@adhdev/daemon-core 1.0.28-rc.6 → 1.0.28-rc.7

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@adhdev/daemon-core",
-  "version": "1.0.28-rc.6",
+  "version": "1.0.28-rc.7",
   "description": "ADHDev daemon core — CDP, IDE detection, providers, command execution",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",
@@ -49,8 +49,8 @@
   "author": "vilmire",
   "license": "AGPL-3.0-or-later",
   "dependencies": {
-    "@adhdev/mesh-shared": "1.0.28-rc.6",
-    "@adhdev/session-host-core": "1.0.28-rc.6",
+    "@adhdev/mesh-shared": "1.0.28-rc.7",
+    "@adhdev/session-host-core": "1.0.28-rc.7",
     "@agentclientprotocol/sdk": "^0.16.1",
     "ajv": "^8.20.0",
     "ajv-formats": "^3.0.1",

package/src/cli-adapters/cli-state-engine.ts

@@ -1604,7 +1604,15 @@ export class CliStateEngine {
         // background-tool race this was meant to guard against. If a provider
         // really needs the gate, the manifest can set
         // `requiresFinalAssistantBeforeIdle: true`.
-        const requiresFinalAssistant = !!this.provider.requiresFinalAssistantBeforeIdle;
+        //
+        // This is a completion-timing JUDGMENT, so it goes through the shared
+        // transcript-authority profile rather than reading the raw flag: the
+        // 'floor' class is exactly `requiresFinalAssistantBeforeIdle && !hold`
+        // (see resolveTranscriptAuthorityProfile), which is equivalent to the
+        // old `!!requiresFinalAssistantBeforeIdle` for every real provider
+        // because none declares both flags — a hold provider (antigravity)
+        // sets holdCompletionForTranscript only, so it was already false here.
+        const requiresFinalAssistant = resolveTranscriptAuthorityProfile(this.provider).timing === 'floor';
         if (!requiresFinalAssistant) return false;
         if (!this.isWaitingForResponse || !this.currentTurnScope || this.hasActionableApproval()) return false;
         const parsedStatus = typeof parsed?.status === 'string' ? parsed.status.trim() : '';

package/src/cli-adapters/provider-cli-adapter.ts

@@ -232,6 +232,9 @@ export class ProviderCliAdapter implements CliAdapter {
     private pendingOutboundQueue: PendingOutboundMessage[] = [];
     private pendingOutboundFlushTimer: NodeJS.Timeout | null = null;
     private pendingOutboundFlushInFlight = false;
+    // Stale-queue watchdog: fires STALE_QUEUE_WARN_MS after the oldest queued
+    // message was enqueued if nothing has been flushed yet.
+    private pendingOutboundStaleTimer: NodeJS.Timeout | null = null;
     // Submit retry timer — PTY-level, not state machine
     private submitRetryTimer: NodeJS.Timeout | null = null;
 
@@ -1715,6 +1718,10 @@ export class ProviderCliAdapter implements CliAdapter {
         await new Promise<void>(resolve => setTimeout(resolve, FORCE_SUBMIT_SETTLE_MS));
     }
 
+    // Stale-queue threshold: warn if a queued message has not been flushed
+    // within this many milliseconds (instrumentation only, no behavior change).
+    private static readonly STALE_QUEUE_WARN_MS = 15000;
+
     private enqueuePendingOutboundMessage(text: string, reason: string, meshTaskId?: string): void {
         const content = String(text || '');
         const duplicate = this.pendingOutboundQueue.some((message) => message.content === content);
@@ -1722,6 +1729,18 @@ export class ProviderCliAdapter implements CliAdapter {
             return;
         }
         const queuedAt = Date.now();
+        const stableMs = this.lastScreenChangeAt ? (queuedAt - this.lastScreenChangeAt) : -1;
+        // Diagnostic context: which gate caused the silent-queue and the full
+        // session readiness snapshot at the moment of enqueue.
+        const gateContext = {
+            reason,
+            startupParseGate: this.startupParseGate,
+            ready: this.ready,
+            engineStatus: this.engine.currentStatus,
+            isWaitingForResponse: this.engine.isWaitingForResponse,
+            stableMs,
+            sessionId: this.engine.getTraceSessionId(),
+        };
         const message: PendingOutboundMessage = {
             id: `${queuedAt}:${this.pendingOutboundQueue.length}:${Math.random().toString(36).slice(2, 10)}`,
             role: 'user',
@@ -1731,8 +1750,23 @@ export class ProviderCliAdapter implements CliAdapter {
             ...(typeof meshTaskId === 'string' && meshTaskId.trim() ? { meshTaskId } : {}),
         };
         this.pendingOutboundQueue.push(message);
-        LOG.info('CLI', `[${this.cliType}] queued outbound message while busy (${reason}); queue=${this.pendingOutboundQueue.length}`);
+        LOG.info('CLI', `[${this.cliType}] queued outbound message; gate=${JSON.stringify(gateContext)}; queue=${this.pendingOutboundQueue.length}`);
         this.onStatusChange?.();
+        // Stale-queue watchdog: emit a warn-level log if the enqueued message
+        // has not been flushed after STALE_QUEUE_WARN_MS. This fires once per
+        // enqueue event (not once per message still in queue) so it does not
+        // spam on a persistently stuck queue; it simply surfaces that the queue
+        // is stuck and records the current gate state at warn time.
+        if (!this.pendingOutboundStaleTimer) {
+            this.pendingOutboundStaleTimer = setTimeout(() => {
+                this.pendingOutboundStaleTimer = null;
+                if (this.pendingOutboundQueue.length === 0) return;
+                const oldest = this.pendingOutboundQueue[0];
+                const staleSec = ((Date.now() - oldest.queuedAt) / 1000).toFixed(1);
+                const nowStableMs = this.lastScreenChangeAt ? (Date.now() - this.lastScreenChangeAt) : -1;
+                LOG.warn('CLI', `[${this.cliType}] STALE QUEUE: ${this.pendingOutboundQueue.length} message(s) undelivered for ${staleSec}s; gate=startupParseGate:${this.startupParseGate} ready:${this.ready} engineStatus:${this.engine.currentStatus} isWaitingForResponse:${this.engine.isWaitingForResponse} stableMs:${nowStableMs} sessionId:${this.engine.getTraceSessionId()} enqueueReason:${oldest.id}`);
+            }, ProviderCliAdapter.STALE_QUEUE_WARN_MS);
+        }
     }
 
     private shouldQueuePendingOutboundMessage(parsedStatusBeforeSend: any | null = null): string | null {
@@ -1785,6 +1819,11 @@ export class ProviderCliAdapter implements CliAdapter {
                 try {
                     await this.sendMessageNow(next.content, false, next.meshTaskId);
                     this.pendingOutboundQueue.shift();
+                    // Clear stale watchdog once the queue drains.
+                    if (this.pendingOutboundQueue.length === 0 && this.pendingOutboundStaleTimer) {
+                        clearTimeout(this.pendingOutboundStaleTimer);
+                        this.pendingOutboundStaleTimer = null;
+                    }
                     this.onStatusChange?.();
                 } catch (error: any) {
                     LOG.warn('CLI', `[${this.cliType}] queued outbound flush failed: ${error?.message || error}`);
@@ -2174,6 +2213,7 @@ export class ProviderCliAdapter implements CliAdapter {
         this.pendingTerminalQueryTail = '';
         this.ptyOutputChunks = [];
         if (this.pendingOutboundFlushTimer) { clearTimeout(this.pendingOutboundFlushTimer); this.pendingOutboundFlushTimer = null; }
+        if (this.pendingOutboundStaleTimer) { clearTimeout(this.pendingOutboundStaleTimer); this.pendingOutboundStaleTimer = null; }
         this.pendingOutboundQueue = [];
         this.pendingOutboundFlushInFlight = false;
         if (this.ptyProcess) {
@@ -2197,6 +2237,7 @@ export class ProviderCliAdapter implements CliAdapter {
         this.pendingTerminalQueryTail = '';
         this.ptyOutputChunks = [];
         if (this.pendingOutboundFlushTimer) { clearTimeout(this.pendingOutboundFlushTimer); this.pendingOutboundFlushTimer = null; }
+        if (this.pendingOutboundStaleTimer) { clearTimeout(this.pendingOutboundStaleTimer); this.pendingOutboundStaleTimer = null; }
         this.pendingOutboundQueue = [];
         this.pendingOutboundFlushInFlight = false;
         if (this.ptyProcess) {

package/src/providers/cli-provider-instance.ts

@@ -785,16 +785,21 @@ export class CliProviderInstance implements ProviderInstance {
             }))
             : mergedMessages;
 
-        // Dashboard-tail repair (native-source providers, e.g. antigravity): the
-        // assistant answer lives only in native-history, so the PTY-parsed
-        // statusMessages end on the user prompt / auto-approve system lines and the
-        // snapshot's preview / lastMessageRole / completionMarker never see the
-        // answer — the session looks stuck on the user turn. We already cached the
-        // real final assistant summary at completion time (lastCompletionSummary),
-        // so append it as the trailing assistant bubble when the current tail has no
-        // assistant message at/after it. Purely additive to the status view; no
-        // per-tick native read, no effect on providers whose PTY carries the
-        // assistant (they surface it themselves and the guard below is a no-op).
+        // purpose: 'display-tail' (zero-read) — Dashboard-tail repair (native-source
+        // providers, e.g. antigravity): the assistant answer lives only in native-history,
+        // so the PTY-parsed statusMessages end on the user prompt / auto-approve system
+        // lines and the snapshot's preview / lastMessageRole / completionMarker never see
+        // the answer — the session looks stuck on the user turn. We already cached the
+        // real final assistant summary at completion time (lastCompletionSummary), so
+        // append it as the trailing assistant bubble when the current tail has no
+        // assistant message at/after it. Purely additive to the status view; no per-tick
+        // native read, no effect on providers whose PTY carries the assistant (they
+        // surface it themselves and the guard below is a no-op).
+        //
+        // authority-ok: this is a DISPLAY-ONLY tail repair, never a completion/stall/
+        // redrive verdict — it reads the pre-cached summary (zero native read) and only
+        // paints the status view. It keys off the adapter's runtime chatMessagesOwnedExternally
+        // capability (not a class predicate); a completion decision is never taken here.
         const adapterOwnsMessagesElsewhereForTail = (this.adapter as any)?.chatMessagesOwnedExternally === true;
         if (adapterOwnsMessagesElsewhereForTail && this.lastCompletionSummary) {
             const summary = this.lastCompletionSummary;
@@ -1580,6 +1585,11 @@ export class CliProviderInstance implements ProviderInstance {
     private readExternalCompletionMessages(): unknown[] | null {
         const adapterOwnsMessagesElsewhere = (this.adapter as any)?.chatMessagesOwnedExternally === true;
         if (!adapterOwnsMessagesElsewhere) return null;
+        // authority-ok: native READ resolution, not a completion/stall/redrive verdict.
+        // This gate only decides whether an on-disk native transcript EXISTS to read for
+        // this session; the completion decision is made by callers over the returned
+        // messages (completionFinalAssistantEvidence / completionFinalSummary), which
+        // route class through resolveTranscriptAuthorityProfile.
         if (!isNativeSourceCanonicalHistory(this.provider.nativeHistory)) return null;
 
         // Resolve a CONCRETE native-history handle for this session's OWN
@@ -2613,6 +2623,11 @@ export class CliProviderInstance implements ProviderInstance {
      * (≥180s of PTY stasis), never on the routine 5s tick.
      */
     private sampleNativeTranscriptProgress(): { msgCount: number; sourceMtimeMs: number } | null {
+        // authority-ok: native fingerprint SAMPLING, not a stall verdict. This only
+        // decides whether a native source exists to sample a progress fingerprint from;
+        // the caller (checkMeshWorkerStall) makes the stall/no-progress decision over the
+        // returned fingerprint. Non-native-source classes have nothing to sample here and
+        // fall back to the unchanged lastOutputAt-only judgment.
         if (!isNativeSourceCanonicalHistory(this.provider?.nativeHistory)) return null;
         // readExternalCompletionMessages resolves this session's OWN native-source
         // conversation (providerSessionId / persisted pin / floor claim) and, as a
@@ -3900,7 +3915,31 @@ export class CliProviderInstance implements ProviderInstance {
             fcEvidenceSource = evidence.source;
             fcFinalSummary = extractFinalSummaryFromMessages(evidence.messages as any);
         } catch { /* best-effort */ }
-        const missingEvidence = (resolveTranscriptAuthorityProfile(this.provider).timing === 'floor' || fcEvidenceSource === 'external-native') && !fcFinalSummary;
+        // SPEC-DRIVEN completion timing (mission f2f6da1b / AGY-BOOT-PHANTOM): the
+        // startup-grace synth must enumerate the SAME transcript-authority timing
+        // classes the genuine finalization gate does (getCompletedFinalizationBlock,
+        // the external-native branch ~line 2120), not just 'floor' + external-native.
+        // The 'hold' class (antigravity — holdCompletionForTranscript) was missing:
+        // at boot its native history is often not yet written, so fcEvidenceSource is
+        // 'unavailable' (neither 'floor' nor 'external-native'), which left
+        // missingEvidence=false and fired a WEAK phantom completion the moment the FSM
+        // collapsed to idle — a completion for a turn whose authoritative transcript
+        // had not landed.
+        const synthTiming = resolveTranscriptAuthorityProfile(this.provider).timing;
+        const missingEvidence = (synthTiming === 'floor' || synthTiming === 'hold' || fcEvidenceSource === 'external-native') && !fcFinalSummary;
+        // HOLD class (antigravity): idle holds for the native transcript to land. The
+        // finalization gate never emits a completion for a hold provider without the
+        // transcript (it returns holdForTranscript / null at ~line 2120), so the synth
+        // must not either — even WITH mesh context. Suppress the synth and leave the
+        // task UNMARKED so a later idle poll re-runs this path once the transcript's
+        // final assistant lands (then fcFinalSummary is present → missingEvidence=false
+        // → a genuine, summary-bearing emit). This is the HOLD-and-retry equivalent of
+        // the finalization gate's non-terminal missing_final_assistant hold; it is what
+        // stops the boot-time phantom weak completion for a mesh worker.
+        if (missingEvidence && synthTiming === 'hold') {
+            LOG.info('CLI', `[${this.type}] ${reason} held: hold-class transcript not yet landed (source=${fcEvidenceSource})`);
+            return false;
+        }
         // Mirror the short-generating idle path's suppression: a provider that
         // requires a final assistant (or external-native history) with NO confirmed
         // summary and NO mesh context emits nothing — the session is idle with no
@@ -5119,6 +5158,9 @@ export class CliProviderInstance implements ProviderInstance {
         const limit = options.full ? Number.MAX_SAFE_INTEGER : STATUS_HYDRATION_TAIL_LIMIT;
         const windowTag = options.full ? 'full' : `tail:${STATUS_HYDRATION_TAIL_LIMIT}`;
 
+        // authority-ok: history-hydration READ routing, not a completion verdict. Selects
+        // the on-disk native transcript vs the materialized-mirror read path; no
+        // completion/stall/redrive decision is taken here.
         if (isNativeSourceCanonicalHistory(canonicalHistory)) {
             const cacheKey = [this.type, this.providerSessionId, this.workingDir, windowTag].join('\0');
             const now = Date.now();
@@ -5188,6 +5230,8 @@ export class CliProviderInstance implements ProviderInstance {
         // transcript so seedSessionHistory can prime dedup state. Pass full so the
         // hydration read is unbounded here (and only here).
         this.syncCanonicalSavedHistoryIfNeeded({ full: true });
+        // authority-ok: history-restore READ routing, not a completion verdict — picks the
+        // native transcript read vs the legacy chat-history read for seeding dedup state.
         const restoredHistory = isNativeSourceCanonicalHistory(this.provider.nativeHistory)
             ? readProviderChatHistory(this.type, {
                 canonicalHistory: this.provider.nativeHistory,