pelmen/kin
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
41 commits 1 branch 0 tags 5.2 MiB
Commit graph

5 commits

Author SHA1 Message Date
Gros Frumos
77ed68c2b5 kin: KIN-020 UI для manual_task эскалации из auto_resolve_pending_actions 2026-03-16 07:14:32 +02:00
Gros Frumos
a0b0976d8d kin: KIN-021 Аудит-лог для --dangerously-skip-permissions в auto mode 2026-03-16 07:13:32 +02:00
Gros Frumos
ae21e48b65 kin: KIN-048 Post-pipeline hook: автокоммит после успешного завершения задачи. git add -A && git commit -m 'kin: TASK_ID TITLE'. Срабатывает автоматически как rebuild-frontend. 2026-03-16 06:59:46 +02:00
johnfrum1234
c129cf9d95 Fix output truncation bug, add language support for agent responses 
Bug 1 — Output truncation:
  _run_claude() was replacing raw stdout with parsed sub-field which
  could be a dict (not string). run_agent() then saved dict.__repr__
  to DB instead of full JSON. Fixed: _run_claude() always returns
  string output; run_agent() ensures string before DB write.
  Added tests: full_output_saved_to_db, dict_output_saved_as_json_string.

Bug 2 — Language support:
  Added projects.language column (TEXT DEFAULT 'ru').
  Auto-migration for existing DBs (ALTER TABLE ADD COLUMN).
  context_builder passes language in project context.
  format_prompt() appends "## Language\nALWAYS respond in {language}"
  at the end of every prompt.
  CLI: kin project add --language ru (default: ru).
  Tests: language in prompt for ru/en, project creation, context.

112 tests, all passing. ~/.kin/kin.db migrated (vdol: language=ru).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-15 14:39:33 +02:00
johnfrum1234
fabae74c19 Add context builder, agent runner, and pipeline executor 
core/context_builder.py:
  build_context() — assembles role-specific context from DB.
  PM gets everything; debugger gets gotchas/workarounds; reviewer
  gets conventions only; tester gets minimal context; security
  gets security-category decisions.
  format_prompt() — injects context into role templates.

agents/runner.py:
  run_agent() — launches claude CLI as subprocess with role prompt.
  run_pipeline() — executes multi-step pipelines sequentially,
  chains output between steps, logs to agent_logs, creates/updates
  pipeline records, handles failures gracefully.

agents/specialists.yaml — 8 roles with tools, permissions, context rules.
agents/prompts/pm.md — PM prompt for task decomposition.
agents/prompts/security.md — security audit prompt (OWASP, auth, secrets).

CLI: kin run <task_id> [--dry-run]
  PM decomposes → shows pipeline → executes with confirmation.

31 new tests (15 context_builder, 11 runner, 5 JSON parsing).
92 total, all passing.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-15 14:03:32 +02:00