/memory:update-full

Orchestrates comprehensive CLAUDE.md updates for all project modules using batched agent execution with automatic tool fallback.

Overview

The /memory:update-full command updates CLAUDE.md documentation for all project modules with intelligent batching and automatic tool fallback (gemini→qwen→codex).

Parameters:

• --tool <gemini|qwen|codex>: Primary tool (default: gemini)
• --path <directory>: Target directory (default: project root)

Execution Flow:

1. Module Detection → 2. Plan Presentation → 3. Batched Execution → 4. Safety Verification

Features

• Full Project Coverage - Updates all modules in the project
• Intelligent Batching - Groups modules by depth (4 modules/batch)
• Automatic Fallback - gemini→qwen→codex on failure
• Depth Sequential - Process depths N→0, parallel batches within depth
• Smart Filtering - Auto-detects and skips tests/build/config/docs

Usage

# Full project update (auto-strategy selection)
/memory:update-full

# Target specific directory
/memory:update-full --path .claude
/memory:update-full --path src/features/auth

# Use specific tool
/memory:update-full --tool qwen
/memory:update-full --path .claude --tool qwen

Tool Fallback Hierarchy

--tool gemini  →  [gemini, qwen, codex]  // default
--tool qwen    →  [qwen, gemini, codex]
--tool codex   →  [codex, gemini, qwen]

Trigger: Non-zero exit code from update script

Execution Modes

Small Projects (<15 modules)

• Direct parallel execution
• Max 4 concurrent per depth
• No agent overhead
• Faster execution

Large Projects (>=15 modules)

• Agent batch processing
• 4 modules/agent
• 73% overhead reduction
• Better resource utilization

Execution Flow

Phase 1: Module Detection & Analysis

// Get module structure
Bash({command: "ccw tool exec get_modules_by_depth '{\"format\":\"list\"}'", run_in_background: false});

// OR with --path
Bash({command: "cd <target-path> && ccw tool exec get_modules_by_depth '{\"format\":\"list\"}'", run_in_background: false});

Parse output depth:N|path:<PATH>|... to extract module paths and count.

Smart filter: Auto-detect and skip tests/build/config/docs based on project tech stack.

Phase 2: Plan Presentation

• Parse --tool (default: gemini)
• Get module structure from workspace
• Smart filter modules (auto-detect tech stack, skip tests/build/config/docs)
• Construct tool fallback order
• Present filtered plan with skip reasons
• Wait for y/n confirmation

Phase 3A: Direct Execution (<15 modules)

for (let depth of sorted_depths.reverse()) {  // N → 0
  let modules = modules_by_depth[depth];
  let batches = batch_modules(modules, 4);

  for (let batch of batches) {
    let parallel_tasks = batch.map(module => {
      return async () => {
        let strategy = module.depth >= 3 ? "multi-layer" : "single-layer";
        for (let tool of tool_order) {
          Bash({
            command: `cd ${module.path} && ccw tool exec update_module_claude '{"strategy":"${strategy}","path":".","tool":"${tool}"}'`,
            run_in_background: false
          });
          if (bash_result.exit_code === 0) {
            report(`✅ ${module.path} updated with ${tool}`);
            return true;
          }
        }
        report(`❌ FAILED: ${module.path} failed all tools`);
        return false;
      };
    });
    await Promise.all(parallel_tasks.map(task => task()));
  }
}

Phase 3B: Agent Execution (>=15 modules)

let modules_by_depth = group_by_depth(all_modules);
let tool_order = construct_tool_order(primary_tool);

for (let depth of sorted_depths.reverse()) {  // N → 0
  let batches = batch_modules(modules_by_depth[depth], 4);
  let worker_tasks = [];

  for (let batch of batches) {
    worker_tasks.push(
      Task(
        subagent_type="memory-bridge",
        description=`Update ${batch.length} modules at depth ${depth}`,
        prompt=generate_batch_worker_prompt(batch, tool_order, "full")
      )
    );
  }

  await parallel_execute(worker_tasks);  // Batches run in parallel
}

Phase 4: Safety Verification

• Verify only CLAUDE.md files were modified
• Display git diff statistics
• Show summary of updates

Strategy Selection

Module Depth	Strategy	Description
Depth < 3	single-layer	Updates only current module's CLAUDE.md
Depth >= 3	multi-layer	Updates current module + all parent CLAUDE.md files

Comparison with Related Update

Aspect	Full Update	Related Update
Scope	All project modules	Changed modules only
Speed	Slower (10-30 min)	Fast (minutes)
Use case	Major refactoring	Daily development
Mode	"full"	"related"
Trigger	After major changes	After commits
Batching	4 modules/agent	4 modules/agent
Fallback	gemini→qwen→codex	gemini→qwen→codex
Complexity threshold	<=20 modules	<=15 modules

Examples

Basic Usage

# Full project update
/memory:update-full

# Output:
# Analyzing workspace...
# Found 45 modules across 8 depth levels
# Filtered: 12 test/build/config modules skipped
# Plan: Update 33 modules with gemini→qwen→codex fallback
# Confirm? (y/n): y
#
# Depth 7: [4/4] ✅
# Depth 6: [8/8] ✅
# ...
# Summary: 33/33 modules updated
# Safety check: Only CLAUDE.md modified ✅

Directory-Specific Update

# Update specific feature directory
/memory:update-full --path src/features/auth

# Only updates modules within src/features/auth

Tool Selection

# Use Qwen for faster updates
/memory:update-full --tool qwen

# Tries qwen → gemini → codex

Related Commands

• /memory:update-related - Update only changed modules
• /memory:load - Load project context into memory
• /memory:compact - Compact session memory

Notes

• Direct execution for <15 modules (faster, no agent overhead)
• Agent execution for >=15 modules (better resource utilization)
• Smart filtering automatically skips test/build/config directories
• Safety check ensures only CLAUDE.md files are modified
• Git diff statistics provide summary of changes
• Automatic backup of existing files before update