psutil profiling, temperature in config.json

7 files changed, 67 insertions, 6 deletions

diff --git a/continuedev/poetry.lock b/continuedev/poetry.lock
index e8927fe7..1cd4a591 100644
--- a/continuedev/poetry.lock
+++ b/continuedev/poetry.lock
@@ -1172,6 +1172,33 @@ sentry = ["django", "sentry-sdk"]
 test = ["coverage", "flake8", "freezegun (==0.3.15)", "mock (>=2.0.0)", "pylint", "pytest"]
 
 [[package]]
+name = "psutil"
+version = "5.9.5"
+description = "Cross-platform lib for process and system monitoring in Python."
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+files = [
+    {file = "psutil-5.9.5-cp27-cp27m-macosx_10_9_x86_64.whl", hash = "sha256:be8929ce4313f9f8146caad4272f6abb8bf99fc6cf59344a3167ecd74f4f203f"},
+    {file = "psutil-5.9.5-cp27-cp27m-manylinux2010_i686.whl", hash = "sha256:ab8ed1a1d77c95453db1ae00a3f9c50227ebd955437bcf2a574ba8adbf6a74d5"},
+    {file = "psutil-5.9.5-cp27-cp27m-manylinux2010_x86_64.whl", hash = "sha256:4aef137f3345082a3d3232187aeb4ac4ef959ba3d7c10c33dd73763fbc063da4"},
+    {file = "psutil-5.9.5-cp27-cp27mu-manylinux2010_i686.whl", hash = "sha256:ea8518d152174e1249c4f2a1c89e3e6065941df2fa13a1ab45327716a23c2b48"},
+    {file = "psutil-5.9.5-cp27-cp27mu-manylinux2010_x86_64.whl", hash = "sha256:acf2aef9391710afded549ff602b5887d7a2349831ae4c26be7c807c0a39fac4"},
+    {file = "psutil-5.9.5-cp27-none-win32.whl", hash = "sha256:5b9b8cb93f507e8dbaf22af6a2fd0ccbe8244bf30b1baad6b3954e935157ae3f"},
+    {file = "psutil-5.9.5-cp27-none-win_amd64.whl", hash = "sha256:8c5f7c5a052d1d567db4ddd231a9d27a74e8e4a9c3f44b1032762bd7b9fdcd42"},
+    {file = "psutil-5.9.5-cp36-abi3-macosx_10_9_x86_64.whl", hash = "sha256:3c6f686f4225553615612f6d9bc21f1c0e305f75d7d8454f9b46e901778e7217"},
+    {file = "psutil-5.9.5-cp36-abi3-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7a7dd9997128a0d928ed4fb2c2d57e5102bb6089027939f3b722f3a210f9a8da"},
+    {file = "psutil-5.9.5-cp36-abi3-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:89518112647f1276b03ca97b65cc7f64ca587b1eb0278383017c2a0dcc26cbe4"},
+    {file = "psutil-5.9.5-cp36-abi3-win32.whl", hash = "sha256:104a5cc0e31baa2bcf67900be36acde157756b9c44017b86b2c049f11957887d"},
+    {file = "psutil-5.9.5-cp36-abi3-win_amd64.whl", hash = "sha256:b258c0c1c9d145a1d5ceffab1134441c4c5113b2417fafff7315a917a026c3c9"},
+    {file = "psutil-5.9.5-cp38-abi3-macosx_11_0_arm64.whl", hash = "sha256:c607bb3b57dc779d55e1554846352b4e358c10fff3abf3514a7a6601beebdb30"},
+    {file = "psutil-5.9.5.tar.gz", hash = "sha256:5410638e4df39c54d957fc51ce03048acd8e6d60abc0f5107af51e5fb566eb3c"},
+]
+
+[package.extras]
+test = ["enum34", "ipaddress", "mock", "pywin32", "wmi"]
+
+[[package]]
 name = "pydantic"
 version = "1.10.7"
 description = "Data validation and settings management using python type hints"
@@ -2015,4 +2042,4 @@ testing = ["big-O", "jaraco.functools", "jaraco.itertools", "more-itertools", "p
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.8.1"
-content-hash = "87dbf6d1e56ce6ba81a01a59c0de2d3717925bac9639710bf3ff3ce30f5f5e2c"
+content-hash = "3fcd19c11b9c338a181e591b56e21d59c7834abff431fb9f40cc1ea874b64557"
diff --git a/continuedev/pyproject.toml b/continuedev/pyproject.toml
index 6a646cbe..0abc9504 100644
--- a/continuedev/pyproject.toml
+++ b/continuedev/pyproject.toml
@@ -26,6 +26,7 @@ jsonschema = "^4.17.3"
 directory-tree = "^0.0.3.1"
 anthropic = "^0.3.4"
 chevron = "^0.14.0"
+psutil = "^5.9.5"
 
 [tool.poetry.scripts]
 typegen = "src.continuedev.models.generate_json_schema:main" 
diff --git a/continuedev/src/continuedev/core/config.py b/continuedev/src/continuedev/core/config.py
index 6af0878d..70c4876e 100644
--- a/continuedev/src/continuedev/core/config.py
+++ b/continuedev/src/continuedev/core/config.py
@@ -82,6 +82,7 @@ class ContinueConfig(BaseModel):
     allow_anonymous_telemetry: Optional[bool] = True
     default_model: Literal["gpt-3.5-turbo", "gpt-3.5-turbo-16k",
                            "gpt-4", "claude-2", "ggml"] = 'gpt-4'
+    temperature: Optional[float] = 0.5
     custom_commands: Optional[List[CustomCommand]] = [CustomCommand(
         name="test",
         description="This is an example custom command. Use /config to edit it and create more",
@@ -98,6 +99,10 @@ class ContinueConfig(BaseModel):
     def default_slash_commands_validator(cls, v):
         return DEFAULT_SLASH_COMMANDS
 
+    @validator('temperature', pre=True)
+    def temperature_validator(cls, v):
+        return max(0.0, min(1.0, v))
+
 
 def load_config(config_file: str) -> ContinueConfig:
     """
diff --git a/continuedev/src/continuedev/libs/llm/proxy_server.py b/continuedev/src/continuedev/libs/llm/proxy_server.py
index 18e0e6f4..bd50fe02 100644
--- a/continuedev/src/continuedev/libs/llm/proxy_server.py
+++ b/continuedev/src/continuedev/libs/llm/proxy_server.py
@@ -1,8 +1,10 @@
 
 from functools import cached_property
 import json
+import traceback
 from typing import Any, Callable, Coroutine, Dict, Generator, List, Literal, Union
 import aiohttp
+from ..util.telemetry import capture_event
 from ...core.main import ChatMessage
 from ..llm import LLM
 from ..util.count_tokens import DEFAULT_ARGS, DEFAULT_MAX_TOKENS, compile_chat_messages, CHAT_MODELS, count_tokens, format_chat_messages
@@ -81,8 +83,10 @@ class ProxyServer(LLM):
                                     yield loaded_chunk
                                     if "content" in loaded_chunk:
                                         completion += loaded_chunk["content"]
-                        except:
-                            raise Exception(str(line[0]))
+                        except Exception as e:
+                            capture_event(self.unique_id, "proxy_server_parse_error", {
+                                "error_title": "Proxy server stream_chat parsing failed", "error_message": '\n'.join(traceback.format_exception(e))})
+
                 self.write_log(f"Completion: \n\n{completion}")
 
     async def stream_complete(self, prompt, with_history: List[ChatMessage] = [], **kwargs) -> Generator[Union[Any, List, Dict], None, None]:
diff --git a/continuedev/src/continuedev/server/main.py b/continuedev/src/continuedev/server/main.py
index aa093853..42dc0cc1 100644
--- a/continuedev/src/continuedev/server/main.py
+++ b/continuedev/src/continuedev/server/main.py
@@ -1,5 +1,6 @@
+import time
+import psutil
 import os
-import sys
 from fastapi import FastAPI
 from fastapi.middleware.cors import CORSMiddleware
 from .ide import router as ide_router
@@ -51,9 +52,31 @@ def cleanup():
         session_manager.persist_session(session_id)
 
 
+def cpu_usage_report():
+    process = psutil.Process(os.getpid())
+    # Call cpu_percent once to start measurement, but ignore the result
+    process.cpu_percent(interval=None)
+    # Wait for a short period of time
+    time.sleep(1)
+    # Call cpu_percent again to get the CPU usage over the interval
+    cpu_usage = process.cpu_percent(interval=None)
+    print(f"CPU usage: {cpu_usage}%")
+
+
 atexit.register(cleanup)
+
 if __name__ == "__main__":
     try:
+        # import threading
+
+        # def cpu_usage_loop():
+        #     while True:
+        #         cpu_usage_report()
+        #         time.sleep(2)
+
+        # cpu_thread = threading.Thread(target=cpu_usage_loop)
+        # cpu_thread.start()
+
         run_server()
     except Exception as e:
         cleanup()
diff --git a/continuedev/src/continuedev/steps/chat.py b/continuedev/src/continuedev/steps/chat.py
index 8c03969e..aade1ea1 100644
--- a/continuedev/src/continuedev/steps/chat.py
+++ b/continuedev/src/continuedev/steps/chat.py
@@ -29,7 +29,8 @@ class SimpleChatStep(Step):
         completion = ""
         messages = self.messages or await sdk.get_chat_context()
 
-        generator = sdk.models.default.stream_chat(messages, temperature=0.5)
+        generator = sdk.models.default.stream_chat(
+            messages, temperature=sdk.config.temperature)
         try:
             async for chunk in generator:
                 if sdk.current_step_was_deleted():
diff --git a/continuedev/src/continuedev/steps/core/core.py b/continuedev/src/continuedev/steps/core/core.py
index 2b049ecc..4afc36e8 100644
--- a/continuedev/src/continuedev/steps/core/core.py
+++ b/continuedev/src/continuedev/steps/core/core.py
@@ -492,7 +492,7 @@ Please output the code to be inserted at the cursor in order to fulfill the user
                 role="user", content=f"```\n{rif.contents}\n```\n\nUser request: \"{self.user_input}\"\n\nThis is the code after changing to perfectly comply with the user request. It does not include any placeholder code, only real implementations:\n\n```\n", summary=self.user_input)]
 
         generator = model_to_use.stream_chat(
-            messages, temperature=0, max_tokens=max_tokens)
+            messages, temperature=sdk.config.temperature, max_tokens=max_tokens)
 
         try:
             async for chunk in generator: