pyinc 1.0.0__tar.gz

pyinc-1.0.0/.gitignore

@@ -0,0 +1,8 @@
+__pycache__/
+.pytest_cache/
+.hypothesis/
+.mypy_cache/
+.ruff_cache/
+dist/
+build/
+*.egg-info/

pyinc-1.0.0/CHANGELOG.md

@@ -0,0 +1,40 @@
+# 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 the
+project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [1.0.0] — 2026-04-18
+
+First stable release.
+
+### Added
+
+- **Kernel.** Pull-based red-green verification, backdating (early cutoff),
+  `strict` / `checked` / `fast` value-membrane modes, LRU eviction, cycle
+  detection, untracked-read guards, `Database.set_many(...)` batch
+  invalidation, `Database.dependency_graph(...)` export,
+  `Database.inspect(...)` / `Database.explain(...)` provenance, and
+  `Database.statistics()` / `Database.query_profile()` observability.
+- **Built-in resources.** `FileResource`, `FileStatResource`, `EnvResource`,
+  `DirectoryResource`.
+- **Twelve shipped integrations** under `pyinc.integrations`:
+  `python_source`, `toml_config`, `requirements_txt` (including
+  `deep_requirements_analysis` for recursive `-r` following),
+  `installed_packages`, `json_config`, `dependency_check`, `env_file`,
+  `xml_config`, `csv_data`, `deep_module_resolution`, `requirement_evaluation`
+  (PEP 440 specifier satisfaction + PEP 508 marker evaluation), and
+  `symbol_resolution` (module- and class-level symbol tables with bounded
+  cross-module re-export resolution).
+- **Typing.** Inline `py.typed` marker; `mypy --strict` clean.
+- **Docs.** `kernel-contract.md`, `integration-contract.md`,
+  `integration-authoring.md`, `architecture.md`.
+
+### Notes
+
+- Zero runtime dependencies; pure-Python, stdlib-only.
+- Tested on CPython 3.11, 3.12, and 3.13.
+- LSP wiring and push-based filesystem watchers are architectural non-goals
+  for v1; see `docs/architecture.md` for scope boundary.
+
+[1.0.0]: https://github.com/Brumbelow/pyinc/releases/tag/v1.0.0

pyinc-1.0.0/LICENSE

@@ -0,0 +1,201 @@
+                                 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.

pyinc-1.0.0/PKG-INFO

@@ -0,0 +1,150 @@
+Metadata-Version: 2.4
+Name: pyinc
+Version: 1.0.0
+Summary: A correctness-first incremental query engine for Python.
+Project-URL: Homepage, https://github.com/Brumbelow/pyinc
+Project-URL: Repository, https://github.com/Brumbelow/pyinc
+Project-URL: Issues, https://github.com/Brumbelow/pyinc/issues
+Author-email: Andrew Brumbelow <andrew@vangelder-inc.com>
+License: Apache-2.0
+License-File: LICENSE
+Keywords: backdating,incremental-computation,provenance,query-kernel,red-green,salsa
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.11
+Provides-Extra: dev
+Requires-Dist: hypothesis>=6.0; extra == 'dev'
+Requires-Dist: mypy>=1.10; extra == 'dev'
+Requires-Dist: pytest-cov>=5.0; extra == 'dev'
+Requires-Dist: pytest>=8.0; extra == 'dev'
+Requires-Dist: ruff>=0.4; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# pyinc
+
+[![CI](https://github.com/Brumbelow/pyinc/actions/workflows/ci.yml/badge.svg)](https://github.com/Brumbelow/pyinc/actions/workflows/ci.yml)
+[![PyPI](https://img.shields.io/pypi/v/pyinc.svg)](https://pypi.org/project/pyinc/)
+[![Python versions](https://img.shields.io/pypi/pyversions/pyinc.svg)](https://pypi.org/project/pyinc/)
+[![License](https://img.shields.io/pypi/l/pyinc.svg)](https://github.com/Brumbelow/pyinc/blob/main/LICENSE)
+
+```
+pip install pyinc
+```
+
+Python is mutable by default, identity-heavy, and full of hidden side effects. These properties make incremental computation unsound in practice: cached results silently depend on mutated state, untracked file reads, and object identity that the cache cannot see.
+
+`pyinc` is a correctness-first incremental computation engine that solves this problem. It is a pure-Python, stdlib-only query kernel in the design space of Salsa, Jane Street Incremental, and Bazel/Skyframe — but designed specifically for the challenges Python creates.
+
+v1.0.0 is the first stable release. The v1 kernel contract and public integration surface are stable under semver, within the soundness envelope documented in [docs/kernel-contract.md](docs/kernel-contract.md).
+
+## Quick example
+
+```python
+from pyinc import Database, FileResource, query
+
+_FILES = FileResource()
+
+@query
+def read_config(db, path):
+    return _FILES.read(db, path)      # tracked file read
+
+@query
+def parse_names(db, path):
+    text = read_config(db, path)
+    return [line.strip() for line in text.splitlines() if line.strip()]
+
+db = Database(mode="strict")
+result = db.get(parse_names, "/tmp/names.txt")   # computes from scratch
+result = db.get(parse_names, "/tmp/names.txt")   # reuses memo — file unchanged
+
+# Edit the file: only affected queries re-execute.
+# Comment-only edits can be backdated (early cutoff) with a cutoff= function.
+# Raw open() inside a query raises UntrackedReadError.
+# In strict mode, returned values are frozen — mutation raises TypeError.
+```
+
+See `examples/correctness_demo.py` for a full walkthrough of backdating (early cutoff), mutation protection, untracked read enforcement, and provenance inspection. `examples/undeclared_imports.py`, `examples/applicable_requirements.py`, and `examples/symbol_lookup.py` demonstrate three of the shipped integrations end-to-end on self-contained tempdir workspaces.
+
+## What pyinc guarantees
+
+pyinc guarantees **from-scratch consistency** — the result of incremental evaluation matches a fresh evaluation on the same declared inputs and resources — when:
+
+1. **Value boundary ownership**: all values crossing cached boundaries are snapshot-safe (frozen)
+2. **Tracked ambient reads**: all external state reads go through the Resource API
+3. **Deterministic queries**: given the same tracked dependencies, queries return semantically equal values
+
+The full contract, including explicit limitations and escape hatches, is in [docs/kernel-contract.md](docs/kernel-contract.md).
+
+## Current scope
+
+- `@query` for derived values, `Input` for explicit base leaves
+- optional `eq=` and `cutoff=` policies for custom equivalence and backdating (early cutoff)
+- `ValueAdapter` for custom snapshot-safe boundary types
+- `FileResource`, `FileStatResource`, `EnvResource`, and `DirectoryResource` for tracked external reads
+- pull-based recomputation with revisions, dependency capture, red-green verification, and backdating (early cutoff)
+- `strict`, `checked`, and `fast` execution modes with explicit boundary semantics
+- optional bounded query memoization via `Database(max_query_nodes=...)`
+- `Database.set_many(...)` for atomic batch invalidation of multiple inputs (single revision bump)
+- `Database.dependency_graph()` for machine-readable graph export of all nodes and edges
+- `Database.inspect(...)` for structured provenance and `Database.explain(...)` for human-readable formatting
+- `Database.statistics()` for aggregate counters and `Database.query_profile()` for per-query timing
+
+## Integrations
+
+- `pyinc.integrations.python_source` — workspace-local module discovery, top-level imports/definitions, simple assignment tracking for export surfaces, conservative import resolution with `workspace`/`stdlib`/`installed`/`missing`/`ambiguous` outcomes (stdlib and installed classification via composition with `installed_packages`; installed imports' `resolved_path` is populated via `deep_module_resolution`).
+- `pyinc.integrations.toml_config` — single-file TOML inspection: section/key extraction, dependency and optional-dependency discovery, tool config discovery.
+- `pyinc.integrations.requirements_txt` — narrow requirements parsing: normalized requirement specs, file references, index directives, editable installs, URL requirements. Includes `deep_requirements_analysis` for recursive `-r`/`--requirement` file following with cycle detection.
+- `pyinc.integrations.installed_packages` — installed package discovery via `importlib.metadata`-compatible `.dist-info` directories, stdlib module identification via `sys.stdlib_module_names`, and import name resolution (`stdlib`/`installed`/`unknown`).
+- `pyinc.integrations.deep_module_resolution` — deep module path resolution: `sys.path` walking, `.pth` file processing with backdating on whitespace/comment edits, PEP 420 namespace package collection, and dotted-name → file resolution. Exposes `resolve_module_path` for per-module queries and `deep_module_resolution_analysis` for a workspace-wide snapshot.
+- `pyinc.integrations.json_config` — single-file JSON inspection: section/key extraction with type detection, nested object traversal, parse error diagnostics.
+- `pyinc.integrations.dependency_check` — cross-integration dependency validation: composes `installed_packages` and `python_source` to detect undeclared imports and missing packages.
+- `pyinc.integrations.env_file` — `.env` file parsing: key-value extraction with quoted/unquoted values, `export` prefix handling, interpolation reference detection.
+- `pyinc.integrations.xml_config` — XML file inspection via `xml.etree.ElementTree`: element/attribute extraction, dot-path traversal, namespace-aware tag normalization.
+- `pyinc.integrations.csv_data` — CSV/TSV structural analysis via stdlib `csv`: header detection, column discovery, delimiter sniffing, row counting, inconsistent column diagnostics.
+- `pyinc.integrations.requirement_evaluation` — PEP 440 version specifier satisfaction and PEP 508 environment marker evaluation; composes with `requirements_txt` and `installed_packages` to surface the effective applicable/satisfied requirement set for the current Python environment. Exposes `evaluate_markers`, `evaluate_version_specifier`, and `applicable_requirements`.
+- `pyinc.integrations.symbol_resolution` — workspace-wide symbol tables (module-level + class-level), cross-module re-export following with cycle detection, and type-annotation text extraction via `ast.unparse` (no type evaluation). Exposes `module_symbol_table`, `resolve_symbol`, and `workspace_symbol_index`.
+
+`pyinc.integrations` re-exports only the stable dataclass/result types and high-level entrypoints for these integrations. Low-level payload queries, decode helpers, and resource helpers remain experimental in their defining submodules.
+
+## Verification
+
+- The runtime contract is summarized in [docs/kernel-contract.md](docs/kernel-contract.md).
+- The repo includes dedicated test modules for value semantics, runtime behavior, provenance/explanation formatting, property-based from-scratch consistency, and each shipped integration.
+- The integration suites exercise `strict`, `checked`, and `fast` modes and compare incremental results against fresh recomputation over edit sequences.
+
+The integration boundary is summarized in [docs/integration-contract.md](docs/integration-contract.md).
+
+## Gotchas
+
+- `Database.inspect(...)` is observational. It returns the last recorded provenance tree for that query key and does not force a fresh revalidation pass by itself.
+- Query identity includes the function definition payload. If you capture ambient values, those captures are part of the query fingerprint, and mutable closure/global captures are rejected.
+- `Database.report_untracked_read(...)` is an explicit impurity escape hatch. It marks that query as always re-executing and disables backdating for that node.
+- The package ships inline typing metadata via `py.typed`.
+
+## Not supported
+
+- LSP wiring
+- File watchers (push-based filesystem invalidation)
+
+These are architectural non-goals for v1. pyinc is a pull-based kernel; LSP servers
+and push-based watchers belong to a consumer tool built on top of pyinc, not to the
+kernel itself. See `docs/architecture.md:80-82` for the v1 scope boundary.
+
+## Development
+
+```bash
+python3 -m venv .venv
+. .venv/bin/activate
+python3 -m pip install -e '.[dev]'
+pytest -q
+python3 -m mypy src tests
+python3 -m ruff check src tests
+```
+
+The runtime contract is summarized in [docs/kernel-contract.md](docs/kernel-contract.md). Integration API boundaries are summarized in [docs/integration-contract.md](docs/integration-contract.md). A guide for building new integrations is at [docs/integration-authoring.md](docs/integration-authoring.md).

pyinc-1.0.0/README.md

@@ -0,0 +1,122 @@
+# pyinc
+
+[![CI](https://github.com/Brumbelow/pyinc/actions/workflows/ci.yml/badge.svg)](https://github.com/Brumbelow/pyinc/actions/workflows/ci.yml)
+[![PyPI](https://img.shields.io/pypi/v/pyinc.svg)](https://pypi.org/project/pyinc/)
+[![Python versions](https://img.shields.io/pypi/pyversions/pyinc.svg)](https://pypi.org/project/pyinc/)
+[![License](https://img.shields.io/pypi/l/pyinc.svg)](https://github.com/Brumbelow/pyinc/blob/main/LICENSE)
+
+```
+pip install pyinc
+```
+
+Python is mutable by default, identity-heavy, and full of hidden side effects. These properties make incremental computation unsound in practice: cached results silently depend on mutated state, untracked file reads, and object identity that the cache cannot see.
+
+`pyinc` is a correctness-first incremental computation engine that solves this problem. It is a pure-Python, stdlib-only query kernel in the design space of Salsa, Jane Street Incremental, and Bazel/Skyframe — but designed specifically for the challenges Python creates.
+
+v1.0.0 is the first stable release. The v1 kernel contract and public integration surface are stable under semver, within the soundness envelope documented in [docs/kernel-contract.md](docs/kernel-contract.md).
+
+## Quick example
+
+```python
+from pyinc import Database, FileResource, query
+
+_FILES = FileResource()
+
+@query
+def read_config(db, path):
+    return _FILES.read(db, path)      # tracked file read
+
+@query
+def parse_names(db, path):
+    text = read_config(db, path)
+    return [line.strip() for line in text.splitlines() if line.strip()]
+
+db = Database(mode="strict")
+result = db.get(parse_names, "/tmp/names.txt")   # computes from scratch
+result = db.get(parse_names, "/tmp/names.txt")   # reuses memo — file unchanged
+
+# Edit the file: only affected queries re-execute.
+# Comment-only edits can be backdated (early cutoff) with a cutoff= function.
+# Raw open() inside a query raises UntrackedReadError.
+# In strict mode, returned values are frozen — mutation raises TypeError.
+```
+
+See `examples/correctness_demo.py` for a full walkthrough of backdating (early cutoff), mutation protection, untracked read enforcement, and provenance inspection. `examples/undeclared_imports.py`, `examples/applicable_requirements.py`, and `examples/symbol_lookup.py` demonstrate three of the shipped integrations end-to-end on self-contained tempdir workspaces.
+
+## What pyinc guarantees
+
+pyinc guarantees **from-scratch consistency** — the result of incremental evaluation matches a fresh evaluation on the same declared inputs and resources — when:
+
+1. **Value boundary ownership**: all values crossing cached boundaries are snapshot-safe (frozen)
+2. **Tracked ambient reads**: all external state reads go through the Resource API
+3. **Deterministic queries**: given the same tracked dependencies, queries return semantically equal values
+
+The full contract, including explicit limitations and escape hatches, is in [docs/kernel-contract.md](docs/kernel-contract.md).
+
+## Current scope
+
+- `@query` for derived values, `Input` for explicit base leaves
+- optional `eq=` and `cutoff=` policies for custom equivalence and backdating (early cutoff)
+- `ValueAdapter` for custom snapshot-safe boundary types
+- `FileResource`, `FileStatResource`, `EnvResource`, and `DirectoryResource` for tracked external reads
+- pull-based recomputation with revisions, dependency capture, red-green verification, and backdating (early cutoff)
+- `strict`, `checked`, and `fast` execution modes with explicit boundary semantics
+- optional bounded query memoization via `Database(max_query_nodes=...)`
+- `Database.set_many(...)` for atomic batch invalidation of multiple inputs (single revision bump)
+- `Database.dependency_graph()` for machine-readable graph export of all nodes and edges
+- `Database.inspect(...)` for structured provenance and `Database.explain(...)` for human-readable formatting
+- `Database.statistics()` for aggregate counters and `Database.query_profile()` for per-query timing
+
+## Integrations
+
+- `pyinc.integrations.python_source` — workspace-local module discovery, top-level imports/definitions, simple assignment tracking for export surfaces, conservative import resolution with `workspace`/`stdlib`/`installed`/`missing`/`ambiguous` outcomes (stdlib and installed classification via composition with `installed_packages`; installed imports' `resolved_path` is populated via `deep_module_resolution`).
+- `pyinc.integrations.toml_config` — single-file TOML inspection: section/key extraction, dependency and optional-dependency discovery, tool config discovery.
+- `pyinc.integrations.requirements_txt` — narrow requirements parsing: normalized requirement specs, file references, index directives, editable installs, URL requirements. Includes `deep_requirements_analysis` for recursive `-r`/`--requirement` file following with cycle detection.
+- `pyinc.integrations.installed_packages` — installed package discovery via `importlib.metadata`-compatible `.dist-info` directories, stdlib module identification via `sys.stdlib_module_names`, and import name resolution (`stdlib`/`installed`/`unknown`).
+- `pyinc.integrations.deep_module_resolution` — deep module path resolution: `sys.path` walking, `.pth` file processing with backdating on whitespace/comment edits, PEP 420 namespace package collection, and dotted-name → file resolution. Exposes `resolve_module_path` for per-module queries and `deep_module_resolution_analysis` for a workspace-wide snapshot.
+- `pyinc.integrations.json_config` — single-file JSON inspection: section/key extraction with type detection, nested object traversal, parse error diagnostics.
+- `pyinc.integrations.dependency_check` — cross-integration dependency validation: composes `installed_packages` and `python_source` to detect undeclared imports and missing packages.
+- `pyinc.integrations.env_file` — `.env` file parsing: key-value extraction with quoted/unquoted values, `export` prefix handling, interpolation reference detection.
+- `pyinc.integrations.xml_config` — XML file inspection via `xml.etree.ElementTree`: element/attribute extraction, dot-path traversal, namespace-aware tag normalization.
+- `pyinc.integrations.csv_data` — CSV/TSV structural analysis via stdlib `csv`: header detection, column discovery, delimiter sniffing, row counting, inconsistent column diagnostics.
+- `pyinc.integrations.requirement_evaluation` — PEP 440 version specifier satisfaction and PEP 508 environment marker evaluation; composes with `requirements_txt` and `installed_packages` to surface the effective applicable/satisfied requirement set for the current Python environment. Exposes `evaluate_markers`, `evaluate_version_specifier`, and `applicable_requirements`.
+- `pyinc.integrations.symbol_resolution` — workspace-wide symbol tables (module-level + class-level), cross-module re-export following with cycle detection, and type-annotation text extraction via `ast.unparse` (no type evaluation). Exposes `module_symbol_table`, `resolve_symbol`, and `workspace_symbol_index`.
+
+`pyinc.integrations` re-exports only the stable dataclass/result types and high-level entrypoints for these integrations. Low-level payload queries, decode helpers, and resource helpers remain experimental in their defining submodules.
+
+## Verification
+
+- The runtime contract is summarized in [docs/kernel-contract.md](docs/kernel-contract.md).
+- The repo includes dedicated test modules for value semantics, runtime behavior, provenance/explanation formatting, property-based from-scratch consistency, and each shipped integration.
+- The integration suites exercise `strict`, `checked`, and `fast` modes and compare incremental results against fresh recomputation over edit sequences.
+
+The integration boundary is summarized in [docs/integration-contract.md](docs/integration-contract.md).
+
+## Gotchas
+
+- `Database.inspect(...)` is observational. It returns the last recorded provenance tree for that query key and does not force a fresh revalidation pass by itself.
+- Query identity includes the function definition payload. If you capture ambient values, those captures are part of the query fingerprint, and mutable closure/global captures are rejected.
+- `Database.report_untracked_read(...)` is an explicit impurity escape hatch. It marks that query as always re-executing and disables backdating for that node.
+- The package ships inline typing metadata via `py.typed`.
+
+## Not supported
+
+- LSP wiring
+- File watchers (push-based filesystem invalidation)
+
+These are architectural non-goals for v1. pyinc is a pull-based kernel; LSP servers
+and push-based watchers belong to a consumer tool built on top of pyinc, not to the
+kernel itself. See `docs/architecture.md:80-82` for the v1 scope boundary.
+
+## Development
+
+```bash
+python3 -m venv .venv
+. .venv/bin/activate
+python3 -m pip install -e '.[dev]'
+pytest -q
+python3 -m mypy src tests
+python3 -m ruff check src tests
+```
+
+The runtime contract is summarized in [docs/kernel-contract.md](docs/kernel-contract.md). Integration API boundaries are summarized in [docs/integration-contract.md](docs/integration-contract.md). A guide for building new integrations is at [docs/integration-authoring.md](docs/integration-authoring.md).

pyinc-1.0.0/docs/architecture.md

@@ -0,0 +1,84 @@
+# pyinc Architecture
+
+## Kernel
+
+`pyinc` is a pull-based incremental query runtime. The database stores query memos, inputs, and resources as revisioned node records with:
+
+- a stable node key
+- a frozen boundary snapshot
+- a semantic digest
+- dependency edges captured dynamically at runtime
+- `changed_at` and `verified_at` revisions
+- the last decision: `executed`, `reused`, or `backdated`
+
+`Database.inspect(...)` returns the last recorded provenance tree for a query key, and `Database.explain(...)` formats that tree without changing the node's recorded decision just by inspecting it.
+
+Evaluation is top-down. `db.get()` verifies dependencies first, then either reuses the memo or re-executes the query. If a re-executed query returns a semantically equal value, the record is **backdated** (also called **early cutoff**) so downstream nodes stay clean.
+
+`Database(max_query_nodes=...)` bounds only query memo nodes via LRU at top-level request boundaries. Inputs and resources remain resident.
+
+## Value Membrane
+
+Values crossing cached boundaries are frozen snapshots.
+
+- `strict`: expose frozen values directly.
+- `checked`: expose thawed copies and verify that queries did not mutate them.
+- `fast`: expose thawed copies without mutation checks.
+
+Hidden reads are not allowed in the core. Raw `open()` inside a query raises `UntrackedReadError` unless the access is routed through a resource object or explicitly marked via `db.report_untracked_read(...)`.
+
+The runtime also blocks raw ambient reads through `os.getenv`, `os.environ`, `os.listdir`, `os.scandir`, and `Path.iterdir` during query execution. Resource `probe`/`load` hooks run in an internal allow-scope so resource implementations can perform those reads safely.
+
+Query definitions are also checked for ambient state. Immutable constants and explicit `Input`/resource/query handles are allowed; mutable closure or global data is rejected so memo reuse never depends on hidden Python object mutation.
+
+Query identity includes the supported function definition payload, so ambient immutable captures contribute to the fingerprint instead of being ignored.
+
+Resource node identity includes resource configuration. Built-in resources are snapshot-safe dataclasses, and custom resources must either be snapshot-safe themselves or expose an `identity()` payload for keying.
+
+## Package Shape Today
+
+`pyinc` exposes a stable kernel surface from the top-level package:
+
+- `Database`, `Input`, and `@query` for the query runtime
+- `FileResource`, `FileStatResource`, `EnvResource`, and `DirectoryResource` for tracked external reads
+- value-boundary helpers such as `freeze`, `thaw`, `semantic_equal`, and `ValueAdapter`
+- structured inspection via `InspectionNode`, `Database.inspect(...)`, and `Database.explain(...)`
+
+`pyinc.integrations` exposes the stable high-level surfaces from the four shipped integrations:
+
+- `python_source` for narrow Python source and workspace-local module analysis
+- `toml_config` for narrow `pyproject.toml` inspection
+- `requirements_txt` for narrow `requirements.txt` inspection
+- `installed_packages` for installed package discovery, stdlib module identification, and import name resolution
+
+Low-level payload queries, decode helpers, and resource helpers remain module-local experimental helpers. The public integration boundary is the dataclass/result layer plus the documented high-level entrypoints in `docs/integration-contract.md`.
+
+The repository also includes small examples under `examples/` plus dedicated tests for kernel semantics, property-based from-scratch consistency, and each shipped integration.
+
+## Cross-Integration Composition
+
+Integrations can compose at the query layer by importing `@query` functions from other integration modules. The kernel's dependency tracking extends automatically across integration boundaries -- no special wiring is required. When an upstream integration's query result changes, downstream queries that depend on it are re-verified and re-executed through the normal red-green algorithm.
+
+Currently, `python_source` composes with `installed_packages`: it imports the `environment_index` query to classify non-workspace imports as `stdlib`, `installed`, or `missing`. This means that if the installed package environment changes (e.g., a package is installed or removed), `python_source`'s import resolution results are automatically invalidated and recomputed on the next request.
+
+Composition queries like `environment_index` are public `@query` functions exported in their module's `__all__`, but they are intentionally not re-exported from `pyinc.integrations`. They exist for query-layer composition between integrations, not as user-facing entrypoints.
+
+## Scope
+
+Version 1 targets:
+
+- module-defined `@query` functions
+- explicit `Input` leaves
+- explicit file, env, and directory resources
+- optional file metadata resources (`FileStatResource`) for stat-level dependencies
+- explanation/provenance for reuse vs recompute
+- inline package typing via `py.typed`
+- narrow supported integrations for Python source analysis, TOML config inspection, requirements parsing, and installed package discovery
+
+Version 1 does not include:
+
+- notebook integration
+- push observers
+- schedulers or worker pools
+- content-addressed artifact storage
+- arbitrary mutable object graphs across cached boundaries