debug-task

Debugging Autonomous Tasks

Data sources

Surface	Location	Content
Task runs	~/.leashd/sessions.db → task_runs table	Phase state, outcome, costs, context, pipeline, timestamps (24 columns)
Sessions	~/.leashd/sessions.db → sessions table	mode, task_run_id link back to task_runs
Audit log	<approved_directories[0]>/.leashd/audit.jsonl (pinned/centralized)	Tool-gating decisions (allow/deny/require_approval), all sessions
App logs	{working_directory}/.leashd/logs/app.log	Structured events: task_phase_changed, task_phase_error, task_terminal, etc.
Messages	~/.leashd/messages.db (centralized)	Agent messages during the task's session

audit.jsonl is centralized, not per-working-directory. Since v0.9.0 it is pinned to approved_directories[0] (the first entry in ~/.leashd/config.yaml) — NOT {working_directory}/.leashd/audit.jsonl, which will look stale for any task that ran outside that dir. The audit queries below resolve the pinned path automatically.

$ARGUMENTS is the task_id — full 16-char hex or first 8 chars from /tasks output.

Tasks may have run under v2 (LLM-driven think-act-observe, phases include explore/plan/retry) or v3 (linear plan → implement → verify → review). Check phase_pipeline in Step 1 to tell which.

Quick diagnosis (run all 5 steps)

Step 1: Load task state

Query task_runs by run_id. Try exact match first, then prefix match.

uv run python -c "
import sqlite3, pathlib, sys, json
db = pathlib.Path.home() / '.leashd' / 'sessions.db'
if not db.exists():
    print('ERROR: sessions.db not found at', db)
    sys.exit(1)
conn = sqlite3.connect(str(db))
conn.row_factory = sqlite3.Row
tid = '$ARGUMENTS'.strip()
if not tid:
    print('No task_id provided. Listing recent tasks...')
    for r in conn.execute('SELECT run_id, phase, outcome, task, created_at, total_cost FROM task_runs ORDER BY created_at DESC LIMIT 20'):
        d = dict(r)
        d['task'] = d['task'][:80]
        print(d)
    sys.exit(0)
# Exact match
row = conn.execute('SELECT * FROM task_runs WHERE run_id = ?', (tid,)).fetchone()
if not row:
    # Prefix match
    row = conn.execute('SELECT * FROM task_runs WHERE run_id LIKE ?', (tid + '%',)).fetchone()
if not row:
    print(f'No task found matching: {tid}')
    sys.exit(1)
d = dict(row)
# Pretty-print key fields
for k in ['run_id','phase','previous_phase','outcome','error_message','retry_count','max_retries',
          'created_at','started_at','phase_started_at','completed_at','last_updated',
          'total_cost','working_directory','session_id','user_id','chat_id','task']:
    print(f'{k:>20}: {d.get(k)}')
print(f\"{'phase_pipeline':>20}: {json.loads(d.get('phase_pipeline','[]'))}\")
print(f\"{'phase_costs':>20}: {json.loads(d.get('phase_costs','{}'))}\")
"