litschema 0.1.1__tar.gz

litschema-0.1.1/.gitignore

@@ -0,0 +1,53 @@
+# Python
+__pycache__/
+*.pyc
+*.egg-info/
+.venv/
+.env
+
+# Build/test outputs
+dist/
+build/
+.pytest_cache/
+.ruff_cache/
+.mypy_cache/
+site/
+static-site/
+.litschema/
+
+# Local agent/editor state
+.claude/
+.codex/
+.idea/
+.DS_Store
+
+# Project data generated by users
+papers/
+data/
+*.pdf
+
+# ...but test fixture projects are source, not user data. Without this the
+# `data/` rule silently drops fixture files, and tests that pass locally on
+# untracked files fail in CI with nothing to point at.
+#
+# Negate only the three rules above that wrongly catch fixture content, rather
+# than the whole subtree: `!tests/fixtures/**` would also un-ignore every
+# generated and private file that happens to land there.
+!tests/fixtures/**/data/
+!tests/fixtures/**/data/**
+!tests/fixtures/**/papers/
+!tests/fixtures/**/papers/**
+!tests/fixtures/**/*.pdf
+
+# Generated or private files stay ignored wherever they land, including inside
+# a fixture — they are rebuilt or personal, not authored.
+tests/fixtures/**/.litschema/
+tests/fixtures/**/__pycache__/
+tests/fixtures/**/.venv/
+tests/fixtures/**/.env
+tests/fixtures/**/.claude/
+tests/fixtures/**/.codex/
+tests/fixtures/**/.DS_Store
+
+# AI tooling
+.roborev.toml

litschema-0.1.1/CITATION.cff

@@ -0,0 +1,19 @@
+cff-version: 1.2.0
+message: "If you use litschema in your research, please cite it as below."
+type: software
+title: "litschema"
+abstract: "Schema-driven extraction of structured data from PDFs, with line-cited evidence and per-field human review."
+authors:
+  - family-names: Levinson
+    given-names: Cory
+    orcid: "https://orcid.org/0009-0009-8902-102X"
+repository-code: "https://github.com/clevinson/litschema"
+license: Apache-2.0
+version: 0.1.1
+date-released: 2026-09-27
+keywords:
+  - linkml
+  - systematic-review
+  - meta-analysis
+  - data-extraction
+  - provenance

litschema-0.1.1/LICENSE

@@ -0,0 +1,191 @@
+
+                                 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 the 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 the 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 any 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
+
+   Copyright 2025 Cory Grinstead
+
+   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.

litschema-0.1.1/PKG-INFO

@@ -0,0 +1,176 @@
+Metadata-Version: 2.5
+Name: litschema
+Version: 0.1.1
+Summary: Schema-driven, agentic extraction of structured data from scientific literature. LinkML-native, local-first, with bundled agent skills.
+Project-URL: Homepage, https://github.com/clevinson/litschema
+Project-URL: Repository, https://github.com/clevinson/litschema
+Project-URL: Issues, https://github.com/clevinson/litschema/issues
+Project-URL: Changelog, https://github.com/clevinson/litschema/blob/main/CHANGELOG.md
+Project-URL: Documentation, https://github.com/clevinson/litschema#readme
+Author-email: Cory Levinson <cjlevinson@gmail.com>
+License-Expression: Apache-2.0
+License-File: LICENSE
+Keywords: extraction,linkml,meta-analysis,pdf,schema,systematic-review
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Text Processing :: Markup
+Requires-Python: >=3.13
+Requires-Dist: duckdb>=1.0.0
+Requires-Dist: fastapi[standard]>=0.115
+Requires-Dist: linkml>=1.10.0
+Requires-Dist: mcp>=1.27.0
+Requires-Dist: pymupdf4llm<1.29,>=1.28.0
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: requests>=2.31.0
+Requires-Dist: typer>=0.12.0
+Description-Content-Type: text/markdown
+
+# litschema
+
+**Turn a folder of PDFs into a dataset you can defend.**
+
+Extraction gets you structured data. `litschema` gets you structured data where
+every value carries the lines it came from, a record of which model produced
+it, and a human's verdict on whether it's right — because in a systematic
+review or meta-analysis, "the model said so" is not a citation.
+
+Everything runs on your machine. The only network calls are optional DOI
+lookups and the verifier's ORCID name resolution.
+
+## What you get
+
+For each document, three artifacts that stay in step:
+
+```text
+data/papers/<article-id>/
+  article-metadata.json                  identity + bibliographic block
+  <article-id>.pdf
+  article.md                             prepared full text
+  active-run.json                        which extraction is current
+  extraction-runs/<run-id>/
+    agent-extraction.json                what the document SAYS (schema-valid)
+    agent-reasoning.json                 why — per-field evidence, line-cited
+    run.json                             inputs hashed, model recorded
+    review.json                          your verdicts on this run
+```
+
+Plain JSON on disk, one directory per document, diffable in git. A run is
+immutable once published: its extraction, reasoning, and `run.json` never
+change, so a review written against it stays meaningful forever. Re-extracting
+creates a new run rather than overwriting the old one.
+
+## Alpha Software
+
+**litschema is early software. Extracted data may need regenerating
+when updating litschema versions.**
+
+One limit qualifies the line-level citations promised above: PDF conversion
+collapses some tables onto a single line, so a citation into a table can name
+the table but not the row. This matters most for measurement-heavy schemas.
+
+Each release documents its breaking changes and known limits in the
+[CHANGELOG.md](https://github.com/clevinson/litschema/blob/main/CHANGELOG.md).
+
+## Specs
+
+The [specs](https://github.com/clevinson/litschema/blob/main/specs/README.md) describe what is currently implemented; anything
+deferred says so and names where it is tracked.
+
+## The flow
+
+```bash
+litschema init my-project       # scaffold a project
+                                # drop PDFs into papers-inbox/
+/litschema-onboard              # agent: drafts your schema, extracts, pilots
+litschema verify                # you: check what was extracted
+litschema export                # the reviewed data, ready for analysis
+```
+
+`/litschema-onboard` is a bundled agent skill, installed into `.claude/skills/`
+by `init`. It interviews you to draft a LinkML schema from your own papers,
+runs intake, extracts one article as a pilot so you can course-correct, then
+batches the rest.
+
+## Install
+
+```bash
+uv tool install litschema      # or: pip install litschema
+litschema --version
+```
+
+`init` pins each project to the version that created it (`litschema_version`
+in `litschema.yaml`), and commands refuse to run under any other. To move a
+project to a new release, install it and edit the pin.
+
+To try an unreleased tag or work on litschema itself:
+
+```bash
+uv tool install "litschema @ git+https://github.com/clevinson/litschema@v0.1.1" --force
+uv tool install --editable path/to/litschema --force   # edits take effect immediately
+```
+
+## Commands
+
+```bash
+litschema init <dir>               scaffold a project; installs agent skills locally
+litschema doctor                   diagnose config, schema, and skill installation
+litschema status                   counts: inbox, articles, runs, reviews
+litschema assemble                 papers-inbox PDFs -> per-article folders (offline)
+litschema prepare-text <id>|--all  PDF -> article.md (offline)
+litschema meta show|set|sync <id>  bibliographic metadata, provenance-tagged
+litschema validate [target]        validate extractions against the schema
+litschema runs list|activate       inspect published runs; choose the active one
+litschema verify [--port 8000]     local review webapp (loopback only)
+litschema export [-f jsonl|csv]    reviewed data as flat files (pandas/R/jq-ready)
+litschema mcp                      DuckDB store served over MCP (experimental)
+litschema skills install           install the agent skills globally
+litschema agent ...                deterministic steps the extraction skill calls
+```
+
+There is no `litschema extract`: extraction is judgment work, so it runs as an
+agent skill (`/extract-article <id>`) with the framework checking the output.
+The verb exists only to say so.
+
+## How it works
+
+**Intake is offline and content-addressed.** `assemble` derives a stable
+article id from each PDF's filename, moves the PDF into the store, and writes a
+minimal manifest. No DOI, bibliography file, or network access is needed to
+reach extraction, and re-dropping the same PDF is a no-op.
+
+**Extraction is agent-executed, framework-checked.** The agent reads only the
+prepared text, writes an extraction plus a line-cited reasoning file, and loops
+until both validate. Validation is closed-world — nothing the schema doesn't
+define gets in — and citations must resolve to real lines in the prepared text,
+so a reference to a line that doesn't exist fails rather than shipping.
+
+**Runs are immutable and provenance-bearing.** Publishing records the SHA-256
+of every input — prepared text, domain context, and the skill that conducted
+the extraction — alongside the schema hash and what produced it. Reproduction
+data is computed by the publisher; attribution is recorded as asserted, since
+an agent cannot verify its own model. Nothing is overwritten.
+
+**Bibliographic metadata is provenance-locked.** Values fetched from a DOI
+registry are marked and locked; machine-written values may be upgraded but
+human edits are never overwritten without explicit consent. Documents with no
+DOI flow through unchanged.
+
+**Review is field-by-field and git-native.** `litschema verify` shows every
+extracted value beside its cited source lines, with the model and effort that
+produced it. You verify a value, correct it, or remove it — one entry per
+field, stored inside the run it reviews. Diffs of `review.json` are the audit
+log. Because a run's payload can never change, a review never goes stale.
+
+**Use the reviewed truth.** `export` writes the review-applied extractions as
+JSONL or CSV for pandas, R, or jq. `mcp` (experimental) derives a DuckDB
+database from your schema and serves it read-only. Both apply overrides and
+skip error markers, so they agree.
+
+## Project layout
+
+- `src/litschema/` — package code and CLI
+- `specs/` — capability specs and decision logs; start at `specs/README.md`
+- `skills/` — the agent-facing extraction and onboarding instructions
+- `tests/` — framework tests and small project fixtures

litschema-0.1.1/README.md

@@ -0,0 +1,147 @@
+# litschema
+
+**Turn a folder of PDFs into a dataset you can defend.**
+
+Extraction gets you structured data. `litschema` gets you structured data where
+every value carries the lines it came from, a record of which model produced
+it, and a human's verdict on whether it's right — because in a systematic
+review or meta-analysis, "the model said so" is not a citation.
+
+Everything runs on your machine. The only network calls are optional DOI
+lookups and the verifier's ORCID name resolution.
+
+## What you get
+
+For each document, three artifacts that stay in step:
+
+```text
+data/papers/<article-id>/
+  article-metadata.json                  identity + bibliographic block
+  <article-id>.pdf
+  article.md                             prepared full text
+  active-run.json                        which extraction is current
+  extraction-runs/<run-id>/
+    agent-extraction.json                what the document SAYS (schema-valid)
+    agent-reasoning.json                 why — per-field evidence, line-cited
+    run.json                             inputs hashed, model recorded
+    review.json                          your verdicts on this run
+```
+
+Plain JSON on disk, one directory per document, diffable in git. A run is
+immutable once published: its extraction, reasoning, and `run.json` never
+change, so a review written against it stays meaningful forever. Re-extracting
+creates a new run rather than overwriting the old one.
+
+## Alpha Software
+
+**litschema is early software. Extracted data may need regenerating
+when updating litschema versions.**
+
+One limit qualifies the line-level citations promised above: PDF conversion
+collapses some tables onto a single line, so a citation into a table can name
+the table but not the row. This matters most for measurement-heavy schemas.
+
+Each release documents its breaking changes and known limits in the
+[CHANGELOG.md](https://github.com/clevinson/litschema/blob/main/CHANGELOG.md).
+
+## Specs
+
+The [specs](https://github.com/clevinson/litschema/blob/main/specs/README.md) describe what is currently implemented; anything
+deferred says so and names where it is tracked.
+
+## The flow
+
+```bash
+litschema init my-project       # scaffold a project
+                                # drop PDFs into papers-inbox/
+/litschema-onboard              # agent: drafts your schema, extracts, pilots
+litschema verify                # you: check what was extracted
+litschema export                # the reviewed data, ready for analysis
+```
+
+`/litschema-onboard` is a bundled agent skill, installed into `.claude/skills/`
+by `init`. It interviews you to draft a LinkML schema from your own papers,
+runs intake, extracts one article as a pilot so you can course-correct, then
+batches the rest.
+
+## Install
+
+```bash
+uv tool install litschema      # or: pip install litschema
+litschema --version
+```
+
+`init` pins each project to the version that created it (`litschema_version`
+in `litschema.yaml`), and commands refuse to run under any other. To move a
+project to a new release, install it and edit the pin.
+
+To try an unreleased tag or work on litschema itself:
+
+```bash
+uv tool install "litschema @ git+https://github.com/clevinson/litschema@v0.1.1" --force
+uv tool install --editable path/to/litschema --force   # edits take effect immediately
+```
+
+## Commands
+
+```bash
+litschema init <dir>               scaffold a project; installs agent skills locally
+litschema doctor                   diagnose config, schema, and skill installation
+litschema status                   counts: inbox, articles, runs, reviews
+litschema assemble                 papers-inbox PDFs -> per-article folders (offline)
+litschema prepare-text <id>|--all  PDF -> article.md (offline)
+litschema meta show|set|sync <id>  bibliographic metadata, provenance-tagged
+litschema validate [target]        validate extractions against the schema
+litschema runs list|activate       inspect published runs; choose the active one
+litschema verify [--port 8000]     local review webapp (loopback only)
+litschema export [-f jsonl|csv]    reviewed data as flat files (pandas/R/jq-ready)
+litschema mcp                      DuckDB store served over MCP (experimental)
+litschema skills install           install the agent skills globally
+litschema agent ...                deterministic steps the extraction skill calls
+```
+
+There is no `litschema extract`: extraction is judgment work, so it runs as an
+agent skill (`/extract-article <id>`) with the framework checking the output.
+The verb exists only to say so.
+
+## How it works
+
+**Intake is offline and content-addressed.** `assemble` derives a stable
+article id from each PDF's filename, moves the PDF into the store, and writes a
+minimal manifest. No DOI, bibliography file, or network access is needed to
+reach extraction, and re-dropping the same PDF is a no-op.
+
+**Extraction is agent-executed, framework-checked.** The agent reads only the
+prepared text, writes an extraction plus a line-cited reasoning file, and loops
+until both validate. Validation is closed-world — nothing the schema doesn't
+define gets in — and citations must resolve to real lines in the prepared text,
+so a reference to a line that doesn't exist fails rather than shipping.
+
+**Runs are immutable and provenance-bearing.** Publishing records the SHA-256
+of every input — prepared text, domain context, and the skill that conducted
+the extraction — alongside the schema hash and what produced it. Reproduction
+data is computed by the publisher; attribution is recorded as asserted, since
+an agent cannot verify its own model. Nothing is overwritten.
+
+**Bibliographic metadata is provenance-locked.** Values fetched from a DOI
+registry are marked and locked; machine-written values may be upgraded but
+human edits are never overwritten without explicit consent. Documents with no
+DOI flow through unchanged.
+
+**Review is field-by-field and git-native.** `litschema verify` shows every
+extracted value beside its cited source lines, with the model and effort that
+produced it. You verify a value, correct it, or remove it — one entry per
+field, stored inside the run it reviews. Diffs of `review.json` are the audit
+log. Because a run's payload can never change, a review never goes stale.
+
+**Use the reviewed truth.** `export` writes the review-applied extractions as
+JSONL or CSV for pandas, R, or jq. `mcp` (experimental) derives a DuckDB
+database from your schema and serves it read-only. Both apply overrides and
+skip error markers, so they agree.
+
+## Project layout
+
+- `src/litschema/` — package code and CLI
+- `specs/` — capability specs and decision logs; start at `specs/README.md`
+- `skills/` — the agent-facing extraction and onboarding instructions
+- `tests/` — framework tests and small project fixtures