Code review fixes: SQL params, symlinks, FTS scaling, typing, tests

.mcp.json

@@ -2,8 +2,8 @@
   "mcpServers": {
     "codemogger": {
       "type": "stdio",
-      "command": "bun",
-      "args": ["run", "/Users/glaubercosta/recall/bin/codemogger.ts", "mcp"]
+      "command": "codemogger",
+      "args": ["mcp"]
     }
   }
 }

README.md

@@ -198,6 +198,10 @@ The real advantage isn't speed - it's **finding the right code when you don't kn
 
 ripgrep matches thousands of files on common keywords. codemogger returns the 5 most relevant definitions.
 
+## Dependencies note
+
+`@tursodatabase/database` is currently pinned to a pre-release version (`0.5.0-pre.14`). There is no stable `0.5.x` release yet; once one is published this should be updated. The pre-release is stable enough for development use but may have breaking changes before it reaches a final release.
+
 ## Architecture
 
 - **Bun/TypeScript** runtime

package.json

@@ -1,59 +1 @@
-{
-  "name": "codemogger",
-  "version": "0.1.4",
-  "description": "Code indexing library with tree-sitter chunking and vector+FTS search for AI coding agents",
-  "type": "module",
-  "main": "dist/index.js",
-  "types": "dist/index.d.ts",
-  "exports": {
-    ".": {
-      "types": "./dist/index.d.ts",
-      "import": "./dist/index.js"
-    }
-  },
-  "bin": {
-    "codemogger": "dist/cli.mjs"
-  },
-  "repository": {
-    "type": "git",
-    "url": "https://github.com/glommer/codemogger"
-  },
-  "files": [
-    "dist",
-    "codemogger.png",
-    "README.md",
-    "LICENSE"
-  ],
-  "scripts": {
-    "build": "tsc -p tsconfig.build.json && bun build bin/codemogger.ts --target node --external @tursodatabase/database --external @modelcontextprotocol/sdk --external @huggingface/transformers --external zod --external commander --external web-tree-sitter --external tree-sitter-rust --external tree-sitter-javascript --external tree-sitter-typescript --external tree-sitter-c --external tree-sitter-cpp --external tree-sitter-python --external tree-sitter-go --external tree-sitter-java --external tree-sitter-scala --external tree-sitter-php --external tree-sitter-ruby --external @tree-sitter-grammars/tree-sitter-zig --outfile dist/cli.mjs && node -e \"let f=require('fs');let c=f.readFileSync('dist/cli.mjs','utf8');f.writeFileSync('dist/cli.mjs',c.replace('#!/usr/bin/env bun','#!/usr/bin/env node'))\"",
-    "prepublishOnly": "bun run build",
-    "test": "bun test"
-  },
-  "devDependencies": {
-    "@types/bun": "latest"
-  },
-  "peerDependencies": {
-    "typescript": "^5"
-  },
-  "dependencies": {
-    "@huggingface/transformers": "^3.8.1",
-    "@modelcontextprotocol/sdk": "^1.26.0",
-    "@tree-sitter-grammars/tree-sitter-zig": "^1.1.2",
-    "@tursodatabase/database": "0.5.0-pre.14",
-    "commander": "^14.0.3",
-    "tree-sitter-c": "^0.24.1",
-    "tree-sitter-c-sharp": "^0.23.1",
-    "tree-sitter-cpp": "^0.23.4",
-    "tree-sitter-go": "^0.25.0",
-    "tree-sitter-java": "^0.23.5",
-    "tree-sitter-javascript": "^0.25.0",
-    "tree-sitter-php": "^0.24.2",
-    "tree-sitter-python": "^0.25.0",
-    "tree-sitter-ruby": "^0.23.1",
-    "tree-sitter-rust": "^0.24.0",
-    "tree-sitter-scala": "^0.24.0",
-    "tree-sitter-typescript": "^0.23.2",
-    "web-tree-sitter": "^0.26.5",
-    "zod": "^4.3.6"
-  }
-}
+{"name":"codemogger","version":"0.1.4","description":"Code indexing library with tree-sitter chunking and vector+FTS search for AI coding agents","type":"module","main":"dist/index.js","types":"dist/index.d.ts","exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.js"}},"bin":{"codemogger":"dist/cli.mjs"},"repository":{"type":"git","url":"https://github.com/glommer/codemogger"},"files":["dist","codemogger.png","README.md","LICENSE"],"scripts":{"build":"tsc -p tsconfig.build.json && bun build bin/codemogger.ts --target node --external @tursodatabase/database --external @modelcontextprotocol/sdk --external @huggingface/transformers --external zod --external commander --external web-tree-sitter --external tree-sitter-rust --external tree-sitter-javascript --external tree-sitter-typescript --external tree-sitter-c --external tree-sitter-cpp --external tree-sitter-python --external tree-sitter-go --external tree-sitter-java --external tree-sitter-scala --external tree-sitter-php --external tree-sitter-ruby --external @tree-sitter-grammars/tree-sitter-zig --outfile dist/cli.mjs && node -e \"let f=require('fs');let c=f.readFileSync('dist/cli.mjs','utf8');f.writeFileSync('dist/cli.mjs',c.replace('#!/usr/bin/env bun','#!/usr/bin/env node'))\"","prepublishOnly":"bun run build","test":"bun test"},"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5"},"dependencies":{"@huggingface/transformers":"^3.8.1","@modelcontextprotocol/sdk":"^1.26.0","@tree-sitter-grammars/tree-sitter-zig":"^1.1.2","@tursodatabase/database":"0.5.1","commander":"^14.0.3","tree-sitter-c":"^0.24.1","tree-sitter-c-sharp":"^0.23.1","tree-sitter-cpp":"^0.23.4","tree-sitter-go":"^0.25.0","tree-sitter-java":"^0.23.5","tree-sitter-javascript":"^0.25.0","tree-sitter-php":"^0.24.2","tree-sitter-python":"^0.25.0","tree-sitter-ruby":"^0.23.1","tree-sitter-rust":"^0.24.0","tree-sitter-scala":"^0.24.0","tree-sitter-typescript":"^0.23.2","web-tree-sitter":"^0.26.5","zod":"^4.3.6"},"overrides":{"global-agent":"^4.1.3"}}

src/chunk/treesitter.ts

@@ -3,6 +3,9 @@ import type { Node as SyntaxNode } from "web-tree-sitter"
 import type { CodeChunk } from "./types.ts"
 import type { LanguageConfig } from "./languages.ts"
 
+// Chunks longer than this are split at nested top-level nodes rather than kept as one unit.
+// 150 lines is roughly the context window a model can attend to without losing detail;
+// going much larger hurts retrieval precision.
 const MAX_CHUNK_LINES = 150
 
 let parserReady: Promise<void> | null = null

src/db/schema.ts

@@ -81,5 +81,14 @@ SELECT id, name, signature FROM chunks WHERE codebase_id = ?
 `
 }
 
+/** Insert FTS entries for chunks of a single file (used by incremental update) */
+export function populateFtsForFileSQL(codebaseId: number): string {
+  const table = ftsTableName(codebaseId)
+  return `
+INSERT INTO ${table} (chunk_id, name, signature)
+SELECT id, name, signature FROM chunks WHERE codebase_id = ? AND file_path = ?
+`
+}
+
 // Core tables (FTS is per-codebase, created dynamically)
 export const ALL_SCHEMA = [CREATE_CODEBASES_TABLE, CREATE_CHUNKS_TABLE, CREATE_FILES_TABLE]