openclaw/reporting-governance-plugin
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: tighten auto-chain dispatch evidence

Browse Source
This commit is contained in:
Eve
2026-04-23 20:11:49 +08:00
parent bff9146280
commit d8290b7ba2
3 changed files with 128 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
scripts/test_force_recall_long_task_preflight.mjs
View File

@@ -107,7 +107,11 @@ async function main() {
claimedExecution: true,
concreteNextAction: 'dispatch_follow_up_subagent',
autoChainNextAction: 'dispatch_follow_up_subagent',
autoChainDispatchEvidence: { sessionKey: 'task-123', dispatched: 'dispatch_follow_up_subagent' },
autoChainDispatchEvidence: {
action: 'dispatch_follow_up_subagent',
dispatched: true,
event: 'dispatch',
},
progressionClaim: 'already progressing to the next step in background',
progressEvidence: { sessionKey: 'task-123' },
});
@@ -142,6 +146,43 @@ async function main() {
assert.equal(directAutoChainFailResult.gateStatus, 'fail', 'direct evaluator should fail when explicit auto-chain action has no dispatch evidence');
assert.match(JSON.stringify(directAutoChainFailResult), /explicit auto-chain next action requires dispatched-action evidence/, 'direct evaluator fail-path should mention missing dispatched-action evidence');
const mismatchedDispatchEvidenceResult = evaluateGate({
classification: 'long_task',
claimedExecution: true,
concreteNextAction: 'dispatch_follow_up_subagent',
autoChainNextAction: 'dispatch_follow_up_subagent',
autoChainDispatchEvidence: {
action: 'dispatch_other_subagent',
dispatched: true,
event: 'dispatch',
},
});
assert.equal(mismatchedDispatchEvidenceResult.gateStatus, 'fail', 'mismatched dispatch evidence should fail');
assert.match(JSON.stringify(mismatchedDispatchEvidenceResult), /autoChainDispatchEvidence/, 'mismatched dispatch evidence should still require matching autoChainDispatchEvidence');
const fakeCheckpointDispatchEvidenceResult = evaluateGate({
classification: 'long_task',
claimedExecution: true,
concreteNextAction: 'dispatch_follow_up_subagent',
autoChainNextAction: 'dispatch_follow_up_subagent',
autoChainDispatchEvidence: {
sessionKey: 'task-123',
checkpointPath: 'checkpoints/task-123.json',
},
});
assert.equal(fakeCheckpointDispatchEvidenceResult.gateStatus, 'fail', 'checkpoint/session-only dispatch evidence should fail');
assert.match(JSON.stringify(fakeCheckpointDispatchEvidenceResult), /explicit auto-chain next action requires dispatched-action evidence/, 'checkpoint/session-only dispatch evidence should be rejected as fake dispatch evidence');
const neutralSnakeCaseResult = evaluateGate({
classification: 'long_task',
claimedExecution: true,
concreteNextAction: 'summarize findings for reply',
autoChainNextAction: 'checkpoint_session_metadata_only',
executionEvidence: { concreteNextAction: 'summarize findings for reply' },
});
assert.equal(neutralSnakeCaseResult.gateStatus, 'pass', 'neutral snake_case non-dispatch action should not trigger dispatch-evidence requirement');
assert.doesNotMatch(JSON.stringify(neutralSnakeCaseResult), /autoChainDispatchEvidence/, 'neutral snake_case non-dispatch action should not mention dispatch-evidence requirement');
const passInjected = await withPatchedWrapper(buildWrapperScript({
classification: 'long_task',
silentCandidate: true,
@@ -151,6 +192,11 @@ async function main() {
silentLaunchOk: true,
silentLaunchReason: 'checkpoint established',
requiredNextAction: 'dispatch_follow_up_subagent',
autoChainDispatchEvidence: {
action: 'dispatch_follow_up_subagent',
dispatched: true,
event: 'dispatch',
},
taskRecord: { task_name: 'task-123' },
handoff: { mode: 'direct_reply' },
}), async () => runScenario(forceRecall, requestText));