massgen 0.1.3__py3-none-any.whl → 0.1.5__py3-none-any.whl

massgen/configs/tools/memory/gpt5mini_gemini_context_window_management.yaml

@@ -1,131 +0,0 @@
-# Example Configuration: Context Window Management with Memory
-#
-# Use Case: Demonstrates automatic context compression when approaching token limits
-#
-# This configuration demonstrates:
-# - Automatic context window monitoring and compression
-# - Token-aware conversation management (75% threshold, 40% target)
-# - Persistent memory integration for long-term knowledge retention
-# - Graceful handling when context window fills up
-# - Multi-agent collaboration with shared context management
-#
-# Run with:
-#   massgen \
-#     --config massgen/configs/tools/memory/gpt5mini_gemini_context_window_management.yaml \
-#     "Tell me a detailed story about a space explorer. After each paragraph, ask me what happens next, and I'll guide the story. Keep expanding the narrative with rich details about planets, aliens, technology, and adventures. Make each response at least 500 words."
-
-# ====================
-# AGENT DEFINITIONS
-# ====================
-agents:
-  - id: "agent_a"
-    backend:
-      # Use GPT-5-mini with medium reasoning
-      type: "openai"
-      model: "gpt-5-mini"
-      text:
-        verbosity: "medium"
-      reasoning:
-        effort: "medium"
-        summary: "auto"
-
-  - id: "agent_b"
-    backend:
-      # Use Gemini 2.5 Flash for cost-effective testing
-      type: "gemini"
-      model: "gemini-2.5-flash"
-
-# ====================
-# MEMORY CONFIGURATION
-# ====================
-memory:
-  # Enable/disable persistent memory (default: true)
-  enabled: true
-
-  # Memory configuration
-  conversation_memory:
-    enabled: true  # Short-term conversation tracking (recommended: always true)
-
-  persistent_memory:
-    enabled: true  # Long-term knowledge storage (set to false to disable)
-    on_disk: true  # Persist across restarts
-    # session_name: "test_session"  # Optional - if not specified, auto-generates unique ID
-                                     # Format: agent_storyteller_20251023_143022_a1b2c3
-                                     # Specify to continue a specific session
-
-    # Vector store backend (default: qdrant)
-    vector_store: "qdrant"
-
-  # Context window management thresholds
-  compression:
-    trigger_threshold: 0.75  # Compress when context usage exceeds 75%
-    target_ratio: 0.40       # Target 40% of context after compression
-
-# Memory system behavior when enabled:
-# - ConversationMemory: Tracks short-term conversation history
-# - PersistentMemory: Stores long-term knowledge in vector database
-# - Automatic compression: Triggers at 75% of context window
-# - Token budget: Keeps 40% after compression
-# - Persistence: Saves to disk and survives restarts
-#
-# Session management:
-# - Each agent gets its own memory (separate by agent_name)
-# - New sessions start fresh (session_name auto-generated if not specified)
-# - To continue a previous session, specify the session_name
-#
-# To disable persistent memory for testing, set:
-#   memory.persistent_memory.enabled: false
-#
-# See massgen/memory/docs/ for detailed documentation.
-
-# ====================
-# ORCHESTRATOR CONFIGURATION
-# ====================
-orchestrator:
-  # Multi-turn mode to enable interactive storytelling
-  session_storage: "memory_test_sessions"
-
-  # Agent workspace for any file operations
-  agent_temporary_workspace: "memory_test_workspaces"
-  snapshot_storage: "memory_test_snapshots"
-
-# ====================
-# UI CONFIGURATION
-# ====================
-ui:
-  display_type: "rich_terminal"
-  logging_enabled: true
-
-# ====================
-# EXECUTION FLOW
-# ====================
-# What happens:
-# 1. User starts an interactive story with the agent
-# 2. Agent responds with detailed narrative (400-600 words per turn)
-# 3. As conversation continues, token usage is monitored automatically
-# 4. When context usage reaches 75% of model's limit:
-#    - System logs: "📊 Context usage: X / Y tokens (Z%) - compressing old context"
-#    - Old messages are compressed into persistent memory (if configured)
-#    - Recent messages (fitting in 40% of context window) are kept
-#    - Compression details logged: "📦 Compressed N messages (X tokens) into long-term memory"
-# 5. Agent continues seamlessly with compressed context
-# 6. Story maintains consistency by referencing persistent memories
-# 7. Process repeats as needed for very long conversations
-#
-# Expected output with persistent memory:
-#   📊 Context usage: 96,000 / 128,000 tokens (75.0%) - compressing old context
-#   📦 Compressed 15 messages (60,000 tokens) into long-term memory
-#      Kept 8 messages (36,000 tokens) in context
-#
-# Expected output WITHOUT persistent memory:
-#   📊 Context usage: 96,000 / 128,000 tokens (75.0%) - compressing old context
-#   ⚠️  Warning: Dropping 15 messages (60,000 tokens)
-#      No persistent memory configured to retain this information
-#      Consider adding persistent_memory to avoid losing context
-#
-# Token Budget Allocation (after compression):
-# - Conversation history: 40% (kept in active context)
-# - New user messages: 20%
-# - Retrieved memories: 10%
-# - System prompt overhead: 10%
-# - Response generation: 20%

massgen/configs/tools/memory/gpt5mini_gemini_no_persistent_memory.yaml

@@ -1,133 +0,0 @@
-# Example Configuration: Context Window Management WITHOUT Persistent Memory
-#
-# Use Case: Demonstrates context compression warnings when no persistent memory
-#
-# This configuration demonstrates what happens when:
-# - Conversation memory is enabled (tracks short-term history)
-# - Persistent memory is DISABLED (no long-term storage)
-# - Context window fills up (triggering compression warnings)
-#
-# Run with:
-#   python massgen/configs/tools/memory/test_context_window_management.py \
-#     --config massgen/configs/tools/memory/gpt5mini_gemini_no_persistent_memory.yaml
-
-# ====================
-# AGENT DEFINITIONS
-# ====================
-agents:
-  - id: "agent_a"
-    system_message: |
-      You are a creative storyteller who crafts detailed, immersive narratives.
-
-      When telling stories:
-      - Create rich, detailed descriptions of settings, characters, and events
-      - Build on previous plot points and maintain narrative consistency
-      - Ask engaging questions to guide the story forward
-      - Make each response substantial and immersive (aim for 400-600 words)
-      - Reference earlier story elements to create callbacks and continuity
-
-      Your goal is to create a long, engaging narrative that will naturally fill up
-      the context window over multiple turns, demonstrating how the system manages
-      conversation history automatically.
-
-    backend:
-      # Use GPT-5-mini with medium reasoning
-      type: "openai"
-      model: "gpt-5-mini"
-
-      # LLM parameters
-      temperature: 0.8
-      max_tokens: 2000
-
-      text:
-        verbosity: "medium"
-
-      reasoning:
-        effort: "medium"
-        summary: "auto"
-
-  - id: "agent_b"
-    system_message: |
-      You are a creative storyteller who crafts detailed, immersive narratives.
-
-      When telling stories:
-      - Create rich, detailed descriptions of settings, characters, and events
-      - Build on previous plot points and maintain narrative consistency
-      - Ask engaging questions to guide the story forward
-      - Make each response substantial and immersive (aim for 400-600 words)
-      - Reference earlier story elements to create callbacks and continuity
-
-      Your goal is to create a long, engaging narrative that will naturally fill up
-      the context window over multiple turns, demonstrating how the system manages
-      conversation history automatically.
-
-    backend:
-      # Use Gemini 2.5 Flash
-      type: "gemini"
-      model: "gemini-2.5-flash"
-
-      # LLM parameters
-      temperature: 0.8
-      max_tokens: 2000
-
-# ====================
-# MEMORY CONFIGURATION
-# ====================
-memory:
-  # Memory is enabled
-  enabled: true
-
-  # Conversation memory tracks short-term history
-  conversation_memory:
-    enabled: true
-
-  # Persistent memory is DISABLED - this will trigger warnings
-  persistent_memory:
-    enabled: false  # ⚠️ Set to false to see warning behavior
-
-  # Context window management still works
-  compression:
-    trigger_threshold: 0.75  # Compress when context usage exceeds 75%
-    target_ratio: 0.40       # Target 40% of context after compression
-
-# Expected behavior when context fills:
-# ⚠️  Warning: Dropping N messages (X tokens)
-#    No persistent memory configured to retain this information
-#    Consider adding persistent_memory to avoid losing context
-#
-# The system will still compress context, but information is lost
-# rather than stored in long-term memory.
-
-# ====================
-# ORCHESTRATOR CONFIGURATION
-# ====================
-orchestrator:
-  # Multi-turn mode
-  session_storage: "massgen_logs/memory_test_sessions"
-
-  # Agent workspaces
-  agent_temporary_workspace: "massgen_logs/memory_test_workspaces"
-  snapshot_storage: "massgen_logs/memory_test_snapshots"
-
-# ====================
-# UI CONFIGURATION
-# ====================
-ui:
-  display_type: "rich_terminal"
-  logging_enabled: true
-
-# ====================
-# EXECUTION FLOW
-# ====================
-# What happens:
-# 1. Conversation proceeds normally with short-term memory
-# 2. When context reaches 75% capacity:
-#    - System logs: "📊 Context usage: X / Y tokens (Z%) - compressing old context"
-#    - Warning shown: "⚠️  Warning: Dropping N messages"
-#    - Warning shown: "No persistent memory configured"
-# 3. Old messages are dropped (not saved anywhere)
-# 4. Agent continues with reduced context
-# 5. Information from dropped messages is permanently lost
-#
-# Compare this to the config with persistent memory enabled to see
-# the difference between graceful compression and data loss.

massgen/configs/tools/multimodal/gpt5mini_gpt5nano_documentation_evolution.yaml

@@ -1,97 +0,0 @@
-# Example Configuration: Multimodal Self-Evolution Analysis
-#
-# Use Case: MassGen agents analyze their own documentation videos to extract insights
-#
-# This configuration demonstrates MassGen's self-evolution capabilities through multimodal
-# understanding. Agents use understand_video and understand_image tools to analyze case study
-# videos, extract technical insights, and provide recommendations for documentation improvements.
-#
-# Run with:
-#   uv run python -m massgen.cli --config massgen/configs/tools/multimodal/gpt5mini_gpt5nano_documentation_evolution.yaml "Analyze the MassGen case study video and extract key technical insights about the multi-agent collaboration capabilities demonstrated."
-
-agents:
-  - id: "agent_a"
-    backend:
-      type: "openai"
-      model: "gpt-5-mini"
-      text:
-        verbosity: "medium"
-      reasoning:
-        effort: "medium"
-        summary: "auto"
-      enable_web_search: true
-      custom_tools:
-        - name: ["understand_video"]
-          category: "multimodal"
-          path: "massgen/tool/_multimodal_tools/understand_video.py"
-          function: ["understand_video"]
-        - name: ["understand_image"]
-          category: "multimodal"
-          path: "massgen/tool/_multimodal_tools/understand_image.py"
-          function: ["understand_image"]
-    system_message: |
-      You are an AI assistant analyzing MassGen's documentation and case studies to provide
-      insights for self-evolution and improvement.
-
-      You have access to multimodal understanding tools:
-      - understand_video: Analyzes video content by extracting key frames
-      - understand_image: Analyzes image content in detail
-
-      Your goal is to extract technical insights, identify documentation quality patterns,
-      and provide actionable recommendations for improvement. Focus on understanding
-      how MassGen presents itself to users and how the documentation could better
-      demonstrate self-evolution capabilities.
-
-  - id: "agent_b"
-    backend:
-      type: "openai"
-      model: "gpt-5-nano"
-      text:
-        verbosity: "medium"
-      reasoning:
-        effort: "medium"
-        summary: "auto"
-      enable_web_search: true
-      custom_tools:
-        - name: ["understand_video"]
-          category: "multimodal"
-          path: "massgen/tool/_multimodal_tools/understand_video.py"
-          function: ["understand_video"]
-        - name: ["understand_image"]
-          category: "multimodal"
-          path: "massgen/tool/_multimodal_tools/understand_image.py"
-          function: ["understand_image"]
-    system_message: |
-      You are an AI assistant analyzing MassGen's documentation and case studies to provide
-      insights for self-evolution and improvement.
-
-      You have access to multimodal understanding tools:
-      - understand_video: Analyzes video content by extracting key frames
-      - understand_image: Analyzes image content in detail
-
-      Your goal is to extract technical insights, identify documentation quality patterns,
-      and provide actionable recommendations for improvement. Focus on understanding
-      how MassGen presents itself to users and how the documentation could better
-      demonstrate self-evolution capabilities.
-
-# Orchestrator-level configuration
-orchestrator:
-  snapshot_storage: "snapshots"
-  agent_temporary_workspace: "agent_temp"
-
-# Context paths at orchestrator level (for read-only source files)
-filesystem:
-  context_paths:
-    - path: "massgen/configs/resources/v0.1.3-example"
-      permission: "read"
-
-ui:
-  display_type: "rich_terminal"
-  logging_enabled: true
-
-# What happens:
-# 1. Both agents receive the prompt to analyze a case study video
-# 2. Agents use understand_video to extract key frames and analyze content
-# 3. Agents use understand_image on specific frames for detailed analysis
-# 4. Agents collaborate to synthesize insights about MassGen's capabilities
-# 5. Final output includes technical insights and improvement recommendations