trialmark 0.1.0__tar.gz

trialmark-0.1.0/.github/workflows/publish.yml

@@ -0,0 +1,33 @@
+name: publish
+on:
+  push:
+    tags: ["v*"]
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+      - run: pip install -e ".[dev]" build
+      - run: pytest -q
+      - name: Check the tag matches the package version
+        run: test "v$(python -c 'import trialmark; print(trialmark.__version__)')" = "${GITHUB_REF_NAME}"
+      - run: python -m build
+      - uses: actions/upload-artifact@v4
+        with:
+          name: dist
+          path: dist/
+  publish:
+    needs: build
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      id-token: write
+    steps:
+      - uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist/
+      - uses: pypa/gh-action-pypi-publish@release/v1

trialmark-0.1.0/.github/workflows/test.yml

@@ -0,0 +1,16 @@
+name: test
+on: [push, pull_request]
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python: ["3.10", "3.11", "3.12", "3.13"]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python }}
+      - run: pip install -e ".[dev]"
+      - run: pytest -q
+      - run: trialmark report examples/run-record.json --by-tag

trialmark-0.1.0/.gitignore

@@ -0,0 +1,7 @@
+__pycache__/
+*.pyc
+.venv/
+dist/
+build/
+*.egg-info/
+.pytest_cache/

trialmark-0.1.0/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 [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

trialmark-0.1.0/PKG-INFO

@@ -0,0 +1,152 @@
+Metadata-Version: 2.5
+Name: trialmark
+Version: 0.1.0
+Summary: Model acceptance tests for language models: your own test set, a pass mark set before the run, and a record anyone can rerun.
+Project-URL: Homepage, https://github.com/peshwar9/trialmark
+Project-URL: Issues, https://github.com/peshwar9/trialmark/issues
+Author: PE (peshwar9)
+License-Expression: Apache-2.0
+License-File: LICENSE
+Keywords: acceptance testing,benchmark,evaluation,llm,model selection
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Testing
+Requires-Python: >=3.10
+Provides-Extra: dev
+Requires-Dist: pytest>=8; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# Trialmark
+
+**Model acceptance tests for language models.** Test models on your own work, decide in advance
+what result is good enough, and keep a record that anyone can rerun and check.
+
+Choosing a language model is a trade between accuracy, cost and speed. Trialmark makes that
+choice systematic:
+
+1. **Your own test set.** Cases from your own work, each with a reference answer written by a
+   person and tagged by kind, such as "factual" or "multi-part". The set is hashed, so a later
+   run can prove it used exactly the same cases.
+2. **A pass mark set before the run.** For example: "choose the cheapest model within 3 points
+   of the best on correctness, as long as at least 95% of its answers are grounded". The rule
+   is stored with its hash and the time it was set, so it cannot be quietly changed after the
+   results are in.
+3. **Repeats, with the range shown.** Models do not give the same answer every time. Each model
+   runs several times, and the report shows the lowest and highest result so that a difference
+   inside the range is read as no difference.
+4. **A report by kind of case.** A small model may be as good as a large one on single facts
+   and worse on multi-part questions. The breakdown by tag shows where.
+5. **A run record and a release gate.** Every run writes one JSON file with the test set's hash,
+   the models and their settings, the judge, the pass mark and every result. `trialmark gate`
+   exits with 0 or 1, so a pipeline can refuse a model change that fails the pass mark.
+
+Trialmark runs on your own machines. Your test sets, reference answers and records stay with you.
+
+## Where it comes from
+
+Trialmark was spun out of the model benchmark in [Forge](https://www.forgeprivate.com), a
+governed layer through which organisations delegate work to AI. That benchmark compares models
+on a fixed set of business-document questions, through Forge's own answer path, with three
+repeats and accuracy, cost and speed side by side. Trialmark makes the same kind of test
+available to any developer or team, with or without Forge.
+
+## Status
+
+Trialmark is at an early stage. Version 0.1 provides the formats and the decision:
+
+| Built in 0.1 | Planned |
+|---|---|
+| The test set format, with hashing and tags | Runners that call models directly (Anthropic, OpenAI and others) |
+| The pass mark and the decision rule | A reference-answer judge, which grades an answer as correct, partly correct or incorrect and checks that it is grounded |
+| The run record, with the pass mark's hash | A field-by-field scorer for extraction and classification |
+| The report, with ranges and the breakdown by tag | A runner that tests a model inside Forge, with Forge's retrieval and rules applied |
+| `trialmark gate` for pipelines | Logging runs to MLflow |
+
+In 0.1 you produce the results yourself, with your own code, and Trialmark records, reports and
+decides on them.
+
+## Install
+
+```bash
+pip install trialmark
+```
+
+Python 3.10 or later. The core has no dependencies.
+
+## Try it
+
+The `examples` folder holds a five-question test set and an illustrative run of three made-up
+models. The scores in it are invented to show the format; they are not measurements of any real
+model.
+
+```bash
+trialmark validate examples/testset.json
+trialmark report examples/run-record.json --by-tag
+trialmark gate examples/run-record.json --model medium-model --test-set examples/testset.json
+```
+
+## Use it from Python
+
+```python
+from trialmark import ModelEntry, PassMark, Result, RunRecord, load_test_set, text_report
+
+test_set = load_test_set("my-testset.json")
+
+# Fix the decision before any model runs.
+pass_mark = PassMark(metric="correct", tolerance_points=3, floors={"grounded": 0.95}, choose="cheapest")
+record = RunRecord.start(
+    test_set,
+    pass_mark,
+    [ModelEntry(id="model-a", provider="provider-x"), ModelEntry(id="model-b", provider="provider-y")],
+    repeats=3,
+    judge={"model": "judge-model", "prompt_version": "1"},
+)
+
+for repeat in range(3):
+    for model in ("model-a", "model-b"):
+        for case in test_set.cases:
+            answer, cost, ms = call_your_model(model, case.input)   # your code
+            score = grade(answer, case.reference)                     # your code: 0, 0.5 or 1
+            record.add(Result(
+                model=model, repeat=repeat, case_id=case.id, tags=list(case.tags),
+                metrics={"correct": score, "grounded": 1.0},
+                output=answer, cost_usd=cost, latency_ms=ms,
+            ))
+
+record.save("run-record.json")
+print(text_report(record, by_tag=True))
+```
+
+## Formats
+
+**Test set**
+
+```json
+{
+  "name": "contract-questions",
+  "version": "2026-11-05",
+  "cases": [
+    { "id": "q1", "input": "What is the notice period?", "reference": "Sixty days' written notice.", "tags": ["factual"] }
+  ]
+}
+```
+
+The hash covers the cases (their ids, inputs, references and tags), not the name or version.
+
+**Pass mark**
+
+| Field | Meaning |
+|---|---|
+| `metric` | The score the decision rests on, such as `correct` |
+| `tolerance_points` | How many percentage points below the best model still passes |
+| `floors` | Minimum mean scores on other metrics, such as `{"grounded": 0.95}` |
+| `choose` | Which passing model to choose: `cheapest`, `fastest` or `best` |
+
+**Metrics** are whatever your scorer produces, each between 0 and 1. A model's score on a
+metric is the mean within each repeat; the report shows the mean of those and their range.
+
+## Licence
+
+Apache-2.0. See [LICENSE](LICENSE).

trialmark-0.1.0/README.md

@@ -0,0 +1,132 @@
+# Trialmark
+
+**Model acceptance tests for language models.** Test models on your own work, decide in advance
+what result is good enough, and keep a record that anyone can rerun and check.
+
+Choosing a language model is a trade between accuracy, cost and speed. Trialmark makes that
+choice systematic:
+
+1. **Your own test set.** Cases from your own work, each with a reference answer written by a
+   person and tagged by kind, such as "factual" or "multi-part". The set is hashed, so a later
+   run can prove it used exactly the same cases.
+2. **A pass mark set before the run.** For example: "choose the cheapest model within 3 points
+   of the best on correctness, as long as at least 95% of its answers are grounded". The rule
+   is stored with its hash and the time it was set, so it cannot be quietly changed after the
+   results are in.
+3. **Repeats, with the range shown.** Models do not give the same answer every time. Each model
+   runs several times, and the report shows the lowest and highest result so that a difference
+   inside the range is read as no difference.
+4. **A report by kind of case.** A small model may be as good as a large one on single facts
+   and worse on multi-part questions. The breakdown by tag shows where.
+5. **A run record and a release gate.** Every run writes one JSON file with the test set's hash,
+   the models and their settings, the judge, the pass mark and every result. `trialmark gate`
+   exits with 0 or 1, so a pipeline can refuse a model change that fails the pass mark.
+
+Trialmark runs on your own machines. Your test sets, reference answers and records stay with you.
+
+## Where it comes from
+
+Trialmark was spun out of the model benchmark in [Forge](https://www.forgeprivate.com), a
+governed layer through which organisations delegate work to AI. That benchmark compares models
+on a fixed set of business-document questions, through Forge's own answer path, with three
+repeats and accuracy, cost and speed side by side. Trialmark makes the same kind of test
+available to any developer or team, with or without Forge.
+
+## Status
+
+Trialmark is at an early stage. Version 0.1 provides the formats and the decision:
+
+| Built in 0.1 | Planned |
+|---|---|
+| The test set format, with hashing and tags | Runners that call models directly (Anthropic, OpenAI and others) |
+| The pass mark and the decision rule | A reference-answer judge, which grades an answer as correct, partly correct or incorrect and checks that it is grounded |
+| The run record, with the pass mark's hash | A field-by-field scorer for extraction and classification |
+| The report, with ranges and the breakdown by tag | A runner that tests a model inside Forge, with Forge's retrieval and rules applied |
+| `trialmark gate` for pipelines | Logging runs to MLflow |
+
+In 0.1 you produce the results yourself, with your own code, and Trialmark records, reports and
+decides on them.
+
+## Install
+
+```bash
+pip install trialmark
+```
+
+Python 3.10 or later. The core has no dependencies.
+
+## Try it
+
+The `examples` folder holds a five-question test set and an illustrative run of three made-up
+models. The scores in it are invented to show the format; they are not measurements of any real
+model.
+
+```bash
+trialmark validate examples/testset.json
+trialmark report examples/run-record.json --by-tag
+trialmark gate examples/run-record.json --model medium-model --test-set examples/testset.json
+```
+
+## Use it from Python
+
+```python
+from trialmark import ModelEntry, PassMark, Result, RunRecord, load_test_set, text_report
+
+test_set = load_test_set("my-testset.json")
+
+# Fix the decision before any model runs.
+pass_mark = PassMark(metric="correct", tolerance_points=3, floors={"grounded": 0.95}, choose="cheapest")
+record = RunRecord.start(
+    test_set,
+    pass_mark,
+    [ModelEntry(id="model-a", provider="provider-x"), ModelEntry(id="model-b", provider="provider-y")],
+    repeats=3,
+    judge={"model": "judge-model", "prompt_version": "1"},
+)
+
+for repeat in range(3):
+    for model in ("model-a", "model-b"):
+        for case in test_set.cases:
+            answer, cost, ms = call_your_model(model, case.input)   # your code
+            score = grade(answer, case.reference)                     # your code: 0, 0.5 or 1
+            record.add(Result(
+                model=model, repeat=repeat, case_id=case.id, tags=list(case.tags),
+                metrics={"correct": score, "grounded": 1.0},
+                output=answer, cost_usd=cost, latency_ms=ms,
+            ))
+
+record.save("run-record.json")
+print(text_report(record, by_tag=True))
+```
+
+## Formats
+
+**Test set**
+
+```json
+{
+  "name": "contract-questions",
+  "version": "2026-11-05",
+  "cases": [
+    { "id": "q1", "input": "What is the notice period?", "reference": "Sixty days' written notice.", "tags": ["factual"] }
+  ]
+}
+```
+
+The hash covers the cases (their ids, inputs, references and tags), not the name or version.
+
+**Pass mark**
+
+| Field | Meaning |
+|---|---|
+| `metric` | The score the decision rests on, such as `correct` |
+| `tolerance_points` | How many percentage points below the best model still passes |
+| `floors` | Minimum mean scores on other metrics, such as `{"grounded": 0.95}` |
+| `choose` | Which passing model to choose: `cheapest`, `fastest` or `best` |
+
+**Metrics** are whatever your scorer produces, each between 0 and 1. A model's score on a
+metric is the mean within each repeat; the report shows the mean of those and their range.
+
+## Licence
+
+Apache-2.0. See [LICENSE](LICENSE).

trialmark-0.1.0/examples/make_example_record.py

@@ -0,0 +1,45 @@
+"""Writes examples/run-record.json: an illustrative run of three made-up models on
+examples/testset.json. The scores are invented to show the format and the
+report; they are not measurements of any real model."""
+
+from pathlib import Path
+
+from trialmark import ModelEntry, PassMark, Result, RunRecord, load_test_set
+
+HERE = Path(__file__).parent
+
+# Per model: correct and grounded scores for q1..q5, cost per case, time per case.
+MODELS = {
+    "large-model": ([1, 1, 1, 1, 1], [1, 1, 1, 1, 1], 0.030, 9000),
+    "medium-model": ([1, 1, 1, 0.5, 1], [1, 1, 1, 1, 1], 0.012, 6000),
+    "small-model": ([0.5, 1, 1, 0.5, 0], [1, 1, 1, 1, 0], 0.003, 3000),
+}
+
+
+def main() -> None:
+    ts = load_test_set(HERE / "testset.json")
+    pass_mark = PassMark(metric="correct", tolerance_points=15, floors={"grounded": 0.95}, choose="cheapest")
+    record = RunRecord.start(
+        ts,
+        pass_mark,
+        [ModelEntry(id=m, provider="example") for m in MODELS],
+        repeats=3,
+        judge={"model": "example-judge", "prompt_version": "1"},
+    )
+    for repeat in range(3):
+        for model, (correct, grounded, cost, ms) in MODELS.items():
+            for case, c, g in zip(ts.cases, correct, grounded):
+                # The medium model misses q1 in one repeat, to show a range.
+                if model == "medium-model" and repeat == 2 and case.id == "q1":
+                    c = 0.5
+                record.add(Result(
+                    model=model, repeat=repeat, case_id=case.id, tags=list(case.tags),
+                    metrics={"correct": c, "grounded": g}, cost_usd=cost, latency_ms=ms + 100 * repeat,
+                ))
+    record.run_id = "example"
+    record.pass_mark_set_at = "2026-11-05T00:00:00+00:00"
+    record.save(HERE / "run-record.json")
+
+
+if __name__ == "__main__":
+    main()