ct-toolkit 0.3.39__tar.gz → 0.4.0__tar.gz

{ct_toolkit-0.3.39/ct_toolkit.egg-info → ct_toolkit-0.4.0}/PKG-INFO

@@ -1,34 +1,47 @@
 Metadata-Version: 2.4
 Name: ct-toolkit
-Version: 0.3.39
+Version: 0.4.0
 Summary: Computational Theseus Toolkit — Identity Continuity Guardrails for Agentic Systems
 Author: Hakan Damar
 License: Apache-2.0
+Project-URL: Homepage, https://theseus-guard.github.io/ct-toolkit/
+Project-URL: Documentation, https://theseus-guard.github.io/ct-toolkit/
+Project-URL: Repository, https://github.com/Theseus-Guard/ct-toolkit
+Project-URL: Issues, https://github.com/Theseus-Guard/ct-toolkit/issues
 Keywords: llm,ai-safety,identity-continuity,guardrails,alignment
 Requires-Python: <3.14,>=3.11
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: instructor>=1.3.0
 Requires-Dist: anyio>=4.14.2
 Requires-Dist: litellm>=1.104.0
 Requires-Dist: aiohttp>=3.14.3
-Requires-Dist: pillow>=11.3.0
 Requires-Dist: numpy>=1.26.0
 Requires-Dist: pyyaml>=6.0
 Requires-Dist: pydantic>=2.5.0
 Requires-Dist: cryptography>=48.0.1
 Requires-Dist: SQLAlchemy>=2.0.0
 Requires-Dist: httpx>=0.27.0
-Requires-Dist: rich>=13.0.0
 Requires-Dist: jinja2>=3.1.0
 Requires-Dist: pyasn1>=0.6.4
-Requires-Dist: typer[all]>=0.12.0
-Requires-Dist: fastapi>=0.110.0
-Requires-Dist: starlette>=1.3.1
-Requires-Dist: uvicorn>=0.29.0
-Requires-Dist: langsmith>=0.8.18
 Requires-Dist: urllib3>=2.8.0
 Requires-Dist: idna>=3.15
+Provides-Extra: server
+Requires-Dist: fastapi>=0.110.0; extra == "server"
+Requires-Dist: starlette>=1.3.1; extra == "server"
+Requires-Dist: uvicorn>=0.29.0; extra == "server"
+Provides-Extra: cli
+Requires-Dist: rich>=13.0.0; extra == "cli"
+Requires-Dist: typer[all]>=0.12.0; extra == "cli"
+Provides-Extra: observability
+Requires-Dist: opentelemetry-api>=1.25.0; extra == "observability"
+Requires-Dist: opentelemetry-sdk>=1.25.0; extra == "observability"
+Requires-Dist: langsmith>=0.8.18; extra == "observability"
+Provides-Extra: structured
+Requires-Dist: instructor>=1.3.0; extra == "structured"
+Provides-Extra: vision
+Requires-Dist: pillow>=11.3.0; extra == "vision"
+Provides-Extra: postgres
+Requires-Dist: psycopg[binary]>=3.1.0; extra == "postgres"
 Provides-Extra: ollama
 Requires-Dist: ollama>=0.2.0; extra == "ollama"
 Provides-Extra: langchain
@@ -40,6 +53,16 @@ Requires-Dist: mkdocs-material>=9.7.7; extra == "docs"
 Requires-Dist: pymdown-extensions>=10.21.3; extra == "docs"
 Provides-Extra: ml
 Requires-Dist: torch>=2.13.0; extra == "ml"
+Requires-Dist: fastembed>=0.3.0; extra == "ml"
+Provides-Extra: all
+Requires-Dist: fastapi>=0.110.0; extra == "all"
+Requires-Dist: starlette>=1.3.1; extra == "all"
+Requires-Dist: uvicorn>=0.29.0; extra == "all"
+Requires-Dist: rich>=13.0.0; extra == "all"
+Requires-Dist: typer[all]>=0.12.0; extra == "all"
+Requires-Dist: instructor>=1.3.0; extra == "all"
+Requires-Dist: pillow>=11.3.0; extra == "all"
+Requires-Dist: langsmith>=0.8.18; extra == "all"
 Provides-Extra: dev
 Requires-Dist: pytest>=8.0; extra == "dev"
 Requires-Dist: pytest-asyncio>=0.23; extra == "dev"
@@ -54,20 +77,61 @@ Dynamic: license-file
 [![Python 3.11+](https://img.shields.io/badge/python-3.11+-blue.svg)](https://www.python.org/)
 [![License: Apache 2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](LICENSE)
 [![PyPI version](https://img.shields.io/pypi/v/ct-toolkit.svg)](https://pypi.org/project/ct-toolkit/)
-[![Documentation](https://img.shields.io/badge/docs-GitHub%20Pages-blue.svg)](https://hakandamar.github.io/ct-toolkit/)
+[![Documentation](https://img.shields.io/badge/docs-GitHub%20Pages-blue.svg)](https://theseus-guard.github.io/ct-toolkit/)
 [![PyPI Downloads](https://static.pepy.tech/personalized-badge/ct-toolkit?period=total&units=INTERNATIONAL_SYSTEM&left_color=BLACK&right_color=MAGENTA&left_text=downloads)](https://pepy.tech/projects/ct-toolkit)
-[![codecov](https://codecov.io/gh/hakandamar/ct-toolkit/graph/badge.svg?token=2OTO27N02C)](https://codecov.io/gh/hakandamar/ct-toolkit)
+[![codecov](https://codecov.io/gh/Theseus-Guard/ct-toolkit/graph/badge.svg?token=2OTO27N02C)](https://codecov.io/gh/Theseus-Guard/ct-toolkit)
 
 CT Toolkit is an open-source security layer designed to preserve the **identity continuity** of AI agents over time. It implements the **Nested Agentic Architecture (NAA)** framework to prevent **Sequential Self-Compression (SSC)** in multi-agent hierarchies.
 
+```text
+$ ct-toolkit status
+
+  _______ _    _ ______  _____ ______ _    _  _____    _____ _    _          _____  _____  
+ |__   __| |  | |  ____|/ ____|  ____| |  | |/ ____|  / ____| |  | |   /\   |  __ \|  __ \ 
+    | |  | |__| | |__  | (___ | |__  | |  | | (___   | |  __| |  | |  /  \  | |__) | |  | |
+    | |  |  __  |  __|  \___ \|  __| | |  | |\___ \  | | |_ | |  | | / /\ \ |  _  /| |  | |
+    | |  | |  | | |____ ____) | |____| |__| |____) | | |__| | |__| |/ ____ \| | \ \| |__| |
+    |_|  |_|  |_|______|_____/|______|_____/|_____/   \_____|\____//_/    \_\_|  \_\_____/ 
+
+  Computational Theseus Toolkit (CT Toolkit) v0.4.0
+  Identity Continuity Guardrails for Agentic Systems
+
+╭──────────────────── CT Toolkit Audit & Telemetry Status ─────────────────────╮
+│ Vault: ./ct_provenance.db (local)                                            │
+│ Chain Integrity: VALID (HMAC Verified)                                       │
+│ Verified Active Entries: 4 (showing last 4)                                  │
+│ Divergence Score (Avg / Max): 0.1525 / 0.3800                                │
+│ Head Hash: 9c64cb51a479c52c207b7fa8c3197a75...                               │
+╰──────────────────────────────────────────────────────────────────────────────╯
+
+    Divergence Tier Breakdown (L1 / L2 / L3)    
+┏━━━━━━━━━━━━┳━━━━━━━┳━━━━━━━┓
+┃ Tier       ┃ Count ┃ Share ┃
+┡━━━━━━━━━━━━╇━━━━━━━╇━━━━━━━┩
+│ OK         │     1 │ 33.3% │
+│ L1_WARNING │     1 │ 33.3% │
+│ L2_JUDGE   │     1 │ 33.3% │
+│ L3_ICM     │     0 │  0.0% │
+└────────────┴───────┴───────┘
+
+                     Staged Kernel Rules (Sandbox Cooldown)                     
+┏━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━┓
+┃ Endorsement ID ┃ Commitment       ┃ Rule Text          ┃ Status              ┃
+┡━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━┩
+│ end-9f8a7b6c   │ fin_integrity_01 │ Require dual       │ ACTIVE COOLDOWN     │
+│                │                  │ sign-off for       │ (1799s left)        │
+│                │                  │ adjustments > $10k │                     │
+└────────────────┴──────────────────┴────────────────────┴─────────────────────┘
+```
+
 ---
 
 ## 📖 Official Documentation
 
 For full API reference, architecture details, examples, and integration guides, visit our documentation site:
-👉 [**https://hakandamar.github.io/ct-toolkit/**](https://hakandamar.github.io/ct-toolkit/)
+👉 [**https://theseus-guard.github.io/ct-toolkit/**](https://theseus-guard.github.io/ct-toolkit/)
 
-- [**Live Examples & Case Studies**](https://hakandamar.github.io/ct-toolkit/examples/): Real-world scenarios like Financial Auditor Integrity.
+- [**Live Examples & Case Studies**](https://theseus-guard.github.io/ct-toolkit/examples/): Real-world scenarios like Financial Auditor Integrity.
 - [**FastAPI Integration Test Project**](https://github.com/hakandamar/ct-toolkit-fastapi): Reference FastAPI app for validating CT Toolkit end-to-end across L1/L2/L3 guardrails and provenance logs with local model infrastructure.
 - [**Deep Agents Integration Test Project**](https://github.com/hakandamar/ct-toolkit-deep-agents): Reference Deep Agents app for validating CT Toolkit end-to-end with hierarchical agent workflows, L1/L2/L3 guardrails, and provenance logs.
 
@@ -77,21 +141,27 @@ For full API reference, architecture details, examples, and integration guides,
 
 In complex agentic workflows, LLMs tend to "drift" from their original instructions. CT Toolkit provides the mathematical and cryptographic guardrails to ensure your agents remain aligned with their core constitution, even across deep hierarchies.
 
+- **Async & Streaming Guardrails (`achat`)**: Native `async/await` and streaming (`stream=True`) support with non-blocking background execution for shadow requests and L3 ICM probes.
+- **Contrastive Semantic L1 Engine**: Provider-independent embeddings (`litellm`, `ollama`, local `fastembed`) with positive/negative anchor analysis and semantic rule conflict detection.
 - **Staged Approval (Cooldown)**: Verify risky kernel updates in a sandbox via shadow requests before production promotion.
 - **Passive Context Compression Detection**: Automatically detects silent provider-side history compression (e.g., OpenAI/Anthropic).
-- **Constitutional Kernels**: Axiomatic identity anchors.
-- **Standalone Auditor CLI**: Rapidly audit any LLM endpoint for identity drift without writing code.
+- **Constitutional Kernels & Distributed Propagation**: Axiomatic identity anchors with HMAC-SHA256 signed HTTP header propagation (`propagate_headers` / `from_headers`).
+- **Standalone Auditor & Status CLI**: Rapidly audit any LLM endpoint (`ct-toolkit audit`) and inspect provenance integrity & divergence tiers (`ct-toolkit status` / `dashboard`).
 - **Autonomous Self-Correction**: Active L2->L1 feedback loop that retries and corrects divergent responses before they reach the user.
-- **Divergence Engine**: Multi-tiered drift analysis (L1/L2/L3).
-- **Hierarchical Propagation**: Mother-to-child constraint inheritance.
-- **Provenance Log**: Immutable HMAC-signed interaction history.
+- **Enterprise Provenance & Observability**: Immutable HMAC-signed hash chain supporting SQLite and PostgreSQL/SQLAlchemy with paginated verification and OpenTelemetry (OTel) spans/metrics.
+
+![CT Toolkit Web Audit & Telemetry Dashboard](docs/ct_toolkit_web_dashboard.png)
 
 ---
 
 ## Quick Start
 
 ```bash
+# Core lightweight install
 pip install ct-toolkit
+
+# Or install with optional extras (cli, server, enterprise, embeddings, observability, all)
+pip install "ct-toolkit[all]"
 ```
 
 ```python
@@ -103,18 +173,24 @@ config = WrapperConfig(compression_passive_detection=True)
 # One-line injection for any LLM provider
 client = TheseusWrapper(provider="openai", config=config)
 
-# Guardrails and drift analysis applied automatically
+# Sync or async (`await client.achat(...)`) with automatic drift analysis
 response = client.chat("What are your core security axioms?")
 
 print(response.content)
 print(f"Divergence Score: {response.divergence_score}")
 ```
 
-### 🔍 Standalone Auditor (CLI)
+### 🔍 Standalone Auditor & Dashboard (CLI & Web UI)
 
-Audit any LLM endpoint (OpenAI, Ollama, LM Studio) directly from your terminal:
+Audit any LLM endpoint (OpenAI, Ollama, LM Studio) and inspect your provenance chain directly from your terminal or in the interactive Web Audit Dashboard:
 
 ```bash
+# View Provenance Chain integrity, L1/L2/L3 tier breakdown, and staged rules in terminal
+ct-toolkit status --vault ./ct_provenance.db
+
+# Launch the interactive Web Audit & Telemetry Dashboard at http://127.0.0.1:8001/dashboard
+ct-toolkit dashboard --web --vault ./ct_provenance.db --port 8001
+
 # Audit a local Ollama model
 ct-toolkit audit --url http://localhost:11434/v1 --kernel defense
 
@@ -142,10 +218,9 @@ The L2 judge does not evaluate Jinja2 expressions in user requests or model resp
 
 | Metric           | Status                                                                                                                                                                                                              |
 | :--------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| **Tests**        | ✅ 397 passed, 3 skipped (100% success rate, 90% coverage)                                                                                                                                                          |
+| **Tests**        | ✅ 426 passed, 3 skipped (100% success rate, 90%+ coverage)                                                                                                                                                         |
 | **Downloads**    | [![PyPI Downloads](https://static.pepy.tech/personalized-badge/ct-toolkit?period=total&units=INTERNATIONAL_SYSTEM&left_color=BLACK&right_color=MAGENTA&left_text=downloads)](https://pepy.tech/projects/ct-toolkit) |
-| **Last Phase**   | ✅ v0.3.39: urllib3 >=2.8.0 and LiteLLM >=1.104.0 fix Chunked Deflate infinite loop and authenticated SSRF / provider-credential exfiltration (Dependabot #69/#70)                                                     |
-| **Current Goal** | 🔶 Phase 7: Multi-Agent Synchronization (Integration)                                                                                                                                                               |
+| **Last Phase**   | ✅ v0.4.0: Async & Streaming (`achat`), Contrastive L1, Background L3 & Circuit Breaker, PostgreSQL/OTel, HMAC Header Propagation, and Web Audit Dashboard |
 
 ### Framework & Model Support
 

ct_toolkit-0.3.39/PKG-INFO → ct_toolkit-0.4.0/README.md

@@ -1,52 +1,3 @@
-Metadata-Version: 2.4
-Name: ct-toolkit
-Version: 0.3.39
-Summary: Computational Theseus Toolkit — Identity Continuity Guardrails for Agentic Systems
-Author: Hakan Damar
-License: Apache-2.0
-Keywords: llm,ai-safety,identity-continuity,guardrails,alignment
-Requires-Python: <3.14,>=3.11
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: instructor>=1.3.0
-Requires-Dist: anyio>=4.14.2
-Requires-Dist: litellm>=1.104.0
-Requires-Dist: aiohttp>=3.14.3
-Requires-Dist: pillow>=11.3.0
-Requires-Dist: numpy>=1.26.0
-Requires-Dist: pyyaml>=6.0
-Requires-Dist: pydantic>=2.5.0
-Requires-Dist: cryptography>=48.0.1
-Requires-Dist: SQLAlchemy>=2.0.0
-Requires-Dist: httpx>=0.27.0
-Requires-Dist: rich>=13.0.0
-Requires-Dist: jinja2>=3.1.0
-Requires-Dist: pyasn1>=0.6.4
-Requires-Dist: typer[all]>=0.12.0
-Requires-Dist: fastapi>=0.110.0
-Requires-Dist: starlette>=1.3.1
-Requires-Dist: uvicorn>=0.29.0
-Requires-Dist: langsmith>=0.8.18
-Requires-Dist: urllib3>=2.8.0
-Requires-Dist: idna>=3.15
-Provides-Extra: ollama
-Requires-Dist: ollama>=0.2.0; extra == "ollama"
-Provides-Extra: langchain
-Requires-Dist: langchain-core>=1.3.3; extra == "langchain"
-Provides-Extra: autogen
-Requires-Dist: pyautogen>=0.4.0; extra == "autogen"
-Provides-Extra: docs
-Requires-Dist: mkdocs-material>=9.7.7; extra == "docs"
-Requires-Dist: pymdown-extensions>=10.21.3; extra == "docs"
-Provides-Extra: ml
-Requires-Dist: torch>=2.13.0; extra == "ml"
-Provides-Extra: dev
-Requires-Dist: pytest>=8.0; extra == "dev"
-Requires-Dist: pytest-asyncio>=0.23; extra == "dev"
-Requires-Dist: ruff>=0.4; extra == "dev"
-Requires-Dist: mypy>=1.10; extra == "dev"
-Dynamic: license-file
-
 # Computational Theseus Toolkit (CT Toolkit)
 
 > **Identity Continuity Guardrails for Agentic Systems**
@@ -54,20 +5,61 @@ Dynamic: license-file
 [![Python 3.11+](https://img.shields.io/badge/python-3.11+-blue.svg)](https://www.python.org/)
 [![License: Apache 2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](LICENSE)
 [![PyPI version](https://img.shields.io/pypi/v/ct-toolkit.svg)](https://pypi.org/project/ct-toolkit/)
-[![Documentation](https://img.shields.io/badge/docs-GitHub%20Pages-blue.svg)](https://hakandamar.github.io/ct-toolkit/)
+[![Documentation](https://img.shields.io/badge/docs-GitHub%20Pages-blue.svg)](https://theseus-guard.github.io/ct-toolkit/)
 [![PyPI Downloads](https://static.pepy.tech/personalized-badge/ct-toolkit?period=total&units=INTERNATIONAL_SYSTEM&left_color=BLACK&right_color=MAGENTA&left_text=downloads)](https://pepy.tech/projects/ct-toolkit)
-[![codecov](https://codecov.io/gh/hakandamar/ct-toolkit/graph/badge.svg?token=2OTO27N02C)](https://codecov.io/gh/hakandamar/ct-toolkit)
+[![codecov](https://codecov.io/gh/Theseus-Guard/ct-toolkit/graph/badge.svg?token=2OTO27N02C)](https://codecov.io/gh/Theseus-Guard/ct-toolkit)
 
 CT Toolkit is an open-source security layer designed to preserve the **identity continuity** of AI agents over time. It implements the **Nested Agentic Architecture (NAA)** framework to prevent **Sequential Self-Compression (SSC)** in multi-agent hierarchies.
 
+```text
+$ ct-toolkit status
+
+  _______ _    _ ______  _____ ______ _    _  _____    _____ _    _          _____  _____  
+ |__   __| |  | |  ____|/ ____|  ____| |  | |/ ____|  / ____| |  | |   /\   |  __ \|  __ \ 
+    | |  | |__| | |__  | (___ | |__  | |  | | (___   | |  __| |  | |  /  \  | |__) | |  | |
+    | |  |  __  |  __|  \___ \|  __| | |  | |\___ \  | | |_ | |  | | / /\ \ |  _  /| |  | |
+    | |  | |  | | |____ ____) | |____| |__| |____) | | |__| | |__| |/ ____ \| | \ \| |__| |
+    |_|  |_|  |_|______|_____/|______|_____/|_____/   \_____|\____//_/    \_\_|  \_\_____/ 
+
+  Computational Theseus Toolkit (CT Toolkit) v0.4.0
+  Identity Continuity Guardrails for Agentic Systems
+
+╭──────────────────── CT Toolkit Audit & Telemetry Status ─────────────────────╮
+│ Vault: ./ct_provenance.db (local)                                            │
+│ Chain Integrity: VALID (HMAC Verified)                                       │
+│ Verified Active Entries: 4 (showing last 4)                                  │
+│ Divergence Score (Avg / Max): 0.1525 / 0.3800                                │
+│ Head Hash: 9c64cb51a479c52c207b7fa8c3197a75...                               │
+╰──────────────────────────────────────────────────────────────────────────────╯
+
+    Divergence Tier Breakdown (L1 / L2 / L3)    
+┏━━━━━━━━━━━━┳━━━━━━━┳━━━━━━━┓
+┃ Tier       ┃ Count ┃ Share ┃
+┡━━━━━━━━━━━━╇━━━━━━━╇━━━━━━━┩
+│ OK         │     1 │ 33.3% │
+│ L1_WARNING │     1 │ 33.3% │
+│ L2_JUDGE   │     1 │ 33.3% │
+│ L3_ICM     │     0 │  0.0% │
+└────────────┴───────┴───────┘
+
+                     Staged Kernel Rules (Sandbox Cooldown)                     
+┏━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━┓
+┃ Endorsement ID ┃ Commitment       ┃ Rule Text          ┃ Status              ┃
+┡━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━┩
+│ end-9f8a7b6c   │ fin_integrity_01 │ Require dual       │ ACTIVE COOLDOWN     │
+│                │                  │ sign-off for       │ (1799s left)        │
+│                │                  │ adjustments > $10k │                     │
+└────────────────┴──────────────────┴────────────────────┴─────────────────────┘
+```
+
 ---
 
 ## 📖 Official Documentation
 
 For full API reference, architecture details, examples, and integration guides, visit our documentation site:
-👉 [**https://hakandamar.github.io/ct-toolkit/**](https://hakandamar.github.io/ct-toolkit/)
+👉 [**https://theseus-guard.github.io/ct-toolkit/**](https://theseus-guard.github.io/ct-toolkit/)
 
-- [**Live Examples & Case Studies**](https://hakandamar.github.io/ct-toolkit/examples/): Real-world scenarios like Financial Auditor Integrity.
+- [**Live Examples & Case Studies**](https://theseus-guard.github.io/ct-toolkit/examples/): Real-world scenarios like Financial Auditor Integrity.
 - [**FastAPI Integration Test Project**](https://github.com/hakandamar/ct-toolkit-fastapi): Reference FastAPI app for validating CT Toolkit end-to-end across L1/L2/L3 guardrails and provenance logs with local model infrastructure.
 - [**Deep Agents Integration Test Project**](https://github.com/hakandamar/ct-toolkit-deep-agents): Reference Deep Agents app for validating CT Toolkit end-to-end with hierarchical agent workflows, L1/L2/L3 guardrails, and provenance logs.
 
@@ -77,21 +69,27 @@ For full API reference, architecture details, examples, and integration guides,
 
 In complex agentic workflows, LLMs tend to "drift" from their original instructions. CT Toolkit provides the mathematical and cryptographic guardrails to ensure your agents remain aligned with their core constitution, even across deep hierarchies.
 
+- **Async & Streaming Guardrails (`achat`)**: Native `async/await` and streaming (`stream=True`) support with non-blocking background execution for shadow requests and L3 ICM probes.
+- **Contrastive Semantic L1 Engine**: Provider-independent embeddings (`litellm`, `ollama`, local `fastembed`) with positive/negative anchor analysis and semantic rule conflict detection.
 - **Staged Approval (Cooldown)**: Verify risky kernel updates in a sandbox via shadow requests before production promotion.
 - **Passive Context Compression Detection**: Automatically detects silent provider-side history compression (e.g., OpenAI/Anthropic).
-- **Constitutional Kernels**: Axiomatic identity anchors.
-- **Standalone Auditor CLI**: Rapidly audit any LLM endpoint for identity drift without writing code.
+- **Constitutional Kernels & Distributed Propagation**: Axiomatic identity anchors with HMAC-SHA256 signed HTTP header propagation (`propagate_headers` / `from_headers`).
+- **Standalone Auditor & Status CLI**: Rapidly audit any LLM endpoint (`ct-toolkit audit`) and inspect provenance integrity & divergence tiers (`ct-toolkit status` / `dashboard`).
 - **Autonomous Self-Correction**: Active L2->L1 feedback loop that retries and corrects divergent responses before they reach the user.
-- **Divergence Engine**: Multi-tiered drift analysis (L1/L2/L3).
-- **Hierarchical Propagation**: Mother-to-child constraint inheritance.
-- **Provenance Log**: Immutable HMAC-signed interaction history.
+- **Enterprise Provenance & Observability**: Immutable HMAC-signed hash chain supporting SQLite and PostgreSQL/SQLAlchemy with paginated verification and OpenTelemetry (OTel) spans/metrics.
+
+![CT Toolkit Web Audit & Telemetry Dashboard](docs/ct_toolkit_web_dashboard.png)
 
 ---
 
 ## Quick Start
 
 ```bash
+# Core lightweight install
 pip install ct-toolkit
+
+# Or install with optional extras (cli, server, enterprise, embeddings, observability, all)
+pip install "ct-toolkit[all]"
 ```
 
 ```python
@@ -103,18 +101,24 @@ config = WrapperConfig(compression_passive_detection=True)
 # One-line injection for any LLM provider
 client = TheseusWrapper(provider="openai", config=config)
 
-# Guardrails and drift analysis applied automatically
+# Sync or async (`await client.achat(...)`) with automatic drift analysis
 response = client.chat("What are your core security axioms?")
 
 print(response.content)
 print(f"Divergence Score: {response.divergence_score}")
 ```
 
-### 🔍 Standalone Auditor (CLI)
+### 🔍 Standalone Auditor & Dashboard (CLI & Web UI)
 
-Audit any LLM endpoint (OpenAI, Ollama, LM Studio) directly from your terminal:
+Audit any LLM endpoint (OpenAI, Ollama, LM Studio) and inspect your provenance chain directly from your terminal or in the interactive Web Audit Dashboard:
 
 ```bash
+# View Provenance Chain integrity, L1/L2/L3 tier breakdown, and staged rules in terminal
+ct-toolkit status --vault ./ct_provenance.db
+
+# Launch the interactive Web Audit & Telemetry Dashboard at http://127.0.0.1:8001/dashboard
+ct-toolkit dashboard --web --vault ./ct_provenance.db --port 8001
+
 # Audit a local Ollama model
 ct-toolkit audit --url http://localhost:11434/v1 --kernel defense
 
@@ -142,10 +146,9 @@ The L2 judge does not evaluate Jinja2 expressions in user requests or model resp
 
 | Metric           | Status                                                                                                                                                                                                              |
 | :--------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| **Tests**        | ✅ 397 passed, 3 skipped (100% success rate, 90% coverage)                                                                                                                                                          |
+| **Tests**        | ✅ 426 passed, 3 skipped (100% success rate, 90%+ coverage)                                                                                                                                                         |
 | **Downloads**    | [![PyPI Downloads](https://static.pepy.tech/personalized-badge/ct-toolkit?period=total&units=INTERNATIONAL_SYSTEM&left_color=BLACK&right_color=MAGENTA&left_text=downloads)](https://pepy.tech/projects/ct-toolkit) |
-| **Last Phase**   | ✅ v0.3.39: urllib3 >=2.8.0 and LiteLLM >=1.104.0 fix Chunked Deflate infinite loop and authenticated SSRF / provider-credential exfiltration (Dependabot #69/#70)                                                     |
-| **Current Goal** | 🔶 Phase 7: Multi-Agent Synchronization (Integration)                                                                                                                                                               |
+| **Last Phase**   | ✅ v0.4.0: Async & Streaming (`achat`), Contrastive L1, Background L3 & Circuit Breaker, PostgreSQL/OTel, HMAC Header Propagation, and Web Audit Dashboard |
 
 ### Framework & Model Support
 

{ct_toolkit-0.3.39 → ct_toolkit-0.4.0}/ct_toolkit/__init__.py

@@ -12,7 +12,7 @@ Identity Continuity Guardrails for LLM Systems.
     print(response.content)
     print(response.divergence_score)
 """
-from ct_toolkit.core.wrapper import TheseusWrapper, WrapperConfig, CTResponse
+from ct_toolkit.core.wrapper import TheseusWrapper, WrapperConfig, CTResponse, CTStreamChunk
 from ct_toolkit.core.kernel import ConstitutionalKernel
 from ct_toolkit.core.compatibility import CompatibilityLayer
 from ct_toolkit.core.exceptions import (
@@ -23,12 +23,13 @@ from ct_toolkit.core.exceptions import (
     ChainIntegrityError,
 )
 
-__version__ = "0.3.39"
+__version__ = "0.4.0"
 
 __all__ = [
     "TheseusWrapper",
     "WrapperConfig",
     "CTResponse",
+    "CTStreamChunk",
     "ConstitutionalKernel",
     "CompatibilityLayer",
     "AxiomaticViolationError",

{ct_toolkit-0.3.39 → ct_toolkit-0.4.0}/ct_toolkit/cli.py

@@ -22,7 +22,7 @@ from rich.table import Table
 
 from ct_toolkit import TheseusWrapper, WrapperConfig, __version__
 from ct_toolkit.divergence.l3_icm import ICMRunner
-from ct_toolkit.server import start_server
+from ct_toolkit.server import start_dashboard_server, start_server
 
 app = typer.Typer(
     help="Computational Theseus Toolkit — Identity Continuity Guardrails for Agentic Systems.",
@@ -95,7 +95,7 @@ BANNER = r"""
 
 def show_banner():
     console.print(f"[bold cyan]{BANNER}[/bold cyan]")
-    console.print(f"[bold white]  Computatonal Theseus Toolkit (CT Toolkit) v{__version__}[/bold white]")
+    console.print(f"[bold white]  Computational Theseus Toolkit (CT Toolkit) v{__version__}[/bold white]")
     console.print("[dim]  Identity Continuity Guardrails for Agentic Systems[/dim]\n")
 
 def version_callback(value: bool):
@@ -205,12 +205,14 @@ def serve(
     policy_environment: str = typer.Option("prod", "--policy-environment", help="Policy environment override (dev, test, prod)."),
     judge_provider: str = typer.Option("openai", "--judge-provider", help="LLM provider for L2/L3 judge calls."),
     judge_model: Optional[str] = typer.Option(None, "--judge-model", help="Model ID for L2/L3 judge calls."),
+    api_key: Optional[str] = typer.Option(None, "--api-key", help="Optional Bearer token / API key for server endpoints."),
 ):
-    """Start the CT-Toolkit Guardrail Server for LiteLLM integration."""
-    console.print("Starting Guardrail Server...")
+    """Start the CT-Toolkit Guardrail & Web Audit Server."""
+    console.print("Starting Guardrail & Audit Server...")
     console.print(f"  - Kernel: [bold yellow]{kernel}[/bold yellow]")
     console.print(f"  - Template: [bold green]{template}[/bold green]")
     console.print(f"  - Bind: [bold cyan]{host}:{port}[/bold cyan]")
+    console.print(f"  - Web Audit Dashboard: [bold underline cyan]http://{host}:{port}/dashboard[/bold underline cyan]")
     
     try:
         config = WrapperConfig(
@@ -225,7 +227,7 @@ def serve(
         wrapper = TheseusWrapper(provider=judge_provider, config=config)
         
         # Start the uvicorn server
-        start_server(wrapper=wrapper, host=host, port=port)
+        start_server(wrapper=wrapper, host=host, port=port, api_key=api_key)
     except Exception as e:
         console.print(f"[bold red]Failed to start server:[/bold red] {e}")
         raise typer.Exit(code=1)
@@ -247,7 +249,7 @@ def setup(
     cross-origin redirects, and require certificate validation against the
     system trust store.
     """
-    base_url = f"https://raw.githubusercontent.com/hakandamar/ct-toolkit/{repo_branch}/examples/agent_dna_config"
+    base_url = f"https://raw.githubusercontent.com/Theseus-Guard/ct-toolkit/{repo_branch}/examples/agent_dna_config"
 
     if not verify_checksums:
         console.print(
@@ -363,5 +365,166 @@ def list_templates():
         
     console.print(table)
 
+
+def _render_status_dashboard(
+    vault_path: str = "./ct_provenance.db",
+    vault_type: str = "local",
+    limit: int = 200,
+) -> None:
+    """Renders the Provenance Chain, L1/L2/L3 Divergence Trends, and Staged Rules Dashboard."""
+    import time as _time
+
+    from ct_toolkit.core.exceptions import ChainIntegrityError
+    from ct_toolkit.provenance.log import ProvenanceLog
+
+    try:
+        log = ProvenanceLog(vault_type=vault_type, vault_path=vault_path)
+    except Exception as exc:
+        console.print(f"[bold red]Failed to open Provenance Log ({vault_path}):[/bold red] {exc}")
+        raise typer.Exit(code=1)
+
+    chain_ok = True
+    tampered_entry_id: str | None = None
+    verified_count = 0
+    last_hash = ProvenanceLog.GENESIS_HASH
+
+    try:
+        checkpoint = log.get_chain_checkpoint(batch_size=500)
+        verified_count = int(checkpoint["verified_count"])
+        last_hash = str(checkpoint["last_content_hash"])
+    except ChainIntegrityError as exc:
+        chain_ok = False
+        tampered_entry_id = getattr(exc, "entry_id", str(exc))
+
+    entries = log.get_entries(limit=limit, include_rolled_back=False)
+    scores = [e.divergence_score for e in entries if e.divergence_score is not None]
+    avg_score = (sum(scores) / len(scores)) if scores else 0.0
+    max_score = max(scores) if scores else 0.0
+
+    tier_counts: dict[str, int] = {
+        "ok": 0,
+        "l1_warning": 0,
+        "l2_judge": 0,
+        "l3_icm": 0,
+    }
+    promoted_ids: set[str] = set()
+    staged_records: list[dict[str, object]] = []
+
+    for entry in entries:
+        meta = entry.metadata or {}
+        event_type = meta.get("event_type")
+        if event_type == "staged_promotion":
+            eid = meta.get("endorsement_id")
+            if eid:
+                promoted_ids.add(str(eid))
+            continue
+        if event_type == "reflective_endorsement" and meta.get("decision") == "staged":
+            staged_records.append(meta)
+            continue
+
+        raw_tier = str(meta.get("tier") or meta.get("divergence_tier") or "").lower()
+        if raw_tier in tier_counts:
+            tier_counts[raw_tier] += 1
+        elif entry.divergence_score is not None:
+            if entry.divergence_score >= 0.50:
+                tier_counts["l3_icm"] += 1
+            elif entry.divergence_score >= 0.30:
+                tier_counts["l2_judge"] += 1
+            elif entry.divergence_score >= 0.15:
+                tier_counts["l1_warning"] += 1
+            else:
+                tier_counts["ok"] += 1
+
+    chain_badge = (
+        "[bold green]VALID (HMAC Verified)[/bold green]"
+        if chain_ok
+        else f"[bold red]COMPROMISED (Entry {tampered_entry_id})[/bold red]"
+    )
+    summary_text = (
+        f"[bold]Vault:[/bold] {vault_path} ({vault_type})\n"
+        f"[bold]Chain Integrity:[/bold] {chain_badge}\n"
+        f"[bold]Verified Active Entries:[/bold] {verified_count} (showing last {len(entries)})\n"
+        f"[bold]Divergence Score (Avg / Max):[/bold] {avg_score:.4f} / {max_score:.4f}\n"
+        f"[bold]Head Hash:[/bold] [dim]{last_hash[:32]}...[/dim]"
+    )
+    console.print(Panel(summary_text, title="CT Toolkit Audit & Telemetry Status", border_style="cyan"))
+
+    tier_table = Table(title="Divergence Tier Breakdown (L1 / L2 / L3)", show_header=True, header_style="bold magenta")
+    tier_table.add_column("Tier", style="cyan")
+    tier_table.add_column("Count", justify="right")
+    tier_table.add_column("Share", justify="right")
+
+    total_tiered = sum(tier_counts.values())
+    for tier_name, count in tier_counts.items():
+        pct = (count / total_tiered * 100.0) if total_tiered > 0 else 0.0
+        tier_table.add_row(tier_name.upper(), str(count), f"{pct:.1f}%")
+    console.print(tier_table)
+
+    staged_table = Table(title="Staged Kernel Rules (Sandbox Cooldown)", show_header=True, header_style="bold yellow")
+    staged_table.add_column("Endorsement ID", style="cyan")
+    staged_table.add_column("Commitment", style="white")
+    staged_table.add_column("Rule Text", style="white")
+    staged_table.add_column("Status", style="bold")
+
+    now = _time.time()
+    if not staged_records:
+        staged_table.add_row("-", "-", "No staged rules recorded", "[dim]NONE[/dim]")
+    else:
+        for s_meta in staged_records:
+            eid = str(s_meta.get("endorsement_id", "unknown"))
+            commitment = str(s_meta.get("commitment_id", "unknown"))
+            rule_text = str(s_meta.get("rule_text", ""))
+            cooldown_until = s_meta.get("cooldown_until")
+            if eid in promoted_ids:
+                status_str = "[green]PROMOTED[/green]"
+            elif isinstance(cooldown_until, (int, float)) and now < cooldown_until:
+                rem = int(cooldown_until - now)
+                status_str = f"[yellow]ACTIVE COOLDOWN ({rem}s left)[/yellow]"
+            else:
+                status_str = "[blue]READY FOR PROMOTION[/blue]"
+            staged_table.add_row(eid[:12], commitment, rule_text, status_str)
+
+    console.print(staged_table)
+
+    if not chain_ok:
+        raise typer.Exit(code=1)
+
+
+@app.command(name="status")
+def status_cmd(
+    vault_path: str = typer.Option("./ct_provenance.db", "--vault", help="Path or SQLAlchemy URL to the provenance log database."),
+    vault_type: str = typer.Option("local", "--vault-type", help="Vault backend type: local, postgres, sqlalchemy."),
+    limit: int = typer.Option(200, "--limit", help="Maximum recent entries to analyze."),
+):
+    """Display Provenance Chain integrity, L1/L2/L3 divergence trends, and active staged rules."""
+    _render_status_dashboard(vault_path=vault_path, vault_type=vault_type, limit=limit)
+
+
+@app.command(name="dashboard")
+def dashboard_cmd(
+    vault_path: str = typer.Option("./ct_provenance.db", "--vault", help="Path or SQLAlchemy URL to the provenance log database."),
+    vault_type: str = typer.Option("local", "--vault-type", help="Vault backend type: local, postgres, sqlalchemy."),
+    limit: int = typer.Option(200, "--limit", help="Maximum recent entries to analyze."),
+    web: bool = typer.Option(False, "--web", "-w", help="Launch the interactive Web Audit & Telemetry Dashboard in browser mode."),
+    host: str = typer.Option("127.0.0.1", "--host", help="Host to bind the Web Dashboard server to (when --web is used)."),
+    port: int = typer.Option(8001, "--port", help="Port to bind the Web Dashboard server to (when --web is used)."),
+    api_key: Optional[str] = typer.Option(None, "--api-key", help="Optional Bearer token / API key for dashboard API authentication."),
+):
+    """Display the terminal audit dashboard or launch the interactive Web Audit Dashboard (--web)."""
+    if web:
+        console.print("🌐 Launching [bold cyan]CT Toolkit Web Audit & Telemetry Dashboard[/bold cyan]...")
+        console.print(f"  - Vault: [bold yellow]{vault_path}[/bold yellow] ({vault_type})")
+        console.print(f"  - Dashboard URL: [bold underline green]http://{host}:{port}/dashboard[/bold underline green]")
+        start_dashboard_server(
+            vault_path=vault_path,
+            vault_type=vault_type,
+            host=host,
+            port=port,
+            api_key=api_key,
+        )
+        return
+    _render_status_dashboard(vault_path=vault_path, vault_type=vault_type, limit=limit)
+
+
 if __name__ == "__main__":
     app()