Variet/gravity_control
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(bridge): approval flow robustness — pending cleanup, MERGE dedup, false positive filter, auto_resolve, 30min timeout

Browse Source
This commit is contained in:
authentik Default Admin
2026-03-10 00:35:41 +09:00
parent 7fdefb0c63
commit 373c0f7ddc
8 changed files with 340 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

108
extension/out/extension.js
View File

@@ -425,6 +425,7 @@ let observerHttpServer = null;
const pendingResponses = new Map();
// Click trigger: extension sets this, renderer polls and clicks button
let clickTrigger = null;
let sessionStalled = false; // true when session is stalled waiting for approval
// Deep inspect trigger: curl sets this, renderer picks it up and POSTs results back
let deepInspectRequested = false;
let deepInspectResult = null;
@@ -459,6 +460,22 @@ function startObserverHttpBridge() {
req.on('end', () => {
try {
const data = JSON.parse(body);
// ── Server-side false positive filter ──
const cmd = (data.command || '').trim();
const FALSE_POSITIVE_RE = /^(Proceed|Continue|Open|Close|OK|Yes|No|Save|Undo|Redo|Back|Next|More|Less|Got it)$/i;
if (FALSE_POSITIVE_RE.test(cmd)) {
logToFile(`[HTTP] filtered false positive: "${cmd}"`);
res.writeHead(200, { 'Content-Type': 'application/json' });
res.end(JSON.stringify({ ok: false, filtered: true }));
return;
}
// "Run" button → only accept if session is actually stalled (waiting for approval)
if (/^Run/i.test(cmd) && !sessionStalled) {
logToFile(`[HTTP] filtered "Run" — session not stalled`);
res.writeHead(200, { 'Content-Type': 'application/json' });
res.end(JSON.stringify({ ok: false, filtered: true }));
return;
}
const rid = data.request_id || Date.now().toString();
// Write pending file for Discord bot
const pendingDir = path.join(bridgePath, 'pending');
@@ -889,8 +906,6 @@ function generateApprovalObserverScript(_port) {
{re:/^Accept$/i, type:'agent_step'},
{re:/^Allow/i, type:'permission'},
{re:/^Approve/i, type:'agent_step'},
{re:/^Continue$/i, type:'continue'},
{re:/^Proceed$/i, type:'continue'},
{re:/^Retry$/i, type:'error_recovery'},
{re:/^Dismiss$/i, type:'error_recovery'},
];
@@ -1393,6 +1408,29 @@ function setupMonitor() {
logToFile(`[STALL-DBG] idle=${consecutiveIdleCount} modTime='${currentModTime}' changed=${modTimeChanged}`);
}
if (delta > 0) {
sessionStalled = false;
// Steps progressed — if we had a pending approval, it was handled in AG directly
if (!sawRunningAfterPending && lastPendingStepIndex >= 0) {
// Mark pending as auto_resolved so bot can update Discord message
try {
const pendingFiles = fs.readdirSync(path.join(bridgePath, 'pending'))
.filter((f) => f.endsWith('.json'));
for (const pf of pendingFiles) {
const pfPath = path.join(bridgePath, 'pending', pf);
const pd = JSON.parse(fs.readFileSync(pfPath, 'utf-8'));
if (pd.status === 'pending' && pd.step_index === lastPendingStepIndex) {
pd.status = 'auto_resolved';
fs.writeFileSync(pfPath, JSON.stringify(pd, null, 2), 'utf-8');
logToFile(`[AUTO-RESOLVE] step=${lastPendingStepIndex} progressed → marked ${pf}`);
break;
}
}
}
catch (e) {
logToFile(`[AUTO-RESOLVE] error: ${e.message}`);
}
lastPendingStepIndex = -1;
}
consecutiveIdleCount = 0;
sawRunningAfterPending = true;
stallProbed = false; // allow re-probe on next stall
@@ -1410,6 +1448,8 @@ function setupMonitor() {
else {
// lastModifiedTime frozen = real stall (approval waiting)
consecutiveIdleCount++;
if (consecutiveIdleCount >= 1)
sessionStalled = true;
}
lastModTime = currentModTime;
// ── Step probe: on stall, fetch latest step via cascadeId (retry until WAITING found) ──
@@ -1490,6 +1530,57 @@ function setupMonitor() {
// (stall fallback was generating false positives and is now redundant)
}
else if (!isRunning) {
// ── Error detection: probe when session transitions from RUNNING→idle ──
if (consecutiveIdleCount > 0 && !stallProbed) {
// Was running, now idle — possible error. Probe once.
try {
const stepsResp = await sdk.ls.rawRPC('GetCascadeTrajectorySteps', {
cascadeId: bestSessionId,
});
if (stepsResp?.steps?.length > 0) {
const steps = stepsResp.steps;
// Check last 3 steps for error/failed status
for (let si = steps.length - 1; si >= Math.max(0, steps.length - 3); si--) {
const step = steps[si];
const stepStatus = step?.status || '';
const stepType = step?.type || '';
if (stepStatus.includes('ERROR') || stepStatus.includes('FAILED')) {
const toolCall = step?.metadata?.toolCall;
const toolName = toolCall?.name || stepType.replace('CORTEX_STEP_TYPE_', '').toLowerCase();
let command = `⚠️ Error: ${toolName}`;
if (toolCall?.argumentsJson) {
try {
const args = JSON.parse(toolCall.argumentsJson);
if (args.CommandLine)
command = `⚠️ Error: ${args.CommandLine.substring(0, 100)}`;
else if (args.TargetFile)
command = `⚠️ Error: ${args.TargetFile.split(/[\\/]/).pop()}`;
}
catch { }
}
const description = `Step #${si} ${stepStatus} — Retry?`;
logToFile(`[STEP-PROBE] ★ ERROR! step=${si} status=${stepStatus} type=${stepType}`);
if (si !== lastPendingStepIndex) {
stallProbed = true;
lastPendingStepIndex = si;
writePendingApproval({
conversation_id: activeSessionId,
command,
description,
step_type: 'error_recovery',
step_index: si,
source: 'step_probe_error',
});
}
break;
}
}
}
}
catch (e) {
logToFile(`[STEP-PROBE-ERR] error check: ${e.message}`);
}
}
consecutiveIdleCount = 0;
lastModTime = currentModTime;
}
@@ -1751,7 +1842,7 @@ function writePendingApproval(data) {
if (!fs.existsSync(pendingDir)) {
fs.mkdirSync(pendingDir, { recursive: true });
}
// ── Dedup: skip if DOM observer already created a pending for same action recently ──
// ── Dedup: if DOM observer already created a "Run"-only pending, MERGE detailed info into it ──
const nowMs = Date.now();
const DEDUP_WINDOW_MS = 15_000; // 15 second dedup window
try {
@@ -1762,7 +1853,16 @@ function writePendingApproval(data) {
if (existing.source === 'dom_observer' && existing.status === 'pending') {
const age = nowMs - (existing.timestamp * 1000);
if (age < DEDUP_WINDOW_MS && age >= 0) {
logToFile(`[DEDUP] skip step_probe pending — DOM observer pending exists: ${ef} (${Math.round(age / 1000)}s ago)`);
// MERGE: update DOM observer pending with detailed step_probe info
existing.command = data.command;
existing.description = data.description;
if (data.step_type)
existing.step_type = data.step_type;
if (data.step_index !== undefined)
existing.step_index = data.step_index;
existing.source = 'dom_observer+step_probe'; // mark as merged
fs.writeFileSync(efPath, JSON.stringify(existing, null, 2), 'utf-8');
logToFile(`[DEDUP] MERGED step_probe info into DOM pending: ${ef} cmd="${data.command.substring(0, 60)}"`);
return;
}
}

2
extension/out/extension.js.map
View File

File diff suppressed because one or more lines are too long

100
extension/src/extension.ts
View File

@@ -402,6 +402,7 @@ const pendingResponses = new Map<string, { approved: boolean } | null>();
// Click trigger: extension sets this, renderer polls and clicks button
let clickTrigger: { action: 'approve' | 'reject'; timestamp: number } | null = null;
let sessionStalled = false; // true when session is stalled waiting for approval
// Deep inspect trigger: curl sets this, renderer picks it up and POSTs results back
let deepInspectRequested = false;
@@ -437,6 +438,24 @@ function startObserverHttpBridge(): Promise<number> {
req.on('end', () => {
try {
const data = JSON.parse(body);
// ── Server-side false positive filter ──
const cmd = (data.command || '').trim();
const FALSE_POSITIVE_RE = /^(Proceed|Continue|Open|Close|OK|Yes|No|Save|Undo|Redo|Back|Next|More|Less|Got it)$/i;
if (FALSE_POSITIVE_RE.test(cmd)) {
logToFile(`[HTTP] filtered false positive: "${cmd}"`);
res.writeHead(200, { 'Content-Type': 'application/json' });
res.end(JSON.stringify({ ok: false, filtered: true }));
return;
}
// "Run" button → only accept if session is actually stalled (waiting for approval)
if (/^Run/i.test(cmd) && !sessionStalled) {
logToFile(`[HTTP] filtered "Run" — session not stalled`);
res.writeHead(200, { 'Content-Type': 'application/json' });
res.end(JSON.stringify({ ok: false, filtered: true }));
return;
}
const rid = data.request_id || Date.now().toString();
// Write pending file for Discord bot
const pendingDir = path.join(bridgePath, 'pending');
@@ -866,8 +885,6 @@ function generateApprovalObserverScript(_port: number): string {
{re:/^Accept$/i, type:'agent_step'},
{re:/^Allow/i, type:'permission'},
{re:/^Approve/i, type:'agent_step'},
{re:/^Continue$/i, type:'continue'},
{re:/^Proceed$/i, type:'continue'},
{re:/^Retry$/i, type:'error_recovery'},
{re:/^Dismiss$/i, type:'error_recovery'},
];
@@ -1379,6 +1396,26 @@ function setupMonitor() {
}
if (delta > 0) {
sessionStalled = false;
// Steps progressed — if we had a pending approval, it was handled in AG directly
if (!sawRunningAfterPending && lastPendingStepIndex >= 0) {
// Mark pending as auto_resolved so bot can update Discord message
try {
const pendingFiles = fs.readdirSync(path.join(bridgePath, 'pending'))
.filter((f: string) => f.endsWith('.json'));
for (const pf of pendingFiles) {
const pfPath = path.join(bridgePath, 'pending', pf);
const pd = JSON.parse(fs.readFileSync(pfPath, 'utf-8'));
if (pd.status === 'pending' && pd.step_index === lastPendingStepIndex) {
pd.status = 'auto_resolved';
fs.writeFileSync(pfPath, JSON.stringify(pd, null, 2), 'utf-8');
logToFile(`[AUTO-RESOLVE] step=${lastPendingStepIndex} progressed → marked ${pf}`);
break;
}
}
} catch (e: any) { logToFile(`[AUTO-RESOLVE] error: ${e.message}`); }
lastPendingStepIndex = -1;
}
consecutiveIdleCount = 0;
sawRunningAfterPending = true;
stallProbed = false; // allow re-probe on next stall
@@ -1394,6 +1431,7 @@ function setupMonitor() {
} else {
// lastModifiedTime frozen = real stall (approval waiting)
consecutiveIdleCount++;
if (consecutiveIdleCount >= 1) sessionStalled = true;
}
lastModTime = currentModTime;
@@ -1474,6 +1512,53 @@ function setupMonitor() {
// Stall fallback REMOVED — step probe is sole fallback source
// (stall fallback was generating false positives and is now redundant)
} else if (!isRunning) {
// ── Error detection: probe when session transitions from RUNNING→idle ──
if (consecutiveIdleCount > 0 && !stallProbed) {
// Was running, now idle — possible error. Probe once.
try {
const stepsResp = await sdk.ls.rawRPC('GetCascadeTrajectorySteps', {
cascadeId: bestSessionId,
});
if (stepsResp?.steps?.length > 0) {
const steps = stepsResp.steps;
// Check last 3 steps for error/failed status
for (let si = steps.length - 1; si >= Math.max(0, steps.length - 3); si--) {
const step = steps[si];
const stepStatus = step?.status || '';
const stepType = step?.type || '';
if (stepStatus.includes('ERROR') || stepStatus.includes('FAILED')) {
const toolCall = step?.metadata?.toolCall;
const toolName = toolCall?.name || stepType.replace('CORTEX_STEP_TYPE_', '').toLowerCase();
let command = `⚠️ Error: ${toolName}`;
if (toolCall?.argumentsJson) {
try {
const args = JSON.parse(toolCall.argumentsJson);
if (args.CommandLine) command = `⚠️ Error: ${args.CommandLine.substring(0, 100)}`;
else if (args.TargetFile) command = `⚠️ Error: ${args.TargetFile.split(/[\\/]/).pop()}`;
} catch { }
}
const description = `Step #${si} ${stepStatus} — Retry?`;
logToFile(`[STEP-PROBE] ★ ERROR! step=${si} status=${stepStatus} type=${stepType}`);
if (si !== lastPendingStepIndex) {
stallProbed = true;
lastPendingStepIndex = si;
writePendingApproval({
conversation_id: activeSessionId,
command,
description,
step_type: 'error_recovery',
step_index: si,
source: 'step_probe_error',
});
}
break;
}
}
}
} catch (e: any) {
logToFile(`[STEP-PROBE-ERR] error check: ${e.message}`);
}
}
consecutiveIdleCount = 0;
lastModTime = currentModTime;
}
@@ -1728,7 +1813,7 @@ function writePendingApproval(data: { conversation_id: string; command: string;
const pendingDir = path.join(bridgePath, 'pending');
if (!fs.existsSync(pendingDir)) { fs.mkdirSync(pendingDir, { recursive: true }); }
// ── Dedup: skip if DOM observer already created a pending for same action recently ──
// ── Dedup: if DOM observer already created a "Run"-only pending, MERGE detailed info into it ──
const nowMs = Date.now();
const DEDUP_WINDOW_MS = 15_000; // 15 second dedup window
try {
@@ -1739,7 +1824,14 @@ function writePendingApproval(data: { conversation_id: string; command: string;
if (existing.source === 'dom_observer' && existing.status === 'pending') {
const age = nowMs - (existing.timestamp * 1000);
if (age < DEDUP_WINDOW_MS && age >= 0) {
logToFile(`[DEDUP] skip step_probe pending — DOM observer pending exists: ${ef} (${Math.round(age/1000)}s ago)`);
// MERGE: update DOM observer pending with detailed step_probe info
existing.command = data.command;
existing.description = data.description;
if (data.step_type) existing.step_type = data.step_type;
if (data.step_index !== undefined) existing.step_index = data.step_index;
existing.source = 'dom_observer+step_probe'; // mark as merged
fs.writeFileSync(efPath, JSON.stringify(existing, null, 2), 'utf-8');
logToFile(`[DEDUP] MERGED step_probe info into DOM pending: ${ef} cmd="${data.command.substring(0, 60)}"`);
return;
}
}