@kaitranntt/ccs 4.4.0 → 5.0.1

package/bin/glmt/locale-enforcer.js

@@ -1,72 +0,0 @@
-#!/usr/bin/env node
-'use strict';
-
-/**
- * LocaleEnforcer - Force English output from GLM models
- *
- * Purpose: GLM models default to Chinese when prompts are ambiguous or contain Chinese context.
- * This module always injects "MUST respond in English" instruction into system prompt or first user message.
- *
- * Usage:
- *   const enforcer = new LocaleEnforcer();
- *   const modifiedMessages = enforcer.injectInstruction(messages);
- *
- * Strategy:
- *   1. If system prompt exists: Prepend instruction
- *   2. If no system prompt: Prepend to first user message
- *   3. Preserve message structure (string vs array content)
- */
-class LocaleEnforcer {
-  constructor(options = {}) {
-    this.instruction = "CRITICAL: You MUST respond in English only, regardless of the input language or context. This is a strict requirement.";
-  }
-
-  /**
-   * Inject English instruction into messages
-   * @param {Array} messages - Messages array to modify
-   * @returns {Array} Modified messages array
-   */
-  injectInstruction(messages) {
-    // Clone messages to avoid mutation
-    const modifiedMessages = JSON.parse(JSON.stringify(messages));
-
-    // Strategy 1: Inject into system prompt (preferred)
-    const systemIndex = modifiedMessages.findIndex(m => m.role === 'system');
-    if (systemIndex >= 0) {
-      const systemMsg = modifiedMessages[systemIndex];
-
-      if (typeof systemMsg.content === 'string') {
-        systemMsg.content = `${this.instruction}\n\n${systemMsg.content}`;
-      } else if (Array.isArray(systemMsg.content)) {
-        systemMsg.content.unshift({
-          type: 'text',
-          text: this.instruction
-        });
-      }
-
-      return modifiedMessages;
-    }
-
-    // Strategy 2: Prepend to first user message
-    const userIndex = modifiedMessages.findIndex(m => m.role === 'user');
-    if (userIndex >= 0) {
-      const userMsg = modifiedMessages[userIndex];
-
-      if (typeof userMsg.content === 'string') {
-        userMsg.content = `${this.instruction}\n\n${userMsg.content}`;
-      } else if (Array.isArray(userMsg.content)) {
-        userMsg.content.unshift({
-          type: 'text',
-          text: this.instruction
-        });
-      }
-
-      return modifiedMessages;
-    }
-
-    // No system or user messages found (edge case)
-    return modifiedMessages;
-  }
-}
-
-module.exports = LocaleEnforcer;

package/bin/glmt/reasoning-enforcer.js

@@ -1,173 +0,0 @@
-#!/usr/bin/env node
-'use strict';
-
-/**
- * ReasoningEnforcer - Inject explicit reasoning instructions into prompts
- *
- * Purpose: Force GLM models to use structured reasoning output format (<reasoning_content>)
- * This complements API parameters (reasoning: true) with explicit prompt instructions.
- *
- * Usage:
- *   const enforcer = new ReasoningEnforcer({ enabled: true });
- *   const modifiedMessages = enforcer.injectInstruction(messages, thinkingConfig);
- *
- * Strategy:
- *   1. If system prompt exists: Prepend reasoning instruction
- *   2. If no system prompt: Prepend to first user message
- *   3. Select prompt template based on effort level (low/medium/high/max)
- *   4. Preserve message structure (string vs array content)
- */
-
-class ReasoningEnforcer {
-  constructor(options = {}) {
-    this.enabled = options.enabled ?? false; // Opt-in by default
-    this.prompts = options.prompts || this._getDefaultPrompts();
-  }
-
-  /**
-   * Inject reasoning instruction into messages
-   * @param {Array} messages - Messages array to modify
-   * @param {Object} thinkingConfig - { thinking: boolean, effort: string }
-   * @returns {Array} Modified messages array
-   */
-  injectInstruction(messages, thinkingConfig = {}) {
-    // Only inject if enabled or thinking explicitly requested
-    if (!this.enabled && !thinkingConfig.thinking) {
-      return messages;
-    }
-
-    // Clone messages to avoid mutation
-    const modifiedMessages = JSON.parse(JSON.stringify(messages));
-
-    // Select prompt based on effort level
-    const prompt = this._selectPrompt(thinkingConfig.effort || 'medium');
-
-    // Strategy 1: Inject into system prompt (preferred)
-    const systemIndex = modifiedMessages.findIndex(m => m.role === 'system');
-    if (systemIndex >= 0) {
-      const systemMsg = modifiedMessages[systemIndex];
-
-      if (typeof systemMsg.content === 'string') {
-        systemMsg.content = `${prompt}\n\n${systemMsg.content}`;
-      } else if (Array.isArray(systemMsg.content)) {
-        systemMsg.content.unshift({
-          type: 'text',
-          text: prompt
-        });
-      }
-
-      return modifiedMessages;
-    }
-
-    // Strategy 2: Prepend to first user message
-    const userIndex = modifiedMessages.findIndex(m => m.role === 'user');
-    if (userIndex >= 0) {
-      const userMsg = modifiedMessages[userIndex];
-
-      if (typeof userMsg.content === 'string') {
-        userMsg.content = `${prompt}\n\n${userMsg.content}`;
-      } else if (Array.isArray(userMsg.content)) {
-        userMsg.content.unshift({
-          type: 'text',
-          text: prompt
-        });
-      }
-
-      return modifiedMessages;
-    }
-
-    // No system or user messages found (edge case)
-    return modifiedMessages;
-  }
-
-  /**
-   * Select prompt template based on effort level
-   * @param {string} effort - 'low', 'medium', 'high', or 'max'
-   * @returns {string} Prompt template
-   * @private
-   */
-  _selectPrompt(effort) {
-    const normalizedEffort = effort.toLowerCase();
-    return this.prompts[normalizedEffort] || this.prompts.medium;
-  }
-
-  /**
-   * Get default prompt templates
-   * @returns {Object} Map of effort levels to prompts
-   * @private
-   */
-  _getDefaultPrompts() {
-    return {
-      low: `You are an expert reasoning model using GLM-4.6 architecture.
-
-CRITICAL: Before answering, write 2-3 sentences of reasoning in <reasoning_content> tags.
-
-OUTPUT FORMAT:
-<reasoning_content>
-(Brief analysis: what is the problem? what's the approach?)
-</reasoning_content>
-
-(Write your final answer here)`,
-
-      medium: `You are an expert reasoning model using GLM-4.6 architecture.
-
-CRITICAL REQUIREMENTS:
-1. Always think step-by-step before answering
-2. Write your reasoning process explicitly in <reasoning_content> tags
-3. Never skip your chain of thought, even for simple problems
-
-OUTPUT FORMAT:
-<reasoning_content>
-(Write your detailed thinking here: analyze the problem, explore approaches,
-evaluate trade-offs, and arrive at a conclusion)
-</reasoning_content>
-
-(Write your final answer here based on your reasoning above)`,
-
-      high: `You are an expert reasoning model using GLM-4.6 architecture.
-
-CRITICAL REQUIREMENTS:
-1. Think deeply and systematically before answering
-2. Write comprehensive reasoning in <reasoning_content> tags
-3. Explore multiple approaches and evaluate trade-offs
-4. Show all steps in your problem-solving process
-
-OUTPUT FORMAT:
-<reasoning_content>
-(Write exhaustive analysis here:
- - Problem decomposition
- - Multiple approach exploration
- - Trade-off analysis for each approach
- - Edge case consideration
- - Final conclusion with justification)
-</reasoning_content>
-
-(Write your final answer here based on your systematic reasoning above)`,
-
-      max: `You are an expert reasoning model using GLM-4.6 architecture.
-
-CRITICAL REQUIREMENTS:
-1. Think exhaustively from first principles
-2. Write extremely detailed reasoning in <reasoning_content> tags
-3. Analyze ALL possible angles, approaches, and edge cases
-4. Challenge your own assumptions and explore alternatives
-5. Provide rigorous justification for every claim
-
-OUTPUT FORMAT:
-<reasoning_content>
-(Write comprehensive analysis here:
- - First principles breakdown
- - Exhaustive approach enumeration
- - Comparative analysis of all approaches
- - Edge case and failure mode analysis
- - Assumption validation
- - Counter-argument consideration
- - Final conclusion with rigorous justification)
-</reasoning_content>
-
-(Write your final answer here based on your exhaustive reasoning above)`
-    };
-  }
-}
-
-module.exports = ReasoningEnforcer;

package/bin/glmt/sse-parser.js

@@ -1,96 +0,0 @@
-#!/usr/bin/env node
-'use strict';
-
-/**
- * SSEParser - Parse Server-Sent Events (SSE) stream
- *
- * Handles:
- * - Incomplete events across chunks
- * - Multiple events in single chunk
- * - Malformed data (skip gracefully)
- * - [DONE] marker
- *
- * Usage:
- *   const parser = new SSEParser();
- *   stream.on('data', chunk => {
- *     const events = parser.parse(chunk);
- *     events.forEach(event => { ... });
- *   });
- */
-class SSEParser {
-  constructor(options = {}) {
-    this.buffer = '';
-    this.eventCount = 0;
-    this.maxBufferSize = options.maxBufferSize || 1024 * 1024; // 1MB default
-  }
-
-  /**
-   * Parse chunk and extract SSE events
-   * @param {Buffer|string} chunk - Data chunk from stream
-   * @returns {Array<Object>} Array of parsed events
-   */
-  parse(chunk) {
-    this.buffer += chunk.toString();
-
-    // C-01 Fix: Prevent unbounded buffer growth (DoS protection)
-    if (this.buffer.length > this.maxBufferSize) {
-      throw new Error(`SSE buffer exceeded ${this.maxBufferSize} bytes (DoS protection)`);
-    }
-
-    const lines = this.buffer.split('\n');
-
-    // Keep incomplete line in buffer
-    this.buffer = lines.pop() || '';
-
-    const events = [];
-    let currentEvent = { event: 'message', data: '' };
-
-    for (const line of lines) {
-      if (line.startsWith('event: ')) {
-        currentEvent.event = line.substring(7).trim();
-      } else if (line.startsWith('data: ')) {
-        const data = line.substring(6);
-
-        if (data === '[DONE]') {
-          this.eventCount++;
-          events.push({
-            event: 'done',
-            data: null,
-            index: this.eventCount
-          });
-          currentEvent = { event: 'message', data: '' };
-        } else {
-          try {
-            currentEvent.data = JSON.parse(data);
-            this.eventCount++;
-            currentEvent.index = this.eventCount;
-            events.push(currentEvent);
-            currentEvent = { event: 'message', data: '' };
-          } catch (e) {
-            // H-01 Fix: Log parse errors for debugging
-            if (typeof console !== 'undefined' && console.error) {
-              console.error('[SSEParser] Malformed JSON event:', e.message, 'Data:', data.substring(0, 100));
-            }
-          }
-        }
-      } else if (line.startsWith('id: ')) {
-        currentEvent.id = line.substring(4).trim();
-      } else if (line.startsWith('retry: ')) {
-        currentEvent.retry = parseInt(line.substring(7), 10);
-      }
-      // Empty lines separate events (already handled by JSON parsing)
-    }
-
-    return events;
-  }
-
-  /**
-   * Reset parser state (for reuse)
-   */
-  reset() {
-    this.buffer = '';
-    this.eventCount = 0;
-  }
-}
-
-module.exports = SSEParser;