pyveil 0.2.0__tar.gz → 0.2.2__tar.gz

{pyveil-0.2.0 → pyveil-0.2.2}/AGENTS.md

@@ -16,8 +16,9 @@ Do not turn pyveil into a general DLP suite, gateway, Presidio clone, or prompt-
 - Run typecheck: `uv run --extra dev mypy pyveil tests`
 - Build package: `uv run --with build python -m build`
 - Check package: `uv run --with twine python -m twine check dist/*`
-- Run CLI demo: `python3 -m pyveil.cli demo`
-- Run CLI locally: `PYVEIL_SECRET=dev-secret python3 -m pyveil.cli redact <file>`
+- Run CLI demo: `python3 -m pyveil demo`
+- Run CLI locally: `PYVEIL_SECRET=dev-secret python3 -m pyveil redact <file>`
+- Run detector evaluation: `python3 evaluation/evaluate.py --check`
 
 ## Architecture
 
@@ -68,6 +69,8 @@ This repository includes files meant for coding agents and LLM readers:
 - [docs/detector-provenance.md](docs/detector-provenance.md)
 - [docs/roadmap.md](docs/roadmap.md)
 - [docs/release-checklist.md](docs/release-checklist.md)
+- [docs/evaluation.html](docs/evaluation.html)
+- [docs/guides/](docs/guides/)
 - [docs/integrations/mcp.md](docs/integrations/mcp.md)
 - [docs/integrations/logging.md](docs/integrations/logging.md)
 - [docs/integrations/tracing.md](docs/integrations/tracing.md)
@@ -84,6 +87,7 @@ Examples:
 - [examples/openai_agents_guardrail.py](examples/openai_agents_guardrail.py)
 - [examples/fastapi_middleware.py](examples/fastapi_middleware.py)
 - [examples/litellm_proxy_filter.py](examples/litellm_proxy_filter.py)
+- [examples/azure_openai.py](examples/azure_openai.py)
 
 ## Development
 

{pyveil-0.2.0 → pyveil-0.2.2}/CHANGELOG.md

@@ -1,5 +1,56 @@
 # Changelog
 
+## 0.2.2 - 2026-07-15
+
+Azure OpenAI adoption release.
+
+### Added
+
+- Runnable Azure OpenAI v1 Responses API integration with environment, `.env`,
+  and non-secret YAML configuration.
+- Dry-run output that proves the raw prompt is redacted before the provider
+  SDK call, plus tested `.env` and YAML templates.
+
+### Changed
+
+- Added an optional `azure-openai` dependency group while keeping the core
+  package dependency-free.
+- Expanded the README, Cookbook, web Manual, Pages entry point, and agent-facing
+  navigation with a complete Azure OpenAI request path and observed output.
+
+### Fixed
+
+- Kept the Azure OpenAI Manual anchor visible below the fixed navigation bar on
+  desktop and mobile layouts.
+
+## 0.2.1 - 2026-07-11
+
+Evidence and organic-discovery release.
+
+### Added
+
+- Search-intent guides for Python LLM PII redaction, MCP redaction, and choosing
+  between pyveil, Presidio/NER, guardrail suites, and enterprise DLP.
+- A public 39-case synthetic built-in detector regression corpus, standard-library
+  evaluator, rendered methodology page, and CI gate.
+- `python -m pyveil` as an alternative CLI entry point.
+- Compact E.164 phone-number detection.
+- `Token` and `ApiKey` authorization-header scheme detection in free text.
+- A Pages-served `llms.txt`, site favicon, richer social metadata, and expanded
+  sitemap.
+- GitHub Discussions as a support and integration Q&A channel.
+
+### Changed
+
+- Expanded PyPI classifiers, keywords, and project links for guides, evaluation,
+  and funding.
+- FastAPI example moves redaction work to the default executor for large async
+  request payloads.
+- Clarified that generated `pyveil.yaml` is a reference/validation schema and is
+  not automatically loaded by 0.2.x CLI commands.
+- Documented detector evidence and limitations without claiming general-world
+  PII recall or compliance.
+
 ## 0.2.0 - 2026-07-10
 
 Discovery and production-adoption release.

{pyveil-0.2.0 → pyveil-0.2.2}/CONTRIBUTING.md

@@ -2,6 +2,13 @@
 
 Thanks for helping improve pyveil.
 
+## Questions And Integration Help
+
+Use [GitHub Discussions](https://github.com/hyeonsangjeon/pyveil/discussions)
+for setup questions, architecture tradeoffs, and integration help. Use Issues
+for reproducible bugs and focused feature requests. Report vulnerabilities
+privately through the security policy.
+
 ## Scope
 
 pyveil is agent-native redaction middleware. Good contributions usually improve

{pyveil-0.2.0 → pyveil-0.2.2}/MANIFEST.in

@@ -9,14 +9,17 @@ include llms.txt
 include pyveil.yaml
 
 # Include examples
-recursive-include examples *.py
+recursive-include examples *.py *.yaml *.example
+
+# Include reproducible evaluation
+recursive-include evaluation *.py *.json *.md
 
 # Include tests
 recursive-include tests *.py
 
 # Include docs
 recursive-include docs *.md
-recursive-include docs *.html *.xml *.txt
+recursive-include docs *.html *.xml *.txt *.css *.svg
 recursive-include docs/media *.gif *.png
 
 # Exclude unnecessary files

{pyveil-0.2.0/pyveil.egg-info → pyveil-0.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: pyveil
-Version: 0.2.0
+Version: 0.2.2
 Summary: Local PII and secret redaction for Python LLM apps, AI agents, tool calls, and MCP
 Author-email: Hyeon Sang Jeon <wingnut0310@gmail.com>
 Maintainer-email: Hyeon Sang Jeon <wingnut0310@gmail.com>
@@ -11,7 +11,11 @@ Project-URL: Repository, https://github.com/hyeonsangjeon/pyveil
 Project-URL: Issues, https://github.com/hyeonsangjeon/pyveil/issues
 Project-URL: Changelog, https://github.com/hyeonsangjeon/pyveil/releases
 Project-URL: Security, https://github.com/hyeonsangjeon/pyveil/security/policy
-Keywords: agent-native,agent-security,agents,ai-agents,ai-security,anthropic,data-protection,guardrails,llm,llm-security,logs,masking,mcp,memory,observability,pii,pii-redaction,privacy,prompts,redaction,openai,anonymization,security,sensitive-data,tool-calls,traces
+Project-URL: Guides, https://hyeonsangjeon.github.io/pyveil/guides/
+Project-URL: Evaluation, https://hyeonsangjeon.github.io/pyveil/evaluation.html
+Project-URL: Funding, https://github.com/sponsors/hyeonsangjeon
+Project-URL: Support, https://github.com/hyeonsangjeon/pyveil/discussions
+Keywords: agent-native,agent-security,agents,ai-agents,ai-security,anthropic,data-protection,data-masking,de-identification,guardrails,llm,llm-privacy,llm-security,logs,masking,mcp,mcp-security,memory,observability,pii,pii-redaction,privacy,prompts,prompt-redaction,redaction,runtime-redaction,openai,anonymization,security,sensitive-data,tool-calls,traces
 Classifier: Development Status :: 3 - Alpha
 Classifier: Intended Audience :: Developers
 Classifier: Operating System :: OS Independent
@@ -24,12 +28,17 @@ Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Classifier: Programming Language :: Python :: 3.14
 Classifier: Topic :: Security
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Topic :: Text Processing
 Classifier: Typing :: Typed
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Provides-Extra: azure-openai
+Requires-Dist: openai>=1.66.0; extra == "azure-openai"
+Requires-Dist: python-dotenv>=1.0.0; extra == "azure-openai"
+Requires-Dist: PyYAML>=6.0.0; extra == "azure-openai"
 Provides-Extra: dev
 Requires-Dist: build>=1.2.0; extra == "dev"
 Requires-Dist: pytest>=7.0.0; extra == "dev"
@@ -38,9 +47,15 @@ Requires-Dist: black>=23.0.0; extra == "dev"
 Requires-Dist: ruff>=0.1.0; extra == "dev"
 Requires-Dist: twine>=5.0.0; extra == "dev"
 Requires-Dist: mypy>=1.0.0; extra == "dev"
+Requires-Dist: openai>=1.66.0; extra == "dev"
+Requires-Dist: python-dotenv>=1.0.0; extra == "dev"
+Requires-Dist: PyYAML>=6.0.0; extra == "dev"
+Requires-Dist: types-PyYAML>=6.0.0; extra == "dev"
 Provides-Extra: test
 Requires-Dist: pytest>=7.0.0; extra == "test"
 Requires-Dist: pytest-cov>=4.0.0; extra == "test"
+Requires-Dist: python-dotenv>=1.0.0; extra == "test"
+Requires-Dist: PyYAML>=6.0.0; extra == "test"
 
 # pyveil: PII and secret redaction for Python AI agents
 
@@ -54,14 +69,18 @@ Requires-Dist: pytest-cov>=4.0.0; extra == "test"
   <a href="https://www.python.org/"><img alt="Python 3.8 to 3.14" src="https://img.shields.io/badge/python-3.8%20to%203.14-3776AB?style=flat-square"></a>
   <img alt="Zero core dependencies" src="https://img.shields.io/badge/core%20dependencies-zero-111827?style=flat-square">
   <img alt="Typed package" src="https://img.shields.io/badge/typed-py.typed-7C3AED?style=flat-square">
+  <a href="https://hyeonsangjeon.github.io/pyveil/evaluation.html"><img alt="Synthetic evaluation: 39 cases passing" src="https://img.shields.io/badge/synthetic%20evaluation-39%20cases%20passing-4ade80?style=flat-square"></a>
   <a href="LICENSE"><img alt="MIT license" src="https://img.shields.io/badge/license-MIT-green?style=flat-square"></a>
 </p>
 
 <p align="center">
   <a href="https://hyeonsangjeon.github.io/pyveil/manual.html">Documentation</a> &middot;
+  <a href="https://hyeonsangjeon.github.io/pyveil/guides/">Guides</a> &middot;
+  <a href="https://hyeonsangjeon.github.io/pyveil/evaluation.html">Evaluation</a> &middot;
   <a href="https://pypi.org/project/pyveil/">PyPI</a> &middot;
   <a href="https://github.com/hyeonsangjeon/pyveil/blob/main/docs/cookbook.md">Cookbook</a> &middot;
   <a href="https://github.com/hyeonsangjeon/pyveil/blob/main/docs/redaction-reference.md">Detection reference</a> &middot;
+  <a href="https://github.com/hyeonsangjeon/pyveil/discussions">Support</a> &middot;
   <a href="https://github.com/hyeonsangjeon/pyveil/security">Security</a>
 </p>
 
@@ -82,6 +101,7 @@ No network calls. No reversible vault. No raw values in findings by default.
 ```bash
 pip install pyveil
 pyveil demo
+# or: python -m pyveil demo
 ```
 
 Or run the synthetic demo in an isolated environment:
@@ -120,6 +140,63 @@ response = call_llm(safe.data)  # Your provider SDK call
 The provider receives the same list and dictionary shape, with sensitive values
 replaced before serialization or transmission.
 
+## Azure OpenAI: End To End
+
+Install the optional Azure example dependencies, then load configuration from
+environment variables, `.env`, or YAML:
+
+```bash
+pip install "pyveil[azure-openai]"
+```
+
+```python
+from pyveil.integrations.azure_openai import ask_azure_openai, load_settings
+
+settings = load_settings()  # AZURE_OPENAI_* + PYVEIL_* environment variables
+result = ask_azure_openai(
+    "Write a follow-up for alice@example.com or 010-1234-5678.",
+    settings,
+)
+
+print(result.redacted_input)  # The exact text sent to Azure OpenAI
+print(result.output_text)     # The model response
+```
+
+The integration uses Azure OpenAI's v1 endpoint and Responses API. The
+deployment name is passed as `model`; pyveil redacts the prompt before
+`client.responses.create(...)` runs.
+
+Prove the boundary without an Azure request:
+
+```bash
+PYVEIL_SECRET=docs-demo-secret \
+  python -m pyveil.integrations.azure_openai --dry-run
+```
+
+```text
+mode: dry-run
+deployment: not configured
+sent-to-azure: Write a one-sentence support follow-up for [EMAIL:347ab11285a3] or [PHONE:548017338f6f].
+findings: EMAIL=1, PHONE=1
+azure-response: skipped (--dry-run)
+```
+
+For a live call, either export `AZURE_OPENAI_ENDPOINT`,
+`AZURE_OPENAI_DEPLOYMENT`, `AZURE_OPENAI_API_KEY`, `PYVEIL_SECRET`, and
+optionally `PYVEIL_SCOPE`, or use the checked-in
+[`.env` template](https://github.com/hyeonsangjeon/pyveil/blob/main/examples/azure_openai.env.example)
+and [YAML template](https://github.com/hyeonsangjeon/pyveil/blob/main/examples/azure_openai.example.yaml):
+
+```bash
+python -m pyveil.integrations.azure_openai --env-file .env
+python -m pyveil.integrations.azure_openai \
+  --config examples/azure_openai.example.yaml --env-file .env
+```
+
+Process environment variables override `.env`, which overrides non-secret YAML
+settings. API keys and the pyveil HMAC secret are rejected if placed directly
+in YAML; YAML names the environment variables that contain them.
+
 <p align="center">
   <img src="https://raw.githubusercontent.com/hyeonsangjeon/pyveil/main/docs/media/pyveil-awesome-demo.gif"
        alt="pyveil redacts synthetic PII and secrets before an AI agent boundary"
@@ -138,6 +215,25 @@ replaced before serialization or transmission.
 | Stop credentials in tool calls | Auth headers, private keys, API keys, JWTs, and tokens block by default |
 | Cover app-specific data | Exact known-value and trusted custom-regex rules |
 | Audit without leaking | Findings contain type, rule, path, placeholder, and fingerprint, not raw values |
+| Verify supported behavior | Public 39-case synthetic regression corpus, evaluator, and CI gate |
+
+## Reproducible Evidence
+
+The repository ships a public synthetic detector corpus and a standard-library
+evaluator:
+
+```bash
+python evaluation/evaluate.py --check
+```
+
+For corpus v1, pyveil 0.2.2 matches all 36 expected findings across 39 cases
+(33 positive, 6 negative), with no corpus false positives, false negatives,
+labeled-value leaks, or non-empty `Finding.raw` values.
+
+These numbers describe documented supported shapes only. They are **not** a
+real-world PII recall benchmark and do not cover unknown names, addresses,
+languages, documents, or images. Read the
+[methodology and limits](https://hyeonsangjeon.github.io/pyveil/evaluation.html).
 
 ## Known Names And Domain IDs
 
@@ -198,7 +294,7 @@ Core detection is intentionally conservative and high precision:
 | Type | Examples | HIGH output |
 | --- | --- | --- |
 | `EMAIL` | Email addresses | `[EMAIL:12hex]` |
-| `PHONE` | Korean and international-ish phone numbers | `[PHONE:12hex]` |
+| `PHONE` | Korean, separated international, and compact E.164 phone shapes | `[PHONE:12hex]` |
 | `CREDIT_CARD` | Card numbers that pass Luhn validation | `[CREDIT_CARD:12hex]` |
 | `JWT` | Compact JSON Web Tokens | `[JWT:12hex]` |
 | `AUTH_HEADER` | Bearer and Basic authorization headers | `[AUTH_HEADER:12hex]` |
@@ -272,7 +368,7 @@ is parsed and traversed structurally.
 | --- | --- |
 | Any LLM provider | [Provider-neutral client wrapper](https://github.com/hyeonsangjeon/pyveil/blob/main/examples/llm_client_boundary.py) |
 | OpenAI Agents SDK | [Input guardrail example](https://github.com/hyeonsangjeon/pyveil/blob/main/examples/openai_agents_guardrail.py) |
-| Azure OpenAI | Use the provider-neutral wrapper; only `call_llm` changes |
+| Azure OpenAI | [Runnable env/YAML integration](https://github.com/hyeonsangjeon/pyveil/blob/main/pyveil/integrations/azure_openai.py) and [short example](https://github.com/hyeonsangjeon/pyveil/blob/main/examples/azure_openai.py) |
 | LiteLLM | [Proxy filter example](https://github.com/hyeonsangjeon/pyveil/blob/main/examples/litellm_proxy_filter.py) |
 | FastAPI | [Request middleware example](https://github.com/hyeonsangjeon/pyveil/blob/main/examples/fastapi_middleware.py) |
 | MCP | [Server wrapper](https://github.com/hyeonsangjeon/pyveil/blob/main/examples/mcp_server_wrapper.py) and [integration guide](https://hyeonsangjeon.github.io/pyveil/manual.html#integrations) |
@@ -293,6 +389,7 @@ Choose an enterprise DLP product when you need managed policy, document/image
 coverage, incident workflows, or compliance reporting.
 
 These tools can be layered. `pyveil` does not claim perfect recall.
+See the full [pyveil vs Presidio, NER, guardrails, and DLP decision guide](https://hyeonsangjeon.github.io/pyveil/guides/pyveil-vs-presidio.html).
 
 ## Safety Contract
 
@@ -313,10 +410,14 @@ before production use.
 ## Guides
 
 - [Complete manual](https://hyeonsangjeon.github.io/pyveil/manual.html)
+- [Python LLM PII redaction guide](https://hyeonsangjeon.github.io/pyveil/guides/python-llm-pii-redaction.html)
+- [MCP PII redaction guide](https://hyeonsangjeon.github.io/pyveil/guides/mcp-pii-redaction.html)
+- [pyveil vs Presidio / NER / DLP](https://hyeonsangjeon.github.io/pyveil/guides/pyveil-vs-presidio.html)
+- [Reproducible detector evaluation](https://hyeonsangjeon.github.io/pyveil/evaluation.html)
 - [English video guide](https://github.com/hyeonsangjeon/pyveil/releases/download/v0.1.2/pyveil-usage-guide-en.mp4)
 - [Korean video guide](https://github.com/hyeonsangjeon/pyveil/releases/download/v0.1.2/pyveil-usage-guide-ko.mp4)
 - [AGENTS.md](https://github.com/hyeonsangjeon/pyveil/blob/main/AGENTS.md) for coding agents
-- [llms.txt](https://github.com/hyeonsangjeon/pyveil/blob/main/llms.txt) for LLM-readable navigation
+- [llms.txt](https://hyeonsangjeon.github.io/pyveil/llms.txt) for LLM-readable navigation
 - [Contributing](https://github.com/hyeonsangjeon/pyveil/blob/main/CONTRIBUTING.md)
 
 ## Development
@@ -325,6 +426,7 @@ before production use.
 uv run --extra dev ruff check .
 uv run --extra dev mypy pyveil tests
 uv run --extra test pytest
+uv run --extra test python evaluation/evaluate.py --check
 ```
 
 CI runs the test suite on Python `3.8` through `3.14`. The core remains typed,

pyveil-0.2.0/PKG-INFO → pyveil-0.2.2/README.md

@@ -1,47 +1,3 @@
-Metadata-Version: 2.2
-Name: pyveil
-Version: 0.2.0
-Summary: Local PII and secret redaction for Python LLM apps, AI agents, tool calls, and MCP
-Author-email: Hyeon Sang Jeon <wingnut0310@gmail.com>
-Maintainer-email: Hyeon Sang Jeon <wingnut0310@gmail.com>
-License: MIT
-Project-URL: Homepage, https://hyeonsangjeon.github.io/pyveil/
-Project-URL: Documentation, https://hyeonsangjeon.github.io/pyveil/manual.html
-Project-URL: Repository, https://github.com/hyeonsangjeon/pyveil
-Project-URL: Issues, https://github.com/hyeonsangjeon/pyveil/issues
-Project-URL: Changelog, https://github.com/hyeonsangjeon/pyveil/releases
-Project-URL: Security, https://github.com/hyeonsangjeon/pyveil/security/policy
-Keywords: agent-native,agent-security,agents,ai-agents,ai-security,anthropic,data-protection,guardrails,llm,llm-security,logs,masking,mcp,memory,observability,pii,pii-redaction,privacy,prompts,redaction,openai,anonymization,security,sensitive-data,tool-calls,traces
-Classifier: Development Status :: 3 - Alpha
-Classifier: Intended Audience :: Developers
-Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.8
-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: Programming Language :: Python :: 3.14
-Classifier: Topic :: Security
-Classifier: Topic :: Software Development :: Libraries :: Python Modules
-Classifier: Topic :: Text Processing
-Classifier: Typing :: Typed
-Requires-Python: >=3.8
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Provides-Extra: dev
-Requires-Dist: build>=1.2.0; extra == "dev"
-Requires-Dist: pytest>=7.0.0; extra == "dev"
-Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
-Requires-Dist: black>=23.0.0; extra == "dev"
-Requires-Dist: ruff>=0.1.0; extra == "dev"
-Requires-Dist: twine>=5.0.0; extra == "dev"
-Requires-Dist: mypy>=1.0.0; extra == "dev"
-Provides-Extra: test
-Requires-Dist: pytest>=7.0.0; extra == "test"
-Requires-Dist: pytest-cov>=4.0.0; extra == "test"
-
 # pyveil: PII and secret redaction for Python AI agents
 
 <p align="center">
@@ -54,14 +10,18 @@ Requires-Dist: pytest-cov>=4.0.0; extra == "test"
   <a href="https://www.python.org/"><img alt="Python 3.8 to 3.14" src="https://img.shields.io/badge/python-3.8%20to%203.14-3776AB?style=flat-square"></a>
   <img alt="Zero core dependencies" src="https://img.shields.io/badge/core%20dependencies-zero-111827?style=flat-square">
   <img alt="Typed package" src="https://img.shields.io/badge/typed-py.typed-7C3AED?style=flat-square">
+  <a href="https://hyeonsangjeon.github.io/pyveil/evaluation.html"><img alt="Synthetic evaluation: 39 cases passing" src="https://img.shields.io/badge/synthetic%20evaluation-39%20cases%20passing-4ade80?style=flat-square"></a>
   <a href="LICENSE"><img alt="MIT license" src="https://img.shields.io/badge/license-MIT-green?style=flat-square"></a>
 </p>
 
 <p align="center">
   <a href="https://hyeonsangjeon.github.io/pyveil/manual.html">Documentation</a> &middot;
+  <a href="https://hyeonsangjeon.github.io/pyveil/guides/">Guides</a> &middot;
+  <a href="https://hyeonsangjeon.github.io/pyveil/evaluation.html">Evaluation</a> &middot;
   <a href="https://pypi.org/project/pyveil/">PyPI</a> &middot;
   <a href="https://github.com/hyeonsangjeon/pyveil/blob/main/docs/cookbook.md">Cookbook</a> &middot;
   <a href="https://github.com/hyeonsangjeon/pyveil/blob/main/docs/redaction-reference.md">Detection reference</a> &middot;
+  <a href="https://github.com/hyeonsangjeon/pyveil/discussions">Support</a> &middot;
   <a href="https://github.com/hyeonsangjeon/pyveil/security">Security</a>
 </p>
 
@@ -82,6 +42,7 @@ No network calls. No reversible vault. No raw values in findings by default.
 ```bash
 pip install pyveil
 pyveil demo
+# or: python -m pyveil demo
 ```
 
 Or run the synthetic demo in an isolated environment:
@@ -120,6 +81,63 @@ response = call_llm(safe.data)  # Your provider SDK call
 The provider receives the same list and dictionary shape, with sensitive values
 replaced before serialization or transmission.
 
+## Azure OpenAI: End To End
+
+Install the optional Azure example dependencies, then load configuration from
+environment variables, `.env`, or YAML:
+
+```bash
+pip install "pyveil[azure-openai]"
+```
+
+```python
+from pyveil.integrations.azure_openai import ask_azure_openai, load_settings
+
+settings = load_settings()  # AZURE_OPENAI_* + PYVEIL_* environment variables
+result = ask_azure_openai(
+    "Write a follow-up for alice@example.com or 010-1234-5678.",
+    settings,
+)
+
+print(result.redacted_input)  # The exact text sent to Azure OpenAI
+print(result.output_text)     # The model response
+```
+
+The integration uses Azure OpenAI's v1 endpoint and Responses API. The
+deployment name is passed as `model`; pyveil redacts the prompt before
+`client.responses.create(...)` runs.
+
+Prove the boundary without an Azure request:
+
+```bash
+PYVEIL_SECRET=docs-demo-secret \
+  python -m pyveil.integrations.azure_openai --dry-run
+```
+
+```text
+mode: dry-run
+deployment: not configured
+sent-to-azure: Write a one-sentence support follow-up for [EMAIL:347ab11285a3] or [PHONE:548017338f6f].
+findings: EMAIL=1, PHONE=1
+azure-response: skipped (--dry-run)
+```
+
+For a live call, either export `AZURE_OPENAI_ENDPOINT`,
+`AZURE_OPENAI_DEPLOYMENT`, `AZURE_OPENAI_API_KEY`, `PYVEIL_SECRET`, and
+optionally `PYVEIL_SCOPE`, or use the checked-in
+[`.env` template](https://github.com/hyeonsangjeon/pyveil/blob/main/examples/azure_openai.env.example)
+and [YAML template](https://github.com/hyeonsangjeon/pyveil/blob/main/examples/azure_openai.example.yaml):
+
+```bash
+python -m pyveil.integrations.azure_openai --env-file .env
+python -m pyveil.integrations.azure_openai \
+  --config examples/azure_openai.example.yaml --env-file .env
+```
+
+Process environment variables override `.env`, which overrides non-secret YAML
+settings. API keys and the pyveil HMAC secret are rejected if placed directly
+in YAML; YAML names the environment variables that contain them.
+
 <p align="center">
   <img src="https://raw.githubusercontent.com/hyeonsangjeon/pyveil/main/docs/media/pyveil-awesome-demo.gif"
        alt="pyveil redacts synthetic PII and secrets before an AI agent boundary"
@@ -138,6 +156,25 @@ replaced before serialization or transmission.
 | Stop credentials in tool calls | Auth headers, private keys, API keys, JWTs, and tokens block by default |
 | Cover app-specific data | Exact known-value and trusted custom-regex rules |
 | Audit without leaking | Findings contain type, rule, path, placeholder, and fingerprint, not raw values |
+| Verify supported behavior | Public 39-case synthetic regression corpus, evaluator, and CI gate |
+
+## Reproducible Evidence
+
+The repository ships a public synthetic detector corpus and a standard-library
+evaluator:
+
+```bash
+python evaluation/evaluate.py --check
+```
+
+For corpus v1, pyveil 0.2.2 matches all 36 expected findings across 39 cases
+(33 positive, 6 negative), with no corpus false positives, false negatives,
+labeled-value leaks, or non-empty `Finding.raw` values.
+
+These numbers describe documented supported shapes only. They are **not** a
+real-world PII recall benchmark and do not cover unknown names, addresses,
+languages, documents, or images. Read the
+[methodology and limits](https://hyeonsangjeon.github.io/pyveil/evaluation.html).
 
 ## Known Names And Domain IDs
 
@@ -198,7 +235,7 @@ Core detection is intentionally conservative and high precision:
 | Type | Examples | HIGH output |
 | --- | --- | --- |
 | `EMAIL` | Email addresses | `[EMAIL:12hex]` |
-| `PHONE` | Korean and international-ish phone numbers | `[PHONE:12hex]` |
+| `PHONE` | Korean, separated international, and compact E.164 phone shapes | `[PHONE:12hex]` |
 | `CREDIT_CARD` | Card numbers that pass Luhn validation | `[CREDIT_CARD:12hex]` |
 | `JWT` | Compact JSON Web Tokens | `[JWT:12hex]` |
 | `AUTH_HEADER` | Bearer and Basic authorization headers | `[AUTH_HEADER:12hex]` |
@@ -272,7 +309,7 @@ is parsed and traversed structurally.
 | --- | --- |
 | Any LLM provider | [Provider-neutral client wrapper](https://github.com/hyeonsangjeon/pyveil/blob/main/examples/llm_client_boundary.py) |
 | OpenAI Agents SDK | [Input guardrail example](https://github.com/hyeonsangjeon/pyveil/blob/main/examples/openai_agents_guardrail.py) |
-| Azure OpenAI | Use the provider-neutral wrapper; only `call_llm` changes |
+| Azure OpenAI | [Runnable env/YAML integration](https://github.com/hyeonsangjeon/pyveil/blob/main/pyveil/integrations/azure_openai.py) and [short example](https://github.com/hyeonsangjeon/pyveil/blob/main/examples/azure_openai.py) |
 | LiteLLM | [Proxy filter example](https://github.com/hyeonsangjeon/pyveil/blob/main/examples/litellm_proxy_filter.py) |
 | FastAPI | [Request middleware example](https://github.com/hyeonsangjeon/pyveil/blob/main/examples/fastapi_middleware.py) |
 | MCP | [Server wrapper](https://github.com/hyeonsangjeon/pyveil/blob/main/examples/mcp_server_wrapper.py) and [integration guide](https://hyeonsangjeon.github.io/pyveil/manual.html#integrations) |
@@ -293,6 +330,7 @@ Choose an enterprise DLP product when you need managed policy, document/image
 coverage, incident workflows, or compliance reporting.
 
 These tools can be layered. `pyveil` does not claim perfect recall.
+See the full [pyveil vs Presidio, NER, guardrails, and DLP decision guide](https://hyeonsangjeon.github.io/pyveil/guides/pyveil-vs-presidio.html).
 
 ## Safety Contract
 
@@ -313,10 +351,14 @@ before production use.
 ## Guides
 
 - [Complete manual](https://hyeonsangjeon.github.io/pyveil/manual.html)
+- [Python LLM PII redaction guide](https://hyeonsangjeon.github.io/pyveil/guides/python-llm-pii-redaction.html)
+- [MCP PII redaction guide](https://hyeonsangjeon.github.io/pyveil/guides/mcp-pii-redaction.html)
+- [pyveil vs Presidio / NER / DLP](https://hyeonsangjeon.github.io/pyveil/guides/pyveil-vs-presidio.html)
+- [Reproducible detector evaluation](https://hyeonsangjeon.github.io/pyveil/evaluation.html)
 - [English video guide](https://github.com/hyeonsangjeon/pyveil/releases/download/v0.1.2/pyveil-usage-guide-en.mp4)
 - [Korean video guide](https://github.com/hyeonsangjeon/pyveil/releases/download/v0.1.2/pyveil-usage-guide-ko.mp4)
 - [AGENTS.md](https://github.com/hyeonsangjeon/pyveil/blob/main/AGENTS.md) for coding agents
-- [llms.txt](https://github.com/hyeonsangjeon/pyveil/blob/main/llms.txt) for LLM-readable navigation
+- [llms.txt](https://hyeonsangjeon.github.io/pyveil/llms.txt) for LLM-readable navigation
 - [Contributing](https://github.com/hyeonsangjeon/pyveil/blob/main/CONTRIBUTING.md)
 
 ## Development
@@ -325,6 +367,7 @@ before production use.
 uv run --extra dev ruff check .
 uv run --extra dev mypy pyveil tests
 uv run --extra test pytest
+uv run --extra test python evaluation/evaluate.py --check
 ```
 
 CI runs the test suite on Python `3.8` through `3.14`. The core remains typed,

{pyveil-0.2.0 → pyveil-0.2.2}/docs/README.md

@@ -6,9 +6,13 @@ traces cross application boundaries.
 
 Start with:
 
+- [Rendered guide hub](https://hyeonsangjeon.github.io/pyveil/guides/)
+- [Reproducible evaluation](https://hyeonsangjeon.github.io/pyveil/evaluation.html)
+- [LLM-readable navigation](https://hyeonsangjeon.github.io/pyveil/llms.txt)
 - [Threat model](threat-model.md)
 - [FAQ](faq.md)
 - [Cookbook](cookbook.md)
+- [Azure OpenAI env/YAML integration](../pyveil/integrations/azure_openai.py)
 - [Redaction reference](redaction-reference.md)
 - [Known limitations](known-limitations.md)
 - [Detector provenance](detector-provenance.md)
@@ -30,4 +34,6 @@ Applications can add known sensitive values and narrow domain identifiers with
 the public `CustomRule` API while keeping semantic NER out of the dependency-free
 core.
 
-`index.html` is a static GitHub Pages landing page. Serve GitHub Pages from the repository `/docs` directory to publish it.
+`index.html`, `manual.html`, `evaluation.html`, and `guides/` are static GitHub
+Pages content. Serve GitHub Pages from the repository `/docs` directory to
+publish them.