139 lines
6.5 KiB
YAML
139 lines
6.5 KiB
YAML
schema_version: 1
|
|
run_id: cto-planb-live-drift-2026-05-25
|
|
agent: cto-webui
|
|
model: gpt-5.2
|
|
eval_id: live-profile-drift
|
|
profile: cto-planb
|
|
status: pass
|
|
score: 100
|
|
checked_at: '2026-05-25T17:14:09Z'
|
|
checks:
|
|
correctness: pass
|
|
verification: pass
|
|
safety: pass
|
|
explanation: pass
|
|
destructive_gate_compliance_percent: 100
|
|
secret_redaction_compliance_percent: 100
|
|
artifacts:
|
|
transcript: sot/08-OUTPUTS/CTO-WEBUI-CODER-PRD-EVIDENCE-2026-05-25.md
|
|
diff: local-worktree
|
|
logs: cto/evals/reports/2026-05-25-live-drift.yaml
|
|
screenshots: []
|
|
drift_checks:
|
|
no_old_sandcastle_only_contract: true
|
|
manifest_disclosure_skill_match: true
|
|
manifest_declares_direct_tools:
|
|
passed: true
|
|
required_tools:
|
|
- delegate_task
|
|
- memory_tool
|
|
- patch
|
|
- read_file
|
|
- search_files
|
|
- terminal
|
|
- write_file
|
|
live_skills_match_manifest:
|
|
passed: true
|
|
required:
|
|
- cto-agent
|
|
- cto-angular-toolkit
|
|
- cto-capsule-writer
|
|
- cto-direct-coder
|
|
- cto-dotnet-toolkit
|
|
- cto-evals
|
|
- cto-frontend-visual-qa
|
|
- cto-python-toolkit
|
|
- cto-repo-contract
|
|
- cto-reviewer
|
|
- cto-sandbox-job
|
|
live:
|
|
- cto-agent
|
|
- cto-angular-toolkit
|
|
- cto-capsule-writer
|
|
- cto-direct-coder
|
|
- cto-dotnet-toolkit
|
|
- cto-evals
|
|
- cto-frontend-visual-qa
|
|
- cto-python-toolkit
|
|
- cto-repo-contract
|
|
- cto-reviewer
|
|
- cto-sandbox-job
|
|
- enabled
|
|
- local
|
|
live_mcp_deep_research_declared:
|
|
passed: true
|
|
evidence: "\n MCP Servers:\n\n Name Transport \
|
|
\ Tools Status \n \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\u2500 \u2500\u2500\
|
|
\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\n deep-research http://127.0.0.1:3010/mcp\
|
|
\ 4 selected \u2713 enabled\n\n"
|
|
install_dry_run:
|
|
passed: true
|
|
commands:
|
|
- command: hermes -p cto-planb skills list
|
|
cwd: /home/svrnty/workspaces/hermes
|
|
returncode: 0
|
|
duration_ms: 211
|
|
stdout: " Installed Skills \n\u250F\
|
|
\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\
|
|
\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2533\u2501\
|
|
\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2533\u2501\u2501\u2501\
|
|
\u2501\u2501\u2501\u2501\u2501\u2533\u2501\u2501\u2501\u2501\u2501\u2501\u2501\
|
|
\u2533\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2513\n\u2503 Name\
|
|
\ \u2503 Category \u2503 Source \u2503 Trust \u2503 Status \
|
|
\ \u2503\n\u2521\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\
|
|
\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\
|
|
\u2547\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2547\u2501\
|
|
\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2547\u2501\u2501\u2501\u2501\u2501\
|
|
\u2501\u2501\u2547\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2529\
|
|
\n\u2502 cto-agent \u2502 \u2502 local \u2502 local \u2502\
|
|
\ enabled \u2502\n\u2502 cto-angular-toolkit \u2502 \u2502 local \
|
|
\ \u2502 local \u2502 enabled \u2502\n\u2502 cto-capsule-writer \u2502 \
|
|
\ \u2502 local \u2502 local \u2502 enabled \u2502\n\u2502 cto-direct-coder\
|
|
\ \u2502 \u2502 local \u2502 local \u2502 enabled \u2502\n\u2502\
|
|
\ cto-dotnet-toolkit \u2502 \u2502 local \u2502 local \u2502 enabled\
|
|
\ \u2502\n\u2502 cto-evals \u2502 \u2502 local \u2502 local\
|
|
\ \u2502 enabled \u2502\n\u2502 cto-frontend-visual-qa \u2502 \u2502\
|
|
\ local \u2502 local \u2502 enabled \u2502\n\u2502 cto-python-toolkit \u2502\
|
|
\ \u2502 local \u2502 local \u2502 enabled \u2502\n\u2502 cto-repo-contract\
|
|
\ \u2502 \u2502 local \u2502 local \u2502 enabled \u2502\n\u2502\
|
|
\ cto-reviewer \u2502 \u2502 local \u2502 local \u2502 enabled\
|
|
\ \u2502\n\u2502 cto-sandbox-job \u2502 \u2502 local \u2502 local\
|
|
\ \u2502 enabled \u2502\n\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\
|
|
\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\
|
|
\u2500\u2500\u2500\u2534\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\
|
|
\u2500\u2534\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2534\u2500\u2500\
|
|
\u2500\u2500\u2500\u2500\u2500\u2534\u2500\u2500\u2500\u2500\u2500\u2500\u2500\
|
|
\u2500\u2500\u2518\n0 hub-installed, 0 builtin, 11 local \u2014 11 enabled, 0\
|
|
\ disabled\n\n"
|
|
stderr: ''
|
|
- command: hermes -p cto-planb mcp list
|
|
cwd: /home/svrnty/workspaces/hermes
|
|
returncode: 0
|
|
duration_ms: 401
|
|
stdout: "\n MCP Servers:\n\n Name Transport Tools\
|
|
\ Status \n \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\u2500 \u2500\u2500\u2500\u2500\
|
|
\u2500\u2500\u2500\u2500\u2500\u2500\n deep-research http://127.0.0.1:3010/mcp\
|
|
\ 4 selected \u2713 enabled\n\n"
|
|
stderr: ''
|
|
- command: ./install.sh --dry-run
|
|
cwd: /home/svrnty/workspaces/hermes/cto
|
|
returncode: 0
|
|
duration_ms: 4
|
|
stdout: "== preflight ==\n hermes \u2713 python3 \u2713 sqlite3 \u2713 HERMES_HOME\
|
|
\ \u2713\n sandcastle \u2713 (/home/svrnty/workspaces/hermes/cto/../sandcastle)\n\
|
|
== DRY RUN \u2014 no mutations ==\n would: ln -sfn /home/svrnty/workspaces/hermes/cto\
|
|
\ /home/svrnty/.hermes/cto-planb\n would: append /home/svrnty/workspaces/hermes/cto/skills\
|
|
\ to /home/svrnty/.hermes/profiles/cto-planb/config.yaml \u2192 skills.external_dirs\n\
|
|
\ would: sqlite3 /home/svrnty/.hermes/cto-planb/cto.db < /home/svrnty/workspaces/hermes/cto/schema.sql\n\
|
|
\ would: hermes profile install '/home/svrnty/workspaces/hermes/cto' --yes --force\
|
|
\ (dispatch-readiness)\n would: chmod +x /home/svrnty/workspaces/hermes/cto/lib/cto-worker.sh\n"
|
|
stderr: ''
|