fix: require minimum continuity dispatch receipt

This commit is contained in:
Eve
2026-04-24 14:38:24 +08:00
parent 37f26727c5
commit 6b1592f066
2 changed files with 123 additions and 21 deletions

View File

@@ -3,6 +3,23 @@ import fs from 'node:fs';
const LEGAL_TERMINAL_STATES = new Set(['waiting_user', 'blocked', 'pending_verification']);
function isNonEmptyString(value) {
return typeof value === 'string' && value.trim().length > 0;
}
function isObject(value) {
return value != null && typeof value === 'object' && !Array.isArray(value);
}
function hasValidDispatchReceipt(receipt) {
if (!isObject(receipt)) return false;
if (!isNonEmptyString(receipt.planId)) return false;
if (!isNonEmptyString(receipt.currentTask)) return false;
if (!isObject(receipt.nextDerivedAction)) return false;
if (!isNonEmptyString(receipt.dispatchedAt)) return false;
return true;
}
function parseArgs(argv) {
let inputPath = null;
let compact = false;
@@ -59,7 +76,7 @@ function evaluateContinuity(payload) {
const taskComplete = payload?.taskState === 'complete';
const nextAction = payload?.nextDerivedAction ?? payload?.derivedAction ?? null;
const nextActionKnown = nextAction != null;
const hasDispatchReceipt = payload?.dispatchReceipt != null;
const hasDispatchReceipt = hasValidDispatchReceipt(payload?.dispatchReceipt ?? null);
const closureState = payload?.replyClosureState ?? null;
const isLegalTerminalState = LEGAL_TERMINAL_STATES.has(closureState);

View File

@@ -149,13 +149,11 @@ const tests = [
});
if (result.status !== 0 && result.status !== null) {
throw new Error(`expected controlled execution, got status=${result.status}
${result.stderr || result.stdout}`);
throw new Error(`expected controlled execution, got status=${result.status}\n${result.stderr || result.stdout}`);
}
if (!result.json || typeof result.json !== 'object') {
throw new Error(`expected JSON output
stdout=${result.stdout}`);
throw new Error(`expected JSON output\nstdout=${result.stdout}`);
}
if (result.json.ok !== false) {
@@ -170,6 +168,54 @@ stdout=${result.stdout}`);
}
},
},
{
name: 'continuity: fails when dispatchReceipt is a fake non-null object without minimum receipt fields',
run() {
const fixture = createFixture({
'input.json': {
planId: 'plan-fake-dispatch-receipt',
currentTask: 'task-6fake',
taskState: 'complete',
nextDerivedAction: {
type: 'message_subagent',
task: 'continue with task-7fake',
},
replyClosureState: 'completed',
dispatchReceipt: {
fake: true,
},
},
});
try {
const result = runGate({
args: ['--compact', '--input', fixture.path('input.json')],
});
if (result.status !== 0 && result.status !== null) {
throw new Error(`expected controlled execution, got status=${result.status}\n${result.stderr || result.stdout}`);
}
if (!result.json || typeof result.json !== 'object') {
throw new Error(`expected JSON output\nstdout=${result.stdout}`);
}
if (result.json.ok !== false) {
throw new Error(`expected continuity failure ok=false for fake dispatch receipt, got ${JSON.stringify(result.json)}`);
}
if (result.json.verdict !== 'continuity_failure') {
throw new Error(`expected verdict=continuity_failure for fake dispatch receipt, got ${JSON.stringify(result.json.verdict)}`);
}
if (result.json.reason !== 'missing_dispatch_receipt') {
throw new Error(`expected reason=missing_dispatch_receipt for fake dispatch receipt, got ${JSON.stringify(result.json.reason)}`);
}
} finally {
fixture.cleanup();
}
},
},
{
name: 'continuity: passes when task is complete, next action is known, and a dispatch receipt already exists',
@@ -202,13 +248,11 @@ stdout=${result.stdout}`);
});
if (result.status !== 0 && result.status !== null) {
throw new Error(`expected controlled execution, got status=${result.status}
${result.stderr || result.stdout}`);
throw new Error(`expected controlled execution, got status=${result.status}\n${result.stderr || result.stdout}`);
}
if (!result.json || typeof result.json !== 'object') {
throw new Error(`expected JSON output
stdout=${result.stdout}`);
throw new Error(`expected JSON output\nstdout=${result.stdout}`);
}
if (result.json.ok !== true) {
@@ -220,6 +264,53 @@ stdout=${result.stdout}`);
},
},
{
name: 'continuity: passes when planner returns derivedAction and a bound dispatch receipt already exists',
run() {
const fixture = createFixture({
'input.json': {
planId: 'plan-derived-action-with-bound-dispatch',
currentTask: 'task-6c',
taskState: 'complete',
derivedAction: {
type: 'message_subagent',
task: 'continue with task-7c',
},
replyClosureState: 'completed',
dispatchReceipt: {
planId: 'plan-derived-action-with-bound-dispatch',
currentTask: 'task-6c',
nextDerivedAction: {
type: 'message_subagent',
task: 'continue with task-7c',
},
dispatchedAt: '2026-04-24T12:05:00+08:00',
},
},
});
try {
const result = runGate({
args: ['--compact', '--input', fixture.path('input.json')],
});
if (result.status !== 0 && result.status !== null) {
throw new Error(`expected controlled execution, got status=${result.status}\n${result.stderr || result.stdout}`);
}
if (!result.json || typeof result.json !== 'object') {
throw new Error(`expected JSON output\nstdout=${result.stdout}`);
}
if (result.json.ok !== true) {
throw new Error(`expected continuity pass ok=true when derivedAction has bound dispatch receipt, got ${JSON.stringify(result.json)}`);
}
} finally {
fixture.cleanup();
}
},
},
{
name: 'continuity: passes when task is complete, next action is known, no dispatch receipt exists, and closure is waiting_user',
run() {
@@ -243,13 +334,11 @@ stdout=${result.stdout}`);
});
if (result.status !== 0 && result.status !== null) {
throw new Error(`expected controlled execution, got status=${result.status}
${result.stderr || result.stdout}`);
throw new Error(`expected controlled execution, got status=${result.status}\n${result.stderr || result.stdout}`);
}
if (!result.json || typeof result.json !== 'object') {
throw new Error(`expected JSON output
stdout=${result.stdout}`);
throw new Error(`expected JSON output\nstdout=${result.stdout}`);
}
if (result.json.ok !== true) {
@@ -284,13 +373,11 @@ stdout=${result.stdout}`);
});
if (result.status !== 0 && result.status !== null) {
throw new Error(`expected controlled execution, got status=${result.status}
${result.stderr || result.stdout}`);
throw new Error(`expected controlled execution, got status=${result.status}\n${result.stderr || result.stdout}`);
}
if (!result.json || typeof result.json !== 'object') {
throw new Error(`expected JSON output
stdout=${result.stdout}`);
throw new Error(`expected JSON output\nstdout=${result.stdout}`);
}
if (result.json.ok !== true) {
@@ -325,13 +412,11 @@ stdout=${result.stdout}`);
});
if (result.status !== 0 && result.status !== null) {
throw new Error(`expected controlled execution, got status=${result.status}
${result.stderr || result.stdout}`);
throw new Error(`expected controlled execution, got status=${result.status}\n${result.stderr || result.stdout}`);
}
if (!result.json || typeof result.json !== 'object') {
throw new Error(`expected JSON output
stdout=${result.stdout}`);
throw new Error(`expected JSON output\nstdout=${result.stdout}`);
}
if (result.json.ok !== true) {