codexa 1.2.1 → 1.2.2

package/README.md

@@ -58,6 +58,8 @@
 - ⚙️ **Highly Configurable**: Fine-tune chunking, retrieval, and model parameters
 - 🚀 **Zero Setup**: Works out of the box with sensible defaults
 
+> ⚠️ **Codebase Size Limitation**: Codexa is optimized for small to medium-sized codebases. It currently supports projects with up to **200 files** and **20,000 chunks**. For larger codebases, consider using more restrictive `includeGlobs` patterns to focus on specific directories or file types.
+
 ## Installation
 
 ### Prerequisites
@@ -165,15 +167,15 @@ Codexa defaults to using Groq when you run `codexa init`. If you need to manuall
 ```json
 {
   "modelProvider": "groq",
-  "model": "llama-3.1-8b-instant",
+  "model": "openai/gpt-oss-120b",
   "embeddingProvider": "local",
   "embeddingModel": "Xenova/all-MiniLM-L6-v2"
 }
 ```
 
-**Available Groq Models:**
-- `llama-3.1-8b-instant` - Fast responses (recommended, default)
-- `llama-3.1-70b-versatile` - Higher quality, slower
+**Models you can use:**
+- `openai/gpt-oss-120b` (recommended, default)
+- `llama-3.1-70b-versatile`
 
 
 
@@ -429,7 +431,7 @@ The LLM provider to use for generating answers.
 
 **Type:** `string`  
 **Type:** `string`  
-**Default:** `"llama-3.1-8b-instant"`
+**Default:** `"openai/gpt-oss-120b"`
 
 The model identifier to use.
 
@@ -585,7 +587,7 @@ Whether to skip files exceeding `maxFileSize` during indexing. Set to `false` if
 ```json
 {
   "modelProvider": "groq",
-  "model": "llama-3.1-8b-instant",
+  "model": "openai/gpt-oss-120b",
   "embeddingProvider": "local",
   "embeddingModel": "Xenova/all-MiniLM-L6-v2",
   "maxChunkSize": 300,
@@ -607,7 +609,7 @@ codexa config set GROQ_API_KEY "your-api-key"
 ```json
 {
   "modelProvider": "groq",
-  "model": "llama-3.1-8b-instant",
+  "model": "openai/gpt-oss-120b",
   "maxChunkSize": 150,
   "chunkOverlap": 15,
   "topK": 6,

package/dist/cli.js

@@ -74,7 +74,7 @@ const program = new commander_1.Command();
 program
     .name('codexa')
     .description('Ask questions about any local repository from the command line.')
-    .version('1.2.1')
+    .version('1.2.2')
     .action(() => {
     showBanner();
 });

package/dist/config/generator.js

@@ -352,7 +352,7 @@ function generateConfig(analysis, baseConfig) {
     // Start with base config or defaults
     const config = {
         modelProvider: 'groq',
-        model: 'llama-3.1-8b-instant',
+        model: 'openai/gpt-oss-120b',
         embeddingProvider: 'local',
         embeddingModel: 'Xenova/all-MiniLM-L6-v2',
         maxChunkSize: 800,

package/dist/config.js

@@ -17,7 +17,7 @@ dotenv_1.default.config();
 exports.CONFIG_FILENAME = '.codexarc.json';
 const DEFAULT_CONFIG = {
     modelProvider: 'groq',
-    model: 'llama-3.1-8b-instant', // can also use llama-3.3-70b-versatile for better perf
+    model: 'openai/gpt-oss-120b', // can also use llama-3.3-70b-versatile for better perf
     embeddingProvider: 'local',
     embeddingModel: 'Xenova/all-MiniLM-L6-v2',
     // localModelUrl: 'http://localhost:11434',

package/dist/ingest.js

@@ -92,6 +92,10 @@ async function ingestRepository({ cwd, config, force = false, }) {
         spinnerFiles.fail('No matching files found.');
         return;
     }
+    if (allFiles.length > 200) {
+        spinnerFiles.stop();
+        throw new Error('Codebase is too large, cannot index it');
+    }
     // Filter files: exclude binaries and large files
     spinnerFiles.text = `Filtering files (found ${allFiles.length})...`;
     const { included: files, excluded } = await (0, file_filter_1.filterFiles)(allFiles, {
@@ -124,6 +128,10 @@ async function ingestRepository({ cwd, config, force = false, }) {
         }
         await tick();
     }
+    if (chunks.length > 20000) {
+        spinnerChunk.stop();
+        throw new Error('Chunk limit exceeded, unable to create embeddings!');
+    }
     spinnerChunk.succeed(`Chunked files (${chunks.length} chunks)`);
     const spinnerCompress = (0, ora_1.default)('Compressing chunks...').start();
     chunks.forEach((c) => (c.compressed = compressText(c.content)));

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "codexa",
-  "version": "1.2.1",
+  "version": "1.2.2",
   "description": "CLI agent that indexes local repos and answers questions with hosted or local LLMs.",
   "bin": {
     "codexa": "bin/codexa.js"