cristiano.hoshikawa/agent_contas
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Ajustes conforme relatorio de testes 2026-08-27

Browse Source
This commit is contained in:
Cristiano Hoshikawa
2026-08-29 21:04:27 -03:00
parent 71f6c18e78
commit 00ac7f0c83
10 changed files with 264 additions and 127 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
agent_framework_oci/libs/agent_framework/build/lib/agent_framework/guardrails/calibrated/llm_client.py
View File

@@ -145,8 +145,17 @@ class GuardrailLLMClient:
except RuntimeError:
return asyncio.run(_call())
# ``ContextVar`` values do not cross ThreadPoolExecutor boundaries by
# default. Preserve the framework request/trace/parent observation when
# this legacy sync bridge needs a worker thread; otherwise a provider
# created inside the worker sees no active correlation context and the
# optional langfuse.openai wrapper may emit a standalone OpenAI-generation
# trace.
from contextvars import copy_context
context = copy_context()
with ThreadPoolExecutor(max_workers=1, thread_name_prefix="guardrail-compat") as executor:
return executor.submit(lambda: asyncio.run(_call())).result()
return executor.submit(context.run, lambda: asyncio.run(_call())).result()
def classify(
self,

106
agent_framework_oci/libs/agent_framework/build/lib/agent_framework/llm/providers.py
View File

@@ -58,6 +58,55 @@ def _coerce_reasoning_text(value: Any) -> str | None:
return text or None
def _coerce_message_content(value: Any) -> str:
"""Normalize OpenAI-compatible message content without using reasoning as answer.
OpenAI-compatible implementations may expose ``message.content`` as a plain
string, a list of content parts, or SDK objects/dicts containing ``text``.
Unknown shapes fail closed to an empty string instead of serializing the raw
response object into the assistant answer.
"""
if value is None:
return ""
if isinstance(value, str):
return value
if isinstance(value, (list, tuple)):
chunks: list[str] = []
for item in value:
if isinstance(item, str):
chunks.append(item)
continue
if isinstance(item, dict):
text = item.get("text")
if isinstance(text, str):
chunks.append(text)
continue
text = getattr(item, "text", None)
if isinstance(text, str):
chunks.append(text)
return "".join(chunks)
if isinstance(value, dict):
text = value.get("text")
return text if isinstance(text, str) else ""
text = getattr(value, "text", None)
return text if isinstance(text, str) else ""
def _extract_openai_message_content(message: Any) -> str:
if message is None:
return ""
if isinstance(message, dict):
return _coerce_message_content(message.get("content"))
return _coerce_message_content(getattr(message, "content", None))
def _extract_finish_reason(choice: Any) -> str | None:
if choice is None:
return None
value = choice.get("finish_reason") if isinstance(choice, dict) else getattr(choice, "finish_reason", None)
return str(value) if value is not None else None
def _extract_reasoning_content(obj: Any) -> str | None:
"""Best-effort extraction across OpenAI-compatible and OCI response shapes."""
if obj is None:
@@ -272,10 +321,27 @@ class OCICompatibleOpenAIProvider(LLMProvider):
getattr(settings, "ENABLE_LANGFUSE_OPENAI_AUTO_INSTRUMENTATION", None)
or os.getenv("ENABLE_LANGFUSE_OPENAI_AUTO_INSTRUMENTATION", "false")
).strip().lower() in {"1", "true", "yes", "on", "y"}
if self.telemetry is not None and use_langfuse_wrapper:
# The framework owns Langfuse correlation. Even compatibility paths may
# instantiate a provider without passing ``Telemetry`` explicitly while a
# request is already active (for example GuardrailLLMClient running in its
# sync bridge). In that situation langfuse.openai would auto-create an
# ``OpenAI-generation`` root trace instead of attaching to the business
# request. Treat an active framework observability context exactly like
# an injected Telemetry instance and keep the standard OpenAI client.
active_framework_trace = False
try:
from agent_framework.observability.context import get_observability_context
obs_ctx = get_observability_context()
active_framework_trace = bool(obs_ctx.trace_id or obs_ctx.request_id)
except Exception:
active_framework_trace = False
if use_langfuse_wrapper and (self.telemetry is not None or active_framework_trace):
logger.warning(
"ENABLE_LANGFUSE_OPENAI_AUTO_INSTRUMENTATION=true ignorado porque o provider já recebeu "
"Telemetry do framework; instrumentação dupla pode criar observations fora do contrato de mapping."
"ENABLE_LANGFUSE_OPENAI_AUTO_INSTRUMENTATION=true ignorado durante execução correlacionada "
"do framework; langfuse.openai pode criar OpenAI-generation como trace raiz separado."
)
use_langfuse_wrapper = False
if getattr(settings, "ENABLE_LANGFUSE", False) and use_langfuse_wrapper:
@@ -432,9 +498,29 @@ class OCICompatibleOpenAIProvider(LLMProvider):
model_parameters=model_parameters,
) as generation:
resp = await client.chat.completions.create(**request_kwargs)
message = resp.choices[0].message
answer = message.content or ""
reasoning_content = _extract_reasoning_content(message)
choices = getattr(resp, "choices", None) or []
if not choices:
message = None
answer = ""
reasoning_content = None
finish_reason = None
logger.warning(
"OpenAI-compatible LLM returned no choices provider=%s model=%s profile=%s component=%s",
provider, model, resolved_profile_name, component_name,
)
else:
choice = choices[0]
message = choice.get("message") if isinstance(choice, dict) else getattr(choice, "message", None)
answer = _extract_openai_message_content(message)
reasoning_content = _extract_reasoning_content(message)
finish_reason = _extract_finish_reason(choice)
logger.info(
"OpenAI-compatible LLM response provider=%s model=%s profile=%s component=%s "
"finish_reason=%s content_len=%d reasoning_len=%d",
provider, model, resolved_profile_name, component_name,
finish_reason, len(answer), len(reasoning_content or ""),
)
usage_metadata = self.token_collector.enrich(model, getattr(resp, "usage", None))
usage_metadata.update({
@@ -445,8 +531,16 @@ class OCICompatibleOpenAIProvider(LLMProvider):
"component": component_name,
"model": model,
"provider": provider,
"finish_reason": finish_reason,
"content_length": len(answer),
"reasoning_content_length": len(reasoning_content or ""),
**model_parameters,
})
llm_metadata.update({
"finish_reason": finish_reason,
"content_length": len(answer),
"reasoning_content_length": len(reasoning_content or ""),
})
generation.set_output(answer)
generation.set_usage(usage_metadata)
generation.set_metadata(**usage_metadata)

8
agent_framework_oci/libs/agent_framework/docs/LANGFUSE_TRACE_CORRELATION_FIX.md
View File

@@ -47,13 +47,13 @@ internal steps = observations/spans/generations inside that trace
- Langfuse OpenAI auto-instrumentation is now opt-in.
- Default behavior uses the standard `openai.AsyncOpenAI` client and relies on the framework's own `Telemetry.generation(...)` to create correlated Langfuse generations.
- To re-enable wrapper-based auto-instrumentation, set:
- The supported framework default is:
```env
ENABLE_LANGFUSE_OPENAI_AUTO_INSTRUMENTATION=true
ENABLE_LANGFUSE_OPENAI_AUTO_INSTRUMENTATION=false
```
For this framework, the recommended default is to keep it disabled.
All `.env.example` files in the repository declare this value explicitly. Set it to `true` only for isolated compatibility/diagnostic deployments that intentionally need to capture OpenAI SDK calls outside the framework telemetry path.
## Expected result
@@ -86,7 +86,7 @@ framework_judges
Run the backend and execute one request. Then verify:
1. The `Traces` screen has one trace row for the request, not one row per node.
2. `OpenAI-generation` no longer appears as a separate top-level trace unless `ENABLE_LANGFUSE_OPENAI_AUTO_INSTRUMENTATION=true`.
2. `OpenAI-generation` no longer appears as a separate top-level trace with the supported default `ENABLE_LANGFUSE_OPENAI_AUTO_INSTRUMENTATION=false`.
3. LangGraph node events and IC/NOC/GRL events appear under the same request trace.

11
agent_framework_oci/libs/agent_framework/src/agent_framework/guardrails/calibrated/llm_client.py
View File

@@ -145,8 +145,17 @@ class GuardrailLLMClient:
except RuntimeError:
return asyncio.run(_call())
# ``ContextVar`` values do not cross ThreadPoolExecutor boundaries by
# default. Preserve the framework request/trace/parent observation when
# this legacy sync bridge needs a worker thread; otherwise a provider
# created inside the worker sees no active correlation context and the
# optional langfuse.openai wrapper may emit a standalone OpenAI-generation
# trace.
from contextvars import copy_context
context = copy_context()
with ThreadPoolExecutor(max_workers=1, thread_name_prefix="guardrail-compat") as executor:
return executor.submit(lambda: asyncio.run(_call())).result()
return executor.submit(context.run, lambda: asyncio.run(_call())).result()
def classify(
self,

23
agent_framework_oci/libs/agent_framework/src/agent_framework/llm/providers.py
View File

@@ -321,10 +321,27 @@ class OCICompatibleOpenAIProvider(LLMProvider):
getattr(settings, "ENABLE_LANGFUSE_OPENAI_AUTO_INSTRUMENTATION", None)
or os.getenv("ENABLE_LANGFUSE_OPENAI_AUTO_INSTRUMENTATION", "false")
).strip().lower() in {"1", "true", "yes", "on", "y"}
if self.telemetry is not None and use_langfuse_wrapper:
# The framework owns Langfuse correlation. Even compatibility paths may
# instantiate a provider without passing ``Telemetry`` explicitly while a
# request is already active (for example GuardrailLLMClient running in its
# sync bridge). In that situation langfuse.openai would auto-create an
# ``OpenAI-generation`` root trace instead of attaching to the business
# request. Treat an active framework observability context exactly like
# an injected Telemetry instance and keep the standard OpenAI client.
active_framework_trace = False
try:
from agent_framework.observability.context import get_observability_context
obs_ctx = get_observability_context()
active_framework_trace = bool(obs_ctx.trace_id or obs_ctx.request_id)
except Exception:
active_framework_trace = False
if use_langfuse_wrapper and (self.telemetry is not None or active_framework_trace):
logger.warning(
"ENABLE_LANGFUSE_OPENAI_AUTO_INSTRUMENTATION=true ignorado porque o provider já recebeu "
"Telemetry do framework; instrumentação dupla pode criar observations fora do contrato de mapping."
"ENABLE_LANGFUSE_OPENAI_AUTO_INSTRUMENTATION=true ignorado durante execução correlacionada "
"do framework; langfuse.openai pode criar OpenAI-generation como trace raiz separado."
)
use_langfuse_wrapper = False
if getattr(settings, "ENABLE_LANGFUSE", False) and use_langfuse_wrapper: