@xelth/eck-snapshot 5.4.0 → 5.4.2

package/README.md

@@ -1,106 +1,128 @@
+# eck-snapshot
 
-# eckSnapshot (v5.4.0)
+A CLI tool that packs your entire Git repository into a single text file optimized for LLMs (Claude, Gemini, ChatGPT). Give any AI full project context in one copy-paste.
 
-A specialized CLI tool designed to create and restore single-file text snapshots of Git repositories. It is specifically optimized for providing full project context to Large Language Models (LLMs) like Claude, Gemini, and OpenCode.
+```bash
+npm install -g @xelth/eck-snapshot
+```
 
-🎉 **WE ARE BACK ON NPM!** Version 5.4.0 and onwards are officially available via the npm registry.
+## Core Workflow
 
-## 🚀 Quick Start
+### 1. Full Snapshot
 
-```bash
-# Install globally via npm
-npm install -g @xelth/eck-snapshot
+Run `eck-snapshot` in your project root. It scans every tracked file, filters out noise (lock files, build artifacts, secrets), and produces a single `.md` file ready for an AI chat.
 
-# Create a snapshot of your current project
+```bash
 eck-snapshot
+# -> .eck/snapshots/eckMyProject_26-02-15_12-00_abc1234.md
 ```
 
-## ✨ Core Features
+That's it. Upload the file to your AI and start working.
+
+### 2. Incremental Update
+
+After you make changes, don't re-send the entire project. Send only what changed since the last full snapshot:
+
+```bash
+eck-snapshot update
+# -> .eck/snapshots/eckMyProject_26-02-15_14-30_abc1234_up1.md
+```
 
-- **Skeleton Mode:** Strips function bodies using Tree-sitter and Babel to save massive amounts of context tokens.
-- **Delta Updates:** Tracks changes via Git anchors and generates incremental snapshots (`eck-snapshot update`).
-- **Royal Court Architecture:** Multi-agent protocol with dedicated modes for Claude Sonnet (JAS), Claude Opus (JAO), and Gemini (JAG).
-- **GLM Z.AI Worker Fleet:** Built-in MCP server integration for delegating heavy coding tasks to specialized AI workers.
-- **Security:** Built-in `SecretScanner` automatically redacts API keys and sensitive credentials before they hit the LLM context.
-- **Context Profiles:** Smart filtering using auto-detected or manual profiles (e.g., `--profile backend`).
+This uses a Git anchor (saved automatically during full snapshot) to detect all modified files and includes their full content. No redundant diffs, no wasted tokens.
 
----
+### 3. Lazy Loading
 
-## 🛠️ The Core Workflow
+If the AI asks to see specific files that weren't in the snapshot, show them instantly:
 
-### 1. Initial Context (Maximum Compression)
-Create a lightweight map of your entire project. Bodies of functions are hidden, allowing huge monoliths to fit into the AI's context window.
 ```bash
-eck-snapshot --skeleton
-# -> Generates: .eck/snapshots/eck[Name]_[Hash]_sk.md
+eck-snapshot show src/auth.rs src/handlers/sync.rs
 ```
 
-### 2. Lazy Loading (On-Demand Details)
-If the AI needs to see the exact implementation of specific files, it can request them on demand.
+## Context Profiles
+
+Large repositories waste tokens on irrelevant code. Profiles let you partition the codebase so the AI only sees what matters.
+
+### Auto-Detection
+
+Let AI scan your directory tree and generate profiles automatically:
+
 ```bash
-eck-snapshot show src/auth.js src/utils/hash.js
+eck-snapshot profile-detect
+# -> Saves profiles to .eck/profiles.json
 ```
 
-### 3. Incremental Updates (Delta)
-As you apply changes, the AI loses context. Instead of re-sending the full repository, send only what changed since the last snapshot!
+### Manual Guide
+
+For very large repos where auto-detection is too slow, generate a prompt guide, paste it into a powerful Web LLM (Gemini, ChatGPT), and save the resulting JSON:
+
 ```bash
-eck-snapshot update
-# -> Generates an update snapshot with git diffs and modified files
+eck-snapshot generate-profile-guide
+# -> .eck/profile_generation_guide.md (paste into AI, get profiles back)
 ```
 
----
+### Using Profiles
 
-## 👑 Royal Court Architecture & GLM Z.AI
+```bash
+eck-snapshot --profile                            # List all available profiles
+eck-snapshot --profile backend                    # Use a named profile
+eck-snapshot --profile backend --skeleton         # Profile + skeleton mode
+eck-snapshot --profile "src/**/*.rs,-**/test_*"   # Ad-hoc glob filtering
+```
 
-`eck-snapshot` is designed to orchestrate a hierarchy of AI agents:
+Profiles work with both full snapshots and incremental updates.
 
-- **Senior Architect:** (You / Gemini / ChatGPT) - Directs the high-level strategy.
-- **Junior Architects:**
-  - `JAS` (Sonnet 4.5): Fast manager for standard features. Run `eck-snapshot --jas`.
-  - `JAO` (Opus 4.5): Deep thinker for critical architecture. Run `eck-snapshot --jao`.
-  - `JAG` (Gemini 3 Pro): Massive context handler. Run `eck-snapshot --jag`.
+## Smart Filtering
 
-### MCP Server Integration
-Delegate heavy coding tasks (>100 lines) to the **GLM Z.AI Worker Fleet** to save expensive context window tokens.
+eck-snapshot automatically detects your project type (Rust, Node.js, Android, Python, etc.) and excludes language-specific noise:
 
-1. Get your API key from [Z.AI](https://z.ai) and export it: `export ZAI_API_KEY="your-key-here"`
-2. Setup the MCP servers for Claude Code or OpenCode:
-   ```bash
-   eck-snapshot setup-mcp --both
-   ```
-3. Your AI will now have access to specialized tools: `glm_zai_frontend`, `glm_zai_backend`, `glm_zai_qa`, `glm_zai_refactor`, and the `eck_finish_task` commit tool.
+- **Rust**: `Cargo.lock`, `target/`
+- **Node.js**: `package-lock.json`, `node_modules/`
+- **Android**: build artifacts, generated code
+- **All projects**: `.git/`, IDE configs, binary files
 
----
+The built-in `SecretScanner` also redacts API keys, tokens, and credentials before they reach the AI.
 
-## 🧩 Context Profiles
+## Multi-Agent Architecture
 
-If your repository is huge, you can partition it using Context Profiles:
+eck-snapshot generates tailored `CLAUDE.md` instructions for different AI agent roles:
 
 ```bash
-# Auto-detect profiles using AI
-eck-snapshot profile-detect
+eck-snapshot --jas    # Junior Architect Sonnet - fast, standard features
+eck-snapshot --jao    # Junior Architect Opus - deep, critical architecture
+eck-snapshot --jag    # Junior Architect Gemini - massive context tasks
+```
 
-# List available profiles
-eck-snapshot --profile
+### MCP Server Integration
 
-# Use a specific profile
-eck-snapshot --profile backend
+Delegate coding tasks to the GLM Z.AI Worker Fleet via MCP:
 
-# Ad-hoc inclusion/exclusion
-eck-snapshot --profile "src/**/*.js,-**/*.test.js"
+```bash
+export ZAI_API_KEY="your-key"
+eck-snapshot setup-mcp --both    # Setup for Claude Code + OpenCode
 ```
 
-## 🔐 Environment Syncing
+This gives your AI access to specialized workers: `glm_zai_frontend`, `glm_zai_backend`, `glm_zai_qa`, `glm_zai_refactor`, and the `eck_finish_task` commit tool.
+
+## Skeleton Mode
 
-Securely share your `.eck/` configuration (profiles, roadmap, AI instructions) between machines without committing them to the public git history:
+For extremely large projects, skeleton mode strips function bodies and keeps only signatures, types, and structure:
 
 ```bash
-# Encrypt and pack .eck/ config files
-eck-snapshot env push
+eck-snapshot --skeleton
+```
 
-# Decrypt and restore on another machine
-eck-snapshot env pull
+Useful for initial orientation in massive codebases, but full snapshots with profiles are usually more practical.
+
+## Other Commands
+
+```bash
+eck-snapshot restore <snapshot>    # Restore files from a snapshot to disk
+eck-snapshot prune <snapshot>      # AI-powered snapshot size reduction
+eck-snapshot doctor                # Check project health
+eck-snapshot env push              # Encrypt and sync .eck/ config between machines
+eck-snapshot env pull              # Restore .eck/ config on another machine
 ```
 
 ## License
-MIT License
+
+MIT

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@xelth/eck-snapshot",
-  "version": "5.4.0",
+  "version": "5.4.2",
   "description": "A powerful CLI tool to create and restore single-file text snapshots of Git repositories and directories. Optimized for AI context and LLM workflows.",
   "main": "index.js",
   "type": "module",

package/src/cli/commands/createSnapshot.js

@@ -10,13 +10,13 @@ import ora from 'ora';
 import micromatch from 'micromatch';
 import chalk from 'chalk';
 
-import {
-  parseSize, formatSize, matchesPattern, checkGitRepository,
-  scanDirectoryRecursively, loadGitignore, readFileWithSizeCheck,
-  generateDirectoryTree, loadConfig, displayProjectInfo, loadProjectEckManifest,
-  ensureSnapshotsInGitignore, initializeEckManifest, generateTimestamp,
-  getShortRepoName, SecretScanner
-} from '../../utils/fileUtils.js';
+import {
+  parseSize, formatSize, matchesPattern, checkGitRepository,
+  scanDirectoryRecursively, loadGitignore, readFileWithSizeCheck,
+  generateDirectoryTree, loadConfig, displayProjectInfo, loadProjectEckManifest,
+  ensureSnapshotsInGitignore, initializeEckManifest, generateTimestamp,
+  getShortRepoName, SecretScanner
+} from '../../utils/fileUtils.js';
 import { detectProjectType, getProjectSpecificFiltering } from '../../utils/projectDetector.js';
 import { estimateTokensWithPolynomial, generateTrainingCommand } from '../../utils/tokenEstimator.js';
 import { loadSetupConfig, getProfile } from '../../config.js';
@@ -312,6 +312,17 @@ async function estimateProjectTokens(projectPath, config, projectType = null) {
 }
 
 async function processProjectFiles(repoPath, options, config, projectType = null) {
+  // Merge project-specific filtering rules (e.g., Cargo.lock for Rust)
+  if (projectType) {
+    const projectSpecific = await getProjectSpecificFiltering(projectType);
+    config = {
+      ...config,
+      dirsToIgnore: [...(config.dirsToIgnore || []), ...(projectSpecific.dirsToIgnore || [])],
+      filesToIgnore: [...(config.filesToIgnore || []), ...(projectSpecific.filesToIgnore || [])],
+      extensionsToIgnore: [...(config.extensionsToIgnore || []), ...(projectSpecific.extensionsToIgnore || [])]
+    };
+  }
+
   const originalCwd = process.cwd();
   console.log(`\n📸 Processing files for: ${path.basename(repoPath)}`);
 
@@ -703,59 +714,59 @@ export async function createRepoSnapshot(repoPath, options) {
 
       // Helper to write snapshot file
       const writeSnapshot = async (suffix, isAgentMode) => {
-        // CHANGE: Force agent to FALSE for the main snapshot header.
-        // The snapshot is read by the Human/Senior Arch, not the Agent itself.
-        // The Agent reads CLAUDE.md.
-        const opts = { ...options, agent: false, jag: isJag, jas: isJas, jao: isJao };
-        const header = await generateEnhancedAIHeader({ stats, repoName, mode: 'file', eckManifest, options: opts, repoPath: processedRepoPath }, isGitRepo);
-
-        // Compact filename format: eck{ShortName}{timestamp}_{hash}_{suffix}.md
-        // getShortRepoName ensures Capitalized Start/End (e.g. SnaOt)
-        const shortHash = gitHash ? gitHash.substring(0, 7) : '';
-        const shortRepoName = getShortRepoName(repoName);
-
-        let fname = `eck${shortRepoName}${timestamp}`;
-        if (shortHash) fname += `_${shortHash}`;
-
-        // Add mode suffix
-        if (options.skeleton) {
-          fname += '_sk';
-        } else if (suffix) {
-          fname += suffix;
-        }
-
-        fname += `.${fileExtension}`;
-        const fpath = path.join(outputPath, fname);
-        const fullContent = header + fileBody;
-        await fs.writeFile(fpath, fullContent);
-        console.log(`📄 Generated Snapshot: ${fname}`);
-
-        // --- FEATURE: Active Snapshot (.eck/lastsnapshot/) ---
-        // Only create .eck/lastsnapshot/ entries for the main snapshot
-        if (!isAgentMode) {
-          try {
-            const snapDir = path.join(originalCwd, '.eck', 'lastsnapshot');
-            await fs.mkdir(snapDir, { recursive: true });
-
-            // 1. Clean up OLD snapshots in this specific folder
-            // We keep AnswerToSA.md, but remove old snapshots and legacy answer.md
-            const existingFiles = await fs.readdir(snapDir);
-            for (const file of existingFiles) {
-              if ((file.startsWith('eck') && file.endsWith('.md')) || file === 'answer.md') {
-                await fs.unlink(path.join(snapDir, file));
-              }
-            }
-
-            // 2. Save the NEW specific named file
-            await fs.writeFile(path.join(snapDir, fname), fullContent);
-
-            console.log(chalk.cyan(`📋 Active snapshot updated in .eck/lastsnapshot/: ${fname}`));
-          } catch (e) {
-            // Non-critical failure
-            console.warn(chalk.yellow(`⚠️  Could not update .eck/lastsnapshot/: ${e.message}`));
-          }
-        }
-        // --------------------------------------------
+        // CHANGE: Force agent to FALSE for the main snapshot header.
+        // The snapshot is read by the Human/Senior Arch, not the Agent itself.
+        // The Agent reads CLAUDE.md.
+        const opts = { ...options, agent: false, jag: isJag, jas: isJas, jao: isJao };
+        const header = await generateEnhancedAIHeader({ stats, repoName, mode: 'file', eckManifest, options: opts, repoPath: processedRepoPath }, isGitRepo);
+
+        // Compact filename format: eck{ShortName}{timestamp}_{hash}_{suffix}.md
+        // getShortRepoName ensures Capitalized Start/End (e.g. SnaOt)
+        const shortHash = gitHash ? gitHash.substring(0, 7) : '';
+        const shortRepoName = getShortRepoName(repoName);
+
+        let fname = `eck${shortRepoName}${timestamp}`;
+        if (shortHash) fname += `_${shortHash}`;
+
+        // Add mode suffix
+        if (options.skeleton) {
+          fname += '_sk';
+        } else if (suffix) {
+          fname += suffix;
+        }
+
+        fname += `.${fileExtension}`;
+        const fpath = path.join(outputPath, fname);
+        const fullContent = header + fileBody;
+        await fs.writeFile(fpath, fullContent);
+        console.log(`📄 Generated Snapshot: ${fname}`);
+
+        // --- FEATURE: Active Snapshot (.eck/lastsnapshot/) ---
+        // Only create .eck/lastsnapshot/ entries for the main snapshot
+        if (!isAgentMode) {
+          try {
+            const snapDir = path.join(originalCwd, '.eck', 'lastsnapshot');
+            await fs.mkdir(snapDir, { recursive: true });
+
+            // 1. Clean up OLD snapshots in this specific folder
+            // We keep AnswerToSA.md, but remove old snapshots and legacy answer.md
+            const existingFiles = await fs.readdir(snapDir);
+            for (const file of existingFiles) {
+              if ((file.startsWith('eck') && file.endsWith('.md')) || file === 'answer.md') {
+                await fs.unlink(path.join(snapDir, file));
+              }
+            }
+
+            // 2. Save the NEW specific named file
+            await fs.writeFile(path.join(snapDir, fname), fullContent);
+
+            console.log(chalk.cyan(`📋 Active snapshot updated in .eck/lastsnapshot/: ${fname}`));
+          } catch (e) {
+            // Non-critical failure
+            console.warn(chalk.yellow(`⚠️  Could not update .eck/lastsnapshot/: ${e.message}`));
+          }
+        }
+        // --------------------------------------------
 
         return fpath;
       };

package/src/cli/commands/updateSnapshot.js

@@ -2,9 +2,10 @@ import fs from 'fs/promises';
 import path from 'path';
 import ora from 'ora';
 import chalk from 'chalk';
-import { getGitAnchor, getChangedFiles, getGitDiffOutput } from '../../utils/gitUtils.js';
+import { getGitAnchor, getChangedFiles } from '../../utils/gitUtils.js';
 import { loadSetupConfig } from '../../config.js';
 import { readFileWithSizeCheck, parseSize, formatSize, matchesPattern, loadGitignore, generateTimestamp, getShortRepoName } from '../../utils/fileUtils.js';
+import { detectProjectType, getProjectSpecificFiltering } from '../../utils/projectDetector.js';
 import { fileURLToPath } from 'url';
 
 const __filename = fileURLToPath(import.meta.url);
@@ -16,18 +17,22 @@ async function generateSnapshotContent(repoPath, changedFiles, anchor, config, g
   let includedCount = 0;
   const fileList = [];
 
-  // Check for Agent Report in .eck/lastsnapshot/AnswerToSA.md (STRICT LOCATION)
-  const reportPath = path.join(repoPath, '.eck', 'lastsnapshot', 'AnswerToSA.md');
-  let agentReport = null;
-  try {
-    agentReport = await fs.readFile(reportPath, 'utf-8');
-    if (!changedFiles.includes('.eck/lastsnapshot/AnswerToSA.md')) {
-      changedFiles.push('.eck/lastsnapshot/AnswerToSA.md');
-    }
-  } catch (e) { /* No report */ }
+  // Check for Agent Report in .eck/lastsnapshot/AnswerToSA.md (STRICT LOCATION)
+  const reportPath = path.join(repoPath, '.eck', 'lastsnapshot', 'AnswerToSA.md');
+  let agentReport = null;
+  try {
+    agentReport = await fs.readFile(reportPath, 'utf-8');
+    if (!changedFiles.includes('.eck/lastsnapshot/AnswerToSA.md')) {
+      changedFiles.push('.eck/lastsnapshot/AnswerToSA.md');
+    }
+  } catch (e) { /* No report */ }
 
   for (const filePath of changedFiles) {
-    if (config.dirsToIgnore.some(d => filePath.startsWith(d))) continue;
+    if (config.dirsToIgnore?.some(d => filePath.startsWith(d))) continue;
+    const fileName = path.basename(filePath);
+    const fileExt = path.extname(filePath);
+    if (config.filesToIgnore?.includes(fileName)) continue;
+    if (fileExt && config.extensionsToIgnore?.includes(fileExt)) continue;
     if (gitignore.ignores(filePath) && filePath !== '.eck/lastsnapshot/AnswerToSA.md') continue;
 
     try {
@@ -55,15 +60,12 @@ async function generateSnapshotContent(repoPath, changedFiles, anchor, config, g
 
   header = reportSection + header;
 
-  const diffOutput = await getGitDiffOutput(repoPath, anchor);
-  const diffSection = `\n--- GIT DIFF (For Context) ---\n\n\`\`\`diff\n${diffOutput}\n\`\`\``;
-
-  return {
-    fullContent: header + contentOutput + diffSection,
-    includedCount,
-    anchor,
-    agentReport
-  };
+  return {
+    fullContent: header + contentOutput,
+    includedCount,
+    anchor,
+    agentReport
+  };
 }
 
 export async function updateSnapshot(repoPath, options) {
@@ -80,11 +82,24 @@ export async function updateSnapshot(repoPath, options) {
       return;
     }
 
-    const setupConfig = await loadSetupConfig();
-    const config = { ...setupConfig.fileFiltering, ...setupConfig.performance, ...options };
-    const gitignore = await loadGitignore(repoPath);
-
-    const { fullContent, includedCount, agentReport } = await generateSnapshotContent(repoPath, changedFiles, anchor, config, gitignore);
+    const setupConfig = await loadSetupConfig();
+    let config = { ...setupConfig.fileFiltering, ...setupConfig.performance, ...options };
+
+    // Detect project type and merge project-specific filters
+    const projectDetection = await detectProjectType(repoPath);
+    if (projectDetection.type) {
+      const projectSpecific = await getProjectSpecificFiltering(projectDetection.type);
+      config = {
+        ...config,
+        dirsToIgnore: [...(config.dirsToIgnore || []), ...(projectSpecific.dirsToIgnore || [])],
+        filesToIgnore: [...(config.filesToIgnore || []), ...(projectSpecific.filesToIgnore || [])],
+        extensionsToIgnore: [...(config.extensionsToIgnore || []), ...(projectSpecific.extensionsToIgnore || [])]
+      };
+    }
+
+    const gitignore = await loadGitignore(repoPath);
+
+    const { fullContent, includedCount, agentReport } = await generateSnapshotContent(repoPath, changedFiles, anchor, config, gitignore);
 
     // Determine sequence number
     let seqNum = 1;
@@ -101,43 +116,43 @@ export async function updateSnapshot(repoPath, options) {
       await fs.writeFile(counterPath, `${anchor.substring(0, 7)}:${seqNum}`);
     } catch (e) {}
 
-    const timestamp = generateTimestamp();
-    const shortRepoName = getShortRepoName(path.basename(repoPath));
-    const outputFilename = `eck${shortRepoName}${timestamp}_${anchor.substring(0, 7)}_up${seqNum}.md`;
-    const outputPath = path.join(repoPath, '.eck', 'snapshots', outputFilename);
-
-    await fs.mkdir(path.dirname(outputPath), { recursive: true });
-    await fs.writeFile(outputPath, fullContent);
-
-    spinner.succeed(`Update snapshot created: .eck/snapshots/${outputFilename}`);
-
-    // --- FEATURE: Active Snapshot (.eck/lastsnapshot/) ---
-    try {
-      const snapDir = path.join(repoPath, '.eck', 'lastsnapshot');
-      await fs.mkdir(snapDir, { recursive: true });
-
-      // 1. Clean up OLD snapshots
-      const existingFiles = await fs.readdir(snapDir);
-      for (const file of existingFiles) {
-        if ((file.startsWith('eck') && file.endsWith('.md')) || file === 'answer.md') {
-          await fs.unlink(path.join(snapDir, file));
-        }
-      }
-
-      // 2. Save new file
-      await fs.writeFile(path.join(snapDir, outputFilename), fullContent);
-      console.log(chalk.cyan(`📋 Active snapshot updated in .eck/lastsnapshot/: ${outputFilename}`));
-    } catch (e) {
-      // Non-critical failure
-    }
-    // --------------------------------------------
-
-    // Check if agent report was included
-    if (agentReport) {
-      console.log(chalk.green('📨 Included Agent Report (.eck/lastsnapshot/AnswerToSA.md)'));
-    }
-
-    console.log(`📦 Included ${includedCount} changed files.`);
+    const timestamp = generateTimestamp();
+    const shortRepoName = getShortRepoName(path.basename(repoPath));
+    const outputFilename = `eck${shortRepoName}${timestamp}_${anchor.substring(0, 7)}_up${seqNum}.md`;
+    const outputPath = path.join(repoPath, '.eck', 'snapshots', outputFilename);
+
+    await fs.mkdir(path.dirname(outputPath), { recursive: true });
+    await fs.writeFile(outputPath, fullContent);
+
+    spinner.succeed(`Update snapshot created: .eck/snapshots/${outputFilename}`);
+
+    // --- FEATURE: Active Snapshot (.eck/lastsnapshot/) ---
+    try {
+      const snapDir = path.join(repoPath, '.eck', 'lastsnapshot');
+      await fs.mkdir(snapDir, { recursive: true });
+
+      // 1. Clean up OLD snapshots
+      const existingFiles = await fs.readdir(snapDir);
+      for (const file of existingFiles) {
+        if ((file.startsWith('eck') && file.endsWith('.md')) || file === 'answer.md') {
+          await fs.unlink(path.join(snapDir, file));
+        }
+      }
+
+      // 2. Save new file
+      await fs.writeFile(path.join(snapDir, outputFilename), fullContent);
+      console.log(chalk.cyan(`📋 Active snapshot updated in .eck/lastsnapshot/: ${outputFilename}`));
+    } catch (e) {
+      // Non-critical failure
+    }
+    // --------------------------------------------
+
+    // Check if agent report was included
+    if (agentReport) {
+      console.log(chalk.green('📨 Included Agent Report (.eck/lastsnapshot/AnswerToSA.md)'));
+    }
+
+    console.log(`📦 Included ${includedCount} changed files.`);
 
   } catch (error) {
     spinner.fail(`Update failed: ${error.message}`);
@@ -159,11 +174,24 @@ export async function updateSnapshotJson(repoPath) {
       return;
     }
 
-    const setupConfig = await loadSetupConfig();
-    const config = { ...setupConfig.fileFiltering, ...setupConfig.performance };
-    const gitignore = await loadGitignore(repoPath);
-
-    const { fullContent, includedCount, agentReport } = await generateSnapshotContent(repoPath, changedFiles, anchor, config, gitignore);
+    const setupConfig = await loadSetupConfig();
+    let config = { ...setupConfig.fileFiltering, ...setupConfig.performance };
+
+    // Detect project type and merge project-specific filters
+    const projectDetection = await detectProjectType(repoPath);
+    if (projectDetection.type) {
+      const projectSpecific = await getProjectSpecificFiltering(projectDetection.type);
+      config = {
+        ...config,
+        dirsToIgnore: [...(config.dirsToIgnore || []), ...(projectSpecific.dirsToIgnore || [])],
+        filesToIgnore: [...(config.filesToIgnore || []), ...(projectSpecific.filesToIgnore || [])],
+        extensionsToIgnore: [...(config.extensionsToIgnore || []), ...(projectSpecific.extensionsToIgnore || [])]
+      };
+    }
+
+    const gitignore = await loadGitignore(repoPath);
+
+    const { fullContent, includedCount, agentReport } = await generateSnapshotContent(repoPath, changedFiles, anchor, config, gitignore);
 
     let seqNum = 1;
     const counterPath = path.join(repoPath, '.eck', 'update_seq');
@@ -179,39 +207,39 @@ export async function updateSnapshotJson(repoPath) {
       await fs.writeFile(counterPath, `${anchor.substring(0, 7)}:${seqNum}`);
     } catch (e) {}
 
-    const timestamp = generateTimestamp();
-    const shortRepoName = getShortRepoName(path.basename(repoPath));
-    const outputFilename = `eck${shortRepoName}${timestamp}_${anchor.substring(0, 7)}_up${seqNum}.md`;
-    const outputPath = path.join(repoPath, '.eck', 'snapshots', outputFilename);
-    await fs.mkdir(path.dirname(outputPath), { recursive: true });
-    await fs.writeFile(outputPath, fullContent);
-
-    // --- FEATURE: Active Snapshot (.eck/lastsnapshot/) ---
-    try {
-      const snapDir = path.join(repoPath, '.eck', 'lastsnapshot');
-      await fs.mkdir(snapDir, { recursive: true });
-
-      // 1. Clean up OLD snapshots
-      const existingFiles = await fs.readdir(snapDir);
-      for (const file of existingFiles) {
-        if ((file.startsWith('eck') && file.endsWith('.md')) || file === 'answer.md') {
-          await fs.unlink(path.join(snapDir, file));
-        }
-      }
-
-      // 2. Save new file
-      await fs.writeFile(path.join(snapDir, outputFilename), fullContent);
-    } catch (e) {
-      // Non-critical failure
-    }
-    // --------------------------------------------
-
-    console.log(JSON.stringify({
-      status: "success",
-      snapshot_file: `.eck/snapshots/${outputFilename}`,
-      files_count: includedCount,
-      timestamp: timestamp
-    }));
+    const timestamp = generateTimestamp();
+    const shortRepoName = getShortRepoName(path.basename(repoPath));
+    const outputFilename = `eck${shortRepoName}${timestamp}_${anchor.substring(0, 7)}_up${seqNum}.md`;
+    const outputPath = path.join(repoPath, '.eck', 'snapshots', outputFilename);
+    await fs.mkdir(path.dirname(outputPath), { recursive: true });
+    await fs.writeFile(outputPath, fullContent);
+
+    // --- FEATURE: Active Snapshot (.eck/lastsnapshot/) ---
+    try {
+      const snapDir = path.join(repoPath, '.eck', 'lastsnapshot');
+      await fs.mkdir(snapDir, { recursive: true });
+
+      // 1. Clean up OLD snapshots
+      const existingFiles = await fs.readdir(snapDir);
+      for (const file of existingFiles) {
+        if ((file.startsWith('eck') && file.endsWith('.md')) || file === 'answer.md') {
+          await fs.unlink(path.join(snapDir, file));
+        }
+      }
+
+      // 2. Save new file
+      await fs.writeFile(path.join(snapDir, outputFilename), fullContent);
+    } catch (e) {
+      // Non-critical failure
+    }
+    // --------------------------------------------
+
+    console.log(JSON.stringify({
+      status: "success",
+      snapshot_file: `.eck/snapshots/${outputFilename}`,
+      files_count: includedCount,
+      timestamp: timestamp
+    }));
 
   } catch (error) {
     console.log(JSON.stringify({ status: "error", message: error.message }));

package/src/config.js

@@ -50,16 +50,6 @@ function validateConfigSchema(config) {
     warnings.push('Missing "aiInstructions" section');
   }
 
-  // Legacy support
-  if (!config.filesToIgnore || !Array.isArray(config.filesToIgnore)) {
-    warnings.push('filesToIgnore missing or not an array - using defaults');
-    config.filesToIgnore = DEFAULT_CONFIG.filesToIgnore;
-  }
-  if (!config.dirsToIgnore || !Array.isArray(config.dirsToIgnore)) {
-    warnings.push('dirsToIgnore missing or not an array - using defaults');
-    config.dirsToIgnore = DEFAULT_CONFIG.dirsToIgnore;
-  }
-
   if (warnings.length > 0) {
     console.warn('\n⚠️ Config Validation Warnings:');
     warnings.forEach(w => console.warn(`   - ${w}`));

package/src/utils/gitUtils.js

@@ -34,9 +34,16 @@ export async function getChangedFiles(repoPath, anchorHash) {
   }
 }
 
-export async function getGitDiffOutput(repoPath, anchorHash) {
+export async function getGitDiffOutput(repoPath, anchorHash, excludeFiles = []) {
   try {
-    const { stdout } = await execa('git', ['diff', anchorHash, 'HEAD'], { cwd: repoPath });
+    const args = ['diff', anchorHash, 'HEAD'];
+    if (excludeFiles.length > 0) {
+      args.push('--');
+      for (const file of excludeFiles) {
+        args.push(`:(exclude)${file}`);
+      }
+    }
+    const { stdout } = await execa('git', args, { cwd: repoPath });
     return stdout;
   } catch (e) {
     return '';