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
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
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
