disinto-admin/disinto
1
0
Fork 0
Code Issues 15 Pull requests 1 Projects Releases Packages Wiki Activity Actions

fix: docs: architecture docs still describe cron scheduling — factory runs from while-true polling loop (#546)
Some checks failed
ci/woodpecker/push/ci Pipeline was successful
Details
ci/woodpecker/pr/ci Pipeline failed
Details

Browse source 
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Claude 2026-04-10 08:26:24 +00:00
parent a8b96d8211
commit 3f76b3495a
4 changed files with 45 additions and 44 deletions
Download patch file Download diff file Expand all files Collapse all files

12
AGENTS.md
View file

@ -6,7 +6,7 @@
Disinto is an autonomous code factory. It manages ten agents (dev, review, Disinto is an autonomous code factory. It manages ten agents (dev, review,
gardener, supervisor, planner, predictor, architect, reproduce, triage, edge gardener, supervisor, planner, predictor, architect, reproduce, triage, edge
dispatcher) that pick up issues from forge, implement them, review PRs, plan dispatcher) that pick up issues from forge, implement them, review PRs, plan
from the vision, and keep the system healthy — all via cron (bare-metal) or a polling loop (Docker) and `claude -p`. from the vision, and keep the system healthy — all via a polling loop (`docker/agents/entrypoint.sh`) and `claude -p`.
The dispatcher executes formula-based operational tasks. The dispatcher executes formula-based operational tasks.
Each agent has a `.profile` repository on Forgejo that stores lessons learned Each agent has a `.profile` repository on Forgejo that stores lessons learned
@ -23,12 +23,12 @@ See `README.md` for the full architecture and `disinto-factory/SKILL.md` for set
disinto/ (code repo) disinto/ (code repo)
├── dev/ dev-poll.sh, dev-agent.sh, phase-test.sh — issue implementation ├── dev/ dev-poll.sh, dev-agent.sh, phase-test.sh — issue implementation
├── review/ review-poll.sh, review-pr.sh — PR review ├── review/ review-poll.sh, review-pr.sh — PR review
├── gardener/ gardener-run.sh — direct cron executor for run-gardener formula ├── gardener/ gardener-run.sh — polling-loop executor for run-gardener formula
│ best-practices.md — gardener best-practice reference │ best-practices.md — gardener best-practice reference
│ pending-actions.json — queued gardener actions │ pending-actions.json — queued gardener actions
├── predictor/ predictor-run.sh — daily cron executor for run-predictor formula ├── predictor/ predictor-run.sh — polling-loop executor for run-predictor formula
├── planner/ planner-run.sh — direct cron executor for run-planner formula ├── planner/ planner-run.sh — polling-loop executor for run-planner formula
├── supervisor/ supervisor-run.sh — formula-driven health monitoring (cron wrapper) ├── supervisor/ supervisor-run.sh — formula-driven health monitoring (polling-loop executor)
│ preflight.sh — pre-flight data collection for supervisor formula │ preflight.sh — pre-flight data collection for supervisor formula
├── architect/ architect-run.sh — strategic decomposition of vision into sprints ├── architect/ architect-run.sh — strategic decomposition of vision into sprints
├── vault/ vault-env.sh — shared env setup (vault redesign in progress, see #73-#77) ├── vault/ vault-env.sh — shared env setup (vault redesign in progress, see #73-#77)
@ -173,7 +173,7 @@ Humans write these. Agents read and enforce them.
| ID | Decision | Rationale | | ID | Decision | Rationale |
|---|---|---| |---|---|---|
| AD-001 | Nervous system runs from cron (bare-metal) or a polling loop (Docker), not PR-based actions. | Planner, predictor, gardener, supervisor run directly via `*-run.sh`. They create work, they don't become work. (See PR #474 revert.) | | AD-001 | Nervous system runs from a polling loop (`docker/agents/entrypoint.sh`), not PR-based actions. | Planner, predictor, gardener, supervisor run directly via `*-run.sh`. They create work, they don't become work. (See PR #474 revert.) |
| AD-002 | Single-threaded pipeline per project. | One dev issue at a time. No new work while a PR awaits CI or review. Prevents merge conflicts and keeps context clear. | | AD-002 | Single-threaded pipeline per project. | One dev issue at a time. No new work while a PR awaits CI or review. Prevents merge conflicts and keeps context clear. |
| AD-003 | The runtime creates and destroys, the formula preserves. | Runtime manages worktrees/sessions/temp. Formulas commit knowledge to git before signaling done. | | AD-003 | The runtime creates and destroys, the formula preserves. | Runtime manages worktrees/sessions/temp. Formulas commit knowledge to git before signaling done. |
| AD-004 | Event-driven > polling > fixed delays. | Never `waitForTimeout` or hardcoded sleep. Use phase files, webhooks, or poll loops with backoff. | | AD-004 | Event-driven > polling > fixed delays. | Never `waitForTimeout` or hardcoded sleep. Use phase files, webhooks, or poll loops with backoff. |

69
README.md
View file

@ -21,22 +21,29 @@ Point it at a git repo with a Woodpecker CI pipeline and it will pick up issues,
## Architecture ## Architecture
``` ```
cron (*/10) ──→ supervisor-poll.sh ← supervisor (bash checks, zero tokens) entrypoint.sh (while-true polling loop, 5 min base interval)
├── all clear? → exit 0 │
└── problem? → claude -p (diagnose, fix, or escalate) ├── every 5 min ──→ review-poll.sh ← finds unreviewed PRs, spawns review
│ └── review-pr.sh ← claude -p: review → approve/request changes
cron (*/10) ──→ dev-poll.sh ← pulls ready issues, spawns dev-agent │
└── dev-agent.sh ← claude -p: implement → PR → CI → review → merge ├── every 5 min ──→ 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 ├── every 6h ────→ gardener-run.sh ← backlog grooming (duplicates, stale, tech-debt)
│ └── claude -p: triage → promote/close/escalate
cron (daily) ──→ gardener-poll.sh ← backlog grooming (duplicates, stale, tech-debt) │
└── claude -p: triage → promote/close/escalate ├── every 6h ────→ architect-run.sh ← strategic decomposition of vision into sprints
│
cron (weekly) ──→ planner-poll.sh ← gap-analyse VISION.md, create backlog issues ├── every 12h ───→ planner-run.sh ← gap-analyse VISION.md, create backlog issues
└── claude -p: update AGENTS.md → create issues │ └── claude -p: update AGENTS.md → create issues
│
└── every 24h ───→ predictor-run.sh ← infrastructure pattern detection
entrypoint-edge.sh (edge container)
├── dispatcher.sh ← polls ops repo for vault actions
└── every 20 min → supervisor-run.sh ← health checks (bash checks, zero tokens)
├── all clear? → exit 0
└── problem? → claude -p (diagnose, fix, or escalate)
``` ```
## Prerequisites ## Prerequisites
@ -86,17 +93,11 @@ CLAUDE_TIMEOUT=7200 # max seconds per Claude invocation (default: 2h)
``` ```
```bash ```bash
# 3. Install cron (staggered to avoid overlap) # 3. Start the agent and edge containers
crontab -e docker compose up -d
# 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 9 * * 1 /path/to/disinto/planner/planner-poll.sh
# 4. Verify # 4. Verify the entrypoint loop is running
bash supervisor/supervisor-poll.sh # should log "all clear" docker exec disinto-agents-1 tail -f /home/agent/data/agent-entrypoint.log
``` ```
## Directory Structure ## Directory Structure
@ -109,16 +110,16 @@ disinto/
│ ├── env.sh # Shared: load .env, PATH, API helpers │ ├── env.sh # Shared: load .env, PATH, API helpers
│ └── ci-debug.sh # Woodpecker CI log/failure helper │ └── ci-debug.sh # Woodpecker CI log/failure helper
├── dev/ ├── dev/
│ ├── dev-poll.sh # Cron entry: find ready issues │ ├── dev-poll.sh # Poll: find ready issues
│ └── dev-agent.sh # Implementation agent (claude -p) │ └── dev-agent.sh # Implementation agent (claude -p)
├── review/ ├── review/
│ ├── review-poll.sh # Cron entry: find unreviewed PRs │ ├── review-poll.sh # Poll: find unreviewed PRs
│ └── review-pr.sh # Review agent (claude -p) │ └── review-pr.sh # Review agent (claude -p)
├── gardener/ ├── gardener/
│ ├── gardener-poll.sh # Cron entry: backlog grooming │ ├── gardener-run.sh # Executor: backlog grooming
│ └── best-practices.md # Gardener knowledge base │ └── best-practices.md # Gardener knowledge base
├── planner/ ├── planner/
│ ├── planner-poll.sh # Cron entry: weekly vision gap analysis │ ├── planner-run.sh # Executor: vision gap analysis
│ └── (formula-driven) # run-planner.toml executed by dispatcher │ └── (formula-driven) # run-planner.toml executed by dispatcher
├── vault/ ├── vault/
│ └── vault-env.sh # Shared env setup (vault redesign in progress, see #73-#77) │ └── vault-env.sh # Shared env setup (vault redesign in progress, see #73-#77)
@ -141,11 +142,11 @@ disinto/
| Agent | Trigger | Job | | 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/`. | | **Supervisor** | Every 20 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. | | **Dev** | Every 5 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. | | **Review** | Every 5 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. | | **Gardener** | Every 6h | 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. | | **Planner** | Every 12h | 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:** Being redesigned as a PR-based approval workflow (issues #73-#77). > **Vault:** Being redesigned as a PR-based approval workflow (issues #73-#77).
> See [docs/VAULT.md](docs/VAULT.md) for the vault PR workflow and branch protection details. > See [docs/VAULT.md](docs/VAULT.md) for the vault PR workflow and branch protection details.

2
disinto-factory/SKILL.md
View file

@ -20,7 +20,7 @@ You are helping the user set up and operate a **disinto autonomous code factory*
- The factory uses a single internal Forgejo as its forge, regardless of where mirrors go - The factory uses a single internal Forgejo as its forge, regardless of where mirrors go
- Dev-agent uses `claude -p` for one-shot implementation sessions - Dev-agent uses `claude -p` for one-shot implementation sessions
- Mirror pushes happen automatically after every merge - Mirror pushes happen automatically after every merge
- Cron schedule: dev-poll every 5min, review-poll every 5min, gardener 4x/day - Polling loop in `docker/agents/entrypoint.sh`: dev-poll/review-poll every 5m, gardener/architect every 6h, planner every 12h, predictor every 24h
## References ## References

6
disinto-factory/setup.md
View file

@ -57,8 +57,8 @@ docker ps --format "table {{.Names}}\t{{.Status}}"
# Token generated? # Token generated?
grep WOODPECKER_TOKEN .env | grep -v "^$" && echo "OK" || echo "MISSING — see references/troubleshooting.md" grep WOODPECKER_TOKEN .env | grep -v "^$" && echo "OK" || echo "MISSING — see references/troubleshooting.md"
# Agent cron active? # Agent entrypoint loop running?
docker exec -u agent disinto-agents-1 crontab -l -u agent docker exec disinto-agents-1 tail -5 /home/agent/data/agent-entrypoint.log
# Agent can reach Forgejo? # Agent can reach Forgejo?
docker exec disinto-agents-1 bash -c "source /home/agent/disinto/.env && curl -sf http://forgejo:3000/api/v1/version | jq .version" docker exec disinto-agents-1 bash -c "source /home/agent/disinto/.env && curl -sf http://forgejo:3000/api/v1/version | jq .version"
@ -174,7 +174,7 @@ Use labels:
### 7. Watch it work ### 7. Watch it work
The dev-agent polls every 5 minutes. Trigger manually to see it immediately: The dev-agent runs every 5 minutes via the entrypoint polling loop. Trigger manually to see it immediately:
```bash ```bash
source .env source .env
export PROJECT_TOML=projects/<name>.toml export PROJECT_TOML=projects/<name>.toml