Workflow tracing to tilebox observability backend (#37)

* Automatically export workflow traces to tilebox

* Update task span attributes

* context.logger for task execute methods

* Query job logs and traces

* to_pandas conversion for job logs/traces

Author: lukasbindreiter

.gitignore

@@ -17,3 +17,5 @@ coverage.xml
 test-report.xml
 
 *.egg-info/
+
+.amp/

.pre-commit-config.yaml

@@ -9,7 +9,7 @@ repos:
     hooks:
       - id: sync-with-uv
   - repo: https://github.com/charliermarsh/ruff-pre-commit
-    rev: v0.15.7
+    rev: v0.15.12
     hooks:
       - id: ruff-check
         args: [--fix, --exit-non-zero-on-fix]

CHANGELOG.md

@@ -7,6 +7,17 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.52.0]
+
+### Added
+
+- `tilebox-workflows`: Added automatic OpenTelemetry-based logging and tracing instrumentation to a Tilebox
+  observability backend.
+- `tilebox-workflows`: Added `ExecutionContext.logger` and `ExecutionContext.tracer` access for task implementations to
+  emit structured logs and custom spans during task execution.
+- `tilebox-workflows`: Added `JobClient.query_logs()` and `JobClient.query_spans()` to fetch telemetry for a job, with
+  list-like results that can be converted to pandas DataFrames via `to_pandas()`.
+
 ## [0.51.0] - 2026-04-07
 
 ### Changed
@@ -357,7 +368,8 @@ the first client that does not cache data (since it's already on the local file
 - Released under the [MIT](https://opensource.org/license/mit) license.
 - Released packages: `tilebox-datasets`, `tilebox-workflows`, `tilebox-storage`, `tilebox-grpc`
 
-[Unreleased]: https://github.com/tilebox/tilebox-python/compare/v0.51.0...HEAD
+[Unreleased]: https://github.com/tilebox/tilebox-python/compare/v0.52.0...HEAD
+[0.52.0]: https://github.com/tilebox/tilebox-python/compare/v0.51.0...v0.52.0
 [0.51.0]: https://github.com/tilebox/tilebox-python/compare/v0.50.1...v0.51.0
 [0.50.1]: https://github.com/tilebox/tilebox-python/compare/v0.50.0...v0.50.1
 [0.50.0]: https://github.com/tilebox/tilebox-python/compare/v0.49.0...v0.50.0

tilebox-datasets/tests/data/datapoint.py

@@ -32,8 +32,6 @@
 from tests.query.pagination import paginations
 from tests.query.time_interval import i64_datetimes
 from tilebox.datasets.data.datapoint import AnyMessage, IngestResponse, QueryResultPage, RepeatedAny
-from tilebox.datasets.datasets.v1 import core_pb2
-from tilebox.datasets.query.time_interval import datetime_to_timestamp
 
 
 @composite
@@ -138,8 +136,7 @@ def example_pandas_datapoints(draw: DrawFn) -> pd.DataFrame:
 @composite
 def anys(draw: DrawFn, generated_fields: bool = False, missing_fields: bool = False) -> AnyMessage:
     """A hypothesis strategy for generating random Any messages"""
-    # we need a random byte string here, but let's actually use a valid protobuf message, in this
-    # case because its easy to generate let's use a DatapointMetadata message
+    # we need a random byte string here, but let's actually use a valid protobuf message
     datapoint = draw(example_datapoints(generated_fields, missing_fields))
     return AnyMessage(example_dataset_type_url(), datapoint.SerializeToString())
 
@@ -158,14 +155,6 @@ def repeated_anys(
     return RepeatedAny(example_dataset_type_url(), [dp.SerializeToString() for dp in datapoints])
 
 
-@composite
-def datapoint_metadata_messages(draw: DrawFn) -> core_pb2.DatapointMetadata:
-    event_time = datetime_to_timestamp(draw(i64_datetimes))
-    ingestion_time = datetime_to_timestamp(draw(i64_datetimes))
-    data_point_id = str(draw(uuids(version=4)))
-    return core_pb2.DatapointMetadata(event_time=event_time, ingestion_time=ingestion_time, id=data_point_id)
-
-
 @composite
 def query_result_pages(
     draw: DrawFn, empty_next_page: bool | None = None, generated_fields: bool = True, missing_fields: bool = False

tilebox-datasets/tilebox/datasets/buf/validate/validate_pb2.py

@@ -388,7 +388,7 @@ class BoolRules(_message.Message):
     def __init__(self, const: bool = ..., example: _Optional[_Iterable[bool]] = ...) -> None: ...
 
 class StringRules(_message.Message):
-    __slots__ = ("const", "len", "min_len", "max_len", "len_bytes", "min_bytes", "max_bytes", "pattern", "prefix", "suffix", "contains", "not_contains", "not_in", "email", "hostname", "ip", "ipv4", "ipv6", "uri", "uri_ref", "address", "uuid", "tuuid", "ip_with_prefixlen", "ipv4_with_prefixlen", "ipv6_with_prefixlen", "ip_prefix", "ipv4_prefix", "ipv6_prefix", "host_and_port", "ulid", "well_known_regex", "strict", "example")
+    __slots__ = ("const", "len", "min_len", "max_len", "len_bytes", "min_bytes", "max_bytes", "pattern", "prefix", "suffix", "contains", "not_contains", "not_in", "email", "hostname", "ip", "ipv4", "ipv6", "uri", "uri_ref", "address", "uuid", "tuuid", "ip_with_prefixlen", "ipv4_with_prefixlen", "ipv6_with_prefixlen", "ip_prefix", "ipv4_prefix", "ipv6_prefix", "host_and_port", "ulid", "protobuf_fqn", "protobuf_dot_fqn", "well_known_regex", "strict", "example")
     Extensions: _python_message._ExtensionDict
     CONST_FIELD_NUMBER: _ClassVar[int]
     LEN_FIELD_NUMBER: _ClassVar[int]
@@ -422,6 +422,8 @@ class StringRules(_message.Message):
     IPV6_PREFIX_FIELD_NUMBER: _ClassVar[int]
     HOST_AND_PORT_FIELD_NUMBER: _ClassVar[int]
     ULID_FIELD_NUMBER: _ClassVar[int]
+    PROTOBUF_FQN_FIELD_NUMBER: _ClassVar[int]
+    PROTOBUF_DOT_FQN_FIELD_NUMBER: _ClassVar[int]
     WELL_KNOWN_REGEX_FIELD_NUMBER: _ClassVar[int]
     STRICT_FIELD_NUMBER: _ClassVar[int]
     EXAMPLE_FIELD_NUMBER: _ClassVar[int]
@@ -456,10 +458,12 @@ class StringRules(_message.Message):
     ipv6_prefix: bool
     host_and_port: bool
     ulid: bool
+    protobuf_fqn: bool
+    protobuf_dot_fqn: bool
     well_known_regex: KnownRegex
     strict: bool
     example: _containers.RepeatedScalarFieldContainer[str]
-    def __init__(self, const: _Optional[str] = ..., len: _Optional[int] = ..., min_len: _Optional[int] = ..., max_len: _Optional[int] = ..., len_bytes: _Optional[int] = ..., min_bytes: _Optional[int] = ..., max_bytes: _Optional[int] = ..., pattern: _Optional[str] = ..., prefix: _Optional[str] = ..., suffix: _Optional[str] = ..., contains: _Optional[str] = ..., not_contains: _Optional[str] = ..., not_in: _Optional[_Iterable[str]] = ..., email: bool = ..., hostname: bool = ..., ip: bool = ..., ipv4: bool = ..., ipv6: bool = ..., uri: bool = ..., uri_ref: bool = ..., address: bool = ..., uuid: bool = ..., tuuid: bool = ..., ip_with_prefixlen: bool = ..., ipv4_with_prefixlen: bool = ..., ipv6_with_prefixlen: bool = ..., ip_prefix: bool = ..., ipv4_prefix: bool = ..., ipv6_prefix: bool = ..., host_and_port: bool = ..., ulid: bool = ..., well_known_regex: _Optional[_Union[KnownRegex, str]] = ..., strict: bool = ..., example: _Optional[_Iterable[str]] = ..., **kwargs) -> None: ...
+    def __init__(self, const: _Optional[str] = ..., len: _Optional[int] = ..., min_len: _Optional[int] = ..., max_len: _Optional[int] = ..., len_bytes: _Optional[int] = ..., min_bytes: _Optional[int] = ..., max_bytes: _Optional[int] = ..., pattern: _Optional[str] = ..., prefix: _Optional[str] = ..., suffix: _Optional[str] = ..., contains: _Optional[str] = ..., not_contains: _Optional[str] = ..., not_in: _Optional[_Iterable[str]] = ..., email: bool = ..., hostname: bool = ..., ip: bool = ..., ipv4: bool = ..., ipv6: bool = ..., uri: bool = ..., uri_ref: bool = ..., address: bool = ..., uuid: bool = ..., tuuid: bool = ..., ip_with_prefixlen: bool = ..., ipv4_with_prefixlen: bool = ..., ipv6_with_prefixlen: bool = ..., ip_prefix: bool = ..., ipv4_prefix: bool = ..., ipv6_prefix: bool = ..., host_and_port: bool = ..., ulid: bool = ..., protobuf_fqn: bool = ..., protobuf_dot_fqn: bool = ..., well_known_regex: _Optional[_Union[KnownRegex, str]] = ..., strict: bool = ..., example: _Optional[_Iterable[str]] = ..., **kwargs) -> None: ...
 
 class BytesRules(_message.Message):
     __slots__ = ("const", "len", "min_len", "max_len", "pattern", "prefix", "suffix", "contains", "not_in", "ip", "ipv4", "ipv6", "uuid", "example")