Auto mode now calls generate_followups() after task_auto_approved hook.
Permission-blocked followup items are auto-resolved: rerun first, fallback
to manual_task on failure. Recursion guard skips followup-sourced tasks.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- scripts/rebuild-frontend.sh: builds Vue 3 frontend and restarts uvicorn API
- cli/main.py: hook group with add/list/remove/logs/setup commands;
`hook setup` idempotently registers rebuild-frontend for a project
- agents/runner.py: call run_hooks(event="pipeline_completed") after
successful pipeline; wrap in try/except so hook errors never block results
- tests: 3 tests for hook_setup CLI + 3 tests for pipeline→hooks integration
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
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>
- 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>
- 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>
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>
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>
