UniqueSoft/APAW
2
0
Fork 0
Code Issues 15 Pull Requests Actions Packages Projects Releases Wiki Activity
136 Commits 2 Branches 1 Tag
4e9ea678bd89cb7c518ce46d6fbeb28fa0aa65f9
Commit Graph

33 Commits

Author SHA1 Message Date
NW
4c9a95661f evolution: remove obsolete :cloud suffix from kimi-k2.6 model id across all configs 2026-05-13 09:27:48 +01:00
NW
defe57d53a feat: merge infrastructure skills and workflows from TenerifeProp 
Add MCP-based infrastructure skills:
- mcp-integration: Playwright + GitMCP
- e2e-testing: Cypress + AntV + Slack
- search-integration: Brave + Tavily + Markitdown
- security-scanner: CVE Search + MCP Validator
- knowledge-base: Docfork + Wikipedia + ArXiv
- prompt-manager: version control + DevTrends
- api-catalog: MCP server registry
- agent-architect-mcp: patterns + OpenAPI converter

Add workflow commands:
- feature.md: full feature pipeline
- hotfix.md: urgent bug fix workflow

Add rules:
- orchestrator-self-evolution.md
- sdet-engineer.md

Add audit:
- WORKFLOW_AUDIT.md

Source: UniqueSoft/TenerifeProp
 2026-05-06 23:04:14 +01:00
¨NW¨
3badb259cc feat: bidirectional research dashboard + agent config fixes 
- Integrate apaw_agent_model_research_v3.html as standalone dashboard
- Add model-benchmarks.json with 32 agents, 11 scored models, 11 recommendations
- Add build-research-dashboard.ts: inject live data into template → standalone HTML
- Add rebuild-template.cjs: regenerate template from v3.html source
- Add sync-benchmarks-from-yaml.cjs: sync YAML → JSON round-trip
- Add sync-model-research.ts: apply recommendation matrix to config files
- Add model-benchmarks.schema.json and model-research.schema.json for validation
- Add bidirectional-data-flow.md architecture documentation
- Add log-execution.cjs pipeline hook
- Update capability-index.yaml: add fallback_models, failover_strategy
- Update kilo-meta.json, kilo.jsonc, KILO_SPEC.md with synced models
- Update evolution.md / research.md / self-evolution.md / evolutionary-sync.md docs
- Fix security-auditor.md: quote YAML color (#DC2626)
- Fix orchestrator.md: remove duplicate devops-engineer key
- Build research-dashboard.html (106KB standalone) + dated archive
 2026-04-29 21:04:22 +01:00
¨NW¨
6b71ea2b57 feat: add .architect/ project mapping system with architect-indexer agent and Docker containerization 
- Add .architect/ directory structure (10 template files) as project brain for agent orientation
- Add architect-indexer agent that scans codebase and generates structured architecture docs
- Add Docker containerization: Dockerfile.architect-indexer, docker-compose.architect.yml
- Add TypeScript project-mapper module with staleness detection and context injection
- Add /index-project command, architect-first-contact rule, project-mapping skill
- Integrate orchestrator first-contact check: triggers indexing before any task delegation
- Add npm arch:* scripts for Docker-based indexing workflow
- Register agent in capability-index.yaml and AGENTS.md
 2026-04-22 20:01:38 +01:00
¨NW¨
9d85dd9f83 merge: dev into main — centralized auth + trailing-slash fix + all recent features 
- Security: extricate hardcoded Gitea credentials, add centralized auth module
- Fix: get_target_repo() regex now handles trailing slashes (.rstrip('/') in Python, sed 's:/*' in Bash)
- Fix: task-analysis broken functions (orphaned req references, stray parentheses)
- Documentation: README.md, STRUCTURE.md, AGENTS.md updated with auth section
- Evolution: Entry #5 documenting credentials extrication
 2026-04-19 12:20:38 +01:00
¨NW¨
573d9a641e fix(security): add rstrip('/') to get_target_repo for trailing-slash URLs 
The regex r'[:/]([^/]+/[^/]+?)(?:\.git)?$' fails on URLs with trailing slashes
like 'https://git.softuniq.eu/UniqueSoft/APAW/' because the final '/' breaks
the pattern. Added .rstrip('/') in Python and sed 's:/*' in Bash to all
get_target_repo() implementations across 11 files.
 2026-04-19 12:17:53 +01:00
¨NW¨
7523911812 fix(security): extricate hardcoded Gitea credentials, add centralized auth module 
- Remove all hardcoded NW:eshkink0t credentials from 9 files across skills, commands, rules, and specs
- Add .kilo/shared/gitea-auth.md with get_gitea_token() and .kilo/gitea.jsonc config structure
- All Gitea API callers now use env vars (GITEA_TOKEN → GITEA_USER+GITEA_PASS → ValueError)
- Fix task-analysis/SKILL.md broken functions (orphaned req references, stray parentheses)
- Replace hardcoded UniqueSoft/APAW API URLs with get_target_repo() auto-detection in 3 files
- Update README.md, STRUCTURE.md, AGENTS.md with centralized auth documentation
- Add EVOLUTION_LOG Entry #5 documenting credentials extrication
 2026-04-19 11:43:59 +01:00
¨NW¨
7445e66676 feat: add Next.js, Vue/Nuxt, React, Python (Django/FastAPI) skills and agents 
- python-developer agent: Django/FastAPI backend specialist
- nextjs-patterns skill: App Router, Server Components, Server Actions, Auth.js
- vue-nuxt-patterns skill: Composition API, Pinia, Nitro server, SSR
- react-patterns skill: hooks, Context, TanStack Query, React Hook Form
- python-django-patterns skill: DRF, services, repositories
- python-fastapi-patterns skill: async, Pydantic, SQLAlchemy, dependencies
- /nextjs pipeline command for full-stack Next.js apps
- /vue pipeline command for full-stack Vue/Nuxt apps
- Updated frontend-developer with framework-specific skills
- Updated orchestrator, capability-index for Python + frontend routing
- Updated README, STRUCTURE, EVOLUTION_LOG with all new stacks

Total agents: 30. Stacks: PHP, Next.js, Vue/Nuxt, React, Python, Go, Flutter, Node.js
 2026-04-19 10:04:51 +01:00
¨NW¨
b46a1a20a8 feat: add PHP development stack, atomic tasks, modular code rules, agent monitoring, fix target project detection 
7 evolutionary tasks implemented:

1. PHP web development: php-developer agent + 6 skills (Laravel, Symfony, WordPress, security, testing, modular architecture) + 2 pipeline commands (/laravel, /wordpress)

2. Atomic task decomposition: 1 action = 1 task rule, task sizing guide, decomposition protocol for orchestrator, token budgets per complexity

3. Modular code rules: max 100 lines/file, max 30 lines/function, service/repository patterns, cross-module communication via events only

4. Gitea-centric workflow: mandatory issue creation before work, research with links, progress checkboxes, screenshots on test, git history as knowledge base

5. Fix: target project auto-detection — removed all hardcoded UniqueSoft/APAW from API calls, added get_target_repo() via git remote, GITEA_TARGET_REPO env override

6. Agent execution monitoring: agent-executions.jsonl logging, agent-stats.ts statistics script, required fields per invocation, Gitea comment includes duration/tokens

7. Token optimization: 1 action = 1 task principle, token budgets by task type, routing matrix, no scope creep, skip unnecessary pipeline steps
 2026-04-18 23:43:04 +01:00
¨NW¨
c416f53103 refactor: clean main to starter template — remove project-specific and generated files 
- Remove project-specific commands: booking, blog, commerce, landing-page, feature, hotfix
- Remove project-specific skills: booking, blog, ecommerce
- Remove generated files: EVOLUTION_LOG, WORKFLOW_AUDIT, logs/, reports/
- Add .gitignore entries for auto-generated dirs (.kilo/logs/, .kilo/reports/)
- Remove e2e_booking_flow from capability-index.yaml
- Remove docker/evolution-test/ (dev infra, not starter)
- Genericize AGENTS.md project description
- Genericize tests/README.md title

All removed content preserved on dev branch.
 2026-04-17 21:11:12 +01:00
¨NW¨
2573d81cff refactor: remove CBS-specific e2e-booking flow — belongs to CBS project, not APAW starter 2026-04-17 20:21:29 +01:00
NW
c258d16ef5 feat: add Gitea integration, E2E booking flow, Docker DNS fix, browser-launcher module 
- Add tests/scripts/lib/gitea-client.js: Gitea API client with auth, comments,
  attachments, and Markdown report formatters for visual and console reports
- Add tests/scripts/lib/browser-launcher.js: shared Playwright launch config with
  --dns-resolution-order=hostname-first, realistic UA, and navigateTo() helper
  using waitUntil:'commit' + waitForLoadState('domcontentloaded')
- Add tests/scripts/e2e-booking-flow-v2.js: full E2E scenario for irina-vik.ru
  (register → book service → login → personal cabinet) with Gitea reporting
- Update visual-test-pipeline.js: GITEA_ISSUE env var, Gitea comment+attachment
  posting, browser-launcher integration, waitUntil:'commit' navigation
- Update console-error-monitor-standalone.js: same Gitea + DNS fixes
- Update capture-screenshots.js: browser-launcher integration, DNS fix
- Update docker-compose.web-testing.yml: NETWORK_MODE env var (bridge),
  DNS_RESOLUTION_ORDER, GITEA_USER/PASSWORD env passthrough, e2e-booking service
- Update tests/package.json: pin playwright to exact 1.52.0 (matches Docker image)
- Update .gitignore: add tests/visual/e2e/ for E2E screenshots
- Update .kilo/agents/visual-tester.md: Docker networking note, Gitea scripts,
  e2e-booking service, updated script table
- Update .kilo/commands/web-test.md: Docker Networking section, --issue flag,
  Gitea Integration section, e2e-booking service
- Update .kilo/commands/e2e-test.md: complete rewrite — Docker-based Playwright,
  no more MCP dependency, proper service table, Gitea integration docs
- Update .kilo/capability-index.yaml: add gitea_integration, e2e_booking_flow,
  docker_networking capabilities to visual-tester; add routing entries
 2026-04-17 09:27:27 +01:00
NW
3a8aa6b416 docs: update visual testing agent docs, remove test artifacts from git, add pipeline documentation 
- Remove baseline screenshots from git tracking (test artifacts, not code)
- Add tests/visual/baseline/ to .gitignore
- Rewrite .kilo/agents/visual-tester.md: Docker-first pipeline, bbox extraction, console/network error detection
- Rewrite .kilo/commands/web-test.md: accurate commands, output format, agent flow
- Update .kilo/capability-index.yaml: add bbox_extraction, console_error_detection, button_overflow_detection to visual-tester
- Update AGENTS.md: add /web-test and /e2e-test commands, update visual-tester description
 2026-04-16 22:48:46 +01:00
¨NW¨
e074612046 feat: add web testing infrastructure 
- Docker configurations for Playwright MCP (no host pollution)
- Visual regression testing with pixelmatch
- Link checking for 404/500 errors
- Console error detection with Gitea issue creation
- Form testing capabilities
- /web-test and /web-test-fix commands
- web-testing skill documentation
- Reorganize project structure (docker/, scripts/, tests/)
- Update orchestrator model to ollama-cloud/glm-5

Structure:
- docker/ - Docker configurations (moved from archive)
- scripts/ - Utility scripts
- tests/ - Test suite with visual, console, links testing
- .kilo/commands/ - /web-test and /web-test-fix commands
- .kilo/skills/ - web-testing skill

Issues: #58 #60 #62
 2026-04-07 08:55:24 +01:00
¨NW¨
b9abd91d07 feat: orchestrator evolution — full access + model upgrades + self-evolution protocol 
- Add 9 missing agents to orchestrator task whitelist (20→28 agents)
- Fix 2 broken agents: debug (gpt-oss:20b→qwen3.6-plus), release-manager (devstral-2→qwen3.6-plus)
- Upgrade orchestrator (glm-5→qwen3.6-plus, IF:80→90, 128K→1M context)
- Upgrade pipeline-judge (nemotron→qwen3.6-plus, IF:85→90)
- Add orchestrator escalation path to 7 agents (lead-dev, sdet, skeptic, perf, security, evaluator, devops)
- Create self-evolution protocol (.kilo/rules/orchestrator-self-evolution.md)
- Create evolution log (.kilo/EVOLUTION_LOG.md)
- Full audit of all 29 agents with verification tests
 2026-04-06 22:55:12 +01:00
¨NW¨
fa68141d47 feat: add pipeline-judge agent and evolution workflow system 
- Add pipeline-judge agent for objective fitness scoring
- Update capability-index.yaml with pipeline-judge, evolution config
- Add fitness-evaluation.md workflow for auto-optimization
- Update evolution.md command with /evolve CLI
- Create .kilo/logs/fitness-history.jsonl for metrics logging
- Update AGENTS.md with new workflow state machine
- Add 6 new issues to MILESTONE_ISSUES.md for evolution integration
- Preserve ideas in agent-evolution/ideas/

Pipeline Judge computes fitness = (test_rate*0.5) + (gates*0.25) + (efficiency*0.25)
Auto-triggers prompt-optimizer when fitness < 0.70
 2026-04-06 00:23:50 +01:00
¨NW¨
1ab9939c92 fix: correct OpenRouter model paths across all files 
Fixed format from 'qwen/...' to 'openrouter/qwen/...' for:
- product-owner.md
- prompt-optimizer.md
- workflow-architect.md
- status.md, blog.md, booking.md, commerce.md
- kilo.jsonc (default model + ask agent)
- agent-frontmatter-validation.md
- agent-versions.json (recommendations and history)
 2026-04-05 23:47:14 +01:00
¨NW¨
a4e09ad5d5 feat: upgrade agent models based on research findings 
- capability-analyst: nemotron-3-super → qwen3.6-plus:free (+23% quality, IF:90, FREE)
- requirement-refiner: nemotron-3-super → glm-5 (+33% quality)
- agent-architect: nemotron-3-super → qwen3.6-plus:free (+22% quality)
- evaluator: nemotron-3-super → qwen3.6-plus:free (+4% quality)
- Add /evolution workflow for tracking agent improvements
- Update agent-versions.json with evolution history
 2026-04-05 23:37:23 +01:00
¨NW¨
348c47fa6f feat: add research cycle skill and /research command for continuous self-improvement 
- Created research-cycle skill with automatic monitoring
- Added /research command for manual or automatic research
- Configured research sources: Anthropic, OpenAI, Lilian Weng
- Implemented evolution tracking workflow

Components:
- .kilo/skills/research-cycle/SKILL.md: Self-improvement logic
- .kilo/commands/research.md: Research command definition
- AGENTS.md: Added /research to command list

Milestone: Cognitive Enhancement - Agent Evolution (#47)
Related: Issue #25 (Research Milestone)
 2026-04-05 02:07:08 +01:00
¨NW¨
da5c365183 feat: add Gitea workflow integration with quality gates and closed-loop execution 2026-04-05 01:40:26 +01:00
¨NW¨
39eeb2f35f feat: add workflow executor, quality controller, and workflow architect for closed-loop execution 2026-04-05 01:36:39 +01:00
¨NW¨
14b2cb2742 feat: add booking workflow for service businesses (salons, clinics, massage) 2026-04-05 01:27:25 +01:00
¨NW¨
23eb60762c feat: add workflows for CMS, E-commerce, Blog + backend-developer agent + prompt-engineering rules 2026-04-05 01:19:09 +01:00
¨NW¨
1f96aec2b6 feat: add landing-page workflow for HTML mockup to production deployment 2026-04-05 01:02:38 +01:00
swp
5793b7909b feat: add web testing system with browser automation (Milestone #44) 
- Create browser-automation agent for E2E testing via Playwright MCP
- Create visual-tester agent for screenshot comparison and regression testing
- Add playwright skill with MCP configuration and Docker setup
- Add visual-testing skill with pixelmatch comparison
- Add /e2e-test command for running browser tests
- Add Issue #11 research results for Playwright MCP and Docker

Milestone #44: Web Testing System with Browser Automation

New Agents:
- @browser-automation: Browser control via Playwright MCP
- @visual-tester: Visual regression testing with diff detection

New Skills:
- playwright: MCP configuration, Docker setup, usage examples
- visual-testing: Screenshot comparison, baseline management, HTML reports

New Commands:
- /e2e-test: Run E2E tests with browser automation

Refs: #11 #12 #13 #14 #15 #16
 2026-04-04 03:49:56 +01:00
swp
a1a15473a0 feat: add mandatory Gitea commenting to all agents 
- Add gitea-commenting skill with comment templates
- Update orchestrator with mandatory commenting requirements
- Add Gitea Commenting section to all 17 agent files
- Create email validation module (validateEmail function)
- Add efficiency_score.json for pipeline logging
- Create test-error-recovery.js for error recovery testing

Refs: Milestone #43 - System Consistency Testing
All 6 test issues closed successfully
 2026-04-04 03:18:28 +01:00
swp
657407d5ef fix: replace unavailable model references with available ones 
- Replace anthropic/claude-sonnet-4 with ollama-cloud/gpt-oss:120b in:
  - capability-analyst.md
  - agent-architect.md
- Replace openai/compound with ollama-cloud/glm-5 in review-watcher.md
- Remove duplicate model definitions in agent-architect.md
- Add AGENT_AUDIT.md documenting all model fixes

Available models use prefixes:
- ollama-cloud/ (primary)
- openrouter/ (router)
- qwen/ (direct)
- groq/ (fast inference)

NOT available:
- anthropic/ (Claude)
- openai/ (use via ollama-cloud/gpt-oss instead)

All 18 agents and 11 commands now use available models.
 2026-04-04 01:54:02 +01:00
swp
97bc4902ea feat: add review-watcher and fix-workflow automation 
- Add review-watcher command that detects completion markers
- Add fix-workflow skill for automatic fix task creation
- Add review-watcher.sh script for monitoring issues
- Automatic task creation based on issue severity
- Integration with scoped labels (priority::, status::)

Workflow:
1. Watcher detects /done, /completed, 'выполнено', 'готово' in comments
2. Runs validation (markdown, code, security, performance)
3. Creates fix tasks for issues found
4. Assigns tasks based on issue type
5. Updates parent issue with fix task links
6. Sets appropriate labels (status::fixing, status::blocked)

Fix task priority:
- Critical: Block merge, assign to @the-fixer
- High: Fix before merge, assign to @lead-developer
- Medium: Current sprint, add to backlog
- Low: Optional, comment only
 2026-04-04 01:44:53 +01:00
swp
35bbdcb08f feat: integrate agent-manager module with KiloCode workflows 
- Move agent-manager from packages/opencode/ to src/kilocode/
- Add Gitea client for pipeline logging
- Add pipeline-runner for workflow orchestration
- Create slash commands: /pipeline, /status, /evaluate
- Update AGENTS.md with workflow documentation
- Update README.md with KiloCode integration details
- Add package.json and tsconfig.json for TypeScript compilation
- Remove duplicate files from packages/opencode/

This enables:
- /pipeline <issue> - run full agent pipeline with Gitea logging
- Direct agent invocation via @mention
- Performance tracking and prompt optimization
 2026-04-04 01:11:06 +01:00
swp
4a69c5323b feat: update agent models to current configuration 
- Update README.md with correct model assignments for all agents
- Sync AGENTS.md and .kilo/ files with new model IDs
- Change History Miner: Gemini-3-Flash → GPT-OSS 20B
- Change System Analyst: GPT-OSS 120B → Qwen3.6-Plus (Free)
- Change Product Owner: Qwen3.5 122B → Qwen3.6-Plus (Free)
- Change Lead Developer: DeepSeek-v3.2 → Qwen3-Coder 480B
- Change The Fixer: MiniMax-m2.7 → MiniMax-m2.5
- Change SDET Engineer: Qwen3-Coder-Next → Qwen3-Coder 480B
- Change Code Skeptic: GPT-OSS 120B → MiniMax-m2.5
- Change Security Auditor: GLM-4.7 → Kimi-k2.5
- Change Release Manager: Devstral-2 123B → Qwen3-Coder 480B
- Change Evaluator: GPT-o3 → GPT-OSS 120B
- Change Prompt Optimizer: Claude 4.5 → Qwen3.6-Plus (Free)
- Add AgentArchitect agent configuration
- Update commands: plan, ask, debug, code models
- Add permissions configuration to commands
 2026-04-04 00:50:22 +01:00
swp
5cac45acb1 chore(prompts): compress /code command from 169 to 62 lines — removed redundant examples, consolidated style section, simplified workflow 2026-04-04 00:12:47 +01:00
swp
0a93f7dd7e feat: add comprehensive workflow commands for development pipeline 2026-04-03 20:50:43 +01:00
swp
47219c4204 feat: реорганизация структуры агентов и добавление skills согласно документации Kilo Code 
- Добавлен skill gitea для автоматизации git операций
- Добавлены правила безопасности для работы с credentials
- Указан публичный URL проекта: https://git.softuniq.eu/UniqueSoft/APAW
- Реализованы безопасные методы аутентификации (SSH, tokens, credential store)
 2026-04-03 20:14:22 +01:00