feat(core): make chunk limit configurable via CHUNK_LIMIT environment variable

.env.example

@@ -20,6 +20,9 @@ EMBEDDING_MODEL=text-embedding-3-small
 # You can customize it according to the throughput of your embedding model. Generally, larger batch size means less indexing time.
 EMBEDDING_BATCH_SIZE=100
 
+# Maximum number of chunks to process during indexing (default: 450000)
+# CHUNK_LIMIT=450000
+
 # =============================================================================
 # OpenAI Configuration
 # =============================================================================

docs/getting-started/environment-variables.md

@@ -60,6 +60,7 @@ Claude Context supports a global configuration file at `~/.context/.env` to simp
 |----------|-------------|---------|
 | `HYBRID_MODE` | Enable hybrid search (BM25 + dense vector). Set to `false` for dense-only search | `true` |
 | `EMBEDDING_BATCH_SIZE` | Batch size for processing. Larger batch size means less indexing time | `100` |
+| `CHUNK_LIMIT` | Maximum number of chunks to process during indexing | `450000` |
 | `SPLITTER_TYPE` | Code splitter type: `ast`, `langchain` | `ast` |
 | `CUSTOM_EXTENSIONS` | Additional file extensions to include (comma-separated, e.g., `.vue,.svelte,.astro`) | None |
 | `CUSTOM_IGNORE_PATTERNS` | Additional ignore patterns (comma-separated, e.g., `temp/**,*.backup,private/**`) | None |

packages/core/src/context.ts

@@ -702,8 +702,9 @@ export class Context {
     ): Promise<{ processedFiles: number; totalChunks: number; status: 'completed' | 'limit_reached' }> {
         const isHybrid = this.getIsHybrid();
         const EMBEDDING_BATCH_SIZE = Math.max(1, parseInt(envManager.get('EMBEDDING_BATCH_SIZE') || '100', 10));
-        const CHUNK_LIMIT = 450000;
+        const CHUNK_LIMIT = Math.max(1, parseInt(envManager.get('CHUNK_LIMIT') || '450000', 10));
         console.log(`[Context] 🔧 Using EMBEDDING_BATCH_SIZE: ${EMBEDDING_BATCH_SIZE}`);
+        console.log(`[Context] 🔧 Using CHUNK_LIMIT: ${CHUNK_LIMIT}`);
 
         let chunkBuffer: Array<{ chunk: CodeChunk; codebasePath: string }> = [];
         let processedFiles = 0;

packages/mcp/src/config.ts

@@ -203,6 +203,12 @@ Environment Variables:
   MILVUS_ADDRESS          Milvus address (optional, can be auto-resolved from token)
   MILVUS_TOKEN            Milvus token (optional, used for authentication and address resolution)
 
+  Advanced Configuration:
+  EMBEDDING_BATCH_SIZE    Batch size for processing (default: 100)
+  CHUNK_LIMIT             Maximum number of chunks to process during indexing (default: 450000)
+  HYBRID_MODE             Enable hybrid search (default: true)
+  SPLITTER_TYPE           Code splitter type: ast, langchain (default: ast)
+
 Examples:
   # Start MCP server with OpenAI (default) and explicit Milvus address
   OPENAI_API_KEY=sk-xxx MILVUS_ADDRESS=localhost:19530 npx @zilliz/claude-context-mcp@latest