1.9.1

changelog.md

@@ -1,5 +1,33 @@
 # Changelog
 
+## 2025-11-04 - 1.9.1 - fix(iterative-context-builder)
+Rely on DiffProcessor for git diff pre-processing; remove raw char truncation, raise diff token safety, and improve logging
+
+- Removed raw character-based truncation of additionalContext — diffs are expected to be pre-processed by DiffProcessor instead of blind substring truncation.
+- Now validates pre-processed diff token count only and treats DiffProcessor as the primary sampler (DiffProcessor typically uses a ~100k token budget).
+- Increased MAX_DIFF_TOKENS safety net to 200,000 to cover edge cases and avoid false positives; updated logs to reflect pre-processed diffs.
+- Improved error messaging to indicate a likely DiffProcessor misconfiguration when pre-processed diffs exceed the safety limit.
+- Updated informational logs to state that a pre-processed git diff was added to context.
+
+## 2025-11-04 - 1.9.0 - feat(context)
+Add intelligent DiffProcessor to summarize and prioritize git diffs and integrate it into the commit context pipeline
+
+- Add DiffProcessor (ts/context/diff-processor.ts) to intelligently process git diffs: include small files fully, summarize medium files (head/tail sampling), and mark very large files as metadata-only to stay within token budgets.
+- Integrate DiffProcessor into commit workflow (ts/aidocs_classes/commit.ts): preprocess raw diffs, emit processed diff statistics, and pass a token-efficient diff section into the TaskContextFactory for commit context generation.
+- Export DiffProcessor and its types through the context index and types (ts/context/index.ts, ts/context/types.ts) so other context components can reuse it.
+- Add comprehensive tests for the DiffProcessor behavior and integration (test/test.diffprocessor.node.ts) covering small/medium/large diffs, added/deleted files, prioritization, token budgets, and formatting for context.
+- Minor adjustments across context/task factories and builders to accept and propagate processed diff strings rather than raw diffs, reducing risk of token overflows during iterative context building.
+
+## 2025-11-04 - 1.8.3 - fix(context)
+Prevent enormous git diffs and OOM during context building by adding exclusion patterns, truncation, and diagnostic logging
+
+- Add comprehensive git diff exclusion globs (locks, build artifacts, maps, bundles, IDE folders, logs, caches) when collecting uncommitted diffs to avoid noisy/huge diffs
+- Pass glob patterns directly to smartgit.getUncommittedDiff for efficient server-side matching
+- Emit diagnostic statistics for diffs (files changed, total characters, estimated tokens, number of exclusion patterns) and warn on unusually large diffs
+- Introduce pre-tokenization safety checks in iterative context builder: truncate raw diff text if it exceeds MAX_DIFF_CHARS and throw a clear error if token count still exceeds MAX_DIFF_TOKENS
+- Format and log token counts using locale-aware formatting for clarity
+- Improve robustness of commit context generation to reduce risk of OOM / model-limit overruns
+
 ## 2025-11-03 - 1.8.0 - feat(context)
 Wire OpenAI provider through task context factory and add git-diff support to iterative context builder
 

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@git.zone/tsdoc",
-  "version": "1.8.0",
+  "version": "1.9.1",
   "private": false,
   "description": "A comprehensive TypeScript documentation tool that leverages AI to generate and enhance project documentation, including dynamic README creation, API docs via TypeDoc, and smart commit message generation.",
   "type": "module",

pnpm-lock.yaml

@@ -3799,8 +3799,8 @@ packages:
     resolution: {integrity: sha512-I9jwMn07Sy/IwOj3zVkVik2JTvgpaykDZEigL6Rx6N9LbMywwUSMtxET+7lVoDLLd3O3IXwJwvuuns8UB/HeAg==}
     engines: {node: '>=4'}
 
-  minimatch@10.0.3:
+  minimatch@10.1.1:
-    resolution: {integrity: sha512-IPZ167aShDZZUMdRk66cyQAW3qr0WzbHkPdMYa8bzZhlHhO3jALbKdxcaak7W9FfT2rZNpQuUu4Od7ILEpXSaw==}
+    resolution: {integrity: sha512-enIvLvRAFZYXJzkCYG5RKmPfrFArdLv+R+lbQ53BmIMLIry74bjKzX6iHAm8WYamJkhSSEabrWN5D97XnKObjQ==}
     engines: {node: 20 || >=22}
 
   minimatch@3.1.2:
@@ -9797,7 +9797,7 @@ snapshots:
     dependencies:
       foreground-child: 3.3.1
       jackspeak: 4.1.1
-      minimatch: 10.0.3
+      minimatch: 10.1.1
       minipass: 7.1.2
       package-json-from-dist: 1.0.1
       path-scurry: 2.0.0
@@ -10680,7 +10680,7 @@ snapshots:
 
   min-indent@1.0.1: {}
 
-  minimatch@10.0.3:
+  minimatch@10.1.1:
     dependencies:
       '@isaacs/brace-expansion': 5.0.0
 

test/test.aidoc.nonci.ts

@@ -33,7 +33,10 @@ tap.test('should build commit object', async () => {
   expect(commitObject).toHaveProperty('recommendedNextVersionLevel');
   expect(commitObject).toHaveProperty('recommendedNextVersionScope');
   expect(commitObject).toHaveProperty('recommendedNextVersionMessage');
+});
 
-})
+tap.test('should stop AIdocs', async () => {
+  await aidocs.stop();
+});
 
 tap.start();

test/test.diffprocessor.node.ts

@@ -0,0 +1,304 @@
+import { tap, expect } from '@git.zone/tstest/tapbundle';
+import { DiffProcessor } from '../ts/context/diff-processor.js';
+
+// Sample diff strings for testing
+const createSmallDiff = (filepath: string, addedLines = 5, removedLines = 3): string => {
+  const lines: string[] = [];
+  lines.push(`--- a/${filepath}`);
+  lines.push(`+++ b/${filepath}`);
+  lines.push(`@@ -1,10 +1,12 @@`);
+
+  for (let i = 0; i < removedLines; i++) {
+    lines.push(`-removed line ${i + 1}`);
+  }
+
+  for (let i = 0; i < addedLines; i++) {
+    lines.push(`+added line ${i + 1}`);
+  }
+
+  lines.push(' unchanged line');
+
+  return lines.join('\n');
+};
+
+const createMediumDiff = (filepath: string): string => {
+  const lines: string[] = [];
+  lines.push(`--- a/${filepath}`);
+  lines.push(`+++ b/${filepath}`);
+  lines.push(`@@ -1,100 +1,150 @@`);
+
+  // 150 lines of changes
+  for (let i = 0; i < 75; i++) {
+    lines.push(`+added line ${i + 1}`);
+  }
+
+  for (let i = 0; i < 75; i++) {
+    lines.push(`-removed line ${i + 1}`);
+  }
+
+  return lines.join('\n');
+};
+
+const createLargeDiff = (filepath: string): string => {
+  const lines: string[] = [];
+  lines.push(`--- a/${filepath}`);
+  lines.push(`+++ b/${filepath}`);
+  lines.push(`@@ -1,1000 +1,1500 @@`);
+
+  // 2500 lines of changes
+  for (let i = 0; i < 1250; i++) {
+    lines.push(`+added line ${i + 1}`);
+  }
+
+  for (let i = 0; i < 1250; i++) {
+    lines.push(`-removed line ${i + 1}`);
+  }
+
+  return lines.join('\n');
+};
+
+const createDeletedFileDiff = (filepath: string): string => {
+  return `--- a/${filepath}
++++ /dev/null
+@@ -1,5 +0,0 @@
+-deleted line 1
+-deleted line 2
+-deleted line 3
+-deleted line 4
+-deleted line 5`;
+};
+
+const createAddedFileDiff = (filepath: string): string => {
+  return `--- /dev/null
++++ b/${filepath}
+@@ -0,0 +1,5 @@
++added line 1
++added line 2
++added line 3
++added line 4
++added line 5`;
+};
+
+tap.test('DiffProcessor should parse small diff correctly', async () => {
+  const processor = new DiffProcessor();
+  const smallDiff = createSmallDiff('src/test.ts', 5, 3);
+
+  const result = processor.processDiffs([smallDiff]);
+
+  expect(result.totalFiles).toEqual(1);
+  expect(result.fullDiffs.length).toEqual(1);
+  expect(result.summarizedDiffs.length).toEqual(0);
+  expect(result.metadataOnly.length).toEqual(0);
+  expect(result.totalTokens).toBeGreaterThan(0);
+});
+
+tap.test('DiffProcessor should summarize medium diff', async () => {
+  const processor = new DiffProcessor();
+  const mediumDiff = createMediumDiff('src/medium-file.ts');
+
+  const result = processor.processDiffs([mediumDiff]);
+
+  expect(result.totalFiles).toEqual(1);
+  expect(result.fullDiffs.length).toEqual(0);
+  expect(result.summarizedDiffs.length).toEqual(1);
+  expect(result.metadataOnly.length).toEqual(0);
+
+  // Verify the summarized diff contains the sample
+  const formatted = processor.formatForContext(result);
+  expect(formatted).toInclude('SUMMARIZED DIFFS');
+  expect(formatted).toInclude('lines omitted');
+});
+
+tap.test('DiffProcessor should handle large diff as metadata only', async () => {
+  const processor = new DiffProcessor();
+  const largeDiff = createLargeDiff('dist/bundle.js');
+
+  const result = processor.processDiffs([largeDiff]);
+
+  expect(result.totalFiles).toEqual(1);
+  expect(result.fullDiffs.length).toEqual(0);
+  expect(result.summarizedDiffs.length).toEqual(0);
+  expect(result.metadataOnly.length).toEqual(1);
+
+  const formatted = processor.formatForContext(result);
+  expect(formatted).toInclude('METADATA ONLY');
+  expect(formatted).toInclude('dist/bundle.js');
+});
+
+tap.test('DiffProcessor should prioritize source files over build artifacts', async () => {
+  const processor = new DiffProcessor();
+  const diffs = [
+    createSmallDiff('dist/bundle.js'),
+    createSmallDiff('src/important.ts'),
+    createSmallDiff('build/output.js'),
+    createSmallDiff('src/core.ts'),
+  ];
+
+  const result = processor.processDiffs(diffs);
+
+  expect(result.totalFiles).toEqual(4);
+
+  // Source files should be included fully first
+  const formatted = processor.formatForContext(result);
+  const srcImportantIndex = formatted.indexOf('src/important.ts');
+  const srcCoreIndex = formatted.indexOf('src/core.ts');
+  const distBundleIndex = formatted.indexOf('dist/bundle.js');
+  const buildOutputIndex = formatted.indexOf('build/output.js');
+
+  // Source files should appear before build artifacts
+  expect(srcImportantIndex).toBeLessThan(distBundleIndex);
+  expect(srcCoreIndex).toBeLessThan(buildOutputIndex);
+});
+
+tap.test('DiffProcessor should respect token budget', async () => {
+  const processor = new DiffProcessor({
+    maxDiffTokens: 500, // Very small budget to force metadata-only
+  });
+
+  // Create multiple large diffs that will exceed budget
+  const diffs = [
+    createLargeDiff('src/file1.ts'),
+    createLargeDiff('src/file2.ts'),
+    createLargeDiff('src/file3.ts'),
+    createLargeDiff('src/file4.ts'),
+  ];
+
+  const result = processor.processDiffs(diffs);
+
+  expect(result.totalTokens).toBeLessThanOrEqual(500);
+  // With such a small budget and large files, most should be metadata only
+  expect(result.metadataOnly.length).toBeGreaterThanOrEqual(2);
+});
+
+tap.test('DiffProcessor should handle deleted files', async () => {
+  const processor = new DiffProcessor();
+  const deletedDiff = createDeletedFileDiff('src/old-file.ts');
+
+  const result = processor.processDiffs([deletedDiff]);
+
+  expect(result.totalFiles).toEqual(1);
+  // Small deleted file should be included fully
+  expect(result.fullDiffs.length).toEqual(1);
+
+  const formatted = processor.formatForContext(result);
+  expect(formatted).toInclude('src/old-file.ts');
+  // Verify the file appears in the output
+  expect(formatted).toInclude('FULL DIFFS');
+});
+
+tap.test('DiffProcessor should handle added files', async () => {
+  const processor = new DiffProcessor();
+  const addedDiff = createAddedFileDiff('src/new-file.ts');
+
+  const result = processor.processDiffs([addedDiff]);
+
+  expect(result.totalFiles).toEqual(1);
+  // Small added file should be included fully
+  expect(result.fullDiffs.length).toEqual(1);
+
+  const formatted = processor.formatForContext(result);
+  expect(formatted).toInclude('src/new-file.ts');
+  // Verify the file appears in the output
+  expect(formatted).toInclude('FULL DIFFS');
+});
+
+tap.test('DiffProcessor should handle mixed file sizes', async () => {
+  const processor = new DiffProcessor();
+  const diffs = [
+    createSmallDiff('src/small.ts'),
+    createMediumDiff('src/medium.ts'),
+    createLargeDiff('dist/large.js'),
+  ];
+
+  const result = processor.processDiffs(diffs);
+
+  expect(result.totalFiles).toEqual(3);
+  expect(result.fullDiffs.length).toEqual(1); // small file
+  expect(result.summarizedDiffs.length).toEqual(1); // medium file
+  expect(result.metadataOnly.length).toEqual(1); // large file
+
+  const formatted = processor.formatForContext(result);
+  expect(formatted).toInclude('FULL DIFFS (1 files)');
+  expect(formatted).toInclude('SUMMARIZED DIFFS (1 files)');
+  expect(formatted).toInclude('METADATA ONLY (1 files)');
+});
+
+tap.test('DiffProcessor should handle empty diff array', async () => {
+  const processor = new DiffProcessor();
+  const result = processor.processDiffs([]);
+
+  expect(result.totalFiles).toEqual(0);
+  expect(result.fullDiffs.length).toEqual(0);
+  expect(result.summarizedDiffs.length).toEqual(0);
+  expect(result.metadataOnly.length).toEqual(0);
+  expect(result.totalTokens).toEqual(0);
+});
+
+tap.test('DiffProcessor should generate comprehensive summary', async () => {
+  const processor = new DiffProcessor();
+  const diffs = [
+    createSmallDiff('src/file1.ts'),
+    createSmallDiff('src/file2.ts'),
+    createMediumDiff('src/file3.ts'),
+    createLargeDiff('dist/bundle.js'),
+  ];
+
+  const result = processor.processDiffs(diffs);
+  const formatted = processor.formatForContext(result);
+
+  expect(formatted).toInclude('GIT DIFF SUMMARY');
+  expect(formatted).toInclude('Files changed: 4 total');
+  expect(formatted).toInclude('included in full');
+  expect(formatted).toInclude('summarized');
+  expect(formatted).toInclude('metadata only');
+  expect(formatted).toInclude('Estimated tokens:');
+  expect(formatted).toInclude('END OF GIT DIFF');
+});
+
+tap.test('DiffProcessor should handle custom options', async () => {
+  const processor = new DiffProcessor({
+    maxDiffTokens: 50000,
+    smallFileLines: 30,
+    mediumFileLines: 150,
+    sampleHeadLines: 10,
+    sampleTailLines: 10,
+  });
+
+  const mediumDiff = createMediumDiff('src/file.ts'); // 150 lines
+  const result = processor.processDiffs([mediumDiff]);
+
+  // With custom settings, this should be summarized (exactly at the mediumFileLines threshold)
+  expect(result.summarizedDiffs.length).toEqual(1);
+});
+
+tap.test('DiffProcessor should prioritize test files appropriately', async () => {
+  const processor = new DiffProcessor();
+  const diffs = [
+    createSmallDiff('src/core.ts'),
+    createSmallDiff('test/core.test.ts'),
+    createSmallDiff('config.json'),
+  ];
+
+  const result = processor.processDiffs(diffs);
+  const formatted = processor.formatForContext(result);
+
+  // Source files should come before test files
+  const srcIndex = formatted.indexOf('src/core.ts');
+  const testIndex = formatted.indexOf('test/core.test.ts');
+
+  expect(srcIndex).toBeLessThan(testIndex);
+});
+
+tap.test('DiffProcessor should handle files with no changes gracefully', async () => {
+  const processor = new DiffProcessor();
+  const emptyDiff = `--- a/src/file.ts
++++ b/src/file.ts
+@@ -1,1 +1,1 @@`;
+
+  const result = processor.processDiffs([emptyDiff]);
+
+  expect(result.totalFiles).toEqual(1);
+  expect(result.fullDiffs.length).toEqual(1); // Still included as a small file
+});
+
+export default tap.start();

test/test.ts

@@ -1,8 +0,0 @@
-import { expect, tap } from '@push.rocks/tapbundle';
-import * as tsdoc from '../ts/index.js';
-
-tap.test('first test', async () => {
-  console.log('test');
-});
-
-tap.start();

ts/00_commitinfo_data.ts

@@ -3,6 +3,6 @@
  */
 export const commitinfo = {
   name: '@git.zone/tsdoc',
-  version: '1.8.0',
+  version: '1.9.1',
   description: 'A comprehensive TypeScript documentation tool that leverages AI to generate and enhance project documentation, including dynamic README creation, API docs via TypeDoc, and smart commit message generation.'
 }

ts/aidocs_classes/commit.ts

@@ -1,6 +1,7 @@
 import * as plugins from '../plugins.js';
 import { AiDoc } from '../classes.aidoc.js';
 import { ProjectContext } from './projectcontext.js';
+import { DiffProcessor } from '../context/diff-processor.js';
 
 export interface INextCommitObject {
   recommendedNextVersionLevel: 'fix' | 'feat' | 'BREAKING CHANGE'; // the recommended next version level of the project
@@ -27,10 +28,92 @@ export class Commit {
       smartgitInstance,
       this.projectDir
     );
-    const diffStringArray = await gitRepo.getUncommittedDiff([
+
+    // Define comprehensive exclusion patterns
+    // smartgit@3.3.0+ supports glob patterns natively
+    const excludePatterns = [
+      // Lock files
       'pnpm-lock.yaml',
       'package-lock.json',
-    ]);
+      'npm-shrinkwrap.json',
+      'yarn.lock',
+      'deno.lock',
+      'bun.lockb',
+
+      // Build artifacts (main culprit for large diffs!)
+      'dist/**',
+      'dist_*/**',           // dist_ts, dist_web, etc.
+      'build/**',
+      '.next/**',
+      'out/**',
+      'public/dist/**',
+
+      // Compiled/bundled files
+      '**/*.js.map',
+      '**/*.d.ts.map',
+      '**/*.min.js',
+      '**/*.bundle.js',
+      '**/*.chunk.js',
+
+      // IDE/Editor directories
+      '.claude/**',
+      '.cursor/**',
+      '.vscode/**',
+      '.idea/**',
+      '**/*.swp',
+      '**/*.swo',
+
+      // Logs and caches
+      '.nogit/**',
+      '**/*.log',
+      '.cache/**',
+      '.rpt2_cache/**',
+      'coverage/**',
+      '.nyc_output/**',
+    ];
+
+    // Pass glob patterns directly to smartgit - it handles matching internally
+    const diffStringArray = await gitRepo.getUncommittedDiff(excludePatterns);
+
+    // Process diffs intelligently using DiffProcessor
+    let processedDiffString: string;
+
+    if (diffStringArray.length > 0) {
+      // Diagnostic logging for raw diff statistics
+      const totalChars = diffStringArray.join('\n\n').length;
+      const estimatedTokens = Math.ceil(totalChars / 4);
+
+      console.log(`📊 Raw git diff statistics:`);
+      console.log(`   Files changed: ${diffStringArray.length}`);
+      console.log(`   Total characters: ${totalChars.toLocaleString()}`);
+      console.log(`   Estimated tokens: ${estimatedTokens.toLocaleString()}`);
+      console.log(`   Exclusion patterns: ${excludePatterns.length}`);
+
+      // Use DiffProcessor to intelligently handle large diffs
+      const diffProcessor = new DiffProcessor({
+        maxDiffTokens: 100000,      // Reserve 100k tokens for diffs
+        smallFileLines: 50,          // Include files <= 50 lines fully
+        mediumFileLines: 200,        // Summarize files <= 200 lines
+        sampleHeadLines: 20,         // Show first 20 lines
+        sampleTailLines: 20,         // Show last 20 lines
+      });
+
+      const processedDiff = diffProcessor.processDiffs(diffStringArray);
+      processedDiffString = diffProcessor.formatForContext(processedDiff);
+
+      console.log(`📝 Processed diff statistics:`);
+      console.log(`   Full diffs: ${processedDiff.fullDiffs.length} files`);
+      console.log(`   Summarized: ${processedDiff.summarizedDiffs.length} files`);
+      console.log(`   Metadata only: ${processedDiff.metadataOnly.length} files`);
+      console.log(`   Final tokens: ${processedDiff.totalTokens.toLocaleString()}`);
+
+      if (estimatedTokens > 50000) {
+        console.log(`✅ DiffProcessor reduced token usage: ${estimatedTokens.toLocaleString()} → ${processedDiff.totalTokens.toLocaleString()}`);
+      }
+    } else {
+      processedDiffString = 'No changes.';
+    }
+
     // Use the new TaskContextFactory for optimized context
     const taskContextFactory = new (await import('../context/index.js')).TaskContextFactory(
       this.projectDir,
@@ -39,9 +122,7 @@ export class Commit {
     await taskContextFactory.initialize();
 
     // Generate context specifically for commit task
-    const contextResult = await taskContextFactory.createContextForCommit(
+    const contextResult = await taskContextFactory.createContextForCommit(processedDiffString);
-      diffStringArray[0] ? diffStringArray.join('\n\n') : 'No changes.'
-    );
     
     // Get the optimized context string
     let contextString = contextResult.context;

ts/classes.aidoc.ts

@@ -64,7 +64,7 @@ export class AiDoc {
         await this.npmextraKV.writeKey('OPENAI_TOKEN', this.openaiToken);
       }
     }
-    if (!this.openaiToken) {
+    if (!this.openaiToken && this.npmextraKV) {
       this.openaiToken = await this.npmextraKV.readKey('OPENAI_TOKEN');
     }
 
@@ -76,7 +76,11 @@ export class AiDoc {
   }
 
   public async stop() {
-    await this.openaiInstance.stop();
+    if (this.openaiInstance) {
+      await this.openaiInstance.stop();
+    }
+    // No explicit cleanup needed for npmextraKV or aidocInteract
+    // They don't keep event loop alive
   }
 
   public async buildReadme(projectDirArg: string) {

ts/context/diff-processor.ts

@@ -0,0 +1,341 @@
+/**
+ * Intelligent git diff processor that handles large diffs by sampling and prioritization
+ * instead of blind truncation.
+ */
+
+export interface IDiffFileInfo {
+  filepath: string;
+  status: 'added' | 'modified' | 'deleted';
+  linesAdded: number;
+  linesRemoved: number;
+  totalLines: number;
+  estimatedTokens: number;
+  diffContent: string;
+}
+
+export interface IProcessedDiff {
+  summary: string;          // Human-readable overview
+  fullDiffs: string[];      // Small files included fully
+  summarizedDiffs: string[]; // Medium files with head/tail
+  metadataOnly: string[];   // Large files, just stats
+  totalFiles: number;
+  totalTokens: number;
+}
+
+export interface IDiffProcessorOptions {
+  maxDiffTokens?: number;      // Maximum tokens for entire diff section (default: 100000)
+  smallFileLines?: number;     // Files <= this are included fully (default: 50)
+  mediumFileLines?: number;    // Files <= this are summarized (default: 200)
+  sampleHeadLines?: number;    // Lines to show at start of medium files (default: 20)
+  sampleTailLines?: number;    // Lines to show at end of medium files (default: 20)
+}
+
+export class DiffProcessor {
+  private options: Required<IDiffProcessorOptions>;
+
+  constructor(options: IDiffProcessorOptions = {}) {
+    this.options = {
+      maxDiffTokens: options.maxDiffTokens ?? 100000,
+      smallFileLines: options.smallFileLines ?? 50,
+      mediumFileLines: options.mediumFileLines ?? 200,
+      sampleHeadLines: options.sampleHeadLines ?? 20,
+      sampleTailLines: options.sampleTailLines ?? 20,
+    };
+  }
+
+  /**
+   * Process an array of git diffs into a structured, token-efficient format
+   */
+  public processDiffs(diffStringArray: string[]): IProcessedDiff {
+    // Parse all diffs into file info objects
+    const fileInfos: IDiffFileInfo[] = diffStringArray
+      .map(diffString => this.parseDiffFile(diffString))
+      .filter(info => info !== null) as IDiffFileInfo[];
+
+    // Prioritize files (source files first, build artifacts last)
+    const prioritized = this.prioritizeFiles(fileInfos);
+
+    const result: IProcessedDiff = {
+      summary: '',
+      fullDiffs: [],
+      summarizedDiffs: [],
+      metadataOnly: [],
+      totalFiles: prioritized.length,
+      totalTokens: 0,
+    };
+
+    let tokensUsed = 0;
+    const tokenBudget = this.options.maxDiffTokens;
+
+    // Categorize and include files based on size and token budget
+    for (const fileInfo of prioritized) {
+      const remainingBudget = tokenBudget - tokensUsed;
+
+      if (remainingBudget <= 0) {
+        // Budget exhausted - rest are metadata only
+        result.metadataOnly.push(this.formatMetadataOnly(fileInfo));
+        continue;
+      }
+
+      if (fileInfo.totalLines <= this.options.smallFileLines) {
+        // Small file - include fully if budget allows
+        if (fileInfo.estimatedTokens <= remainingBudget) {
+          const statusPrefix = this.getFileStatusPrefix(fileInfo);
+          result.fullDiffs.push(`${statusPrefix}${fileInfo.diffContent}`);
+          tokensUsed += fileInfo.estimatedTokens;
+        } else {
+          result.metadataOnly.push(this.formatMetadataOnly(fileInfo));
+        }
+      } else if (fileInfo.totalLines <= this.options.mediumFileLines) {
+        // Medium file - try to include summary with head/tail
+        const summary = this.extractDiffSample(
+          fileInfo,
+          this.options.sampleHeadLines,
+          this.options.sampleTailLines
+        );
+        const summaryTokens = Math.ceil(summary.length / 4); // Rough estimate
+
+        if (summaryTokens <= remainingBudget) {
+          result.summarizedDiffs.push(summary);
+          tokensUsed += summaryTokens;
+        } else {
+          result.metadataOnly.push(this.formatMetadataOnly(fileInfo));
+        }
+      } else {
+        // Large file - metadata only
+        result.metadataOnly.push(this.formatMetadataOnly(fileInfo));
+      }
+    }
+
+    result.totalTokens = tokensUsed;
+    result.summary = this.generateSummary(result);
+
+    return result;
+  }
+
+  /**
+   * Format the processed diff for inclusion in context
+   */
+  public formatForContext(processed: IProcessedDiff): string {
+    const sections: string[] = [];
+
+    // Summary section
+    sections.push('====== GIT DIFF SUMMARY ======');
+    sections.push(processed.summary);
+    sections.push('');
+
+    // Full diffs section
+    if (processed.fullDiffs.length > 0) {
+      sections.push(`====== FULL DIFFS (${processed.fullDiffs.length} files) ======`);
+      sections.push(processed.fullDiffs.join('\n\n'));
+      sections.push('');
+    }
+
+    // Summarized diffs section
+    if (processed.summarizedDiffs.length > 0) {
+      sections.push(`====== SUMMARIZED DIFFS (${processed.summarizedDiffs.length} files) ======`);
+      sections.push(processed.summarizedDiffs.join('\n\n'));
+      sections.push('');
+    }
+
+    // Metadata only section
+    if (processed.metadataOnly.length > 0) {
+      sections.push(`====== METADATA ONLY (${processed.metadataOnly.length} files) ======`);
+      sections.push(processed.metadataOnly.join('\n'));
+      sections.push('');
+    }
+
+    sections.push('====== END OF GIT DIFF ======');
+
+    return sections.join('\n');
+  }
+
+  /**
+   * Parse a single git diff string into file information
+   */
+  private parseDiffFile(diffString: string): IDiffFileInfo | null {
+    if (!diffString || diffString.trim().length === 0) {
+      return null;
+    }
+
+    const lines = diffString.split('\n');
+    let filepath = '';
+    let status: 'added' | 'modified' | 'deleted' = 'modified';
+    let linesAdded = 0;
+    let linesRemoved = 0;
+
+    // Parse diff header to extract filepath and status
+    for (const line of lines) {
+      if (line.startsWith('--- a/')) {
+        filepath = line.substring(6);
+      } else if (line.startsWith('+++ b/')) {
+        const newPath = line.substring(6);
+        if (newPath === '/dev/null') {
+          status = 'deleted';
+        } else if (filepath === '/dev/null') {
+          status = 'added';
+          filepath = newPath;
+        } else {
+          filepath = newPath;
+        }
+      } else if (line.startsWith('+') && !line.startsWith('+++')) {
+        linesAdded++;
+      } else if (line.startsWith('-') && !line.startsWith('---')) {
+        linesRemoved++;
+      }
+    }
+
+    const totalLines = linesAdded + linesRemoved;
+    const estimatedTokens = Math.ceil(diffString.length / 4);
+
+    return {
+      filepath,
+      status,
+      linesAdded,
+      linesRemoved,
+      totalLines,
+      estimatedTokens,
+      diffContent: diffString,
+    };
+  }
+
+  /**
+   * Prioritize files by importance (source files before build artifacts)
+   */
+  private prioritizeFiles(files: IDiffFileInfo[]): IDiffFileInfo[] {
+    return files.sort((a, b) => {
+      const scoreA = this.getFileImportanceScore(a.filepath);
+      const scoreB = this.getFileImportanceScore(b.filepath);
+      return scoreB - scoreA; // Higher score first
+    });
+  }
+
+  /**
+   * Calculate importance score for a file path
+   */
+  private getFileImportanceScore(filepath: string): number {
+    // Source files - highest priority
+    if (filepath.match(/^(src|lib|app|components|pages|api)\//)) {
+      return 100;
+    }
+
+    // Test files - high priority
+    if (filepath.match(/\.(test|spec)\.(ts|js|tsx|jsx)$/) || filepath.startsWith('test/')) {
+      return 80;
+    }
+
+    // Configuration files - medium-high priority
+    if (filepath.match(/\.(json|yaml|yml|toml|config\.(ts|js))$/)) {
+      return 60;
+    }
+
+    // Documentation - medium priority
+    if (filepath.match(/\.(md|txt|rst)$/)) {
+      return 40;
+    }
+
+    // Build artifacts - low priority
+    if (filepath.match(/^(dist|build|out|\.next|public\/dist)\//)) {
+      return 10;
+    }
+
+    // Everything else - default priority
+    return 50;
+  }
+
+  /**
+   * Extract head and tail lines from a diff, omitting the middle
+   */
+  private extractDiffSample(fileInfo: IDiffFileInfo, headLines: number, tailLines: number): string {
+    const lines = fileInfo.diffContent.split('\n');
+    const totalLines = lines.length;
+
+    if (totalLines <= headLines + tailLines) {
+      // File is small enough to include fully
+      return fileInfo.diffContent;
+    }
+
+    // Extract file metadata from diff header
+    const headerLines: string[] = [];
+    let bodyStartIndex = 0;
+    for (let i = 0; i < lines.length; i++) {
+      if (lines[i].startsWith('@@')) {
+        headerLines.push(...lines.slice(0, i + 1));
+        bodyStartIndex = i + 1;
+        break;
+      }
+    }
+
+    const bodyLines = lines.slice(bodyStartIndex);
+    const head = bodyLines.slice(0, headLines);
+    const tail = bodyLines.slice(-tailLines);
+    const omittedLines = bodyLines.length - headLines - tailLines;
+
+    const statusEmoji = fileInfo.status === 'added' ? '➕' :
+                       fileInfo.status === 'deleted' ? '➖' : '📝';
+
+    const parts: string[] = [];
+    parts.push(`${statusEmoji} FILE: ${fileInfo.filepath}`);
+    parts.push(`CHANGES: +${fileInfo.linesAdded} lines, -${fileInfo.linesRemoved} lines (${fileInfo.totalLines} total)`);
+    parts.push('');
+    parts.push(...headerLines);
+    parts.push(...head);
+    parts.push('');
+    parts.push(`[... ${omittedLines} lines omitted - use Read tool to see full file ...]`);
+    parts.push('');
+    parts.push(...tail);
+
+    return parts.join('\n');
+  }
+
+  /**
+   * Get file status prefix with emoji
+   */
+  private getFileStatusPrefix(fileInfo: IDiffFileInfo): string {
+    const statusEmoji = fileInfo.status === 'added' ? '➕' :
+                       fileInfo.status === 'deleted' ? '➖' : '📝';
+    return `${statusEmoji} `;
+  }
+
+  /**
+   * Extract filepath from diff content
+   */
+  private extractFilepathFromDiff(diffContent: string): string {
+    const lines = diffContent.split('\n');
+    for (const line of lines) {
+      if (line.startsWith('+++ b/')) {
+        return line.substring(6);
+      }
+    }
+    return 'unknown';
+  }
+
+  /**
+   * Format file info as metadata only
+   */
+  private formatMetadataOnly(fileInfo: IDiffFileInfo): string {
+    const statusEmoji = fileInfo.status === 'added' ? '➕' :
+                       fileInfo.status === 'deleted' ? '➖' : '📝';
+    return `${statusEmoji} ${fileInfo.filepath} (+${fileInfo.linesAdded}, -${fileInfo.linesRemoved})`;
+  }
+
+  /**
+   * Generate human-readable summary of processed diff
+   */
+  private generateSummary(result: IProcessedDiff): string {
+    const parts: string[] = [];
+    parts.push(`Files changed: ${result.totalFiles} total`);
+    parts.push(`- ${result.fullDiffs.length} included in full`);
+    parts.push(`- ${result.summarizedDiffs.length} summarized (head/tail shown)`);
+    parts.push(`- ${result.metadataOnly.length} metadata only`);
+    parts.push(`Estimated tokens: ~${result.totalTokens.toLocaleString()}`);
+
+    if (result.metadataOnly.length > 0) {
+      parts.push('');
+      parts.push('NOTE: Some files excluded to stay within token budget.');
+      parts.push('Use Read tool with specific file paths to see full content.');
+    }
+
+    return parts.join('\n');
+  }
+}

ts/context/index.ts

@@ -5,6 +5,7 @@ import { ContextTrimmer } from './context-trimmer.js';
 import { LazyFileLoader } from './lazy-file-loader.js';
 import { ContextCache } from './context-cache.js';
 import { ContextAnalyzer } from './context-analyzer.js';
+import { DiffProcessor } from './diff-processor.js';
 import type {
   ContextMode,
   IContextConfig,
@@ -24,7 +25,10 @@ import type {
   IFileAnalysis,
   IAnalysisResult,
   IIterativeConfig,
-  IIterativeContextResult
+  IIterativeContextResult,
+  IDiffFileInfo,
+  IProcessedDiff,
+  IDiffProcessorOptions
 } from './types.js';
 
 export {
@@ -36,6 +40,7 @@ export {
   LazyFileLoader,
   ContextCache,
   ContextAnalyzer,
+  DiffProcessor,
 };
 
 // Types
@@ -58,5 +63,8 @@ export type {
   IFileAnalysis,
   IAnalysisResult,
   IIterativeConfig,
-  IIterativeContextResult
+  IIterativeContextResult,
+  IDiffFileInfo,
+  IProcessedDiff,
+  IDiffProcessorOptions
 };

ts/context/iterative-context-builder.ts

@@ -115,6 +115,10 @@ export class IterativeContextBuilder {
 
     // If additional context (e.g., git diff) is provided, prepend it
     if (additionalContext) {
+      // NOTE: additionalContext is expected to be pre-processed by DiffProcessor
+      // which intelligently samples large diffs to stay within token budget (100k default)
+      const MAX_DIFF_TOKENS = 200000; // Safety net for edge cases (DiffProcessor uses 100k budget)
+
       const diffSection = `
 ====== GIT DIFF ======
 
@@ -122,10 +126,23 @@ ${additionalContext}
 
 ====== END OF GIT DIFF ======
 `;
-      loadedContent = diffSection;
+
+      // Validate token count (should already be under budget from DiffProcessor)
       const diffTokens = this.countTokens(diffSection);
+
+      if (diffTokens > MAX_DIFF_TOKENS) {
+        logger.log('error', `❌ Pre-processed git diff exceeds safety limit (${diffTokens.toLocaleString()} tokens > ${MAX_DIFF_TOKENS.toLocaleString()} limit)`);
+        logger.log('error', `   This should not happen - DiffProcessor should have limited to ~100k tokens.`);
+        logger.log('error', `   Please check DiffProcessor configuration and output.`);
+        throw new Error(
+          `Pre-processed git diff size (${diffTokens.toLocaleString()} tokens) exceeds safety limit (${MAX_DIFF_TOKENS.toLocaleString()} tokens). ` +
+          `This indicates a bug in DiffProcessor or misconfiguration.`
+        );
+      }
+
+      loadedContent = diffSection;
       totalTokensUsed += diffTokens;
-      logger.log('info', `📝 Added git diff to context (${diffTokens} tokens)`);
+      logger.log('info', `📝 Added pre-processed git diff to context (${diffTokens.toLocaleString()} tokens)`);
     }
 
     // Phase 3: Iterative file selection and loading

ts/context/types.ts

@@ -319,3 +319,6 @@ export interface IIterativeContextResult extends IContextResult {
   /** Total duration in ms */
   totalDuration: number;
 }
+
+// Export DiffProcessor types
+export type { IDiffFileInfo, IProcessedDiff, IDiffProcessorOptions } from './diff-processor.js';