Adopt immutable NodeGym consumer

[HomenShum]

Summary

• vendor and lock the exact @nodekit/gym-core 0.1.0 candidate
• add direct NodeRoom evaluation and six-run HOLD consumer proof
• verify immutable bytes, npm install identity, and direct consumer journey in CI
• harden two filesystem-heavy tests with explicit bounded timeouts

Verification

• npm run nodegym:consumer:proof
• npx vitest run tests/nodeGymConsumer.test.ts
• npm run floor (371 files, 2,565 tests)
• npm run typecheck

No route or user mutation is auto-applied; the consumer remains HOLD with autoApply false.

[vercel]

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

Project	Deployment	Actions	Updated (UTC)
noderoom	Ready	Preview, Comment	Jul 22, 2026 11:23am

[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/NODE_GYM_CONSUMER.md
• 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/20260722T112249Z.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/node-gym-candidate-stage.json
• docs/eval/node-gym-consumer-proof.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/20260722T112258936Z-cae08ea4_dirty.da74ce64df31f1b2/cascade-healthy.json
• docs/eval/traces/credit/20260722T112258936Z-cae08ea4_dirty.da74ce64df31f1b2/delta-incomplete.json
• docs/eval/traces/credit/20260722T112258936Z-cae08ea4_dirty.da74ce64df31f1b2/mapping-correct.json
• docs/eval/traces/credit/20260722T112258936Z-cae08ea4_dirty.da74ce64df31f1b2/mapping-misbind.json
• docs/eval/traces/credit/20260722T112258936Z-cae08ea4_dirty.da74ce64df31f1b2/summit-stressed.json
• docs/eval/traces/ladder/20260722T112258460Z-cae08ea4_dirty.3ed58071adc5d0d8/ladder_L1_read_scripted.json
• docs/eval/traces/ladder/20260722T112258460Z-cae08ea4_dirty.3ed58071adc5d0d8/ladder_L2_edit_scripted.json
• docs/eval/traces/ladder/20260722T112258460Z-cae08ea4_dirty.3ed58071adc5d0d8/ladder_L3_conflict_scripted.json
• docs/eval/traces/ladder/20260722T112258460Z-cae08ea4_dirty.3ed58071adc5d0d8/ladder_L4_blocked_scripted.json
• docs/eval/traces/ladder/20260722T112258460Z-cae08ea4_dirty.3ed58071adc5d0d8/ladder_L5_large_range_scripted.json
• docs/eval/traces/ladder/20260722T112258460Z-cae08ea4_dirty.3ed58071adc5d0d8/ladder_L6_long_horizon_scripted.json
• docs/eval/traces/ladder/20260722T112258460Z-cae08ea4_dirty.3ed58071adc5d0d8/ladder_L7_resume_scripted.json
• package-lock.json
• package.json
• scripts/node-gym-consumer-proof.ts
• scripts/stage-node-gym-candidate.mjs
• src/integrations/nodegym/nodeRoomGymConsumer.ts
• tests/nodeGymConsumer.test.ts
• tests/nodeagentImportGuards.test.ts
• tests/spreadsheetBenchChunkedRepair.test.ts
• vendor/nodekit-gym-core/README.md
• vendor/nodekit-gym-core/nodekit-gym-core-0.1.0.tgz
• vendor/nodekit-gym-core/release-lock.json

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