¨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¨
|
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¨
|
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¨
|
8e492ffa90
|
test: run evolution test with exact measurements
Results:
- Tests: 54/54 passed (100%)
- Time: 214.16ms (millisecond precision)
- Fitness: 1.00 (PASS)
Breakdown:
- Test pass rate: 100% (weight 50%, contribution 0.50)
- Quality gates: 5/5 (weight 25%, contribution 0.25)
- Efficiency: 0.9993 (weight 25%, contribution 0.25)
System verified:
- Bun runtime installed and working
- Fitness calculation precise to 2 decimals
- Logging to fitness-history.jsonl working
|
2026-04-06 01:08:54 +01:00 |
|
¨NW¨
|
1703247651
|
feat: add Docker-based evolution testing with precise measurements
- Add docker/evolution-test/Dockerfile with bun, TypeScript
- Add docker/evolution-test/docker-compose.yml for parallel workflow testing
- Add run-evolution-test.sh and .bat scripts for cross-platform
- Update pipeline-judge.md with Docker-first approach:
- Millisecond precision timing (date +%s%3N)
- 2 decimal places for test pass rate and coverage
- Docker container for consistent test environment
- Multiple workflow types (feature/bugfix/refactor/security)
Enables:
- Parallel testing with docker-compose
- Consistent environment across machines
- Precise fitness measurements (ms, 2 decimals)
- Multi-workflow testing in containers
|
2026-04-06 00:48:21 +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 |
|
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 |
|