Commit graph

77 commits

Author SHA1 Message Date
Gros Frumos
6705b302f7 test(KIN-005): parameterize task status update test for all valid statuses
Expand test_task_update_status to test all 7 valid statuses including
'cancelled' via CLI. Each status now has its own test case through
pytest parametrization.

Test suite now: 208 → 214 tests (all passing ✓)

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
2026-03-15 18:48:16 +02:00
Gros Frumos
8e517d5888 fix(tests): update test expectations to match KIN_NONINTERACTIVE env behavior
test_interactive_uses_600s_timeout: 600 → 300
test_interactive_no_stdin_override: None → subprocess.DEVNULL

When KIN_NONINTERACTIVE=1 is set in environment, runner always uses
300s timeout and DEVNULL stdin regardless of noninteractive parameter.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-15 18:34:47 +02:00
Gros Frumos
d311c2fb66 feat: add post-pipeline hooks (KIN-003)
- core/hooks.py: HookRunner с CRUD, run_hooks(), _execute_hook(), логированием
- core/db.py: новые таблицы hooks и hook_logs в схеме
- agents/runner.py: вызов run_hooks() после завершения pipeline
- tests/test_hooks.py: 23 теста (CRUD, fnmatch-матчинг, выполнение, таймаут)

Хуки запускаются синхронно после update_task(status="review").
Ошибка хука логируется, не блокирует пайплайн.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-15 18:31:00 +02:00
Gros Frumos
bf38532f59 Add cancelled status for tasks
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-15 18:22:17 +02:00
Gros Frumos
6e872121eb feat: status dropdown on task detail page 2026-03-15 18:17:57 +02:00
Gros Frumos
9cbb3cec37 Fix audit hanging: add auto_apply param + allow_write for tool access
Root cause: claude agent without --dangerously-skip-permissions
hangs on tool permission prompts when stdin=DEVNULL.

Fixes:
- run_audit() now passes allow_write=True so agent can use
  Read/Bash tools without interactive permission prompts
- Added auto_apply param: False for API (result only),
  CLI confirms with user then applies manually
- API explicitly passes auto_apply=False
- Tests for auto_apply=True/False behavior

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-15 18:00:39 +02:00
Gros Frumos
96509dcafc Add backlog audit and task update command
- agents/prompts/backlog_audit.md: QA analyst prompt for checking
  which pending tasks are already implemented in the codebase
- agents/runner.py: run_audit() — project-level agent that reads
  all pending tasks, inspects code, returns classification
- cli/main.py: kin audit <project_id> — runs audit, offers to mark
  done tasks; kin task update <id> --status --priority
- web/api.py: POST /api/projects/{id}/audit (runs audit inline),
  POST /api/projects/{id}/audit/apply (batch mark as done)
- Frontend: "Audit backlog" button on ProjectView with results
  modal showing already_done/still_pending/unclear categories

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-15 17:44:16 +02:00
Gros Frumos
e755a19633 Add Auto/Review mode toggle and non-interactive runner
- GUI: Auto/Review toggle on TaskDetail and ProjectView
  persisted per-project in localStorage
- Runner: noninteractive param (stdin=DEVNULL, 300s timeout)
  activated by KIN_NONINTERACTIVE=1 env or param
- CLI: --allow-write flag for kin run command
- API: POST /run accepts {allow_write: bool}, sets
  KIN_NONINTERACTIVE=1 and stdin=DEVNULL for subprocess
- Fixes pipeline hanging on interactive claude input (VDOL-002)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-15 17:35:08 +02:00
Gros Frumos
03961500e6 Use relative API paths for Tailscale access
Replaced hardcoded http://localhost:8420/api with /api so the
frontend works from any host (Tailscale, LAN, etc).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-15 17:13:37 +02:00
Gros Frumos
3ef00bced1 Add SPA static serving and open CORS for Tailscale access
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-15 17:11:38 +02:00
johnfrum1234
db1729730f Full pipeline flow through web interface with live updates
API:
  POST /api/tasks/{id}/run — sets task to in_progress immediately,
    launches subprocess with error handling and logging.
  GET /api/tasks/{id}/running — checks pipelines table for active run.
  Fixed --db flag position in subprocess command.

TaskDetail (live pipeline):
  - Run button starts pipeline, auto-starts 3s polling
  - Pipeline cards update in real-time as agent_logs appear
  - Pulsing blue dot on header while in_progress
  - Spinner on run button during execution
  - Auto-stops polling when status changes from in_progress
  - Cleanup on component unmount (no leaked timers)

ProjectView (run from list):
  - [>] button on each pending task row
  - Confirm dialog before starting
  - Pulsing blue dot for in_progress tasks
  - Click task row → /task/:id with live view

Dashboard (live statuses):
  - Pulsing blue dot next to active task count
  - Auto-poll every 5s when any project has active tasks
  - Stops polling when no active tasks

5 new API tests (running endpoint, run sets status, not found).
141 tests total, all passing. Frontend builds clean.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 15:29:05 +02:00
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
johnfrum1234
9264415776 Add follow-up task generation on approve
When approving a task, PM agent analyzes pipeline output and creates
follow-up tasks automatically (e.g. security audit → 8 fix tasks).

core/followup.py:
  generate_followups() — collects pipeline output, runs followup agent,
  parses JSON task list, creates tasks with parent_task_id linkage.
  Handles: bare arrays, {tasks:[...]} wrappers, invalid JSON, empty.

agents/prompts/followup.md — PM prompt for analyzing results and
  creating actionable follow-up tasks with priority from severity.

CLI: kin approve <task_id> [--followup] [--decision "text"]
API: POST /api/tasks/{id}/approve {create_followups: true}
  Returns {status, decision, followup_tasks: [...]}

Frontend (TaskDetail approve modal):
  - Checkbox "Create follow-up tasks" (default ON)
  - Loading state during generation
  - Results view: list of created tasks with links to /task/:id

ProjectView: tasks show "from VDOL-001" for follow-ups.

13 new tests (followup), 125 total, all passing.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 15:02:58 +02:00
johnfrum1234
f7830d484c Let pipeline subprocess stderr flow to uvicorn terminal
Removed stderr=subprocess.DEVNULL from POST /api/tasks/{id}/run
so errors from background kin run are visible in the API server log.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 14:46:20 +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
38c252fc1b Add task detail view, pipeline visualization, approve/reject workflow
API (web/api.py) — 5 new endpoints:
  GET  /api/tasks/{id}/pipeline — agent_logs as pipeline steps
  GET  /api/tasks/{id}/full — task + steps + related decisions
  POST /api/tasks/{id}/approve — mark done, optionally add decision
  POST /api/tasks/{id}/reject — return to pending with reason
  POST /api/tasks/{id}/run — launch pipeline in background (202)

Frontend:
  TaskDetail (/task/:id) — full task page with:
    - Pipeline graph: role cards with icons, arrows, status colors
    - Click step → expand output (pre-formatted, JSON detected)
    - Action bar: Approve (with optional decision), Reject, Run Pipeline
    - Polling for live pipeline updates
  Dashboard: review_tasks badge ("awaiting review" in yellow)
  ProjectView: task rows are now clickable links to /task/:id

Runner: output_summary no longer truncated (full output for GUI).
Models: get_project_summary includes review_tasks count.

13 new API tests, 105 total, all passing. Frontend builds clean.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 14:32:29 +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
johnfrum1234
86e5b8febf Add web GUI: FastAPI API + Vue 3 frontend with dark theme
API (web/api.py):
  GET  /api/projects, /api/projects/{id}, /api/tasks/{id}
  GET  /api/decisions?project=X, /api/cost?days=7, /api/support/tickets
  POST /api/projects, /api/tasks, /api/decisions, /api/bootstrap
  CORS for localhost:5173, all queries via models.py

Frontend (web/frontend/):
  Vue 3 + TypeScript + Vite + Tailwind CSS v3
  Dashboard: project cards with task counters, cost, status badges
  ProjectView: tabs for Tasks/Decisions/Modules with filters
  Modals: Add Project, Add Task, Add Decision, Bootstrap
  Dark theme, monospace font, minimal clean design

Startup:
  API:  cd web && uvicorn api:app --reload --port 8420
  Web:  cd web/frontend && npm install && npm run dev

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 13:50:15 +02:00
johnfrum1234
b95db7c7d6 bootstrap: vdol project loaded with real data 2026-03-15 13:40:58 +02:00
johnfrum1234
e5444114bd Fix bootstrap: deep scan, CLAUDE.md fallback, noise filtering
1. Tech stack: recursive file search (depth 3) + CLAUDE.md text fallback
   when config files are on remote server (detects nodejs, postgresql, etc.)
2. Modules: scan */src/ patterns in top-level dirs (frontend/src/, backend-pg/src/)
3. Decisions: filter out unrelated sections (Jitsi, Nextcloud, Prosody, GOIP),
   filter noise (commit hashes, shell commands, external service paths).
   Noise filtering also applied to Obsidian decisions.

Tested on vdolipoperek: 4 tech, 5 modules, 9 clean decisions, 24 Obsidian tasks.
61 tests, all passing.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 13:37:42 +02:00
johnfrum1234
da4a8aae72 Add bootstrap command — auto-detect project stack, modules, decisions
kin bootstrap <path> --id <id> --name <name> [--vault <path>]

Detects: package.json, requirements.txt, go.mod, config files → tech_stack.
Scans src/app/lib/frontend/backend dirs → modules with type detection.
Parses CLAUDE.md for GOTCHA/WORKAROUND/FIXME/ВАЖНО → decisions.
Scans Obsidian vault for kanban tasks, checkboxes, and decisions.
Preview before save, -y to skip confirmation.
18 bootstrap tests, 57 total passing.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 13:29:01 +02:00
johnfrum1234
432cfd55d4 Add CLI (cli/main.py) — click-based interface for all core operations
Commands: project (add/list/show), task (add/list/show),
decision (add/list), module (add/list), status, cost.
Auto-generated task IDs (PROJ-001). DB at ~/.kin/kin.db or $KIN_DB.
pyproject.toml with `kin` entry point. 18 CLI tests, 39 total passing.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 13:20:57 +02:00
johnfrum1234
3db73332ad Add core/models.py — data access functions for all 9 tables
20 functions covering: projects, tasks, decisions, modules,
agent_logs, pipelines, support tickets, and dashboard stats.
Parameterized queries, JSON encode/decode, no ORM.
21 tests, all passing.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 13:16:12 +02:00
johnfrum1234
d7491705d9 Add core/db.py — SQLite schema with all 9 tables from DESIGN.md 3.5
Tables: projects, tasks, decisions, agent_logs, modules, pipelines,
project_links, support_tickets, support_bot_config.
WAL mode, foreign keys enabled, idempotent init.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 13:12:54 +02:00
johnfrum1234
bdb9fb4a65 Add CLAUDE.md — project-level instructions for Kin
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 13:10:47 +02:00
johnfrum1234
f5a0e2f0b9 Add DESIGN.md — main architecture document for Kin agent orchestrator
Copied from agent-orchestrator-research.md as the foundational design reference.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 13:10:10 +02:00
58ce85495d Initial commit 2026-03-15 12:09:02 +01:00