Files

indifferentketchup c935687725 chore(openspec): drop 9 superseded proposals + 11 stub archive files

Drop 9 batch proposals that are superseded by the boocode-lift-analysis
(boocontext-audit, conductor upgrades, self-healing/verify-gate skills):
add-3tier-memory, import-llm-evaluator, import-pregel-engine, plugin-platform,
conductor-evolution, code-intelligence-upgrade, dev-workflow, ui-overhaul,
agent-reliability.

Delete 11 stub archive files (49-66B each, 'Status: Shipped. Archived.' only)
that provide zero documentation value over the existing CHANGELOG.md + git tags.

2026-06-07 22:15:38 +00:00

2.5 KiB

Raw Blame History

Session Lifecycle Commands — Spec

Overview

Four agent-invocable commands that manage audit session lifecycle. Each command is a skill markdown file loaded by the agent on invocation.

/start

/start "task description"

Creates a named audit session:

Generate session_id = adhoc_YYYYMMDD_HHMM
mkdir -p .boo/runs/{session_id}

Write session.json:

{
  "session_id": "adhoc_20260320_1400",
  "task": "task description",
  "start_time": "2026-03-20T14:00:00Z",
  "status": "in_progress",
  "expected_record_types": ["data", "change", "conversation"]
}

Write .boo/runs/.current_session containing session_id (handshake for hooks)
Run context recovery:
- L0: read index.json → last 5 entries
- L2: scan recent audit_trail.jsonl for user_correction records
Output recovery summary: recent activity, corrections, priorities
Check for unfinished sessions: scan for status: "in_progress" sessions, prompt user

/end

/end

Ends the current audit session:

Read .current_session → get session_id
Collect remaining buffer data from audit_buffer.jsonl + audit_pending.jsonl
Append to audit_trail.jsonl
Clear buffer files
Extract user_correction records from audit_trail
Run integrity checks:
- Has records? (>0 audit_trail lines)
- All files covered? (changes in audit_trail match modified files)
- Corrections persisted? (persisted_to is non-empty)
Generate session_summary.md
Update session.json status=completed, end_time
Clear .current_session

/recover

/recover              # L0+L1+L2
/recover full         # L3 (full audit_trail)
/recover {session_id} # load specific session

Graded context loading:

L0 (~200t): index.json → last 5 entries (id, task, status)
L1 (~500t): .current_session + session.json + last 3 audit_trail entries
L2 (~1000t): scan all audit_trails for user_correction records + conclusions + daily report §4+§6
L3 (~3000t): full audit_trail.jsonl + audit_pending.jsonl

/report-daily

/report-daily              # today
/report-daily 20260319     # specific date
/report-daily review       # + morning self-review

7-section report:

Task overview (from index.json)
Operation stats (tool counts)
Change records (file modifications)
User feedback & corrections
Anomaly alerts
Backlog tracking
Integrity summary

review variant: adds morning self-review with trend analysis and recommended priorities.

2.5 KiB Raw Blame History