agentleFS
0-CYBERDYNE-SYSTEMS-00-CYBERDYNE-SYSTEMS-0/FFT_nano/skills/runtime/fft-debug/SKILL.md

fft-debug

Skill4 starsChanged 8 months agoMITView on GitHub

Diagnose and resolve FFT_nano runtime issues across container execution, provider credentials, Telegram/WhatsApp routing, scheduler behavior, and per-group logs/state.

The file

Show its rules and text

We split this skill into the rules it gives an agent

14 rules. About 0 are common, 11 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈11

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill for incident triage and deterministic debugging of FFT_nano host and container paths.

    line 8
  2. Distinctive:

    Use when runtime behavior is failing, degraded, or inconsistent.

    line 12
  3. Distinctive:

    Use when investigating provider wiring, routing, logs, or IPC state.

    line 13
  4. Distinctive:

    Use when producing reproducible triage output before any fix attempt.

    line 14
  5. Distinctive:

    Do not use as the default path for normal feature work.

    line 18
  6. Distinctive:

    Do not use when the request is purely product behavior, not incident/debug.

    line 19
  7. Distinctive:

    Do not use to justify destructive cleanup without explicit approval.

    line 20
  8. Distinctive:

    Never use destructive git commands unless explicitly requested.

    line 24
  9. Distinctive:

    Keep admin/coder controls in main chat only.

    line 26
  10. Distinctive:

    Check startup/runtime logs:

    line 32
  11. Distinctive:

    Check per-group container logs:

    line 35
  12. Distinctive:

    Verify bot token present at runtime.

    line 61
  13. Very specific:

    If /main <secret> fails, verify TELEGRAM_ADMIN_SECRET and restart.

    line 64
  14. Very specific:

    verify explicit flags: CONTAINER_RUNTIME=host, FFT_NANO_ALLOW_HOST_RUNTIME=1

    line 72

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

FFT Debug

Use this skill for incident triage and deterministic debugging of FFT_nano host and container paths.

When to use this skill

  • Use when runtime behavior is failing, degraded, or inconsistent.
  • Use when investigating provider wiring, routing, logs, or IPC state.
  • Use when producing reproducible triage output before any fix attempt.

When not to use this skill

  • Do not use as the default path for normal feature work.
  • Do not use when the request is purely product behavior, not incident/debug.
  • Do not use to justify destructive cleanup without explicit approval.

Guardrails

  • Never use destructive git commands unless explicitly requested.
  • Preserve unrelated worktree changes.
  • Keep admin/coder controls in main chat only; do not bypass main-chat restrictions.

Fast Triage

  1. Confirm single instance lock:
    • ls -la data/fft_nano.lock
  2. Check startup/runtime logs:
    • tail -n 200 logs/fft_nano.log
    • tail -n 200 logs/fft_nano.error.log
  3. Check per-group container logs:
    • ls -la groups/<group>/logs
    • tail -n 200 groups/<group>/logs/*
  4. Inspect registration + IPC state:
    • cat data/registered_groups.json
    • find data/ipc -maxdepth 3 -type f

Common Failure Modes

  • Provider key missing: Pi reports no models available.
  • Wrong PI_API/PI_MODEL: model/provider not found.
  • Multiple bot instances: Telegram getUpdates conflict.
  • Docker daemon unavailable or runtime permission issues.

Recommended Debug Commands

  • Build/runtime checks:
    • npm run typecheck
    • npm test
  • Dry-run routing check (no live model call):
    • FFT_NANO_DRY_RUN=1 ./scripts/start.sh dev telegram-only
  • Runtime detail logging:
    • LOG_LEVEL=debug ./scripts/start.sh dev telegram-only

Telegram Debug Path

  • Verify bot token present at runtime.
  • In bot DM: /id, /status, /help.
  • Admin checks in main chat only: /tasks, /groups, /panel, /coder, /coder-plan.
  • If /main <secret> fails, verify TELEGRAM_ADMIN_SECRET and restart.

Container Runtime Debug

  • Docker runtime:
    • docker info
    • docker ps
  • Host runtime (unisolated):
    • verify explicit flags: CONTAINER_RUNTIME=host, FFT_NANO_ALLOW_HOST_RUNTIME=1

Database/State Debug

  • SQLite file location: store/messages.db
  • Router state: data/router_state.json
  • Group registry: data/registered_groups.json
  • Per-group Pi state: data/pi/<group>/.pi/

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.