Commit graph

5 commits

Author SHA1 Message Date
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
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