No description
On crash (PHASE:crashed or non-zero exit), preserve the worktree and log its location instead of destroying it unconditionally. Successful sessions still clean up normally. Supervisor runs housekeeping to remove stale crashed worktrees older than 24h. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|---|---|---|
| .codeberg/ISSUE_TEMPLATE | ||
| .woodpecker | ||
| action | ||
| bin | ||
| dev | ||
| docker/agents | ||
| docs | ||
| evidence/engagement | ||
| formulas | ||
| gardener | ||
| lib | ||
| planner | ||
| predictor | ||
| projects | ||
| review | ||
| site | ||
| skill | ||
| state | ||
| supervisor | ||
| tests | ||
| vault | ||
| .env.example | ||
| .gitignore | ||
| .shellcheckrc | ||
| AGENTS.md | ||
| BOOTSTRAP.md | ||
| README.md | ||
| RESOURCES.example.md | ||
| RESOURCES.md | ||
| VISION.md | ||
Disinto
Autonomous code factory — disinto.ai
A mining robot, lost and confused, builds a Disinto from scrap —
a device so powerful it vaporizes three-quarters of a mountain on a single battery.
— Isaac Asimov, "Robot AL-76 Goes Astray" (1942)
Point it at a git repo with a Woodpecker CI pipeline and it will pick up issues, implement them, review PRs, and keep the system healthy — all on its own.
Architecture
cron (*/10) ──→ supervisor-poll.sh ← supervisor (bash checks, zero tokens)
├── all clear? → exit 0
└── problem? → claude -p (diagnose, fix, or escalate)
cron (*/10) ──→ dev-poll.sh ← pulls ready issues, spawns dev-agent
└── dev-agent.sh ← claude -p: implement → PR → CI → review → merge
cron (*/10) ──→ review-poll.sh ← finds unreviewed PRs, spawns review
└── review-pr.sh ← claude -p: review → approve/request changes
cron (daily) ──→ gardener-poll.sh ← backlog grooming (duplicates, stale, tech-debt)
└── claude -p: triage → promote/close/escalate
cron (weekly) ──→ planner-poll.sh ← gap-analyse VISION.md, create backlog issues
└── claude -p: update AGENTS.md → create issues
cron (*/30) ──→ vault-poll.sh ← safety gate for dangerous/irreversible actions
└── claude -p: classify → auto-approve/reject or escalate
systemd ──→ matrix_listener.sh ← long-poll daemon for human replies
└── dispatches thread replies → supervisor/gardener/dev/review/vault
all agents ──→ matrix_send() ← status updates, escalations, merge notifications
Prerequisites
Required:
- Claude CLI —
claudein PATH, authenticated - Docker — for provisioning a local Forgejo instance (or a running Forgejo/Gitea instance)
- Woodpecker CI — local instance connected to your forge; disinto monitors pipelines, retries failures, and queries the Woodpecker Postgres DB directly
- PostgreSQL client (
psql) — for Woodpecker DB queries (pipeline status, build counts) jq,curl,git
Optional:
- Matrix homeserver (Dendrite or Synapse) — real-time notifications, escalation threads with human-in-the-loop replies
- Foundry (
forge,cast,anvil) — only needed if your target project uses Solidity - Node.js — only needed if your target project uses Node
Setup
# 1. Clone
git clone https://github.com/johba/disinto.git
cd disinto
# 2. Bootstrap a project (provisions local Forgejo, creates tokens, clones repo)
disinto init https://github.com/yourorg/yourproject
Or configure manually — edit .env with your values:
# Forge (auto-populated by disinto init)
FORGE_URL=http://localhost:3000 # local Forgejo instance
FORGE_TOKEN=... # dev-bot token
FORGE_REVIEW_TOKEN=... # review-bot token
# Woodpecker CI
WOODPECKER_SERVER=http://localhost:8000
WOODPECKER_TOKEN=...
WOODPECKER_DB_PASSWORD=...
WOODPECKER_DB_USER=woodpecker
WOODPECKER_DB_HOST=127.0.0.1
WOODPECKER_DB_NAME=woodpecker
# Tuning
CLAUDE_TIMEOUT=7200 # max seconds per Claude invocation (default: 2h)
# 3. Install cron (staggered to avoid overlap)
crontab -e
# Add:
# 0,10,20,30,40,50 * * * * /path/to/disinto/supervisor/supervisor-poll.sh
# 3,13,23,33,43,53 * * * * /path/to/disinto/review/review-poll.sh
# 6,16,26,36,46,56 * * * * /path/to/disinto/dev/dev-poll.sh
# 15 8 * * * /path/to/disinto/gardener/gardener-poll.sh
# 0,30 * * * * /path/to/disinto/vault/vault-poll.sh
# 0 9 * * 1 /path/to/disinto/planner/planner-poll.sh
# 4. Verify
bash supervisor/supervisor-poll.sh # should log "all clear"
Directory Structure
disinto/
├── .env.example # Template — copy to .env, add secrets + project config
├── .gitignore # Excludes .env, logs, state files
├── lib/
│ ├── env.sh # Shared: load .env, PATH, API helpers, matrix_send()
│ ├── ci-debug.sh # Woodpecker CI log/failure helper
│ ├── matrix_listener.sh # Matrix long-poll daemon (dispatches replies)
│ └── matrix_listener.service # systemd unit for the listener
├── dev/
│ ├── dev-poll.sh # Cron entry: find ready issues
│ └── dev-agent.sh # Implementation agent (claude -p)
├── review/
│ ├── review-poll.sh # Cron entry: find unreviewed PRs
│ └── review-pr.sh # Review agent (claude -p)
├── gardener/
│ ├── gardener-poll.sh # Cron entry: backlog grooming
│ └── best-practices.md # Gardener knowledge base
├── planner/
│ ├── planner-poll.sh # Cron entry: weekly vision gap analysis
│ └── (formula-driven) # run-planner.toml executed by action-agent
├── vault/
│ ├── vault-poll.sh # Cron entry: process pending dangerous actions
│ ├── vault-agent.sh # Classifies and routes actions (claude -p)
│ ├── vault-fire.sh # Executes an approved action
│ ├── vault-reject.sh # Marks an action as rejected
│ └── PROMPT.md # System prompt for vault agent
└── supervisor/
├── supervisor-poll.sh # Supervisor: health checks + claude -p
├── PROMPT.md # Supervisor's system prompt
├── update-prompt.sh # Self-learning: append to best-practices
└── best-practices/ # Progressive disclosure knowledge base
├── memory.md
├── disk.md
├── ci.md
├── forge.md
├── dev-agent.md
├── review-agent.md
└── git.md
Agents
| Agent | Trigger | Job |
|---|---|---|
| Supervisor | Every 10 min | Health checks (RAM, disk, CI, git). Calls Claude only when something is broken. Self-improving via best-practices/. |
| Dev | Every 10 min | Picks up backlog-labeled issues, creates a branch, implements, opens a PR, monitors CI, responds to review, merges. |
| Review | Every 10 min | Finds PRs without review, runs Claude-powered code review, approves or requests changes. |
| Gardener | Daily | Grooms the issue backlog: detects duplicates, promotes tech-debt to backlog, closes stale issues, escalates ambiguous items. |
| Planner | Weekly | Updates AGENTS.md documentation to reflect recent code changes, then gap-analyses VISION.md vs current state and creates up to 5 backlog issues for the highest-leverage gaps. |
| Vault | Every 30 min | Safety gate for dangerous or irreversible actions. Classifies pending actions via Claude: auto-approve, auto-reject, or escalate to a human via Matrix. |
Design Principles
- Bash for checks, AI for judgment — polling and health checks are shell scripts; Claude is only invoked when something needs diagnosing or deciding
- Pull over push — dev-agent derives readiness from merged dependencies, not labels or manual assignment
- Progressive disclosure — the supervisor reads only the best-practices file relevant to the current problem, not all of them
- Self-improving — when Claude fixes something new, the lesson is appended to best-practices for next time
- Project-agnostic — all project-specific values (repo, paths, CI IDs) come from
.env, not hardcoded scripts
Runtime constraints
Disinto is intentionally opinionated about its own runtime. These are hard constraints, not preferences:
- Debian + GNU userland — all scripts target Debian with standard GNU tools (
bash,awk,sed,date,timeout). No portability shims for macOS or BSD. - Shell + a small set of runtimes — every agent is a bash script. The only interpreted runtimes used by disinto core are
python3(TOML parsing inlib/load-project.sh, JSON state tracking indev/dev-poll.sh, recipe matching ingardener/gardener-poll.sh) andclaude(the AI CLI). No Ruby, Perl, or other runtimes. Do not add new runtime dependencies without a strong justification. - Few, powerful dependencies — required non-standard tools:
jq,curl,git,tmux,psql, andpython3(≥ 3.11 fortomllib; or installtomlifor older Pythons). Adding anything beyond this list requires justification. - Node.js and Foundry are target-project dependencies — if your target repo uses Node or Solidity, install those on the host. They are not part of disinto's core and must not be assumed present in disinto scripts.
The goal: any Debian machine with the prerequisites listed above can run disinto. Keep it that way.