rp/pr/core/advanced_context.py

import re
from typing import Any, Dict, List


class AdvancedContextManager:
    def __init__(self, knowledge_store=None, conversation_memory=None):
        self.knowledge_store = knowledge_store
        self.conversation_memory = conversation_memory

    def adaptive_context_window(self, messages: List[Dict[str, Any]], complexity: str) -> int:
        """Calculate adaptive context window size based on message complexity."""
        base_window = 10

        complexity_multipliers = {
            "simple": 1.0,
            "medium": 2.0,
            "complex": 3.5,
            "very_complex": 5.0,
        }

        multiplier = complexity_multipliers.get(complexity, 2.0)
        return int(base_window * multiplier)

    def _analyze_message_complexity(self, messages: List[Dict[str, Any]]) -> float:
        """Analyze the complexity of messages and return a score between 0.0 and 1.0."""
        if not messages:
            return 0.0

        total_complexity = 0.0
        for message in messages:
            content = message.get("content", "")
            if not content:
                continue

            # Calculate complexity based on various factors
            word_count = len(content.split())
            sentence_count = len(re.split(r"[.!?]+", content))
            avg_word_length = sum(len(word) for word in content.split()) / max(word_count, 1)

            # Complexity score based on length, vocabulary, and structure
            length_score = min(1.0, word_count / 100)  # Normalize to 0-1
            structure_score = min(1.0, sentence_count / 10)
            vocabulary_score = min(1.0, avg_word_length / 8)

            message_complexity = (length_score + structure_score + vocabulary_score) / 3
            total_complexity += message_complexity

        return min(1.0, total_complexity / len(messages))

    def extract_key_sentences(self, text: str, top_k: int = 5) -> List[str]:
        if not text.strip():
            return []
        sentences = re.split(r"(?<=[.!?])\s+", text)
        if not sentences:
            return []

        # Simple scoring based on length and position
        scored_sentences = []
        for i, sentence in enumerate(sentences):
            length_score = min(1.0, len(sentence) / 50)
            position_score = 1.0 if i == 0 else 0.8 if i < len(sentences) / 2 else 0.6
            score = (length_score + position_score) / 2
            scored_sentences.append((sentence, score))

        scored_sentences.sort(key=lambda x: x[1], reverse=True)
        return [s[0] for s in scored_sentences[:top_k]]

    def advanced_summarize_messages(self, messages: List[Dict[str, Any]]) -> str:
        all_content = " ".join([msg.get("content", "") for msg in messages])
        key_sentences = self.extract_key_sentences(all_content, top_k=3)
        summary = " ".join(key_sentences)
        return summary if summary else "No content to summarize."

    def score_message_relevance(self, message: Dict[str, Any], context: str) -> float:
        content = message.get("content", "")
        content_words = set(re.findall(r"\b\w+\b", content.lower()))
        context_words = set(re.findall(r"\b\w+\b", context.lower()))

        intersection = content_words & context_words
        union = content_words | context_words

        if not union:
            return 0.0

        return len(intersection) / len(union)

    def create_enhanced_context(
        self, messages: List[Dict[str, Any]], user_message: str, include_knowledge: bool = True
    ) -> tuple:
        """Create enhanced context with knowledge base integration."""
        working_messages = messages.copy()

        if include_knowledge and self.knowledge_store:
            # Search knowledge base for relevant information
            search_results = self.knowledge_store.search_entries(user_message, top_k=3)

            if search_results:
                knowledge_parts = []
                for idx, entry in enumerate(search_results, 1):
                    content = entry.content
                    if len(content) > 2000:
                        content = content[:2000] + "..."

                    knowledge_parts.append(f"Match {idx} (Category: {entry.category}):\n{content}")

                knowledge_message_content = (
                    "[KNOWLEDGE_BASE_CONTEXT]\nRelevant knowledge base entries:\n\n"
                    + "\n\n".join(knowledge_parts)
                )

                knowledge_message = {"role": "user", "content": knowledge_message_content}
                working_messages.append(knowledge_message)

                context_info = f"Added {len(search_results)} knowledge base entries"
            else:
                context_info = "No relevant knowledge base entries found"
        else:
            context_info = "Knowledge base integration disabled"

        return working_messages, context_info