tsdoc/ts/context/diff-processor.ts

/**
 * 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');
  }
}