feat(integrations): prove NodeSlide through NodeAgent

[HomenShum]

Summary

• bind NodeSlide tools to NodeRoom's canonical runAgent types and runtime
• extend the packed consumer journey through unapplied proposal, host acceptance, trace receipt, reload, and JSON round-trip
• add bidirectional cross-repo CI and document the still-unproven mounted-product gaps

Verification

• npm run typecheck
• npx vitest run tests/nodeSlideNodeAgentAdapter.test.ts tests/nodeSlideHostPrincipal.test.ts
• repository-root and packed-tarball consumer proofs (reported in the implementation handoff)
• production build and workflow parse (reported in the implementation handoff)

[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 4:49am

[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

⚠️ Immutable proof files changed: .github/workflows/ci.yml

This is advisory because the check is not running in strict scaffold-repair mode.
If this PR is applying accepted scaffold proposals, rerun with --strict-immutability
and reject the PR unless the immutable changes are removed.

Immutable files guarded during scaffold repair:

• 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

Changed Files

• .github/workflows/ci.yml
• 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/20260720T044900Z.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/20260720T044909350Z-8586241b_dirty.74d637206038b14e/cascade-healthy.json
• docs/eval/traces/credit/20260720T044909350Z-8586241b_dirty.74d637206038b14e/delta-incomplete.json
• docs/eval/traces/credit/20260720T044909350Z-8586241b_dirty.74d637206038b14e/mapping-correct.json
• docs/eval/traces/credit/20260720T044909350Z-8586241b_dirty.74d637206038b14e/mapping-misbind.json
• docs/eval/traces/credit/20260720T044909350Z-8586241b_dirty.74d637206038b14e/summit-stressed.json
• docs/eval/traces/ladder/20260720T044908882Z-8586241b_dirty.01ebc350c131e523/ladder_L1_read_scripted.json
• docs/eval/traces/ladder/20260720T044908882Z-8586241b_dirty.01ebc350c131e523/ladder_L2_edit_scripted.json
• docs/eval/traces/ladder/20260720T044908882Z-8586241b_dirty.01ebc350c131e523/ladder_L3_conflict_scripted.json
• docs/eval/traces/ladder/20260720T044908882Z-8586241b_dirty.01ebc350c131e523/ladder_L4_blocked_scripted.json
• docs/eval/traces/ladder/20260720T044908882Z-8586241b_dirty.01ebc350c131e523/ladder_L5_large_range_scripted.json
• docs/eval/traces/ladder/20260720T044908882Z-8586241b_dirty.01ebc350c131e523/ladder_L6_long_horizon_scripted.json
• docs/eval/traces/ladder/20260720T044908882Z-8586241b_dirty.01ebc350c131e523/ladder_L7_resume_scripted.json
• docs/integrations/NODESLIDE_CONSUMER_PROOF.md
• scripts/nodeslide-consumer-proof.ts
• src/integrations/nodeslide/nodeAgentAdapter.ts
• tests/nodeSlideNodeAgentAdapter.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

[HomenShum]

Superseded by #221. The implementation is unchanged; #221 uses a squash commit whose message explicitly covers .github, docs, scripts, src, and tests, satisfying NodeRoom's changed-area commit contract without rewriting this published branch.