fourtheorem-tempo-worker 0.3.0__tar.gz

fourtheorem_tempo_worker-0.3.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

fourtheorem_tempo_worker-0.3.0/PKG-INFO

@@ -0,0 +1,154 @@
+Metadata-Version: 2.4
+Name: fourtheorem-tempo-worker
+Version: 0.3.0
+Summary: Tempo worker SDK: failure reporting, logging, and custom metrics for worker tasks
+Author: fourTheorem
+License-Expression: Apache-2.0
+License-File: LICENSE
+Requires-Dist: opentelemetry-api>=1.25
+Requires-Python: >=3.11
+Project-URL: Homepage, https://fourtheorem.com/high-performance-compute/
+Description-Content-Type: text/markdown
+
+# Tempo Worker SDK (Python)
+
+A Tempo **worker** is a process that Tempo runs on its compute backends to
+execute tasks. A **task** is your own custom business logic, packaged as a
+function with this signature:
+
+```python
+from pathlib import Path
+
+def run(working_dir: Path, params: dict) -> None: ...
+```
+
+Tempo calls `run` with a working directory (inputs under
+`working_dir/inputs/`, outputs written to `working_dir/outputs/`) and the
+job parameters. Task code needs no platform imports, so you do not need an
+SDK to write a task. An SDK is still convenient: it gives you easy,
+standardised access to the job run context, structured logging, custom
+metrics, and failure reporting. `fourtheorem-tempo-worker` (import name
+`tempo_worker`) provides all of this.
+
+```bash
+pip install fourtheorem-tempo-worker
+```
+
+When you run task code yourself (locally, or in unit tests) instead of on a
+Tempo worker, this is a **standalone run**: the SDK detects it and falls
+back to the safe defaults noted in each section below.
+
+## Features
+
+Here is the list of features you find in the SDK.
+
+### Run context
+
+`current_context()` returns the identifiers of the running job attempt.
+
+```python
+from tempo_worker import current_context
+
+def run(working_dir, params):
+    ctx = current_context()
+    if ctx is not None:
+        print(ctx.workload_id, ctx.job_id, ctx.attempt, ctx.worker_id)
+```
+
+The context object carries four properties:
+
+- `workload_id`: the workload the job belongs to.
+- `job_id`: the job the worker is executing.
+- `attempt`: the zero-based retry attempt number.
+- `worker_id`: the worker process running the job.
+
+In a standalone run, `current_context()` returns `None`.
+
+### Logging
+
+`get_logger` returns a standard library logger that emits structured,
+single-line JSON records, ready for observability and monitoring tools. On a
+Tempo worker each record automatically carries `workload_id`, `job_id`,
+`attempt`, and `worker_id`, so you can filter and correlate task logs with
+the rest of the platform logs.
+
+```python
+from tempo_worker import get_logger
+
+logger = get_logger(__name__)
+
+def run(working_dir, params):
+    logger.info("Pricing started", extra={"scenario_count": len(params["scenarios"])})
+```
+
+In a standalone run the SDK installs a JSON handler with the same field
+shape, so log lines look identical in both environments. Standalone runs
+read the service name from `TEMPO_SERVICE_NAME` (default `tempo-task`) and
+the level from `LOG_LEVEL` (default `INFO`).
+
+### Custom metrics
+
+The `tempo_worker.metrics` module provides `counter`, `histogram`, and
+`up_down_counter`. They create instruments that export through the worker's
+metrics pipeline. Tempo prefixes each name with `tr_custom_` and attaches
+the `workload_id` label from the run context. The series appear in the
+Tempo Grafana dashboard under "Custom task metrics".
+
+```python
+from tempo_worker import metrics
+
+rows = metrics.counter("rows_processed", description="Rows processed per job.")
+latency = metrics.histogram("pricing_seconds", unit="s")
+
+def run(working_dir, params):
+    rows.add(1_000)
+    latency.record(2.31)
+```
+
+The attribute keys `job_id` and `worker_id` are rejected: their cardinality
+is unbounded and would overload the time-series store.
+
+A standalone run has no configured metrics provider, so every call is a
+no-op.
+
+> **A note on naming.** You might have noticed that logging has a factory
+> function, `get_logger`, while metrics is a module namespace. This is
+> deliberate: each follows the strongest convention in its own domain.
+> `get_logger(__name__)` mirrors the stdlib `logging.getLogger(__name__)`
+> idiom, and `metrics.counter(...)` mirrors the OpenTelemetry module-style
+> API. A logger is a stateful object you keep; the metrics functions are
+> factories for named instruments.
+
+### Explicit failure reporting
+
+Raise `TaskFailure` to report a failure with structured context. Set
+`retriable=False` to tell the scheduler not to retry the job, even when retry
+budget remains. Use it when a retry cannot change the outcome, for example
+corrupt input data or invalid parameters: every attempt would fail the same
+way, so skipping the retries saves time and compute, and the workload
+reaches its final state sooner.
+
+The `detail` dict is stored in the job attempt record, so
+keep its values JSON-serialisable.
+
+```python
+from tempo_worker import TaskFailure
+
+def run(working_dir, params):
+    if "rate_table" not in params:
+        raise TaskFailure(
+            "missing rate_table parameter",
+            retriable=False,
+            detail={"missing_field": "rate_table"},
+        )
+```
+
+By default, any exception other than `TaskFailure` is reported as a
+retriable failure.
+
+In a standalone run, `TaskFailure` is a plain exception and propagates
+normally.
+
+## Versioning
+
+The SDK follows the Tempo platform release version.

fourtheorem_tempo_worker-0.3.0/README.md

@@ -0,0 +1,142 @@
+# Tempo Worker SDK (Python)
+
+A Tempo **worker** is a process that Tempo runs on its compute backends to
+execute tasks. A **task** is your own custom business logic, packaged as a
+function with this signature:
+
+```python
+from pathlib import Path
+
+def run(working_dir: Path, params: dict) -> None: ...
+```
+
+Tempo calls `run` with a working directory (inputs under
+`working_dir/inputs/`, outputs written to `working_dir/outputs/`) and the
+job parameters. Task code needs no platform imports, so you do not need an
+SDK to write a task. An SDK is still convenient: it gives you easy,
+standardised access to the job run context, structured logging, custom
+metrics, and failure reporting. `fourtheorem-tempo-worker` (import name
+`tempo_worker`) provides all of this.
+
+```bash
+pip install fourtheorem-tempo-worker
+```
+
+When you run task code yourself (locally, or in unit tests) instead of on a
+Tempo worker, this is a **standalone run**: the SDK detects it and falls
+back to the safe defaults noted in each section below.
+
+## Features
+
+Here is the list of features you find in the SDK.
+
+### Run context
+
+`current_context()` returns the identifiers of the running job attempt.
+
+```python
+from tempo_worker import current_context
+
+def run(working_dir, params):
+    ctx = current_context()
+    if ctx is not None:
+        print(ctx.workload_id, ctx.job_id, ctx.attempt, ctx.worker_id)
+```
+
+The context object carries four properties:
+
+- `workload_id`: the workload the job belongs to.
+- `job_id`: the job the worker is executing.
+- `attempt`: the zero-based retry attempt number.
+- `worker_id`: the worker process running the job.
+
+In a standalone run, `current_context()` returns `None`.
+
+### Logging
+
+`get_logger` returns a standard library logger that emits structured,
+single-line JSON records, ready for observability and monitoring tools. On a
+Tempo worker each record automatically carries `workload_id`, `job_id`,
+`attempt`, and `worker_id`, so you can filter and correlate task logs with
+the rest of the platform logs.
+
+```python
+from tempo_worker import get_logger
+
+logger = get_logger(__name__)
+
+def run(working_dir, params):
+    logger.info("Pricing started", extra={"scenario_count": len(params["scenarios"])})
+```
+
+In a standalone run the SDK installs a JSON handler with the same field
+shape, so log lines look identical in both environments. Standalone runs
+read the service name from `TEMPO_SERVICE_NAME` (default `tempo-task`) and
+the level from `LOG_LEVEL` (default `INFO`).
+
+### Custom metrics
+
+The `tempo_worker.metrics` module provides `counter`, `histogram`, and
+`up_down_counter`. They create instruments that export through the worker's
+metrics pipeline. Tempo prefixes each name with `tr_custom_` and attaches
+the `workload_id` label from the run context. The series appear in the
+Tempo Grafana dashboard under "Custom task metrics".
+
+```python
+from tempo_worker import metrics
+
+rows = metrics.counter("rows_processed", description="Rows processed per job.")
+latency = metrics.histogram("pricing_seconds", unit="s")
+
+def run(working_dir, params):
+    rows.add(1_000)
+    latency.record(2.31)
+```
+
+The attribute keys `job_id` and `worker_id` are rejected: their cardinality
+is unbounded and would overload the time-series store.
+
+A standalone run has no configured metrics provider, so every call is a
+no-op.
+
+> **A note on naming.** You might have noticed that logging has a factory
+> function, `get_logger`, while metrics is a module namespace. This is
+> deliberate: each follows the strongest convention in its own domain.
+> `get_logger(__name__)` mirrors the stdlib `logging.getLogger(__name__)`
+> idiom, and `metrics.counter(...)` mirrors the OpenTelemetry module-style
+> API. A logger is a stateful object you keep; the metrics functions are
+> factories for named instruments.
+
+### Explicit failure reporting
+
+Raise `TaskFailure` to report a failure with structured context. Set
+`retriable=False` to tell the scheduler not to retry the job, even when retry
+budget remains. Use it when a retry cannot change the outcome, for example
+corrupt input data or invalid parameters: every attempt would fail the same
+way, so skipping the retries saves time and compute, and the workload
+reaches its final state sooner.
+
+The `detail` dict is stored in the job attempt record, so
+keep its values JSON-serialisable.
+
+```python
+from tempo_worker import TaskFailure
+
+def run(working_dir, params):
+    if "rate_table" not in params:
+        raise TaskFailure(
+            "missing rate_table parameter",
+            retriable=False,
+            detail={"missing_field": "rate_table"},
+        )
+```
+
+By default, any exception other than `TaskFailure` is reported as a
+retriable failure.
+
+In a standalone run, `TaskFailure` is a plain exception and propagates
+normally.
+
+## Versioning
+
+The SDK follows the Tempo platform release version.

fourtheorem_tempo_worker-0.3.0/pyproject.toml

@@ -0,0 +1,28 @@
+[project]
+name = "fourtheorem-tempo-worker"
+version = "0.3.0"
+description = "Tempo worker SDK: failure reporting, logging, and custom metrics for worker tasks"
+authors = [{ name = "fourTheorem" }]
+license = "Apache-2.0"
+license-files = ["LICENSE"]
+requires-python = ">=3.11"
+readme = "README.md"
+dependencies = [
+    "opentelemetry-api>=1.25",
+]
+
+[tool.uv.build-backend]
+module-name = "tempo_worker"
+
+[build-system]
+requires = ["uv_build>=0.11.0,<0.12.0"]
+build-backend = "uv_build"
+
+[tool.ruff]
+line-length = 120
+
+[tool.ruff.lint]
+select = ["F", "I", "UP"]
+
+[project.urls]
+Homepage = "https://fourtheorem.com/high-performance-compute/"

fourtheorem_tempo_worker-0.3.0/src/tempo_worker/__init__.py

@@ -0,0 +1,18 @@
+"""Tempo worker SDK.
+
+Public surface for customer task code: explicit failure reporting
+(:class:`TaskFailure`), Tempo-shaped logging (:func:`get_logger`), custom
+metrics (:mod:`tempo_worker.metrics`), and read access to the per-job run
+context (:func:`current_context`).
+"""
+
+from tempo_worker.context import TaskRunContext, current_context
+from tempo_worker.errors import TaskFailure
+from tempo_worker.logging import get_logger
+
+__all__ = [
+    "TaskFailure",
+    "TaskRunContext",
+    "current_context",
+    "get_logger",
+]

fourtheorem_tempo_worker-0.3.0/src/tempo_worker/context.py

@@ -0,0 +1,43 @@
+"""Per-job run context exposed to task code.
+
+The worker harness sets the context around each task invocation. Task code
+reads it through :func:`current_context`; the ``_set_run_context`` /
+``_reset_run_context`` pair is the harness integration surface.
+"""
+
+from __future__ import annotations
+
+from contextvars import ContextVar, Token
+from dataclasses import dataclass
+
+
+@dataclass(frozen=True, slots=True)
+class TaskRunContext:
+    """Identifiers for the job attempt that is currently executing.
+
+    :param workload_id: Workload the job belongs to.
+    :param job_id: Job identifier.
+    :param attempt: Zero-based retry attempt number.
+    :param worker_id: Identifier of the worker process running the job.
+    """
+
+    workload_id: str
+    job_id: str
+    attempt: int
+    worker_id: str
+
+
+_CURRENT: ContextVar[TaskRunContext | None] = ContextVar("tempo_worker_run_context", default=None)
+
+
+def current_context() -> TaskRunContext | None:
+    """Return the context of the running job, or ``None`` outside the harness."""
+    return _CURRENT.get()
+
+
+def _set_run_context(ctx: TaskRunContext) -> Token[TaskRunContext | None]:
+    return _CURRENT.set(ctx)
+
+
+def _reset_run_context(token: Token[TaskRunContext | None]) -> None:
+    _CURRENT.reset(token)

fourtheorem_tempo_worker-0.3.0/src/tempo_worker/errors.py

@@ -0,0 +1,27 @@
+"""Explicit failure reporting for worker tasks."""
+
+from __future__ import annotations
+
+from typing import Any
+
+
+class TaskFailure(Exception):
+    """Explicit task failure raised by task code.
+
+    The Tempo worker harness maps this exception to a failed completion.
+    ``retriable=False`` tells the scheduler not to retry the job, even when
+    retry budget remains. ``detail`` is persisted in the job attempt record,
+    so keep its values JSON-serialisable.
+
+    Outside the harness this is a plain exception and propagates normally.
+
+    :param message: Human-readable failure description.
+    :param retriable: ``False`` marks the failure as permanent.
+    :param detail: Optional structured context stored with the attempt record.
+    """
+
+    def __init__(self, message: str, *, retriable: bool = True, detail: dict[str, Any] | None = None) -> None:
+        super().__init__(message)
+        self.message = message
+        self.retriable = retriable
+        self.detail = detail

fourtheorem_tempo_worker-0.3.0/src/tempo_worker/logging.py

@@ -0,0 +1,136 @@
+"""Tempo-shaped structured logging for worker tasks.
+
+Under the worker harness the root logger already emits single-line JSON, so
+:func:`get_logger` only attaches a filter that injects the run context into
+each record. In a standalone run (no handlers configured) it also installs a
+JSON handler with the same field shape, so task logs look identical in both
+environments.
+"""
+
+from __future__ import annotations
+
+import json
+import logging
+import os
+import sys
+from datetime import UTC, datetime
+from typing import Any
+
+from tempo_worker.context import current_context
+
+# Keep in sync with ts_common.logging._RESERVED_LOG_RECORD_FIELDS. The SDK
+# stays dependency-free, so the set is duplicated rather than imported.
+_RESERVED_LOG_RECORD_FIELDS = {
+    "args",
+    "asctime",
+    "created",
+    "exc_info",
+    "exc_text",
+    "filename",
+    "funcName",
+    "levelname",
+    "levelno",
+    "lineno",
+    "module",
+    "msecs",
+    "message",
+    "msg",
+    "name",
+    "pathname",
+    "process",
+    "processName",
+    "relativeCreated",
+    "stack_info",
+    "thread",
+    "threadName",
+    "taskName",
+}
+
+
+def _normalise_log_value(value: Any) -> Any:
+    if isinstance(value, str | int | float | bool) or value is None:
+        return value
+    if isinstance(value, dict):
+        return {str(key): _normalise_log_value(item) for key, item in value.items()}
+    if isinstance(value, list | tuple | set | frozenset):
+        return [_normalise_log_value(item) for item in value]
+    return str(value)
+
+
+class JsonFormatter(logging.Formatter):
+    """Render log records as single-line JSON objects.
+
+    Keep in sync with ``ts_common.logging.JsonFormatter`` (same field shape),
+    duplicated so the SDK needs no platform dependency.
+    """
+
+    def __init__(self, service_name: str) -> None:
+        super().__init__()
+        self._service_name = service_name
+
+    def format(self, record: logging.LogRecord) -> str:
+        """Serialise the record to a compact JSON string."""
+        payload: dict[str, Any] = {
+            "timestamp": datetime.fromtimestamp(record.created, tz=UTC).isoformat(timespec="milliseconds"),
+            "level": record.levelname,
+            "logger": record.name,
+            "service": self._service_name,
+            "message": record.getMessage(),
+        }
+        for key, value in record.__dict__.items():
+            if key.startswith("_") or key in _RESERVED_LOG_RECORD_FIELDS:
+                continue
+            payload[key] = _normalise_log_value(value)
+        if record.exc_info is not None:
+            payload["exception"] = self.formatException(record.exc_info)
+        if record.stack_info is not None:
+            payload["stack"] = self.formatStack(record.stack_info)
+        return json.dumps(payload, separators=(",", ":"), sort_keys=True)
+
+
+class _ContextInjectionFilter(logging.Filter):
+    """Copy the run-context identifiers onto each record.
+
+    Explicit ``extra`` values win over injected ones. Outside the harness the
+    filter is a no-op.
+    """
+
+    def filter(self, record: logging.LogRecord) -> bool:
+        ctx = current_context()
+        if ctx is None:
+            return True
+        for key, value in (
+            ("workload_id", ctx.workload_id),
+            ("job_id", ctx.job_id),
+            ("attempt", ctx.attempt),
+            ("worker_id", ctx.worker_id),
+        ):
+            if not hasattr(record, key):
+                setattr(record, key, value)
+        return True
+
+
+def get_logger(name: str | None = None) -> logging.Logger:
+    """Return a stdlib logger wired for Tempo-shaped structured output.
+
+    The logger carries a filter that injects ``workload_id``, ``job_id``,
+    ``attempt``, and ``worker_id`` from the current run context. When no
+    handler is configured on the root logger (a standalone run), a JSON
+    handler with the Tempo field shape is installed: the service name comes
+    from ``TEMPO_SERVICE_NAME`` (default ``tempo-task``) and the level from
+    ``LOG_LEVEL`` (default ``INFO``).
+
+    :param name: Logger name, usually ``__name__``.
+    """
+    logger = logging.getLogger(name)
+    if not any(isinstance(f, _ContextInjectionFilter) for f in logger.filters):
+        logger.addFilter(_ContextInjectionFilter())
+
+    root_logger = logging.getLogger()
+    if not root_logger.handlers:
+        handler = logging.StreamHandler(sys.stdout)
+        handler.setFormatter(JsonFormatter(service_name=os.environ.get("TEMPO_SERVICE_NAME", "tempo-task")))
+        root_logger.addHandler(handler)
+        root_logger.setLevel(os.environ.get("LOG_LEVEL", "INFO").upper())
+
+    return logger

fourtheorem_tempo_worker-0.3.0/src/tempo_worker/metrics.py

@@ -0,0 +1,151 @@
+"""Custom metrics emission for worker tasks.
+
+Instruments are created from the ``tempo`` meter, so they export through the
+MeterProvider the worker harness initialises. Without a configured provider
+(a standalone run) every call is a no-op.
+
+Guardrails keep customer series compatible with the platform conventions:
+names get the ``tr_custom_`` prefix, ``workload_id`` is attached from the run
+context, and the unbounded-cardinality keys ``job_id`` and ``worker_id`` are
+rejected as attributes.
+"""
+
+from __future__ import annotations
+
+import re
+from typing import Any
+
+from opentelemetry import metrics as otel_metrics
+
+from tempo_worker.context import current_context
+
+_PREFIX = "tr_custom_"
+# Keep in sync with ts_adapters.metrics.catalog._METER_NAME.
+_METER_NAME = "tempo"
+_FORBIDDEN_ATTRIBUTE_KEYS = frozenset({"job_id", "worker_id"})
+_NAME_RE = re.compile(r"^[a-z][a-z0-9_]*$")
+
+_instruments: dict[tuple[str, str], Any] = {}
+
+
+def _full_name(name: str) -> str:
+    if name.startswith("tr_"):
+        raise ValueError(f"Metric name {name!r} must not start with 'tr_'; the prefix is added automatically")
+    if not _NAME_RE.match(name):
+        raise ValueError(f"Metric name {name!r} must match {_NAME_RE.pattern}")
+    return _PREFIX + name
+
+
+def _merged_attributes(attributes: dict[str, Any] | None) -> dict[str, Any]:
+    merged = dict(attributes) if attributes else {}
+    forbidden = _FORBIDDEN_ATTRIBUTE_KEYS & merged.keys()
+    if forbidden:
+        raise ValueError(f"Attribute keys {sorted(forbidden)} are not allowed: their cardinality is unbounded")
+    ctx = current_context()
+    if ctx is not None:
+        merged["workload_id"] = ctx.workload_id
+    return merged
+
+
+class Counter:
+    """Monotonic counter named ``tr_custom_<name>``."""
+
+    def __init__(self, instrument: otel_metrics.Counter) -> None:
+        self._instrument = instrument
+
+    def add(self, amount: int | float = 1, attributes: dict[str, Any] | None = None) -> None:
+        """Add a non-negative amount to the counter.
+
+        :param amount: Increment to record.
+        :param attributes: Optional labels. ``workload_id`` is added from the
+            run context; ``job_id`` and ``worker_id`` are rejected.
+        :raises ValueError: If a forbidden attribute key is present.
+        """
+        self._instrument.add(amount, _merged_attributes(attributes))
+
+
+class UpDownCounter:
+    """Non-monotonic counter named ``tr_custom_<name>``."""
+
+    def __init__(self, instrument: otel_metrics.UpDownCounter) -> None:
+        self._instrument = instrument
+
+    def add(self, amount: int | float, attributes: dict[str, Any] | None = None) -> None:
+        """Add a positive or negative amount to the counter.
+
+        :param amount: Increment or decrement to record.
+        :param attributes: Optional labels. ``workload_id`` is added from the
+            run context; ``job_id`` and ``worker_id`` are rejected.
+        :raises ValueError: If a forbidden attribute key is present.
+        """
+        self._instrument.add(amount, _merged_attributes(attributes))
+
+
+class Histogram:
+    """Distribution instrument named ``tr_custom_<name>``."""
+
+    def __init__(self, instrument: otel_metrics.Histogram) -> None:
+        self._instrument = instrument
+
+    def record(self, value: int | float, attributes: dict[str, Any] | None = None) -> None:
+        """Record one observed value.
+
+        :param value: Observation to record.
+        :param attributes: Optional labels. ``workload_id`` is added from the
+            run context; ``job_id`` and ``worker_id`` are rejected.
+        :raises ValueError: If a forbidden attribute key is present.
+        """
+        self._instrument.record(value, _merged_attributes(attributes))
+
+
+def counter(name: str, *, unit: str = "1", description: str = "") -> Counter:
+    """Return the counter ``tr_custom_<name>``, creating it on first use.
+
+    ``unit`` and ``description`` apply only on first creation.
+
+    :param name: Metric name without the ``tr_custom_`` prefix. Must match
+        ``^[a-z][a-z0-9_]*$``.
+    :raises ValueError: If the name is invalid or already carries a ``tr_`` prefix.
+    """
+    full_name = _full_name(name)
+    key = ("counter", full_name)
+    if key not in _instruments:
+        instrument = otel_metrics.get_meter(_METER_NAME).create_counter(full_name, unit=unit, description=description)
+        _instruments[key] = Counter(instrument)
+    return _instruments[key]
+
+
+def up_down_counter(name: str, *, unit: str = "1", description: str = "") -> UpDownCounter:
+    """Return the up-down counter ``tr_custom_<name>``, creating it on first use.
+
+    ``unit`` and ``description`` apply only on first creation.
+
+    :param name: Metric name without the ``tr_custom_`` prefix. Must match
+        ``^[a-z][a-z0-9_]*$``.
+    :raises ValueError: If the name is invalid or already carries a ``tr_`` prefix.
+    """
+    full_name = _full_name(name)
+    key = ("up_down_counter", full_name)
+    if key not in _instruments:
+        instrument = otel_metrics.get_meter(_METER_NAME).create_up_down_counter(
+            full_name, unit=unit, description=description
+        )
+        _instruments[key] = UpDownCounter(instrument)
+    return _instruments[key]
+
+
+def histogram(name: str, *, unit: str = "1", description: str = "") -> Histogram:
+    """Return the histogram ``tr_custom_<name>``, creating it on first use.
+
+    ``unit`` and ``description`` apply only on first creation.
+
+    :param name: Metric name without the ``tr_custom_`` prefix. Must match
+        ``^[a-z][a-z0-9_]*$``.
+    :raises ValueError: If the name is invalid or already carries a ``tr_`` prefix.
+    """
+    full_name = _full_name(name)
+    key = ("histogram", full_name)
+    if key not in _instruments:
+        instrument = otel_metrics.get_meter(_METER_NAME).create_histogram(full_name, unit=unit, description=description)
+        _instruments[key] = Histogram(instrument)
+    return _instruments[key]