UniqueSoft/APAW
2
0
Fork 0
Code Issues 15 Pull Requests Actions Packages Projects Releases Wiki Activity
155 Commits 2 Branches 1 Tag
36455ccf24bebec7c19002e570378f95ecea059c
Commit Graph

19 Commits

Author SHA1 Message Date
Deploy Bot
36455ccf24 feat:apply model recommendations - 18 agents migrated to kimi-k2.6\n\nSources from agent-evolution/data/evolution.json\nAgents: architect-indexer, backend-developer, browser-automation,\n code-skeptic, evaluator, flutter-developer, frontend-developer,\n history-miner, lead-developer, markdown-validator, php-developer,\n product-owner, prompt-optimizer, python-developer,\n requirement-refiner, sdet-engineer, visual-tester,\n workflow-architect\nAlso synced 4 agents via sync-agents.cjs 2026-05-27 13:38:49 +01:00
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
2287122f91 fix(agents): add Tool-First Enforcement to agent definitions and global rules 2026-05-13 09:37:40 +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¨
9e48a4960e fix: restore optimal v3 models + add fitness gate protection 
- 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.
 2026-04-29 23:19:16 +01:00
¨NW¨
3badb259cc feat: bidirectional research dashboard + agent config fixes 
- Integrate apaw_agent_model_research_v3.html as standalone dashboard
- Add model-benchmarks.json with 32 agents, 11 scored models, 11 recommendations
- Add build-research-dashboard.ts: inject live data into template → standalone HTML
- Add rebuild-template.cjs: regenerate template from v3.html source
- Add sync-benchmarks-from-yaml.cjs: sync YAML → JSON round-trip
- Add sync-model-research.ts: apply recommendation matrix to config files
- Add model-benchmarks.schema.json and model-research.schema.json for validation
- Add bidirectional-data-flow.md architecture documentation
- Add log-execution.cjs pipeline hook
- Update capability-index.yaml: add fallback_models, failover_strategy
- Update kilo-meta.json, kilo.jsonc, KILO_SPEC.md with synced models
- Update evolution.md / research.md / self-evolution.md / evolutionary-sync.md docs
- Fix security-auditor.md: quote YAML color (#DC2626)
- Fix orchestrator.md: remove duplicate devops-engineer key
- Build research-dashboard.html (106KB standalone) + dated archive
 2026-04-29 21:04:22 +01:00
¨NW¨
dbea8c90db feat: evolutionary agent model upgrades based on recommendation matrix 
- devops-engineer: deepseek-v3.2 → kimi-k2.6:cloud (★88)
- browser-automation: glm-5 → kimi-k2.6:cloud (★86)
- visual-tester: glm-5 → qwen3-coder:480b (★82)
- agent-architect: nemotron-3-super → kimi-k2.6:cloud (★86)
- orchestrator: glm-5 → kimi-k2.6:cloud (dispatch critical)
- product-owner: glm-5 → glm-5.1 (★84)
- prompt-optimizer: qwen3.6-plus:free → glm-5.1 (stable fallback)
- system-analyst: qwen3.6-plus:free → glm-5.1 (★90)
- Add autonomous-mode.md rule for zero-confirmation workflow
 2026-04-27 12:09:36 +01:00
¨NW¨
af43eaef80 Merge remote-tracking branch 'origin/agent-sync-features' 2026-04-24 07:21:39 +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¨
4af7355429 feat: update agent models based on research recommendations 
- requirement-refiner: kimi-k2-thinking -> nemotron-3-super (1M context for specs)
- history-miner: glm-5 -> nemotron-3-super (better git search, 1M context)
- capability-analyst: gpt-oss:120b -> nemotron-3-super (gap analysis improvement)
- agent-architect: gpt-oss:120b -> nemotron-3-super (agent design, 1M context)
- prompt-optimizer: gpt-oss:120b -> qwen3.6-plus:free (FREE on OpenRouter)
- product-owner: glm-5 -> qwen3.6-plus:free (FREE on OpenRouter, 1M context)
- evaluator: gpt-oss:120b -> nemotron-3-super (quality scoring)
- markdown-validator: nemotron-3-nano:30b -> gemma4:26b (better validation)
- debug (kilo.jsonc): gpt-oss:20b -> gemma4:31b (Intelligence Index 39)
- devops-engineer: NEW -> nemotron-3-super (Docker, K8s, CI/CD)
- flutter-developer: NEW -> qwen3-coder:480b (Dart/Flutter support)

Synced all agent models between capability-index.yaml and agent/*.md files.
Validated YAML and JSON5 configs.
 2026-04-05 20:28:47 +01:00
¨NW¨
6c4756f8b4 fix: correct agent modes from 'all' to 'subagent' 
These agents are invoked by other agents (orchestrator/evaluator), not directly by user:
- agent-architect: invoked by capability-analyst
- browser-automation: invoked by orchestrator for E2E testing
- history-miner: invoked by orchestrator during [planned] phase
- product-owner: invoked by evaluator for process improvements
- prompt-optimizer: invoked by evaluator when score < 7
- system-analyst: invoked by orchestrator during [researching] phase
- visual-tester: invoked by orchestrator for visual regression

Mode 'all' should be used only for agents that can be both
primary (user-facing) and subagent (invoked by other agents).
 2026-04-05 16:19:18 +01:00
¨NW¨
b517ad5dad feat: add synchronization system for agent definitions 
- Add kilo.jsonc (official Kilo Code config)
- Add kilo-meta.json (source of truth for sync)
- Add evolutionary-sync.md rule for documentation
- Add scripts/sync-agents.cjs for validation
- Fix agent mode mismatches (8 agents had wrong mode)
- Update KILO_SPEC.md and AGENTS.md

The sync system ensures:
- kilo-meta.json is the single source of truth
- Agent .md files frontmatter matches meta
- KILO_SPEC.md tables stay synchronized
- AGENTS.md category tables stay synchronized

Run: node scripts/sync-agents.cjs --check
Fix: node scripts/sync-agents.cjs --fix
 2026-04-05 13:19:54 +01:00
¨NW¨
ebbb4d01b2 feat: optimize agent models for better performance 
- Update agent-architect to nemotron-3-super for detailed specs
- Update capability-analyst to nemotron-3-super for deeper analysis
- Update history-miner to nemotron-3-super for better relevance
- Update prompt-optimizer to qwen3.6-plus via OpenRouter
- Fix system-analyst model path (remove openrouter prefix)

Testing showed ~28% quality improvement across cognitive agents
 2026-04-05 12:15:30 +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
swp
4a69c5323b feat: update agent models to current configuration 
- Update README.md with correct model assignments for all agents
- Sync AGENTS.md and .kilo/ files with new model IDs
- Change History Miner: Gemini-3-Flash → GPT-OSS 20B
- Change System Analyst: GPT-OSS 120B → Qwen3.6-Plus (Free)
- Change Product Owner: Qwen3.5 122B → Qwen3.6-Plus (Free)
- Change Lead Developer: DeepSeek-v3.2 → Qwen3-Coder 480B
- Change The Fixer: MiniMax-m2.7 → MiniMax-m2.5
- Change SDET Engineer: Qwen3-Coder-Next → Qwen3-Coder 480B
- Change Code Skeptic: GPT-OSS 120B → MiniMax-m2.5
- Change Security Auditor: GLM-4.7 → Kimi-k2.5
- Change Release Manager: Devstral-2 123B → Qwen3-Coder 480B
- Change Evaluator: GPT-o3 → GPT-OSS 120B
- Change Prompt Optimizer: Claude 4.5 → Qwen3.6-Plus (Free)
- Add AgentArchitect agent configuration
- Update commands: plan, ask, debug, code models
- Add permissions configuration to commands
 2026-04-04 00:50:22 +01:00
swp
be295039eb fix: configure full permissions for autonomous agent operation 2026-04-03 22:57:55 +01:00
swp
72d6f52844 fix: correct agent mode configuration and add Task tool invocation sections 2026-04-03 20:50:40 +01:00
swp
47219c4204 feat: реорганизация структуры агентов и добавление skills согласно документации Kilo Code 
- 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)
 2026-04-03 20:14:22 +01:00