dagprobe 0.1.0__tar.gz

dagprobe-0.1.0/.gitignore

@@ -0,0 +1,32 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.egg-info/
+.eggs/
+build/
+dist/
+
+# Virtual envs
+.venv/
+venv/
+env/
+# Windows-окружение рядом с linux-venv песочницы (на хосте .venv занят линуксовым, см. HANDOFF «Уроки»)
+.venv-win/
+
+# uv
+.uv/
+
+# Editors / IDE
+.idea/
+.vscode/
+*.swp
+
+# OS
+.DS_Store
+Thumbs.db
+# артефакты сравнения A/B — генерятся spike/inspect_dags.py и CI
+spike/out/
+.coverage
+# артефакты A/B статусов — генерятся spike/run_ab.py
+spike/ab_dags/

dagprobe-0.1.0/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.

dagprobe-0.1.0/PKG-INFO

@@ -0,0 +1,110 @@
+Metadata-Version: 2.5
+Name: dagprobe
+Version: 0.1.0
+Summary: Debug and test Apache Airflow DAGs without installing and running Airflow
+Project-URL: Homepage, https://github.com/AndreyGor97/dagprobe
+Project-URL: Repository, https://github.com/AndreyGor97/dagprobe
+Project-URL: Issues, https://github.com/AndreyGor97/dagprobe/issues
+Author: AndreyGor97
+License-Expression: Apache-2.0
+License-File: LICENSE
+Keywords: airflow,apache-airflow,ci,dag,lint,migration,testing
+Classifier: Development Status :: 3 - Alpha
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Software Development :: Quality Assurance
+Classifier: Topic :: Software Development :: Testing
+Requires-Python: >=3.11
+Requires-Dist: jinja2>=3.1
+Requires-Dist: pandas>=2.2
+Requires-Dist: pyyaml>=6.0.3
+Description-Content-Type: text/markdown
+
+# DagProbe
+
+Debug and test [Apache Airflow](https://airflow.apache.org/) DAGs **without installing or running Airflow**.
+
+DagProbe imports your DAG files against a lightweight shim of the Airflow SDK, then lets you
+lint them, preview their Jinja rendering, run tasks against YAML fixtures, and audit behavior
+differences between Airflow 2.10 and 3.3 — all in a plain Python environment, in seconds,
+with no Airflow installation, no database and no scheduler.
+
+```console
+$ pip install dagprobe
+```
+
+## What it does
+
+| Command | Purpose |
+|---|---|
+| `dagprobe list` | Import a DAGs folder, list DAG ids and import errors (with timing) |
+| `dagprobe lint` | Import + static lint for CI: duplicate task ids, `datetime.now()` in DAG code, missing `catchup=`, deprecated kwargs; `--changed-only` lints just the files changed vs a base branch |
+| `dagprobe render` | Jinja preview: rendered `template_fields` per task (before → after) |
+| `dagprobe run` | Task Test: execute a DAG's tasks against fixtures — `PythonOperator` callables run for real, `trigger_rule` and `BranchPythonOperator` branching follow Airflow semantics, in-memory DB connections read/write across tasks |
+| `dagprobe audit 2to3` | Run the same DAG under the 2.10 and 3.3 behavior profiles and report divergences (e.g. XCom value unwrapping, task `status` changes) |
+
+`lint` and `run` are CI-first: `--format text|json|junit` and `--fail-on error|warning|never`,
+stable exit codes (`0` clean, `1` findings at gate level, `2` usage/setup error), JUnit output
+for PR test reports. A ready GitHub Actions workflow ships in
+[`examples/ci/github-actions.yml`](examples/ci/github-actions.yml).
+
+## Quickstart
+
+```console
+# what's in my DAGs folder, and does everything even import?
+$ dagprobe list --dags-folder dags
+
+# run one DAG's tasks against fixtures (fake conns, tables, files)
+$ dagprobe run --dags-folder dags --dag-id branch_etl \
+    --fixtures fixtures/branch.yaml
+```
+
+Fixtures are a small YAML file — no Airflow metadata database involved:
+
+```yaml
+conns:
+  dwh:
+    conn_type: postgres
+    tables:
+      events:
+        - {event: signup, n: 3}
+        - {event: purchase, n: 1}
+```
+
+More runnable examples: [`examples/dags/`](examples/dags/) with matching
+[`examples/fixtures/`](examples/fixtures/), including a deliberately broken DAG
+(`examples/broken/`) that demonstrates the CI gate.
+
+## How it works
+
+DagProbe ships a versioned shim of the Airflow import surface (`airflow.sdk`,
+`airflow.providers.standard`, hooks, operators). Your DAG file is imported against the shim,
+so imports resolve without an Airflow install — typically in well under a second per file,
+versus tens of seconds to boot a real Airflow environment. Task execution reuses the same
+Jinja engine Airflow uses, so template rendering is comparable 1:1.
+
+Behavior profiles: `run` defaults to the Airflow 3.3 profile; `dagprobe audit 2to3` runs the
+same DAG under both the 2.10 legacy and the 3.3 profile and reports concrete behavioral
+divergences per task — the things that break silently during a 2.x → 3.x migration.
+
+## Scope and limitations
+
+- Airflow version profiles: **2.10 and 3.3** (arbitrary version pinning is on the roadmap).
+- SQL runs on an in-memory SQLite via an emulated engine — real warehouse dialects are out of scope.
+- No scheduler, no real network/connections: tasks run in-process against fixtures.
+- Static lint covers a focused rule set, not a general Python linter — pair it with `ruff`.
+
+## Development
+
+```console
+$ git clone https://github.com/AndreyGor97/dagprobe
+$ cd dagprobe && uv sync
+$ uv run pytest
+```
+
+Requires Python 3.11+. Apache-2.0 licensed; not affiliated with the Apache Software Foundation.

dagprobe-0.1.0/README.md

@@ -0,0 +1,83 @@
+# DagProbe
+
+Debug and test [Apache Airflow](https://airflow.apache.org/) DAGs **without installing or running Airflow**.
+
+DagProbe imports your DAG files against a lightweight shim of the Airflow SDK, then lets you
+lint them, preview their Jinja rendering, run tasks against YAML fixtures, and audit behavior
+differences between Airflow 2.10 and 3.3 — all in a plain Python environment, in seconds,
+with no Airflow installation, no database and no scheduler.
+
+```console
+$ pip install dagprobe
+```
+
+## What it does
+
+| Command | Purpose |
+|---|---|
+| `dagprobe list` | Import a DAGs folder, list DAG ids and import errors (with timing) |
+| `dagprobe lint` | Import + static lint for CI: duplicate task ids, `datetime.now()` in DAG code, missing `catchup=`, deprecated kwargs; `--changed-only` lints just the files changed vs a base branch |
+| `dagprobe render` | Jinja preview: rendered `template_fields` per task (before → after) |
+| `dagprobe run` | Task Test: execute a DAG's tasks against fixtures — `PythonOperator` callables run for real, `trigger_rule` and `BranchPythonOperator` branching follow Airflow semantics, in-memory DB connections read/write across tasks |
+| `dagprobe audit 2to3` | Run the same DAG under the 2.10 and 3.3 behavior profiles and report divergences (e.g. XCom value unwrapping, task `status` changes) |
+
+`lint` and `run` are CI-first: `--format text|json|junit` and `--fail-on error|warning|never`,
+stable exit codes (`0` clean, `1` findings at gate level, `2` usage/setup error), JUnit output
+for PR test reports. A ready GitHub Actions workflow ships in
+[`examples/ci/github-actions.yml`](examples/ci/github-actions.yml).
+
+## Quickstart
+
+```console
+# what's in my DAGs folder, and does everything even import?
+$ dagprobe list --dags-folder dags
+
+# run one DAG's tasks against fixtures (fake conns, tables, files)
+$ dagprobe run --dags-folder dags --dag-id branch_etl \
+    --fixtures fixtures/branch.yaml
+```
+
+Fixtures are a small YAML file — no Airflow metadata database involved:
+
+```yaml
+conns:
+  dwh:
+    conn_type: postgres
+    tables:
+      events:
+        - {event: signup, n: 3}
+        - {event: purchase, n: 1}
+```
+
+More runnable examples: [`examples/dags/`](examples/dags/) with matching
+[`examples/fixtures/`](examples/fixtures/), including a deliberately broken DAG
+(`examples/broken/`) that demonstrates the CI gate.
+
+## How it works
+
+DagProbe ships a versioned shim of the Airflow import surface (`airflow.sdk`,
+`airflow.providers.standard`, hooks, operators). Your DAG file is imported against the shim,
+so imports resolve without an Airflow install — typically in well under a second per file,
+versus tens of seconds to boot a real Airflow environment. Task execution reuses the same
+Jinja engine Airflow uses, so template rendering is comparable 1:1.
+
+Behavior profiles: `run` defaults to the Airflow 3.3 profile; `dagprobe audit 2to3` runs the
+same DAG under both the 2.10 legacy and the 3.3 profile and reports concrete behavioral
+divergences per task — the things that break silently during a 2.x → 3.x migration.
+
+## Scope and limitations
+
+- Airflow version profiles: **2.10 and 3.3** (arbitrary version pinning is on the roadmap).
+- SQL runs on an in-memory SQLite via an emulated engine — real warehouse dialects are out of scope.
+- No scheduler, no real network/connections: tasks run in-process against fixtures.
+- Static lint covers a focused rule set, not a general Python linter — pair it with `ruff`.
+
+## Development
+
+```console
+$ git clone https://github.com/AndreyGor97/dagprobe
+$ cd dagprobe && uv sync
+$ uv run pytest
+```
+
+Requires Python 3.11+. Apache-2.0 licensed; not affiliated with the Apache Software Foundation.

dagprobe-0.1.0/examples/broken/double_task.py

@@ -0,0 +1,12 @@
+"""DAG с дублем `task_id` — демонстрация CI-гейта (§6.21).
+
+`dagprobe lint --dags-folder examples/broken` отдаёт DUPLICATE_TASK_ID (error),
+exit 1 и JUnit с `<failure>`: ровно то, на чём CI не пропускает мердж.
+"""
+
+from airflow.providers.standard.operators.python import PythonOperator
+from airflow.sdk import DAG
+
+with DAG("double_task", schedule=None, start_date=None, catchup=False) as dag:
+    PythonOperator(task_id="extract", python_callable=lambda **_: 1)
+    PythonOperator(task_id="extract", python_callable=lambda **_: 2)

dagprobe-0.1.0/examples/ci/github-actions.yml

@@ -0,0 +1,51 @@
+# DAGProbe в CI (§6.21): шаблон GitHub Actions.
+# Копируется в <ваш-репозиторий>/.github/workflows/dagprobe.yml и правится
+# только --dags-folder (каталог с DAG'ами) и база diff.
+#
+# Поведение: линтуются и импортируются только изменённые в PR файлы; ошибки
+# роняют джобу (exit 1 — шаг падает), рядом падает отчёт JUnit в PR.
+# Уровень, который роняет мердж, настраивается --fail-on error|warning|never.
+name: dagprobe
+
+on: pull_request
+
+jobs:
+  dags:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0 # нужен diff к базовой ветке для --changed-only
+
+      - uses: astral-sh/setup-uv@v5
+      - run: uv sync --frozen
+
+      # exit 1 при находках уровня gate: джоба падает, мердж не проходит
+      - name: Линт изменённых DAG
+        run: |
+          uv run dagprobe lint --dags-folder dags --changed-only \
+            --base-ref "origin/${{ github.base_ref }}" --format junit \
+            > dagprobe-lint.xml
+
+      # отчёт в PR — даже когда шаг выше упал (файл уже записан)
+      - name: Отчёт в PR
+        if: always()
+        uses: dorny/test-reporter@v1
+        with:
+          name: dagprobe lint
+          path: dagprobe-lint.xml
+          reporter: java-junit
+
+      # прогон DAG на фикстурах: те же exit-коды и тот же JUnit
+      - name: Прогон DAG на фикстурах
+        run: |
+          uv run dagprobe run --dags-folder examples/dags --dag-id db_join_etl \
+            --fixtures examples/fixtures/dwh.yaml --format junit > dagprobe-run.xml
+
+      - name: Отчёт по прогону
+        if: always()
+        uses: dorny/test-reporter@v1
+        with:
+          name: dagprobe run
+          path: dagprobe-run.xml
+          reporter: java-junit

dagprobe-0.1.0/examples/dags/branch_etl.py

@@ -0,0 +1,54 @@
+"""Пример Среза 7: ветвление и trigger_rule в прогоне.
+
+``route`` — BranchPythonOperator: на непустых данных выбирает ``load_events``,
+иначе ``load_empty``. Невыбранные ветки получают skipped, дальше решает
+trigger_rule: ``load_empty`` стоит с ``all_failed`` (не выполнено → skipped,
+как в Airflow), ``report`` после ``load_events`` — обычный all_success.
+
+``load_events`` пишет в таблицу через ``DbApiHook.insert_rows`` (Срез 7),
+``report`` читает её обратно — запись видна следующей задаче прогона.
+
+Запуск из клона DagProbe:
+
+    uv run dagprobe run --dags-folder examples/dags --dag-id branch_etl \\
+        --fixtures examples/fixtures/branch.yaml
+"""
+
+from airflow.providers.standard.operators.python import BranchPythonOperator, PythonOperator
+from airflow.sdk import DAG
+from airflow.sdk.bases.hook import DbApiHook
+
+with DAG("branch_etl", schedule=None, start_date=None, catchup=False) as dag:
+
+    def extract(**_):
+        return DbApiHook(conn_id="dwh").get_records("SELECT * FROM events")
+
+    def route(rows, **_):
+        return "load_events" if rows else "load_empty"
+
+    def load_events(rows, **_):
+        # таблицу создаём сами: фикстура даёт только events, INSERT в несуществующую — ошибка
+        DbApiHook(conn_id="dwh").run("CREATE TABLE IF NOT EXISTS events_loaded (event, n)")
+        DbApiHook(conn_id="dwh").insert_rows("events_loaded", rows, target_fields=["event", "n"])
+        return f"loaded {len(rows)} rows"
+
+    def report(msg, **_):
+        count = DbApiHook(conn_id="dwh").get_records("SELECT COUNT(*) AS c FROM events_loaded")
+        return f"{msg}; в таблице events_loaded строк: {count[0]['c']}"
+
+    extract_task = PythonOperator(task_id="extract", python_callable=extract)
+    route_task = BranchPythonOperator(
+        task_id="route", python_callable=route, op_kwargs={"rows": extract_task.output}
+    )
+    load_empty = PythonOperator(
+        task_id="load_empty", python_callable=lambda **_: "пустые данные", trigger_rule="all_failed"
+    )
+    load_events_task = PythonOperator(
+        task_id="load_events", python_callable=load_events, op_kwargs={"rows": extract_task.output}
+    )
+    report_task = PythonOperator(
+        task_id="report", python_callable=report, op_kwargs={"msg": load_events_task.output}
+    )
+
+    extract_task >> route_task >> [load_events_task, load_empty]
+    load_events_task >> report_task

dagprobe-0.1.0/examples/dags/db_join.py

@@ -0,0 +1,34 @@
+"""Пример Среза 4: честный SQL (JOIN + GROUP BY) без Postgres и без Docker.
+
+Данные для соединения ``dwh`` лежат в ``examples/fixtures/dwh.yaml`` (уровень
+Emulated Engine §8.2): таблицы грузятся в in-memory SQLite, и запрос исполняется
+по-настоящему — считает движок, а не фикстура.
+
+Запуск из клона DagProbe:
+
+    uv run dagprobe run --dags-folder examples/dags --dag-id db_join_etl \\
+        --fixtures examples/fixtures/dwh.yaml
+"""
+
+from airflow.providers.standard.operators.python import PythonOperator
+from airflow.sdk import DAG, task
+from airflow.sdk.bases.hook import DbApiHook
+
+with DAG("db_join_etl", schedule=None, start_date=None, catchup=False) as dag:
+
+    def extract(**_):
+        return DbApiHook(conn_id="dwh").get_records(
+            "SELECT c.name AS customer, SUM(o.amount) AS revenue"
+            " FROM orders o JOIN customers c ON o.customer_id = c.customer_id"
+            " WHERE o.amount > 0"
+            " GROUP BY c.name ORDER BY revenue DESC"
+        )
+
+    extract_task = PythonOperator(task_id="extract", python_callable=extract)
+
+    @task
+    def load(rows):
+        assert rows, "нечего грузить: extract вернул пусто"
+        return [f"{r['customer']}: {r['revenue']}" for r in rows]
+
+    load(extract_task.output)

dagprobe-0.1.0/examples/dags/migration_legacy.py

@@ -0,0 +1,46 @@
+"""Пример Среза 8: поведенческий аудит миграции Airflow 2.10 → 3.x.
+
+``uses_execution_date`` — эталон из G2 (demand_validation_report): шаблон с
+легаси-ключом контекста. В 2.10 он рендерится в дату (задача ok), в 3.x ключ
+удалён из контекста (задача падает) — именно это находит ``audit``.
+``uses_tomorrow_ds`` — помягче: в обеих версиях задача ok, но значение разное
+(дата против пустой строки) — находка уровня ``value``. ``plain`` — чистая
+задача, находок не даёт (контроль).
+
+Запуск из клона DagProbe:
+
+    uv run dagprobe audit 2to3 --dags-folder examples/dags --dag-id migration_legacy
+
+Exit 1 = есть расхождения (см. JSON: ``--format json``), 0 = поведение совпадает.
+"""
+
+from airflow.providers.standard.operators.python import PythonOperator
+from airflow.sdk import DAG
+
+
+def fail_on_empty(value):
+    if not value:
+        raise ValueError("легаси-ключ контекста не отрендерился (удалён в Airflow 3?)")
+    return value
+
+
+def echo(value):
+    return value
+
+
+with DAG("migration_legacy", schedule=None, start_date=None, catchup=False) as dag:
+    PythonOperator(
+        task_id="uses_execution_date",
+        python_callable=fail_on_empty,
+        op_kwargs={"value": "{{ execution_date }}"},
+    )
+    PythonOperator(
+        task_id="uses_tomorrow_ds",
+        python_callable=echo,
+        op_kwargs={"value": "{{ tomorrow_ds }}"},
+    )
+    PythonOperator(
+        task_id="plain",
+        python_callable=echo,
+        op_kwargs={"value": "{{ ds }}"},
+    )