kin/agents
johnfrum1234 ab693d3c4d Add permission-aware follow-up flow with interactive resolution
When follow-up agent detects permission-blocked items ("ручное
применение", "permission denied", etc.), they become pending_actions
instead of auto-created tasks. User chooses per item:
  1. Rerun with --dangerously-skip-permissions
  2. Create manual task
  3. Skip

core/followup.py:
  _is_permission_blocked() — regex detection of 9 permission patterns
  generate_followups() returns {created, pending_actions}
  resolve_pending_action() — handles rerun/manual_task/skip

agents/runner.py:
  _run_claude(allow_write=True) adds --dangerously-skip-permissions
  run_agent/run_pipeline pass allow_write through

CLI: kin approve --followup — interactive 1/2/3 prompt per blocked item
API: POST /approve returns {needs_decision, pending_actions}
     POST /resolve resolves individual actions
Frontend: pending actions shown as cards with 3 buttons in approve modal

136 tests, all passing. Frontend builds clean.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 15:16:48 +02:00
..
prompts Add follow-up task generation on approve 2026-03-15 15:02:58 +02:00
__init__.py Add bootstrap command — auto-detect project stack, modules, decisions 2026-03-15 13:29:01 +02:00
bootstrap.py Fix bootstrap: deep scan, CLAUDE.md fallback, noise filtering 2026-03-15 13:37:42 +02:00
runner.py Add permission-aware follow-up flow with interactive resolution 2026-03-15 15:16:48 +02:00
specialists.yaml Add context builder, agent runner, and pipeline executor 2026-03-15 14:03:32 +02:00