@stephen-lord/docs 1.0.0 → 1.0.1

package/dist-docs/Agent-Skills-for-Context-Engineering/skills/memory-systems/scripts/memory_store.py

@@ -0,0 +1,396 @@
+"""
+Memory System Implementation
+
+This module provides utilities for implementing memory systems.
+"""
+
+import numpy as np
+from typing import List, Dict, Any, Optional
+import json
+import hashlib
+from datetime import datetime
+
+
+class VectorStore:
+    """Simple vector store with metadata indexing."""
+    
+    def __init__(self, dimension: int = 768):
+        self.dimension = dimension
+        self.vectors: List[np.ndarray] = []
+        self.metadata: List[Dict] = []
+        self.entity_index: Dict[str, List[int]] = {}
+        self.time_index: Dict[str, List[int]] = {}
+    
+    def add(self, text: str, metadata: Dict[str, Any] = None) -> int:
+        """Add document to store."""
+        embedding = self._embed(text)
+        index = len(self.vectors)
+        
+        self.vectors.append(embedding)
+        self.metadata.append(metadata or {})
+        
+        # Index by entity
+        if "entity" in metadata:
+            entity = metadata["entity"]
+            if entity not in self.entity_index:
+                self.entity_index[entity] = []
+            self.entity_index[entity].append(index)
+        
+        # Index by time
+        if "valid_from" in metadata:
+            time_key = self._time_key(metadata["valid_from"])
+            if time_key not in self.time_index:
+                self.time_index[time_key] = []
+            self.time_index[time_key].append(index)
+        
+        return index
+    
+    def search(self, query: str, limit: int = 5, 
+               filters: Dict[str, Any] = None) -> List[Dict]:
+        """Search for similar documents."""
+        query_embedding = self._embed(query)
+        
+        scores = []
+        for i, vec in enumerate(self.vectors):
+            score = np.dot(query_embedding, vec) / (
+                np.linalg.norm(query_embedding) * np.linalg.norm(vec) + 1e-8
+            )
+            
+            # Apply filters
+            if filters and not self._matches_filters(self.metadata[i], filters):
+                score = -1
+            
+            scores.append((i, score))
+        
+        scores.sort(key=lambda x: x[1], reverse=True)
+        
+        results = []
+        for idx, score in scores[:limit]:
+            if score > 0:
+                results.append({
+                    "index": idx,
+                    "score": score,
+                    "text": self.metadata[idx].get("text", ""),
+                    "metadata": self.metadata[idx]
+                })
+        
+        return results
+    
+    def search_by_entity(self, entity: str, query: str = "", 
+                         limit: int = 5) -> List[Dict]:
+        """Search within specific entity."""
+        indices = self.entity_index.get(entity, [])
+        
+        if not indices:
+            return []
+        
+        if query:
+            query_embedding = self._embed(query)
+            scored = []
+            for i in indices:
+                vec = self.vectors[i]
+                score = np.dot(query_embedding, vec) / (
+                    np.linalg.norm(query_embedding) * np.linalg.norm(vec) + 1e-8
+                )
+                scored.append((i, score, self.metadata[i]))
+            
+            scored.sort(key=lambda x: x[1], reverse=True)
+            return [{"index": i, "score": s, "metadata": m} 
+                    for i, s, m in scored[:limit]]
+        else:
+            return [{"index": i, "score": 1.0, "metadata": self.metadata[i]} 
+                    for i in indices[:limit]]
+    
+    def _embed(self, text: str) -> np.ndarray:
+        """Generate embedding for text."""
+        # In production, use actual embedding model
+        np.random.seed(hash(text) % (2**32))
+        return np.random.randn(self.dimension)
+    
+    def _time_key(self, timestamp: Any) -> str:
+        """Create time key for indexing."""
+        if isinstance(timestamp, datetime):
+            return timestamp.strftime("%Y-%m")
+        return str(timestamp)
+    
+    def _matches_filters(self, metadata: Dict, filters: Dict) -> bool:
+        """Check if metadata matches filters."""
+        for key, value in filters.items():
+            if key not in metadata:
+                return False
+            if isinstance(value, list):
+                if metadata[key] not in value:
+                    return False
+            elif metadata[key] != value:
+                return False
+        return True
+
+
+class PropertyGraph:
+    """Simple property graph storage."""
+    
+    def __init__(self):
+        self.nodes: Dict[str, Dict] = {}
+        self.edges: Dict[str, Dict] = {}
+        self.node_index: Dict[str, List[str]] = {}  # label -> node_ids
+        self.edge_index: Dict[str, List[str]] = {}  # type -> edge_ids
+    
+    def create_node(self, label: str, properties: Dict = None) -> str:
+        """Create node with label and properties."""
+        import time
+        node_id = hashlib.md5(f"{label}{time.time()}".encode()).hexdigest()[:16]
+        
+        self.nodes[node_id] = {
+            "id": node_id,
+            "label": label,
+            "properties": properties or {},
+            "created_at": time.time()
+        }
+        
+        if label not in self.node_index:
+            self.node_index[label] = []
+        self.node_index[label].append(node_id)
+        
+        return node_id
+    
+    def create_relationship(self, source_id: str, rel_type: str, 
+                           target_id: str, properties: Dict = None) -> str:
+        """Create directed relationship between nodes."""
+        import time
+        if source_id not in self.nodes:
+            raise ValueError(f"Unknown source node: {source_id}")
+        if target_id not in self.nodes:
+            raise ValueError(f"Unknown target node: {target_id}")
+        
+        edge_id = hashlib.md5(f"{source_id}{rel_type}{target_id}{time.time()}".encode()).hexdigest()[:16]
+        
+        self.edges[edge_id] = {
+            "id": edge_id,
+            "source": source_id,
+            "target": target_id,
+            "type": rel_type,
+            "properties": properties or {},
+            "created_at": time.time()
+        }
+        
+        if rel_type not in self.edge_index:
+            self.edge_index[rel_type] = []
+        self.edge_index[rel_type].append(edge_id)
+        
+        return edge_id
+    
+    def query(self, pattern: Dict) -> List[Dict]:
+        """Query graph with simple pattern matching."""
+        results = []
+        
+        # Match by edge type
+        if "type" in pattern:
+            edge_ids = self.edge_index.get(pattern["type"], [])
+            for eid in edge_ids:
+                edge = self.edges[eid]
+                source = self.nodes.get(edge["source"], {})
+                target = self.nodes.get(edge["target"], {})
+                
+                # Match source label
+                if "source_label" in pattern:
+                    if source.get("label") != pattern["source_label"]:
+                        continue
+                
+                # Match target label
+                if "target_label" in pattern:
+                    if target.get("label") != pattern["target_label"]:
+                        continue
+                
+                results.append({
+                    "source": source,
+                    "edge": edge,
+                    "target": target
+                })
+        
+        return results
+    
+    def get_node(self, node_id: str) -> Optional[Dict]:
+        """Get node by ID."""
+        return self.nodes.get(node_id)
+    
+    def get_relationships(self, node_id: str, 
+                          direction: str = "both") -> List[Dict]:
+        """Get relationships for a node."""
+        relationships = []
+        
+        for edge in self.edges.values():
+            if direction in ["outgoing", "both"] and edge["source"] == node_id:
+                relationships.append({
+                    "edge": edge,
+                    "target": self.nodes.get(edge["target"]),
+                    "direction": "outgoing"
+                })
+            if direction in ["incoming", "both"] and edge["target"] == node_id:
+                relationships.append({
+                    "edge": edge,
+                    "source": self.nodes.get(edge["source"]),
+                    "direction": "incoming"
+                })
+        
+        return relationships
+
+
+class TemporalKnowledgeGraph(PropertyGraph):
+    """Property graph with temporal validity for facts."""
+    
+    def create_temporal_relationship(
+        self, 
+        source_id: str, 
+        rel_type: str, 
+        target_id: str,
+        valid_from: datetime,
+        valid_until: Optional[datetime] = None,
+        properties: Dict = None
+    ) -> str:
+        """Create relationship with temporal validity."""
+        edge_id = super().create_relationship(
+            source_id, rel_type, target_id, properties
+        )
+        
+        # Add temporal properties
+        self.edges[edge_id]["valid_from"] = valid_from.isoformat()
+        self.edges[edge_id]["valid_until"] = (
+            valid_until.isoformat() if valid_until else None
+        )
+        
+        return edge_id
+    
+    def query_at_time(self, query: Dict, query_time: datetime) -> List[Dict]:
+        """Query graph state at specific time."""
+        results = []
+        
+        # Get base query results
+        base_results = self.query(query)
+        
+        for result in base_results:
+            edge = result["edge"]
+            valid_from = datetime.fromisoformat(edge.get("valid_from", "1970-01-01"))
+            valid_until = edge.get("valid_until")
+            
+            # Check temporal validity
+            if valid_from <= query_time:
+                if valid_until is None or datetime.fromisoformat(valid_until) > query_time:
+                    results.append({
+                        **result,
+                        "valid_from": valid_from,
+                        "valid_until": valid_until
+                    })
+        
+        return results
+    
+    def query_time_range(self, query: Dict, 
+                         start_time: datetime, 
+                         end_time: datetime) -> List[Dict]:
+        """Query facts valid during time range."""
+        results = []
+        
+        base_results = self.query(query)
+        
+        for result in base_results:
+            edge = result["edge"]
+            valid_from = datetime.fromisoformat(edge.get("valid_from", "1970-01-01"))
+            valid_until = edge.get("valid_until")
+            
+            # Check if overlaps with query range
+            until_dt = datetime.fromisoformat(valid_until) if valid_until else datetime.max
+            
+            if until_dt >= start_time and valid_from <= end_time:
+                results.append({
+                    **result,
+                    "valid_from": valid_from,
+                    "valid_until": valid_until
+                })
+        
+        return results
+
+
+# Memory System Integration
+
+class IntegratedMemorySystem:
+    """Integrated memory system combining vector store and graph."""
+    
+    def __init__(self):
+        self.vector_store = VectorStore()
+        self.graph = TemporalKnowledgeGraph()
+        self.session_id: str = ""
+    
+    def start_session(self, session_id: str):
+        """Start a new memory session."""
+        self.session_id = session_id
+    
+    def store_fact(self, fact: str, entity: str, 
+                   timestamp: datetime = None, 
+                   relationships: List[Dict] = None):
+        """Store a fact with entity and relationships."""
+        # Store in vector store
+        self.vector_store.add(fact, {
+            "text": fact,
+            "entity": entity,
+            "valid_from": (timestamp or datetime.now()).isoformat(),
+            "session_id": self.session_id
+        })
+        
+        # Create entity node if not exists
+        entity_node = self.graph.get_node(entity)
+        if not entity_node:
+            self.graph.create_node("Entity", {"id": entity, "name": entity})
+        
+        # Create relationships
+        if relationships:
+            for rel in relationships:
+                self.graph.create_relationship(
+                    entity,
+                    rel["type"],
+                    rel["target"],
+                    properties=rel.get("properties", {})
+                )
+    
+    def retrieve_memories(self, query: str, 
+                          entity_filter: str = None,
+                          time_filter: Dict = None,
+                          limit: int = 5) -> List[Dict]:
+        """Retrieve memories matching query."""
+        # Vector search
+        filters = {"session_id": self.session_id}
+        if entity_filter:
+            filters["entity"] = entity_filter
+        
+        results = self.vector_store.search(query, limit=limit, filters=filters)
+        
+        # Enrich with graph relationships
+        for result in results:
+            entity = result["metadata"].get("entity")
+            if entity:
+                result["relationships"] = self.graph.get_relationships(entity)
+        
+        return results
+    
+    def retrieve_entity_context(self, entity: str) -> Dict:
+        """Retrieve complete context for an entity."""
+        # Get entity node
+        entity_node = self.graph.get_node(entity)
+        
+        # Get relationships
+        relationships = self.graph.get_relationships(entity)
+        
+        # Get vector memories
+        memories = self.vector_store.search_by_entity(entity, limit=10)
+        
+        return {
+            "entity": entity_node,
+            "relationships": relationships,
+            "memories": memories
+        }
+    
+    def consolidate(self):
+        """Consolidate memories and remove outdated information."""
+        # In production, implement actual consolidation logic
+        # - Merge related facts
+        # - Update validity periods
+        # - Archive obsolete facts
+        pass

package/dist-docs/Agent-Skills-for-Context-Engineering/skills/multi-agent-patterns/SKILL.md

@@ -0,0 +1,255 @@
+---
+name: multi-agent-patterns
+description: This skill should be used when the user asks to "design multi-agent system", "implement supervisor pattern", "create swarm architecture", "coordinate multiple agents", or mentions multi-agent patterns, context isolation, agent handoffs, sub-agents, or parallel agent execution.
+---
+
+# Multi-Agent Architecture Patterns
+
+Multi-agent architectures distribute work across multiple language model instances, each with its own context window. When designed well, this distribution enables capabilities beyond single-agent limits. When designed poorly, it introduces coordination overhead that negates benefits. The critical insight is that sub-agents exist primarily to isolate context, not to anthropomorphize role division.
+
+## When to Activate
+
+Activate this skill when:
+- Single-agent context limits constrain task complexity
+- Tasks decompose naturally into parallel subtasks
+- Different subtasks require different tool sets or system prompts
+- Building systems that must handle multiple domains simultaneously
+- Scaling agent capabilities beyond single-context limits
+- Designing production agent systems with multiple specialized components
+
+## Core Concepts
+
+Multi-agent systems address single-agent context limitations through distribution. Three dominant patterns exist: supervisor/orchestrator for centralized control, peer-to-peer/swarm for flexible handoffs, and hierarchical for layered abstraction. The critical design principle is context isolation—sub-agents exist primarily to partition context rather than to simulate organizational roles.
+
+Effective multi-agent systems require explicit coordination protocols, consensus mechanisms that avoid sycophancy, and careful attention to failure modes including bottlenecks, divergence, and error propagation.
+
+## Detailed Topics
+
+### Why Multi-Agent Architectures
+
+**The Context Bottleneck**
+Single agents face inherent ceilings in reasoning capability, context management, and tool coordination. As tasks grow more complex, context windows fill with accumulated history, retrieved documents, and tool outputs. Performance degrades according to predictable patterns: the lost-in-middle effect, attention scarcity, and context poisoning.
+
+Multi-agent architectures address these limitations by partitioning work across multiple context windows. Each agent operates in a clean context focused on its subtask. Results aggregate at a coordination layer without any single context bearing the full burden.
+
+**The Token Economics Reality**
+Multi-agent systems consume significantly more tokens than single-agent approaches. Production data shows:
+
+| Architecture | Token Multiplier | Use Case |
+|--------------|------------------|----------|
+| Single agent chat | 1× baseline | Simple queries |
+| Single agent with tools | ~4× baseline | Tool-using tasks |
+| Multi-agent system | ~15× baseline | Complex research/coordination |
+
+Research on the BrowseComp evaluation found that three factors explain 95% of performance variance: token usage (80% of variance), number of tool calls, and model choice. This validates the multi-agent approach of distributing work across agents with separate context windows to add capacity for parallel reasoning.
+
+Critically, upgrading to better models often provides larger performance gains than doubling token budgets. Claude Sonnet 4.5 showed larger gains than doubling tokens on earlier Sonnet versions. GPT-5.2's thinking mode similarly outperforms raw token increases. This suggests model selection and multi-agent architecture are complementary strategies.
+
+**The Parallelization Argument**
+Many tasks contain parallelizable subtasks that a single agent must execute sequentially. A research task might require searching multiple independent sources, analyzing different documents, or comparing competing approaches. A single agent processes these sequentially, accumulating context with each step.
+
+Multi-agent architectures assign each subtask to a dedicated agent with a fresh context. All agents work simultaneously, then return results to a coordinator. The total real-world time approaches the duration of the longest subtask rather than the sum of all subtasks.
+
+**The Specialization Argument**
+Different tasks benefit from different agent configurations: different system prompts, different tool sets, different context structures. A general-purpose agent must carry all possible configurations in context. Specialized agents carry only what they need.
+
+Multi-agent architectures enable specialization without combinatorial explosion. The coordinator routes to specialized agents; each agent operates with lean context optimized for its domain.
+
+### Architectural Patterns
+
+**Pattern 1: Supervisor/Orchestrator**
+The supervisor pattern places a central agent in control, delegating to specialists and synthesizing results. The supervisor maintains global state and trajectory, decomposes user objectives into subtasks, and routes to appropriate workers.
+
+```
+User Query -> Supervisor -> [Specialist, Specialist, Specialist] -> Aggregation -> Final Output
+```
+
+When to use: Complex tasks with clear decomposition, tasks requiring coordination across domains, tasks where human oversight is important.
+
+Advantages: Strict control over workflow, easier to implement human-in-the-loop interventions, ensures adherence to predefined plans.
+
+Disadvantages: Supervisor context becomes bottleneck, supervisor failures cascade to all workers, "telephone game" problem where supervisors paraphrase sub-agent responses incorrectly.
+
+**The Telephone Game Problem and Solution**
+LangGraph benchmarks found supervisor architectures initially performed 50% worse than optimized versions due to the "telephone game" problem where supervisors paraphrase sub-agent responses incorrectly, losing fidelity.
+
+The fix: implement a `forward_message` tool allowing sub-agents to pass responses directly to users:
+
+```python
+def forward_message(message: str, to_user: bool = True):
+    """
+    Forward sub-agent response directly to user without supervisor synthesis.
+    
+    Use when:
+    - Sub-agent response is final and complete
+    - Supervisor synthesis would lose important details
+    - Response format must be preserved exactly
+    """
+    if to_user:
+        return {"type": "direct_response", "content": message}
+    return {"type": "supervisor_input", "content": message}
+```
+
+With this pattern, swarm architectures slightly outperform supervisors because sub-agents respond directly to users, eliminating translation errors.
+
+Implementation note: Implement direct pass-through mechanisms allowing sub-agents to pass responses directly to users rather than through supervisor synthesis when appropriate.
+
+**Pattern 2: Peer-to-Peer/Swarm**
+The peer-to-peer pattern removes central control, allowing agents to communicate directly based on predefined protocols. Any agent can transfer control to any other through explicit handoff mechanisms.
+
+```python
+def transfer_to_agent_b():
+    return agent_b  # Handoff via function return
+
+agent_a = Agent(
+    name="Agent A",
+    functions=[transfer_to_agent_b]
+)
+```
+
+When to use: Tasks requiring flexible exploration, tasks where rigid planning is counterproductive, tasks with emergent requirements that defy upfront decomposition.
+
+Advantages: No single point of failure, scales effectively for breadth-first exploration, enables emergent problem-solving behaviors.
+
+Disadvantages: Coordination complexity increases with agent count, risk of divergence without central state keeper, requires robust convergence constraints.
+
+Implementation note: Define explicit handoff protocols with state passing. Ensure agents can communicate their context needs to receiving agents.
+
+**Pattern 3: Hierarchical**
+Hierarchical structures organize agents into layers of abstraction: strategic, planning, and execution layers. Strategy layer agents define goals and constraints; planning layer agents break goals into actionable plans; execution layer agents perform atomic tasks.
+
+```
+Strategy Layer (Goal Definition) -> Planning Layer (Task Decomposition) -> Execution Layer (Atomic Tasks)
+```
+
+When to use: Large-scale projects with clear hierarchical structure, enterprise workflows with management layers, tasks requiring both high-level planning and detailed execution.
+
+Advantages: Mirrors organizational structures, clear separation of concerns, enables different context structures at different levels.
+
+Disadvantages: Coordination overhead between layers, potential for misalignment between strategy and execution, complex error propagation.
+
+### Context Isolation as Design Principle
+
+The primary purpose of multi-agent architectures is context isolation. Each sub-agent operates in a clean context window focused on its subtask without carrying accumulated context from other subtasks.
+
+**Isolation Mechanisms**
+Full context delegation: For complex tasks where the sub-agent needs complete understanding, the planner shares its entire context. The sub-agent has its own tools and instructions but receives full context for its decisions.
+
+Instruction passing: For simple, well-defined subtasks, the planner creates instructions via function call. The sub-agent receives only the instructions needed for its specific task.
+
+File system memory: For complex tasks requiring shared state, agents read and write to persistent storage. The file system serves as the coordination mechanism, avoiding context bloat from shared state passing.
+
+**Isolation Trade-offs**
+Full context delegation provides maximum capability but defeats the purpose of sub-agents. Instruction passing maintains isolation but limits sub-agent flexibility. File system memory enables shared state without context passing but introduces latency and consistency challenges.
+
+The right choice depends on task complexity, coordination needs, and acceptable latency.
+
+### Consensus and Coordination
+
+**The Voting Problem**
+Simple majority voting treats hallucinations from weak models as equal to reasoning from strong models. Without intervention, multi-agent discussions devolve into consensus on false premises due to inherent bias toward agreement.
+
+**Weighted Voting**
+Weight agent votes by confidence or expertise. Agents with higher confidence or domain expertise carry more weight in final decisions.
+
+**Debate Protocols**
+Debate protocols require agents to critique each other's outputs over multiple rounds. Adversarial critique often yields higher accuracy on complex reasoning than collaborative consensus.
+
+**Trigger-Based Intervention**
+Monitor multi-agent interactions for specific behavioral markers. Stall triggers activate when discussions make no progress. Sycophancy triggers detect when agents mimic each other's answers without unique reasoning.
+
+### Framework Considerations
+
+Different frameworks implement these patterns with different philosophies. LangGraph uses graph-based state machines with explicit nodes and edges. AutoGen uses conversational/event-driven patterns with GroupChat. CrewAI uses role-based process flows with hierarchical crew structures.
+
+## Practical Guidance
+
+### Failure Modes and Mitigations
+
+**Failure: Supervisor Bottleneck**
+The supervisor accumulates context from all workers, becoming susceptible to saturation and degradation.
+
+Mitigation: Implement output schema constraints so workers return only distilled summaries. Use checkpointing to persist supervisor state without carrying full history.
+
+**Failure: Coordination Overhead**
+Agent communication consumes tokens and introduces latency. Complex coordination can negate parallelization benefits.
+
+Mitigation: Minimize communication through clear handoff protocols. Batch results where possible. Use asynchronous communication patterns.
+
+**Failure: Divergence**
+Agents pursuing different goals without central coordination can drift from intended objectives.
+
+Mitigation: Define clear objective boundaries for each agent. Implement convergence checks that verify progress toward shared goals. Use time-to-live limits on agent execution.
+
+**Failure: Error Propagation**
+Errors in one agent's output propagate to downstream agents that consume that output.
+
+Mitigation: Validate agent outputs before passing to consumers. Implement retry logic with circuit breakers. Use idempotent operations where possible.
+
+## Examples
+
+**Example 1: Research Team Architecture**
+```text
+Supervisor
+├── Researcher (web search, document retrieval)
+├── Analyzer (data analysis, statistics)
+├── Fact-checker (verification, validation)
+└── Writer (report generation, formatting)
+```
+
+**Example 2: Handoff Protocol**
+```python
+def handle_customer_request(request):
+    if request.type == "billing":
+        return transfer_to(billing_agent)
+    elif request.type == "technical":
+        return transfer_to(technical_agent)
+    elif request.type == "sales":
+        return transfer_to(sales_agent)
+    else:
+        return handle_general(request)
+```
+
+## Guidelines
+
+1. Design for context isolation as the primary benefit of multi-agent systems
+2. Choose architecture pattern based on coordination needs, not organizational metaphor
+3. Implement explicit handoff protocols with state passing
+4. Use weighted voting or debate protocols for consensus
+5. Monitor for supervisor bottlenecks and implement checkpointing
+6. Validate outputs before passing between agents
+7. Set time-to-live limits to prevent infinite loops
+8. Test failure scenarios explicitly
+
+## Integration
+
+This skill builds on context-fundamentals and context-degradation. It connects to:
+
+- memory-systems - Shared state management across agents
+- tool-design - Tool specialization per agent
+- context-optimization - Context partitioning strategies
+
+## References
+
+Internal reference:
+- [Frameworks Reference](./references/frameworks.md) - Detailed framework implementation patterns
+
+Related skills in this collection:
+- context-fundamentals - Context basics
+- memory-systems - Cross-agent memory
+- context-optimization - Partitioning strategies
+
+External resources:
+- [LangGraph Documentation](https://langchain-ai.github.io/langgraph/) - Multi-agent patterns and state management
+- [AutoGen Framework](https://microsoft.github.io/autogen/) - GroupChat and conversational patterns
+- [CrewAI Documentation](https://docs.crewai.com/) - Hierarchical agent processes
+- [Research on Multi-Agent Coordination](https://arxiv.org/abs/2308.00352) - Survey of multi-agent systems
+
+---
+
+## Skill Metadata
+
+**Created**: 2025-12-20
+**Last Updated**: 2025-12-20
+**Author**: Agent Skills for Context Engineering Contributors
+**Version**: 1.0.0