feat(agent-models): assign best-fit models from real-fit evaluation report
Updated all 36 agents to their highest-scoring model per real-fit-report.json:
- kimi-k2.6: code-skeptic(91.2), system-analyst(92.0), sdet-engineer(97.0),
lead-developer(72.5), security-auditor(63.8), history-miner,
browser-automation, evolution-prompt, product-owner,
orchestrator, release-manager, reflector
- glm-5.1: devops-engineer(96.2), evaluator, the-fixer, memory-manager,
performance-engineer, prompt-optimizer, workflow-architect,
visual-tester, flutter-developer, incident-responder
- qwen3-coder:480b: architect-indexer, frontend-developer, go-developer,
markdown-validator, pipeline-judge, workflow-cross-checker,
evolution-skeptic, requirement-refiner
- deepseek-v4-pro: backend-developer, capability-analyst, planner,
php-developer, python-developer
Files updated:
- kilo-meta.json (source of truth)
- kilo.jsonc (runtime config)
- capability-index.yaml (routing)
- 30 agent .md frontmatters (via sync-agents.cjs)
- KILO_SPEC.md + AGENTS.md (auto-synced)
- real-fit-report.json (regenerated from DB)
ccca685fdc