Harden NodeAgent workbook recovery and live sheet rendering

[HomenShum]

Summary

• recover required-tool workbook runs across OpenRouter routes with provider-aware cooldown scheduling
• allow artifact-bound approved plans to commit without weakening explicit-op validation
• render canonical A1 NodeAgent writes alongside legacy fresh-room sheet cells
• extend the live-room scenario landing selector without bypassing authentication

Verification

• npm run floor (349 files, 2,485 tests)
• npm run prod:gate
• live production NodeAgent run: GLM timeout -> Qwen recovery -> 5 formula proposals approved and persisted

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated (UTC)
noderoom	Building	Preview, Comment	Jul 16, 2026 8:27pm

[github-actions]

Scaffold Handoff — For Your Coding Agent

Your coding agent (Codex, Claude Code, etc.) should apply the accepted
scaffold proposals below. Do NOT touch any immutable files.

Immutability Check

Mode: advisory

✅ No immutable files were modified in this branch.

Changed Files

• .env.example
• convex/agentJobRunner.ts
• docs/eval/OFFICIAL_BENCHMARK_READINESS.md
• docs/eval/OFFICIAL_BENCHMARK_TASK_COVERAGE.md
• docs/eval/OPENROUTER_CONVEX_BENCHMARK.md
• docs/eval/agent-improvement-loop.md
• docs/eval/agent-improvement-loop.svg
• docs/eval/agent-improvement-loop/20260716T202804Z.json
• docs/eval/agent-improvement-loop/latest.json
• docs/eval/agent-workspace-sandbox-smoke.json
• docs/eval/algorithm-artifact-smoke.json
• docs/eval/bankertoolbench-official-contract.json
• docs/eval/docker-sandbox-probe.json
• docs/eval/eval-runs.jsonl
• docs/eval/halo-convex-context-telemetry.json
• docs/eval/halo-self-improvement-smoke.json
• docs/eval/halo-variant-selection.json
• docs/eval/official-benchmark-readiness.json
• docs/eval/official-benchmark-task-coverage.json
• docs/eval/openrouter-convex-benchmark.json
• docs/eval/professional-catalog-proofs.json
• docs/eval/professional-proof-ledger.json
• docs/eval/spreadsheetbench-chart-visual-probe.json
• docs/eval/traces/credit/20260716T202814235Z-0c0449a6_dirty.11198559dae24203/cascade-healthy.json
• docs/eval/traces/credit/20260716T202814235Z-0c0449a6_dirty.11198559dae24203/delta-incomplete.json
• docs/eval/traces/credit/20260716T202814235Z-0c0449a6_dirty.11198559dae24203/mapping-correct.json
• docs/eval/traces/credit/20260716T202814235Z-0c0449a6_dirty.11198559dae24203/mapping-misbind.json
• docs/eval/traces/credit/20260716T202814235Z-0c0449a6_dirty.11198559dae24203/summit-stressed.json
• docs/eval/traces/ladder/20260716T202813767Z-0c0449a6_dirty.987a58d0d74bffd9/ladder_L1_read_scripted.json
• docs/eval/traces/ladder/20260716T202813767Z-0c0449a6_dirty.987a58d0d74bffd9/ladder_L2_edit_scripted.json
• docs/eval/traces/ladder/20260716T202813767Z-0c0449a6_dirty.987a58d0d74bffd9/ladder_L3_conflict_scripted.json
• docs/eval/traces/ladder/20260716T202813767Z-0c0449a6_dirty.987a58d0d74bffd9/ladder_L4_blocked_scripted.json
• docs/eval/traces/ladder/20260716T202813767Z-0c0449a6_dirty.987a58d0d74bffd9/ladder_L5_large_range_scripted.json
• docs/eval/traces/ladder/20260716T202813767Z-0c0449a6_dirty.987a58d0d74bffd9/ladder_L6_long_horizon_scripted.json
• docs/eval/traces/ladder/20260716T202813767Z-0c0449a6_dirty.987a58d0d74bffd9/ladder_L7_resume_scripted.json
• proofloop/benchmarks/common/live-room-scenario.spec.ts
• src/nodeagent/guardrails/workbookWorkflow.ts
• src/nodeagent/models/convexModel.ts
• src/nodeagent/models/modelCatalog.ts
• src/nodeagent/models/qualityFailover.ts
• src/ui/panels/Artifact.tsx
• tests/agentJobsSource.test.ts
• tests/convexModelFreeAutoMode.test.ts
• tests/qualityFailover.test.ts
• tests/sheetVirtualization.test.ts
• tests/workbookWorkflowHook.test.ts

Needs Adversarial Review — Do NOT Apply Yet

These proposals passed the reject check but have not been approved by
an adversarial reviewer. A human or frozen LLM judge must approve them first.

• scaf-001 (AGENTS.md): Add explicit instruction for step spreadsheetbench-runner-fixture: Step spreadsheetbench-runner-fixture failed — scaffold may need explicit instruction or evidence assertion.
• scaf-002 (AGENTS.md): Add explicit instruction for step convex-boundaries: Step convex-boundaries failed — scaffold may need explicit instruction or evidence assertion.

Safety Boundary

Agent may improve the scaffold.
Agent may NOT weaken the proof gate.

Immutable files (never modify):

• scripts/proofloop.mjs
• scripts/agent-improvement-loop.ts
• tests/harnessChangeEval.test.ts
• .github/workflows/
• src/eval/evalTrustPolicy.ts
• src/eval/architectureBudget.ts
• evals/evalStore.ts

Scaffold files (safe to modify):

• AGENTS.md
• CLAUDE.md
• proofloop/scenarios/*.yaml
• proofloop/rubrics/*.yaml
• proofloop/subagents/*.md
• proofloop/adapters/*.js
• .proofloop/memory.jsonl
• src/nodeagent/models/prompts/systemPrompt.ts