colloquial 0.1.0__tar.gz

colloquial-0.1.0/LICENSE

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

colloquial-0.1.0/PKG-INFO

@@ -0,0 +1,244 @@
+Metadata-Version: 2.4
+Name: colloquial
+Version: 0.1.0
+Summary: Rewrite machine text into colloquial, native-sounding language — humanize in the same language or translate-and-humanize, in any tongue.
+Author: XScryer
+License: MIT License
+        
+        Copyright (c) 2026 Robert (XScryer)
+        
+        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.
+        
+Project-URL: Homepage, https://github.com/XScryer/colloquial
+Project-URL: Repository, https://github.com/XScryer/colloquial
+Project-URL: Issues, https://github.com/XScryer/colloquial/issues
+Project-URL: Changelog, https://github.com/XScryer/colloquial/blob/main/CHANGELOG.md
+Keywords: nlp,writing,humanize,translation,llm,slop
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Text Processing :: Linguistic
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Provides-Extra: dev
+Requires-Dist: bandit>=1.7; extra == "dev"
+Requires-Dist: mypy>=1.10; extra == "dev"
+Requires-Dist: pip-audit>=2.7; extra == "dev"
+Requires-Dist: pre-commit>=3.7; extra == "dev"
+Requires-Dist: pytest>=8; extra == "dev"
+Requires-Dist: pytest-cov>=5; extra == "dev"
+Requires-Dist: ruff>=0.6; extra == "dev"
+Dynamic: license-file
+
+# Colloquial
+
+Rewrite machine text into colloquial, native-sounding language, in any tongue.
+
+Colloquial takes text written by an LLM and produces text that reads like a
+person wrote it. It works in the same language (`--same-lang`) or translates and
+humanizes in one pass (`--to <lang>`). A deterministic detection core (no
+network, no LLM) scores how machine a text sounds, a report ranks the worst
+sections first, and an optional self-check loop re-evaluates the output.
+
+The name says it. Colloquial. How people actually talk and write.
+
+## Why this exists
+
+Machine-written prose has a signature, and it is not just word choice. Research
+on 61,608 stories (StoryScope, COLM 2026) shows that narrative features alone
+separate human from machine text at 93.2% macro-F1, and that these structural
+patterns survive paraphrasing. Surface detectors break when the wording
+changes. The structure does not.
+
+Colloquial is built on that finding. It reads how a text is built and rewrites
+it the way a person would have built it. The result is not text with words
+swapped. It is text with a different skeleton.
+
+## What it does
+
+| Command | What you get |
+|---|---|
+| `colloquial detect FILE` | A machine-likeness score from 0 to 100, ranked findings, and the worst sections first |
+| `colloquial humanize FILE` | A rewrite that reads human, in the same language, offline and deterministic |
+| `colloquial humanize FILE --mode llm` | The same rewrite driven by your own model, with a style profile built from the research |
+| `colloquial humanize FILE --to ar` | Translate and humanize in one pass, without translationese |
+| `colloquial humanize FILE --self-check` | Re-detect the output and iterate when it still reads machine-made |
+| `colloquial mcp` | The engine as an MCP server, for Claude Code, Codex, Cursor and Hermes |
+
+## How it works
+
+Five layers, cheapest first. Each one feeds the next, and every layer is
+grounded in published measurements.
+
+1. **Surface rules.** Filler transitions, inflated significance, machine
+   punctuation, AI self-reference. Hundreds of rules across eight languages.
+   This layer is deliberately the weakest, because wordlists alone produce
+   false positives on legitimate human text.
+2. **Rhythm.** Burstiness (the coefficient of variation of sentence length),
+   type-token ratio, trigram repetition. Machine text keeps an even tempo.
+   People do not.
+3. **Lexical diversity.** Six dimensions from arXiv 2508.00086, including
+   dispersion (how close repeated words sit) and evenness (how uniformly
+   vocabulary spreads). The counter-intuitive finding of that paper is that
+   machine text is *more* lexically varied than human text and repeats words
+   at *longer* distances. Dispersion alone carries a SHAP weight of 0.279,
+   the strongest single discriminator measured.
+4. **Discourse.** A ten-dimension narrative profile ported from StoryScope
+   (revelation, events, perspective, plot, setting, style, situatedness,
+   temporal structure, agents, social networks). It measures how the text is
+   constructed, not what words it uses, and it produces a soft per-model
+   fingerprint (Claude-like flat escalation, GPT-like gossip as plot
+   mechanism, Gemini-like external description) on texts above 300 words.
+5. **Persona.** AI-assisted writing makes the writer seem more confident, more
+   positive and more privileged than they are (arXiv 2604.22503). This layer
+   strips the tells and keeps the writer's actual voice.
+
+The mechanical rewriter reverses what the detector finds, offline. The LLM
+rewriter sends the text with a style profile built from the same research, so
+either way the rules behind the rewrite are the same rules behind the score.
+
+## The science behind it
+
+Colloquial is not a prompt pack with a CLI glued on. Every layer cites its
+source, and the sources are peer-reviewed.
+
+| Source | What it contributed |
+|---|---|
+| **StoryScope** (arXiv 2604.03136, COLM 2026) | The ten discourse dimensions, the per-model fingerprints, and the finding that structural features survive paraphrasing (93.2% macro-F1 on 61,608 stories) |
+| **Lexical diversity** (arXiv 2508.00086) | The six diversity dimensions and their AI/human directions; dispersion as the strongest discriminator |
+| **AI Argues Differently** (arXiv 2604.22503, EMNLP 2025) | The persona-distortion catalog: over-confidence, forced positivity, compressed emotional range |
+| **The Arabic AI Fingerprint** (arXiv 2505.23276, KFUPM) | Arabic stylometric tells: overused high-frequency words, lower vocabulary spread, domain-specific signatures |
+| **Falsely Accused** (arXiv 2511.16690) | The calibration lesson: detectors misjudge slightly-polished Arabic (92% to 12% accuracy on polished text), so the Arabic profile fails open instead of accusing |
+| **"Signs of AI writing"** (Wikipedia, WikiProject AI Cleanup) | The shared heritage behind the surface rule sets |
+
+Two design commitments follow from the research. First, detection is
+deterministic and offline, so a score is reproducible and a rewrite never
+depends on a network call. Second, the tool fails open. It prefers a missed
+detection to a false accusation, because the real cost of an AI detector is
+sending a human's honest text back to them marked as machine-made.
+
+## What makes it different
+
+An honest comparison with the tools that came before.
+
+- **Eight languages with real machinery.** English, Portuguese (Brazil),
+  Arabic (neutral MSA), Chinese, Japanese, Korean, Hindi and Ukrainian. Each
+  language ships its own surface rules, discourse lexicons, style profile and
+  rewrite transforms. The Arabic profile includes a dialect-consistency lock.
+  Egyptian, Levantine, Gulf, Maghrebi and Iraqi markers are rewritten to
+  neutral MSA, so a text never comes back as a dialectal mix. The Ukrainian
+  profile does the same for Russian calques, known as surzhyk.
+- **Discourse, not just vocabulary.** Most humanizers work at the word level.
+  Colloquial reads event escalation, dialogue balance, theme explicitness and
+  temporal texture, because that is where the research says the signal lives.
+- **Per-model fingerprints.** The report says which family the text resembles.
+  This is a soft signal, never a verdict.
+- **Two rewrite paths from one rulebook.** The offline path needs no key, no
+  account and no network. The LLM path uses whatever provider the user
+  configures, and both are judged by the same detector.
+- **Zero runtime dependencies.** Standard library only, by design. The quality
+  wall (ruff, mypy strict, bandit, pytest at 80% coverage minimum) runs on
+  every push in CI.
+
+## Install
+
+```bash
+pip install colloquial
+```
+
+Or run it without installing anything:
+
+```bash
+uvx colloquial detect README.md
+```
+
+## Quick start
+
+```bash
+colloquial detect README.md
+colloquial detect docs/ --report --format json
+colloquial humanize draft.md --lang pt-br --report
+colloquial humanize draft.md --mode llm --self-check
+colloquial humanize draft.md --to ar
+colloquial langs
+```
+
+## Using it from coding agents (MCP)
+
+Colloquial runs as an MCP server, so any MCP-capable agent (Claude Code,
+Codex, Cursor, Cline, Hermes) can call it as native tools.
+
+```bash
+colloquial mcp
+```
+
+Tools: `detect_text`, `humanize_text`, `translate_humanize`, `list_languages`,
+`get_report`. See [docs/plugins.md](docs/plugins.md) for per-agent setup, and
+`skills/` for ready-made skill files.
+
+## Choosing a provider (llm mode)
+
+The mechanical rewriter is offline and needs nothing. The `--mode llm`
+rewriter runs against any OpenAI-compatible API, and the provider is always
+your choice. Your key, your model, your machine.
+
+```bash
+colloquial providers          # see the catalog
+colloquial setup              # interactive: pick provider, key, model
+colloquial models             # live model list from your provider
+colloquial config             # show the resolved configuration
+```
+
+`colloquial setup` writes `~/.config/colloquial/config.toml` (mode 0600).
+It queries the provider's live `/models` endpoint with your key, so the
+model list is always current. Local providers (Ollama, vLLM, llama.cpp,
+LM Studio) need no key at all.
+
+The catalog covers OpenAI, Anthropic (Claude), Google Gemini, xAI (Grok),
+Mistral, DeepSeek, Groq, Cerebras, MiniMax, Moonshot (Kimi), Z.ai (GLM),
+Alibaba Qwen, Nous Research, OpenRouter, Together AI, Fireworks AI, and
+the local servers above, plus a `custom` entry for any other
+OpenAI-compatible endpoint.
+
+Environment variables still work and take precedence over the config file:
+`COLLOQUIAL_PROVIDER`, `COLLOQUIAL_API_KEY` (or `OPENAI_API_KEY`),
+`COLLOQUIAL_BASE_URL`, `COLLOQUIAL_MODEL`.
+
+## Supported languages
+
+English (en) · Arabic (ar, neutral MSA) · Chinese (zh) · Japanese (ja) ·
+Korean (ko) · Hindi (hi) · Ukrainian (uk) · Portuguese (pt-BR)
+
+The Arabic, Chinese, Japanese, Korean, Hindi and Ukrainian profiles ship as
+community-validated beta. Their rule sets were researched against public
+sources but deserve review from native speakers. Pull requests that sharpen a
+lexicon, add a tell, or fix a false positive are the most valuable
+contribution this project can receive.
+
+## Contributing
+
+See [CONTRIBUTING.md](CONTRIBUTING.md). The short version is that every change
+runs through the quality wall, and language profiles need a minimum test
+corpus.
+
+## License
+
+MIT

colloquial-0.1.0/README.md

@@ -0,0 +1,194 @@
+# Colloquial
+
+Rewrite machine text into colloquial, native-sounding language, in any tongue.
+
+Colloquial takes text written by an LLM and produces text that reads like a
+person wrote it. It works in the same language (`--same-lang`) or translates and
+humanizes in one pass (`--to <lang>`). A deterministic detection core (no
+network, no LLM) scores how machine a text sounds, a report ranks the worst
+sections first, and an optional self-check loop re-evaluates the output.
+
+The name says it. Colloquial. How people actually talk and write.
+
+## Why this exists
+
+Machine-written prose has a signature, and it is not just word choice. Research
+on 61,608 stories (StoryScope, COLM 2026) shows that narrative features alone
+separate human from machine text at 93.2% macro-F1, and that these structural
+patterns survive paraphrasing. Surface detectors break when the wording
+changes. The structure does not.
+
+Colloquial is built on that finding. It reads how a text is built and rewrites
+it the way a person would have built it. The result is not text with words
+swapped. It is text with a different skeleton.
+
+## What it does
+
+| Command | What you get |
+|---|---|
+| `colloquial detect FILE` | A machine-likeness score from 0 to 100, ranked findings, and the worst sections first |
+| `colloquial humanize FILE` | A rewrite that reads human, in the same language, offline and deterministic |
+| `colloquial humanize FILE --mode llm` | The same rewrite driven by your own model, with a style profile built from the research |
+| `colloquial humanize FILE --to ar` | Translate and humanize in one pass, without translationese |
+| `colloquial humanize FILE --self-check` | Re-detect the output and iterate when it still reads machine-made |
+| `colloquial mcp` | The engine as an MCP server, for Claude Code, Codex, Cursor and Hermes |
+
+## How it works
+
+Five layers, cheapest first. Each one feeds the next, and every layer is
+grounded in published measurements.
+
+1. **Surface rules.** Filler transitions, inflated significance, machine
+   punctuation, AI self-reference. Hundreds of rules across eight languages.
+   This layer is deliberately the weakest, because wordlists alone produce
+   false positives on legitimate human text.
+2. **Rhythm.** Burstiness (the coefficient of variation of sentence length),
+   type-token ratio, trigram repetition. Machine text keeps an even tempo.
+   People do not.
+3. **Lexical diversity.** Six dimensions from arXiv 2508.00086, including
+   dispersion (how close repeated words sit) and evenness (how uniformly
+   vocabulary spreads). The counter-intuitive finding of that paper is that
+   machine text is *more* lexically varied than human text and repeats words
+   at *longer* distances. Dispersion alone carries a SHAP weight of 0.279,
+   the strongest single discriminator measured.
+4. **Discourse.** A ten-dimension narrative profile ported from StoryScope
+   (revelation, events, perspective, plot, setting, style, situatedness,
+   temporal structure, agents, social networks). It measures how the text is
+   constructed, not what words it uses, and it produces a soft per-model
+   fingerprint (Claude-like flat escalation, GPT-like gossip as plot
+   mechanism, Gemini-like external description) on texts above 300 words.
+5. **Persona.** AI-assisted writing makes the writer seem more confident, more
+   positive and more privileged than they are (arXiv 2604.22503). This layer
+   strips the tells and keeps the writer's actual voice.
+
+The mechanical rewriter reverses what the detector finds, offline. The LLM
+rewriter sends the text with a style profile built from the same research, so
+either way the rules behind the rewrite are the same rules behind the score.
+
+## The science behind it
+
+Colloquial is not a prompt pack with a CLI glued on. Every layer cites its
+source, and the sources are peer-reviewed.
+
+| Source | What it contributed |
+|---|---|
+| **StoryScope** (arXiv 2604.03136, COLM 2026) | The ten discourse dimensions, the per-model fingerprints, and the finding that structural features survive paraphrasing (93.2% macro-F1 on 61,608 stories) |
+| **Lexical diversity** (arXiv 2508.00086) | The six diversity dimensions and their AI/human directions; dispersion as the strongest discriminator |
+| **AI Argues Differently** (arXiv 2604.22503, EMNLP 2025) | The persona-distortion catalog: over-confidence, forced positivity, compressed emotional range |
+| **The Arabic AI Fingerprint** (arXiv 2505.23276, KFUPM) | Arabic stylometric tells: overused high-frequency words, lower vocabulary spread, domain-specific signatures |
+| **Falsely Accused** (arXiv 2511.16690) | The calibration lesson: detectors misjudge slightly-polished Arabic (92% to 12% accuracy on polished text), so the Arabic profile fails open instead of accusing |
+| **"Signs of AI writing"** (Wikipedia, WikiProject AI Cleanup) | The shared heritage behind the surface rule sets |
+
+Two design commitments follow from the research. First, detection is
+deterministic and offline, so a score is reproducible and a rewrite never
+depends on a network call. Second, the tool fails open. It prefers a missed
+detection to a false accusation, because the real cost of an AI detector is
+sending a human's honest text back to them marked as machine-made.
+
+## What makes it different
+
+An honest comparison with the tools that came before.
+
+- **Eight languages with real machinery.** English, Portuguese (Brazil),
+  Arabic (neutral MSA), Chinese, Japanese, Korean, Hindi and Ukrainian. Each
+  language ships its own surface rules, discourse lexicons, style profile and
+  rewrite transforms. The Arabic profile includes a dialect-consistency lock.
+  Egyptian, Levantine, Gulf, Maghrebi and Iraqi markers are rewritten to
+  neutral MSA, so a text never comes back as a dialectal mix. The Ukrainian
+  profile does the same for Russian calques, known as surzhyk.
+- **Discourse, not just vocabulary.** Most humanizers work at the word level.
+  Colloquial reads event escalation, dialogue balance, theme explicitness and
+  temporal texture, because that is where the research says the signal lives.
+- **Per-model fingerprints.** The report says which family the text resembles.
+  This is a soft signal, never a verdict.
+- **Two rewrite paths from one rulebook.** The offline path needs no key, no
+  account and no network. The LLM path uses whatever provider the user
+  configures, and both are judged by the same detector.
+- **Zero runtime dependencies.** Standard library only, by design. The quality
+  wall (ruff, mypy strict, bandit, pytest at 80% coverage minimum) runs on
+  every push in CI.
+
+## Install
+
+```bash
+pip install colloquial
+```
+
+Or run it without installing anything:
+
+```bash
+uvx colloquial detect README.md
+```
+
+## Quick start
+
+```bash
+colloquial detect README.md
+colloquial detect docs/ --report --format json
+colloquial humanize draft.md --lang pt-br --report
+colloquial humanize draft.md --mode llm --self-check
+colloquial humanize draft.md --to ar
+colloquial langs
+```
+
+## Using it from coding agents (MCP)
+
+Colloquial runs as an MCP server, so any MCP-capable agent (Claude Code,
+Codex, Cursor, Cline, Hermes) can call it as native tools.
+
+```bash
+colloquial mcp
+```
+
+Tools: `detect_text`, `humanize_text`, `translate_humanize`, `list_languages`,
+`get_report`. See [docs/plugins.md](docs/plugins.md) for per-agent setup, and
+`skills/` for ready-made skill files.
+
+## Choosing a provider (llm mode)
+
+The mechanical rewriter is offline and needs nothing. The `--mode llm`
+rewriter runs against any OpenAI-compatible API, and the provider is always
+your choice. Your key, your model, your machine.
+
+```bash
+colloquial providers          # see the catalog
+colloquial setup              # interactive: pick provider, key, model
+colloquial models             # live model list from your provider
+colloquial config             # show the resolved configuration
+```
+
+`colloquial setup` writes `~/.config/colloquial/config.toml` (mode 0600).
+It queries the provider's live `/models` endpoint with your key, so the
+model list is always current. Local providers (Ollama, vLLM, llama.cpp,
+LM Studio) need no key at all.
+
+The catalog covers OpenAI, Anthropic (Claude), Google Gemini, xAI (Grok),
+Mistral, DeepSeek, Groq, Cerebras, MiniMax, Moonshot (Kimi), Z.ai (GLM),
+Alibaba Qwen, Nous Research, OpenRouter, Together AI, Fireworks AI, and
+the local servers above, plus a `custom` entry for any other
+OpenAI-compatible endpoint.
+
+Environment variables still work and take precedence over the config file:
+`COLLOQUIAL_PROVIDER`, `COLLOQUIAL_API_KEY` (or `OPENAI_API_KEY`),
+`COLLOQUIAL_BASE_URL`, `COLLOQUIAL_MODEL`.
+
+## Supported languages
+
+English (en) · Arabic (ar, neutral MSA) · Chinese (zh) · Japanese (ja) ·
+Korean (ko) · Hindi (hi) · Ukrainian (uk) · Portuguese (pt-BR)
+
+The Arabic, Chinese, Japanese, Korean, Hindi and Ukrainian profiles ship as
+community-validated beta. Their rule sets were researched against public
+sources but deserve review from native speakers. Pull requests that sharpen a
+lexicon, add a tell, or fix a false positive are the most valuable
+contribution this project can receive.
+
+## Contributing
+
+See [CONTRIBUTING.md](CONTRIBUTING.md). The short version is that every change
+runs through the quality wall, and language profiles need a minimum test
+corpus.
+
+## License
+
+MIT

colloquial-0.1.0/pyproject.toml

@@ -0,0 +1,114 @@
+[build-system]
+requires = ["setuptools>=68"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "colloquial"
+version = "0.1.0"
+description = "Rewrite machine text into colloquial, native-sounding language — humanize in the same language or translate-and-humanize, in any tongue."
+readme = "README.md"
+requires-python = ">=3.10"
+license = { file = "LICENSE" }
+authors = [{ name = "XScryer" }]
+keywords = ["nlp", "writing", "humanize", "translation", "llm", "slop"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Topic :: Text Processing :: Linguistic",
+]
+dependencies = []
+
+[project.urls]
+Homepage = "https://github.com/XScryer/colloquial"
+Repository = "https://github.com/XScryer/colloquial"
+Issues = "https://github.com/XScryer/colloquial/issues"
+Changelog = "https://github.com/XScryer/colloquial/blob/main/CHANGELOG.md"
+
+[project.optional-dependencies]
+dev = [
+    "bandit>=1.7",
+    "mypy>=1.10",
+    "pip-audit>=2.7",
+    "pre-commit>=3.7",
+    "pytest>=8",
+    "pytest-cov>=5",
+    "ruff>=0.6",
+]
+
+[project.scripts]
+colloquial = "colloquial.cli:main"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+colloquial = ["style/*.md"]
+
+[tool.ruff]
+line-length = 100
+target-version = "py310"
+src = ["src", "tests"]
+
+[tool.ruff.lint]
+select = [
+    "E",
+    "W",
+    "F",
+    "I",
+    "UP",
+    "B",
+    "SIM",
+    "C4",
+    "RUF",
+    "PERF",
+    "ASYNC",
+    "S",
+    "N",
+]
+ignore = [
+    "S101",
+    "N802",
+]
+
+[tool.ruff.lint.per-file-ignores]
+"tests/*" = ["S101"]
+
+[tool.ruff.lint.isort]
+known-first-party = ["colloquial"]
+
+[tool.ruff.format]
+quote-style = "double"
+indent-style = "space"
+
+[tool.mypy]
+python_version = "3.10"
+strict = true
+show_error_codes = true
+warn_unreachable = true
+exclude = ["tests/"]
+
+[tool.bandit]
+exclude_dirs = ["tests", ".venv"]
+skips = ["B101"]
+
+[tool.coverage.run]
+# Branch coverage too: an `if` whose false side nobody exercised is untested
+# logic, and line coverage alone would call it covered.
+branch = true
+source = ["colloquial"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+addopts = [
+    "--cov=colloquial",
+    "--cov-report=term-missing",
+    "--cov-fail-under=100",
+    "-ra",
+]
+filterwarnings = [
+    # Running a module as __main__ after it was imported is exactly what the
+    # entrypoint tests do; runpy's warning about it is expected and harmless.
+    "ignore::RuntimeWarning:runpy",
+]

colloquial-0.1.0/setup.cfg

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

colloquial-0.1.0/src/colloquial/__init__.py

@@ -0,0 +1,3 @@
+"""Colloquial — rewrite machine text into colloquial, native-sounding language."""
+
+__version__ = "0.1.0"

colloquial-0.1.0/src/colloquial/__main__.py

@@ -0,0 +1,4 @@
+from colloquial.cli import main
+
+if __name__ == "__main__":
+    raise SystemExit(main())