phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-23 05:02:26 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: add auto-generated CI documentation pre-commit hook (#2890)

Browse source 
Our CI is entirely undocumented, this commit adds a README.md file with
a table of the current CI and what is does

---------

Signed-off-by: Nathan Weinberg <nweinber@redhat.com>
This commit is contained in:
Nathan Weinberg 2025-07-25 11:57:01 -04:00 • committed by Mustafa Elbehery
parent 7f834339ba
commit b381ed6d64
93 changed files with 495 additions and 477 deletions
Download patch file Download diff file Expand all files Collapse all files

10
llama_stack/providers/utils/inference/openai_compat.py
View file

@ -5,7 +5,6 @@
# the root directory of this source tree.
import base64
import json
import logging
import struct
import time
import uuid
@ -116,6 +115,7 @@ from llama_stack.apis.inference import (
from llama_stack.apis.inference import (
OpenAIChoice as OpenAIChatCompletionChoice,
)
from llama_stack.log import get_logger
from llama_stack.models.llama.datatypes import (
BuiltinTool,
StopReason,
@ -128,7 +128,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
decode_assistant_message,
)
logger = logging.getLogger(__name__)
log = get_logger(name=__name__, category="inference")
class OpenAICompatCompletionChoiceDelta(BaseModel):
@ -316,7 +316,7 @@ def process_chat_completion_response(
if t.tool_name in request_tools:
new_tool_calls.append(t)
else:
logger.warning(f"Tool {t.tool_name} not found in request tools")
log.warning(f"Tool {t.tool_name} not found in request tools")
if len(new_tool_calls) < len(raw_message.tool_calls):
raw_message.tool_calls = new_tool_calls
@ -477,7 +477,7 @@ async def process_chat_completion_stream_response(
)
)
else:
logger.warning(f"Tool {tool_call.tool_name} not found in request tools")
log.warning(f"Tool {tool_call.tool_name} not found in request tools")
yield ChatCompletionResponseStreamChunk(
event=ChatCompletionResponseEvent(
event_type=ChatCompletionResponseEventType.progress,
@ -1198,7 +1198,7 @@ async def convert_openai_chat_completion_stream(
)
for idx, buffer in tool_call_idx_to_buffer.items():
logger.debug(f"toolcall_buffer[{idx}]: {buffer}")
log.debug(f"toolcall_buffer[{idx}]: {buffer}")
if buffer["name"]:
delta = ")"
buffer["content"] += delta