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

feat(logging): implement category-based logging (#1362)

Browse source 
# What does this PR do?

This commit introduces a new logging system that allows loggers to be
assigned
a category while retaining the logger name based on the file name. The
log
format includes both the logger name and the category, producing output
like:

```
INFO     2025-03-03 21:44:11,323 llama_stack.distribution.stack:103 [core]: Tool_groups: builtin::websearch served by
         tavily-search
```

Key features include:

- Category-based logging: Loggers can be assigned a category (e.g.,
  "core", "server") when programming. The logger can be loaded like
  this: `logger = get_logger(name=__name__, category="server")`
- Environment variable control: Log levels can be configured
per-category using the
  `LLAMA_STACK_LOGGING` environment variable. For example:
`LLAMA_STACK_LOGGING="server=DEBUG;core=debug"` enables DEBUG level for
the "server"
    and "core" categories.
- `LLAMA_STACK_LOGGING="all=debug"` sets DEBUG level globally for all
categories and
    third-party libraries.

This provides fine-grained control over logging levels while maintaining
a clean and
informative log format.

The formatter uses the rich library which provides nice colors better
stack traces like so:

```
ERROR    2025-03-03 21:49:37,124 asyncio:1758 [uncategorized]: unhandled exception during asyncio.run() shutdown
         task: <Task finished name='Task-16' coro=<handle_signal.<locals>.shutdown() done, defined at
         /Users/leseb/Documents/AI/llama-stack/llama_stack/distribution/server/server.py:146>
         exception=UnboundLocalError("local variable 'loop' referenced before assignment")>
         ╭────────────────────────────────────── Traceback (most recent call last) ───────────────────────────────────────╮
         │ /Users/leseb/Documents/AI/llama-stack/llama_stack/distribution/server/server.py:178 in shutdown                │
         │                                                                                                                │
         │   175 │   │   except asyncio.CancelledError:                                                                   │
         │   176 │   │   │   pass                                                                                         │
         │   177 │   │   finally:                                                                                         │
         │ ❱ 178 │   │   │   loop.stop()                                                                                  │
         │   179 │                                                                                                        │
         │   180 │   loop = asyncio.get_running_loop()                                                                    │
         │   181 │   loop.create_task(shutdown())                                                                         │
         ╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
         UnboundLocalError: local variable 'loop' referenced before assignment
```

Co-authored-by: Ashwin Bharambe <@ashwinb>
Signed-off-by: Sébastien Han <seb@redhat.com>

[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])

## Test Plan

```
python -m llama_stack.distribution.server.server --yaml-config ./llama_stack/templates/ollama/run.yaml
INFO     2025-03-03 21:55:35,918 __main__:365 [server]: Using config file: llama_stack/templates/ollama/run.yaml           
INFO     2025-03-03 21:55:35,925 __main__:378 [server]: Run configuration:                                                 
INFO     2025-03-03 21:55:35,928 __main__:380 [server]: apis:                                                              
         - agents                                                     
``` 
[//]: # (## Documentation)

---------

Signed-off-by: Sébastien Han <seb@redhat.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
This commit is contained in:
Sébastien Han 2025-03-07 20:34:30 +01:00 • committed by GitHub
parent bad12ee21f
commit 7cf1e24c4e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
16 changed files with 296 additions and 431 deletions
Download patch file Download diff file Expand all files Collapse all files

24
llama_stack/providers/inline/agents/meta_reference/agent_instance.py
View file

@ -17,7 +17,6 @@ from urllib.parse import urlparse
import httpx
from llama_stack import logcat
from llama_stack.apis.agents import (
AgentConfig,
AgentToolGroup,
@ -67,6 +66,7 @@ from llama_stack.apis.tools import (
ToolRuntime,
)
from llama_stack.apis.vector_io import VectorIO
from llama_stack.log import get_logger
from llama_stack.models.llama.datatypes import (
BuiltinTool,
ToolCall,
@ -88,6 +88,8 @@ MEMORY_QUERY_TOOL = "knowledge_search"
WEB_SEARCH_TOOL = "web_search"
RAG_TOOL_GROUP = "builtin::rag"
logger = get_logger(name=__name__, category="agents")
class ChatAgent(ShieldRunnerMixin):
def __init__(
@ -609,7 +611,7 @@ class ChatAgent(ShieldRunnerMixin):
)
if n_iter >= self.agent_config.max_infer_iters:
logcat.info("agents", f"done with MAX iterations ({n_iter}), exiting.")
logger.info(f"done with MAX iterations ({n_iter}), exiting.")
# NOTE: mark end_of_turn to indicate to client that we are done with the turn
# Do not continue the tool call loop after this point
message.stop_reason = StopReason.end_of_turn
@ -617,7 +619,7 @@ class ChatAgent(ShieldRunnerMixin):
break
if stop_reason == StopReason.out_of_tokens:
logcat.info("agents", "out of token budget, exiting.")
logger.info("out of token budget, exiting.")
yield message
break
@ -631,16 +633,10 @@ class ChatAgent(ShieldRunnerMixin):
message.content = [message.content] + output_attachments
yield message
else:
logcat.debug(
"agents",
f"completion message with EOM (iter: {n_iter}): {str(message)}",
)
logger.debug(f"completion message with EOM (iter: {n_iter}): {str(message)}")
input_messages = input_messages + [message]
else:
logcat.debug(
"agents",
f"completion message (iter: {n_iter}) from the model: {str(message)}",
)
logger.debug(f"completion message (iter: {n_iter}) from the model: {str(message)}")
# 1. Start the tool execution step and progress
step_id = str(uuid.uuid4())
yield AgentTurnResponseStreamChunk(
@ -983,7 +979,7 @@ async def attachment_message(tempdir: str, urls: List[URL]) -> ToolResponseMessa
path = urlparse(uri).path
basename = os.path.basename(path)
filepath = f"{tempdir}/{make_random_string() + basename}"
logcat.info("agents", f"Downloading {url} -> {filepath}")
logger.info(f"Downloading {url} -> {filepath}")
async with httpx.AsyncClient() as client:
r = await client.get(uri)
@ -1023,7 +1019,7 @@ async def execute_tool_call_maybe(
else:
name = name.value
logcat.info("agents", f"executing tool call: {name} with args: {tool_call.arguments}")
logger.info(f"executing tool call: {name} with args: {tool_call.arguments}")
result = await tool_runtime_api.invoke_tool(
tool_name=name,
kwargs={
@ -1033,7 +1029,7 @@ async def execute_tool_call_maybe(
**toolgroup_args.get(group_name, {}),
},
)
logcat.debug("agents", f"tool call {name} completed with result: {result}")
logger.info(f"tool call {name} completed with result: {result}")
return result