batchwizard 0.2.0__tar.gz → 0.5.0__tar.gz

batchwizard-0.5.0/.github/workflows/ci.yml

@@ -0,0 +1,52 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+
+permissions:
+  contents: read
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v7.0.0
+        with:
+          fetch-depth: 0
+          persist-credentials: false
+      - uses: astral-sh/setup-uv@v8.3.2
+      - run: uv sync --frozen --group dev
+      - run: uv run --frozen ruff check .
+      - run: uv run --frozen ruff format --check .
+
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.11", "3.12", "3.13", "3.14"]
+    steps:
+      - uses: actions/checkout@v7.0.0
+        with:
+          fetch-depth: 0
+          persist-credentials: false
+      - uses: astral-sh/setup-uv@v8.3.2
+        with:
+          python-version: ${{ matrix.python-version }}
+      - run: uv sync --frozen --group dev
+      - run: uv run --frozen pytest tests/
+
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v7.0.0
+        with:
+          fetch-depth: 0
+          persist-credentials: false
+      - uses: astral-sh/setup-uv@v8.3.2
+      - run: uv build
+      - uses: actions/upload-artifact@v7.0.1
+        with:
+          name: dist
+          path: dist/

batchwizard-0.5.0/.github/workflows/publish.yml

@@ -0,0 +1,37 @@
+name: Publish to PyPI
+
+on:
+  release:
+    types: [published]
+
+permissions:
+  contents: read
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v7.0.0
+        with:
+          fetch-depth: 0
+          persist-credentials: false
+      - uses: astral-sh/setup-uv@v8.3.2
+      - run: uv build
+      - uses: actions/upload-artifact@v7.0.1
+        with:
+          name: dist
+          path: dist/
+
+  publish:
+    needs: build
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      # Required for PyPI Trusted Publishing (OIDC) — no API token needed
+      id-token: write
+    steps:
+      - uses: actions/download-artifact@v8.0.1
+        with:
+          name: dist
+          path: dist/
+      - uses: pypa/gh-action-pypi-publish@release/v1

batchwizard-0.5.0/.gitignore

@@ -0,0 +1,162 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

batchwizard-0.5.0/PKG-INFO

@@ -0,0 +1,205 @@
+Metadata-Version: 2.4
+Name: batchwizard
+Version: 0.5.0
+Summary: Durable batch orchestration across OpenAI and Anthropic
+Project-URL: Homepage, https://github.com/cmakafui/batchwizard
+Project-URL: Repository, https://github.com/cmakafui/batchwizard
+Project-URL: Issues, https://github.com/cmakafui/batchwizard/issues
+Author: Carl Kugblenu
+License-Expression: MIT
+License-File: LICENSE
+Keywords: anthropic,async,batch,cli,openai
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Requires-Python: >=3.11
+Requires-Dist: anthropic[aiohttp]<1,>=0.117
+Requires-Dist: loguru>=0.7
+Requires-Dist: openai[aiohttp]<3,>=2.46
+Requires-Dist: pydantic-settings>=2.3
+Requires-Dist: pydantic>=2.8
+Requires-Dist: python-dotenv>=1.0
+Requires-Dist: rich>=13.7
+Requires-Dist: typer>=0.12
+Description-Content-Type: text/markdown
+
+# BatchWizard
+
+BatchWizard is one durable CLI for OpenAI and Anthropic batch jobs. Submit
+provider-native JSONL, close the terminal, and come back later: a local SQLite
+manifest remembers what is running, what still needs to be downloaded, and what
+needs your attention.
+
+It deliberately does not translate prompts between APIs. OpenAI and Anthropic
+have different request formats and capabilities; BatchWizard gives them one
+operational lifecycle without pretending they are the same protocol.
+
+## Quickstart
+
+Install BatchWizard as an isolated Python 3.11+ tool:
+
+```bash
+uv tool install batchwizard
+```
+
+Provide one or both standard API-key environment variables:
+
+```bash
+export OPENAI_API_KEY="..."
+export ANTHROPIC_API_KEY="..."
+```
+
+Submit native JSONL to either provider:
+
+```bash
+batchwizard submit openai.jsonl --endpoint /v1/responses
+batchwizard submit --provider anthropic anthropic.jsonl
+```
+
+The submit process can exit once the providers accept the work. One later
+command resumes every actionable job, grouped by provider:
+
+```bash
+batchwizard watch --output-directory ./results
+batchwizard status --all
+```
+
+`watch` is intentionally provider-free. The manifest records which adapter owns
+each batch, so a single invocation can resume a mixture of OpenAI and Anthropic
+jobs. Missing credentials or a temporary download failure for one provider do
+not erase work or prevent other provider groups from advancing.
+
+## Input formats
+
+BatchWizard accepts each provider's native JSONL rather than maintaining a lossy
+common prompt schema.
+
+| | OpenAI | Anthropic |
+| --- | --- | --- |
+| Select with | default, or `--provider openai` | `--provider anthropic` |
+| JSONL row | `{"custom_id", "method", "url", "body"}` | `{"custom_id", "params"}` |
+| Model location | `body.model` | `params.model` |
+| Submission | file upload, then Batch creation | requests sent inline to Message Batches |
+| Provider status | Batch `status` | Message Batch `processing_status` |
+| Results | provider output and error files | unordered result stream split by outcome |
+| Recovery after an uncertain submit | automatic intent matching through Batch metadata | manual attachment by batch ID |
+
+### OpenAI
+
+```jsonl
+{"custom_id":"ticket-1","method":"POST","url":"/v1/responses","body":{"model":"gpt-5.4","input":"Classify this ticket as billing, technical, or other."}}
+```
+
+The endpoint passed to BatchWizard must match the `url` in every row:
+
+```bash
+batchwizard submit openai.jsonl --endpoint /v1/responses
+```
+
+`/v1/chat/completions` is the default. BatchWizard also accepts the Responses,
+Embeddings, Completions, Moderations, Images, and Videos Batch API endpoints.
+
+### Anthropic
+
+```jsonl
+{"custom_id":"ticket-1","params":{"model":"claude-opus-4-8","max_tokens":256,"messages":[{"role":"user","content":"Classify this ticket as billing, technical, or other."}]}}
+```
+
+```bash
+batchwizard submit --provider anthropic anthropic.jsonl
+```
+
+BatchWizard validates the batch envelope, `custom_id` syntax and uniqueness,
+batch size, `max_tokens`, and the non-streaming requirement before submission.
+Anthropic remains responsible for validating its evolving Messages parameter
+surface. See [Anthropic Message Batches](docs/anthropic.md) for result routing,
+prompt caching, cancellation, and retention behavior.
+
+## Durable jobs and recovery
+
+The manifest separates remote execution from local artifact collection. A
+provider can report a batch complete while its result files are still pending
+locally; that row remains actionable until collection succeeds or the provider
+confirms that the artifacts are no longer available.
+
+Submission is durable too. BatchWizard writes an intent before making provider
+requests. If a connection fails after the remote service may have accepted the
+batch, it keeps that intent instead of blindly submitting a duplicate:
+
+```bash
+batchwizard reconcile
+batchwizard reconcile INTENT
+batchwizard reconcile INTENT --batch-id MSGBATCH_ID
+```
+
+OpenAI intents can be matched through Batch metadata. Anthropic does not expose
+equivalent batch metadata, so its uncertain submissions are attached after the
+matching batch is identified with `list-jobs`.
+
+The lifecycle and SQLite migrations are documented in
+[Job lifecycle](docs/job-lifecycle.md).
+
+## Result files
+
+Provider output stays JSONL and is written atomically:
+
+- `<batch_id>_results.jsonl` contains successful rows.
+- `<batch_id>_errors.jsonl` contains request-level failures when present.
+
+Anthropic result rows can arrive in any order. BatchWizard preserves each raw row
+and routes `succeeded` results to the results file and `errored`, `expired`, or
+`canceled` results to the errors file.
+
+## Credentials and configuration
+
+Environment variables are the preferred way to supply credentials. Keys can
+also be persisted for convenience:
+
+```bash
+batchwizard configure --provider openai --set-key "$OPENAI_API_KEY"
+batchwizard configure --provider anthropic --set-key "$ANTHROPIC_API_KEY"
+batchwizard configure --show --provider openai
+```
+
+Persisted keys are plaintext JSON. BatchWizard writes the configuration
+atomically with owner-only file permissions, but it does not use the operating
+system keychain in v0.5. Treat that file as a secret; keyring-backed storage is
+deferred to v0.6.
+
+## Commands
+
+| Command | Purpose |
+| --- | --- |
+| `submit` | Submit files and return after provider acceptance. |
+| `watch` | Resume actionable jobs and collect terminal artifacts. |
+| `process` | Submit, watch, and collect in one invocation. |
+| `status` | Inspect the local SQLite manifest. |
+| `reconcile` | Recover a submission with an uncertain provider outcome. |
+| `list-jobs` | List recent jobs directly from one provider. |
+| `cancel` | Request cancellation for a tracked or provider-native batch ID. |
+| `download` | Collect result artifacts for one batch. |
+| `configure` | Store, inspect, or reset local settings. |
+
+Use `batchwizard <command> --help` for the exact arguments and options.
+
+## Development
+
+```bash
+uv sync --all-groups
+uv run pytest
+uv run ruff format --check .
+uv run ruff check .
+uv build
+```
+
+The supported runtime matrix is Python 3.11 through 3.14. The lockfile is
+committed; update it intentionally with `uv lock --upgrade-package <package>`.
+
+## License
+
+[MIT](LICENSE)

batchwizard-0.5.0/README.md

@@ -0,0 +1,175 @@
+# BatchWizard
+
+BatchWizard is one durable CLI for OpenAI and Anthropic batch jobs. Submit
+provider-native JSONL, close the terminal, and come back later: a local SQLite
+manifest remembers what is running, what still needs to be downloaded, and what
+needs your attention.
+
+It deliberately does not translate prompts between APIs. OpenAI and Anthropic
+have different request formats and capabilities; BatchWizard gives them one
+operational lifecycle without pretending they are the same protocol.
+
+## Quickstart
+
+Install BatchWizard as an isolated Python 3.11+ tool:
+
+```bash
+uv tool install batchwizard
+```
+
+Provide one or both standard API-key environment variables:
+
+```bash
+export OPENAI_API_KEY="..."
+export ANTHROPIC_API_KEY="..."
+```
+
+Submit native JSONL to either provider:
+
+```bash
+batchwizard submit openai.jsonl --endpoint /v1/responses
+batchwizard submit --provider anthropic anthropic.jsonl
+```
+
+The submit process can exit once the providers accept the work. One later
+command resumes every actionable job, grouped by provider:
+
+```bash
+batchwizard watch --output-directory ./results
+batchwizard status --all
+```
+
+`watch` is intentionally provider-free. The manifest records which adapter owns
+each batch, so a single invocation can resume a mixture of OpenAI and Anthropic
+jobs. Missing credentials or a temporary download failure for one provider do
+not erase work or prevent other provider groups from advancing.
+
+## Input formats
+
+BatchWizard accepts each provider's native JSONL rather than maintaining a lossy
+common prompt schema.
+
+| | OpenAI | Anthropic |
+| --- | --- | --- |
+| Select with | default, or `--provider openai` | `--provider anthropic` |
+| JSONL row | `{"custom_id", "method", "url", "body"}` | `{"custom_id", "params"}` |
+| Model location | `body.model` | `params.model` |
+| Submission | file upload, then Batch creation | requests sent inline to Message Batches |
+| Provider status | Batch `status` | Message Batch `processing_status` |
+| Results | provider output and error files | unordered result stream split by outcome |
+| Recovery after an uncertain submit | automatic intent matching through Batch metadata | manual attachment by batch ID |
+
+### OpenAI
+
+```jsonl
+{"custom_id":"ticket-1","method":"POST","url":"/v1/responses","body":{"model":"gpt-5.4","input":"Classify this ticket as billing, technical, or other."}}
+```
+
+The endpoint passed to BatchWizard must match the `url` in every row:
+
+```bash
+batchwizard submit openai.jsonl --endpoint /v1/responses
+```
+
+`/v1/chat/completions` is the default. BatchWizard also accepts the Responses,
+Embeddings, Completions, Moderations, Images, and Videos Batch API endpoints.
+
+### Anthropic
+
+```jsonl
+{"custom_id":"ticket-1","params":{"model":"claude-opus-4-8","max_tokens":256,"messages":[{"role":"user","content":"Classify this ticket as billing, technical, or other."}]}}
+```
+
+```bash
+batchwizard submit --provider anthropic anthropic.jsonl
+```
+
+BatchWizard validates the batch envelope, `custom_id` syntax and uniqueness,
+batch size, `max_tokens`, and the non-streaming requirement before submission.
+Anthropic remains responsible for validating its evolving Messages parameter
+surface. See [Anthropic Message Batches](docs/anthropic.md) for result routing,
+prompt caching, cancellation, and retention behavior.
+
+## Durable jobs and recovery
+
+The manifest separates remote execution from local artifact collection. A
+provider can report a batch complete while its result files are still pending
+locally; that row remains actionable until collection succeeds or the provider
+confirms that the artifacts are no longer available.
+
+Submission is durable too. BatchWizard writes an intent before making provider
+requests. If a connection fails after the remote service may have accepted the
+batch, it keeps that intent instead of blindly submitting a duplicate:
+
+```bash
+batchwizard reconcile
+batchwizard reconcile INTENT
+batchwizard reconcile INTENT --batch-id MSGBATCH_ID
+```
+
+OpenAI intents can be matched through Batch metadata. Anthropic does not expose
+equivalent batch metadata, so its uncertain submissions are attached after the
+matching batch is identified with `list-jobs`.
+
+The lifecycle and SQLite migrations are documented in
+[Job lifecycle](docs/job-lifecycle.md).
+
+## Result files
+
+Provider output stays JSONL and is written atomically:
+
+- `<batch_id>_results.jsonl` contains successful rows.
+- `<batch_id>_errors.jsonl` contains request-level failures when present.
+
+Anthropic result rows can arrive in any order. BatchWizard preserves each raw row
+and routes `succeeded` results to the results file and `errored`, `expired`, or
+`canceled` results to the errors file.
+
+## Credentials and configuration
+
+Environment variables are the preferred way to supply credentials. Keys can
+also be persisted for convenience:
+
+```bash
+batchwizard configure --provider openai --set-key "$OPENAI_API_KEY"
+batchwizard configure --provider anthropic --set-key "$ANTHROPIC_API_KEY"
+batchwizard configure --show --provider openai
+```
+
+Persisted keys are plaintext JSON. BatchWizard writes the configuration
+atomically with owner-only file permissions, but it does not use the operating
+system keychain in v0.5. Treat that file as a secret; keyring-backed storage is
+deferred to v0.6.
+
+## Commands
+
+| Command | Purpose |
+| --- | --- |
+| `submit` | Submit files and return after provider acceptance. |
+| `watch` | Resume actionable jobs and collect terminal artifacts. |
+| `process` | Submit, watch, and collect in one invocation. |
+| `status` | Inspect the local SQLite manifest. |
+| `reconcile` | Recover a submission with an uncertain provider outcome. |
+| `list-jobs` | List recent jobs directly from one provider. |
+| `cancel` | Request cancellation for a tracked or provider-native batch ID. |
+| `download` | Collect result artifacts for one batch. |
+| `configure` | Store, inspect, or reset local settings. |
+
+Use `batchwizard <command> --help` for the exact arguments and options.
+
+## Development
+
+```bash
+uv sync --all-groups
+uv run pytest
+uv run ruff format --check .
+uv run ruff check .
+uv build
+```
+
+The supported runtime matrix is Python 3.11 through 3.14. The lockfile is
+committed; update it intentionally with `uv lock --upgrade-package <package>`.
+
+## License
+
+[MIT](LICENSE)