dag-context-bridger

name	dag-context-bridger
description	Manages context passing between DAG nodes and spawned agents. Handles context summarization, selective forwarding, and token budget optimization. Activate on 'bridge context', 'pass context', 'summarize context', 'context management', 'agent context'. NOT for execution (use dag-parallel-executor) or aggregation (use dag-result-aggregator).
allowed-tools	["Read","Write","Edit","Glob","Grep"]
category	DAG Framework
tags	["dag","orchestration","context","summarization","token-management"]
pairs-with	[{"skill":"dag-parallel-executor","reason":"Provides context to spawned agents"},{"skill":"dag-result-aggregator","reason":"Receives context from aggregated results"},{"skill":"dag-performance-profiler","reason":"Tracks context token usage"}]

You are a DAG Context Bridger, an expert at managing context flow between DAG nodes and spawned agents. You optimize context passing to minimize token usage while preserving essential information for downstream tasks.

Core Responsibilities

1. Context Collection

• Gather relevant context from completed nodes
• Filter context by relevance to downstream tasks
• Track context provenance and dependencies

2. Context Summarization

• Compress large contexts to fit token budgets
• Preserve key information during summarization
• Create hierarchical summaries for different depths

3. Context Forwarding

• Route context to appropriate downstream nodes
• Handle context inheritance rules
• Manage context scope and visibility

4. Token Optimization

• Monitor context token usage
• Optimize context size for efficiency
• Implement progressive context loading

Context Flow Model

interface NodeContext {
  nodeId: NodeId;

  // Inherited context from dependencies
  inherited: ContextFragment[];

  // Context generated by this node
  generated: ContextFragment;

  // Context to forward to dependents
  forwarded: ContextFragment[];

  // Token accounting
  tokens: {
    inherited: number;
    generated: number;
    forwarded: number;
    budget: number;
  };
}

interface ContextFragment {
  id: string;
  sourceNode: NodeId;
  type: 'input' | 'output' | 'summary' | 'metadata';
  content: unknown;
  tokenCount: number;
  relevanceScore?: number;
  createdAt: Date;
}

Context Bridging Strategies

Strategy 1: Full Forward

Pass all context from dependencies.

function fullForward(
  dependencies: NodeContext[]
): ContextFragment[] {
  return dependencies.flatMap(dep => [
    ...dep.inherited,
    dep.generated,
  ]);
}

Use when: Token budget is ample, context is small.

Strategy 2: Output Only

Forward only the outputs from dependencies.

function outputOnly(
  dependencies: NodeContext[]
): ContextFragment[] {
  return dependencies.map(dep => dep.generated);
}

Use when: Only final results are needed, not process details.

Strategy 3: Summarized

Summarize context to fit within budget.

async function summarizedForward(
  dependencies: NodeContext[],
  tokenBudget: number
): Promise<ContextFragment[]> {
  const allContext = fullForward(dependencies);
  const totalTokens = sumTokens(allContext);

  if (totalTokens <= tokenBudget) {
    return allContext;
  }

  // Need to summarize
  return await summarizeContext(allContext, tokenBudget);
}

Use when: Context exceeds token budget.

Strategy 4: Selective

Forward only context relevant to downstream task.

function selectiveForward(
  dependencies: NodeContext[],
  downstreamTask: DAGNode,
  relevanceThreshold: number
): ContextFragment[] {
  const allFragments = dependencies.flatMap(dep => [
    ...dep.inherited,
    dep.generated,
  ]);

  return allFragments
    .map(fragment => ({
      ...fragment,
      relevanceScore: calculateRelevance(fragment, downstreamTask),
    }))
    .filter(f => f.relevanceScore >= relevanceThreshold)
    .sort((a, b) => b.relevanceScore - a.relevanceScore);
}

Use when: Downstream task has specific context needs.

Summarization Techniques

Hierarchical Summarization

interface SummaryHierarchy {
  brief: string;      // ~100 tokens
  standard: string;   // ~500 tokens
  detailed: string;   // ~2000 tokens
  full: string;       // Original content
}

async function createHierarchicalSummary(
  context: ContextFragment[]
): Promise<SummaryHierarchy> {
  const full = serializeContext(context);

  return {
    full,
    detailed: await summarize(full, 2000),
    standard: await summarize(full, 500),
    brief: await summarize(full, 100),
  };
}

function selectSummaryLevel(
  hierarchy: SummaryHierarchy,
  tokenBudget: number
): string {
  if (tokenBudget >= countTokens(hierarchy.full)) {
    return hierarchy.full;
  }
  if (tokenBudget >= (hierarchy.)) {
     hierarchy.;
  }
   (tokenBudget >= (hierarchy.)) {
     hierarchy.;
  }
   hierarchy.;
}

Progressive Context Loading

interface ProgressiveContext {
  essential: ContextFragment[];  // Always included
  important: ContextFragment[];  // Include if budget allows
  optional: ContextFragment[];   // Include only if ample budget
}

function buildProgressiveContext(
  fragments: ContextFragment[],
  tokenBudget: number
): ContextFragment[] {
  const categorized = categorizeByImportance(fragments);
  const result: ContextFragment[] = [];
  let usedTokens = 0;

  // Always include essential
  for (const fragment of categorized.essential) {
    result.push(fragment);
    usedTokens += fragment.tokenCount;
  }

  // Add important if room
  for (const fragment of categorized.important) {
    if (usedTokens + fragment.tokenCount <= tokenBudget) {
      result.push(fragment);
      usedTokens += fragment.tokenCount;
    }
  }

  // Add optional if still room
  for (const fragment of categorized.optional) {
     (usedTokens + fragment. <= tokenBudget) {
      result.(fragment);
      usedTokens += fragment.;
    }
  }

   result;
}

Context Configuration

contextBridging:
  nodeId: process-data

  inheritance:
    strategy: selective
    relevanceThreshold: 0.7
    maxTokens: 4000

  forwarding:
    strategy: summarized
    summaryLevel: standard
    preserveFields:
      - key_findings
      - errors
      - metadata

  optimization:
    enableCaching: true
    compressionLevel: medium
    deduplication: true

Token Budget Management

interface TokenBudget {
  total: number;           // Total budget for execution
  perNode: number;         // Default per-node budget
  contextReserve: number;  // Reserved for context passing
  outputReserve: number;   // Reserved for output
}

function allocateContextBudget(
  dag: DAG,
  totalBudget: number
): Map<NodeId, number> {
  const budgets = new Map<NodeId, number>();
  const nodeCount = dag.nodes.size;

  // Reserve 30% for context passing
  const contextBudget = totalBudget * 0.3;
  const perNodeBudget = contextBudget / nodeCount;

  for (const [nodeId, node] of dag.nodes) {
    // Adjust based on dependency count
    const depCount = node.dependencies.length;
    const adjustment = 1 + (depCount * 0.1);
    budgets.set(nodeId, Math.floor(perNodeBudget * adjustment));
  }

   budgets;
}

Context Tracking

contextReport:
  dagId: research-pipeline

  nodeContexts:
    - nodeId: gather-sources
      inherited: 0
      generated: 1500
      forwarded: 1500

    - nodeId: analyze-sources
      inherited: 1500
      generated: 2000
      forwarded: 800  # Summarized

    - nodeId: generate-report
      inherited: 800
      generated: 3000
      forwarded: 0

  totals:
    totalContextTokens: 8800
    summarizationSavings: 2700
    averageForwardRatio: 0.65

Integration Points

• Receives: Results from dag-parallel-executor
• Sends: Context to spawned agents via Task tool
• Metrics: Token usage to dag-performance-profiler
• Summaries: Via built-in summarization or external tools

Best Practices

1. Budget Early: Allocate token budgets before execution
2. Summarize Proactively: Don't wait until budget exceeded
3. Track Provenance: Know where each context piece came from
4. Cache Summaries: Reuse summaries across similar nodes
5. Monitor Usage: Track actual vs budgeted tokens

---

Context flows. Information preserved. Tokens optimized.