phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into remove-deprecated-completion

Browse source
This commit is contained in:
Matthew Farrellee 2025-10-01 08:56:33 -04:00
commit 0a0e02a0ac
66 changed files with 13976 additions and 5631 deletions
Download patch file Download diff file Expand all files Collapse all files

10
llama_stack/providers/inline/agents/meta_reference/responses/streaming.py
View file

@ -129,13 +129,16 @@ class StreamingResponseOrchestrator:
messages = self.ctx.messages.copy()
while True:
# Text is the default response format for chat completion so don't need to pass it
# (some providers don't support non-empty response_format when tools are present)
response_format = None if self.ctx.response_format.type == "text" else self.ctx.response_format
completion_result = await self.inference_api.openai_chat_completion(
model=self.ctx.model,
messages=messages,
tools=self.ctx.chat_tools,
stream=True,
temperature=self.ctx.temperature,
response_format=self.ctx.response_format,
response_format=response_format,
)
# Process streaming chunks and build complete response
@ -352,8 +355,11 @@ class StreamingResponseOrchestrator:
# Emit arguments.done events for completed tool calls (differentiate between MCP and function calls)
for tool_call_index in sorted(chat_response_tool_calls.keys()):
tool_call = chat_response_tool_calls[tool_call_index]
# Ensure that arguments, if sent back to the inference provider, are not None
tool_call.function.arguments = tool_call.function.arguments or "{}"
tool_call_item_id = tool_call_item_ids[tool_call_index]
final_arguments = chat_response_tool_calls[tool_call_index].function.arguments or ""
final_arguments = tool_call.function.arguments
tool_call_name = chat_response_tool_calls[tool_call_index].function.name
# Check if this is an MCP tool call

4
llama_stack/providers/inline/telemetry/meta_reference/config.py
View file

@ -30,7 +30,7 @@ class TelemetryConfig(BaseModel):
description="The service name to use for telemetry",
)
sinks: list[TelemetrySink] = Field(
default=[TelemetrySink.CONSOLE, TelemetrySink.SQLITE],
default=[TelemetrySink.SQLITE],
description="List of telemetry sinks to enable (possible values: otel_trace, otel_metric, sqlite, console)",
)
sqlite_db_path: str = Field(
@ -49,7 +49,7 @@ class TelemetryConfig(BaseModel):
def sample_run_config(cls, __distro_dir__: str, db_name: str = "trace_store.db") -> dict[str, Any]:
return {
"service_name": "${env.OTEL_SERVICE_NAME:=\u200b}",
"sinks": "${env.TELEMETRY_SINKS:=console,sqlite}",
"sinks": "${env.TELEMETRY_SINKS:=sqlite}",
"sqlite_db_path": "${env.SQLITE_STORE_DIR:=" + __distro_dir__ + "}/" + db_name,
"otel_exporter_otlp_endpoint": "${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}",
}