Skip to content

feat: add optional native trajectory tracing with OTLP export #313

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
lodyai wants to merge 2 commits into
base: main
Choose a base branch
from
Open

feat: add optional native trajectory tracing with OTLP export #313

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
76b407a
Add OpenTelemetry tracing support and update observability documentation
frostming Sep 16, 2026
3e9a71c
fix: improve OpenTelemetry import handling for type checking
frostming Sep 16, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,7 +48,13 @@ Documentation = "https://bub.build"
bub = "bub.__main__:app"

[project.optional-dependencies]
trace = [
"opentelemetry-api>=1.39.0",
"opentelemetry-sdk>=1.39.0",
"opentelemetry-exporter-otlp-proto-http>=1.39.0",
]
logfire = [
"bub[trace]",
"logfire>=4.31.0",
]

Expand Down
10 changes: 10 additions & 0 deletions src/bub/__main__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@

from __future__ import annotations

import os
import sys

import typer
Expand All @@ -22,6 +23,15 @@ def _instrument_bub(level: str) -> None:
logger.remove()
logger.add(sys.stderr, level=level, colorize=True, diagnose=False)

if os.getenv("OTEL_EXPORTER_OTLP_TRACES_ENDPOINT") or os.getenv("OTEL_EXPORTER_OTLP_ENDPOINT"):
from bub.tracing import configure_otlp

try:
configure_otlp()
except Exception as exc:
logger.warning("OTLP instrumentation disabled: {}", exc)
return

try:
import logfire
from logfire.integrations.loguru import LogfireHandler
Expand Down
163 changes: 104 additions & 59 deletions src/bub/builtin/agent.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,8 +7,8 @@
import re
import shlex
import time
from collections.abc import AsyncGenerator, AsyncIterator, Callable, Collection, Coroutine, Iterable
from contextlib import AsyncExitStack
from collections.abc import AsyncGenerator, AsyncIterator, Collection, Iterable
from contextlib import AsyncExitStack, aclosing
from dataclasses import dataclass, replace
from datetime import UTC, datetime
from functools import cached_property
Expand All @@ -34,6 +34,7 @@
ToolContext,
model_tools,
)
from bub.tracing import Span, current_span
from bub.turn import TurnState
from bub.utils import workspace_from_state

Expand Down Expand Up @@ -73,19 +74,6 @@ async def generator() -> AsyncIterator:

return AsyncStreamEvents(generator())

@staticmethod
def _events_with_callback(
events: AsyncStreamEvents, callback: Callable[[], Coroutine[Any, Any, Any]]
) -> AsyncStreamEvents:
async def generator() -> AsyncIterator[StreamEvent]:
try:
async for event in events:
yield event
finally:
await callback()

return AsyncStreamEvents(generator(), state=events._state)

async def run_stream(
self,
*,
Expand All @@ -96,37 +84,87 @@ async def run_stream(
allowed_skills: Collection[str] | None = None,
allowed_tools: Collection[str] | None = None,
) -> AsyncStreamEvents:
if not prompt:
return self._events_from_iterable([
StreamEvent("text", {"delta": "error: empty prompt"}),
StreamEvent("final", {"text": "error: empty prompt", "ok": False}),
])

state.setdefault("session_id", session_id)
tape = self.tape.session_tape(
session_id, workspace_from_state(state), context=replace(self.tape.context, state=state)
span = Span(
"invoke_agent bub",
{
"gen_ai.operation.name": "invoke_agent",
"gen_ai.agent.name": "bub",
"gen_ai.conversation.id": session_id,
},
)
merge_back = not session_id.startswith("temp/")
span.messages("gen_ai.input.messages", [{"role": "user", "content": prompt}])
stack = AsyncExitStack()
# The fork_tape context manager must not be exited until the last chunk of the stream is consumed.
tape = await stack.enter_async_context(tape.fork_tape(merge_back=merge_back))
await tape.ensure_bootstrap_anchor()
if isinstance(prompt, str) and prompt.strip().startswith(","):
result = await self._run_command(tape=tape, line=prompt.strip())
events = self._events_from_iterable([
StreamEvent("text", {"delta": result}),
StreamEvent("final", {"text": result, "ok": True}),
])
else:
events = await self._agent_loop(
tape=tape,
prompt=prompt,
model=model,
allowed_skills=allowed_skills,
allowed_tools=allowed_tools,
)
try:
with span.activate():
if not prompt:
events = self._events_from_iterable([
StreamEvent("text", {"delta": "error: empty prompt"}),
StreamEvent("final", {"text": "error: empty prompt", "ok": False}),
])
else:
state.setdefault("session_id", session_id)
tape = self.tape.session_tape(
session_id, workspace_from_state(state), context=replace(self.tape.context, state=state)
)
# Keep the tape fork open until the stream closes, even if it is never consumed.
tape = await stack.enter_async_context(
tape.fork_tape(merge_back=not session_id.startswith("temp/"))
)
await tape.ensure_bootstrap_anchor()
if isinstance(prompt, str) and prompt.strip().startswith(","):
result = await self._run_command(tape=tape, line=prompt.strip())
events = self._events_from_iterable([
StreamEvent("text", {"delta": result}),
StreamEvent("final", {"text": result, "ok": True}),
])
else:
events = await self._agent_loop(
tape=tape,
prompt=prompt,
model=model,
allowed_skills=allowed_skills,
allowed_tools=allowed_tools,
)
except BaseException as exc:
span.fail(exc)
try:
with span.activate():
await stack.aclose()
finally:
span.end()
raise
return AsyncStreamEvents(
self._trace_events(events, span),
state=events._state,
on_close=stack.aclose,
span=span,
)

return self._events_with_callback(events, callback=stack.aclose)
@staticmethod
async def _trace_events(events: AsyncStreamEvents, span: Span) -> AsyncGenerator[StreamEvent, None]:
messages: list[dict[str, Any]] = []
text: list[str] = []
calls: list[dict[str, Any]] = []
try:
async with aclosing(events):
async for event in events:
if span.recording:
if event.kind == "text":
text.append(str(event.data.get("delta", "")))
elif event.kind == "tool_call":
calls = event.data.get("tool_calls", [])
messages.append({"role": "assistant", "content": "".join(text), "tool_calls": calls})
text.clear()
elif event.kind == "tool_result":
for call, result in zip(calls, event.data.get("tool_results", []), strict=False):
messages.append({"role": "tool", "tool_call_id": call["id"], "content": result})
elif event.kind == "error":
span.fail(RuntimeError(str(event.data.get("message", "agent failed"))))
yield event
finally:
if text:
messages.append({"role": "assistant", "content": "".join(text)})
span.messages("gen_ai.output.messages", messages)

async def _run_command(self, tape: Tape, *, line: str) -> str:
line = line[1:].strip()
Expand Down Expand Up @@ -224,22 +262,23 @@ async def _stream_events_with_auto_handoff(
allowed_skills=allowed_skills,
allowed_tools=allowed_tools,
)
async for event in output:
yield event
if event.kind == "error":
elapsed_ms = int((time.monotonic() - start) * 1000)
await tape.append_event(
"loop.step",
{
"step": step,
"elapsed_ms": elapsed_ms,
"status": "error",
"error": event.data.get("message", ""),
"date": datetime.now(UTC).isoformat(),
},
)
elif event.kind == "final":
should_continue = bool(event.data.get("tool_calls") or event.data.get("tool_results"))
async with aclosing(output):
async for event in output:
yield event
if event.kind == "error":
elapsed_ms = int((time.monotonic() - start) * 1000)
await tape.append_event(
"loop.step",
{
"step": step,
"elapsed_ms": elapsed_ms,
"status": "error",
"error": event.data.get("message", ""),
"date": datetime.now(UTC).isoformat(),
},
)
elif event.kind == "final":
should_continue = bool(event.data.get("tool_calls") or event.data.get("tool_results"))
except Exception as exc:
error_message = f"{exc!s}"
elapsed_ms = int((time.monotonic() - start) * 1000)
Expand Down Expand Up @@ -363,6 +402,12 @@ async def _run_once_stream(
resolved_model = model or self.settings.model

model_tools_for_call = model_tools(tools)
if (span := current_span()) and span.recording:
span.set(**{
"gen_ai.tool.definitions": [
tool.to_schema()["function"] | {"type": "function"} for tool in model_tools_for_call
]
})
steering_inbox = self.framework.get_steering_inbox()
steering_envelopes = await steering_inbox.drain_messages(tape.context.state) if steering_inbox else []
steering_messages = list(
Expand Down
Loading
Loading