haystack/test/tracing/utils.py
mathislucka eec91824bc
fix: pipeline run bugs in cyclic and acyclic pipelines (#8707)
* add component checks

* pipeline should run deterministically

* add FIFOQueue

* add agent tests

* add order dependent tests

* run new tests

* remove code that is not needed

* test: intermediate from cycle outputs are available outside cycle

* add tests for component checks (Claude)

* adapt tests for component checks (o1 review)

* chore: format

* remove tests that aren't needed anymore

* add _calculate_priority tests

* revert accidental change in pyproject.toml

* test format conversion

* adapt to naming convention

* chore: proper docstrings and type hints for PQ

* format

* add more unit tests

* rm unneeded comments

* test input consumption

* lint

* fix: docstrings

* lint

* format

* format

* fix license header

* fix license header

* add component run tests

* fix: pass correct input format to tracing

* fix types

* format

* format

* types

* add defaults from Socket instead of signature

- otherwise components with dynamic inputs would fail

* fix test names

* still wait for optional inputs on greedy variadic sockets

- mirrors previous behavior

* fix format

* wip: warn for ambiguous running order

* wip: alternative warning

* fix license header

* make code more readable

Co-authored-by: Amna Mubashar <amnahkhan.ak@gmail.com>

* Introduce content tracing to a behavioral test

* Fixing linting

* Remove debug print statements

* Fix tracer tests

* remove print

* test: test for component inputs

* test: remove testing for run order

* chore: update component checks from experimental

* chore: update pipeline and base from experimental

* refactor: remove unused method

* refactor: remove unused method

* refactor: outdated comment

* refactor: inputs state is updated as side effect

- to prepare for AsyncPipeline implementation

* format

* test: add file conversion test

* format

* fix: original implementation deepcopies outputs

* lint

* fix: from_dict was updated

* fix: format

* fix: test

* test: add test for thread safety

* remove unused imports

* format

* test: FIFOPriorityQueue

* chore: add release note

* fix: resolve merge conflict with mermaid changes

* fix: format

* fix: remove unused import

* refactor: rename to avoid accidental conflicts

* chore: remove unused inputs, add missing license header

* chore: extend release notes

* Update releasenotes/notes/fix-pipeline-run-2fefeafc705a6d91.yaml

Co-authored-by: Amna Mubashar <amnahkhan.ak@gmail.com>

* fix: format

* fix: format

* Update release note

---------

Co-authored-by: Amna Mubashar <amnahkhan.ak@gmail.com>
Co-authored-by: David S. Batista <dsbatista@gmail.com>
2025-02-06 14:19:47 +00:00

53 lines
1.6 KiB
Python

# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
#
# SPDX-License-Identifier: Apache-2.0
import contextlib
import dataclasses
import uuid
from typing import Dict, Any, Optional, List, Iterator
from haystack.tracing import Span, Tracer
@dataclasses.dataclass
class SpyingSpan(Span):
operation_name: str
parent_span: Optional[Span] = None
tags: Dict[str, Any] = dataclasses.field(default_factory=dict)
trace_id: Optional[str] = dataclasses.field(default_factory=lambda: str(uuid.uuid4()))
span_id: Optional[str] = dataclasses.field(default_factory=lambda: str(uuid.uuid4()))
def set_tag(self, key: str, value: Any) -> None:
self.tags[key] = value
def get_correlation_data_for_logs(self) -> Dict[str, Any]:
return {"trace_id": self.trace_id, "span_id": self.span_id}
def set_content_tag(self, key: str, value: Any) -> None:
"""
Set a content tag, but only if content tracing is enabled in the tracer.
"""
self.set_tag(key, value)
class SpyingTracer(Tracer):
def current_span(self) -> Optional[Span]:
return self.spans[-1] if self.spans else None
def __init__(self) -> None:
self.spans: List[SpyingSpan] = []
@contextlib.contextmanager
def trace(
self, operation_name: str, tags: Optional[Dict[str, Any]] = None, parent_span: Optional[Span] = None
) -> Iterator[Span]:
new_span = SpyingSpan(operation_name, parent_span)
for key, value in (tags or {}).items():
new_span.set_tag(key, value)
self.spans.append(new_span)
yield new_span