# formulas/run-predictor.toml — Predictor formula (disinto-specific signals)
#
# Executed by predictor/predictor-run.sh via cron — no action issues.
# predictor-run.sh creates a tmux session with Claude (sonnet) and injects
# this formula as context. Claude executes all steps autonomously.
#
# Steps: preflight → collect-signals → analyze-and-predict
#
# Disinto-specific signal sources:
#   - CI pipeline trends (Woodpecker)
#   - Stale issues (open issues with no recent activity)
#   - Agent health (tmux sessions, recent logs)
#   - Resource patterns (RAM, disk, load, containers)

name        = "run-predictor"
description = "Evidence-based prediction: CI trends, stale issues, agent health, resource patterns"
version     = 1
model       = "sonnet"

[context]
files = ["AGENTS.md", "RESOURCES.md"]

[[steps]]
id    = "preflight"
title = "Pull latest code and gather environment"
description = """
Set up the working environment for this prediction run.

1. Change to the project repository:
     cd "$PROJECT_REPO_ROOT"

2. Pull the latest code:
     git fetch origin "$PRIMARY_BRANCH" --quiet
     git checkout "$PRIMARY_BRANCH" --quiet
     git pull --ff-only origin "$PRIMARY_BRANCH" --quiet
"""

[[steps]]
id    = "collect-signals"
title = "Collect disinto-specific signals"
description = """
Gather raw signal data for pattern analysis. Collect each signal category
and store the results for the analysis step.

### 1. CI pipeline trends (Woodpecker)

Fetch recent builds from Woodpecker CI:
  curl -sf -H "Authorization: Bearer $WOODPECKER_TOKEN" \
    "${WOODPECKER_SERVER}/api/repos/${WOODPECKER_REPO_ID}/pipelines?page=1&perPage=20"

Look for:
- Build failure rate over last 20 builds
- Repeated failures on the same step
- Builds stuck in running/pending state
- Time since last successful build

If WOODPECKER_TOKEN or WOODPECKER_SERVER are not set, skip CI signals and note
"CI signals unavailable — WOODPECKER_TOKEN not configured".

### 2. Stale issues

Fetch all open issues:
  curl -sf -H "Authorization: token $CODEBERG_TOKEN" \
    "$CODEBERG_API/issues?state=open&type=issues&limit=50&sort=updated&direction=asc"

Identify:
- Issues with no update in 14+ days (stale)
- Issues with no update in 30+ days (very stale)
- Issues labeled 'action' or 'backlog' that are stale (work not progressing)
- Blocked issues where the blocker may have been resolved

### 3. Agent health

Check active tmux sessions:
  tmux list-sessions 2>/dev/null || echo "no sessions"

Check recent agent logs (last 24h of activity):
  for log in supervisor/supervisor.log planner/planner.log planner/prediction.log \
             gardener/gardener.log dev/dev.log review/review.log; do
    if [ -f "$PROJECT_REPO_ROOT/$log" ]; then
      echo "=== $log (last 20 lines) ==="
      tail -20 "$PROJECT_REPO_ROOT/$log"
    fi
  done

Look for:
- Agents that haven't run recently (missing log entries in last 24h)
- Repeated errors or failures in logs
- Sessions stuck or crashed (tmux sessions present but no recent activity)
- Lock files that may be stale: /tmp/*-poll.lock, /tmp/*-run.lock

### 4. Resource patterns

Collect current resource state:
  free -m                          # RAM
  df -h /                          # Disk
  cat /proc/loadavg                # Load average
  docker ps --format '{{.Names}} {{.Status}}' 2>/dev/null || true  # Containers

Look for:
- Available RAM < 2000MB (agents will skip runs)
- Disk usage > 80% (approaching danger zone)
- Load average > 3.0 (box overloaded)
- Containers in unhealthy or restarting state

### 5. Already-open predictions (deduplication)

Fetch existing open predictions to avoid duplicates:
  curl -sf -H "Authorization: token $CODEBERG_TOKEN" \
    "$CODEBERG_API/issues?state=open&type=issues&labels=prediction%2Funreviewed&limit=50"

Also check prediction/backlog (watched but not yet actioned):
  curl -sf -H "Authorization: token $CODEBERG_TOKEN" \
    "$CODEBERG_API/issues?state=open&type=issues&labels=prediction%2Fbacklog&limit=50"

Record their titles so you can avoid duplicating them.
"""
needs = ["preflight"]

[[steps]]
id    = "analyze-and-predict"
title = "Analyze signals and file prediction issues"
description = """
Analyze the collected signals for patterns and file up to 5 prediction issues.

## What to look for

**CI regression** — Build failure rate increasing or repeated failures:
- Failure rate > 30% over last 20 builds → high confidence
- Same step failing 3+ times in a row → high confidence
- No successful build in 24+ hours → medium confidence

**Stale work** — Issues not progressing:
- Action issues stale 7+ days → the action agent may be stuck
- Backlog issues stale 14+ days → work not being picked up
- Blocked issues whose blockers are now closed → can be unblocked

**Agent health** — Agents not running or failing:
- Agent log with no entries in 24+ hours → agent may be down
- Repeated errors in agent logs → systemic problem
- Stale lock files (process not running but lock exists)

**Resource pressure** — System approaching limits:
- RAM < 2000MB → agents will start skipping runs
- Disk > 80% → approaching critical threshold
- Load sustained > 3.0 → box is overloaded, queued work backing up

**Opportunity** — Good conditions for expensive work:
- Box idle (RAM > 3000MB, load < 1.0, few active sessions) → good time
  for expensive operations if any are pending

## Filing predictions

For each prediction, create a Codeberg issue with the `prediction/unreviewed` label.

1. Look up the label ID:
     curl -sf -H "Authorization: token $CODEBERG_TOKEN" \
       "$CODEBERG_API/labels" | jq '.[] | select(.name == "prediction/unreviewed") | .id'

2. For each prediction, create an issue:
     curl -sf -X POST -H "Authorization: token $CODEBERG_TOKEN" \
       -H "Content-Type: application/json" \
       "$CODEBERG_API/issues" \
       -d '{"title":"<title>","body":"<body>","labels":[<label_id>]}'

   Body format:
     <2-4 sentence description of what was observed, why it matters,
      what the planner should consider>

     ---
     **Signal source:** <which signal triggered this>
     **Confidence:** <high|medium|low>
     **Suggested action:** <concrete next step for the planner>

3. Send a Matrix notification for each prediction created (optional):
     Use matrix_send if available, or skip if MATRIX_TOKEN is not set.

## Rules
- Max 5 predictions total
- Do NOT predict feature work — only infrastructure/health/metric observations
- Do NOT duplicate existing open predictions (checked in collect-signals)
- Be specific: name the metric, the value, the threshold
- Prefer high-confidence predictions backed by concrete data
- If no meaningful patterns found, file zero issues — that is a valid outcome

"""
needs = ["collect-signals"]