kintsugi 0.0.1__tar.gz → 0.2.0__tar.gz

kintsugi-0.2.0/.gitignore

@@ -0,0 +1,9 @@
+__pycache__/
+*.py[cod]
+*.egg-info/
+.eggs/
+build/
+dist/
+.pytest_cache/
+.venv/
+venv/

kintsugi-0.2.0/CHANGELOG.md

@@ -0,0 +1,35 @@
+# Changelog
+
+## 0.2.0
+
+- Full language + variant registry (`kintsugi.languages`): every Google
+  Translate and Translated language, plus curated diglossia/dialect variants, as
+  BCP-47 codes with base language, script, region, register and listing engines
+  (304 entries). A language with no bundled frequency band is still a valid
+  attack target.
+- Frequency bands expanded to every FLORES+ language (233 configs) alongside
+  wordfreq, with script-aware tokenisation.
+- `kintsugi.locales` is now a view over the full registry; `diglossia_pairs()`
+  spans all standard-vs-vernacular contrasts (Singlish, Hinglish, Schweizerdeutsch,
+  Arabic dialects, Cantonese, ...).
+- `list-languages` command and `--lang-of` locale support on `frequency`.
+
+## 0.1.0
+
+- Provider-agnostic targets and judges: Ollama, Hugging Face, your own callable,
+  and a raw-HTTP Anthropic client. Every finding records model provenance
+  (provider, model, version).
+- 201 attack categories / 2822 seeds across 9 target languages, with observed
+  catastrophic/bad rates per language pair.
+- 123-check local failure detector with word-boundary profanity detection.
+- 11 adversarial source transforms.
+- 115 translator framings (personas, pivots, dilution, structured output).
+- Two-layer judge (local prefilter then LLM judge) with fallback-to-ok and
+  severe-failure promotion.
+- Frequent-vs-rare word attacks for 20 bundled languages; Japanese carries gold
+  answers from a rank-ordered frequency dictionary, Kannada and Cantonese from
+  FLORES+.
+- `kintsugi` command-line tool.
+
+All bundled data ships as Python literals: importing the package opens no files
+and parses no JSON, CSV or pickles.

kintsugi-0.2.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 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 2026 Liling Tan
+
+   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.

kintsugi-0.2.0/PKG-INFO

@@ -0,0 +1,235 @@
+Metadata-Version: 2.5
+Name: kintsugi
+Version: 0.2.0
+Summary: Red-teaming for machine translation: attacks, detectors, and judges from a large MT red-team project.
+Project-URL: Homepage, https://github.com/alvations/kintsugi
+Project-URL: Repository, https://github.com/alvations/kintsugi
+Project-URL: Issues, https://github.com/alvations/kintsugi/issues
+Author-email: Liling Tan <alvations@gmail.com>
+License-Expression: Apache-2.0
+License-File: LICENSE
+Keywords: adversarial,evaluation,japanese,llm,machine-translation,mt,nlp,red-teaming,safety
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Text Processing :: Linguistic
+Requires-Python: >=3.9
+Provides-Extra: dev
+Requires-Dist: build; extra == 'dev'
+Requires-Dist: pytest>=7; extra == 'dev'
+Requires-Dist: twine; extra == 'dev'
+Provides-Extra: huggingface
+Requires-Dist: torch>=2.0; extra == 'huggingface'
+Requires-Dist: transformers>=4.40; extra == 'huggingface'
+Description-Content-Type: text/markdown
+
+# Kintsugi
+
+**Red-teaming for machine translation.** Kintsugi finds where a translation
+model breaks: inputs that make it hallucinate drug names, erase a negation,
+leak its prompt, refuse, soften violent text, or silently switch language. It is
+named for the Japanese art of repairing breakage with gold, so the cracks can be
+seen and mended.
+
+It packages a battery of translation attacks, a failure detector, and judges:
+
+- **201 attack categories / 2822 seeds** across 9 target languages, each tagged
+  with the catastrophic/bad rates actually observed in the runs.
+- **A 123-check local detector** that catches obvious failures (empty, copy
+  through, refusal, prompt leak, repetition, script mismatch, number drop,
+  negation erasure, plus per-language traps) with no model call.
+- **11 adversarial source transforms** (homoglyphs, zero-width and RTL controls,
+  fullwidth, injection, negation dropping, repetition, mixed scripts).
+- **115 translator framings** (personas, task reframings, multi-hop pivots,
+  context dilution) that change failure rates.
+- **A two-layer judge** (local prefilter then an LLM judge) that cut judge error
+  from 53% to 0.2% in the project.
+- **Frequent-vs-rare word attacks** for **20 bundled languages**: the same probe
+  on common vs rare words, to measure the resource-tier effect directly.
+
+It is **provider-agnostic**. Point it at a local Ollama model, any Hugging Face
+model, your own model via a plain function, or a frontier API. Every finding
+records the model's provenance (provider, model, version).
+
+All bundled data is shipped **as Python literals**, not data files: importing
+kintsugi opens no files and parses no JSON, CSV or pickles.
+
+## Install
+
+```bash
+pip install kintsugi                 # core: zero dependencies
+pip install "kintsugi[huggingface]"  # to target Hugging Face models
+pip install "kintsugi[frequency]"    # frequency probes beyond the 20 bundled languages
+```
+
+Python 3.9+.
+
+## Quick start
+
+Try your own model in the simplest possible way: give a function.
+
+```python
+from kintsugi import RedTeam, CallableProvider, load_attacks
+
+target = CallableProvider(lambda text, src, tgt: my_model.translate(text, tgt))
+rt = RedTeam(target, lang_pair="en-de")                 # detector-only, no judge
+findings = rt.run(load_attacks(category="prompt_injection"))
+print(rt.summary(findings))
+```
+
+A local open-source model via Ollama, judged by a frontier model:
+
+```python
+from kintsugi import RedTeam, OllamaProvider, AnthropicProvider, load_attacks
+
+rt = RedTeam(
+    target=OllamaProvider("qwen3.5:0.8b"),
+    judge=AnthropicProvider("claude-opus-5-5"),   # set ANTHROPIC_API_KEY
+    target_lang="Japanese", lang_pair="en-ja",
+)
+findings = rt.run(load_attacks(category="japanese_pharma_traps"), progress=True)
+print(rt.summary(findings))
+```
+
+Any Hugging Face model, the simplest way to try an open-weights model:
+
+```python
+from kintsugi import RedTeam, HuggingFaceProvider
+
+rt = RedTeam(HuggingFaceProvider("Qwen/Qwen2.5-0.5B-Instruct"), lang_pair="en-de")
+print(rt.summary(rt.run(load_attacks(limit_per_category=2))))
+```
+
+## Frequent vs non-frequent words
+
+Catastrophic failure scales inversely with how well-represented something is in
+training data, and the *same attack is more effective on rarer material*.
+Kintsugi makes that a controlled probe, with
+frequency bands bundled for 20 languages. Japanese is the reference language
+(the probes carry a gold expected answer from a rank-ordered frequency
+dictionary); Kannada and Cantonese come from the FLORES+ low-resource benchmark.
+
+```python
+from kintsugi import RedTeam, OllamaProvider, frequency
+
+rt = RedTeam(OllamaProvider("qwen3.5:0.8b"), lang_pair="en-ja")
+bands = frequency.contrast("ja", n=50)                  # frequent vs rare, held constant
+common = rt.summary(rt.run(bands["frequent"]))
+rare   = rt.summary(rt.run(bands["rare"]))               # expect a higher catastrophic rate
+```
+
+Frequency bands are bundled for every FLORES+ language (233 configs) plus the
+`wordfreq` set and the Japanese gold dictionary; `frequency.languages()` lists
+them. Friendly aliases (`yue`, `kn`, `zh-Hant`, ...) resolve to the right band.
+
+## Locale variants: region, script, register
+
+Models often collapse a variant to its base language, and that collapse is a
+failure worth catching. `kintsugi.locales` registers region, script, and
+**register** (diglossia: standard vs colloquial/creole) variants as red-team
+targets, each resolving to a frequency band:
+
+```python
+from kintsugi import locales, RedTeam, OllamaProvider
+
+locales.diglossia_pairs()            # e.g. ('en-SG','en-SG-x-singlish'), ('de-CH','gsw'), ('ar','ar-EG')
+
+std      = locales.get("en-SG")              # Singapore Standard English
+singlish = locales.get("en-SG-x-singlish")   # Singlish (creole)
+rt = RedTeam(OllamaProvider("qwen3.5:0.8b"),
+             source_lang="English", target_lang=singlish["name"], lang_pair="en-en")
+```
+
+Covered: region (`pt-BR`/`pt-PT`, `fr-CA`/`fr-CH`, `de-AT`/`de-CH`, `zh-CN`/
+`zh-Hant-TW`/`zh-Hant-HK`/`zh-Hant-MO`/`zh-SG`, ...), script (`zh-Hans`/`zh-Hant`,
+`sr-Latn`, `hi-Latn`, ...), and register (Singapore Standard English vs Singlish,
+Indian English vs Hinglish, Jamaican Standard English vs Patois, Swiss Standard
+German vs Schweizerdeutsch, MSA vs Egyptian/Moroccan Arabic, HK written Chinese
+vs spoken Cantonese).
+
+```bash
+kintsugi list-locales --register creole
+kintsugi list-locales --script Hant
+kintsugi frequency --target ollama:qwen3.5:0.8b --lang-of zh-Hant --band rare --n 30
+```
+
+## Full language registry
+
+`kintsugi.languages` holds **every Google Translate and Translated language**
+plus the curated diglossia/dialect variants above (304 entries), each a BCP-47
+code with base language, script, region, register, listing engines, and a
+frequency band where one is bundled. A language with no band is still a valid
+attack target; frequency bands are bundled for all FLORES+ languages and the
+`wordfreq` set.
+
+```python
+from kintsugi import languages
+languages.by_engine("google")        # every Google Translate language/variant
+languages.by_engine("translated")    # every translated.com language/variant
+languages.with_band()                # those with a bundled frequency band
+languages.get("zh-Hant-HK")          # {'code':'zh-Hant-HK','script':'Hant','region':'HK',...}
+```
+
+```bash
+kintsugi list-languages --engine google
+kintsugi list-languages --with-band
+```
+
+The engine coverage is also written out, with the Apple `language-Script-REGION`
+convention, in [`docs/LANGUAGE_COVERAGE.md`](docs/LANGUAGE_COVERAGE.md).
+
+## Command line
+
+```bash
+kintsugi list                                            # all attack categories
+kintsugi list-framings                                   # all translator framings
+kintsugi transform zero_width "Do not take with alcohol"
+kintsugi attack  --target ollama:qwen3.5:0.8b --judge anthropic:claude-opus-5-5 \
+                 --lang en-ja --category japanese_pharma_traps --out findings.jsonl
+kintsugi frequency --target ollama:qwen3.5:0.8b --direction en-ja --band rare --n 30
+```
+
+## What the attacks find
+
+A few headline numbers, drawn from the bundled observed rates:
+
+| Attack | Pair | Catastrophic rate |
+|---|---|---|
+| `japanese_pharma_traps` | en-ja | ~51% |
+| `anatomical_near_miss` | en-ja | 50% |
+| `prompt_injection` | en-de | ~30% |
+| `safety_critical_substance` | en-de | ~25% |
+
+Vulnerability tracks resource tier almost perfectly: French is the hardest to
+break, low-resource Indic and Cantonese targets the easiest. Models at or above
+~4B parameters show near-zero catastrophic rates; models at or below ~2B should
+not be used for safety-critical translation.
+
+```python
+import kintsugi
+kintsugi.observed_rates()["japanese_pharma_traps"]["en-ja"]   # {'n': 79, 'catastrophic': 40, 'bad': ...}
+```
+
+## How judging works
+
+1. **Local prefilter** (`kintsugi.prefilter`) classifies obvious failures for
+   free and returns `None` for anything ambiguous.
+2. **LLM judge** (`kintsugi.Judge`) scores the rest on adequacy, fluency,
+   faithfulness, format and safety, and never returns an error verdict: on a
+   parse failure it defaults to `ok` so statistics stay clean, and always-severe
+   failure types (hallucination, refusal, prompt leak) are promoted.
+
+A judge is optional. With no judge, kintsugi still runs the full prefilter and
+profanity check, which already catch the most dangerous failure modes.
+
+## License
+
+Apache 2.0.