Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 5 additions & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@
[![PyPI](https://img.shields.io/pypi/v/dprovenancekit)](https://pypi.org/project/dprovenancekit/)
[![PyPI Downloads](https://static.pepy.tech/personalized-badge/dprovenancekit?period=total&units=INTERNATIONAL_SYSTEM&left_color=BLACK&right_color=GREEN&left_text=downloads)](https://pepy.tech/projects/dprovenancekit)
[![Listed in the official OpenAI Agents SDK docs](https://img.shields.io/badge/OpenAI%20Agents%20SDK-listed%20in%20the%20official%20docs-412991)](https://github.com/openai/openai-agents-python/blob/main/docs/tracing.md#external-tracing-processors-list)
[![Open in Spaces](https://huggingface.co/datasets/huggingface/badges/resolve/main/open-in-hf-spaces-sm.svg)](https://huggingface.co/spaces/dpk890/D.P.K)

**Your agent skipped its verification step. The final answer still looked right, so every eval and
snapshot test passed. DProvenanceKit — regression testing for AI agents — caught the skipped
Expand All @@ -20,6 +21,8 @@ has zero third-party dependencies.
(plan → search → rank → verify → decide), then catches a later run that drops verification and
loops its search tool. It flags the regression as HIGH severity, writes a local SQLite trace,
anomaly rules, and a shareable HTML report, then prints copy-paste commands for the gate and viewer.
Or skip the install entirely: the same gate, anomaly rules, diff, and HTML report run in a
[live browser demo on Hugging Face Spaces](https://huggingface.co/spaces/dpk890/D.P.K).

> Run → Record → Query → Diff → Detect regressions → Gate in CI

Expand All @@ -32,7 +35,8 @@ anomaly rules, and a shareable HTML report, then prints copy-paste commands for
**Guides:** [Regression testing for AI agents](https://dprovenance.dev/guides/regression-testing-for-ai-agents/) ·
[A CI gate for LLM agents](https://dprovenance.dev/guides/ci-gate-for-llm-agents/) ·
[DProvenanceKit vs LangSmith](https://dprovenance.dev/compare/dprovenancekit-vs-langsmith/) ·
[OpenAI Agents SDK integration](https://dprovenance.dev/openai-agents/)
[OpenAI Agents SDK integration](https://dprovenance.dev/openai-agents/) ·
[Live demo (Hugging Face Space)](https://huggingface.co/spaces/dpk890/D.P.K)

**It's not just the library** — it ships the surfaces that make reasoning regressions actionable:

Expand Down
2 changes: 1 addition & 1 deletion docs/crewai/index.html
Original file line number Diff line number Diff line change
Expand Up @@ -192,7 +192,7 @@ <h2>What gets recorded</h2>
<div class="wrap">
<p class="sec-kicker"><span class="no"># 04</span> · gate in ci</p>
<h2>Then gate it in CI</h2>
<p class="lede">Once runs are recorded, <strong>diff any run against a golden baseline and fail the PR when the reasoning drifts</strong>. The server-less <code>gate</code> CLI exits non-zero on regression, and the <a href="https://github.com/marketplace/actions/dprovenancekit-regression-gate">DProvenanceKit Regression Gate</a> GitHub Action drops it into any workflow — see <a href="https://dprovenance.dev/#ci">the full gate story on the main page</a>.</p>
<p class="lede">Once runs are recorded, <strong>diff any run against a golden baseline and fail the PR when the reasoning drifts</strong>. The server-less <code>gate</code> CLI exits non-zero on regression, and the <a href="https://github.com/marketplace/actions/dprovenancekit-regression-gate">DProvenanceKit Regression Gate</a> GitHub Action drops it into any workflow — see <a href="https://dprovenance.dev/#ci">the full gate story on the main page</a>. Or <a href="https://huggingface.co/spaces/dpk890/D.P.K">try the regression gate live in your browser</a> — an interactive demo of the gate, anomaly rules, diff, and HTML report.</p>
</div>
</section>
</main>
Expand Down
3 changes: 2 additions & 1 deletion docs/index.html
Original file line number Diff line number Diff line change
Expand Up @@ -234,7 +234,7 @@ <h1>Your agent skipped a step.<br>The answer still looked right.<br><span class=
<p class="proof"><span class="ok" aria-hidden="true">✓</span> Listed in the official <a href="https://github.com/openai/openai-agents-python/blob/main/docs/tracing.md#external-tracing-processors-list">OpenAI Agents SDK docs</a> as an external tracing processor · <a href="https://dprovenance.dev/openai-agents/">integration guide</a></p>
<p class="ctas">
<a class="btn primary" href="https://github.com/Therealdk8890/DProvenanceKitPython">View on GitHub →</a>
<span class="cta-links"><a href="https://pypi.org/project/dprovenancekit/">PyPI</a> · <a href="https://github.com/marketplace/actions/dprovenancekit-regression-gate">GitHub Action</a></span>
<span class="cta-links"><a href="https://pypi.org/project/dprovenancekit/">PyPI</a> · <a href="https://github.com/marketplace/actions/dprovenancekit-regression-gate">GitHub Action</a> · <a href="https://huggingface.co/spaces/dpk890/D.P.K">Try it in your browser (HF Space)</a></span>
</p>

<div class="term" role="img" aria-label="Illustrative CI terminal (not a real run): the dprovenancekit gate command fails the build because the candidate run is missing its Verify Claims step and repeated its search step; the job exits with code 1.">
Expand Down Expand Up @@ -474,6 +474,7 @@ <h2>The hosted dashboard: see the drift, not just fail on it.</h2>
<a href="https://github.com/Therealdk8890/DProvenanceKitPython">GitHub</a>
<a href="https://pypi.org/project/dprovenancekit/">PyPI</a>
<a href="https://github.com/marketplace/actions/dprovenancekit-regression-gate">GitHub Action</a>
<a href="https://huggingface.co/spaces/dpk890/D.P.K">Browser demo (HF)</a>
<a href="https://github.com/Therealdk8890/DProvenanceKit">Swift original</a>
<a href="https://dprovenance.dev/guides/regression-testing-for-ai-agents/">Regression-testing guide</a>
<a href="https://dprovenance.dev/guides/ci-gate-for-llm-agents/">CI-gate guide</a>
Expand Down
2 changes: 1 addition & 1 deletion docs/langchain/index.html
Original file line number Diff line number Diff line change
Expand Up @@ -190,7 +190,7 @@ <h2>What gets recorded</h2>
<div class="wrap">
<p class="sec-kicker"><span class="no"># 04</span> · gate in ci</p>
<h2>Then gate it in CI</h2>
<p class="lede">Once runs are recorded, <strong>diff any run against a golden baseline and fail the PR when the reasoning drifts</strong>. The server-less <code>gate</code> CLI exits non-zero on regression, and the <a href="https://github.com/marketplace/actions/dprovenancekit-regression-gate">DProvenanceKit Regression Gate</a> GitHub Action drops it into any workflow — see <a href="https://dprovenance.dev/#ci">the full gate story on the main page</a>.</p>
<p class="lede">Once runs are recorded, <strong>diff any run against a golden baseline and fail the PR when the reasoning drifts</strong>. The server-less <code>gate</code> CLI exits non-zero on regression, and the <a href="https://github.com/marketplace/actions/dprovenancekit-regression-gate">DProvenanceKit Regression Gate</a> GitHub Action drops it into any workflow — see <a href="https://dprovenance.dev/#ci">the full gate story on the main page</a>. Or <a href="https://huggingface.co/spaces/dpk890/D.P.K">try the regression gate live in your browser</a> — an interactive demo of the gate, anomaly rules, diff, and HTML report.</p>
</div>
</section>
</main>
Expand Down
2 changes: 1 addition & 1 deletion docs/llama-index/index.html
Original file line number Diff line number Diff line change
Expand Up @@ -195,7 +195,7 @@ <h2>What gets recorded</h2>
<div class="wrap">
<p class="sec-kicker"><span class="no"># 04</span> · gate in ci</p>
<h2>Then gate it in CI</h2>
<p class="lede">Once runs are recorded, <strong>diff any run against a golden baseline and fail the PR when the reasoning drifts</strong>. The server-less <code>gate</code> CLI exits non-zero on regression, and the <a href="https://github.com/marketplace/actions/dprovenancekit-regression-gate">DProvenanceKit Regression Gate</a> GitHub Action drops it into any workflow — see <a href="https://dprovenance.dev/#ci">the full gate story on the main page</a>.</p>
<p class="lede">Once runs are recorded, <strong>diff any run against a golden baseline and fail the PR when the reasoning drifts</strong>. The server-less <code>gate</code> CLI exits non-zero on regression, and the <a href="https://github.com/marketplace/actions/dprovenancekit-regression-gate">DProvenanceKit Regression Gate</a> GitHub Action drops it into any workflow — see <a href="https://dprovenance.dev/#ci">the full gate story on the main page</a>. Or <a href="https://huggingface.co/spaces/dpk890/D.P.K">try the regression gate live in your browser</a> — an interactive demo of the gate, anomaly rules, diff, and HTML report.</p>
</div>
</section>
</main>
Expand Down
2 changes: 1 addition & 1 deletion docs/openai-agents/index.html
Original file line number Diff line number Diff line change
Expand Up @@ -192,7 +192,7 @@ <h2>What gets recorded</h2>
<div class="wrap">
<p class="sec-kicker"><span class="no"># 04</span> · gate in ci</p>
<h2>Then gate it in CI</h2>
<p class="lede">Once runs are recorded, <strong>diff any run against a golden baseline and fail the PR when the reasoning drifts</strong>. The server-less <code>gate</code> CLI exits non-zero on regression, and the <a href="https://github.com/marketplace/actions/dprovenancekit-regression-gate">DProvenanceKit Regression Gate</a> GitHub Action drops it into any workflow — see <a href="https://dprovenance.dev/#ci">the full gate story on the main page</a>.</p>
<p class="lede">Once runs are recorded, <strong>diff any run against a golden baseline and fail the PR when the reasoning drifts</strong>. The server-less <code>gate</code> CLI exits non-zero on regression, and the <a href="https://github.com/marketplace/actions/dprovenancekit-regression-gate">DProvenanceKit Regression Gate</a> GitHub Action drops it into any workflow — see <a href="https://dprovenance.dev/#ci">the full gate story on the main page</a>. Or <a href="https://huggingface.co/spaces/dpk890/D.P.K">try the regression gate live in your browser</a> — an interactive demo of the gate, anomaly rules, diff, and HTML report.</p>
</div>
</section>
</main>
Expand Down
1 change: 1 addition & 0 deletions pyproject.toml
Original file line number Diff line number Diff line change
Expand Up @@ -59,6 +59,7 @@ dprovenancekit = "dprovenancekit.pytest_plugin"
Homepage = "https://github.com/Therealdk8890/DProvenanceKitPython"
Repository = "https://github.com/Therealdk8890/DProvenanceKitPython"
Issues = "https://github.com/Therealdk8890/DProvenanceKitPython/issues"
Demo = "https://huggingface.co/spaces/dpk890/D.P.K"
"Swift original" = "https://github.com/Therealdk8890/DProvenanceKit"

[tool.setuptools.package-data]
Expand Down
Loading