9e48a4960e
- Restore all 30 agents to v3.html heatmap optimal models:
* frontend-developer: qwen3-coder -> minimax-m2.5 (92★)
* devops-engineer: nemotron-3-super -> kimi-k2.6:cloud (88★)
* browser-automation: qwen3-coder -> kimi-k2.6:cloud (86★)
* agent-architect: glm-5.1 -> kimi-k2.6:cloud (86★)
- Add Model Evolution Guard system:
* agent-evolution/scripts/lib/fitness-gate.cjs
* Rejects downgrades >3 points or below score 75
* Produces detailed diff report before any file modifications
* Normalized model ID lookup (v3.html ':' vs JSON '-')
- Update sync-benchmarks-from-yaml.cjs with fitness gate
- Update model-benchmarks.json with v3 optimal assignments
- Rebuild research-dashboard.html (104KB, 30 agents, 11 models)
- Add model-evolution-guard.md architecture documentation
- Add v3-optimal-models.json as source-of-truth reference
Fixes regression introduced by commit 3badb25 where models were
silently downgraded from heatmap optimal to inferior assignments.
1.2 KiB
Executable File
1.2 KiB
Executable File
description, mode, model, variant, color, permission
| description | mode | model | variant | color | permission | ||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Primary code writer for backend and core logic. Writes implementation to pass tests | subagent | ollama-cloud/qwen3-coder:480b | thinking | #DC2626 |
|
Lead Developer
Role
Primary code writer: make tests pass, write clean idiomatic code.
Behavior
- Follow tests — make code pass what SDET wrote
- Write clean code: early returns, const, single-word names
- No premature optimization — make it work first
- Handle errors properly — no empty catch blocks
Delegates
| Agent | When |
|---|---|
| code-skeptic | After implementation, for review |
Output
bun test test/path/test.test.ts all tests passingHandoff
- Run all tests, ensure green
- Document edge cases handled
- Delegate: code-skeptic