sub-checker 0.1.0__tar.gz

sub_checker-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 odafeng
+
+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.

sub_checker-0.1.0/PKG-INFO

@@ -0,0 +1,193 @@
+Metadata-Version: 2.4
+Name: sub-checker
+Version: 0.1.0
+Summary: Pre-submission manuscript checker powered by Claude agents
+Author: odafeng
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/odafeng/sub-checker
+Project-URL: Repository, https://github.com/odafeng/sub-checker
+Project-URL: Issues, https://github.com/odafeng/sub-checker/issues
+Keywords: academic,manuscript,submission,checker,agent,claude,proofreading,citation,journal
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+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 :: Scientific/Engineering
+Classifier: Topic :: Text Processing :: Linguistic
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: click>=8.0
+Requires-Dist: python-docx>=1.0
+Requires-Dist: anthropic>=0.106
+Requires-Dist: httpx>=0.27
+Requires-Dist: pydantic>=2.0
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: rich>=13.0
+Provides-Extra: web
+Requires-Dist: fastapi>=0.115; extra == "web"
+Requires-Dist: uvicorn[standard]>=0.32; extra == "web"
+Requires-Dist: python-multipart>=0.0.12; extra == "web"
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.23; extra == "dev"
+Requires-Dist: pytest-httpx>=0.30; extra == "dev"
+Requires-Dist: ruff>=0.8; extra == "dev"
+Requires-Dist: pyright>=1.1; extra == "dev"
+Requires-Dist: pre-commit>=4.0; extra == "dev"
+Dynamic: license-file
+
+# sub-checker
+
+[繁體中文](README.zh-TW.md) | English
+
+Pre-submission manuscript checker powered by Claude agents with a Plan-Execute-Verify harness. Each check is performed by a specialized AI agent, then validated by deterministic checks and a reviewer agent to eliminate false positives.
+
+## What it checks
+
+| Agent | What it does |
+|-------|-------------|
+| **typo_grammar** | Spelling, grammar, awkward phrasing (skips reference list) |
+| **figure_table** | Figure/table references exist, numbering is sequential, files present |
+| **citation_exist** | In-text citations match the reference list (deterministic pre-scan + agent) |
+| **citation_format** | Reference list follows target journal's citation style (APA, Vancouver, AMA, etc.) |
+| **journal_guidelines** | Word count, required sections, abstract format, required statements (COI, ethics, data availability) |
+| **logic** | Contradictions, unsupported claims, methods-results mismatches |
+| **citation_claim** | Multi-source verification (PubMed + Semantic Scholar + Crossref), then verifies claims against abstracts |
+
+## Install
+
+```bash
+pip install sub-checker
+```
+
+## Setup
+
+You need an Anthropic API key:
+
+```bash
+export ANTHROPIC_API_KEY=sk-ant-...
+```
+
+Or create a `.env` file in your working directory:
+
+```
+ANTHROPIC_API_KEY=sk-ant-...
+```
+
+## Usage
+
+### CLI
+
+```bash
+# Full check with target journal
+sub-check paper.docx -j "The Lancet"
+
+# Chinese report output
+sub-check paper.docx -j "Nature Medicine" --lang zh-TW
+
+# Only run specific checkers (cheaper & faster)
+sub-check paper.docx --only figure,citation
+
+# Skip expensive checkers
+sub-check paper.docx --skip claim,logic
+
+# Output as styled HTML report (includes COT viewer + confidence scores)
+sub-check paper.docx -o html --output-file report.html
+
+# Output as JSON (for programmatic use)
+sub-check paper.docx -o json --output-file report.json
+
+# Dry run (just parse, no agents)
+sub-check paper.docx --dry-run
+```
+
+### Web GUI
+
+```bash
+# Start backend
+uvicorn sub_checker.api:app --reload
+
+# Start frontend (in another terminal)
+cd frontend && npm run dev
+```
+
+Open `http://localhost:5173` — upload a `.docx`, pick a journal, run, and view the report with confidence badges and filtered false positives.
+
+### CLI options
+
+```
+sub-check [OPTIONS] MANUSCRIPT_PATH
+
+Arguments:
+  MANUSCRIPT_PATH    Path to .docx file or directory containing one
+
+Options:
+  -j, --journal      Target journal name (e.g. "The Lancet")
+  -o, --output       terminal | json | markdown | html (default: terminal)
+  --output-file      Write report to file
+  --lang             Report language: en (default) or zh-TW
+  --only             Comma-separated: typo,logic,figure,citation,format,guidelines,claim
+  --skip             Comma-separated checkers to skip
+  -v, --verbose      Show agent tool calls in real-time
+  --dry-run          Only parse .docx, don't run agents
+  --init             Generate default .sub-checker.yaml
+```
+
+## Pipeline (5 phases)
+
+```
+Phase 1-3  │  7 checker agents (parallel within each phase)
+Phase 4    │  Deterministic post-validation (date math, citation cross-check)
+Phase 5    │  Reviewer agent validates all findings → confidence scores
+```
+
+- **Pre-execution**: deterministic citation pre-scan + multi-source reference verification
+- **Post-validation**: false positives filtered, remaining findings get confidence scores (0-100%)
+- See [harness-architecture.md](docs/harness-architecture.md) for full technical details
+
+## HTML report features
+
+- Dark-themed styled report with severity badges
+- **Confidence scores** — each finding shows reviewer-assigned confidence (%)
+- **False positive filtering** — deterministic + reviewer agent removes incorrect findings
+- **Chain of Thought viewer** — expand to see every API call, tool use, and reasoning step
+- **Model display** — shows which Claude model generated the report
+- i18n support (English / Traditional Chinese)
+
+## Cost estimate
+
+Uses Claude Opus 4.8 by default. Approximate cost per manuscript (~4000 words):
+
+| Scope | Agents | Time | Cost |
+|-------|--------|------|------|
+| Quick check | `--only figure,citation` | ~4 min | ~$3 |
+| Standard | `--skip claim` | ~8 min | ~$7 |
+| Full check | all 7 agents + harness | ~12 min | ~$12–16 |
+
+You can change the model in `.sub-checker.yaml` (e.g. use `claude-sonnet-4-6` for cheaper runs).
+
+## Logging
+
+All logs are stored in `~/.sub-checker/`:
+
+- `logs/sub-checker.log` — application log (auto-rotated, 10MB x 5)
+- `logs/sub-checker.error.log` — errors only
+- `cot/` — agent chain-of-thought JSON logs (every tool call, every response)
+
+Set `cot_dir: "disabled"` in `.sub-checker.yaml` to turn off COT file logging (entries still appear in HTML reports).
+
+## Architecture
+
+- **5-phase pipeline**: Plan-Execute-Verify harness ([ADR-0010](docs/adr/0010-plan-execute-verify-harness.md))
+- 7 agents + reviewer agent, each with system prompt + curated tools + agentic loop ([ADR-0002](docs/adr/0002-agent-per-checker-architecture.md))
+- Parser provides raw data; agents judge document structure ([ADR-0009](docs/adr/0009-agent-over-deterministic-parsing.md))
+- Multi-source citation verification: PubMed + Semantic Scholar + Crossref ([ADR-0005](docs/adr/0005-semantic-scholar-fallback.md))
+- FastAPI + React + TypeScript GUI ([ADR-0006](docs/adr/0006-fastapi-react-gui.md))
+- [Benchmark comparison](docs/benchmark-comparison.md) | [Harness architecture](docs/harness-architecture.md)
+
+## License
+
+MIT

sub_checker-0.1.0/README.md

@@ -0,0 +1,152 @@
+# sub-checker
+
+[繁體中文](README.zh-TW.md) | English
+
+Pre-submission manuscript checker powered by Claude agents with a Plan-Execute-Verify harness. Each check is performed by a specialized AI agent, then validated by deterministic checks and a reviewer agent to eliminate false positives.
+
+## What it checks
+
+| Agent | What it does |
+|-------|-------------|
+| **typo_grammar** | Spelling, grammar, awkward phrasing (skips reference list) |
+| **figure_table** | Figure/table references exist, numbering is sequential, files present |
+| **citation_exist** | In-text citations match the reference list (deterministic pre-scan + agent) |
+| **citation_format** | Reference list follows target journal's citation style (APA, Vancouver, AMA, etc.) |
+| **journal_guidelines** | Word count, required sections, abstract format, required statements (COI, ethics, data availability) |
+| **logic** | Contradictions, unsupported claims, methods-results mismatches |
+| **citation_claim** | Multi-source verification (PubMed + Semantic Scholar + Crossref), then verifies claims against abstracts |
+
+## Install
+
+```bash
+pip install sub-checker
+```
+
+## Setup
+
+You need an Anthropic API key:
+
+```bash
+export ANTHROPIC_API_KEY=sk-ant-...
+```
+
+Or create a `.env` file in your working directory:
+
+```
+ANTHROPIC_API_KEY=sk-ant-...
+```
+
+## Usage
+
+### CLI
+
+```bash
+# Full check with target journal
+sub-check paper.docx -j "The Lancet"
+
+# Chinese report output
+sub-check paper.docx -j "Nature Medicine" --lang zh-TW
+
+# Only run specific checkers (cheaper & faster)
+sub-check paper.docx --only figure,citation
+
+# Skip expensive checkers
+sub-check paper.docx --skip claim,logic
+
+# Output as styled HTML report (includes COT viewer + confidence scores)
+sub-check paper.docx -o html --output-file report.html
+
+# Output as JSON (for programmatic use)
+sub-check paper.docx -o json --output-file report.json
+
+# Dry run (just parse, no agents)
+sub-check paper.docx --dry-run
+```
+
+### Web GUI
+
+```bash
+# Start backend
+uvicorn sub_checker.api:app --reload
+
+# Start frontend (in another terminal)
+cd frontend && npm run dev
+```
+
+Open `http://localhost:5173` — upload a `.docx`, pick a journal, run, and view the report with confidence badges and filtered false positives.
+
+### CLI options
+
+```
+sub-check [OPTIONS] MANUSCRIPT_PATH
+
+Arguments:
+  MANUSCRIPT_PATH    Path to .docx file or directory containing one
+
+Options:
+  -j, --journal      Target journal name (e.g. "The Lancet")
+  -o, --output       terminal | json | markdown | html (default: terminal)
+  --output-file      Write report to file
+  --lang             Report language: en (default) or zh-TW
+  --only             Comma-separated: typo,logic,figure,citation,format,guidelines,claim
+  --skip             Comma-separated checkers to skip
+  -v, --verbose      Show agent tool calls in real-time
+  --dry-run          Only parse .docx, don't run agents
+  --init             Generate default .sub-checker.yaml
+```
+
+## Pipeline (5 phases)
+
+```
+Phase 1-3  │  7 checker agents (parallel within each phase)
+Phase 4    │  Deterministic post-validation (date math, citation cross-check)
+Phase 5    │  Reviewer agent validates all findings → confidence scores
+```
+
+- **Pre-execution**: deterministic citation pre-scan + multi-source reference verification
+- **Post-validation**: false positives filtered, remaining findings get confidence scores (0-100%)
+- See [harness-architecture.md](docs/harness-architecture.md) for full technical details
+
+## HTML report features
+
+- Dark-themed styled report with severity badges
+- **Confidence scores** — each finding shows reviewer-assigned confidence (%)
+- **False positive filtering** — deterministic + reviewer agent removes incorrect findings
+- **Chain of Thought viewer** — expand to see every API call, tool use, and reasoning step
+- **Model display** — shows which Claude model generated the report
+- i18n support (English / Traditional Chinese)
+
+## Cost estimate
+
+Uses Claude Opus 4.8 by default. Approximate cost per manuscript (~4000 words):
+
+| Scope | Agents | Time | Cost |
+|-------|--------|------|------|
+| Quick check | `--only figure,citation` | ~4 min | ~$3 |
+| Standard | `--skip claim` | ~8 min | ~$7 |
+| Full check | all 7 agents + harness | ~12 min | ~$12–16 |
+
+You can change the model in `.sub-checker.yaml` (e.g. use `claude-sonnet-4-6` for cheaper runs).
+
+## Logging
+
+All logs are stored in `~/.sub-checker/`:
+
+- `logs/sub-checker.log` — application log (auto-rotated, 10MB x 5)
+- `logs/sub-checker.error.log` — errors only
+- `cot/` — agent chain-of-thought JSON logs (every tool call, every response)
+
+Set `cot_dir: "disabled"` in `.sub-checker.yaml` to turn off COT file logging (entries still appear in HTML reports).
+
+## Architecture
+
+- **5-phase pipeline**: Plan-Execute-Verify harness ([ADR-0010](docs/adr/0010-plan-execute-verify-harness.md))
+- 7 agents + reviewer agent, each with system prompt + curated tools + agentic loop ([ADR-0002](docs/adr/0002-agent-per-checker-architecture.md))
+- Parser provides raw data; agents judge document structure ([ADR-0009](docs/adr/0009-agent-over-deterministic-parsing.md))
+- Multi-source citation verification: PubMed + Semantic Scholar + Crossref ([ADR-0005](docs/adr/0005-semantic-scholar-fallback.md))
+- FastAPI + React + TypeScript GUI ([ADR-0006](docs/adr/0006-fastapi-react-gui.md))
+- [Benchmark comparison](docs/benchmark-comparison.md) | [Harness architecture](docs/harness-architecture.md)
+
+## License
+
+MIT

sub_checker-0.1.0/pyproject.toml

@@ -0,0 +1,107 @@
+[build-system]
+requires = ["setuptools>=68.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "sub-checker"
+version = "0.1.0"
+description = "Pre-submission manuscript checker powered by Claude agents"
+readme = "README.md"
+license = "MIT"
+requires-python = ">=3.11"
+authors = [
+    { name = "odafeng" },
+]
+keywords = [
+    "academic",
+    "manuscript",
+    "submission",
+    "checker",
+    "agent",
+    "claude",
+    "proofreading",
+    "citation",
+    "journal",
+]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Science/Research",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Scientific/Engineering",
+    "Topic :: Text Processing :: Linguistic",
+]
+dependencies = [
+    "click>=8.0",
+    "python-docx>=1.0",
+    "anthropic>=0.106",
+    "httpx>=0.27",
+    "pydantic>=2.0",
+    "pyyaml>=6.0",
+    "rich>=13.0",
+]
+
+[project.optional-dependencies]
+web = [
+    "fastapi>=0.115",
+    "uvicorn[standard]>=0.32",
+    "python-multipart>=0.0.12",
+]
+dev = [
+    "pytest>=8.0",
+    "pytest-asyncio>=0.23",
+    "pytest-httpx>=0.30",
+    "ruff>=0.8",
+    "pyright>=1.1",
+    "pre-commit>=4.0",
+]
+
+[project.urls]
+Homepage = "https://github.com/odafeng/sub-checker"
+Repository = "https://github.com/odafeng/sub-checker"
+Issues = "https://github.com/odafeng/sub-checker/issues"
+
+[project.scripts]
+sub-check = "sub_checker.cli:main"
+sub-check-eval = "sub_checker.eval_runner:main"
+
+# ── Ruff ──────────────────────────────────────────────
+[tool.ruff]
+target-version = "py311"
+line-length = 100
+src = ["src", "tests"]
+
+[tool.ruff.lint]
+select = [
+    "E",    # pycodestyle errors
+    "W",    # pycodestyle warnings
+    "F",    # pyflakes
+    "I",    # isort
+    "N",    # pep8-naming
+    "UP",   # pyupgrade
+    "B",    # flake8-bugbear
+    "SIM",  # flake8-simplify
+    "RUF",  # ruff-specific
+]
+ignore = [
+    "E501",   # line too long (handled by formatter)
+]
+
+[tool.ruff.lint.isort]
+known-first-party = ["sub_checker"]
+
+# ── Pyright ───────────────────────────────────────────
+[tool.pyright]
+pythonVersion = "3.11"
+pythonPlatform = "All"
+typeCheckingMode = "basic"
+venvPath = "."
+venv = ".venv"
+reportMissingImports = false
+
+# ── Pytest ────────────────────────────────────────────
+[tool.pytest.ini_options]
+asyncio_mode = "auto"
+testpaths = ["tests"]

sub_checker-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

sub_checker-0.1.0/src/sub_checker/__init__.py

@@ -0,0 +1,3 @@
+"""Sub-Checker: Pre-submission manuscript checker powered by Claude agents."""
+
+__version__ = "0.1.0"