feat: introduce AgentTide module for enhanced code context and patch generation

Author: BrunoV21

README.md

@@ -446,9 +446,57 @@ Here’s what’s next for CodeTide:
   
 ~~- 🧭 **Handle relative imports** in Python projects  
   → Improve resolution for intra-package navigation.~~
-- 🤖 **Long-term vision**: Release a native **CodeTide Agent**  
-  → Seamless, intelligent context resolution directly integrated into the CodeTide core.  
-  → Unlock **clinical issue detection**, **guided refactors**, and **agent-level navigation**.
+
+---
+
+## 🤖 Agents Module: AgentTide
+
+CodeTide now includes an `agents` module, featuring **AgentTide**—a precision-driven software engineering agent that connects directly to your codebase and executes your requests with full code context.
+
+**AgentTide** leverages CodeTide’s symbolic code understanding to:
+- Retrieve and reason about relevant code context for any request
+- Generate atomic, high-precision patches using strict protocols
+- Apply changes directly to your codebase, with robust validation
+
+### Where to Find It
+- Source: [`codetide/agents/tide/agent.py`](codetide/agents/tide/agent.py)
+
+### What It Does
+AgentTide acts as an autonomous agent that:
+- Connects to your codebase using CodeTide’s parsing and context tools
+- Interacts with users via a conversational interface
+- Identifies relevant files, classes, and functions for any request
+- Generates and applies diff-style patches, ensuring code quality and requirements fidelity
+
+### Example Usage
+To use AgentTide, ensure you have the `aicore` package installed (`pip install codetide[agents]`), then instantiate and run the agent:
+
+```python
+from codetide import CodeTide
+from codetide.agents.tide.agent import AgentTide
+from aicore.llm import Llm, LlmConfig
+import os, asyncio
+
+async def main():
+    tide = await CodeTide.from_path("/path/to/your/repo")
+    llm = Llm.from_config(
+        LlmConfig(
+            model="deepseek-chat",
+            provider="deepseek",
+            temperature=0,
+            api_key=os.getenv("DEEPSEEK-API-KEY")
+        )
+    )
+    agent = AgentTide(llm=llm, tide=tide)
+    await agent.run()
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+AgentTide will prompt you for requests, retrieve the relevant code context, and generate precise patches to fulfill your requirements.
+
+For more details, see the [agents module source code](codetide/agents/tide/agent.py).
 
 ---
 

examples/agent_tide.py

@@ -1,96 +1,36 @@
 """
-install aicore - pip install core-for-ai
-Make sure to set `CODETIDE_WORKSPACE` env var which will be requried for the MCP server to work
+Install the agents version with pip install codetide[agents]
 """
 
-from codetide.mcp.agent_tide_system import AGENT_TIDE_SYSTEM_PROMPT
-from codetide.mcp import codeTideMCPServer
+from codetide.mcp.utils import initCodeTide
+from codetide.agents.tide import AgentTide
 from aicore.llm import Llm, LlmConfig
-from aicore.logger import _logger
-
-from prompt_toolkit.key_binding import KeyBindings
-from prompt_toolkit import PromptSession
-from typing import Optional
 import os
 
-AGENT_TIDE_ASCII_ART = """
-
-█████╗  ██████╗ ███████╗███╗   ██╗████████╗    ████████╗██╗██████╗ ███████╗
-██╔══██╗██╔════╝ ██╔════╝████╗  ██║╚══██╔══╝    ╚══██╔══╝██║██╔══██╗██╔════╝
-███████║██║  ███╗█████╗  ██╔██╗ ██║   ██║          ██║   ██║██║  ██║█████╗  
-██╔══██║██║   ██║██╔══╝  ██║╚██╗██║   ██║          ██║   ██║██║  ██║██╔══╝  
-██║  ██║╚██████╔╝███████╗██║ ╚████║   ██║          ██║   ██║██████╔╝███████╗
-╚═╝  ╚═╝ ╚═════╝ ╚══════╝╚═╝  ╚═══╝   ╚═╝          ╚═╝   ╚═╝╚═════╝ ╚══════╝
-
-"""
-
 def init_llm()->Llm:
     llm = Llm.from_config(
         LlmConfig(
-            model="deepseek-chat",
-            provider="deepseek",
+            # model="deepseek-chat",
+            # provider="deepseek",
+            # api_key=os.getenv("DEEPSEEK-API-KEY")
+            model="gpt-4.1",
+            provider="openai",
+            api_key=os.getenv("OPENAI-API-KEY"),
             temperature=0,
-            api_key=os.getenv("DEEPSEEK-API-KEY")
         )
     )
-    
-    llm.provider.mcp.add_server(name=codeTideMCPServer.name, parameters=codeTideMCPServer)
     return llm
 
-def trim_messages(messages, tokenizer_fn, max_tokens :Optional[int]=None):
-    max_tokens = max_tokens or int(os.environ.get("MAX_HISTORY_TOKENS", 1028))
-    while messages and sum(len(tokenizer_fn(msg)) for msg in messages) > max_tokens:
-        messages.pop(0)  # Remove from the beginning
-
-async def main(max_tokens: int = 48000):
+async def main():
     llm = init_llm()
-    history = []
-
-    # 1. Set up key bindings
-    bindings = KeyBindings()
-
-    @bindings.add('escape')
-    def _(event):
-        """When Esc is pressed, exit the application."""
-        _logger.logger.warning("Escape key pressed — exiting...")
-        event.app.exit()
+    tide = await initCodeTide()
 
-    # 2. Create a prompt session with the custom key bindings
-    session = PromptSession(key_bindings=bindings)
+    tide = AgentTide(llm=llm, tide=tide)
+    await tide.run()
 
-    _logger.logger.info(f"\n{AGENT_TIDE_ASCII_ART}\nReady to surf. Press ESC to exit.\n")
-    try:
-        while True:
-            try:
-                # 3. Use the async prompt instead of input()
-                message = await session.prompt_async("You: ")
-                message = message.strip()
-
-                if not message:
-                    continue
-
-            except (EOFError, KeyboardInterrupt):
-                # prompt_toolkit raises EOFError on Ctrl-D and KeyboardInterrupt on Ctrl-C
-                _logger.warning("\nExiting...")
-                break
-
-            history.append(message)
-            trim_messages(history, llm.tokenizer, max_tokens)
-
-            print("Agent: Thinking...")
-            response = await llm.acomplete(history, system_prompt=[AGENT_TIDE_SYSTEM_PROMPT], as_message_records=True)
-            print(f"Agent: {response}")
-            history.extend(response)
-
-    except asyncio.CancelledError:
-        # This can happen if the event loop is shut down
-        pass
-    finally:
-        _logger.logger.info("\nExited by user. Goodbye!")
-
-if __name__ == "__main__": 
+if __name__ == "__main__":
     from dotenv import load_dotenv
     import asyncio
-
+    
     load_dotenv()
-    asyncio.run(main())
+    asyncio.run(main())