phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

fix: handle log errors (#1499)

Browse source 
Summary:
| File
"/Users/erichuang/projects/llama-stack/llama_stack/distribution/server/server.py",
line 213, in sse_generator
    |     logger.exception(f"Error in sse_generator: {e}")
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py",
line 1864, in exception
    |     self.log(ERROR, msg, *args, exc_info=exc_info, **kwargs)
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py",
line 1879, in log
    |     self.logger.log(level, msg, *args, **kwargs)
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py",
line 1547, in log
    |     self._log(level, msg, args, **kwargs)
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py",
line 1624, in _log
    |     self.handle(record)
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py",
line 1634, in handle
    |     self.callHandlers(record)
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py",
line 1696, in callHandlers
    |     hdlr.handle(record)
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/logging/__init__.py",
line 968, in handle
    |     self.emit(record)
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/site-packages/rich/logging.py",
line 167, in emit
    |     message_renderable = self.render_message(record, message)
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/site-packages/rich/logging.py",
line 193, in render_message
| message_text = Text.from_markup(message) if use_markup else
Text(message)
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/site-packages/rich/text.py",
line 287, in from_markup
| rendered_text = render(text, style, emoji=emoji,
emoji_variant=emoji_variant)
| File
"/opt/homebrew/Caskroom/miniconda/base/envs/myenv/lib/python3.10/site-packages/rich/markup.py",
line 167, in render
    |     raise MarkupError(
| rich.errors.MarkupError: closing tag '[/INST]' at position 105 doesn't
match any open tag


Test Plan:
reran failing rag_with_vector_db example
This commit is contained in:
ehhuang 2025-03-07 15:58:26 -08:00 • committed by GitHub
parent ade76e4a69
commit 23e39cc3c4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 14 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

13
llama_stack/log.py
View file

@ -11,6 +11,7 @@ from typing import Dict
from rich.console import Console
from rich.logging import RichHandler
from rich.errors import MarkupError
# Default log level
DEFAULT_LOG_LEVEL = logging.INFO
@ -82,6 +83,18 @@ class CustomRichHandler(RichHandler):
kwargs["console"] = Console(width=120)
super().__init__(*args, **kwargs)
def emit(self, record):
"""Override emit to handle markup errors gracefully."""
try:
super().emit(record)
except MarkupError:
original_markup = self.markup
self.markup = False
try:
super().emit(record)
finally:
self.markup = original_markup
def setup_logging(category_levels: Dict[str, int]) -> None:
"""

3
llama_stack/providers/inline/agents/meta_reference/agent_instance.py
View file

@ -16,7 +16,6 @@ from typing import Any, AsyncGenerator, Dict, List, Optional, Tuple, Union
from urllib.parse import urlparse
import httpx
from rich.markup import escape
from llama_stack.apis.agents import (
AgentConfig,
@ -1030,7 +1029,7 @@ async def execute_tool_call_maybe(
**toolgroup_args.get(group_name, {}),
},
)
logger.info(f"tool call {name} completed with result: {escape(str(result))}")
logger.info(f"tool call {name} completed with result: {result}")
return result