{
  "run_id": "icip-cas--PPTAgent-gpt-6-luna-1792855554496864415",
  "date": "2026-10-24T15:36:08.464174+00:00",
  "repo": "icip-cas/PPTAgent",
  "kind": "repo",
  "source": "https://github.com/icip-cas/PPTAgent",
  "commit": "833cda553b343be0e486a93b0b57cac962cdd566",
  "model": "gpt-6-luna",
  "model_version": "gpt-6-luna",
  "test_version": "readme-20cd1bc4ab0be6730266a08d7400e342dd7d403c08aabf42aab2e51dc9b34ce0",
  "pass": true,
  "outcome": "pass",
  "time_to_working_s": 569.948742217035,
  "total_s": 613.9672820568085,
  "steps": [
    "cd <guest-path> && vault-search 'PPTAgent render review browser' 2>&1; cat <host-path> 2>/dev/null; cat ~/.agents/skills/i-have-adhd/SKILL.md 2>/dev/null; cat ~/.agents/skills/ponytail/SKILL.md 2>/dev/null; cat ~/.agents/skills/p3-mode/SKILL.md 2>/dev/null; pwd; git status --short; rg --files -g 'README*' -g 'AGENTS.md' -g 'p3-models.md' -g '*.md' | head -80",
    "cd <guest-path> && ls -la && find .. -name AGENTS.md -o -name README.md -o -name README.rst | head -80",
    "cd <guest-path> && cat README.md && cat AGENTS.md && cat skills/pptagent/README.md && python3 --version && id -u && env | grep -E '^(CDP_URL|<env-var>|PYTHONPATH|COLDPASS_SHARED_BROWSER)='",
    "cd <guest-path> && curl -sS -i \"$CDP_URL/json/version\"; command -v uv || true; command -v npm || true; command -v libreoffice || true; command -v chromium || true; ls skills/pptagent; sed -n '1,220p' skills/pptagent/scripts/pptagent.py",
    "sudo -n apt-get update && sudo -n apt-get install -y npm libreoffice-impress && curl -LsSf https://astral.sh/uv/install.sh | sh",
    "cd <guest-path> && export PATH=\"$HOME/.local/bin:$PATH\" && uv venv --python 3.12 .venv && uv pip install --python .venv/bin/python -r requirements.txt",
    "sudo -n apt-get install -y python3.12-dev",
    "cd <guest-path> && export PATH=\"$HOME/.local/bin:$PATH\" && uv pip install --python .venv/bin/python -r requirements.txt",
    "cd <guest-path> && .venv/bin/python scripts/install.py --client opencode",
    "cd <guest-path> && .venv/bin/python scripts/pptagent.py doctor",
    "sed -n '1,240p' <guest-path> 2>/dev/null; find <guest-path> -maxdepth 2 -type f -print; cd <guest-path> && sed -n '1,180p' scripts/pptagent.py | tail -20 && sed -n '220,380p' scripts/pptagent.py",
    "cd <guest-path> && sed -n '1,260p' pptagent_runtime/core.py 2>/dev/null || find . -maxdepth 2 -type f",
    "cd <guest-path> && git init && git remote add origin https://github.com/icip-cas/PPTAgent.git && git fetch --depth 1 origin 833cda553b343be0e486a93b0b57cac962cdd566 && git reset --mixed FETCH_HEAD",
    "cd <guest-path> && git status --short | head -60 && git rev-parse HEAD && git status --short | wc -l",
    "cd <guest-path> && mkdir -p /tmp/pptagent-coldpass && .venv/bin/python scripts/pptagent.py init --workspace /tmp/pptagent-coldpass --slides 1 --language en && .venv/bin/python scripts/pptagent.py scaffold --workspace /tmp/pptagent-coldpass && find /tmp/pptagent-coldpass -maxdepth 2 -type f -print",
    "cd <guest-path> && sed -n '1,200p' assets/slide-template.html && cat package.json && sed -n '1,180p' references/task-contract.md",
    "cd <guest-path> && PYTHONPATH=<guest-path> COLDPASS_SHARED_BROWSER=$CDP_URL <env-var>=<guest-path> COLDPASS_BROWSER_FILE_ROOT=/tmp .venv/bin/python scripts/pptagent.py review-slides --workspace /tmp/pptagent-coldpass",
    "cat > /tmp/pptagent-coldpass/slides/slide01.html <<'EOF'\n<!doctype html>\n<html lang=\"en\">\n<head><meta charset=\"utf-8\"><style>html,body{width:1280px;height:720px;margin:0}body{font-family:Arial;background:#f4f1ea;color:#182231}.slide{padding:48px}h1{font-size:44px}.message{font-size:22px}</style></head>\n<body><main class=\"slide\"><p>SLIDE 1</p><h1>AI coding assistants accelerate delivery</h1><p class=\"message\">Teams can spend more time reviewing designs and less time on repetitive implementation.</p></main></body>\n</html>\nEOF\ncd <guest-path> && PYTHONPATH=<guest-path> COLDPASS_SHARED_BROWSER=$CDP_URL <env-var>=<guest-path> COLDPASS_BROWSER_FILE_ROOT=/tmp .venv/bin/python scripts/pptagent.py review-slides --workspace /tmp/pptagent-coldpass && file /tmp/pptagent-coldpass/qa/slides/slide01.jpg && python3 -c 'from PIL import Image; im=Image.open(\"/tmp/pptagent-coldpass/qa/slides/slide01.jpg\"); print(im.size, im.getbbox())'",
    "cd <guest-path> && .venv/bin/python -c 'from PIL import Image; im=Image.open(\"/tmp/pptagent-coldpass/qa/slides/slide01.jpg\"); print(im.size, im.getbbox())' && ls -l /tmp/pptagent-coldpass/qa/slides/slide01.jpg",
    "cd <guest-path> && mkdir -p .coldpass && cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"cli\",\"argv\":[\"<guest-path>\",\"<guest-path>\",\"review-slides\",\"--workspace\",\"/tmp/pptagent-coldpass\"],\"cwd\":\"<guest-path>\",\"env\":{\"PYTHONPATH\":\"<guest-path>\",\"COLDPASS_SHARED_BROWSER\":\"http://<internal-ip>:9226\",\"<env-var>\":\"<guest-path>\",\"COLDPASS_BROWSER_FILE_ROOT\":\"/tmp\"},\"expected_text\":\"qa/slides/slide01.jpg\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"The skill renders editable HTML slides for visual review.\",\"source\":\"In text mode, the skill sends rendered slides to the visual API and returns review results to your host model.\",\"input\":\"One 1280x720 HTML slide titled AI coding assistants accelerate delivery.\",\"expected\":\"A slide image is rendered at qa/slides/slide01.jpg.\",\"probe_kind\":\"cli\",\"argv\":[\"<guest-path>\",\"<guest-path>\",\"review-slides\",\"--workspace\",\"/tmp/pptagent-coldpass\"],\"cwd\":\"<guest-path>\",\"env\":{\"PYTHONPATH\":\"<guest-path>\",\"COLDPASS_SHARED_BROWSER\":\"http://<internal-ip>:9226\",\"<env-var>\":\"<guest-path>\",\"COLDPASS_BROWSER_FILE_ROOT\":\"/tmp\"},\"expected_text\":\"qa/slides/slide01.jpg\"}]\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[{\"kind\":\"example\",\"claim\":\"Render a sample slide in the documented task workspace.\",\"source\":\"skills/pptagent/README.md#Quick Start\",\"input\":\"Single slide authored in slides/slide01.html\",\"expected\":\"Rendered image is returned by review-slides.\",\"argv\":[\"<guest-path>\",\"<guest-path>\",\"review-slides\",\"--workspace\",\"/tmp/pptagent-coldpass\"],\"cwd\":\"<guest-path>\",\"env\":{\"PYTHONPATH\":\"<guest-path>\",\"COLDPASS_SHARED_BROWSER\":\"http://<internal-ip>:9226\",\"<env-var>\":\"<guest-path>\",\"COLDPASS_BROWSER_FILE_ROOT\":\"/tmp\"},\"expected_text\":\"qa/slides/slide01.jpg\"}]\nEOF\ncat > .coldpass/cycles.json <<'EOF'\n{\"detected\":false,\"reason\":\"The skill workflow is invoked as discrete CLI operations (init, review-slides, build, review-deck, finalize); inspected the CLI command parser and README and found no scheduler or product cycle mechanism.\",\"checks\":[]}\nEOF",
    "<env-var>=<guest-path> python3 -I <guest-path> --validate --replay",
    "cd <guest-path> && cat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"The skill delivers rendered slide previews.\",\"source_file\":\"skills/pptagent/README.md\",\"source\":\"Your task folder also keeps the HTML slide sources, local assets, rendered previews, and a final review report.\",\"input\":\"One 1280x720 HTML slide titled AI coding assistants accelerate delivery.\",\"expected\":\"A slide image is rendered at qa/slides/slide01.jpg.\",\"probe_kind\":\"cli\",\"argv\":[\"<guest-path>\",\"<guest-path>\",\"review-slides\",\"--workspace\",\"/tmp/pptagent-coldpass\"],\"cwd\":\"<guest-path>\",\"env\":{\"PYTHONPATH\":\"<guest-path>\",\"COLDPASS_SHARED_BROWSER\":\"http://<internal-ip>:9226\",\"<env-var>\":\"<guest-path>\",\"COLDPASS_BROWSER_FILE_ROOT\":\"/tmp\"},\"expected_text\":\"qa/slides/slide01.jpg\"}]\nEOF\n",
    "<env-var>=<guest-path> python3 -I <guest-path> --validate --replay",
    "cd <guest-path> && python3 - <<'PY'\nfrom pathlib import Path\np=Path('skills/pptagent/README.md')\nfor i,line in enumerate(p.read_text().splitlines(),1):\n if 'Your task folder' in line or 'deliverable is' in line: print(i,repr(line))\nPY\nsed -n '1,220p' <guest-path>",
    "rg -n 'source_file|expected_file|kind.*claim|probe_kind' <guest-path> | tail -30",
    "grep -n 'source_file\\|claims.json\\|expected_file' <guest-path> | tail -35",
    "cd <guest-path> && cat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"The skill keeps rendered previews in the task folder.\",\"source_file\":\"skills/pptagent/README.md\",\"source\":\"rendered previews\",\"input\":\"One 1280x720 HTML slide titled AI coding assistants accelerate delivery.\",\"expected\":\"A slide image is rendered at qa/slides/slide01.jpg.\",\"probe_kind\":\"cli\",\"argv\":[\"<guest-path>\",\"<guest-path>\",\"review-slides\",\"--workspace\",\"/tmp/pptagent-coldpass\"],\"cwd\":\"<guest-path>\",\"env\":{\"PYTHONPATH\":\"<guest-path>\",\"COLDPASS_SHARED_BROWSER\":\"http://<internal-ip>:9226\",\"<env-var>\":\"<guest-path>\",\"COLDPASS_BROWSER_FILE_ROOT\":\"/tmp\"},\"expected_text\":\"qa/slides/slide01.jpg\"}]\nEOF",
    "<env-var>=<guest-path> python3 -I <guest-path> --validate --replay",
    "cd <guest-path> && cat > .coldpass/report.json <<'EOF'\n{\"outcome\":\"working\",\"fault_owner\":null,\"operation\":\"Render and visually review an HTML slide using PPTAgent Skill CLI over shared Chromium CDP.\",\"operation_scope\":\"One slide at 1280x720; Python 3.12 venv, Node/npm, LibreOffice, and supplied remote browser relay.\",\"steps\":[\"Read skills/pptagent/README.md Quick Start and task contract.\",\"Installed documented Debian dependencies with sudo apt-get install npm libreoffice-impress; installed Python 3.12 development headers required to build declared fasttext dependency.\",\"Installed uv, created .venv with Python 3.12, and installed requirements.txt.\",\"Ran scripts/install.py --client opencode, as documented.\",\"Initialized a one-slide workspace, scaffolded its HTML source, and ran scripts/pptagent.py review-slides.\",\"Replayed probe, README claim, example, and cycle inspection through the checker successfully.\"],\"deviations\":[\"README's playwright install --with-deps chromium step was not run because browser installation is prohibited. Captured HTTP 200 from $CDP_URL/json/version (Chrome/155.0.8059.84) and used the supplied Playwright CDP adapter instead; product rendered a 1280x720 JPEG successfully.\",\"Initial requirements installation failed because Python.h was absent (fasttext build); installed python3.12-dev and reran successfully.\",\"Doctor reports html2pptx:runtime false because its local Chromium binary is absent; browser-backed skill slide rendering through the shared relay works.\"],\"stuck_step\":null,\"main_blocker\":null,\"plain_failure\":null,\"suggested_fix\":null}\nEOF\ncat .coldpass/report.json",
    "test -s .coldpass/probe.json && test -s .coldpass/report.json && test -s .coldpass/claims.json"
  ],
  "stuck_step": null,
  "error_excerpt": null,
  "what_it_did": "Render and visually review an HTML slide using PPTAgent Skill CLI over shared Chromium CDP.",
  "suggested_fix": null,
  "tokens_in": 1558616,
  "tokens_out": 4398,
  "cost_usd": null,
  "usage_complete": true,
  "checks": [
    {
      "check": "operation",
      "status": "PASS",
      "details": {
        "working": true,
        "argv": [
          "<guest-path>",
          "<guest-path>",
          "review-slides",
          "--workspace",
          "/tmp/pptagent-coldpass"
        ],
        "kind": "cli",
        "returncode": 0,
        "stdout": "{\n  \"ok\": true,\n  \"renders\": [\n    \"qa/slides/slide01.jpg\"\n  ],\n  \"count\": 1,\n  \"review_mode\": \"host\",\n  \"instruction\": \"Inspect every render with the host image viewer, then call record-slide-review for each current slide.\"\n}",
        "stderr": "",
        "needs_credentials": false,
        "needs_browser": false,
        "scope": "product operation"
      }
    }
  ],
  "safety": {
    "version": "z2x-1",
    "rules_version": "z2x-1",
    "summary": "Review signals: 1 connection review, 75 known vulnerability.",
    "findings": [
      {
        "kind": "connection-review",
        "count": 1,
        "note": "Repository processes attempted these non-loopback connections; proxies can hide the final hostname.",
        "location_count": 1,
        "path": "<internal-ip>:9226",
        "process_count": 8
      },
      {
        "kind": "known-vulnerability",
        "count": 75,
        "note": "OSV reports a known vulnerability in this dependency version.",
        "location_count": 3
      }
    ],
    "context": [],
    "limitations": [
      "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."
    ],
    "static": {
      "dependency_note": "OSV scanned supported lockfiles; unpinned dependencies and unsupported formats are outside this check."
    },
    "evidence_url": "/safety/?run=icip-cas--PPTAgent-gpt-6-luna-1792855554496864415",
    "evidence_file": "/data/safety/icip-cas--PPTAgent-gpt-6-luna-1792855554496864415.json.gz"
  },
  "agent_execution": "native_agent",
  "agent_runtime": "codex",
  "agent_runtime_version": "codex-cli 0.163.0",
  "tool_transport": "mcp-assigned-vm",
  "platform": "linux",
  "reasoning": "low",
  "service_tier": "standard",
  "resources": {
    "cpus": 2,
    "memory_mib": 4096,
    "disk_mib": 32768
  },
  "native_tool_calls": 29,
  "native_bundle": null,
  "architecture": null,
  "backend": "hyperv",
  "platform_details": {
    "backend": "hyperv",
    "os": "linux"
  },
  "platform_conflicts": null,
  "sandbox_source": null,
  "source_pin": {
    "commit": "833cda553b343be0e486a93b0b57cac962cdd566",
    "url": "https://github.com/icip-cas/PPTAgent"
  },
  "purpose": "test_rerun",
  "profile": {
    "model": "gpt-6-luna",
    "reasoning": "low"
  },
  "fault": {
    "owner": null,
    "status": "resolved",
    "reason": null
  },
  "fix_id": null,
  "verifies_run_id": "icip-cas--PPTAgent-gpt-6-luna-1792854325651345859",
  "hosting": null,
  "operation_scope": "product operation",
  "tool_calls": 29,
  "guest_setup": null,
  "runtime": null,
  "runtime_version": null,
  "runtime_revision": null,
  "source_revision": null,
  "evidence_version": null,
  "failure_origin": null,
  "evidence_strength": "readme_checked",
  "works": "yes",
  "install_s": null,
  "first_use_s": null,
  "mcp": "none",
  "needs": [],
  "needs_which": null,
  "agent_interface": [
    "cli"
  ],
  "license": "MIT",
  "repo_url": "https://github.com/icip-cas/PPTAgent",
  "cost_to_try": "free",
  "hardware": null,
  "what_failed": null,
  "local_or_hosted": "local",
  "cycle_checks": [
    {
      "kind": "cycle",
      "claim": "Scheduled or looping main behavior",
      "source": "repository entry points",
      "input": "source inspection",
      "expected": "identify the product trigger",
      "verdict": "yes",
      "outcome": "The skill workflow is invoked as discrete CLI operations (init, review-slides, build, review-deck, finalize); inspected the CLI command parser and README and found no scheduler or product cycle mechanism.",
      "evidence": "The skill workflow is invoked as discrete CLI operations (init, review-slides, build, review-deck, finalize); inspected the CLI command parser and README and found no scheduler or product cycle mechanism.",
      "command": ""
    }
  ],
  "claims": [
    {
      "kind": "claim",
      "claim": "The skill keeps rendered previews in the task folder.",
      "source": "rendered previews",
      "input": "One 1280x720 HTML slide titled AI coding assistants accelerate delivery.",
      "expected": "A slide image is rendered at qa/slides/slide01.jpg.",
      "command": "<guest-path> <guest-path> review-slides --workspace /tmp/pptagent-coldpass",
      "verdict": "yes",
      "outcome": "Real input produced the expected result: qa/slides/slide01.jpg",
      "evidence": "qa/slides/slide01.jpg\"\n  ],\n  \"count\": 1,\n  \"review_mode\": \"host\",\n  \"instruction\": \"Inspect every render with the host image viewer, then call record-slide-review for each current slide.\"\n}\n",
      "returncode": 0,
      "source_checked": true,
      "source_file": "skills/pptagent/README.md"
    }
  ],
  "claims_note": null,
  "example_checks": [
    {
      "kind": "example",
      "claim": "Render a sample slide in the documented task workspace.",
      "source": "skills/pptagent/README.md#Quick Start",
      "input": "Single slide authored in slides/slide01.html",
      "command": "<guest-path> <guest-path> review-slides --workspace /tmp/pptagent-coldpass",
      "evidence": "{\n  \"ok\": true,\n  \"renders\": [\n    \"qa/slides/slide01.jpg\"\n  ],\n  \"count\": 1,\n  \"review_mode\": \"host\",\n  \"instruction\": \"Inspect every render with the host image viewer, then call record-slide-review for each current slide.\"\n}",
      "deferred": false,
      "expected": "Rendered image is returned by review-slides.",
      "returncode": 0,
      "verdict": "yes",
      "outcome": "command completed successfully"
    }
  ],
  "does_what_it_says": "yes",
  "maintenance": {
    "archived": false,
    "commits_90d": 3,
    "last_commit_at": "2026-09-20T22:29:53Z",
    "last_release_at": "2025-12-16T04:15:19Z",
    "median_reply_hours": 6.2,
    "merged_prs_90d": 1,
    "note": "actively maintained: last commit 33 days ago; 3 commits and 1 merged PRs in 90 days; 12 open issues, 6 open PRs; 14 of 37 recent threads got a maintainer reply, median first reply 6.2h; latest release 2025-12-16",
    "open_issues": 12,
    "open_prs": 6,
    "reply_share": 0.38,
    "reply_threads": 37,
    "verdict": "maintained"
  },
  "maintenance_verdict": "maintained",
  "maintenance_note": "actively maintained: last commit 33 days ago; 3 commits and 1 merged PRs in 90 days; 12 open issues, 6 open PRs; 14 of 37 recent threads got a maintainer reply, median first reply 6.2h; latest release 2025-12-16",
  "maintained": "active",
  "maintained_note": "last commit 4 days ago; 9 open issues, 10 answered or closed",
  "last_commit_at": "2026-10-19T21:35:58Z",
  "last_release_at": "2025-12-16T04:15:19Z",
  "open_issues": 9,
  "answered_issues": 10,
  "platforms_claimed": [
    "linux",
    "mac"
  ],
  "topic": "mcp-server",
  "agent_interfaces": [
    {
      "interface": "mcp",
      "evidence": "README metadata",
      "observed": false,
      "operation_checked": false
    },
    {
      "interface": "cli",
      "evidence": "independent checker",
      "observed": true,
      "operation_checked": true
    }
  ],
  "agent_interfaces_note": "README metadata is a discovery hint, not pinned documentation proof. Observed interfaces were exercised in this run. An empty list means unknown.",
  "mcp_context": null,
  "tested_at": "2026-10-24T15:36:08.464174+00:00",
  "tested_commit": "833cda553b343be0e486a93b0b57cac962cdd566",
  "tested_with": {
    "agent": "codex",
    "agent_version": "codex-cli 0.163.0",
    "model": "gpt-6-luna",
    "model_route": "gpt-6-luna",
    "reasoning": "low",
    "os": "linux",
    "backend": "hyperv",
    "transport": "mcp-assigned-vm"
  },
  "setup_identity": {
    "repo": "icip-cas/PPTAgent",
    "source": "https://github.com/icip-cas/PPTAgent",
    "commit": "833cda553b343be0e486a93b0b57cac962cdd566",
    "source_revision": null,
    "os": "linux",
    "architecture": null,
    "backend": "hyperv",
    "model": "gpt-6-luna",
    "model_version": "gpt-6-luna",
    "agent_execution": "native_agent",
    "agent_runtime": "codex",
    "agent_runtime_version": "codex-cli 0.163.0",
    "tool_transport": "mcp-assigned-vm",
    "runtime": null,
    "runtime_version": null,
    "runtime_revision": null,
    "sandbox_source": null,
    "guest_setup": null,
    "source_pin": {
      "commit": "833cda553b343be0e486a93b0b57cac962cdd566",
      "url": "https://github.com/icip-cas/PPTAgent"
    },
    "platform_details": {
      "os": "linux",
      "backend": "hyperv"
    },
    "platform_conflicts": null,
    "reasoning": "low",
    "service_tier": "standard",
    "resources": {
      "cpus": 2,
      "memory_mib": 4096,
      "disk_mib": 32768
    },
    "operation": "Render and visually review an HTML slide using PPTAgent Skill CLI over shared Chromium CDP.",
    "operation_scope": "product operation",
    "hosting": null,
    "kind": "repo",
    "test_version": "readme-20cd1bc4ab0be6730266a08d7400e342dd7d403c08aabf42aab2e51dc9b34ce0",
    "evidence_version": null
  },
  "transcript_url": null,
  "report_url": "/reports/icip-cas--PPTAgent-gpt-6-luna-1792855554496864415.json"
}