Prove NodeSlide host authorization through NodeRoom

[HomenShum]

Summary

• exercise the operation-scoped, host-supplied authorization contract introduced by NodeSlide PR Component-state defects: bounds, honesty, crash, idempotency + render-test layer #17
• bind NodeRoom fixture policy evidence to direct, proposal, stale, rejection, and custom receipts
• keep the existing NodeAgent proposal → review → CAS → reload journey
• bridge the bilateral CI cutover explicitly: legacy-v0 reports no v1 evidence; operation-v1 requires frozen requests and bound receipts; unknown or mixed ABIs fail closed

Verification

• npm run typecheck -- --pretty false
• npm test -- --run (360 files / 2,530 tests)
• current NodeSlide main 0789c61 proof: legacy-v0, green, v1 flags false
• NodeSlide PR Component-state defects: bounds, honesty, crash, idempotency + render-test layer #17 cc6e3b9 proof: operation-v1, green, all seven actions and v1 flags true
• focused integration tests: 3 files / 10 tests

Rollout

Merge this compatibility proof first. Then rerun NodeSlide PR #17 against NodeRoom main, merge only after its packed-consumer check is green, and rerun NodeRoom main against the new producer.

[vercel]

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

Project	Deployment	Actions	Updated (UTC)
noderoom	Ready	Preview, Comment	Jul 20, 2026 8:09am

[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

• 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/20260720T080914Z.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/20260720T080924119Z-3288b5c7_dirty.495f454b283114eb/cascade-healthy.json
• docs/eval/traces/credit/20260720T080924119Z-3288b5c7_dirty.495f454b283114eb/delta-incomplete.json
• docs/eval/traces/credit/20260720T080924119Z-3288b5c7_dirty.495f454b283114eb/mapping-correct.json
• docs/eval/traces/credit/20260720T080924119Z-3288b5c7_dirty.495f454b283114eb/mapping-misbind.json
• docs/eval/traces/credit/20260720T080924119Z-3288b5c7_dirty.495f454b283114eb/summit-stressed.json
• docs/eval/traces/ladder/20260720T080923659Z-3288b5c7_dirty.6fa911e33d47a2cb/ladder_L1_read_scripted.json
• docs/eval/traces/ladder/20260720T080923659Z-3288b5c7_dirty.6fa911e33d47a2cb/ladder_L2_edit_scripted.json
• docs/eval/traces/ladder/20260720T080923659Z-3288b5c7_dirty.6fa911e33d47a2cb/ladder_L3_conflict_scripted.json
• docs/eval/traces/ladder/20260720T080923659Z-3288b5c7_dirty.6fa911e33d47a2cb/ladder_L4_blocked_scripted.json
• docs/eval/traces/ladder/20260720T080923659Z-3288b5c7_dirty.6fa911e33d47a2cb/ladder_L5_large_range_scripted.json
• docs/eval/traces/ladder/20260720T080923659Z-3288b5c7_dirty.6fa911e33d47a2cb/ladder_L6_long_horizon_scripted.json
• docs/eval/traces/ladder/20260720T080923659Z-3288b5c7_dirty.6fa911e33d47a2cb/ladder_L7_resume_scripted.json
• docs/integrations/NODESLIDE_CONSUMER_PROOF.md
• scripts/nodeslide-consumer-proof.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

[HomenShum]

Superseded by the identical tree on a single policy-compliant docs+scripts commit; no force-push. The replacement keeps the same reviewed dual-protocol rollout proof.