agenticdome-python-sdk 1.2.16__tar.gz → 1.2.17__tar.gz

{agenticdome_python_sdk-1.2.16 → agenticdome_python_sdk-1.2.17}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agenticdome-python-sdk
-Version: 1.2.16
+Version: 1.2.17
 Summary: Official Python SDK for AgenticDome security guardrails, DLP, tool authorization, and multi-agent delegation enforcement.
 Author: AgenticDome
 License-Expression: Apache-2.0
@@ -38,10 +38,10 @@ Requires-Dist: redis>=4.5.0; extra == "redis"
 Provides-Extra: pop
 Requires-Dist: cryptography>=42.0.0; extra == "pop"
 Provides-Extra: pydanticai
-Requires-Dist: pydantic-ai<=2.28.0,>=2.16.0; extra == "pydanticai"
+Requires-Dist: pydantic-ai<=2.29.0,>=2.16.0; extra == "pydanticai"
 Requires-Dist: anyio>=4.0.0; extra == "pydanticai"
 Provides-Extra: pydantic
-Requires-Dist: pydantic-ai<=2.28.0,>=2.16.0; extra == "pydantic"
+Requires-Dist: pydantic-ai<=2.29.0,>=2.16.0; extra == "pydantic"
 Requires-Dist: anyio>=4.0.0; extra == "pydantic"
 Provides-Extra: langgraph
 Requires-Dist: langgraph<=1.2.11,>=1.2.9; extra == "langgraph"
@@ -63,9 +63,9 @@ Requires-Dist: openai-agents<=0.20.0,>=0.18.3; extra == "openai-agents"
 Provides-Extra: mcp
 Requires-Dist: mcp<=1.28.1,>=1.26.0; extra == "mcp"
 Provides-Extra: bedrock
-Requires-Dist: boto3<=1.43.69,>=1.43.54; extra == "bedrock"
+Requires-Dist: boto3<=1.43.70,>=1.43.54; extra == "bedrock"
 Provides-Extra: aws-bedrock
-Requires-Dist: boto3<=1.43.69,>=1.43.54; extra == "aws-bedrock"
+Requires-Dist: boto3<=1.43.70,>=1.43.54; extra == "aws-bedrock"
 Provides-Extra: llamaindex
 Requires-Dist: llama-index==0.14.23; extra == "llamaindex"
 Provides-Extra: llama-index
@@ -75,16 +75,16 @@ Requires-Dist: google-adk<=2.6.3,>=2.5.0; extra == "google-adk"
 Provides-Extra: adk
 Requires-Dist: google-adk<=2.6.3,>=2.5.0; extra == "adk"
 Provides-Extra: claude
-Requires-Dist: claude-agent-sdk<=0.2.136,>=0.2.126; extra == "claude"
+Requires-Dist: claude-agent-sdk<=0.2.137,>=0.2.126; extra == "claude"
 Provides-Extra: claude-agent-sdk
-Requires-Dist: claude-agent-sdk<=0.2.136,>=0.2.126; extra == "claude-agent-sdk"
+Requires-Dist: claude-agent-sdk<=0.2.137,>=0.2.126; extra == "claude-agent-sdk"
 Provides-Extra: smolagents
 Requires-Dist: smolagents==1.26.0; extra == "smolagents"
 Provides-Extra: all
 Requires-Dist: crewai<=1.15.15,>=1.15.5; extra == "all"
 Requires-Dist: redis>=4.5.0; extra == "all"
 Requires-Dist: cryptography>=42.0.0; extra == "all"
-Requires-Dist: pydantic-ai<=2.28.0,>=2.16.0; extra == "all"
+Requires-Dist: pydantic-ai<=2.29.0,>=2.16.0; extra == "all"
 Requires-Dist: anyio>=4.0.0; extra == "all"
 Requires-Dist: langgraph<=1.2.11,>=1.2.9; extra == "all"
 Requires-Dist: langchain-core<=1.5.4,>=1.5.0; extra == "all"
@@ -95,10 +95,10 @@ Requires-Dist: azure-ai-projects<=2.4.0,>=2.3.0; extra == "all"
 Requires-Dist: azure-identity==1.25.3; extra == "all"
 Requires-Dist: openai-agents<=0.20.0,>=0.18.3; extra == "all"
 Requires-Dist: mcp<=1.28.1,>=1.26.0; extra == "all"
-Requires-Dist: boto3<=1.43.69,>=1.43.54; extra == "all"
+Requires-Dist: boto3<=1.43.70,>=1.43.54; extra == "all"
 Requires-Dist: llama-index==0.14.23; extra == "all"
 Requires-Dist: google-adk<=2.6.3,>=2.5.0; extra == "all"
-Requires-Dist: claude-agent-sdk<=0.2.136,>=0.2.126; extra == "all"
+Requires-Dist: claude-agent-sdk<=0.2.137,>=0.2.126; extra == "all"
 Requires-Dist: smolagents==1.26.0; extra == "all"
 Provides-Extra: dev
 Requires-Dist: pytest>=8.0.0; extra == "dev"
@@ -147,7 +147,14 @@ No account, API key, tenant, network connection, or third-party framework packag
 agenticdome-demo --framework langgraph --scenario both
 ```
 
-Look for `ALLOWED — TOOL WOULD EXECUTE` followed by `BLOCKED — TOOL WOULD NOT EXECUTE`. These are simulations: the example does not execute either tool.
+Look for `ALLOWED — TOOL WOULD EXECUTE` followed by `BLOCKED — TOOL WOULD NOT EXECUTE`.
+
+> **Offline demonstration—not runtime evidence.** This command evaluates two
+> fixed onboarding scenarios with a deterministic, bundled public baseline. It
+> does not contact AgenticDome, load tenant policy, execute either tool, or
+> instantiate a LangGraph graph. `--framework langgraph` labels the example
+> payload and points you to the matching integration; it is not a LangGraph
+> integration test.
 
 ### 4. Select your framework
 
@@ -170,7 +177,13 @@ export AGENTICDOME_TENANT_ID="your_tenant_id"
 agenticdome-demo --framework langgraph --scenario both --live
 ```
 
-Offline simulation demonstrates the SDK decision flow using a bundled public baseline. Only live mode applies the customer's policy, topology, telemetry, signed decisions and runtime enforcement.
+With `--live`, the same fixed scenarios are sent to the actual assigned
+AgenticDome runtime sidecar, so their verdicts come from the customer's tenant
+policy and engine. The live demo still does not instantiate LangGraph or prove
+that an application has attached the framework adapter at every execution
+boundary. Use the framework guide to attach the adapter, test the real
+application path, and use AgenticDome Runtime Assurance for production
+evidence.
 
 ```python
 # The 30-second version: block a prompt-injected refund before it executes.
@@ -205,6 +218,21 @@ result = crew.kickoff()          # hostile prompts, unsafe tools, and rogue
 
 An agent can be hijacked while holding valid tokens, approved tools, and fully authorized paths. Legacy security sees a compliant request; the business sees a breach. AgenticDome adds an intent-aware enforcement layer at the exact boundaries where agents act:
 
+### Identity is necessary, but it is not the action decision
+
+Give every agent and workload a distinct principal and keep your identity
+provider authoritative for authentication, scopes, conditional access,
+credential lifecycle, and downstream entitlements. Then pass the identity the
+application has actually authenticated into AgenticDome alongside the agent,
+purpose, tool, final arguments, session, and delegation context. A valid token
+proves access authority; it does not prove that a prompt-influenced action is
+appropriate. AgenticDome complements IAM by evaluating that action at the
+application-controlled execution boundary. It does not issue enterprise
+identities or make a stolen credential safe.
+
+For the architectural rationale, see
+[An agent principal proves who—not why](https://www.agenticdome.io/research/agent-principal-identity).
+
 | Control | What it stops | Where it runs |
 | :--- | :--- | :--- |
 | **Prompt ingress guardrails** | Prompt injection, jailbreaks, system-prompt extraction, instruction override, policy bypass | Before agent/LLM execution |
@@ -300,15 +328,23 @@ Start with a network-free simulation, then connect the same SDK to your assigned
 
 ```bash
 pip install agenticdome-python-sdk
-# Show one ALLOWED and one BLOCKED action for LangGraph.
+# Label the fixed demonstration as LangGraph and show one ALLOWED and one BLOCKED path.
 agenticdome-demo --framework langgraph --scenario both
 
-# Or prove the same offline contract across all 15 integrations.
+# Or repeat the fixed demonstration under every supported framework label.
 agenticdome-demo --framework all --scenario both
 agenticdome-demo --list-frameworks
 ```
 
-This is visibly labelled **LOCAL SIMULATION — NOT CLOUD ENFORCEMENT**. It evaluates a small bundled demonstration policy through the real public client contract, but it does not load tenant policy, issue signed decision tokens or execution receipts, write cloud evidence, or provide runtime assurance. To exercise any wrapper inside your own process without credentials, set `AGENTICDOME_MODE=local_sim`. The SDK refuses that mode when `AGENTICDOME_PRODUCTION_MODE=true`.
+This is visibly labelled **LOCAL SIMULATION — NOT CLOUD ENFORCEMENT**. It
+evaluates two fixed inputs with a small deterministic bundled baseline through
+the public core-client response shape. The `--framework` option changes the
+payload label and integration guidance; it does not import, instantiate, or run
+the selected framework. The simulation does not load tenant policy, issue
+signed decision tokens or execution receipts, write cloud evidence, or provide
+runtime assurance. To exercise a real adapter inside your own process without
+credentials, set `AGENTICDOME_MODE=local_sim` in that application or framework
+example. The SDK refuses that mode when `AGENTICDOME_PRODUCTION_MODE=true`.
 
 Browse the public [`examples/`](examples/README.md) gallery for a runnable allowed/blocked example for CrewAI, PydanticAI, LangGraph, Microsoft Agent Framework, AutoGen, AI Foundry, OpenAI Agents, Claude, smolagents, Agno, Google ADK, LlamaIndex, Bedrock, MCP, and custom Python. Local blocked/redacted results emit safe terminal logs containing verdict metadata only—not raw prompts, arguments, keys, or secrets.
 

{agenticdome_python_sdk-1.2.16 → agenticdome_python_sdk-1.2.17}/README.md

@@ -35,7 +35,14 @@ No account, API key, tenant, network connection, or third-party framework packag
 agenticdome-demo --framework langgraph --scenario both
 ```
 
-Look for `ALLOWED — TOOL WOULD EXECUTE` followed by `BLOCKED — TOOL WOULD NOT EXECUTE`. These are simulations: the example does not execute either tool.
+Look for `ALLOWED — TOOL WOULD EXECUTE` followed by `BLOCKED — TOOL WOULD NOT EXECUTE`.
+
+> **Offline demonstration—not runtime evidence.** This command evaluates two
+> fixed onboarding scenarios with a deterministic, bundled public baseline. It
+> does not contact AgenticDome, load tenant policy, execute either tool, or
+> instantiate a LangGraph graph. `--framework langgraph` labels the example
+> payload and points you to the matching integration; it is not a LangGraph
+> integration test.
 
 ### 4. Select your framework
 
@@ -58,7 +65,13 @@ export AGENTICDOME_TENANT_ID="your_tenant_id"
 agenticdome-demo --framework langgraph --scenario both --live
 ```
 
-Offline simulation demonstrates the SDK decision flow using a bundled public baseline. Only live mode applies the customer's policy, topology, telemetry, signed decisions and runtime enforcement.
+With `--live`, the same fixed scenarios are sent to the actual assigned
+AgenticDome runtime sidecar, so their verdicts come from the customer's tenant
+policy and engine. The live demo still does not instantiate LangGraph or prove
+that an application has attached the framework adapter at every execution
+boundary. Use the framework guide to attach the adapter, test the real
+application path, and use AgenticDome Runtime Assurance for production
+evidence.
 
 ```python
 # The 30-second version: block a prompt-injected refund before it executes.
@@ -93,6 +106,21 @@ result = crew.kickoff()          # hostile prompts, unsafe tools, and rogue
 
 An agent can be hijacked while holding valid tokens, approved tools, and fully authorized paths. Legacy security sees a compliant request; the business sees a breach. AgenticDome adds an intent-aware enforcement layer at the exact boundaries where agents act:
 
+### Identity is necessary, but it is not the action decision
+
+Give every agent and workload a distinct principal and keep your identity
+provider authoritative for authentication, scopes, conditional access,
+credential lifecycle, and downstream entitlements. Then pass the identity the
+application has actually authenticated into AgenticDome alongside the agent,
+purpose, tool, final arguments, session, and delegation context. A valid token
+proves access authority; it does not prove that a prompt-influenced action is
+appropriate. AgenticDome complements IAM by evaluating that action at the
+application-controlled execution boundary. It does not issue enterprise
+identities or make a stolen credential safe.
+
+For the architectural rationale, see
+[An agent principal proves who—not why](https://www.agenticdome.io/research/agent-principal-identity).
+
 | Control | What it stops | Where it runs |
 | :--- | :--- | :--- |
 | **Prompt ingress guardrails** | Prompt injection, jailbreaks, system-prompt extraction, instruction override, policy bypass | Before agent/LLM execution |
@@ -188,15 +216,23 @@ Start with a network-free simulation, then connect the same SDK to your assigned
 
 ```bash
 pip install agenticdome-python-sdk
-# Show one ALLOWED and one BLOCKED action for LangGraph.
+# Label the fixed demonstration as LangGraph and show one ALLOWED and one BLOCKED path.
 agenticdome-demo --framework langgraph --scenario both
 
-# Or prove the same offline contract across all 15 integrations.
+# Or repeat the fixed demonstration under every supported framework label.
 agenticdome-demo --framework all --scenario both
 agenticdome-demo --list-frameworks
 ```
 
-This is visibly labelled **LOCAL SIMULATION — NOT CLOUD ENFORCEMENT**. It evaluates a small bundled demonstration policy through the real public client contract, but it does not load tenant policy, issue signed decision tokens or execution receipts, write cloud evidence, or provide runtime assurance. To exercise any wrapper inside your own process without credentials, set `AGENTICDOME_MODE=local_sim`. The SDK refuses that mode when `AGENTICDOME_PRODUCTION_MODE=true`.
+This is visibly labelled **LOCAL SIMULATION — NOT CLOUD ENFORCEMENT**. It
+evaluates two fixed inputs with a small deterministic bundled baseline through
+the public core-client response shape. The `--framework` option changes the
+payload label and integration guidance; it does not import, instantiate, or run
+the selected framework. The simulation does not load tenant policy, issue
+signed decision tokens or execution receipts, write cloud evidence, or provide
+runtime assurance. To exercise a real adapter inside your own process without
+credentials, set `AGENTICDOME_MODE=local_sim` in that application or framework
+example. The SDK refuses that mode when `AGENTICDOME_PRODUCTION_MODE=true`.
 
 Browse the public [`examples/`](examples/README.md) gallery for a runnable allowed/blocked example for CrewAI, PydanticAI, LangGraph, Microsoft Agent Framework, AutoGen, AI Foundry, OpenAI Agents, Claude, smolagents, Agno, Google ADK, LlamaIndex, Bedrock, MCP, and custom Python. Local blocked/redacted results emit safe terminal logs containing verdict metadata only—not raw prompts, arguments, keys, or secrets.
 

{agenticdome_python_sdk-1.2.16 → agenticdome_python_sdk-1.2.17}/agenticdome_python_sdk.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agenticdome-python-sdk
-Version: 1.2.16
+Version: 1.2.17
 Summary: Official Python SDK for AgenticDome security guardrails, DLP, tool authorization, and multi-agent delegation enforcement.
 Author: AgenticDome
 License-Expression: Apache-2.0
@@ -38,10 +38,10 @@ Requires-Dist: redis>=4.5.0; extra == "redis"
 Provides-Extra: pop
 Requires-Dist: cryptography>=42.0.0; extra == "pop"
 Provides-Extra: pydanticai
-Requires-Dist: pydantic-ai<=2.28.0,>=2.16.0; extra == "pydanticai"
+Requires-Dist: pydantic-ai<=2.29.0,>=2.16.0; extra == "pydanticai"
 Requires-Dist: anyio>=4.0.0; extra == "pydanticai"
 Provides-Extra: pydantic
-Requires-Dist: pydantic-ai<=2.28.0,>=2.16.0; extra == "pydantic"
+Requires-Dist: pydantic-ai<=2.29.0,>=2.16.0; extra == "pydantic"
 Requires-Dist: anyio>=4.0.0; extra == "pydantic"
 Provides-Extra: langgraph
 Requires-Dist: langgraph<=1.2.11,>=1.2.9; extra == "langgraph"
@@ -63,9 +63,9 @@ Requires-Dist: openai-agents<=0.20.0,>=0.18.3; extra == "openai-agents"
 Provides-Extra: mcp
 Requires-Dist: mcp<=1.28.1,>=1.26.0; extra == "mcp"
 Provides-Extra: bedrock
-Requires-Dist: boto3<=1.43.69,>=1.43.54; extra == "bedrock"
+Requires-Dist: boto3<=1.43.70,>=1.43.54; extra == "bedrock"
 Provides-Extra: aws-bedrock
-Requires-Dist: boto3<=1.43.69,>=1.43.54; extra == "aws-bedrock"
+Requires-Dist: boto3<=1.43.70,>=1.43.54; extra == "aws-bedrock"
 Provides-Extra: llamaindex
 Requires-Dist: llama-index==0.14.23; extra == "llamaindex"
 Provides-Extra: llama-index
@@ -75,16 +75,16 @@ Requires-Dist: google-adk<=2.6.3,>=2.5.0; extra == "google-adk"
 Provides-Extra: adk
 Requires-Dist: google-adk<=2.6.3,>=2.5.0; extra == "adk"
 Provides-Extra: claude
-Requires-Dist: claude-agent-sdk<=0.2.136,>=0.2.126; extra == "claude"
+Requires-Dist: claude-agent-sdk<=0.2.137,>=0.2.126; extra == "claude"
 Provides-Extra: claude-agent-sdk
-Requires-Dist: claude-agent-sdk<=0.2.136,>=0.2.126; extra == "claude-agent-sdk"
+Requires-Dist: claude-agent-sdk<=0.2.137,>=0.2.126; extra == "claude-agent-sdk"
 Provides-Extra: smolagents
 Requires-Dist: smolagents==1.26.0; extra == "smolagents"
 Provides-Extra: all
 Requires-Dist: crewai<=1.15.15,>=1.15.5; extra == "all"
 Requires-Dist: redis>=4.5.0; extra == "all"
 Requires-Dist: cryptography>=42.0.0; extra == "all"
-Requires-Dist: pydantic-ai<=2.28.0,>=2.16.0; extra == "all"
+Requires-Dist: pydantic-ai<=2.29.0,>=2.16.0; extra == "all"
 Requires-Dist: anyio>=4.0.0; extra == "all"
 Requires-Dist: langgraph<=1.2.11,>=1.2.9; extra == "all"
 Requires-Dist: langchain-core<=1.5.4,>=1.5.0; extra == "all"
@@ -95,10 +95,10 @@ Requires-Dist: azure-ai-projects<=2.4.0,>=2.3.0; extra == "all"
 Requires-Dist: azure-identity==1.25.3; extra == "all"
 Requires-Dist: openai-agents<=0.20.0,>=0.18.3; extra == "all"
 Requires-Dist: mcp<=1.28.1,>=1.26.0; extra == "all"
-Requires-Dist: boto3<=1.43.69,>=1.43.54; extra == "all"
+Requires-Dist: boto3<=1.43.70,>=1.43.54; extra == "all"
 Requires-Dist: llama-index==0.14.23; extra == "all"
 Requires-Dist: google-adk<=2.6.3,>=2.5.0; extra == "all"
-Requires-Dist: claude-agent-sdk<=0.2.136,>=0.2.126; extra == "all"
+Requires-Dist: claude-agent-sdk<=0.2.137,>=0.2.126; extra == "all"
 Requires-Dist: smolagents==1.26.0; extra == "all"
 Provides-Extra: dev
 Requires-Dist: pytest>=8.0.0; extra == "dev"
@@ -147,7 +147,14 @@ No account, API key, tenant, network connection, or third-party framework packag
 agenticdome-demo --framework langgraph --scenario both
 ```
 
-Look for `ALLOWED — TOOL WOULD EXECUTE` followed by `BLOCKED — TOOL WOULD NOT EXECUTE`. These are simulations: the example does not execute either tool.
+Look for `ALLOWED — TOOL WOULD EXECUTE` followed by `BLOCKED — TOOL WOULD NOT EXECUTE`.
+
+> **Offline demonstration—not runtime evidence.** This command evaluates two
+> fixed onboarding scenarios with a deterministic, bundled public baseline. It
+> does not contact AgenticDome, load tenant policy, execute either tool, or
+> instantiate a LangGraph graph. `--framework langgraph` labels the example
+> payload and points you to the matching integration; it is not a LangGraph
+> integration test.
 
 ### 4. Select your framework
 
@@ -170,7 +177,13 @@ export AGENTICDOME_TENANT_ID="your_tenant_id"
 agenticdome-demo --framework langgraph --scenario both --live
 ```
 
-Offline simulation demonstrates the SDK decision flow using a bundled public baseline. Only live mode applies the customer's policy, topology, telemetry, signed decisions and runtime enforcement.
+With `--live`, the same fixed scenarios are sent to the actual assigned
+AgenticDome runtime sidecar, so their verdicts come from the customer's tenant
+policy and engine. The live demo still does not instantiate LangGraph or prove
+that an application has attached the framework adapter at every execution
+boundary. Use the framework guide to attach the adapter, test the real
+application path, and use AgenticDome Runtime Assurance for production
+evidence.
 
 ```python
 # The 30-second version: block a prompt-injected refund before it executes.
@@ -205,6 +218,21 @@ result = crew.kickoff()          # hostile prompts, unsafe tools, and rogue
 
 An agent can be hijacked while holding valid tokens, approved tools, and fully authorized paths. Legacy security sees a compliant request; the business sees a breach. AgenticDome adds an intent-aware enforcement layer at the exact boundaries where agents act:
 
+### Identity is necessary, but it is not the action decision
+
+Give every agent and workload a distinct principal and keep your identity
+provider authoritative for authentication, scopes, conditional access,
+credential lifecycle, and downstream entitlements. Then pass the identity the
+application has actually authenticated into AgenticDome alongside the agent,
+purpose, tool, final arguments, session, and delegation context. A valid token
+proves access authority; it does not prove that a prompt-influenced action is
+appropriate. AgenticDome complements IAM by evaluating that action at the
+application-controlled execution boundary. It does not issue enterprise
+identities or make a stolen credential safe.
+
+For the architectural rationale, see
+[An agent principal proves who—not why](https://www.agenticdome.io/research/agent-principal-identity).
+
 | Control | What it stops | Where it runs |
 | :--- | :--- | :--- |
 | **Prompt ingress guardrails** | Prompt injection, jailbreaks, system-prompt extraction, instruction override, policy bypass | Before agent/LLM execution |
@@ -300,15 +328,23 @@ Start with a network-free simulation, then connect the same SDK to your assigned
 
 ```bash
 pip install agenticdome-python-sdk
-# Show one ALLOWED and one BLOCKED action for LangGraph.
+# Label the fixed demonstration as LangGraph and show one ALLOWED and one BLOCKED path.
 agenticdome-demo --framework langgraph --scenario both
 
-# Or prove the same offline contract across all 15 integrations.
+# Or repeat the fixed demonstration under every supported framework label.
 agenticdome-demo --framework all --scenario both
 agenticdome-demo --list-frameworks
 ```
 
-This is visibly labelled **LOCAL SIMULATION — NOT CLOUD ENFORCEMENT**. It evaluates a small bundled demonstration policy through the real public client contract, but it does not load tenant policy, issue signed decision tokens or execution receipts, write cloud evidence, or provide runtime assurance. To exercise any wrapper inside your own process without credentials, set `AGENTICDOME_MODE=local_sim`. The SDK refuses that mode when `AGENTICDOME_PRODUCTION_MODE=true`.
+This is visibly labelled **LOCAL SIMULATION — NOT CLOUD ENFORCEMENT**. It
+evaluates two fixed inputs with a small deterministic bundled baseline through
+the public core-client response shape. The `--framework` option changes the
+payload label and integration guidance; it does not import, instantiate, or run
+the selected framework. The simulation does not load tenant policy, issue
+signed decision tokens or execution receipts, write cloud evidence, or provide
+runtime assurance. To exercise a real adapter inside your own process without
+credentials, set `AGENTICDOME_MODE=local_sim` in that application or framework
+example. The SDK refuses that mode when `AGENTICDOME_PRODUCTION_MODE=true`.
 
 Browse the public [`examples/`](examples/README.md) gallery for a runnable allowed/blocked example for CrewAI, PydanticAI, LangGraph, Microsoft Agent Framework, AutoGen, AI Foundry, OpenAI Agents, Claude, smolagents, Agno, Google ADK, LlamaIndex, Bedrock, MCP, and custom Python. Local blocked/redacted results emit safe terminal logs containing verdict metadata only—not raw prompts, arguments, keys, or secrets.
 

{agenticdome_python_sdk-1.2.16 → agenticdome_python_sdk-1.2.17}/agenticdome_python_sdk.egg-info/requires.txt

@@ -11,7 +11,7 @@ agno<=2.8.7,>=2.8.0
 crewai<=1.15.15,>=1.15.5
 redis>=4.5.0
 cryptography>=42.0.0
-pydantic-ai<=2.28.0,>=2.16.0
+pydantic-ai<=2.29.0,>=2.16.0
 anyio>=4.0.0
 langgraph<=1.2.11,>=1.2.9
 langchain-core<=1.5.4,>=1.5.0
@@ -22,26 +22,26 @@ azure-ai-projects<=2.4.0,>=2.3.0
 azure-identity==1.25.3
 openai-agents<=0.20.0,>=0.18.3
 mcp<=1.28.1,>=1.26.0
-boto3<=1.43.69,>=1.43.54
+boto3<=1.43.70,>=1.43.54
 llama-index==0.14.23
 google-adk<=2.6.3,>=2.5.0
-claude-agent-sdk<=0.2.136,>=0.2.126
+claude-agent-sdk<=0.2.137,>=0.2.126
 smolagents==1.26.0
 
 [autogen]
 autogen-agentchat==0.7.5
 
 [aws-bedrock]
-boto3<=1.43.69,>=1.43.54
+boto3<=1.43.70,>=1.43.54
 
 [bedrock]
-boto3<=1.43.69,>=1.43.54
+boto3<=1.43.70,>=1.43.54
 
 [claude]
-claude-agent-sdk<=0.2.136,>=0.2.126
+claude-agent-sdk<=0.2.137,>=0.2.126
 
 [claude-agent-sdk]
-claude-agent-sdk<=0.2.136,>=0.2.126
+claude-agent-sdk<=0.2.137,>=0.2.126
 
 [crewai]
 crewai<=1.15.15,>=1.15.5
@@ -91,11 +91,11 @@ openai-agents<=0.20.0,>=0.18.3
 cryptography>=42.0.0
 
 [pydantic]
-pydantic-ai<=2.28.0,>=2.16.0
+pydantic-ai<=2.29.0,>=2.16.0
 anyio>=4.0.0
 
 [pydanticai]
-pydantic-ai<=2.28.0,>=2.16.0
+pydantic-ai<=2.29.0,>=2.16.0
 anyio>=4.0.0
 
 [redis]

{agenticdome_python_sdk-1.2.16 → agenticdome_python_sdk-1.2.17}/agenticdome_sdk/demo.py

@@ -81,6 +81,16 @@ def _run_demo(framework_key: str, scenario_key: str, *, live: bool) -> Dict[str,
     mode = "LIVE SIDECAR" if live else "LOCAL SIMULATION — NOT CLOUD ENFORCEMENT"
     print(f"AgenticDome demo: {framework['label']}")
     print(f"Mode: {mode}")
+    if live:
+        print(
+            "Scope: fixed onboarding input sent to the assigned runtime sidecar; "
+            f"this does not instantiate {framework['label']}."
+        )
+    else:
+        print(
+            "Scope: fixed onboarding input evaluated by the bundled deterministic baseline; "
+            f"this does not instantiate {framework['label']} or contact AgenticDome."
+        )
     print(f"Scenario: {scenario['title']}")
     print("Without AgenticDome: TOOL WOULD EXECUTE (no policy decision)")
 
@@ -102,7 +112,7 @@ def _run_demo(framework_key: str, scenario_key: str, *, live: bool) -> Dict[str,
     outcome = "TOOL WOULD EXECUTE" if verdict in {"ALLOWED", "REDACTED"} else "TOOL WOULD NOT EXECUTE"
     print(f"With AgenticDome: {verdict} — {outcome}")
     print(json.dumps(decision, indent=2, sort_keys=True))
-    print("Production integration import:")
+    print("Next step — production adapter import (not executed by this demo):")
     print(framework["import"])
     return decision
 
@@ -113,7 +123,7 @@ def main(argv: Optional[List[str]] = None) -> int:
         "--framework",
         choices=[*sorted(FRAMEWORKS), "all"],
         default="crewai",
-        help="Framework to demonstrate, or 'all' for complete parity coverage.",
+        help="Framework label for the fixed demo payload and integration guidance; this does not run the framework.",
     )
     parser.add_argument(
         "--scenario",
@@ -148,7 +158,8 @@ def main(argv: Optional[List[str]] = None) -> int:
 
     if total > 1:
         summary = ", ".join(f"{key}={value}" for key, value in sorted(verdict_totals.items()))
-        print(f"\nCompleted {total} offline framework/scenario proofs: {summary}")
+        evidence_scope = "live sidecar decision checks" if args.live else "offline SDK-flow demonstrations"
+        print(f"\nCompleted {total} {evidence_scope}: {summary}")
     return 0
 
 

{agenticdome_python_sdk-1.2.16 → agenticdome_python_sdk-1.2.17}/docs/frameworks/README.md

@@ -26,7 +26,10 @@ prove both an allowed and blocked path.
 ## Shared five-step path
 
 1. Install the matching package extra.
-2. Run `AGENTICDOME_MODE=local_sim` with one allowed and one blocked scenario.
+2. Run `AGENTICDOME_MODE=local_sim` with one allowed and one blocked fixed
+   scenario to understand the SDK decision flow. This deterministic offline
+   demo does not import or execute the selected framework and is not runtime
+   assurance evidence.
 3. Obtain the assigned runtime sidecar URL, Runtime/SDK key and tenant ID.
 4. Attach the adapter in the application construction path and remove raw
    execution routes that bypass it.
@@ -41,7 +44,12 @@ to install Redis; Redis is optional only for Python delegation state that must
 cross application processes, workers, or pods. See
 [Runtime location and Redis responsibilities](../runtime-deployment.md).
 
-The offline simulator proves SDK control flow, not tenant enforcement. The
+The offline simulator proves core SDK control flow, not framework attachment or
+tenant enforcement. The `--framework` option labels the fixed demo payload and
+selects the relevant guidance; it does not instantiate that framework. Adding
+`--live` sends those same inputs to the assigned sidecar and proves the real
+engine decision path, but application-level framework attachment must still be
+tested at the actual prompt, tool, delegation, and output boundaries. The
 public SDK does not expose AgenticDome policy algorithms, private threat
 signatures, decision-token formats or control-plane internals.
 

{agenticdome_python_sdk-1.2.16 → agenticdome_python_sdk-1.2.17}/docs/frameworks/agno.md

@@ -12,6 +12,11 @@ export AGENTICDOME_MODE=local_sim
 agenticdome-demo --framework agno --scenario both
 ```
 
+**Demo scope:** this command evaluates two fixed inputs with a deterministic,
+bundled public baseline. It does not contact AgenticDome, load tenant policy,
+execute tools, or instantiate Agno. The framework option is a label and guide
+selector, not an Agno integration test.
+
 ## Attach in production
 
 Configure the assigned runtime, and make sure simulation is not inherited by
@@ -24,6 +29,11 @@ export AGENTICDOME_API_KEY="your-runtime-sdk-key"
 export AGENTICDOME_TENANT_ID="your-tenant-id"
 ```
 
+Run `agenticdome-demo --framework agno --scenario both --live` to obtain real
+tenant-engine decisions for those fixed inputs. That checks the assigned
+sidecar, not Agno attachment; the code below attaches the adapter to the real
+application boundary.
+
 For managed service, the API base is assigned in the selected supported
 geographic region, subject to availability. A contracted Sovereign runtime is
 inside the customer-controlled environment. Normal SDK calls do not require

{agenticdome_python_sdk-1.2.16 → agenticdome_python_sdk-1.2.17}/docs/frameworks/autogen.md

@@ -12,6 +12,11 @@ export AGENTICDOME_MODE=local_sim
 agenticdome-demo --framework autogen --scenario both
 ```
 
+**Demo scope:** this command evaluates two fixed inputs with a deterministic,
+bundled public baseline. It does not contact AgenticDome, load tenant policy,
+execute tools, or instantiate AutoGen. The framework option is a label and
+guide selector, not an AutoGen integration test.
+
 ## Attach in production
 
 Configure the assigned runtime first:
@@ -23,6 +28,11 @@ export AGENTICDOME_API_KEY="your-runtime-sdk-key"
 export AGENTICDOME_TENANT_ID="your-tenant-id"
 ```
 
+Run `agenticdome-demo --framework autogen --scenario both --live` to obtain
+real tenant-engine decisions for those fixed inputs. That checks the assigned
+sidecar, not AutoGen attachment; the code below attaches the adapter to the
+real application boundary.
+
 For managed service, the API base is assigned in the selected supported
 geographic region, subject to availability. A contracted Sovereign runtime is
 inside the customer-controlled environment. Normal SDK calls do not require

{agenticdome_python_sdk-1.2.16 → agenticdome_python_sdk-1.2.17}/docs/frameworks/aws-bedrock.md

@@ -12,6 +12,11 @@ export AGENTICDOME_MODE=local_sim
 agenticdome-demo --framework bedrock --scenario both
 ```
 
+**Demo scope:** this command evaluates two fixed inputs with a deterministic,
+bundled public baseline. It does not contact AgenticDome, load tenant policy,
+execute tools, or call AWS Bedrock. The framework option is a label and guide
+selector, not a Bedrock integration test.
+
 ## Attach in production
 
 Configure the assigned runtime first:
@@ -23,6 +28,11 @@ export AGENTICDOME_API_KEY="your-runtime-sdk-key"
 export AGENTICDOME_TENANT_ID="your-tenant-id"
 ```
 
+Run `agenticdome-demo --framework bedrock --scenario both --live` to obtain
+real tenant-engine decisions for those fixed inputs. That checks the assigned
+sidecar, not Bedrock attachment; the code below attaches the adapter to the
+real application boundary.
+
 For managed service, the API base is assigned in the selected supported
 geographic region, subject to availability. A contracted Sovereign runtime is
 inside the customer-controlled environment. Normal SDK calls do not require

{agenticdome_python_sdk-1.2.16 → agenticdome_python_sdk-1.2.17}/docs/frameworks/claude-agent-sdk.md

@@ -12,6 +12,11 @@ export AGENTICDOME_MODE=local_sim
 agenticdome-demo --framework claude --scenario both
 ```
 
+**Demo scope:** this command evaluates two fixed inputs with a deterministic,
+bundled public baseline. It does not contact AgenticDome, load tenant policy,
+execute tools, or instantiate the Claude Agent SDK. The framework option is a
+label and guide selector, not a Claude integration test.
+
 ## Attach in production
 
 Configure the assigned runtime first:
@@ -23,6 +28,11 @@ export AGENTICDOME_API_KEY="your-runtime-sdk-key"
 export AGENTICDOME_TENANT_ID="your-tenant-id"
 ```
 
+Run `agenticdome-demo --framework claude --scenario both --live` to obtain real
+tenant-engine decisions for those fixed inputs. That checks the assigned
+sidecar, not Claude Agent SDK attachment; the code below attaches the adapter
+to the real application boundary.
+
 For managed service, the API base is assigned in the selected supported
 geographic region, subject to availability. A contracted Sovereign runtime is
 inside the customer-controlled environment. Normal SDK calls do not require

{agenticdome_python_sdk-1.2.16 → agenticdome_python_sdk-1.2.17}/docs/frameworks/crewai.md

@@ -12,8 +12,10 @@ export AGENTICDOME_MODE=local_sim
 agenticdome-demo --framework crewai --scenario both
 ```
 
-This prints one allowed and one blocked decision without importing CrewAI,
-contacting a sidecar or executing either demonstration tool.
+**Demo scope:** this command evaluates two fixed inputs with a deterministic,
+bundled public baseline. It does not contact AgenticDome, load tenant policy,
+execute tools, or instantiate CrewAI. The framework option is a label and guide
+selector, not a CrewAI integration test.
 
 ## Attach in production
 
@@ -27,6 +29,11 @@ export AGENTICDOME_API_KEY="your-runtime-sdk-key"
 export AGENTICDOME_TENANT_ID="your-tenant-id"
 ```
 
+Run `agenticdome-demo --framework crewai --scenario both --live` to obtain real
+tenant-engine decisions for those fixed inputs. That checks the assigned
+sidecar, not CrewAI attachment; the code below attaches the adapter to the real
+application boundary.
+
 For managed service, the API base is assigned in the selected supported
 geographic region, subject to availability. A contracted Sovereign runtime is
 inside the customer-controlled environment. Normal SDK calls do not require

{agenticdome_python_sdk-1.2.16 → agenticdome_python_sdk-1.2.17}/docs/frameworks/custom-python.md

@@ -12,6 +12,11 @@ export AGENTICDOME_MODE=local_sim
 agenticdome-demo --framework custom-python --scenario both
 ```
 
+**Demo scope:** this command evaluates two fixed inputs with a deterministic,
+bundled public baseline. It does not contact AgenticDome, load tenant policy,
+or execute either example tool. The framework option labels this core-client
+example; it is not a live application integration test.
+
 ## Attach in production
 
 Configure the assigned runtime first. The executor remains application-owned:
@@ -23,6 +28,11 @@ export AGENTICDOME_API_KEY="your-runtime-sdk-key"
 export AGENTICDOME_TENANT_ID="your-tenant-id"
 ```
 
+Run `agenticdome-demo --framework custom-python --scenario both --live` to
+obtain real tenant-engine decisions for those fixed inputs. That checks the
+assigned sidecar; the code below is what places the client at the application's
+real execution boundary.
+
 For managed service, the API base is assigned in the selected supported
 geographic region, subject to availability. A contracted Sovereign runtime is
 inside the customer-controlled environment. Normal SDK calls do not require