aizen-ai-cli 2.4.2__tar.gz → 2.5.0__tar.gz

{aizen_ai_cli-2.4.2 → aizen_ai_cli-2.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: aizen-ai-cli
-Version: 2.4.2
+Version: 2.5.0
 Summary: Aizen AI Agent — A professional-grade AI coding assistant for your terminal.
 Author: Irtaza Malik
 License: MIT
@@ -52,6 +52,7 @@ Aizen is a powerful, asynchronous AI assistant that integrates seamlessly into y
 - **Cost‑Aware Usage** — Real‑time cost estimation for all major LLMs.
 - **Persistent Sessions** — Save and restore conversations with checkpoints.
 - **Rich Visual Feedback** — Stream responses with live previews and animated thought indicators.
+- **Semantic Codebase Search** — Fast local RAG (Retrieval-Augmented Generation) using the `/search` command.
 - **Extensible Architecture** — Custom plugins and project‑specific rules tailor Aizen to your workflow.
 - **Comprehensive Logging** — Rotating logs with optional verbose output for debugging.
 
@@ -72,6 +73,9 @@ Aizen is a powerful, asynchronous AI assistant that integrates seamlessly into y
 ### Vision Support
 - Native image handling and encoding for Vision APIs (e.g., GPT‑4o, Claude 3.5 Sonnet).
 
+### Local Codebase RAG
+- Intelligent semantic search across your entire codebase using local embeddings and SQLite vector caching, accessible via the `/search` command and available to the agent.
+
 ### Real‑Time Command Streaming
 - Background command execution with async streaming of stdout/stderr; use `run_command --background`.
 
@@ -88,8 +92,10 @@ Aizen is a powerful, asynchronous AI assistant that integrates seamlessly into y
 - Current cost estimate shown in the CLI status bar.
 - Supports Anthropic (Claude 3.5/3.7 Sonnet, Opus, Haiku), Google (Gemini 2.5 Pro/Flash), and OpenAI (GPT‑4o, o1, o3‑mini).
 
-## 📌 Session Management
+## 📌 Session Management & Search
 
+- `/search [query]` — Perform semantic search across your codebase.
+- `/reindex [dir]` — Manually trigger indexing for local semantic search.
 - `/checkpoint [name]` — Save conversation snapshots.
 - `/restore [name]` — Restore a previous checkpoint.
 

{aizen_ai_cli-2.4.2 → aizen_ai_cli-2.5.0}/README.md

@@ -12,6 +12,7 @@ Aizen is a powerful, asynchronous AI assistant that integrates seamlessly into y
 - **Cost‑Aware Usage** — Real‑time cost estimation for all major LLMs.
 - **Persistent Sessions** — Save and restore conversations with checkpoints.
 - **Rich Visual Feedback** — Stream responses with live previews and animated thought indicators.
+- **Semantic Codebase Search** — Fast local RAG (Retrieval-Augmented Generation) using the `/search` command.
 - **Extensible Architecture** — Custom plugins and project‑specific rules tailor Aizen to your workflow.
 - **Comprehensive Logging** — Rotating logs with optional verbose output for debugging.
 
@@ -32,6 +33,9 @@ Aizen is a powerful, asynchronous AI assistant that integrates seamlessly into y
 ### Vision Support
 - Native image handling and encoding for Vision APIs (e.g., GPT‑4o, Claude 3.5 Sonnet).
 
+### Local Codebase RAG
+- Intelligent semantic search across your entire codebase using local embeddings and SQLite vector caching, accessible via the `/search` command and available to the agent.
+
 ### Real‑Time Command Streaming
 - Background command execution with async streaming of stdout/stderr; use `run_command --background`.
 
@@ -48,8 +52,10 @@ Aizen is a powerful, asynchronous AI assistant that integrates seamlessly into y
 - Current cost estimate shown in the CLI status bar.
 - Supports Anthropic (Claude 3.5/3.7 Sonnet, Opus, Haiku), Google (Gemini 2.5 Pro/Flash), and OpenAI (GPT‑4o, o1, o3‑mini).
 
-## 📌 Session Management
+## 📌 Session Management & Search
 
+- `/search [query]` — Perform semantic search across your codebase.
+- `/reindex [dir]` — Manually trigger indexing for local semantic search.
 - `/checkpoint [name]` — Save conversation snapshots.
 - `/restore [name]` — Restore a previous checkpoint.
 

{aizen_ai_cli-2.4.2 → aizen_ai_cli-2.5.0}/aizen/commands.py

@@ -6,9 +6,7 @@ import subprocess
 from datetime import datetime
 
 import questionary
-
 from prompt_toolkit.completion import Completer, Completion
-from prompt_toolkit import PromptSession
 from rich.table import Table
 
 from .config import (
@@ -47,6 +45,8 @@ SLASH_COMMANDS = [
     ("/commit", "Auto-generate and commit changes"),
     ("/diff", "Show all uncommitted changes"),
     ("/auto", "Enter autonomous agentic mode for a complex task"),
+    ("/search", "Search the codebase using semantic (RAG) search"),
+    ("/reindex", "Reindex the codebase for semantic search"),
 ]
 
 # In-memory checkpoint storage for conversation branching
@@ -69,7 +69,7 @@ class AizenCompleter(Completer):
         if stripped.startswith("/"):
             if " " not in stripped:
                 query = stripped.lower()
-                cmds_with_args = {"/model", "/save", "/load", "/export", "/checkpoint", "/restore"}
+                cmds_with_args = {"/model", "/save", "/load", "/export", "/checkpoint", "/restore", "/search", "/reindex"}
                 for cmd, description in SLASH_COMMANDS:
                     if cmd.startswith(query):
                         completion_text = cmd + " " if cmd in cmds_with_args else cmd
@@ -287,6 +287,11 @@ async def handle_slash_command(
         help_table.add_row("  🔀 /commit", "Auto-generate and commit changes")
         help_table.add_row("  📊 /diff", "Show all uncommitted changes")
 
+        # ── Search & RAG ──
+        help_table.add_row(f"[bold {Theme.MUTED}]── Search & RAG ──[/bold {Theme.MUTED}]", "")
+        help_table.add_row("  🔍 /search [query]", "Search the codebase using semantic (RAG) search")
+        help_table.add_row("  🔄 /reindex [dir]", "Reindex the codebase for semantic search")
+
         # ── Agent ──
         help_table.add_row(f"[bold {Theme.MUTED}]── Agent ──[/bold {Theme.MUTED}]", "")
         help_table.add_row("  🤖 /auto [task]", "Enter autonomous mode for a complex task (max iterations apply)")
@@ -732,6 +737,23 @@ async def handle_slash_command(
         except Exception as e:
             console.print(f"  [{Theme.ERROR}]Error showing diff: {e}[/{Theme.ERROR}]\n")
 
+    elif cmd == "/search":
+        from .rag import get_global_vector_store, get_global_embedding_generator, SlashCommandRunner
+        runner = SlashCommandRunner(get_global_vector_store(), get_global_embedding_generator())
+        runner.run(command_str, console)
+        console.print()
+
+    elif cmd == "/reindex":
+        import asyncio
+        from .rag import reindex_directory
+        target_dir = arg if arg else "."
+        console.print(f"  [{Theme.MUTED}]Re-indexing codebase directory '{target_dir}' in background...[/{Theme.MUTED}]")
+        try:
+            await asyncio.to_thread(reindex_directory, target_dir)
+            console.print(f"  [{Theme.SUCCESS}]✓ Reindexing complete.[/{Theme.SUCCESS}]\n")
+        except Exception as e:
+            console.print(f"  [{Theme.ERROR}]Error during reindexing: {e}[/{Theme.ERROR}]\n")
+
     else:
         console.print(
             f"  [{Theme.ERROR}]Unknown command: {cmd}[/{Theme.ERROR}] — type [bold {Theme.ACCENT}]/help[/bold {Theme.ACCENT}] for commands.\n"

{aizen_ai_cli-2.4.2 → aizen_ai_cli-2.5.0}/aizen/config.py

@@ -20,7 +20,7 @@ logger = logging.getLogger("aizen")
 
 # Read version from installed package metadata (stays in sync with pyproject.toml).
 # Falls back to a hardcoded value only when running from source without installing.
-_FALLBACK_VERSION = "2.4.2"
+_FALLBACK_VERSION = "2.5.0"
 try:
     VERSION = _pkg_version("aizen-ai-cli")
 except PackageNotFoundError:

{aizen_ai_cli-2.4.2 → aizen_ai_cli-2.5.0}/aizen/context.py

@@ -184,7 +184,7 @@ class ContextPruner:
         """
         import re
         dropped_count = 0
-        
+
         # Keep the system prompt and the last couple of turns intact
         if len(messages) <= 3:
             return 0
@@ -200,7 +200,7 @@ class ContextPruner:
                 if old_content != new_content:
                     msg["content"] = new_content
                     dropped_count += 1
-                    
+
         return dropped_count
 
     @staticmethod
@@ -215,20 +215,20 @@ class ContextPruner:
         system_msg = messages[0]
         recent = messages[-recent_count:]
         middle = messages[1:-recent_count]
-        
+
         user_topics = [
-            m["content"][:100].replace('\n', ' ') 
-            for m in middle 
+            m["content"][:100].replace('\n', ' ')
+            for m in middle
             if m.get("role") == "user" and m.get("content")
         ]
-        
+
         summary = "Previous conversation summary: The user and assistant discussed " + "; ".join(user_topics[:5]) + ". The assistant helped with these requests."
-        
+
         messages[:] = [
             system_msg,
             {"role": "user", "content": f"Previous conversation summary:\n{summary}"},
             {"role": "assistant", "content": "Understood. I have the context. How can I continue helping?"},
         ] + recent
-        
+
         return summary
 

{aizen_ai_cli-2.4.2 → aizen_ai_cli-2.5.0}/aizen/main.py

@@ -6,28 +6,20 @@ Aizen AI Agent — A professional-grade AI coding assistant for your terminal.
 import argparse
 import asyncio
 import base64
-import json
 import mimetypes
 import os
-import random
 import re
 import subprocess
 import sys
-from typing import Any
 
-from openai import APIConnectionError as OpenAIConnectionError
-from openai import APITimeoutError, AsyncOpenAI, AuthenticationError, BadRequestError
-from openai import RateLimitError as OpenAIRateLimitError
+from openai import AsyncOpenAI
 from prompt_toolkit import PromptSession
 from prompt_toolkit.filters import completion_is_selected, has_completions
 from prompt_toolkit.formatted_text import FormattedText
 from prompt_toolkit.key_binding import KeyBindings
 from prompt_toolkit.styles import Style
-from rich.live import Live
-from rich.markdown import Markdown
-from rich.spinner import Spinner
-from rich.text import Text
 
+from .agent import AgentRunner
 from .commands import AizenCompleter, handle_slash_command
 from .config import (
     AIZEN_ASCII,
@@ -52,9 +44,8 @@ from .mcp import MCPManager
 from .plugins import plugin_manager
 from .retry import retry_with_backoff
 from .session import save_session
-from .tools import backup_manager, execute_tool, tools
-from .agent import AgentRunner
-from .utils import Struct, TokenTracker, fetch_url_content, generate_directory_tree, truncate_output
+from .tools import backup_manager, tools
+from .utils import TokenTracker, fetch_url_content, generate_directory_tree
 
 
 def inject_file_context(user_input: str) -> str:
@@ -420,7 +411,7 @@ async def main_loop():
             # ── Auto-compact if context is critically full ──
             if context_manager.needs_auto_compact() and len(messages) > 4:
                 console.print("[dim yellow]⚡ Context limit reached. Attempting smart pruning...[/dim yellow]")
-                
+
                 dropped_count = ContextPruner.prune_attached_contexts(messages)
                 estimated_total = context_manager.estimate_messages_tokens(messages, token_tracker.estimate_tokens)
                 context_manager.update(estimated_total)
@@ -447,10 +438,10 @@ async def main_loop():
                 auto_iteration_count=auto_iteration_count,
                 max_auto_iterations=max_auto_iterations,
             )
-            
+
             try:
                 await runner.run_turn(messages)
-                
+
                 # Update state back from runner (if it changed during auto mode)
                 is_auto_mode = runner.is_auto_mode
                 auto_iteration_count = runner.auto_iteration_count