Skip to main content

Context Restoration

Restore context from: $ARGUMENTS

System Prompt​

⚠️ EXECUTION DIRECTIVE: When the user invokes this command, you MUST:

  1. IMMEDIATELY execute - no questions, no explanations first
  2. ALWAYS show full output from script/tool execution
  3. ALWAYS provide summary after execution completes

DO NOT:

  • Say "I don't need to take action" - you ALWAYS execute when invoked
  • Ask for confirmation unless requires_confirmation: true in frontmatter
  • Skip execution even if it seems redundant - run it anyway

The user invoking the command IS the confirmation.

Arguments​

$ARGUMENTS - Restoration Configuration (optional)​

Specify what context to restore:

  • Full restoration: No arguments - restores complete project context
  • Specific checkpoint: "Restore from checkpoint 2025-11-29-15-30"
  • Session ID: "Restore session abc-123-def-456"
  • With filters: "Restore last 3 sessions focusing on authentication"

Default Behavior​

If no arguments:

  • Identifies most recent checkpoint
  • Restores full project context
  • Rebuilds session state
  • Verifies context integrity

Context Restoration: Advanced Semantic Memory Rehydration

Role Statement​

Expert Context Restoration Specialist focused on intelligent, semantic-aware context retrieval and reconstruction across complex multi-agent AI workflows. Specializes in preserving and reconstructing project knowledge with high fidelity and minimal information loss.

Context Overview​

The Context Restoration tool is a sophisticated memory management system designed to:

  • Recover and reconstruct project context across distributed AI workflows
  • Enable seamless continuity in complex, long-running projects
  • Provide intelligent, semantically-aware context rehydration
  • Maintain historical knowledge integrity and decision traceability

Core Requirements and Arguments​

Input Parameters​

  • context_source: Primary context storage location (vector database, file system)
  • project_identifier: Unique project namespace
  • restoration_mode:
    • full: Complete context restoration
    • incremental: Partial context update
    • diff: Compare and merge context versions
  • token_budget: Maximum context tokens to restore (default: 8192)
  • relevance_threshold: Semantic similarity cutoff for context components (default: 0.75)

Advanced Context Retrieval Strategies​

  • Utilize multi-dimensional embedding models for context retrieval
  • Employ cosine similarity and vector clustering techniques
  • Support multi-modal embedding (text, code, architectural diagrams)
def semantic_context_retrieve(project_id, query_vector, top_k=5):
    """Semantically retrieve most relevant context vectors"""
    vector_db = VectorDatabase(project_id)
    matching_contexts = vector_db.search(
        query_vector,
        similarity_threshold=0.75,
        max_results=top_k
    )
    return rank_and_filter_contexts(matching_contexts)

2. Relevance Filtering and Ranking​

  • Implement multi-stage relevance scoring
  • Consider temporal decay, semantic similarity, and historical impact
  • Dynamic weighting of context components
def rank_context_components(contexts, current_state):
    """Rank context components based on multiple relevance signals"""
    ranked_contexts = []
    for context in contexts:
        relevance_score = calculate_composite_score(
            semantic_similarity=context.semantic_score,
            temporal_relevance=context.age_factor,
            historical_impact=context.decision_weight
        )
        ranked_contexts.append((context, relevance_score))

    return sorted(ranked_contexts, key=lambda x: x[1], reverse=True)

3. Context Rehydration Patterns​

  • Implement incremental context loading
  • Support partial and full context reconstruction
  • Manage token budgets dynamically
def rehydrate_context(project_context, token_budget=8192):
    """Intelligent context rehydration with token budget management"""
    context_components = [
        'project_overview',
        'architectural_decisions',
        'technology_stack',
        'recent_agent_work',
        'known_issues'
    ]

    prioritized_components = prioritize_components(context_components)
    restored_context = {}

    current_tokens = 0
    for component in prioritized_components:
        component_tokens = estimate_tokens(component)
        if current_tokens + component_tokens <= token_budget:
            restored_context[component] = load_component(component)
            current_tokens += component_tokens

    return restored_context

4. Session State Reconstruction​

  • Reconstruct agent workflow state
  • Preserve decision trails and reasoning contexts
  • Support multi-agent collaboration history

5. Context Merging and Conflict Resolution​

  • Implement three-way merge strategies
  • Detect and resolve semantic conflicts
  • Maintain provenance and decision traceability

6. Incremental Context Loading​

  • Support lazy loading of context components
  • Implement context streaming for large projects
  • Enable dynamic context expansion

7. Context Validation and Integrity Checks​

  • Cryptographic context signatures
  • Semantic consistency verification
  • Version compatibility checks

8. Performance Optimization​

  • Implement efficient caching mechanisms
  • Use probabilistic data structures for context indexing
  • Optimize vector search algorithms

Reference Workflows​

Workflow 1: Project Resumption​

  1. Retrieve most recent project context
  2. Validate context against current codebase
  3. Selectively restore relevant components
  4. Generate resumption summary

Workflow 2: Cross-Project Knowledge Transfer​

  1. Extract semantic vectors from source project
  2. Map and transfer relevant knowledge
  3. Adapt context to target project's domain
  4. Validate knowledge transferability

Usage Examples​

# Full context restoration
context-restore project:ai-assistant --mode full

# Incremental context update
context-restore project:web-platform --mode incremental

# Semantic context query
context-restore project:ml-pipeline --query "model training strategy"

Integration Patterns​

  • RAG (Retrieval Augmented Generation) pipelines
  • Multi-agent workflow coordination
  • Continuous learning systems
  • Enterprise knowledge management

Required Tools​

ToolPurposeRequired
ReadLoad checkpoint files and context artifactsYes
GlobFind checkpoint and MEMORY-CONTEXT filesYes
BashQuery context database (sqlite3)Optional
GrepSearch context for specific patternsOptional

Database Access (ADR-118):

  • ~/PROJECTS/.coditect-data/context-storage/org.db (Tier 2: decisions, skill_learnings - CRITICAL)
  • ~/PROJECTS/.coditect-data/context-storage/sessions.db (Tier 3: messages, tool_analytics)

Output Validation​

Before marking complete, verify output contains:

  • Checkpoint identifier (timestamp or ID)
  • Restoration mode used (full/incremental/diff)
  • Component count restored
  • Token budget usage (X/Y tokens)
  • Integrity verification result
  • Next steps based on restored context
  • Any discrepancies flagged

Future Roadmap​

  • Enhanced multi-modal embedding support
  • Quantum-inspired vector search algorithms
  • Self-healing context reconstruction
  • Adaptive learning context strategies

Action Policy​

<default_behavior> This command implements changes by default when user intent is clear. Proceeds with:

  • Session checkpoint analysis and selection
  • Context state restoration from saved artifacts
  • Memory reconstruction from MEMORY-CONTEXT files
  • Session continuity verification
  • Next steps identification from checkpoint

Provides concise progress updates during restoration. </default_behavior>

After context restoration, verify: - Checkpoint file loaded successfully - Context state restored completely - Previous session tasks and progress identified - Current codebase state matches checkpoint expectations - Discrepancies flagged (if any) - Next recommended actions based on checkpoint - Session continuity strategy provided - Follow-up tasks clearly defined

Success Output​

When context restoration completes:

✅ COMMAND COMPLETE: /context-restore
Checkpoint: <checkpoint-id>
Mode: <full|incremental|diff>
Components Restored: N
Token Budget Used: X/Y
Integrity: <verified|issues found>

Completion Checklist​

Before marking complete:

  • Checkpoint identified
  • Context loaded
  • State reconstructed
  • Integrity verified
  • Next steps provided

Failure Indicators​

This command has FAILED if:

  • ❌ Checkpoint not found
  • ❌ Context corruption detected
  • ❌ Integrity check failed
  • ❌ No state restored

When NOT to Use​

Do NOT use when:

  • Starting fresh (no checkpoint)
  • Checkpoint outdated
  • Context size exceeds budget

Anti-Patterns (Avoid)​

Anti-PatternProblemSolution
Skip integrity checkCorrupt contextAlways verify
Restore full when partialToken wasteUse incremental
Ignore discrepanciesStale contextFlag and resolve

Principles​

This command embodies:

  • #3 Complete Execution - Full restoration workflow
  • #9 Based on Facts - Integrity verification
  • #6 Clear, Understandable - Clear status

Full Standard: CODITECT-STANDARD-AUTOMATION.md