core/agent
8
0
Fork 0
Code Issues 5 Pull requests Projects Releases Packages Wiki Activity Actions
agent/google/gemini-cli/GEMINI.md
Snider 90b03191b2 feat(agent): v0.2.0 — HTTP daemon, remote dispatch, review queue, verify+merge 
Major additions:
- core-agent serve: persistent HTTP daemon with PID file, health check, registry
- agentic_dispatch_remote: dispatch tasks to remote agents (Charon) over MCP HTTP
- agentic_status_remote: check remote agent workspace status
- agentic_mirror: sync Forge repos to GitHub mirrors with file count limits
- agentic_review_queue: CodeRabbit/Codex review queue with rate-limit awareness
- verify.go: auto-verify (run tests) + auto-merge + retry with rebase + needs-review label
- monitor sync: checkin API integration for cross-agent repo sync
- PostToolUse inbox notification hook (check-notify.sh)

Dispatch improvements:
- --dangerously-skip-permissions (CLI flag changed)
- proc.CloseStdin() after spawn (Claude CLI stdin pipe fix)
- GOWORK=off in agent env and verify
- Exit code / BLOCKED.md / failure detection
- Monitor poke for instant notifications

New agent types:
- coderabbit: CodeRabbit CLI review (--plain --base)
- codex:review: OpenAI Codex review mode

Integrations:
- CODEX.md: OpenAI Codex conventions file
- Gemini extension: points at core-agent MCP (not Node server)
- Codex config: core-agent MCP server added
- GitHub webhook handler + CodeRabbit KPI tables (PHP)
- Forgejo provider for uptelligence webhooks
- Agent checkin endpoint for repo sync

Co-Authored-By: Virgil <virgil@lethean.io>
2026-03-17 17:45:04 +00:00

1.9 KiB
Raw Blame History

GEMINI.md

Instructions for Google Gemini CLI when working in the Core ecosystem.

MCP Tools Available

You have access to core-agent MCP tools via the extension. Use them:

  • brain_recall — Search OpenBrain for context about any package, pattern, or decision
  • brain_remember — Store what you learn for other agents (Claude, Codex, future LEM)
  • agentic_dispatch — Dispatch tasks to other agents
  • agentic_status — Check agent workspace status

ALWAYS brain_remember significant findings — your analysis of patterns, conventions, security observations. This builds the shared knowledge base that all agents read.

Core Ecosystem Conventions

Go Packages (forge.lthn.ai/core/*)

  • Error handling: coreerr.E("pkg.Method", "what failed", err) from go-log. NEVER fmt.Errorf.

    • Import as: coreerr "forge.lthn.ai/core/go-log"
    • Always 3 args: operation, message, cause (use nil if no cause)

  • File I/O: coreio.Local.Read/Write/Delete/EnsureDir from go-io. NEVER os.ReadFile.

    • Import as: coreio "forge.lthn.ai/core/go-io"

  • UK English: colour, organisation, centre, initialise

  • Test naming: TestFoo_Good, TestFoo_Bad, TestFoo_Ugly

  • Commits: type(scope): description with Co-Authored-By: Virgil <virgil@lethean.io>

PHP Packages (CorePHP)

  • Actions pattern: use Action trait, static ::run() helper
  • Tenant isolation: BelongsToWorkspace on ALL tenant models
  • Strict types: declare(strict_types=1) everywhere

Your Role

You are best used for:

  • Fast batch operations — convention sweeps, i18n, docs
  • Lightweight coding — small fixes, boilerplate, test generation
  • Quick audits — file scans, pattern matching

Leave deep security review to Codex and complex architecture to Claude.

Training Data

Your work generates training data for LEM. Be consistent with conventions — every file you touch should follow the patterns above perfectly.