coldpass

HeyPuter/everything

GitHub ↗ · How this check works

Per-setup public labels: Linux / Haiku: Didn’t work

Static status badge · SVG · read-only JSON. Embed with ![Coldpass status](https://coldpass.dev/badge/HeyPuter--everything.svg).

adobeofficephotoshopcadspreadsheetsaas

Didn’t work

Only older checks are saved; no current product test.

Answers apply to each recorded setup, revision and operation. Earlier observations remain in Run details.

Tested on Linux
PlatformHaikuLuna
Linuxno

Linux / Haiku 5.5: no · Oct 18, 2026 · fe402697b279 · claude-code / 2.1.300 (Claude Code)
Recorded operation: /opt/node22/bin/npm run mcp:demo

Local or hosted
local
Local: runs on your machine
Setup time
11 s to install
Issue
filed; fix not cold-proven
Filed upstream: issue #45 (open as of 2026-10-20 UTC) · PR #46 (open as of 2026-10-20 UTC)

No strict 3-fail / 3-pass cold-prove fix recorded.

Safety: no observations were recorded for the selected revision. Functional results do not establish a safety result.

Recorded repair observations

Retained repair evidence. This record does not qualify for a controlled cold comparison. Its declarations are historical evidence, not a current proof badge.

Historical record (JSON)

  • incomplete or contradictory comparison declaration

Retained repair evidence. This record does not qualify for a controlled cold comparison. Its declarations are historical evidence, not a current proof badge.

Historical record (JSON) · Declared comparison (JSON) · Retained patch · Direct check report

  • run ID missing from saved ledger
Repair history and test corrections
Current diagnosis: unknown · verifying

HeyPuter/everything src/contacts/scripts/mcp-demo.js starts its server as callerApp calendar (READ_METHODS only per ALLOWED_CALLERS), then calls create_contact -> Unknown tool. Demo should run as the ai app, which holds the write grant.

Repair record fix-recovery-everything-20261026 · current status JSON. Original run outcomes remain unchanged.

Failed run: HeyPuter/everything · Oct 17, 2026 · Recorded operation failed.

Current diagnosis: unknown · fix verification did not pass

HeyPuter/everything src/contacts/scripts/mcp-demo.js starts its server as callerApp calendar (READ_METHODS only per ALLOWED_CALLERS), then calls create_contact -> Unknown tool. Demo should run as the ai app, which holds the write grant.

Repair record fix-recovery-everything-patch-20261026 · current status JSON. Original run outcomes remain unchanged.

Failed run: HeyPuter/everything · Oct 17, 2026 · Recorded operation failed.

Fix verification: HeyPuter/everything · Oct 26, 2026 · Recorded operation failed.

Current diagnosis: unknown · verified

Proven by fix-g3-heputer-demo2: before 0/3 (blocked,blocked,unsupported), after 3/3 pass; after runs 1792304218651445315, 1792304598594412472, 1792304956244385591.

Repair record fix-60870a6759a8d95c94e4 · current status JSON. Original run outcomes remain unchanged.

Failed run: HeyPuter/everything · Oct 17, 2026 · Recorded operation failed.

Fix verification: HeyPuter/everything · Oct 18, 2026 · Checked operation passed.

Current diagnosis: unknown · verified

HeyPuter/everything src/contacts/scripts/mcp-demo.js starts its server as callerApp calendar (READ_METHODS only per ALLOWED_CALLERS), then calls create_contact -> Unknown tool. Demo should run as the ai app, which holds the write grant.

Repair record fix-g3-heputer-demo · current status JSON. Original run outcomes remain unchanged.

Failed run: HeyPuter/everything · Oct 17, 2026 · Recorded operation failed.

Fix verification: HeyPuter/everything · Oct 18, 2026 · Checked operation passed.

Current diagnosis: unknown · verified

HeyPuter/everything src/contacts/scripts/mcp-demo.js starts its server as callerApp calendar (READ_METHODS only per ALLOWED_CALLERS), then calls create_contact -> Unknown tool. Demo should run as the ai app, which holds the write grant.

Repair record fix-g3-heputer-demo2 · current status JSON. Original run outcomes remain unchanged.

Failed run: HeyPuter/everything · Oct 17, 2026 · Recorded operation failed.

Fix verification: HeyPuter/everything · Oct 18, 2026 · Checked operation passed.

Current diagnosis: unknown · resolved

A pass row for this fix landed 07:09Z; the 08:12Z repair run hung in the cli probe (npm run dev never exits) (probe timeout).

Repair record fix-7643e9848a0bf93c5f1e · current status JSON. Original run outcomes remain unchanged.

Failed run: HeyPuter/everything · Oct 18, 2026 · Recorded operation failed.

Repair development: HeyPuter/everything · Oct 18, 2026 · Repair work (development) · not an initial-trial result.

Run details

Haiku 5.5

Native agent · Recorded operation failed

Operation / attempted scope /opt/node22/bin/npm run mcp:demo

Agent-reported scope: Contacts MCP server (src/contacts): npm run mcp:demo runs a real MCP session over the server: initialize, tools/list (4 calendar-granted tools), tools/call search_contacts and suggest_recipients returning real results. The create_contact step is refused by the calendar grant and the demo script then throws, exit 1.

Run details
run
HeyPuter--everything-claude-haiku-5-5-1792306158676469780
date
Oct 18, 2026
time to working
not recorded
product hosting / execution
Local command in the guest
recorded operation scope
Offline demo only, using an in-memory kv and a fake AppConnection. No Puter account or desktop, so the live Puter cloud path was not exercised. Full npm test/lint/build were intentionally not run.
model
claude-haiku-5-5
agent / version
claude-code / 2.1.300 (Claude Code)
platform
linux
reported cost
$0.014966
Recorded source
https://github.com/HeyPuter/everything
Tool transport
mcp-assigned-vm
Test version
readme-a2e9d2658ac9fb55f10240d0cb65b58fe7404f4db075e780d3ec01384f065849
revision
fe402697b27949b8e26c44e205bac9088798a7e7
Current diagnosis: unknown · resolved

A pass row for this fix landed 07:09Z; the 08:12Z repair run hung in the cli probe (npm run dev never exits) (probe timeout).

Repair record fix-7643e9848a0bf93c5f1e · current status JSON. Original run outcomes remain unchanged.

Failed run: HeyPuter/everything · Oct 18, 2026 · Recorded operation failed.

Repair development: HeyPuter/everything · Oct 18, 2026 · Repair work (development) · not an initial-trial result.

Double-checks failed run: HeyPuter/everything · Oct 17, 2026.

Fix: fix-7643e9848a0bf93c5f1e.

Saved before the Q1 checker correction (f4b66c0); retained as older evidence. Fresh R5 records are separate.

Recorded blocker / warning

Step: /opt/node22/bin/npm run mcp:demo

an expected operation error cannot prove working behavior: {"returncode": 1, "stdout": "\n> [email protected] mcp:demo\n> node scripts/mcp-demo.js\n\n\u001b[1m\nContacts over MCP \u2014 a full session, no Puter required.\u001b[0m\n\u001b[2m3 contacts seeded in the fake cloud.\n\u001b[0m\n \u001b[33m\

Answers recorded for this run

Local or hosted: local

Suggested next step (agent-reported): None required for the server. The demo script should use a write-capable caller (or skip the create step) so npm run mcp:demo exits 0.

What the agent did

Contacts MCP server (src/contacts): npm run mcp:demo runs a real MCP session over the server: initialize, tools/list (4 calendar-granted tools), tools/call search_contacts and suggest_recipients returning real results. The create_contact step is refused by the calendar grant and the demo script then throws, exit 1.

Read root README.md (catalog only, no install command) and src/contacts/README.md
Installed Node.js 22.12.0 from https://nodejs.org/dist/v22.12.0 into /opt/node22 (apt only had 18.19); apt-get install xz-utils to unpack it
cd src/contacts && NODE_USE_ENV_PROXY=1 npm install (exit 0)
NODE_USE_ENV_PROXY=1 npm run mcp:demo (exit 1 at create_contact step)
Earlier attempts (2)

Haiku 5.5

Native agent · Recorded operation failed

Operation / attempted scope limited checks

Agent-reported scope: Contacts MCP server (src/contacts): initialize handshake, tools/list, and read tool calls search_contacts and suggest_recipients via the documented `npm run mcp:demo`, all against the real server code with an in-memory store.

Run details
run
HeyPuter--everything-claude-haiku-5-5-1792284893054766376
date
Oct 17, 2026
time to working
not recorded
product hosting / execution
Not recorded
recorded operation scope
limited checks
model
claude-haiku-5-5
agent / version
claude-code / 2.1.300 (Claude Code)
platform
linux
reported cost
$0.014025
Recorded source
https://github.com/HeyPuter/everything
Tool transport
mcp-assigned-vm
Test version
readme-508462a99ba6c45473094c91c7b73d8090c06158165b92f97626e2d7928c0d56
revision
fe402697b27949b8e26c44e205bac9088798a7e7
Current diagnosis: unknown · fix verification did not pass

HeyPuter/everything src/contacts/scripts/mcp-demo.js starts its server as callerApp calendar (READ_METHODS only per ALLOWED_CALLERS), then calls create_contact -> Unknown tool. Demo should run as the ai app, which holds the write grant.

Repair record fix-recovery-everything-patch-20261026 · current status JSON. Original run outcomes remain unchanged.

Failed run: HeyPuter/everything · Oct 17, 2026 · Recorded operation failed.

Fix verification: HeyPuter/everything · Oct 26, 2026 · Recorded operation failed.

Double-checks failed run: HeyPuter/everything · Oct 16, 2026.

Fix: fix-60870a6759a8d95c94e4.

Saved before the Q1 checker correction (f4b66c0); retained as older evidence. Fresh R5 records are separate.

Recorded blocker / warning

Step: npm run mcp:demo (src/contacts README, Development section): fails at the create_contact step

Demo script defect: it calls create_contact on a server granted only calendar read methods.

Install / setup / connection checks
[
  {
    "status": "PASS",
    "details": {
      "working": false,
      "argv": [
        "npm",
        "install"
      ],
      "kind": "cli",
      "returncode": 0,
      "stdout": "\nup to date, audited 142 packages in 757ms\n\n40 packages are looking for funding\n  run `npm fund` for details\n\n12 vulnerabilities (3 moderate, 6 high, 3 critical)\n\nTo address issues that do not require attention, run:\n  npm audit fix\n\nTo address all issues (including breaking changes), run:\n[excerpt truncated]",
      "stderr": "",
      "needs_credentials": false,
      "needs_browser": false,
      "scope": "partial: install"
    },
    "check": "install",
    "optional": false
  },
  {
    "status": "FAIL",
    "details": {
      "working": false,
      "argv": [
        "npm",
        "run",
        "mcp:demo"
      ],
      "kind": "cli",
      "returncode": 1,
      "stdout": "\n> [email protected] mcp:demo\n> node scripts/mcp-demo.js\n\n[1m\nContacts over MCP \u2014 a full session, no Puter required.[0m\n[2m3 contacts seeded in the fake cloud.\n[0m\n  [33m\u2190[0m ready [2m(notification)[0m\n[2mServer up for \"calendar\". Tools offered: search_contacts, list_contacts, suggest_recipients, get_contact[0m\n[2m(That first \u2190 is the app-to-app protocol's greeting \u2014 an MCP client ignores it.)[0m\n\n[excerpt truncated]",
      "stderr": "file:///workspace/src/contacts/scripts/mcp-demo.js:174\nconst radiaId = created.result.structuredContent.contact.id\n                               ^\n\nTypeError: Cannot read properties of undefined (reading 'structuredContent')\n    at file:///workspace/src/contacts/scripts/mcp-demo.js:174:32\n\nNode.js v22.23.3",
      "needs_credentials": false,
      "needs_browser": false,
      "blocker": "product invocation failed: {\"returncode\": 1, \"stdout\": \"\\n> [email protected] mcp:demo\\n> node scripts/mcp-demo.js\\n\\n\\u001b[1m\\nContacts over MCP \\u2014 a full session, no Puter required.\\u001b[0m\\n\\u001b[2m3 contacts seeded in the fake cloud.\\n\\u001b[0m\\n  \\u001b[33m\\u2190\\u001b[0m ready \\u001b[2m(notification)\\u001b[0m\\n\\u001b[2mServer up for \\\"calendar\\\". Tools offered: search_contacts, list_contacts, suggest_recipients, get_contact\\u001b[0m\\n\\u001b[2m(That first \\u2190 is the app-to-app protocol's greeting \\u2014 an MCP client ignores it.)\\u001b[0m\\n\\n\\u001b[1m\\u2500\\u2500 Handshake \\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u001b[0m\\n  \\u001b[36m\\u2192\\u001b[0m initialize\\u001b[2m #1\\u001b[0m\\n      \\u001b[2m{\\\"protocolVersion\\\":\\\"2025-06-18\\\",\\\"clientInfo\\\":{\\\"name\\\":\\\"demo\\\",\\\"version\\\":\\\"1\\\"}}\\u001b[0m\\n  \\u001b[32m\\u2190\\u001b[0m \\u001b[32mok\\u001b[0m\\n      \\u001b[2m{\\\"protocolVersion\\\":\\\"2025-06-18\\\",\\\"capabilities\\\":{\\\"tools\\\":{\\\"listChanged\\\":false},\\\"resources\\\":{\\\"listChanged\\\":true,\\\"subscribe\\\":false}},\\\"serverInfo\\\":{\\\"name\\\":\\\"contacts\\\",\\\"title\\\":\\\"Contacts\\\",\\\"version\\\":\\\"1.0.0\\\"},\\u2026 \\u001b[2m(+531 chars)\\u001b[0m\\u001b[0m\\n  \\u001b[36m\\u2192\\u001b[0m notifications/initialized \\u001b[2m(notification)\\u001b[0m\\n      \\u001b[2m(no reply \\u2014 JSON-RPC forbids replying to a notification)\\u001b[0m\\n\\n\\u001b[1m\\u2500\\u2500 What can it do? \\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u001b[0m\\n  \\u001b[36m\\u2192\\u001b[0m tools/list\\u001b[2m #2\\u001b[0m\\n  \\u001b[32m\\u2190\\u001b[0m \\u001b[32mok\\u001b[0m\\n      \\u001b[2m{\\\"tools\\\":[{\\\"name\\\":\\\"search_contacts\\\",\\\"title\\\":\\\"Search contacts\\\",\\\"description\\\":\\\"Search the user's address book across every field \\u2014 name, email, phone, company, job title, tags, notes and address. Use th\\u2026 \\u001b[2m(+2543 chars)\\u001b[0m\\u001b[0m\\n      search_contacts\\u001b[2m \\u2014 Search contacts\\u001b[0m\\n      list_contacts\\u001b[2m \\u2014 List contacts\\u001b[0m\\n      suggest_recipients\\u001b[2m \\u2014 Suggest recipients\\u001b[0m\\n      get_contact\\u001b[2m \\u2014 Get a contact\\u001b[0m\\n\\n\\u001b[1m\\u2500\\u2500 Find someone \\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u001b[0m\\n  \\u001b[36m\\u2192\\u001b[0m tools/call\\u001b[2m #3\\u001b[0m\\n      \\u001b[2m{\\\"name\\\":\\\"search_contacts\\\",\\\"arguments\\\":{\\\"query\\\":\\\"engines\\\"}}\\u001b[0m\\n  \\u001b[32m\\u2190\\u001b[0m \\u001b[32mok\\u001b[0m\\n      1 contact:\\n      \\u2605 Ada Lovelace \\u00b7 Founder \\u00b7 Analytical Engines \\u00b7 <email> \\u00b7 #pioneers  [4ecec3b1-cd6d-4559-b831-cde64e7df87d]\\n      \\u001b[2m+ structuredContent (373 bytes of exact JSON)\\u001b[0m\\n\\n\\u001b[1m\\u2500\\u2500 Who can I email? \\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u001b[0m\\n  \\u001b[36m\\u2192\\u001b[0m tools/call\\u001b[2m #4\\u001b[0m\\n      \\u001b[2m{\\\"name\\\":\\\"suggest_recipients\\\",\\\"arguments\\\":{\\\"query\\\":\\\"a\\\"}}\\u001b[0m\\n  \\u001b[32m\\u2190\\u001b[0m \\u001b[32mok\\u001b[0m\\n      2 matching addresses:\\n      Ada Lovelace <<email>> (Work, Analytical Engines)  [4ecec3b1-cd6d-4559-b831-cde64e7df87d]\\n      Alan Turing <<email>> (Work, Bletchley Park)  [dce31b71-4dd5-43e0-9434-9fb6bd5a1f24]\\n      \\u001b[2m+ structuredContent (353 bytes of exact JSON)\\u001b[0m\\n\\n\\u001b[1m\\u2500\\u2500 Add someone \\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u2500\\u001b[0m\\n  \\u001b[36m\\u2192\\u001b[0m tools/call\\u001b[2m #5\\u001b[0m\\n      \\u001b[2m{\\\"name\\\":\\\"create_contact\\\",\\\"arguments\\\":{\\\"firstName\\\":\\\"Radia\\\",\\\"lastName\\\":\\\"Perlman\\\",\\\"company\\\":\\\"Spanning Tree\\\",\\\"emails\\\":[{\\\"label\\\":\\\"Work\\\",\\\"value\\\":\\\"<email>\\\"}],\\\"tags\\\":[\\\"pioneers\\\"]}}\\u001b[0m\\n  \\u001b[33m\\u2190\\u001b[0m \\u001b[33merror -32602\\u001b[0m  Unknown tool \\\"create_contact\\\"\\n\", \"stderr\": \"file:///workspace/src/contacts/scripts/mcp-demo.js:174\\nconst radiaId = created.result.structuredContent.contact.id\\n                               ^\\n\\nTypeError: Cannot read properties of undefined (reading 'structuredContent')\\n    at file:///workspace/src/contacts/scripts/mcp-demo.js:174:32\\n\\nNode.js v22.23.3\\n\", \"needs_credentials\": false, \"needs_browser\": false}"
    },
    "check": "list_tools",
    "optional": false
  }
]
Answers recorded for this run

Local or hosted: local

Suggested next step (agent-reported): In scripts/mcp-demo.js, either register the fake server with a caller that has the write grant (for example 'ai'), or skip the create/update/delete steps when the grant lacks them. Then rerun `npm run mcp:demo` in src/contacts.

What the agent did

Contacts MCP server (src/contacts): initialize handshake, tools/list, and read tool calls search_contacts and suggest_recipients via the documented `npm run mcp:demo`, all against the real server code with an in-memory store.

Installed Node.js 22 via NodeSource setup_22.x + apt nodejs (v22.23.3, npm 10.9.9) because the guest had no node
cd src/contacts && npm install (rc 0; npm audit reports 12 vulnerabilities, not addressed)
npm run mcp:demo (rc 1; handshake, tools/list, search_contacts, suggest_recipients succeeded; failed at create_contact)
Wrote .coldpass/probe.json and .coldpass/observed.json

Haiku 5.5

Native agent · Recorded operation failed

Operation / attempted scope Covers install, dev-server start, and a single HTTP GET. Not exercised: sending requests in the UI, Puter.js cloud sync, Playwright e2e tests, unit tests, and the browser-based UI (no browser installed; the shared CDP endpoint was not used). The repo has no MCP server, so no tools/list step applies.

Agent-reported scope: Started the API Client Vite dev server (npm run dev in src/api-client) and fetched http://127.0.0.1:5173/ which returned HTTP 200 with the API Client index.html.

Run details
run
HeyPuter--everything-claude-haiku-5-5-1792224835578539008
date
Oct 17, 2026
time to working
not recorded
product hosting / execution
Not recorded
recorded operation scope
Covers install, dev-server start, and a single HTTP GET. Not exercised: sending requests in the UI, Puter.js cloud sync, Playwright e2e tests, unit tests, and the browser-based UI (no browser installed; the shared CDP endpoint was not used). The repo has no MCP server, so no tools/list step applies.
model
claude-haiku-5-5
agent / version
claude-code / 2.1.300 (Claude Code)
platform
linux
reported cost
$0.008042
Recorded source
https://github.com/HeyPuter/everything
Tool transport
mcp-assigned-vm
Test version
readme-359f3439af01dab84b3b7a5ff69ed13014bb7581c8e2819eac980c531de7c5ef
revision
fe402697b27949b8e26c44e205bac9088798a7e7
Current diagnosis: unknown · resolved

superseded; repo HeyPuter/everything has a later non-harness result a recorded run

Repair record fix-5636f3933c951fde7a53 · current status JSON. Original run outcomes remain unchanged.

Failed run: HeyPuter/everything · Oct 17, 2026 · Recorded operation failed.

Test-repair rerun: HeyPuter/everything · Oct 18, 2026 · Checked operation passed.

Fix: fix-5636f3933c951fde7a53.

Saved before the Q1 checker correction (f4b66c0); retained as older evidence. Fresh R5 records are separate.

Recorded blocker / warning

Step: cd /workspace && mkdir -p .coldpass && ls -la .coldpass && cat > .coldpass/probe.json <<'EOF' {"kind":"http","argv":[],"cwd":"/workspace","url":"http://127.0.0.1:5173/","env":{}} EOF cat > .coldpass/report.json <<'EOF' {"outcome":"working","operation":"Started the API Client Vite dev server (npm run dev in src/api-client) and fetched http://127.0.0.1:5173/ which returned HTTP 200 with the API Client index.html.","operation_scope":"Covers install, dev-server start, and a single HTTP GET. Not exercised: sending requests in the UI, Puter.js cloud sync, Playwright e2e tests, unit tests, and the browser-based UI (no browser installed; the shared CDP endpoint was not used). The repo has no MCP server, so no tools/list step applies.","steps":["Read /workspace/README.md; Getting started says: cd src/[app-name] && npm install && npm run dev (Node 22.12+ required).","Installed Node v22.14.0 from nodejs.org tarball to /opt/node22 (system had no node; the initial v22.12.0 install triggered an EBADENGINE warning for vite/jsdom deps).","cd src/api-client && npm install (added 103 packages; 0 vulnerabilities; engine warnings only).","Started dev server: npx vite --host 127.0.0.1 --port 5173 --strictPort (equivalent to npm run dev, pinned host/port). Vite v8.3.4 ready.","curl http://127.0.0.1:5173/ returned HTTP 200 with <title>API Client</title>."],"stuck_step":null,"main_blocker":null,"suggested_fix":null} EOF cat > .coldpass/observed.json <<'EOF' {"repo":"HeyPuter/everything","commit":"fe402697b27949b8e26c44e205bac9088798a7e7","app":"src/api-client","node":"v22.14.0","npm_install":"ok (103 packages then +2 on second install)","dev_server":"http://127.0.0.1:5173/ ready (Vite 8.3.4), process left running","http_status":200,"page_title":"API Client","engine_warnings":["lockfile deps require Node ^22.22.2 or >=24 for some transitive packages (jsdom 30, undici 8); install and dev server still succeeded on 22.14.0","vite requires >=22.14 (node 22.12 rejected by install)"]} EOF python3 -I -c "import json;[json.load(open('.coldpass/'+f)) for f in ['probe.json','report.json','observed.json']];print('ok')"; curl -s -o /dev/null -w "%{http_code}\n" http://127.0.0.1:5173/

probe argv must be a nonempty string array

Answers recorded for this run

Local or hosted: local

Suggested next step (agent-reported): Inspect the recorded blocker and correct the README prerequisites or harness error.

What the agent did

Started the API Client Vite dev server (npm run dev in src/api-client) and fetched http://127.0.0.1:5173/ which returned HTTP 200 with the API Client index.html.

Read /workspace/README.md; Getting started says: cd src/[app-name] && npm install && npm run dev (Node 22.12+ required).
Installed Node v22.14.0 from nodejs.org tarball to /opt/node22 (system had no node; the initial v22.12.0 install triggered an EBADENGINE warning for vite/jsdom deps).
cd src/api-client && npm install (added 103 packages; 0 vulnerabilities; engine warnings only).
Started dev server: npx vite --host 127.0.0.1 --port 5173 --strictPort (equivalent to npm run dev, pinned host/port). Vite v8.3.4 ready.
curl http://127.0.0.1:5173/ returned HTTP 200 with <title>API Client</title>.

No product verdict. Run record.

No product verdict. Run record.

No product verdict. Run record.

No product verdict. Run record.

Fix double-checks (4)

Luna

Native agent · Recorded operation failed

Operation / attempted scope README getting-started workflow; Node.js 22.12+ and npm install

Agent-reported scope: Run the Spreadsheet app development server

Run details
run
HeyPuter--everything-gpt-6-luna-1793038510213903328
date
Oct 26, 2026
time to working
not recorded
product hosting / execution
Not recorded
recorded operation scope
README getting-started workflow; Node.js 22.12+ and npm install
model
gpt-6-luna
agent / version
codex / codex-cli 0.164.0
platform
linux
reported cost
not reported (not assumed free)
Recorded source
https://github.com/HeyPuter/everything
Backend
hyperv
Tool transport
mcp-assigned-vm
Requested source pin (not an observed revision)
{"commit": "734ad458ca5fe9443cb1be84115036a2a7d3f925", "url": "https://github.com/HeyPuter/everything"}
Test version
readme-a17389bda4cc696f9601c0c4ff1b2c16e23bfa1d907883b715ccdd9e92ddec56
revision
734ad458ca5fe9443cb1be84115036a2a7d3f925
Current diagnosis: unknown · fix verification did not pass

HeyPuter/everything src/contacts/scripts/mcp-demo.js starts its server as callerApp calendar (READ_METHODS only per ALLOWED_CALLERS), then calls create_contact -> Unknown tool. Demo should run as the ai app, which holds the write grant.

Repair record fix-recovery-everything-patch-20261026 · current status JSON. Original run outcomes remain unchanged.

Failed run: HeyPuter/everything · Oct 17, 2026 · Recorded operation failed.

Fix verification: HeyPuter/everything · Oct 26, 2026 · Recorded operation failed.

Double-checks failed run: HeyPuter/everything · Oct 17, 2026 (a different model than this run).

Fix: fix-recovery-everything-patch-20261026.

Recorded blocker / warning

Step: npm run dev dependency optimization

Installed lucide package is missing icon modules referenced by its entry point

Safety: Review signals: 63 encoded blob, 63 encoded execution, 11 hardcoded secret, 63 known vulnerability. 23 static matches retained as context.

Review signals: 63 encoded blob, 63 encoded execution, 11 hardcoded secret, 63 known vulnerability. 23 static matches retained as context.

Reviewed as expected for a test run: attempted writes that failed, so nothing was written.

Source contains encoded blob; review its purpose. 7 distinct locations. 9 findings.

Source contains encoded execution; review its purpose. 24 distinct locations. 63 findings.

Gitleaks found a possible hardcoded secret; value withheld. 6 distinct locations. 11 findings.

OSV reports a known vulnerability in this dependency version. 8 distinct locations. 51 findings.

8 encoded blob matches retained as context; full list in the evidence.

12 hardcoded secret matches retained as context; full list in the evidence.

OSV scanned supported lockfiles; unpinned dependencies and unsupported formats are outside this check.

A short run cannot establish that code is safe.

Connections show IP addresses; proxies can hide the final hostname.

Tracing covers dispatched commands and their children, not the whole OS; guest root can interfere with tracing.

Only 200 of 2647 findings are stored; the summary counts all of them.

Full safety evidence →

Answers recorded for this run

Local or hosted: local

Suggested next step (agent-reported): Repair the lucide dependency installation or update the app dependency/imports so all referenced icon modules are present.

What the agent did

Run the Spreadsheet app development server

pwd; git status --short --branch; git remote -v; git rev-parse --is-inside-work-tree; rg --files -g 'README*' -g 'AGENTS.md' -g 'package.json' -g 'pyproject.toml' -g 'requirements*.txt' -g 'Makefile' -g 'Dockerfile' -g '*.yml' -g '*.yaml' | head -80
ls -la; find . -maxdepth 2 -type f | head -80
sed -n '1,240p' README.md; python3 --version; id -u; ls -la .coldpass
ls src | head; ls src/spreadsheet; cat src/spreadsheet/package.json; node --version; npm --version
cd src/spreadsheet && npm install && npm run dev -- --host 0.0.0.0 > /tmp/spreadsheet-dev.log 2>&1 &
cat /tmp/spreadsheet-dev.log; curl -sS -D /tmp/hdr http://127.0.0.1:5173/ -o /tmp/body; head -3 /tmp/hdr; head -c 300 /tmp/body; ps aux | grep '[v]ite'
cd src/spreadsheet && npm install
cd src/spreadsheet && npm install
cd src/spreadsheet && npm run dev -- --host 0.0.0.0 > /tmp/spreadsheet-dev.log 2>&1 & echo $! > /tmp/spreadsheet.pid; sleep 2; cat /tmp/spreadsheet-dev.log; curl -sS http://127.0.0.1:5173/ | head -c 300; kill $(cat /tmp/spreadsheet.pid) 2>/dev/null || true
mkdir -p .coldpass; cat > .coldpass/claims.json <<'EOF'
[{"kind":"claim","claim":"Getting started supports running an app development server","source":"npm run dev","input":"Spreadsheet development server","expected":"Vite development server starts","probe_kind":"cli","argv":["npm","run","dev","--","--host","0.0.0.0"],"expected_returncode":1,"expected_text":"Could not resolve './icons/tv.mjs'","cwd":"<guest-path>"}]
EOF
cat > .coldpass/probe.json <<'EOF'
{"kind":"cli","argv":["npm","run","dev","--","--host","0.0.0.0"],"cwd":"<guest-path>","expected_returncode":1,"expected_text":"Could not resolve './icons/tv.mjs'"}
EOF
cat > .coldpass/examples.json <<'EOF'
[{"kind":"example","claim":"README Getting started workflow","source":"README.md#Getting started","input":"Spreadsheet app","expected":"npm dependencies install; dev server starts","argv":["npm","install"],"cwd":"<guest-path>"}]
EOF
cat > .coldpass/cycles.json <<'EOF'
{"detected":false,"reason":"README documents app development servers but no cron, scheduling, looping, webhook, or cycle behavior; inspected app package scripts for Spreadsheet.","checks":[]}
EOF
cat > .coldpass/report.json <<'EOF'
{"outcome":"blocked","fault_owner":"repo","operation":"Run the Spreadsheet app development server","operation_scope":"README getting-started workflow; Node.js 22.12+ and npm install","steps":["Checked Node.js 22.23.4 against README minimum 22.12","Ran npm install successfully in src/spreadsheet","Ran npm run dev -- --host 0.0.0.0"],"deviations":["Initial npm install failed with ENOTEMPTY during npm cleanup; retry succeeded","The documented dev command exits after Vite dependency optimization reports 91 unresolved lucide icon imports, including ./icons/tv.mjs"],"stuck_step":"npm run dev dependency optimization","main_blocker":"Installed lucide package is missing icon modules referenced by its entry point","plain_failure":"The Spreadsheet development server cannot start because Vite cannot resolve many lucide icon files.","suggested_fix":"Repair the lucide dependency installation or update the app dependency/imports so all referenced icon modules are present."}
EOF
<env-var>=<guest-path> python3 -I <guest-path> --validate --replay

Haiku 5.5

Native agent · Checked operation passed

Checked operation npm run mcp:demo

Agent-reported scope: Contacts MCP server (src/contacts) started via the README-documented `npm run mcp:demo`: MCP initialize handshake, tools/list (7 tools), tools/call search_contacts / suggest_recipients / create_contact, resources/read of contact://<id> as vCard 3.0, and tool-error and protocol-error paths. Exit code 0 with the session-complete banner.

Run details
run
HeyPuter--everything-claude-haiku-5-5-1792304956244385591
date
Oct 18, 2026
time to working
98.4s
product hosting / execution
Local command in the guest
recorded operation scope
product operation
model
claude-haiku-5-5
agent / version
claude-code / 2.1.300 (Claude Code)
platform
linux
reported cost
$0.010131
Recorded source
https://github.com/HeyPuter/everything
Tool transport
mcp-assigned-vm
Test version
readme-08dbe418cab0ce4c03a9bda5fc2d4c6dc2f0451994594b77dae934b144d9cff7
revision
96814b61df9b0c40d7b72fed92888ee14e86e544
Current diagnosis: unknown · fix verification did not pass

HeyPuter/everything src/contacts/scripts/mcp-demo.js starts its server as callerApp calendar (READ_METHODS only per ALLOWED_CALLERS), then calls create_contact -> Unknown tool. Demo should run as the ai app, which holds the write grant.

Repair record fix-recovery-everything-patch-20261026 · current status JSON. Original run outcomes remain unchanged.

Failed run: HeyPuter/everything · Oct 17, 2026 · Recorded operation failed.

Fix verification: HeyPuter/everything · Oct 26, 2026 · Recorded operation failed.

Double-checks failed run: HeyPuter/everything · Oct 17, 2026.

Fix: fix-g3-heputer-demo2.

Saved before the Q1 checker correction (f4b66c0); retained as older evidence. Fresh R5 records are separate.

Answers recorded for this run

Local or hosted: local

What the agent did

Contacts MCP server (src/contacts) started via the README-documented `npm run mcp:demo`: MCP initialize handshake, tools/list (7 tools), tools/call search_contacts / suggest_recipients / create_contact, resources/read of contact://<id> as vCard 3.0, and tool-error and protocol-error paths. Exit code 0 with the session-complete banner.

Read /workspace/README.md; Getting started requires Node.js 22.12+ and `cd src/[app-name] && npm install && npm run dev`
Chose src/contacts because it is the app that documents an MCP server (README 'MCP' section)
Installed Node.js 22: curl -fsSL https://deb.nodesource.com/setup_22.x | bash - && apt-get install -y nodejs (node v22.23.3, npm 10.9.9)
cd src/contacts && npm install (rc=0; npm audit reported 12 advisories, not addressed)
cd src/contacts && npm run mcp:demo (rc=0, 'Session complete')

Haiku 5.5

Native agent · Checked operation passed

Checked operation /usr/local/bin/npm run mcp:demo

Agent-reported scope: Ran the Contacts app's documented MCP session demo (npm run mcp:demo) against the real MCP server: initialize handshake, tools/list, search_contacts, suggest_recipients, create_contact, resources/read of a contact vCard, and tool-error and protocol-error handling. Exit 0, 'Session complete'.

Run details
run
HeyPuter--everything-claude-haiku-5-5-1792304598594412472
date
Oct 18, 2026
time to working
88.4s
product hosting / execution
Local command in the guest
recorded operation scope
product operation
model
claude-haiku-5-5
agent / version
claude-code / 2.1.300 (Claude Code)
platform
linux
reported cost
$0.011278
Recorded source
https://github.com/HeyPuter/everything
Tool transport
mcp-assigned-vm
Test version
readme-08dbe418cab0ce4c03a9bda5fc2d4c6dc2f0451994594b77dae934b144d9cff7
revision
96814b61df9b0c40d7b72fed92888ee14e86e544
Current diagnosis: unknown · fix verification did not pass

HeyPuter/everything src/contacts/scripts/mcp-demo.js starts its server as callerApp calendar (READ_METHODS only per ALLOWED_CALLERS), then calls create_contact -> Unknown tool. Demo should run as the ai app, which holds the write grant.

Repair record fix-recovery-everything-patch-20261026 · current status JSON. Original run outcomes remain unchanged.

Failed run: HeyPuter/everything · Oct 17, 2026 · Recorded operation failed.

Fix verification: HeyPuter/everything · Oct 26, 2026 · Recorded operation failed.

Double-checks failed run: HeyPuter/everything · Oct 17, 2026.

Fix: fix-g3-heputer-demo2.

Saved before the Q1 checker correction (f4b66c0); retained as older evidence. Fresh R5 records are separate.

Answers recorded for this run

Local or hosted: local

What the agent did

Ran the Contacts app's documented MCP session demo (npm run mcp:demo) against the real MCP server: initialize handshake, tools/list, search_contacts, suggest_recipients, create_contact, resources/read of a contact vCard, and tool-error and protocol-error handling. Exit 0, 'Session complete'.

Read /workspace/README.md; the per-app quickstart is 'cd src/[app-name] && npm install && npm run dev'. Chose src/contacts, which documents an MCP server and an offline demo.
Installed Node.js 22.12.0 (README requires 22.12+): downloaded node-v22.12.0-linux-x64.tar.xz from nodejs.org and extracted to /opt/node22, symlinked node/npm/npx into /usr/local/bin.
cd src/contacts && npm install (exit 0; npm audit reported 12 vulnerabilities in dev dependencies, not addressed).
cd src/contacts && npm run mcp:demo (exit 0, 'Session complete').

Haiku 5.5

Native agent · Checked operation passed

Checked operation /usr/bin/npm run mcp:demo

Agent-reported scope: Contacts MCP server: initialize, tools/list, search/suggest/create tool calls, vCard resource read, and error handling, via the README's 'npm run mcp:demo' (MCP section).

Run details
run
HeyPuter--everything-claude-haiku-5-5-1792300760205614879
date
Oct 18, 2026
time to working
99.5s
product hosting / execution
Local command in the guest
recorded operation scope
product operation
model
claude-haiku-5-5
agent / version
claude-code / 2.1.300 (Claude Code)
platform
linux
reported cost
$0.011525
Recorded source
https://github.com/HeyPuter/everything
Tool transport
mcp-assigned-vm
Test version
readme-306059071b890b7a0173cd37731adb3ab770bd66cdc80ae10646c97236550c3d
revision
af792feaec00f42261df1219ec87d38b02f7b1b4
Current diagnosis: unknown · fix verification did not pass

HeyPuter/everything src/contacts/scripts/mcp-demo.js starts its server as callerApp calendar (READ_METHODS only per ALLOWED_CALLERS), then calls create_contact -> Unknown tool. Demo should run as the ai app, which holds the write grant.

Repair record fix-recovery-everything-patch-20261026 · current status JSON. Original run outcomes remain unchanged.

Failed run: HeyPuter/everything · Oct 17, 2026 · Recorded operation failed.

Fix verification: HeyPuter/everything · Oct 26, 2026 · Recorded operation failed.

Double-checks failed run: HeyPuter/everything · Oct 17, 2026.

Fix: fix-g3-heputer-demo.

Saved before the Q1 checker correction (f4b66c0); retained as older evidence. Fresh R5 records are separate.

Answers recorded for this run

Local or hosted: local

What the agent did

Contacts MCP server: initialize, tools/list, search/suggest/create tool calls, vCard resource read, and error handling, via the README's 'npm run mcp:demo' (MCP section).

Read /workspace/README.md; Getting started points to src/[app-name]; chose src/contacts (the MCP server app per its README).
Installed Node.js 22 (v22.23.3, npm 10.9.9) via NodeSource setup_22.x + apt (nodejs package).
cd /workspace/src/contacts && npm install (src/contacts/README.md Development section) -> exit 0.
npm run mcp:demo (src/contacts/README.md MCP section, 'Seeing it work') -> exit 0, ends with 'Session complete.'
Repair work and diagnoses (1)

Haiku 5.5

Native agent · Repair work (development) · not an initial-trial result

Operation / attempted scope /opt/node22/bin/npm run mcp:demo

Agent-reported scope: Contacts MCP session via README command `npm run mcp:demo` (src/contacts): initialize, tools/list, search, suggest, create contact, vCard resource read, and tool/protocol error handling against the real server.

Run details
run
HeyPuter--everything-claude-haiku-5-5-1792306694426713361
date
Oct 18, 2026
time to working
209.7s (recorded; checker proof unavailable)
product hosting / execution
Local command in the guest
recorded operation scope
product operation
model
claude-haiku-5-5
agent / version
claude-code / 2.1.300 (Claude Code)
platform
linux
reported cost
$0.020260
Recorded source
https://github.com/HeyPuter/everything
Tool transport
mcp-assigned-vm
Test version
readme-44d3975f003bf712462048b7b5f9676667513b8946dce268d16f7fdcb03cc4ac
revision
fe402697b27949b8e26c44e205bac9088798a7e7
Current diagnosis: unknown · resolved

A pass row for this fix landed 07:09Z; the 08:12Z repair run hung in the cli probe (npm run dev never exits) (probe timeout).

Repair record fix-7643e9848a0bf93c5f1e · current status JSON. Original run outcomes remain unchanged.

Failed run: HeyPuter/everything · Oct 18, 2026 · Recorded operation failed.

Repair development: HeyPuter/everything · Oct 18, 2026 · Repair work (development) · not an initial-trial result.

Double-checks failed run: HeyPuter/everything · Oct 18, 2026.

Fix: fix-7643e9848a0bf93c5f1e.

Saved before the Q1 checker correction (f4b66c0); retained as older evidence. Fresh R5 records are separate.

Answers recorded for this run

Local or hosted: local

What the agent did

Contacts MCP session via README command `npm run mcp:demo` (src/contacts): initialize, tools/list, search, suggest, create contact, vCard resource read, and tool/protocol error handling against the real server.

Read README.md (root) and src/contacts/README.md
Installed Node.js v22.23.3 to /opt/node22 from nodejs.org (README requires Node >= 22.12)
cd src/contacts && npm install (exit 0; audit warnings only)
npm run mcp:demo (after fix below) exit 0, printed 'Session complete'
Probe re-run in a clean env: exit 0