fix hardcoded values part 5

src/services/llm/constants/search_constants.ts

@@ -47,6 +47,7 @@ export const SEARCH_CONSTANTS = {
     // Token/char limits
     LIMITS: {
         DEFAULT_NOTE_SUMMARY_LENGTH: 500,
+        DEFAULT_MAX_TOKENS: 4096,
         RELATIONSHIP_TOOL_MAX_TOKENS: 50,
         VECTOR_SEARCH_MAX_TOKENS: 500,
         QUERY_PROCESSOR_MAX_TOKENS: 300,

src/services/llm/context_extractors/note_navigator_tool.ts

@@ -289,7 +289,7 @@ export class NoteNavigatorTool {
   /**
    * Search for notes by title
    */
-  searchNotesByTitle(searchTerm: string, limit: number = 10): NoteInfo[] {
+  searchNotesByTitle(searchTerm: string, limit: number = SEARCH_CONSTANTS.HIERARCHY.MAX_NOTES_PER_QUERY): NoteInfo[] {
     try {
       if (!searchTerm || searchTerm.trim().length === 0) {
         return [];
@@ -369,14 +369,14 @@ export class NoteNavigatorTool {
       if (paths.length > 1) {
         result += `This note appears in ${paths.length} different locations:\n`;
 
-        // Show max 3 paths to avoid overwhelming context
+        // Show max paths to avoid overwhelming context
-        for (let i = 0; i < Math.min(3, paths.length); i++) {
+        for (let i = 0; i < Math.min(SEARCH_CONSTANTS.HIERARCHY.MAX_PATHS_TO_SHOW, paths.length); i++) {
           const path = paths[i];
           result += `${i+1}. ${path.notePathTitles.join(' > ')}\n`;
         }
 
-        if (paths.length > 3) {
+        if (paths.length > SEARCH_CONSTANTS.HIERARCHY.MAX_PATHS_TO_SHOW) {
-          result += `... and ${paths.length - 3} more locations\n`;
+          result += `... and ${paths.length - SEARCH_CONSTANTS.HIERARCHY.MAX_PATHS_TO_SHOW} more locations\n`;
         }
       } else {
         // Just one path
@@ -385,7 +385,7 @@ export class NoteNavigatorTool {
       }
 
       // Children info using the async function
-      const children = await this.getChildNotes(noteId, 5);
+      const children = await this.getChildNotes(noteId, SEARCH_CONSTANTS.CONTEXT.MAX_POINTS);
 
       if (children.length > 0) {
         result += `\nContains ${note.children.length} child notes`;
@@ -520,7 +520,7 @@ export class NoteNavigatorTool {
   /**
    * Get child notes of a specified note
    */
-  async getChildNotes(noteId: string, limit: number = 10): Promise<Array<{noteId: string, title: string}>> {
+  async getChildNotes(noteId: string, limit: number = SEARCH_CONSTANTS.CONTEXT.MAX_CHILDREN): Promise<Array<{noteId: string, title: string}>> {
     try {
       const note = becca.notes[noteId];
 
@@ -564,7 +564,7 @@ export class NoteNavigatorTool {
   /**
    * Find notes linked to/from the specified note
    */
-  async getLinkedNotes(noteId: string, limit: number = 10): Promise<Array<{noteId: string, title: string, direction: 'from'|'to'}>> {
+  async getLinkedNotes(noteId: string, limit: number = SEARCH_CONSTANTS.CONTEXT.MAX_LINKS): Promise<Array<{noteId: string, title: string, direction: 'from'|'to'}>> {
     try {
       const note = becca.notes[noteId];
 

src/services/llm/embeddings/chunking/chunking_processor.ts

@@ -5,6 +5,7 @@ import becca from "../../../../becca/becca.js";
 import cls from "../../../../services/cls.js";
 import type { NoteEmbeddingContext } from "../types.js";
 import { LLM_CONSTANTS } from "../../../llm/constants/provider_constants.js";
+import { EMBEDDING_PROCESSING } from '../../constants/search_constants.js';
 
 // Define error categories for better handling
 const ERROR_CATEGORIES = {
@@ -27,14 +28,14 @@ const ERROR_CATEGORIES = {
 };
 
 // Maximum time (in milliseconds) allowed for the entire chunking process
-const MAX_TOTAL_PROCESSING_TIME = 5 * 60 * 1000; // 5 minutes
+const MAX_TOTAL_PROCESSING_TIME = EMBEDDING_PROCESSING.MAX_TOTAL_PROCESSING_TIME;
 
 // Maximum number of retry attempts per chunk
-const MAX_CHUNK_RETRY_ATTEMPTS = 2;
+const MAX_CHUNK_RETRY_ATTEMPTS = EMBEDDING_PROCESSING.MAX_CHUNK_RETRY_ATTEMPTS;
 
 // Maximum time per chunk processing (to prevent individual chunks from hanging)
-const DEFAULT_MAX_CHUNK_PROCESSING_TIME = 60 * 1000; // 1 minute
+const DEFAULT_MAX_CHUNK_PROCESSING_TIME = EMBEDDING_PROCESSING.DEFAULT_MAX_CHUNK_PROCESSING_TIME;
-const OLLAMA_MAX_CHUNK_PROCESSING_TIME = 120 * 1000; // 2 minutes
+const OLLAMA_MAX_CHUNK_PROCESSING_TIME = EMBEDDING_PROCESSING.OLLAMA_MAX_CHUNK_PROCESSING_TIME;
 
 /**
  * Categorize an error as temporary or permanent based on its message

src/services/llm/embeddings/providers/openai.ts

@@ -5,6 +5,7 @@ import { NormalizationStatus } from "../embeddings_interface.js";
 import { LLM_CONSTANTS } from "../../constants/provider_constants.js";
 import type { EmbeddingModelInfo } from "../../interfaces/embedding_interfaces.js";
 import OpenAI from "openai";
+import { PROVIDER_EMBEDDING_CAPABILITIES } from '../../constants/search_constants.js';
 
 /**
  * OpenAI embedding provider implementation using the official SDK
@@ -40,7 +41,7 @@ export class OpenAIEmbeddingProvider extends BaseEmbeddingProvider {
             if (!this.client && this.apiKey) {
                 this.initClient();
             }
-            
+
             // Detect model capabilities
             const modelInfo = await this.getModelInfo(modelName);
 
@@ -64,7 +65,7 @@ export class OpenAIEmbeddingProvider extends BaseEmbeddingProvider {
         try {
             // Get model details using the SDK
             const model = await this.client.models.retrieve(modelName);
-            
+
             if (model) {
                 // Different model families may have different ways of exposing context window
                 let contextWindow = 0;
@@ -72,7 +73,7 @@ export class OpenAIEmbeddingProvider extends BaseEmbeddingProvider {
 
                 // Extract context window if available from the response
                 const modelData = model as any;
-                
+
                 if (modelData.context_window) {
                     contextWindow = modelData.context_window;
                 } else if (modelData.limits && modelData.limits.context_window) {
@@ -90,15 +91,11 @@ export class OpenAIEmbeddingProvider extends BaseEmbeddingProvider {
 
                 // If we didn't get all the info, use defaults for missing values
                 if (!contextWindow) {
-                    // Set default context window based on model name patterns
+                    // Set contextWindow based on model name patterns
-                    if (modelName.includes('ada') || modelName.includes('embedding-ada')) {
+                    if (modelName.includes('embedding-3')) {
-                        contextWindow = LLM_CONSTANTS.CONTEXT_WINDOW.OPENAI;
+                        contextWindow = PROVIDER_EMBEDDING_CAPABILITIES.OPENAI.MODELS['text-embedding-3-small'].contextWindow;
-                    } else if (modelName.includes('davinci')) {
-                        contextWindow = 8192;
-                    } else if (modelName.includes('embedding-3')) {
-                        contextWindow = 8191;
                     } else {
-                        contextWindow = LLM_CONSTANTS.CONTEXT_WINDOW.OPENAI;
+                        contextWindow = PROVIDER_EMBEDDING_CAPABILITIES.OPENAI.MODELS.default.contextWindow;
                     }
                 }
 
@@ -107,11 +104,11 @@ export class OpenAIEmbeddingProvider extends BaseEmbeddingProvider {
                     if (modelName.includes('ada') || modelName.includes('embedding-ada')) {
                         dimension = LLM_CONSTANTS.EMBEDDING_DIMENSIONS.OPENAI.ADA;
                     } else if (modelName.includes('embedding-3-small')) {
-                        dimension = 1536;
+                        dimension = PROVIDER_EMBEDDING_CAPABILITIES.OPENAI.MODELS['text-embedding-3-small'].dimension;
                     } else if (modelName.includes('embedding-3-large')) {
-                        dimension = 3072;
+                        dimension = PROVIDER_EMBEDDING_CAPABILITIES.OPENAI.MODELS['text-embedding-3-large'].dimension;
                     } else {
-                        dimension = LLM_CONSTANTS.EMBEDDING_DIMENSIONS.OPENAI.DEFAULT;
+                        dimension = PROVIDER_EMBEDDING_CAPABILITIES.OPENAI.MODELS.default.dimension;
                     }
                 }
 
@@ -155,7 +152,7 @@ export class OpenAIEmbeddingProvider extends BaseEmbeddingProvider {
             const dimension = testEmbedding.length;
 
             // Use default context window
-            let contextWindow = LLM_CONSTANTS.CONTEXT_WINDOW.OPENAI;
+            let contextWindow = PROVIDER_EMBEDDING_CAPABILITIES.OPENAI.MODELS.default.contextWindow;
 
             const modelInfo: EmbeddingModelInfo = {
                 name: modelName,
@@ -170,8 +167,8 @@ export class OpenAIEmbeddingProvider extends BaseEmbeddingProvider {
             return modelInfo;
         } catch (error: any) {
             // If detection fails, use defaults
-            const dimension = LLM_CONSTANTS.EMBEDDING_DIMENSIONS.OPENAI.DEFAULT;
+            const dimension = PROVIDER_EMBEDDING_CAPABILITIES.OPENAI.MODELS.default.dimension;
-            const contextWindow = LLM_CONSTANTS.CONTEXT_WINDOW.OPENAI;
+            const contextWindow = PROVIDER_EMBEDDING_CAPABILITIES.OPENAI.MODELS.default.contextWindow;
 
             log.info(`Using default parameters for OpenAI model ${modelName}: dimension ${dimension}, context ${contextWindow}`);
 
@@ -209,7 +206,7 @@ export class OpenAIEmbeddingProvider extends BaseEmbeddingProvider {
                 input: text,
                 encoding_format: "float"
             });
-            
+
             if (response && response.data && response.data[0] && response.data[0].embedding) {
                 return new Float32Array(response.data[0].embedding);
             } else {
@@ -258,7 +255,7 @@ export class OpenAIEmbeddingProvider extends BaseEmbeddingProvider {
             input: texts,
             encoding_format: "float"
         });
-        
+
         if (response && response.data) {
             // Sort the embeddings by index to ensure they match the input order
             const sortedEmbeddings = response.data

src/services/llm/embeddings/providers/voyage.ts

@@ -51,21 +51,17 @@ export class VoyageEmbeddingProvider extends BaseEmbeddingProvider {
      */
     private async fetchModelCapabilities(modelName: string): Promise<EmbeddingModelInfo | null> {
         try {
-            // Get context window size from our local registry of known models
+            // Find the closest matching model
-            const modelBase = Object.keys(VOYAGE_MODEL_CONTEXT_WINDOWS).find(
+            const modelMapKey = Object.keys(PROVIDER_EMBEDDING_CAPABILITIES.VOYAGE.MODELS).find(
                 model => modelName.startsWith(model)
             ) || "default";
 
-            const modelInfo = VOYAGE_MODEL_CONTEXT_WINDOWS[modelBase as keyof typeof VOYAGE_MODEL_CONTEXT_WINDOWS];
+            // Use as keyof to tell TypeScript this is a valid key
-            const contextWindow = modelInfo.contextWidth;
+            const modelInfo = PROVIDER_EMBEDDING_CAPABILITIES.VOYAGE.MODELS[modelMapKey as keyof typeof PROVIDER_EMBEDDING_CAPABILITIES.VOYAGE.MODELS];
-
-            // Get dimension from our registry of known models
-            const dimension = VOYAGE_MODEL_DIMENSIONS[modelBase as keyof typeof VOYAGE_MODEL_DIMENSIONS] ||
-                              VOYAGE_MODEL_DIMENSIONS["default"];
 
             return {
-                dimension,
+                dimension: modelInfo.dimension,
-                contextWidth: contextWindow,
+                contextWidth: modelInfo.contextWidth,
                 name: modelName,
                 type: 'float32'
             };
@@ -86,8 +82,9 @@ export class VoyageEmbeddingProvider extends BaseEmbeddingProvider {
 
         // Try to determine model capabilities
         const capabilities = await this.fetchModelCapabilities(modelName);
-        const contextWindow = capabilities?.contextWidth || 8192; // Default context window for Voyage
+        const defaults = PROVIDER_EMBEDDING_CAPABILITIES.VOYAGE.MODELS.default;
-        const knownDimension = capabilities?.dimension || 1024; // Default dimension for Voyage models
+        const contextWindow = capabilities?.contextWidth || defaults.contextWidth;
+        const knownDimension = capabilities?.dimension || defaults.dimension;
 
         // For Voyage, we can use known dimensions or detect with a test call
         try {
@@ -166,7 +163,7 @@ export class VoyageEmbeddingProvider extends BaseEmbeddingProvider {
             const modelInfo = await this.getModelInfo(modelName);
 
             // Trim text if it might exceed context window (rough character estimate)
-            const charLimit = (modelInfo.contextWidth || 8192) * 4; // Rough estimate: avg 4 chars per token
+            const charLimit = (modelInfo.contextWidth || PROVIDER_EMBEDDING_CAPABILITIES.VOYAGE.MODELS.default.contextWidth) * 4; // Rough estimate: avg 4 chars per token
             const trimmedText = text.length > charLimit ? text.substring(0, charLimit) : text;
 
             const response = await fetch(`${this.baseUrl}/embeddings`, {

src/services/llm/embeddings/storage.ts

@@ -7,6 +7,7 @@ import type { EmbeddingResult } from "./types.js";
 import entityChangesService from "../../../services/entity_changes.js";
 import type { EntityChange } from "../../../services/entity_changes_interface.js";
 import { EMBEDDING_CONSTANTS } from "../constants/embedding_constants.js";
+import { SEARCH_CONSTANTS } from '../constants/search_constants.js';
 /**
  * Creates or updates an embedding for a note
  */
@@ -139,14 +140,14 @@ export async function findSimilarNotes(
     embedding: Float32Array,
     providerId: string,
     modelId: string,
-    limit = 10,
+    limit = SEARCH_CONSTANTS.VECTOR_SEARCH.DEFAULT_MAX_RESULTS,
     threshold?: number,  // Made optional to use constants
     useFallback = true   // Whether to try other providers if no embeddings found
 ): Promise<{noteId: string, similarity: number, contentType?: string}[]> {
     // Import constants dynamically to avoid circular dependencies
     const llmModule = await import('../../../routes/api/llm.js');
-    // Use a default threshold of 0.65 if not provided
+    // Use default threshold if not provided
-    const actualThreshold = threshold || 0.65;
+    const actualThreshold = threshold || SEARCH_CONSTANTS.VECTOR_SEARCH.EXACT_MATCH_THRESHOLD;
 
     try {
         log.info(`Finding similar notes with provider: ${providerId}, model: ${modelId}, dimension: ${embedding.length}, threshold: ${actualThreshold}`);

src/services/llm/embeddings/vector_utils.ts

@@ -1,3 +1,5 @@
+import { SEARCH_CONSTANTS } from '../constants/search_constants.js';
+
 /**
  * Computes the cosine similarity between two vectors
  * If dimensions don't match, automatically adapts using the enhanced approach
@@ -549,9 +551,9 @@ export function ensembleSimilarity(
 ): number {
     // Default weights if not provided
     const weights = options.ensembleWeights ?? {
-        [SimilarityMetric.COSINE]: 0.6,
+        [SimilarityMetric.COSINE]: SEARCH_CONSTANTS.VECTOR_SEARCH.SIMILARITY_THRESHOLD.COSINE,
-        [SimilarityMetric.HYBRID]: 0.3,
+        [SimilarityMetric.HYBRID]: SEARCH_CONSTANTS.VECTOR_SEARCH.SIMILARITY_THRESHOLD.HYBRID,
-        [SimilarityMetric.DIM_AWARE]: 0.1
+        [SimilarityMetric.DIM_AWARE]: SEARCH_CONSTANTS.VECTOR_SEARCH.SIMILARITY_THRESHOLD.DIM_AWARE
     };
 
     let totalWeight = 0;

src/services/llm/providers/anthropic_service.ts

@@ -6,6 +6,7 @@ import type { AnthropicOptions } from './provider_options.js';
 import { getAnthropicOptions } from './providers.js';
 import log from '../../log.js';
 import Anthropic from '@anthropic-ai/sdk';
+import { SEARCH_CONSTANTS } from '../constants/search_constants.js';
 
 export class AnthropicService extends BaseAIService {
     private client: any = null;
@@ -78,7 +79,7 @@ export class AnthropicService extends BaseAIService {
                 model: providerOptions.model,
                 messages: anthropicMessages,
                 system: systemPrompt,
-                max_tokens: providerOptions.max_tokens || 4096,
+                max_tokens: providerOptions.max_tokens || SEARCH_CONSTANTS.LIMITS.DEFAULT_MAX_TOKENS,
                 temperature: providerOptions.temperature,
                 top_p: providerOptions.top_p,
                 stream: !!providerOptions.stream

src/services/llm/rest_chat_service.ts

@@ -355,7 +355,7 @@ class RestChatService {
                     createdAt: now,
                     lastActive: now,
                     metadata: {
-                        temperature: 0.7,
+                        temperature: SEARCH_CONSTANTS.TEMPERATURE.DEFAULT,
                         maxTokens: undefined,
                         model: undefined,
                         provider: undefined
@@ -1645,7 +1645,7 @@ class RestChatService {
                 lastActive: now,
                 noteContext: options.contextNoteId,
                 metadata: {
-                    temperature: options.temperature,
+                    temperature: SEARCH_CONSTANTS.TEMPERATURE.DEFAULT,
                     maxTokens: options.maxTokens,
                     model: options.model,
                     provider: options.provider,

src/services/llm/tools/note_summarization_tool.ts

@@ -8,6 +8,7 @@ import type { Tool, ToolHandler } from './tool_interfaces.js';
 import log from '../../log.js';
 import becca from '../../../becca/becca.js';
 import aiServiceManager from '../ai_service_manager.js';
+import { SEARCH_CONSTANTS } from '../constants/search_constants.js';
 
 /**
  * Definition of the note summarization tool
@@ -59,7 +60,7 @@ export class NoteSummarizationTool implements ToolHandler {
         focus?: string
     }): Promise<string | object> {
         try {
-            const { noteId, maxLength = 500, format = 'paragraph', focus } = args;
+            const { noteId, maxLength = SEARCH_CONSTANTS.LIMITS.DEFAULT_NOTE_SUMMARY_LENGTH, format = 'paragraph', focus } = args;
 
             log.info(`Executing summarize_note tool - NoteID: "${noteId}", MaxLength: ${maxLength}, Format: ${format}`);
 
@@ -134,8 +135,8 @@ export class NoteSummarizationTool implements ToolHandler {
                 { role: 'system', content: 'You are a skilled summarizer. Create concise, accurate summaries while preserving the key information.' },
                 { role: 'user', content: prompt }
             ], {
-                temperature: 0.3, // Lower temperature for more focused summaries
+                temperature: SEARCH_CONSTANTS.TEMPERATURE.VECTOR_SEARCH, // Lower temperature for more focused summaries
-                maxTokens: 1000 // Enough tokens for the summary
+                maxTokens: SEARCH_CONSTANTS.LIMITS.VECTOR_SEARCH_MAX_TOKENS // Enough tokens for the summary
             });
 
             const summaryDuration = Date.now() - summaryStartTime;