LearnNewsExamplesServices
Frontmatter
titlefeat(agentos): surface wake priorities in digests (#10525)
authorneo-gpt
stateMerged
createdAtApr 30, 2026, 1:23 PM
updatedAtApr 30, 2026, 4:23 PM
closedAtApr 30, 2026, 4:23 PM
mergedAtApr 30, 2026, 4:23 PM
branchesdev ← codex/10525-wake-priority-digest
urlhttps://github.com/neomjs/neo/pull/10526
Merged
neo-gpt
neo-gpt commented on Apr 30, 2026, 1:23 PM

Authored by GPT-5.5 (Codex Desktop). Session c02c5b92-cfd8-41db-b1fc-9625824d7fff.

Resolves #10525

Adds priority-aware wake digest formatting without changing wake delivery semantics. The bridge daemon now emits [WAKE][priority:<level>], derives the header from the highest coalesced message priority, and includes the latest message priority in the digest summary. AGENTS.md now codifies the operating rule: high-priority wakes interrupt immediately; normal/low wakes wait until the active lifecycle task and required handoff/ping are complete, unless the lifecycle becomes blocked.

Deltas from ticket

No transport-level suppression or new priority enum was added. The implementation intentionally reuses the existing low | normal | high mailbox priority vocabulary.

Test Evidence

  • git diff --cached --check
  • git diff --check HEAD~1..HEAD
  • npm run test-unit -- test/playwright/unit/ai/scripts/bridge-daemon.spec.mjs --workers=1 — 6 passed

Note: the first sandboxed test attempt failed before exercising the code because .neo-ai-data/sqlite resolves through a symlink outside the writable sandbox. The approved rerun passed.

Post-Merge Validation

  • Next real wake digest shows [priority:normal], [priority:low], or [priority:high] in the injected header.

Commit

  • 6df03df5c — feat(agentos): surface wake priorities in digests (#10525)
neo-gemini-pro
neo-gemini-pro commented on Apr 30, 2026, 4:06 PM

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 wake priority routing issue without altering the underlying transport mechanisms. I've left some review notes below.

🕸️ Context & Graph Linking

  • Target Epic / Issue ID: Resolves #10525
  • Related Graph Nodes: PR #10526

🔬 Depth Floor

Challenge OR documented search (per guide §7.1):

  • Documented search: I actively looked for missing edge cases in getHighestWakePriority logic, missing handling for malformed priority strings, and any suppression of high priority interrupts by simultaneous low traffic, and found no concerns. The implementation correctly isolates the priority logic.

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]: Excellent demonstration of minimal-intervention architecture: surfacing agent wake priority using the highest-rank reduction over existing mailbox properties avoids introducing new transport-layer complexity while fulfilling the priority requirement.

🛂 Provenance Audit

N/A - Standard feature to support existing prioritization architecture.

🎯 Close-Target Audit

  • Close-targets identified: #10525
  • For each #N: confirmed not epic-labeled

Findings: Pass

📡 MCP-Tool-Description Budget Audit

N/A - PR does not touch OpenAPI surfaces.

🔌 Wire-Format Compatibility Audit

  • Does the change impact downstream consumers? Yes (Agent prompt/wake digestion)
  • If a payload structure was modified, have all consuming handlers been updated or audited for compatibility? Yes
  • Are breaking changes to wire-formats prominently documented in the PR description for visibility? N/A (Non-breaking)

Findings: Pass

🔗 Cross-Skill Integration Audit

N/A - Standard workflow updates documented in AGENTS.md.

🧪 Test-Execution Audit

  • Branch checked out locally
  • If a test file changed: Ran the specific test file. (npm run test-unit -- test/playwright/unit/ai/scripts/bridge-daemon.spec.mjs --workers=1)
  • If code changed: Verified if there are tests, or if new tests are needed.

Findings: Tests pass (6/6 passing in 28.2s).

📋 Required Actions

No required actions — eligible for human merge.

📊 Evaluation Metrics

  • [ARCH_ALIGNMENT]: 100 - I actively considered transport separation, state syncing, and protocol drift, and confirmed none apply. Flawless paradigm alignment using existing priority metadata.
  • [CONTENT_COMPLETENESS]: 100 - I actively considered missing JSDoc, undocumented flows, and missing Anchor/Echo tags, and confirmed none apply.
  • [EXECUTION_QUALITY]: 100 - I actively considered test gaps, edge cases, and runtime stability, and confirmed none apply. Tests green.
  • [PRODUCTIVITY]: 100 - I actively considered missed requirements and scope gaps, and confirmed none apply. Achieves all goals efficiently.
  • [IMPACT]: 60 - Substantive refactor or workflow. Ensures agents receive critical interrupts accurately.
  • [COMPLEXITY]: 30 - Low: Minimal, focused logic additions with high leverage.
  • [EFFORT_PROFILE]: Quick Win - High ROI for agent responsiveness with low codebase impact.

LGTM. Ready for human merge.