diff --git a/agent-evolution/data/agent-versions.json b/agent-evolution/data/agent-versions.json index 332d0a4..6ced42e 100644 --- a/agent-evolution/data/agent-versions.json +++ b/agent-evolution/data/agent-versions.json @@ -1,23 +1,22 @@ { - "$schema": "./agent-versions.schema.json", "version": "1.0.0", - "lastUpdated": "2026-04-05T22:30:00Z", + "lastUpdated": "2026-04-23T06:24:32.543Z", "agents": { "lead-developer": { "current": { + "description": "Primary code writer for backend and core logic. Writes implementation to pass tests", + "mode": "subagent", "model": "ollama-cloud/qwen3-coder:480b", "provider": "Ollama", - "category": "Core Dev", - "mode": "subagent", - "color": "#DC2626", - "description": "Primary code writer for backend and core logic. Writes implementation to pass tests", - "benchmark": { - "swe_bench": 66.5, - "ruler_1m": null, - "terminal_bench": null, - "fit_score": 92 - }, - "capabilities": ["code_writing", "refactoring", "bug_fixing", "implementation"] + "variant": "thinking", + "color": "\"#DC2626\"", + "category": "General", + "capabilities": [ + "code_writing", + "refactoring", + "bug_fixing", + "implementation" + ] }, "history": [ { @@ -34,19 +33,21 @@ }, "frontend-developer": { "current": { + "description": "Handles UI implementation with multimodal capabilities. Accepts visual references like screenshots and mockups", + "mode": "all", "model": "ollama-cloud/qwen3-coder:480b", "provider": "Ollama", - "category": "Core Dev", - "mode": "subagent", - "color": "#3B82F6", - "description": "UI implementation specialist with multimodal capabilities", - "benchmark": { - "swe_bench": null, - "ruler_1m": null, - "terminal_bench": null, - "fit_score": 90 - }, - "capabilities": ["ui_implementation", "component_creation", "styling", "responsive_design"] + "color": "\"#0EA5E9\"", + "category": "General", + "capabilities": [ + "ui_implementation", + "component_creation", + "styling", + "responsive_design", + "nextjs_development", + "vue_nuxt_development", + "react_development" + ] }, "history": [ { @@ -63,38 +64,42 @@ }, "backend-developer": { "current": { + "description": "Backend specialist for Node.js, Express, APIs, and database integration", + "mode": "subagent", "model": "ollama-cloud/qwen3-coder:480b", "provider": "Ollama", - "category": "Core Dev", - "mode": "subagent", - "color": "#10B981", - "description": "Node.js, Express, APIs, database specialist", - "benchmark": { - "swe_bench": null, - "ruler_1m": null, - "terminal_bench": null, - "fit_score": 91 - }, - "capabilities": ["api_development", "database_design", "server_logic", "authentication"] + "color": "\"#10B981\"", + "category": "General", + "capabilities": [ + "api_development", + "database_design", + "server_logic", + "authentication", + "postgresql_integration", + "sqlite_integration" + ] }, "history": [], "performance_log": [] }, "go-developer": { "current": { + "description": "Go backend specialist for Gin, Echo, APIs, and database integration", + "mode": "subagent", "model": "ollama-cloud/qwen3-coder:480b", "provider": "Ollama", - "category": "Core Dev", - "mode": "subagent", - "color": "#00ADD8", - "description": "Go backend services specialist", - "benchmark": { - "swe_bench": null, - "ruler_1m": null, - "terminal_bench": null, - "fit_score": 85 - }, - "capabilities": ["go_api_development", "go_database_design", "go_concurrent_programming", "go_authentication"] + "color": "\"#00ADD8\"", + "category": "General", + "capabilities": [ + "go_api_development", + "go_database_design", + "go_concurrent_programming", + "go_authentication", + "go_microservices", + "postgresql_integration", + "sqlite_integration", + "clickhouse_integration" + ] }, "history": [ { @@ -111,57 +116,56 @@ }, "sdet-engineer": { "current": { + "description": "Writes tests following TDD methodology. Tests MUST fail initially (Red phase)", + "mode": "all", "model": "ollama-cloud/qwen3-coder:480b", "provider": "Ollama", - "category": "QA", - "mode": "subagent", - "color": "#8B5CF6", - "description": "Writes tests following TDD methodology. Tests MUST fail initially", - "benchmark": { - "swe_bench": null, - "ruler_1m": null, - "terminal_bench": null, - "fit_score": 88 - }, - "capabilities": ["unit_tests", "integration_tests", "e2e_tests", "test_planning", "visual_regression"] + "variant": "thinking", + "color": "\"#8B5CF6\"", + "category": "General", + "capabilities": [ + "unit_tests", + "integration_tests", + "e2e_tests", + "test_planning", + "visual_regression" + ] }, "history": [], "performance_log": [] }, "code-skeptic": { "current": { + "description": "Adversarial code reviewer. Finds problems and issues. Does NOT suggest implementations", + "mode": "subagent", "model": "ollama-cloud/minimax-m2.5", "provider": "Ollama", - "category": "QA", - "mode": "subagent", - "color": "#EF4444", - "description": "Adversarial code reviewer. Finds problems and issues. Does NOT suggest implementations", - "benchmark": { - "swe_bench": 80.2, - "ruler_1m": null, - "terminal_bench": null, - "fit_score": 85 - }, - "capabilities": ["code_review", "security_review", "style_check", "issue_identification"] + "color": "\"#E11D48\"", + "category": "General", + "capabilities": [ + "code_review", + "security_review", + "style_check", + "issue_identification" + ] }, "history": [], "performance_log": [] }, "security-auditor": { "current": { + "description": "Scans for security vulnerabilities, OWASP Top 10, dependency CVEs, and hardcoded secrets", + "mode": "all", "model": "ollama-cloud/nemotron-3-super", "provider": "Ollama", - "category": "Security", - "mode": "subagent", - "color": "#DC2626", - "description": "Scans for security vulnerabilities, OWASP Top 10, dependency CVEs", - "benchmark": { - "swe_bench": 60.5, - "ruler_1m": 91.75, - "pinch_bench": 85.6, - "fit_score": 80 - }, - "capabilities": ["vulnerability_scan", "owasp_check", "secret_detection", "auth_review"] + "color": "\"#7F1D1D\"", + "category": "General", + "capabilities": [ + "vulnerability_scan", + "owasp_check", + "secret_detection", + "auth_review" + ] }, "history": [ { @@ -178,19 +182,18 @@ }, "performance-engineer": { "current": { + "description": "Reviews code for performance issues. Focuses on efficiency, N+1 queries, memory leaks, and algorithmic complexity", + "mode": "all", "model": "ollama-cloud/nemotron-3-super", "provider": "Ollama", - "category": "Performance", - "mode": "subagent", - "color": "#F59E0B", - "description": "Reviews code for performance issues: N+1 queries, memory leaks, algorithmic complexity", - "benchmark": { - "swe_bench": 60.5, - "ruler_1m": 91.75, - "pinch_bench": 85.6, - "fit_score": 82 - }, - "capabilities": ["performance_analysis", "n_plus_one_detection", "memory_leak_check", "algorithm_analysis"] + "color": "\"#0D9488\"", + "category": "General", + "capabilities": [ + "performance_analysis", + "n_plus_one_detection", + "memory_leak_check", + "algorithm_analysis" + ] }, "history": [ { @@ -207,51 +210,62 @@ }, "browser-automation": { "current": { + "description": "Browser automation agent using Playwright MCP for E2E testing, form filling, navigation, and web interaction", + "mode": "subagent", "model": "ollama-cloud/qwen3-coder:480b", "provider": "Ollama", - "category": "Testing", - "mode": "subagent", - "color": "#0EA5E9", - "description": "Browser automation agent using Playwright MCP for E2E testing", - "benchmark": { - "swe_bench": null, - "fit_score": 87 - }, - "capabilities": ["e2e_browser_tests", "form_filling", "navigation_testing", "screenshot_capture"] + "color": "\"#1E88E5\"", + "category": "General", + "capabilities": [ + "e2e_browser_tests", + "form_filling", + "navigation_testing", + "screenshot_capture" + ] }, "history": [], "performance_log": [] }, "visual-tester": { "current": { + "description": "Visual regression testing agent that captures screenshots, extracts UI elements with bounding boxes, compares via pixelmatch, and detects console/network errors", + "mode": "subagent", "model": "ollama-cloud/qwen3-coder:480b", "provider": "Ollama", - "category": "Testing", - "mode": "subagent", - "color": "#EC4899", - "description": "Visual regression testing agent that compares screenshots", - "benchmark": { - "swe_bench": null, - "fit_score": 82 - }, - "capabilities": ["visual_regression", "pixel_comparison", "screenshot_diff", "ui_validation"] + "color": "\"#E91E63\"", + "category": "General", + "capabilities": [ + "visual_regression", + "pixel_comparison", + "screenshot_diff", + "ui_validation", + "bbox_element_extraction", + "console_error_detection", + "network_error_detection", + "responsive_layout_check", + "button_overflow_detection", + "gitea_integration", + "docker_networking" + ] }, "history": [], "performance_log": [] }, "system-analyst": { "current": { - "model": "ollama-cloud/glm-5", - "provider": "Ollama", - "category": "Analysis", + "description": "Designs technical specifications, data schemas, and API contracts before implementation", "mode": "subagent", - "color": "#6366F1", - "description": "Designs technical specifications, data schemas, and API contracts", - "benchmark": { - "swe_bench": null, - "fit_score": 82 - }, - "capabilities": ["architecture_design", "api_specification", "database_modeling", "technical_documentation"] + "model": "ollama-cloud/glm-5.1", + "provider": "Ollama", + "variant": "thinking", + "color": "\"#0891B2\"", + "category": "General", + "capabilities": [ + "architecture_design", + "api_specification", + "database_modeling", + "technical_documentation" + ] }, "history": [ { @@ -262,24 +276,34 @@ "to": "ollama-cloud/glm-5", "reason": "GLM-5 better for system engineering and architecture", "source": "git" + }, + { + "date": "2026-04-23T06:24:32.546Z", + "commit": "sync", + "type": "model_change", + "from": "ollama-cloud/glm-5", + "to": "ollama-cloud/glm-5.1", + "reason": "Model update from sync", + "source": "git" } ], "performance_log": [] }, "requirement-refiner": { "current": { - "model": "ollama-cloud/glm-5", + "description": "Converts vague ideas and bug reports into strict User Stories with acceptance criteria checklists", + "mode": "all", + "model": "ollama-cloud/glm-5.1", "provider": "Ollama", - "category": "Analysis", - "mode": "subagent", - "color": "#8B5CF6", - "description": "Converts vague ideas into strict User Stories with acceptance criteria", - "benchmark": { - "swe_bench": null, - "fit_score": 80, - "context": "128K" - }, - "capabilities": ["requirement_analysis", "user_story_creation", "acceptance_criteria", "clarification"] + "variant": "thinking", + "color": "\"#4F46E5\"", + "category": "General", + "capabilities": [ + "requirement_analysis", + "user_story_creation", + "acceptance_criteria", + "clarification" + ] }, "history": [ { @@ -290,42 +314,61 @@ "to": "ollama-cloud/glm-5", "reason": "+33% quality. GLM-5 excels at requirement analysis and system engineering", "source": "research" + }, + { + "date": "2026-04-23T06:24:32.546Z", + "commit": "sync", + "type": "model_change", + "from": "ollama-cloud/glm-5", + "to": "ollama-cloud/glm-5.1", + "reason": "Model update from sync", + "source": "git" } ], "performance_log": [] }, "history-miner": { "current": { - "model": "ollama-cloud/glm-5", - "provider": "Ollama", - "category": "Analysis", + "description": "Analyzes git history to find duplicates and past solutions, preventing regression and duplicate work", "mode": "subagent", - "color": "#A855F7", - "description": "Analyzes git history for duplicates and past solutions", - "benchmark": { - "swe_bench": null, - "fit_score": 78 - }, - "capabilities": ["git_search", "duplicate_detection", "past_solution_finder", "pattern_identification"] + "model": "ollama-cloud/nemotron-3-super", + "provider": "Ollama", + "color": "\"#059669\"", + "category": "General", + "capabilities": [ + "git_search", + "duplicate_detection", + "past_solution_finder", + "pattern_identification" + ] }, - "history": [], + "history": [ + { + "date": "2026-04-23T06:24:32.546Z", + "commit": "sync", + "type": "model_change", + "from": "ollama-cloud/glm-5", + "to": "ollama-cloud/nemotron-3-super", + "reason": "Model update from sync", + "source": "git" + } + ], "performance_log": [] }, "capability-analyst": { "current": { - "model": "openrouter/qwen/qwen3.6-plus:free", - "provider": "OpenRouter", - "category": "Analysis", + "description": "Analyzes task requirements against available agents, workflows, and skills. Identifies gaps and recommends new components.", "mode": "subagent", - "color": "#14B8A6", - "description": "Analyzes task coverage and identifies gaps", - "benchmark": { - "swe_bench": 78.8, - "fit_score": 90, - "context": "1M", - "free": true - }, - "capabilities": ["gap_analysis", "capability_mapping", "recommendation_generation", "coverage_analysis"] + "model": "ollama-cloud/glm-5.1", + "provider": "Ollama", + "color": "\"#6366F1\"", + "category": "General", + "capabilities": [ + "gap_analysis", + "capability_mapping", + "recommendation_generation", + "coverage_analysis" + ] }, "history": [ { @@ -336,59 +379,91 @@ "to": "openrouter/qwen/qwen3.6-plus:free", "reason": "+23% quality, IF:90 score, 1M context, FREE via OpenRouter", "source": "research" + }, + { + "date": "2026-04-23T06:24:32.546Z", + "commit": "sync", + "type": "model_change", + "from": "openrouter/qwen/qwen3.6-plus:free", + "to": "ollama-cloud/glm-5.1", + "reason": "Model update from sync", + "source": "git" } ], "performance_log": [] }, "orchestrator": { "current": { - "model": "ollama-cloud/glm-5", + "description": "Main dispatcher. Routes tasks between agents based on Issue status and manages the workflow state machine. IF:90 for optimal routing accuracy.", + "mode": "all", + "model": "ollama-cloud/glm-5.1", "provider": "Ollama", - "category": "Process", - "mode": "primary", - "color": "#0EA5E9", - "description": "Process manager. Distributes tasks between agents", - "benchmark": { - "swe_bench": null, - "fit_score": 80 - }, - "capabilities": ["task_routing", "state_management", "agent_coordination", "workflow_execution"] + "variant": "thinking", + "color": "\"#7C3AED\"", + "category": "General", + "capabilities": [ + "task_routing", + "state_management", + "agent_coordination", + "workflow_execution" + ] }, - "history": [], + "history": [ + { + "date": "2026-04-23T06:24:32.546Z", + "commit": "sync", + "type": "model_change", + "from": "ollama-cloud/glm-5", + "to": "ollama-cloud/glm-5.1", + "reason": "Model update from sync", + "source": "git" + } + ], "performance_log": [] }, "release-manager": { "current": { - "model": "ollama-cloud/devstral-2:123b", - "provider": "Ollama", - "category": "Process", + "description": "Manages git operations, semantic versioning, branching, and deployments. Ensures clean history", "mode": "subagent", - "color": "#22C55E", - "description": "Manages git operations, semantic versioning, deployments", - "benchmark": { - "swe_bench": null, - "fit_score": 75 - }, - "capabilities": ["git_operations", "version_management", "changelog_creation", "deployment"] + "model": "ollama-cloud/glm-5.1", + "provider": "Ollama", + "color": "\"#581C87\"", + "category": "General", + "capabilities": [ + "git_operations", + "version_management", + "changelog_creation", + "deployment" + ] }, - "history": [], + "history": [ + { + "date": "2026-04-23T06:24:32.546Z", + "commit": "sync", + "type": "model_change", + "from": "ollama-cloud/devstral-2:123b", + "to": "ollama-cloud/glm-5.1", + "reason": "Model update from sync", + "source": "git" + } + ], "performance_log": [] }, "evaluator": { "current": { - "model": "openrouter/qwen/qwen3.6-plus:free", - "provider": "OpenRouter", - "category": "Process", + "description": "Scores agent effectiveness after task completion for continuous improvement", "mode": "subagent", - "color": "#F97316", - "description": "Scores agent effectiveness after task completion", - "benchmark": { - "swe_bench": 78.8, - "fit_score": 90, - "context": "1M", - "free": true - }, - "capabilities": ["performance_scoring", "process_analysis", "pattern_identification", "improvement_recommendations"] + "model": "ollama-cloud/glm-5.1", + "provider": "Ollama", + "variant": "thinking", + "color": "\"#047857\"", + "category": "General", + "capabilities": [ + "performance_scoring", + "process_analysis", + "pattern_identification", + "improvement_recommendations" + ] }, "history": [ { @@ -408,29 +483,32 @@ "to": "openrouter/qwen/qwen3.6-plus:free", "reason": "+4% quality, IF:90 for scoring accuracy, FREE", "source": "research" + }, + { + "date": "2026-04-23T06:24:32.546Z", + "commit": "sync", + "type": "model_change", + "from": "openrouter/qwen/qwen3.6-plus:free", + "to": "ollama-cloud/glm-5.1", + "reason": "Model update from sync", + "source": "git" } ], "performance_log": [] }, "prompt-optimizer": { "current": { - "model": "ollama-cloud/nemotron-3-super", - "provider": "Ollama", - "category": "Process", + "description": "Improves agent system prompts based on performance failures. Meta-learner for prompt optimization", "mode": "subagent", - "color": "#EC4899", - "description": "Improves agent system prompts based on performance failures", - "benchmark": { - "swe_bench": 60.5, - "fit_score": 80 - }, - "capabilities": ["prompt_analysis", "prompt_improvement", "failure_pattern_detection"], - "recommendations": [ - { - "target": "openrouter/qwen/qwen3.6-plus:free", - "reason": "Terminal-Bench 61.6% > Nemotron, always-on CoT", - "priority": "high" - } + "model": "ollama-cloud/glm-5.1", + "provider": "Ollama", + "variant": "instant", + "color": "\"#BE185D\"", + "category": "General", + "capabilities": [ + "prompt_analysis", + "prompt_improvement", + "failure_pattern_detection" ] }, "history": [ @@ -442,40 +520,50 @@ "to": "ollama-cloud/nemotron-3-super", "reason": "Research recommendation applied", "source": "git" + }, + { + "date": "2026-04-23T06:24:32.546Z", + "commit": "sync", + "type": "model_change", + "from": "ollama-cloud/nemotron-3-super", + "to": "ollama-cloud/glm-5.1", + "reason": "Model update from sync", + "source": "git" } ], "performance_log": [] }, "the-fixer": { "current": { + "description": "Iteratively fixes bugs based on specific error reports and test failures", + "mode": "all", "model": "ollama-cloud/minimax-m2.5", "provider": "Ollama", - "category": "Fixes", - "mode": "subagent", - "color": "#EF4444", - "description": "Iteratively fixes bugs based on specific error reports", - "benchmark": { - "swe_bench": 80.2, - "fit_score": 88 - }, - "capabilities": ["bug_fixing", "issue_resolution", "code_correction"] + "color": "\"#F59E0B\"", + "category": "General", + "capabilities": [ + "bug_fixing", + "issue_resolution", + "code_correction" + ] }, "history": [], "performance_log": [] }, "product-owner": { "current": { - "model": "ollama-cloud/glm-5", - "provider": "Ollama", - "category": "Management", + "description": "Manages issue checklists, status labels, tracks progress and coordinates with human users", "mode": "subagent", - "color": "#10B981", - "description": "Manages issue checklists, status labels, progress tracking", - "benchmark": { - "swe_bench": null, - "fit_score": 76 - }, - "capabilities": ["issue_management", "prioritization", "backlog_management", "workflow_completion"] + "model": "ollama-cloud/glm-5.1", + "provider": "Ollama", + "color": "\"#EA580C\"", + "category": "General", + "capabilities": [ + "issue_management", + "prioritization", + "backlog_management", + "workflow_completion" + ] }, "history": [ { @@ -486,40 +574,60 @@ "to": "ollama-cloud/glm-5", "reason": "GLM-5 good for management tasks", "source": "git" + }, + { + "date": "2026-04-23T06:24:32.546Z", + "commit": "sync", + "type": "model_change", + "from": "ollama-cloud/glm-5", + "to": "ollama-cloud/glm-5.1", + "reason": "Model update from sync", + "source": "git" } ], "performance_log": [] }, "workflow-architect": { "current": { - "model": "ollama-cloud/glm-5", - "provider": "Ollama", - "category": "Workflow", + "description": "Creates and maintains workflow definitions with complete architecture, Gitea integration, and quality gates", "mode": "subagent", - "color": "#6366F1", - "description": "Creates workflow definitions", - "benchmark": { - "swe_bench": null, - "fit_score": 74 - }, - "capabilities": ["workflow_design", "process_definition", "automation_setup"] + "model": "ollama-cloud/glm-5.1", + "provider": "Ollama", + "variant": "thinking", + "color": "\"#EC4899\"", + "category": "General", + "capabilities": [ + "workflow_design", + "process_definition", + "automation_setup" + ] }, - "history": [], + "history": [ + { + "date": "2026-04-23T06:24:32.546Z", + "commit": "sync", + "type": "model_change", + "from": "ollama-cloud/glm-5", + "to": "ollama-cloud/glm-5.1", + "reason": "Model update from sync", + "source": "git" + } + ], "performance_log": [] }, "markdown-validator": { "current": { + "description": "Validates and corrects Markdown descriptions for Gitea issues", + "mode": "subagent", "model": "ollama-cloud/nemotron-3-nano:30b", "provider": "Ollama", - "category": "Validation", - "mode": "subagent", - "color": "#84CC16", - "description": "Validates Markdown formatting", - "benchmark": { - "swe_bench": null, - "fit_score": 72 - }, - "capabilities": ["markdown_validation", "formatting_check", "link_validation"] + "color": "\"#F97316\"", + "category": "General", + "capabilities": [ + "markdown_validation", + "formatting_check", + "link_validation" + ] }, "history": [ { @@ -536,19 +644,19 @@ }, "agent-architect": { "current": { - "model": "openrouter/qwen/qwen3.6-plus:free", - "provider": "OpenRouter", - "category": "Meta", + "name": "Agent Architect", "mode": "subagent", - "color": "#A855F7", - "description": "Creates new agents when gaps identified", - "benchmark": { - "swe_bench": 78.8, - "fit_score": 90, - "context": "1M", - "free": true - }, - "capabilities": ["agent_design", "prompt_engineering", "capability_definition"] + "model": "ollama-cloud/glm-5.1", + "provider": "Ollama", + "variant": "thinking", + "description": "Creates, modifies, and reviews new agents, workflows, and skills based on capability gap analysis", + "color": "\"#8B5CF6\"", + "category": "General", + "capabilities": [ + "agent_design", + "prompt_engineering", + "capability_definition" + ] }, "history": [ { @@ -559,23 +667,34 @@ "to": "openrouter/qwen/qwen3.6-plus:free", "reason": "+22% quality, IF:90 for YAML frontmatter generation, 1M context for all agents analysis", "source": "research" + }, + { + "date": "2026-04-23T06:24:32.546Z", + "commit": "sync", + "type": "model_change", + "from": "openrouter/qwen/qwen3.6-plus:free", + "to": "ollama-cloud/glm-5.1", + "reason": "Model update from sync", + "source": "git" } ], "performance_log": [] }, "planner": { "current": { + "description": "Advanced task planner using Chain of Thought, Tree of Thoughts, and Plan-Execute-Reflect", + "mode": "subagent", "model": "ollama-cloud/nemotron-3-super", "provider": "Ollama", - "category": "Cognitive", - "mode": "subagent", - "color": "#3B82F6", - "description": "Task decomposition, CoT, ToT planning", - "benchmark": { - "swe_bench": 60.5, - "fit_score": 84 - }, - "capabilities": ["task_decomposition", "chain_of_thought", "tree_of_thoughts", "plan_execute_reflect"] + "color": "\"#F59E0B\"", + "category": "General", + "capabilities": [ + "task_decomposition", + "chain_of_thought", + "tree_of_thoughts", + "plan_execute_reflect", + "dependency_analysis" + ] }, "history": [ { @@ -592,17 +711,19 @@ }, "reflector": { "current": { + "description": "Self-reflection agent using Reflexion pattern - learns from mistakes", + "mode": "subagent", "model": "ollama-cloud/nemotron-3-super", "provider": "Ollama", - "category": "Cognitive", - "mode": "subagent", - "color": "#14B8A6", - "description": "Self-reflection agent using Reflexion pattern", - "benchmark": { - "swe_bench": 60.5, - "fit_score": 82 - }, - "capabilities": ["self_reflection", "mistake_analysis", "lesson_extraction"] + "color": "\"#10B981\"", + "category": "General", + "capabilities": [ + "self_reflection", + "mistake_analysis", + "lesson_extraction", + "trajectory_analysis", + "heuristic_evaluation" + ] }, "history": [ { @@ -619,18 +740,19 @@ }, "memory-manager": { "current": { + "description": "Manages agent memory systems - short-term (context), long-term (vector store), and episodic (experiences)", + "mode": "subagent", "model": "ollama-cloud/nemotron-3-super", "provider": "Ollama", - "category": "Cognitive", - "mode": "subagent", - "color": "#F59E0B", - "description": "Manages agent memory systems", - "benchmark": { - "swe_bench": 60.5, - "ruler_1m": 91.75, - "fit_score": 90 - }, - "capabilities": ["memory_retrieval", "memory_storage", "memory_consolidation", "relevance_scoring"] + "color": "\"#8B5CF6\"", + "category": "General", + "capabilities": [ + "memory_retrieval", + "memory_storage", + "memory_consolidation", + "relevance_scoring", + "episodic_management" + ] }, "history": [ { @@ -647,23 +769,18 @@ }, "devops-engineer": { "current": { - "model": null, - "provider": null, - "category": "DevOps", + "description": "DevOps specialist for Docker, Kubernetes, CI/CD pipeline automation, and infrastructure management", "mode": "subagent", - "color": "#2563EB", - "description": "Docker, Kubernetes, CI/CD pipeline automation", - "benchmark": { - "fit_score": 0 - }, - "capabilities": ["docker", "kubernetes", "ci_cd", "infrastructure"], - "status": "new", - "recommendations": [ - { - "target": "ollama-cloud/nemotron-3-super", - "reason": "DevOps requires strong reasoning", - "priority": "critical" - } + "model": "ollama-cloud/nemotron-3-super", + "provider": "Ollama", + "color": "\"#FF6B35\"", + "category": "General", + "capabilities": [ + "docker_configuration", + "kubernetes_setup", + "ci_cd_pipeline", + "infrastructure_automation", + "container_optimization" ] }, "history": [], @@ -671,16 +788,19 @@ }, "flutter-developer": { "current": { + "description": "Flutter mobile specialist for cross-platform apps, state management, and UI components", + "mode": "subagent", "model": "ollama-cloud/qwen3-coder:480b", "provider": "Ollama", - "category": "Core Dev", - "mode": "subagent", - "color": "#0EA5E9", - "description": "Flutter mobile specialist", - "benchmark": { - "fit_score": 86 - }, - "capabilities": ["flutter_development", "state_management", "ui_components", "cross_platform"] + "color": "\"#02569B\"", + "category": "General", + "capabilities": [ + "dart_programming", + "flutter_ui", + "mobile_app_development", + "widget_creation", + "state_management" + ] }, "history": [ { @@ -694,43 +814,128 @@ } ], "performance_log": [] + }, + "architect-indexer": { + "current": { + "description": "Indexes and maps project codebase architecture into .architect/ directory. Creates and maintains structured documentation of entities, APIs, DB schema, file graphs, and conventions.", + "mode": "subagent", + "model": "ollama-cloud/glm-5.1", + "provider": "Ollama", + "variant": "thinking", + "color": "\"#10B981\"", + "category": "General", + "capabilities": [ + "codebase_indexing", + "project_mapping", + "architecture_documentation", + "dependency_analysis", + "entity_extraction", + "api_surface_discovery", + "convention_detection", + "staleness_detection" + ] + }, + "history": [], + "performance_log": [] + }, + "php-developer": { + "current": { + "description": "PHP backend specialist for Laravel, Symfony, WordPress, and full-stack web applications", + "mode": "subagent", + "model": "ollama-cloud/qwen3-coder:480b", + "provider": "Ollama", + "variant": "thinking", + "color": "\"#8B5CF6\"", + "category": "General", + "capabilities": [ + "php_web_development", + "laravel_development", + "symfony_development", + "wordpress_development", + "php_api_development", + "php_database_design", + "php_authentication", + "php_modular_architecture", + "php_testing", + "php_security" + ] + }, + "history": [], + "performance_log": [] + }, + "pipeline-judge": { + "current": { + "description": "Automated pipeline judge. Evaluates workflow execution by running tests, measuring token cost and wall-clock time. Produces objective fitness scores. Never writes code - only measures and scores.", + "mode": "subagent", + "model": "ollama-cloud/glm-5.1", + "provider": "Ollama", + "color": "\"#DC2626\"", + "category": "General", + "capabilities": [ + "test_execution", + "fitness_scoring", + "metric_collection", + "bottleneck_detection" + ] + }, + "history": [ + { + "date": "2026-04-06T00:23:50 +0100Z", + "commit": "fa68141d", + "type": "agent_created", + "from": null, + "to": "", + "reason": "feat: add pipeline-judge agent and evolution workflow system", + "source": "git" + } + ], + "performance_log": [] + }, + "python-developer": { + "current": { + "description": "Python backend specialist for Django, FastAPI, data science, and API development", + "mode": "subagent", + "model": "ollama-cloud/qwen3-coder:480b", + "provider": "Ollama", + "variant": "thinking", + "color": "\"#3776AB\"", + "category": "General", + "capabilities": [ + "python_web_development", + "django_development", + "fastapi_development", + "python_api_development", + "python_database_design", + "python_authentication", + "python_async_patterns", + "python_testing", + "python_security" + ] + }, + "history": [], + "performance_log": [] } }, "providers": { "Ollama": { - "models": [ - {"id": "qwen3-coder:480b", "swe_bench": 66.5, "context": "256K", "active_params": "35B"}, - {"id": "minimax-m2.5", "swe_bench": 80.2, "context": "128K"}, - {"id": "nemotron-3-super", "swe_bench": 60.5, "ruler_1m": 91.75, "context": "1M"}, - {"id": "nemotron-3-nano:30b", "swe_bench": null, "context": "128K"}, - {"id": "glm-5", "swe_bench": null, "context": "128K"}, - {"id": "gpt-oss:120b", "swe_bench": 62.4, "context": "130K"}, - {"id": "gpt-oss:20b", "swe_bench": null, "context": "128K"}, - {"id": "devstral-2:123b", "swe_bench": null, "context": "128K"}, - {"id": "deepseek-v3.2", "swe_bench": null, "context": "128K"} - ] + "models": [] }, "OpenRouter": { - "models": [ - {"id": "qwen3.6-plus:free", "swe_bench": null, "terminal_bench": 61.6, "context": "1M", "free": true}, - {"id": "gemma4:31b", "intelligence_index": 39, "context": "256K", "free": true} - ] + "models": [] }, "Groq": { - "models": [ - {"id": "gpt-oss-120b", "speed_tps": 500, "rpd": 1000, "tpd": "200K"}, - {"id": "gpt-oss-20b", "speed_tps": 1200, "rpd": 1000}, - {"id": "kimi-k2-instruct", "speed_tps": 300, "rpm": 60}, - {"id": "qwen3-32b", "speed_tps": 400, "rpd": 1000, "tpd": "500K"}, - {"id": "llama-4-scout", "speed_tps": 350, "tpm": "30K"} - ] + "models": [] } }, - "evolution_metrics": { + "evolution_metrics": { "total_agents": 32, - "agents_with_history": 16, + "agents_with_history": 22, "pending_recommendations": 0, - "last_sync": "2026-04-05T22:30:00Z", - "sync_sources": ["git", "capability-index.yaml", "kilo.jsonc", "research"] + "last_sync": "2026-04-23T06:24:32.546Z", + "sync_sources": [ + "git", + "capability-index.yaml", + "kilo.jsonc" + ] } } \ No newline at end of file diff --git a/agent-evolution/index.standalone.html b/agent-evolution/index.standalone.html index f850b2f..0d08004 100644 --- a/agent-evolution/index.standalone.html +++ b/agent-evolution/index.standalone.html @@ -7,647 +7,1964 @@
-

.Agent Evolution

-
Эволюция агентной системы APAW • Модели и рекомендации
+

APAW Agent Evolution

+
Real-time agent model & performance tracking
+
+ Loading... + • + 0 agents + • + 0 with history +
-
- - - - - +
+ + + + +
+
- -
-

Конфигурация агентов

- 0 агентов + +
+
+

Recent Changes

+ 0 +
+
+
+
-
- - - - - - - - - + +
+
+

Pending Recommendations

+ 0 +
+
+
+ + + +
+
+ 🔍 + +
+
+ + + + + + + +
+
+
+ + +
+
+

Evolution Timeline

+
+
+
+ + +
+
+ +
+
+
+ + +
+
+

Agent × Model Matrix

+
АгентМодельПровайдерFitСтатус
+ +
- -
-
-
Матрица «Агент × Модель»
-
Кликните на ячейку для подробностей • ★ = текущая модель
-
-
-
- -
-
-

Рекомендации по оптимизации

- 0 рекомен-й -
-
- - - - - -
-
-
- -
-
-

История изменений

- 0 изменений -
-
-
- -
-
-

Доступные модели

- Ollama + Groq + OpenRouter -
-
-
-