pyconveyor 1.0.0__tar.gz

pyconveyor-1.0.0/.github/workflows/ci.yml

@@ -0,0 +1,36 @@
+name: CI
+
+on:
+  push:
+    branches: ["main"]
+  pull_request:
+
+jobs:
+  test:
+    name: "Python ${{ matrix.python-version }}"
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10", "3.11", "3.12", "3.13", "3.14"]
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          allow-prereleases: true
+
+      - name: Install dependencies
+        run: pip install -e ".[dev]"
+
+      - name: Lint (ruff)
+        run: ruff check src tests
+
+      - name: Type check (mypy)
+        run: mypy src
+
+      - name: Test (pytest)
+        run: pytest --cov=pyconveyor --cov-report=term-missing

pyconveyor-1.0.0/.github/workflows/publish.yml

@@ -0,0 +1,62 @@
+name: Publish to PyPI
+
+on:
+  push:
+    tags:
+      - "v*.*.*"
+
+permissions:
+  contents: write
+  id-token: write
+
+jobs:
+  publish:
+    name: Build and publish
+    runs-on: ubuntu-latest
+
+    environment:
+      name: pypi
+      url: https://pypi.org/p/pyconveyor
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Install dependencies
+        run: pip install -e ".[dev]"
+
+      - name: Lint (ruff)
+        run: ruff check src tests
+
+      - name: Type check (mypy)
+        run: mypy src
+
+      - name: Test (pytest)
+        run: pytest
+
+      - name: Build sdist and wheel
+        run: |
+          pip install build
+          python -m build
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+
+      - name: Extract changelog for this version
+        id: changelog
+        run: |
+          VERSION="${GITHUB_REF_NAME#v}"
+          NOTES=$(awk "/^## \[$VERSION\]/{found=1; next} found && /^## \[/{exit} found{print}" CHANGELOG.md)
+          echo "notes<<EOF" >> "$GITHUB_OUTPUT"
+          echo "$NOTES" >> "$GITHUB_OUTPUT"
+          echo "EOF" >> "$GITHUB_OUTPUT"
+
+      - name: Create GitHub Release
+        uses: softprops/action-gh-release@v2
+        with:
+          body: ${{ steps.changelog.outputs.notes }}
+          files: dist/*

pyconveyor-1.0.0/.gitignore

@@ -0,0 +1,221 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$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
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.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
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.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/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+# Temporary file for partial code execution
+tempCodeRunnerFile.py
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml
+
+# gstack dev tool
+.gstack/

pyconveyor-1.0.0/.readthedocs.yaml

@@ -0,0 +1,16 @@
+version: 2
+
+build:
+  os: ubuntu-24.04
+  tools:
+    python: "3.12"
+
+mkdocs:
+  configuration: mkdocs.yml
+
+python:
+  install:
+    - method: pip
+      path: .
+      extra_requirements:
+        - docs

pyconveyor-1.0.0/CHANGELOG.md

@@ -0,0 +1,110 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+> **Note:** The YAML pipeline format is treated as a public API subject to the same
+> semver rules as the Python API. See the [Versioning Policy](README.md#versioning-policy).
+
+---
+
+## [1.0.0] — 2026-05-10
+
+### Added
+
+- `Vocabulary.description` — human-written rationale field; shown to the LLM in the prompt suffix to guide novel-term and `_ideal` decisions
+- `Vocabulary.growth_policy` — three built-in modes: `"auto"` (add immediately), `"human"` (queue for CLI review), `"llm"` (LLM decides); also accepts a custom callable `fn(VocabSuggestion) -> bool`
+- `Vocabulary.growth_policy_model` — optional model name override for `growth_policy="llm"`; falls back to the pipeline's default model
+- `Vocabulary.capture_ideal` — when `True`, the LLM prompt asks for `{field}_ideal` alongside the constrained value; extracted before Pydantic validation and stored in `VocabSuggestion.ideal_value`
+- `Vocabulary.inject_prompt` — auto-appends vocab constraints + description + denied terms to the LLM prompt; disable per-step with `inject_vocab_prompt: false`
+- `Vocabulary.persist` — `True` or explicit path; vocabulary file is saved after each run that produces suggestions
+- `Vocabulary.denied` — set of explicitly rejected terms; not re-surfaced as suggestions; shown to LLM in prompt suffix
+- `Vocabulary.pending` — pending suggestions queue used by `"human"` growth policy
+- `Vocabulary.add_term()` — add a term to `known` and update the internal lookup
+- `Vocabulary.add_pending()` — queue a `VocabSuggestion`, incrementing `seen` if already present
+- `Vocabulary.build_prompt_suffix()` — render the vocab constraint block for prompt injection
+- `Vocabulary.save(path)` — persist vocabulary YAML (known, pending, denied, metadata)
+- `Vocabulary.from_file(path)` — load vocabulary from a YAML file
+- `VocabField(vocab="label")` — string reference resolved from the pipeline's `vocabularies:` block; keeps `schemas.py` free of file paths
+- `VocabSuggestion.ideal_value` — LLM's unconstrained preferred answer (populated when `capture_ideal=True`)
+- `VocabSuggestion.vocab_label` — which vocabulary the suggestion came from
+- `{{ vocab_hints }}` Jinja2 variable — pre-rendered vocab constraint block for manual placement in prompt templates
+- `pyconveyor vocab review pipeline.yaml` CLI command — interactive review of pending vocab suggestions; shows full list with `seen` counts, accepts by index, writes denied to `denied:` block; `--auto-accept` flag for non-interactive use
+- `vocabularies/` directory scaffolded by `pyconveyor init`
+- Caching guide (`docs/guides/caching.md`) covering `ResponseCache`, CLI flags, Python API, cache key semantics, and TTL configuration
+- `on_llm_call` hook now fires for LLM calls inside `type: parallel` steps (previously only top-level steps)
+
+### Changed
+
+- `Development Status` classifier updated from `3 - Alpha` to `5 - Production/Stable`
+- `pyproject.toml` version bumped to `1.0.0` — stable public API
+
+---
+
+## [0.2.0] — 2026-05-09
+
+### Added
+
+- `pyconveyor batch` CLI subcommand — process a JSONL file through a pipeline with configurable parallelism; outputs JSONL results
+- `BatchResult` — rich result wrapper returned by `BatchRunner.run_all()`, with `.successes`, `.failures`, `.error_rate`, and `.summary()` properties; fully backward-compatible via `__iter__` and `__getitem__`
+- `BatchSummary` dataclass — aggregate statistics (`total`, `succeeded`, `failed`, `error_rate`, `failed_ids`)
+- `BatchRunner.on_batch_item_end` hook — callback fired after each item completes, useful for streaming results to a database without waiting for the full batch
+- `PipelineRunner.on_run_start` hook — callback fired before any steps execute; `fn(input_data: dict) -> None`
+- `PipelineRunner.on_run_end` hook — callback fired after the run completes (success or failure); `fn(rctx: RunContext) -> None`
+- `VocabField` pipeline integration — the LLM step now automatically applies vocabulary normalisation (from `json_schema_extra["_pyconveyor_vocab"]`) to Pydantic model fields before validation; novel and fuzzy-matched terms are recorded in `rctx._vocab_suggestions` and surfaced in `RunSummary.vocab_suggestions`
+- GitHub Actions CI workflow (`.github/workflows/ci.yml`) — ruff, mypy, pytest on Python 3.10–3.14 matrix
+- GitHub Actions publish workflow (`.github/workflows/publish.yml`) — tag-triggered PyPI publish via OIDC Trusted Publisher + GitHub Release creation
+- MkDocs + Material theme docs site (`docs/`) — 11 pages covering quickstart, all step types, expressions, providers, CLI reference, and examples
+- `.readthedocs.yaml` v2 config targeting Read the Docs at `https://pyconveyor.readthedocs.io`
+- Python 3.13 and 3.14 trove classifiers in `pyproject.toml`
+
+---
+
+## [0.1.0] — 2026-05-09
+
+### Added
+
+- `PipelineRunner` — YAML-driven step executor with full load-time validation
+- `RunContext` — per-run state carrier with `steps`, `metadata`, `failed`, `failure_state`
+- `_NullSafeProxy` — null-safe attribute access for `ctx` in expressions
+- Step types: `llm`, `transform`, `validate`, `io`, `parallel`, `condition`
+- AST-whitelisted expression evaluator with `ExpressionSecurityError` at pipeline load time
+- Rich load-time validation errors with "did you mean?" suggestions (string-distance scoring)
+- LLM utilities (`make_client`, `call_llm`, `probe_json_mode`, `extract_json`) importable standalone
+- Jinja2 prompt rendering (`render_prompt`, `render_prompt_string`)
+- Unified parse + schema error feedback retry loop (§10) with conversation message structure
+- `retry_on`, `schema_strict`, `max_feedback_tokens`, `error_template` per-step configuration
+- Smart conditional defaults: `max_attempts` and `error_feedback` based on presence of `schema:`
+- `last_attempt` accessor on `StepResult` for failure introspection
+- Step-level `on_error` (`raise` | `continue` | `skip_remaining`) and `on_failure` hook
+- Full model config: `temperature`, `top_p`, `max_tokens`, `seed`, `extra_params`, `pricing`
+- Programmatic model overrides via `runner.run(..., model_overrides={})`
+- `mock` provider for unit tests without API calls
+- `openai_compat` provider (works with OpenAI, Ollama, vLLM, LM Studio)
+- Native Anthropic provider (optional dependency)
+- Custom provider registration via `@register_provider("name")` decorator
+- `BatchRunner` — batch processing with configurable concurrency and optional tqdm progress
+- Mermaid DAG visualisation (`generate_mermaid`)
+- Dry-run mode (`runner.run(..., dry_run=True)`)
+- `RunContext.summary()` with step counts, LLM call counts, elapsed time, attempt logs
+- `VocabField` and `Vocabulary` — vocabulary-constrained fields with fuzzy matching
+- Response caching for development (file-per-key, TTL support, cache control flags)
+- `pyconveyor init` — bootstrap a working pipeline directory
+- `pyconveyor run` — run a pipeline from the CLI
+- `pyconveyor validate` — validate pipeline YAML with line-number errors
+- `pyconveyor schema` — emit JSONSchema for editor autocomplete
+- `pyconveyor visualise` — produce Mermaid DAG diagram
+- Standard `logging` integration under `pyconveyor.*` namespaces
+- `SCHEMA.md` — YAML format reference as a public contract
+- Full unit test suite with fixture pipelines — 167 tests, 80% line coverage
+
+### Fixed
+
+- **ISSUE-001**: Fixed 52 ruff lint errors (unused imports, undefined names, bare excepts, unused variables, type annotation issues).
+- **ISSUE-002**: Fixed 12 mypy strict-mode type errors (missing `-> None` returns, untyped dicts, improper Optional handling).
+- **ISSUE-003**: `pyconveyor validate` / `pyconveyor run` now insert the pipeline directory into `sys.path` so local schema modules are importable without installation.
+- **ISSUE-004**: `pyconveyor run --input` now accepts an inline JSON string starting with `{` or `[`, eliminating the spurious `FileNotFoundError` on inline JSON input.
+
+[0.1.0]: https://github.com/VictorGambarini/pyconveyor/releases/tag/v0.1.0

pyconveyor-1.0.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Victor Gambarini
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

pyconveyor-1.0.0/PKG-INFO

@@ -0,0 +1,65 @@
+Metadata-Version: 2.4
+Name: pyconveyor
+Version: 1.0.0
+Summary: Deterministic YAML pipeline engine for structured LLM extraction
+Project-URL: Repository, https://github.com/VictorGambarini/pyconveyor
+Project-URL: Documentation, https://pyconveyor.readthedocs.io
+Project-URL: Changelog, https://github.com/VictorGambarini/pyconveyor/blob/main/CHANGELOG.md
+License: MIT License
+        
+        Copyright (c) 2026 Victor Gambarini
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+License-File: LICENSE
+Keywords: deterministic,extraction,llm,pipeline,pydantic,structured-output,yaml
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+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 :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Typing :: Typed
+Requires-Python: >=3.10
+Requires-Dist: jinja2>=3.0
+Requires-Dist: openai>=1.0
+Requires-Dist: pydantic>=2.0
+Requires-Dist: python-dotenv>=1.0
+Requires-Dist: pyyaml>=6.0
+Provides-Extra: anthropic
+Requires-Dist: anthropic>=0.25; extra == 'anthropic'
+Provides-Extra: dev
+Requires-Dist: mypy>=1.0; extra == 'dev'
+Requires-Dist: pytest-cov>=4.0; extra == 'dev'
+Requires-Dist: pytest>=7.0; extra == 'dev'
+Requires-Dist: ruff>=0.1; extra == 'dev'
+Requires-Dist: types-pyyaml; extra == 'dev'
+Requires-Dist: types-tqdm; extra == 'dev'
+Provides-Extra: docs
+Requires-Dist: mkdocs-material>=9.5; extra == 'docs'
+Requires-Dist: mkdocs>=1.6; extra == 'docs'
+Provides-Extra: progress
+Requires-Dist: tqdm>=4.0; extra == 'progress'
+Description-Content-Type: text/markdown
+
+# pyconveyor