mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-04 02:31:27 +00:00
fix(otel): populate gen_ai.output.messages and gen_ai.system_instructions for Responses API
Fixes #25840 The OTel integration's set_attributes() method never populates gen_ai.output.messages, gen_ai.system_instructions, or gen_ai.response.finish_reasons for /v1/responses calls because ResponsesAPIResponse uses 'output' instead of 'choices' and the system prompt arrives as 'instructions' instead of 'system_instructions'. Changes: - Add elif branch for response_obj.get('output') to extract response text from Responses API output items (type='message'/output_text) and tool calls (type='function_call') - Coalesce system_instructions/instructions/system kwargs so the system prompt is captured for Responses API, Anthropic Messages API, and Vertex AI Gemini paths - Handle plain-string system prompts without unnecessary wrapping - Extract response_obj.get('status') as finish reason for Responses API - Add _transform_responses_api_output_to_otel() method
This commit is contained in:
Aneesh-Fiddler
parent
3d2b8fed32
commit
c0da139540
1 changed files with 101 additions and 10 deletions
|
|
@ -1678,17 +1678,35 @@ class OpenTelemetry(CustomLogger):
|
|||
value=safe_dumps(transformed_messages),
|
||||
)
|
||||
|
||||
if kwargs.get("system_instructions"):
|
||||
transformed_system_instructions = (
|
||||
self._transform_messages_to_otel_semantic_conventions(
|
||||
kwargs.get("system_instructions")
|
||||
# Coalesce the different kwarg names that carry the system
|
||||
# prompt depending on the call path:
|
||||
# - "system_instructions" — Vertex AI Gemini chat-completion
|
||||
# - "instructions" — OpenAI Responses API
|
||||
# - "system" — Anthropic Messages API
|
||||
system_instructions = (
|
||||
kwargs.get("system_instructions")
|
||||
or kwargs.get("instructions")
|
||||
or kwargs.get("system")
|
||||
)
|
||||
if system_instructions:
|
||||
if isinstance(system_instructions, str):
|
||||
# Plain text system prompt — no transformation needed
|
||||
self.safe_set_attribute(
|
||||
span=span,
|
||||
key=SpanAttributes.GEN_AI_SYSTEM_INSTRUCTIONS.value,
|
||||
value=system_instructions,
|
||||
)
|
||||
else:
|
||||
transformed_system_instructions = (
|
||||
self._transform_messages_to_otel_semantic_conventions(
|
||||
system_instructions
|
||||
)
|
||||
)
|
||||
self.safe_set_attribute(
|
||||
span=span,
|
||||
key=SpanAttributes.GEN_AI_SYSTEM_INSTRUCTIONS.value,
|
||||
value=safe_dumps(transformed_system_instructions),
|
||||
)
|
||||
)
|
||||
self.safe_set_attribute(
|
||||
span=span,
|
||||
key=SpanAttributes.GEN_AI_SYSTEM_INSTRUCTIONS.value,
|
||||
value=safe_dumps(transformed_system_instructions),
|
||||
)
|
||||
|
||||
self.safe_set_attribute(
|
||||
span=span,
|
||||
|
|
@ -1747,6 +1765,32 @@ class OpenTelemetry(CustomLogger):
|
|||
value=value,
|
||||
)
|
||||
|
||||
elif response_obj.get("output"):
|
||||
# Responses API: ResponsesAPIResponse has an "output"
|
||||
# list instead of "choices". Each item with
|
||||
# type="message" contains a "content" list of
|
||||
# OutputText objects (type="output_text").
|
||||
output_messages = (
|
||||
self._transform_responses_api_output_to_otel(
|
||||
response_obj.get("output")
|
||||
)
|
||||
)
|
||||
if output_messages:
|
||||
self.safe_set_attribute(
|
||||
span=span,
|
||||
key=SpanAttributes.GEN_AI_OUTPUT_MESSAGES.value,
|
||||
value=safe_dumps(output_messages),
|
||||
)
|
||||
|
||||
# Extract finish reason from ResponsesAPIResponse.status
|
||||
status = response_obj.get("status")
|
||||
if status:
|
||||
self.safe_set_attribute(
|
||||
span=span,
|
||||
key=SpanAttributes.GEN_AI_RESPONSE_FINISH_REASONS.value,
|
||||
value=safe_dumps([status]),
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
self.handle_callback_failure(
|
||||
callback_name=self.callback_name or "opentelemetry"
|
||||
|
|
@ -1842,6 +1886,53 @@ class OpenTelemetry(CustomLogger):
|
|||
transformed.append(transformed_msg)
|
||||
return transformed
|
||||
|
||||
def _transform_responses_api_output_to_otel(
|
||||
self, output: List[dict]
|
||||
) -> List[dict]:
|
||||
"""
|
||||
Transform Responses API output items into OTEL GenAI 1.38 format.
|
||||
|
||||
The Responses API returns output as a list of items, each with a
|
||||
``type`` field. Message items (``type="message"``) contain a
|
||||
``content`` list of ``OutputText`` objects with ``type="output_text"``
|
||||
and ``text`` fields.
|
||||
|
||||
This method converts them to the same ``{"role": ..., "parts": [...]}``
|
||||
format used by ``_transform_choices_to_otel_semantic_conventions``.
|
||||
"""
|
||||
transformed = []
|
||||
for item in output:
|
||||
if not isinstance(item, dict):
|
||||
continue
|
||||
if item.get("type") == "message":
|
||||
role = item.get("role", "assistant")
|
||||
parts = []
|
||||
for content in item.get("content", []):
|
||||
if not isinstance(content, dict):
|
||||
continue
|
||||
if content.get("type") == "output_text":
|
||||
text = content.get("text", "")
|
||||
if text:
|
||||
parts.append({"type": "text", "content": text})
|
||||
if parts:
|
||||
transformed.append({"role": role, "parts": parts})
|
||||
elif item.get("type") == "function_call":
|
||||
# Surface tool calls from Responses API output
|
||||
tool_call = {
|
||||
"role": "assistant",
|
||||
"parts": [
|
||||
{
|
||||
"type": "tool_call",
|
||||
"name": item.get("name", ""),
|
||||
"arguments": item.get("arguments", ""),
|
||||
}
|
||||
],
|
||||
}
|
||||
if item.get("call_id"):
|
||||
tool_call["parts"][0]["id"] = item["call_id"]
|
||||
transformed.append(tool_call)
|
||||
return transformed
|
||||
|
||||
def set_raw_request_attributes(self, span: Span, kwargs, response_obj):
|
||||
try:
|
||||
# Only set provider-specific raw payload attributes on this span.
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue