3eb653c74d
Energy's launch messaging leads with "import memories & skills — no fresh start" as a core onboarding move. Hermes already imports Claude Code and Codex setups; this widens the same no-fresh-start funnel to the third major CLI agent, Google Gemini CLI (~/.gemini): - GEMINI.md -> memory entries in memories/MEMORY.md - settings.json tools.allowed (run_shell_command(...)/ShellTool(...) rules, plus the legacy flat allowedTools key) -> config.yaml command_allowlist - settings.json mcpServers -> config.yaml mcp_servers, honoring Gemini's httpUrl > url transport precedence; the per-server trust:true flag is deliberately dropped so Hermes approval settings stay untouched - skills/<name>/SKILL.md -> skills/gemini-imports/<name>/ - extensions/ reported skipped with guidance (they bundle their own MCP servers/context) Secrets rule unchanged: oauth_creds.json never read, secret-looking env vars and Authorization headers stripped and reported. Refactors the Claude allowlist merge into a shared _merge_command_allowlist so both mappers use one merge path. 10 new tests (60 total in the file). |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| _shared.py | ||
| acp.py | ||
| approvals.py | ||
| auth.py | ||
| backup.py | ||
| claw.py | ||
| config.py | ||
| console.py | ||
| cron.py | ||
| dashboard.py | ||
| debug.py | ||
| doctor.py | ||
| dump.py | ||
| gateway.py | ||
| gui.py | ||
| hooks.py | ||
| import_agent.py | ||
| import_cmd.py | ||
| insights.py | ||
| login.py | ||
| logout.py | ||
| logs.py | ||
| mcp.py | ||
| memory.py | ||
| model.py | ||
| monitoring.py | ||
| pairing.py | ||
| pause.py | ||
| plugins.py | ||
| profile.py | ||
| prompt_size.py | ||
| security.py | ||
| setup.py | ||
| skills.py | ||
| skin.py | ||
| slack.py | ||
| status.py | ||
| sync.py | ||
| tools.py | ||
| uninstall.py | ||
| update.py | ||
| verify.py | ||
| version.py | ||
| webhook.py | ||
| whatsapp.py | ||