Deploy Bot
4a0c78e5c9
feat(agent-models): apply CRITICAL+HIGH model migrations from research
...
Migrations based on model-research-2026-05-24:
- prompt-optimizer: qwen3.6-plus → qwen3.5-122b (CRITICAL, IF=92)
- memory-manager: qwen3.6-plus → deepseek-v4-pro-max (CRITICAL, 1M ctx)
- system-analyst: glm-5.1 → deepseek-v4-pro-max (HIGH, matrix +6)
- evaluator: glm-5.1 → qwen3.5-122b (HIGH, IF=92)
- pipeline-judge: glm-5.1 → kimi-k2.6 (HIGH, matrix +8, 1M ctx)
- workflow-architect: glm-5.1 → qwen3.5-122b (HIGH, IF=92)
7 files changed, 12 insertions(+), 12 deletions(-)
Closes: model-research data gaps for idle models
2026-05-25 14:36:31 +01:00
NW
bd154f24d0
feat(gns2): mass-update all 30 agents with GNS-2 protocol
...
- 29 agents updated with GNS-2 checkpoint/event protocol
- 12 Tier 0 (leaf) agents: read checkpoint, write event footer, no cascade
- 17 Tier 1 (task) agents: read checkpoint, recommend next agent, no direct task calls
- 2 Tier 2 (meta) agents already updated: capability-analyst, agent-architect, evaluator
- All agents now include GNS_EVENT footer template in comments
- Frontmatter updated with '(GNS-2 Tier N)' classification
Scripts added:
- scripts/mass-update-gns-agents.py — idempotent mass updater
- scripts/validate-gns-agents.py — protocol checker
Refs: Milestone #67 , Issues #99-#107
2026-05-08 22:03:08 +01:00
NW
994ca58821
fix(agents): add missing permissions + complete kilo-meta.json
...
- Fix 12 agents missing edit/write/bash permissions
- Add 5 missing agents to kilo-meta.json (architect-indexer, flutter-developer, php-developer, pipeline-judge, python-developer)
- Remove BOM from kilo.jsonc
- All 32 agents now consistent between files and meta
2026-05-07 07:22:32 +01:00
¨NW¨
fb552e0020
feat: v3 optimal model assignments + fitness gate
...
- Update 30 agents to v3 heatmap maximum-score models:
* go-dev: qwen3-coder -> deepseek-v4-pro-max (85->88 +3)
* planner: nemotron -> deepseek-v4-pro-max (80->88 +8)
* perf-engineer: nemotron -> deepseek-v4-pro-max (78->84 +6)
* reflector: nemotron -> deepseek-v4-pro-max (78->84 +6)
* security: nemotron -> deepseek-v4-pro-max (76->80 +4)
* memory-manager: nemotron -> qwen3.6-plus (86->87 +1)
* frontend: kimi-k2.5 -> minimax-m2.5 (92)
* the-fixer: minimax-m2.5 -> kimi-k2.6 (88->90 +2)
* browser-auto: kimi-k2.6 -> qwen3-coder (86->87 +1)
* prompt-opt: glm-5.1 -> qwen3.6-plus (82->83 +1)
* backend: deepseek-v3.2 -> qwen3-coder (91)
* capability-analyst: nemotron -> glm-5.1 (85)
* release-man: devstral-2 -> glm-5.1 (82)
* evaluator: nemotron -> glm-5.1 (86)
* workflow-arch: gpt-oss -> glm-5.1 (84)
- Add Model Evolution Guard:
* fitness-gate.cjs: rejects downgrades >3 points or <75 score
* Normalized model ID lookup (: vs -)
* Diff report before any file modifications
- Update sync-benchmarks-from-yaml.cjs with fitness gate
- Sync kilo-meta.json, kilo.jsonc, .md agent files
- Rebuild research-dashboard.html (104KB, 30 agents, 11 models)
Total improvement: +105 points across 11 agents
Source: v3.html heatmap IF-adjusted composite scores
2026-04-30 08:42:10 +01:00
¨NW¨
28a3b648cc
refactor(prompts): compress 29 agents (-77%) and 7 rules (-55%), delete 2 duplicates
...
Agents: 6,235 → 1,454 lines (-77%). Each agent compressed to Role/Behavior/Delegates/Output/Handoff format.
Gitea commenting extracted to shared block (.kilo/shared/gitea-commenting.md).
Self-evolution protocol extracted to shared block (.kilo/shared/self-evolution.md).
Gitea API client centralized (.kilo/shared/gitea-api.md).
Rules: 2,358 → 1,189 lines (-50%). Deleted sdet-engineer.md (duplicate of agent)
and orchestrator-self-evolution.md (moved to shared/). Compressed docker (549→26),
flutter (521→28), go (283→21), nodejs (271→27), code-skeptic (59→14) to checklists
with skill references.
Fitness: 54/54 tests pass, 29/29 agents validated, fitness=0.92
2026-04-18 13:49:24 +01:00
NW
e19fa3effd
refactor: full agent system revision — migrate to GLM-5.1, fix delegation chains, audit consistency
...
- Migrate 8 agents from openrouter/qwen3.6-plus:free to ollama-cloud/glm-5.1
- Assign thinking/variant/instant depth by role complexity
- Fix broken delegation chains: system-analyst, all developer agents, devops-engineer now can reach orchestrator
- Add task permissions to browser-automation, visual-tester, capability-analyst, markdown-validator
- Add visual-tester permission to flutter-developer and frontend-developer
- Fix capability-index.yaml routing map indentation (go_* keys misplaced)
- Add delegates_to and variant fields to capability-index.yaml
- Update KILO_SPEC.md agent table with Variant column
- Update AGENTS.md with Model/Variant/CanCall columns
- Update kilo.jsonc ask agent model
- Fix YAML indentation in capability-analyst.md and markdown-validator.md
- Update agent-architect.md template models (remove gpt-oss, qwen3.6-plus)
- Add Skills Reference tables to 7 previously unlinked agents
- Full audit: 10/10 consistency checks passed
2026-04-12 22:38:41 +01:00
¨NW¨
caf77f53c8
feat: update agent models based on recommendations
...
- Update security-auditor to ollama-cloud/nemotron-3-super-120b-a12b
- Update performance-engineer to ollama-cloud/nemotron-3-super-120b-a12b
- Update memory-manager to ollama-cloud/nemotron-3-super-120b-a12b
- Update evaluator to ollama-cloud/nemotron-3-super-120b-a12b
- Update planner to ollama-cloud/nemotron-3-super-120b-a12b
- Update reflector to ollama-cloud/nemotron-3-super-120b-a12b
- Update system-analyst to ollama-cloud/glm-5
- Update go-developer to ollama-cloud/qwen3-coder:480b
- Update markdown-validator to ollama-cloud/nemotron-3-nano
- Update prompt-optimizer to ollama-cloud/nemotron-3-super-120b-a12b
- Update product-owner to ollama-cloud/glm-5
Based on archive/agent-model-recommendations.json analysis
2026-04-05 05:21:02 +01:00
¨NW¨
774dc9ac40
feat: add cognitive enhancement agents based on research
...
Based on Anthropic 'Building Effective Agents' and Lilian Weng's research:
New Agents:
- @planner: Task decomposition using CoT, ToT, Plan-Execute-Reflect
- @reflector: Self-reflection using Reflexion pattern
- @memory-manager: Memory systems (short/long/episodic)
New Skills:
- memory-systems: Memory architecture for autonomous agents
- planning-patterns: CoT, ToT, ReAct, Reflexion patterns
- tool-use: ACI design principles from Anthropic
New Rules:
- agent-patterns: Core patterns from research
Updated AGENTS.md with new agent categories:
- Cognitive Enhancement: planner, reflector, memory-manager
- Improved workflow state machine with reflection loop
Related: Issue #25 (Research Milestone)
2026-04-05 02:01:05 +01:00
