singularity/singularity-forge
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

fix: prevent phantom skip loop from stale crash recovery context (#790)

Browse source 
When a crash lock references a unit from a fully-completed milestone,
crash recovery injects stale context that fights the skip-loop breaker,
creating an infinite evict/repair cycle with selfHealRuntimeRecords.

Fix 1: Validate recovered unit's milestone before synthesizing recovery
context. If the milestone has a SUMMARY file (complete), discard the
stale recovery context and clear the lock without injection.

Fix 2: Skip-loop breaker cross-checks whether the evicted unit belongs
to a completed milestone. If so, the eviction is counterproductive —
clear the skip counter and re-dispatch from fresh state instead.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Lex Christopherson 2026-03-16 22:30:15 -06:00
parent ad4e68551d
commit 0184498a44
1 changed files with 67 additions and 13 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

80
src/resources/extensions/gsd/auto.ts
View file

@ -889,23 +889,37 @@ export async function startAuto(
);
return;
}
// Stale lock from a dead process — synthesize crash recovery context.
const activityDir = join(gsdRoot(base), "activity");
const recovery = synthesizeCrashRecovery(
base, crashLock.unitType, crashLock.unitId,
crashLock.sessionFile, activityDir,
);
if (recovery && recovery.trace.toolCallCount > 0) {
pendingCrashRecovery = recovery.prompt;
// Stale lock from a dead process — validate before synthesizing recovery context.
// If the recovered unit belongs to a fully-completed milestone (SUMMARY exists),
// discard recovery context to prevent phantom skip loops (#790).
const recoveredMid = crashLock.unitId.split("/")[0];
const milestoneAlreadyComplete = recoveredMid
? !!resolveMilestoneFile(base, recoveredMid, "SUMMARY")
: false;
if (milestoneAlreadyComplete) {
ctx.ui.notify(
`${formatCrashInfo(crashLock)}\nRecovered ${recovery.trace.toolCallCount} tool calls from crashed session. Resuming with full context.`,
"warning",
`Crash recovery: discarding stale context for ${crashLock.unitId} — milestone ${recoveredMid} is already complete.`,
"info",
);
} else {
ctx.ui.notify(
`${formatCrashInfo(crashLock)}\nNo session data recovered. Resuming from disk state.`,
"warning",
const activityDir = join(gsdRoot(base), "activity");
const recovery = synthesizeCrashRecovery(
base, crashLock.unitType, crashLock.unitId,
crashLock.sessionFile, activityDir,
);
if (recovery && recovery.trace.toolCallCount > 0) {
pendingCrashRecovery = recovery.prompt;
ctx.ui.notify(
`${formatCrashInfo(crashLock)}\nRecovered ${recovery.trace.toolCallCount} tool calls from crashed session. Resuming with full context.`,
"warning",
);
} else {
ctx.ui.notify(
`${formatCrashInfo(crashLock)}\nNo session data recovered. Resuming from disk state.`,
"warning",
);
}
}
clearLock(base);
}
@ -2418,6 +2432,28 @@ async function dispatchNextUnit(
const skipCount = (unitConsecutiveSkips.get(idempotencyKey) ?? 0) + 1;
unitConsecutiveSkips.set(idempotencyKey, skipCount);
if (skipCount > MAX_CONSECUTIVE_SKIPS) {
// Cross-check: verify deriveState actually returns this unit (#790).
// If the unit's milestone is already complete, this is a phantom skip
// loop from stale crash recovery context — don't evict.
const skippedMid = unitId.split("/")[0];
const skippedMilestoneComplete = skippedMid
? !!resolveMilestoneFile(basePath, skippedMid, "SUMMARY")
: false;
if (skippedMilestoneComplete) {
// Milestone is complete — evicting this key would fight self-heal.
// Clear skip counter and re-dispatch from fresh state.
unitConsecutiveSkips.delete(idempotencyKey);
invalidateStateCache();
ctx.ui.notify(
`Phantom skip loop cleared: ${unitType} ${unitId} belongs to completed milestone ${skippedMid}. Re-dispatching from fresh state.`,
"info",
);
_skipDepth++;
await new Promise(r => setTimeout(r, 50));
await dispatchNextUnit(ctx, pi);
_skipDepth = Math.max(0, _skipDepth - 1);
return;
}
unitConsecutiveSkips.delete(idempotencyKey);
completedKeySet.delete(idempotencyKey);
removePersistedKey(basePath, idempotencyKey);
@ -2465,6 +2501,24 @@ async function dispatchNextUnit(
const skipCount2 = (unitConsecutiveSkips.get(idempotencyKey) ?? 0) + 1;
unitConsecutiveSkips.set(idempotencyKey, skipCount2);
if (skipCount2 > MAX_CONSECUTIVE_SKIPS) {
// Cross-check: verify the unit's milestone is still active (#790).
const skippedMid2 = unitId.split("/")[0];
const skippedMilestoneComplete2 = skippedMid2
? !!resolveMilestoneFile(basePath, skippedMid2, "SUMMARY")
: false;
if (skippedMilestoneComplete2) {
unitConsecutiveSkips.delete(idempotencyKey);
invalidateStateCache();
ctx.ui.notify(
`Phantom skip loop cleared: ${unitType} ${unitId} belongs to completed milestone ${skippedMid2}. Re-dispatching from fresh state.`,
"info",
);
_skipDepth++;
await new Promise(r => setTimeout(r, 50));
await dispatchNextUnit(ctx, pi);
_skipDepth = Math.max(0, _skipDepth - 1);
return;
}
unitConsecutiveSkips.delete(idempotencyKey);
completedKeySet.delete(idempotencyKey);
removePersistedKey(basePath, idempotencyKey);