- Added planner, reflector, memory-manager to capability-index.yaml
- Extended capability_routing with cognitive capabilities
- Updated orchestrator.md with new agent permissions and routing table
- All 3 new agents integrated into workflow
Related: Issue #25 (Research Milestone)
- Add upload_screenshot function to gitea-commenting skill
- Support multipart/form-data for attachments
- Create .test/e2e_test_screenshots.py test script
- Support SVG screenshots as placeholders
- 2 attachments uploaded to Issue #12 successfully
Gitea API:
- POST /repos/{owner}/{repo}/issues/{id}/assets - Upload attachment
- POST /repos/{owner}/{repo}/issues/{id}/comments - Comment with image reference
- GET /repos/{owner}/{repo}/issues/{id}/assets - List attachments
Milestone #44: All issues completed
- Create Dockerfile.playwright with headed mode by default
- Create docker-compose.yml with MCP server, headed, and test profiles
- Update Playwright skill to recommend headed mode for observation
- Remove --headless flag so browser window is visible
- Add BROWSER_VISIBILITY.md guide for X11/Docker setup
- Add README.Docker.md with quick start instructions
Configuration:
- PLAYWRIGHT_MCP_HEADLESS=false (browser visible)
- Requires X11 display for Docker (DISPLAY=:0)
- Three profiles: default, debug, test
Refs: #12 in 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
CRITICAL: All agents MUST now:
1. Check history before starting work (git log, closed issues)
2. Create milestones for complex tasks
3. Update issue checkboxes before closing
Changes:
- Add .kilo/skills/task-analysis/SKILL.md - history check, milestone creation, checkbox updates
- Update requirement-refiner.md - add history check and milestone creation workflow
- Update release-manager.md - add mandatory checkbox updates before closing issues
All agents now require:
- Post comment to Gitea (MANDATORY)
- Update issue checkboxes (MANDATORY)
- Close issue only when all checkboxes done
- 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.
- Add @capability-analyst agent to analyze task requirements vs available tools
- Update @agent-architect to create new agents/workflows/skills based on gap analysis
- Add workflow for automatic review and fix task creation
Workflow:
1. @capability-analyst analyzes incoming task
2. Maps requirements to existing capabilities
3. Identifies gaps (agents, workflows, skills)
4. Recommends new components or enhancements
5. @agent-architect creates requested components
6. @capability-analyst reviews and validates
Gap types:
- Critical: No tool covers this requirement
- Partial: Tool exists but lacks feature
- Integration: Tools exist but don't work together
- Skill: Need domain knowledge
Output:
- Coverage analysis with requirements mapping
- Recommendations for new agents/workflows/skills
- Integration points and dependencies
- Handoff to @agent-architect for creation
- 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
Update the git authentication failure reporting guidelines to provide
specific remote URL commands for SSH and HTTPS. Include troubleshooting
steps for common password typos and provide specific credential examples
for the internal Gitea repository.
- 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)
- Rename .kilos/ → .kilo/ (correct name for @kilocode/plugin discovery)
- 19 agents in .kilo/agent/ with proper YAML frontmatter:
description, mode, model, color — all correctly set
- Fix ask.md: rename ## Response Format → ## Output Format
- Add ## Output Format section to code.md (Quick Coder)
- README: update structure to reflect .kilo/ as primary KiloCode runtime
- .kilocode/agents/ kept as legacy archive (root-owned, read-only)
Fixes: KiloCode losing agent settings when .kilo/ directory present.
Root cause was conflicting agent sources — now resolved by using
.kilo/agent/ as single source of truth for KiloCode plugin.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
