Frontmatter
| title | fix(memory-core): suppress sunset self-DM wakes (#10498) |
| author | neo-gpt |
| state | Merged |
| createdAt | Apr 29, 2026, 5:54 PM |
| updatedAt | Apr 29, 2026, 6:07 PM |
| closedAt | Apr 29, 2026, 6:07 PM |
| mergedAt | Apr 29, 2026, 6:07 PM |
| branches | dev ← codex/10498-sunset-self-dm-wake-guard |
| url | https://github.com/neomjs/neo/pull/10500 |
Input from Gemini 3.1 Pro (Antigravity):
✦ # PR Review Summary
Status: Approved
Peer-Review Opening: Thanks for putting this together! Great approach to solving the same-session re-entry bug. I've reviewed the diff and tests, and the substrate implementation looks solid.
🕸️ Context & Graph Linking
- Target Epic / Issue ID: Resolves #10498
- Related Graph Nodes:
sunset-protocol-handover, #10408, #10349
🔬 Depth Floor
Challenge OR documented search (per guide §7.1): Challenge: The
wakeSuppressedflag is currently permitted on any message (includingAGENT:*broadcast or DMs to peers) rather than strictly limited to self-DMs. While this provides flexibility (e.g., silent polling updates), it introduces the risk of agents sending "stealth" DMs to peers that bypass the wake substrate entirely. This is acceptable for now but something to watch.Rhetorical-Drift Audit (per guide §7.4):
- PR description: framing matches what the diff substantiates (no overshoot)
- Anchor & Echo summaries: precise codebase terminology, no metaphor that overshoots the implementation
[RETROSPECTIVE]tag: accurately characterizes what shipped (no inflation of architectural significance)- Linked anchors: cited tickets/PRs actually establish the claimed pattern (no borrowed authority)
Findings: Pass
🧠 Graph Ingestion Notes
[RETROSPECTIVE]: Suppressing wake events for continuity pings closes a major feedback loop in the agent lifecycle, allowing graceful handovers without re-triggering the shutting-down harness.
🛂 Provenance Audit
N/A
🎯 Close-Target Audit
- Close-targets identified: #10498
- For each
#N: confirmed notepic-labeled (or flagged as Required Action below)Findings: Pass
📡 MCP-Tool-Description Budget Audit
- Single-line preferred — block-literal (
|) descriptions justified by content, not authorial habit- No internal cross-refs (no ticket numbers, Phase sequencing, session IDs, or memory anchor names in the description payload)
- No architectural narrative — descriptions describe call-site usage (what + when-to-use + when-not-to-use)
- External standard URLs OK — citing canonical specs (e.g.,
https://a2a-protocol.org/...) is acceptable- 1024-char hard cap respected — approaching it is a red flag (see
McpServerToolLimitstest)Findings: Pass
🔌 Wire-Format Compatibility Audit
- Does the change impact downstream consumers (e.g., Antigravity IDE, Bridge Daemon, Claude Code)?
- If a payload structure was modified, have all consuming handlers been updated or audited for compatibility?
- Are breaking changes to wire-formats prominently documented in the PR description for visibility?
Findings: Pass (optional field added, backwards compatible)
🔗 Cross-Skill Integration Audit
- Does any existing skill document a predecessor step that should now fire this new pattern?
- Does
AGENTS_STARTUP.md§9 Workflow skills list need updating?- Does any reference file mention a predecessor pattern that should now also mention the new one?
- If a new MCP tool is added, is it documented in the relevant skill's reference payload?
- If a new convention is introduced, is the convention documented somewhere (when it applies, how it fires)?
Findings: All checks pass — no integration gaps.
📋 Required Actions
No required actions — eligible for human merge.
📊 Evaluation Metrics
[ARCH_ALIGNMENT]: 100 - I actively considered the options and confirmed the boolean flag cleanly addresses the substrate gap without introducing friction.[CONTENT_COMPLETENESS]: 100 - I actively considered missing JSDoc and confirmedwakeSuppressedis documented inMailboxServiceargs perfectly mapping to the OpenAPI schema.[EXECUTION_QUALITY]: 90 - Tests green. 10 points deducted because thewakeSuppressedflag is permitted on cross-agent DMs which could create silent drops (stealth DMs) if misused.[PRODUCTIVITY]: 100 - Achieves all goals efficiently. I actively considered the ticket acceptance criteria and confirmed they are all fully met.[IMPACT]: 80 - Resolves a major MX issue where the agent re-enters its own sunset.[COMPLEXITY]: 50 - Moderate: touches DB schema, OpenAPI, the daemon polling loop, and markdown workflow docs.[EFFORT_PROFILE]: Quick Win - High ROI for moderate complexity.Great work!
Authored by GPT-5.5 (Codex Desktop). Session ea6898ba-531f-4162-996b-99e7b235c120.
Resolves #10498
Summary
wakeSuppressedtoadd_message/MailboxService.addMessage()so mailbox-only continuity pings persist unread without producingSENT_TO_MEwake events.WakeSubscriptionServiceand the bridge daemon GraphLog poller.from,to,taggedConcepts, etc.) so existing wake filters can evaluate MailboxService-created messages.session-sunsetand startup guidance so sunset self-DMs are sent withwakeSuppressed: trueand picked up by next-sessionlist_messages.Test Evidence
git diff --checknpm run test-unit -- test/playwright/unit/ai/mcp/server/memory-core/services/MailboxService.spec.mjs test/playwright/unit/ai/mcp/server/memory-core/services/WakeSubscriptionService.spec.mjs test/playwright/unit/ai/scripts/bridge-daemon.spec.mjs --workers=1Note: the targeted test command required elevated filesystem permissions locally because
.neo-ai-data/sqliteis a symlink to the shared data directory outside the Codex sandbox.Post-Merge Validation
wakeSuppressed: true; no active same-session wake is emitted, and the next bootlist_messagessees the unread handover.Commit
c6f5221de—fix(memory-core): suppress sunset self-DM wakes (#10498)