toHaveLength(0);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('schedules an active tree-restored goal and preserves terminal state through compaction', async () => {
|
|
|
|
|
vi.useFakeTimers();
|
|
|
|
|
const source = new FakePi();
|
|
|
|
|
await source.goal('set Restore active tree work');
|
|
|
|
|
const active = latestGoalStateData(source);
|
|
|
|
|
|
|
|
|
|
const restored = new FakePi();
|
|
|
|
|
restored.branch = [{ type: 'custom', customType: 'mosaic-goal-state', data: active }];
|
|
|
|
|
await restored.emit('session_tree', {});
|
|
|
|
|
await vi.runAllTimersAsync();
|
|
|
|
|
expect(restored.sentMessages).toHaveLength(1);
|
|
|
|
|
expect(restored.sentMessages[0]?.message.content).toContain('tree navigation');
|
|
|
|
|
|
|
|
|
|
await restored.goal('cancel');
|
|
|
|
|
await restored.emit('session_compact', { reason: 'manual', willRetry: false });
|
|
|
|
|
expect(stateField(restored, 'phase')).toBe('cancelled');
|
|
|
|
|
expect(stateField(restored, 'compactionCount')).toBe(1);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('cancels deferred continuation when the session shuts down', async () => {
|
|
|
|
|
vi.useFakeTimers();
|
|
|
|
|
const pi = new FakePi();
|
|
|
|
|
await pi.goal('set Do not leak a stale timer');
|
|
|
|
|
pi.sentMessages.length = 0;
|
|
|
|
|
|
|
|
|
|
await pi.emit('session_compact', { reason: 'manual', willRetry: false });
|
|
|
|
|
await pi.emit('session_shutdown', { reason: 'reload' });
|
|
|
|
|
await vi.runAllTimersAsync();
|
|
|
|
|
|
|
|
|
|
expect(pi.sentMessages).toHaveLength(0);
|
|
|
|
|
});
|
|
|
|
|
});
|
Jason Woltje