PraisonAI 4.6.164__tar.gz → 4.7.0__tar.gz

{praisonai-4.6.164 → praisonai-4.7.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: PraisonAI
-Version: 4.6.164
+Version: 4.7.0
 Summary: PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent collaboration.
 Author: Mervin Praison
 License: MIT
@@ -11,14 +11,14 @@ Description-Content-Type: text/markdown
 Requires-Dist: rich>=13.7
 Requires-Dist: markdown>=3.5
 Requires-Dist: pyparsing>=3.0.0
-Requires-Dist: praisonaiagents>=1.6.168
-Requires-Dist: praisonai-code>=0.0.64
-Requires-Dist: praisonai-bot>=0.0.49
-Requires-Dist: praisonai-train>=0.0.19
-Requires-Dist: praisonai-browser>=0.0.15
-Requires-Dist: praisonai-mcp>=0.0.15
-Requires-Dist: praisonai-sandbox>=0.0.13
-Requires-Dist: praisonai-deploy>=0.0.8
+Requires-Dist: praisonaiagents>=1.7.0
+Requires-Dist: praisonai-code>=0.1.0
+Requires-Dist: praisonai-bot>=0.1.0
+Requires-Dist: praisonai-train>=0.1.0
+Requires-Dist: praisonai-browser>=0.1.0
+Requires-Dist: praisonai-mcp>=0.1.0
+Requires-Dist: praisonai-sandbox>=0.1.0
+Requires-Dist: praisonai-deploy>=0.1.0
 Requires-Dist: python-dotenv>=0.19.0
 Requires-Dist: litellm<2,>=1.83.14
 Requires-Dist: PyYAML>=6.0
@@ -69,9 +69,14 @@ Provides-Extra: ssh
 Requires-Dist: praisonai-sandbox[ssh]; extra == "ssh"
 Provides-Extra: modal
 Requires-Dist: praisonai-sandbox[modal]; extra == "modal"
+Provides-Extra: e2b
+Requires-Dist: praisonai-sandbox[e2b]; extra == "e2b"
+Provides-Extra: docker
+Requires-Dist: praisonai-sandbox[docker]; extra == "docker"
 Provides-Extra: daytona
+Requires-Dist: praisonai-sandbox[daytona]; extra == "daytona"
 Provides-Extra: tenki
-Requires-Dist: tenki>=0.5.4; extra == "tenki"
+Requires-Dist: praisonai-sandbox[tenki]; extra == "tenki"
 Provides-Extra: realtime
 Requires-Dist: aiui<0.4,>=0.3.121; extra == "realtime"
 Requires-Dist: tavily-python==0.5.0; extra == "realtime"
@@ -337,7 +342,7 @@ Each layer wraps the one inside it. When an agent misbehaves, the layer tells yo
 | **3 · Harness** | Can it act, and be checked? | `tools=`, `MCP()`, `guardrails=`, `approval=`, `hooks=`, `sandbox=` |
 | **4 · Loop** | When do we stop? | `execution=ExecutionConfig(...)`, `reflection=`, `autonomy=`, doom-loop detection |
 | **5 · Graph** | Who runs when, and who checks whom? | `AgentFlow`, `route()`, `parallel()`, `loop()`, `repeat()` |
-| **⬡ Managed** | *Where does it actually run?* | `run_on="docker"` — one shared remote sandbox, or a fully hosted loop |
+| **⬡ Managed** | *Where does it actually run?* | `tools_run_on="docker"` — one shared sandbox for the tools, or `run_on="anthropic"` for the whole agent |
 
 ### Layer 1 · Prompt — *Did I say it clearly?*
 
@@ -442,7 +447,7 @@ The harness is commoditising; **where** the agent executes is the next multiplie
 pip install praisonai
 ```
 
-The simplest way in is `run_on=` — one whole team or workflow shares **one** sandbox, so a file written by step 1 is there for step 2:
+The simplest way in is `tools_run_on=` — one whole team or workflow shares **one** sandbox, so a file written by step 1 is there for step 2. Thinking stays on your machine:
 
 ```python
 from praisonaiagents import Agent, AgentFlow
@@ -450,7 +455,7 @@ from praisonaiagents import Agent, AgentFlow
 writer = Agent(name="Writer", instructions="You write files.")
 reader = Agent(name="Reader", instructions="You read files.")
 
-flow = AgentFlow(run_on="docker", steps=[writer, reader])   # or e2b | modal | daytona | flyio
+flow = AgentFlow(tools_run_on="docker", steps=[writer, reader])  # or e2b | modal | daytona | flyio
 flow.run("Write 'hello' to /workspace/note.txt, then read it back")
 ```
 
@@ -458,7 +463,7 @@ Same thing with no Python at all:
 
 ```yaml
 name: remote-demo
-run_on: docker            # every step shares one sandbox
+tools_run_on: docker      # every step shares one sandbox
 agents:
   writer: {role: Writer, goal: Write files}
   reader: {role: Reader, goal: Read files}
@@ -469,22 +474,51 @@ steps:
     action: "Read /workspace/note.txt"
 ```
 
-For a single agent, pick the axis you need — remote **tools** or a remote **loop**:
+For a single agent, two words cover it — and they answer different questions:
 
 ```python
-from praisonai import Agent, LocalAgent, LocalAgentConfig, HostedAgent
+from praisonaiagents import Agent
 
-# A. Tools run in a remote sandbox; the agent loop stays local
-agent = Agent(name="builder", backend=LocalAgent(
-    compute="e2b",                     # or modal | daytona | flyio | docker | tenki
-    config=LocalAgentConfig(model="gpt-4o-mini", name="RemoteTools"),
-))
+# A. Only the TOOLS move. Thinking stays on your machine.
+agent = Agent(name="builder", instructions="You build things.",
+              tools_run_on="docker")   # docker | e2b | modal | daytona | flyio
+                                       # tenki | sandlock | ssh | novita | subprocess
 
-# B. The entire agent loop runs in the cloud (needs ANTHROPIC_API_KEY)
-agent = Agent(name="teacher", backend=HostedAgent(provider="anthropic"))
+# B. The WHOLE agent moves — model calls, loop and tools
+agent = Agent(name="teacher", instructions="You teach.", run_on="anthropic")  # hosted
+agent = Agent(name="builder", instructions="You build.", run_on="docker")     # self-hosted
 agent.start("Write a Python script that prints the first 10 primes, then run it")
 ```
 
+Ask any object where it runs, and it will tell you:
+
+```python
+>>> Agent(name="builder", instructions="x", tools_run_on="docker")
+Agent(name='builder', thinks_on='this machine', tools_run_on='a Docker container')
+
+>>> agent.where_does_it_run()
+Thinking (the AI model calls) happens on this machine.
+Tools run on a Docker container.
+Your own tools (check_db) still run on this machine -- only shell, file and
+code tools move. They read and write this machine's files.
+```
+
+Naming a place that cannot do the job is a typo, not a preference, so it says so:
+
+```python
+>>> Agent(name="x", instructions="i", run_on="e2b")
+TypeError: Agent(run_on='e2b') is not valid: run_on= places the whole agent
+-- model calls, loop and tools -- on a managed runtime, and 'e2b' runs
+commands but cannot host an agent loop.
+  To run only the tools there:  Agent(tools_run_on='e2b')
+```
+
+To run one block of code somewhere else, name the place on that call:
+
+```python
+agent.execute_code_sync("print(6 * 7)", run_in="sandlock")   # kernel-enforced
+```
+
 See what is running and reclaim strays:
 
 ```bash

{praisonai-4.6.164 → praisonai-4.7.0}/PraisonAI.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: PraisonAI
-Version: 4.6.164
+Version: 4.7.0
 Summary: PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent collaboration.
 Author: Mervin Praison
 License: MIT
@@ -11,14 +11,14 @@ Description-Content-Type: text/markdown
 Requires-Dist: rich>=13.7
 Requires-Dist: markdown>=3.5
 Requires-Dist: pyparsing>=3.0.0
-Requires-Dist: praisonaiagents>=1.6.168
-Requires-Dist: praisonai-code>=0.0.64
-Requires-Dist: praisonai-bot>=0.0.49
-Requires-Dist: praisonai-train>=0.0.19
-Requires-Dist: praisonai-browser>=0.0.15
-Requires-Dist: praisonai-mcp>=0.0.15
-Requires-Dist: praisonai-sandbox>=0.0.13
-Requires-Dist: praisonai-deploy>=0.0.8
+Requires-Dist: praisonaiagents>=1.7.0
+Requires-Dist: praisonai-code>=0.1.0
+Requires-Dist: praisonai-bot>=0.1.0
+Requires-Dist: praisonai-train>=0.1.0
+Requires-Dist: praisonai-browser>=0.1.0
+Requires-Dist: praisonai-mcp>=0.1.0
+Requires-Dist: praisonai-sandbox>=0.1.0
+Requires-Dist: praisonai-deploy>=0.1.0
 Requires-Dist: python-dotenv>=0.19.0
 Requires-Dist: litellm<2,>=1.83.14
 Requires-Dist: PyYAML>=6.0
@@ -69,9 +69,14 @@ Provides-Extra: ssh
 Requires-Dist: praisonai-sandbox[ssh]; extra == "ssh"
 Provides-Extra: modal
 Requires-Dist: praisonai-sandbox[modal]; extra == "modal"
+Provides-Extra: e2b
+Requires-Dist: praisonai-sandbox[e2b]; extra == "e2b"
+Provides-Extra: docker
+Requires-Dist: praisonai-sandbox[docker]; extra == "docker"
 Provides-Extra: daytona
+Requires-Dist: praisonai-sandbox[daytona]; extra == "daytona"
 Provides-Extra: tenki
-Requires-Dist: tenki>=0.5.4; extra == "tenki"
+Requires-Dist: praisonai-sandbox[tenki]; extra == "tenki"
 Provides-Extra: realtime
 Requires-Dist: aiui<0.4,>=0.3.121; extra == "realtime"
 Requires-Dist: tavily-python==0.5.0; extra == "realtime"
@@ -337,7 +342,7 @@ Each layer wraps the one inside it. When an agent misbehaves, the layer tells yo
 | **3 · Harness** | Can it act, and be checked? | `tools=`, `MCP()`, `guardrails=`, `approval=`, `hooks=`, `sandbox=` |
 | **4 · Loop** | When do we stop? | `execution=ExecutionConfig(...)`, `reflection=`, `autonomy=`, doom-loop detection |
 | **5 · Graph** | Who runs when, and who checks whom? | `AgentFlow`, `route()`, `parallel()`, `loop()`, `repeat()` |
-| **⬡ Managed** | *Where does it actually run?* | `run_on="docker"` — one shared remote sandbox, or a fully hosted loop |
+| **⬡ Managed** | *Where does it actually run?* | `tools_run_on="docker"` — one shared sandbox for the tools, or `run_on="anthropic"` for the whole agent |
 
 ### Layer 1 · Prompt — *Did I say it clearly?*
 
@@ -442,7 +447,7 @@ The harness is commoditising; **where** the agent executes is the next multiplie
 pip install praisonai
 ```
 
-The simplest way in is `run_on=` — one whole team or workflow shares **one** sandbox, so a file written by step 1 is there for step 2:
+The simplest way in is `tools_run_on=` — one whole team or workflow shares **one** sandbox, so a file written by step 1 is there for step 2. Thinking stays on your machine:
 
 ```python
 from praisonaiagents import Agent, AgentFlow
@@ -450,7 +455,7 @@ from praisonaiagents import Agent, AgentFlow
 writer = Agent(name="Writer", instructions="You write files.")
 reader = Agent(name="Reader", instructions="You read files.")
 
-flow = AgentFlow(run_on="docker", steps=[writer, reader])   # or e2b | modal | daytona | flyio
+flow = AgentFlow(tools_run_on="docker", steps=[writer, reader])  # or e2b | modal | daytona | flyio
 flow.run("Write 'hello' to /workspace/note.txt, then read it back")
 ```
 
@@ -458,7 +463,7 @@ Same thing with no Python at all:
 
 ```yaml
 name: remote-demo
-run_on: docker            # every step shares one sandbox
+tools_run_on: docker      # every step shares one sandbox
 agents:
   writer: {role: Writer, goal: Write files}
   reader: {role: Reader, goal: Read files}
@@ -469,22 +474,51 @@ steps:
     action: "Read /workspace/note.txt"
 ```
 
-For a single agent, pick the axis you need — remote **tools** or a remote **loop**:
+For a single agent, two words cover it — and they answer different questions:
 
 ```python
-from praisonai import Agent, LocalAgent, LocalAgentConfig, HostedAgent
+from praisonaiagents import Agent
 
-# A. Tools run in a remote sandbox; the agent loop stays local
-agent = Agent(name="builder", backend=LocalAgent(
-    compute="e2b",                     # or modal | daytona | flyio | docker | tenki
-    config=LocalAgentConfig(model="gpt-4o-mini", name="RemoteTools"),
-))
+# A. Only the TOOLS move. Thinking stays on your machine.
+agent = Agent(name="builder", instructions="You build things.",
+              tools_run_on="docker")   # docker | e2b | modal | daytona | flyio
+                                       # tenki | sandlock | ssh | novita | subprocess
 
-# B. The entire agent loop runs in the cloud (needs ANTHROPIC_API_KEY)
-agent = Agent(name="teacher", backend=HostedAgent(provider="anthropic"))
+# B. The WHOLE agent moves — model calls, loop and tools
+agent = Agent(name="teacher", instructions="You teach.", run_on="anthropic")  # hosted
+agent = Agent(name="builder", instructions="You build.", run_on="docker")     # self-hosted
 agent.start("Write a Python script that prints the first 10 primes, then run it")
 ```
 
+Ask any object where it runs, and it will tell you:
+
+```python
+>>> Agent(name="builder", instructions="x", tools_run_on="docker")
+Agent(name='builder', thinks_on='this machine', tools_run_on='a Docker container')
+
+>>> agent.where_does_it_run()
+Thinking (the AI model calls) happens on this machine.
+Tools run on a Docker container.
+Your own tools (check_db) still run on this machine -- only shell, file and
+code tools move. They read and write this machine's files.
+```
+
+Naming a place that cannot do the job is a typo, not a preference, so it says so:
+
+```python
+>>> Agent(name="x", instructions="i", run_on="e2b")
+TypeError: Agent(run_on='e2b') is not valid: run_on= places the whole agent
+-- model calls, loop and tools -- on a managed runtime, and 'e2b' runs
+commands but cannot host an agent loop.
+  To run only the tools there:  Agent(tools_run_on='e2b')
+```
+
+To run one block of code somewhere else, name the place on that call:
+
+```python
+agent.execute_code_sync("print(6 * 7)", run_in="sandlock")   # kernel-enforced
+```
+
 See what is running and reclaim strays:
 
 ```bash

{praisonai-4.6.164 → praisonai-4.7.0}/PraisonAI.egg-info/SOURCES.txt

@@ -332,6 +332,7 @@ praisonai/integrations/backend_registry.py
 praisonai/integrations/base.py
 praisonai/integrations/claude_code.py
 praisonai/integrations/codex_cli.py
+praisonai/integrations/compute_managed_agent.py
 praisonai/integrations/cursor_cli.py
 praisonai/integrations/db_session_adapter.py
 praisonai/integrations/gemini_cli.py
@@ -342,6 +343,7 @@ praisonai/integrations/managed_local.py
 praisonai/integrations/registry.py
 praisonai/integrations/sandboxed_agent.py
 praisonai/integrations/compute/__init__.py
+praisonai/integrations/compute/_sync_base.py
 praisonai/integrations/compute/daytona.py
 praisonai/integrations/compute/docker.py
 praisonai/integrations/compute/e2b.py

praisonai-4.7.0/PraisonAI.egg-info/entry_points.txt

@@ -0,0 +1,18 @@
+[console_scripts]
+praisonai = praisonai.__main__:main
+praisonai-call = praisonai.api.call:main
+setup-conda-env = praisonai.setup.setup_conda_env:main
+
+[praisonai.endpoint_providers]
+a2a = praisonai.endpoints.providers.a2a:A2AProvider
+a2u = praisonai.endpoints.providers.a2u:A2UProvider
+agents-api = praisonai.endpoints.providers.agents_api:AgentsAPIProvider
+mcp = praisonai.endpoints.providers.mcp:MCPProvider
+openai-compat = praisonai.endpoints.providers.openai_compat:OpenAICompatProvider
+recipe = praisonai.endpoints.providers.recipe:RecipeProvider
+tools-mcp = praisonai.endpoints.providers.tools_mcp:ToolsMCPProvider
+
+[praisonai.framework_adapters]
+autogen = praisonai.framework_adapters.autogen_adapter:AutoGenFamilyAdapter
+autogen_v2 = praisonai.framework_adapters.autogen_adapter:AutoGenAdapter
+crewai = praisonai.framework_adapters.crewai_adapter:CrewAIAdapter

{praisonai-4.6.164 → praisonai-4.7.0}/PraisonAI.egg-info/requires.txt

@@ -1,14 +1,14 @@
 rich>=13.7
 markdown>=3.5
 pyparsing>=3.0.0
-praisonaiagents>=1.6.168
-praisonai-code>=0.0.64
-praisonai-bot>=0.0.49
-praisonai-train>=0.0.19
-praisonai-browser>=0.0.15
-praisonai-mcp>=0.0.15
-praisonai-sandbox>=0.0.13
-praisonai-deploy>=0.0.8
+praisonaiagents>=1.7.0
+praisonai-code>=0.1.0
+praisonai-bot>=0.1.0
+praisonai-train>=0.1.0
+praisonai-browser>=0.1.0
+praisonai-mcp>=0.1.0
+praisonai-sandbox>=0.1.0
+praisonai-deploy>=0.1.0
 python-dotenv>=0.19.0
 litellm<2,>=1.83.14
 PyYAML>=6.0
@@ -131,6 +131,7 @@ crewai>=0.157.0
 praisonai-tools>=0.1.0
 
 [daytona]
+praisonai-sandbox[daytona]
 
 [deploy]
 praisonai-deploy[all]
@@ -140,9 +141,15 @@ textual-dev>=1.0.0
 pytest>=7.0.0
 pytest-asyncio>=0.21.0
 
+[docker]
+praisonai-sandbox[docker]
+
 [dynamodb]
 boto3>=1.35.0
 
+[e2b]
+praisonai-sandbox[e2b]
+
 [flow]
 langflow>=1.0.0
 requests>=2.31.0
@@ -227,7 +234,7 @@ praisonai-sandbox[all]
 praisonai-sandbox[ssh]
 
 [tenki]
-tenki>=0.5.4
+praisonai-sandbox[tenki]
 
 [train]
 praisonai-train[llm]

{praisonai-4.6.164 → praisonai-4.7.0}/README.md

@@ -130,7 +130,7 @@ Each layer wraps the one inside it. When an agent misbehaves, the layer tells yo
 | **3 · Harness** | Can it act, and be checked? | `tools=`, `MCP()`, `guardrails=`, `approval=`, `hooks=`, `sandbox=` |
 | **4 · Loop** | When do we stop? | `execution=ExecutionConfig(...)`, `reflection=`, `autonomy=`, doom-loop detection |
 | **5 · Graph** | Who runs when, and who checks whom? | `AgentFlow`, `route()`, `parallel()`, `loop()`, `repeat()` |
-| **⬡ Managed** | *Where does it actually run?* | `run_on="docker"` — one shared remote sandbox, or a fully hosted loop |
+| **⬡ Managed** | *Where does it actually run?* | `tools_run_on="docker"` — one shared sandbox for the tools, or `run_on="anthropic"` for the whole agent |
 
 ### Layer 1 · Prompt — *Did I say it clearly?*
 
@@ -235,7 +235,7 @@ The harness is commoditising; **where** the agent executes is the next multiplie
 pip install praisonai
 ```
 
-The simplest way in is `run_on=` — one whole team or workflow shares **one** sandbox, so a file written by step 1 is there for step 2:
+The simplest way in is `tools_run_on=` — one whole team or workflow shares **one** sandbox, so a file written by step 1 is there for step 2. Thinking stays on your machine:
 
 ```python
 from praisonaiagents import Agent, AgentFlow
@@ -243,7 +243,7 @@ from praisonaiagents import Agent, AgentFlow
 writer = Agent(name="Writer", instructions="You write files.")
 reader = Agent(name="Reader", instructions="You read files.")
 
-flow = AgentFlow(run_on="docker", steps=[writer, reader])   # or e2b | modal | daytona | flyio
+flow = AgentFlow(tools_run_on="docker", steps=[writer, reader])  # or e2b | modal | daytona | flyio
 flow.run("Write 'hello' to /workspace/note.txt, then read it back")
 ```
 
@@ -251,7 +251,7 @@ Same thing with no Python at all:
 
 ```yaml
 name: remote-demo
-run_on: docker            # every step shares one sandbox
+tools_run_on: docker      # every step shares one sandbox
 agents:
   writer: {role: Writer, goal: Write files}
   reader: {role: Reader, goal: Read files}
@@ -262,22 +262,51 @@ steps:
     action: "Read /workspace/note.txt"
 ```
 
-For a single agent, pick the axis you need — remote **tools** or a remote **loop**:
+For a single agent, two words cover it — and they answer different questions:
 
 ```python
-from praisonai import Agent, LocalAgent, LocalAgentConfig, HostedAgent
+from praisonaiagents import Agent
 
-# A. Tools run in a remote sandbox; the agent loop stays local
-agent = Agent(name="builder", backend=LocalAgent(
-    compute="e2b",                     # or modal | daytona | flyio | docker | tenki
-    config=LocalAgentConfig(model="gpt-4o-mini", name="RemoteTools"),
-))
+# A. Only the TOOLS move. Thinking stays on your machine.
+agent = Agent(name="builder", instructions="You build things.",
+              tools_run_on="docker")   # docker | e2b | modal | daytona | flyio
+                                       # tenki | sandlock | ssh | novita | subprocess
 
-# B. The entire agent loop runs in the cloud (needs ANTHROPIC_API_KEY)
-agent = Agent(name="teacher", backend=HostedAgent(provider="anthropic"))
+# B. The WHOLE agent moves — model calls, loop and tools
+agent = Agent(name="teacher", instructions="You teach.", run_on="anthropic")  # hosted
+agent = Agent(name="builder", instructions="You build.", run_on="docker")     # self-hosted
 agent.start("Write a Python script that prints the first 10 primes, then run it")
 ```
 
+Ask any object where it runs, and it will tell you:
+
+```python
+>>> Agent(name="builder", instructions="x", tools_run_on="docker")
+Agent(name='builder', thinks_on='this machine', tools_run_on='a Docker container')
+
+>>> agent.where_does_it_run()
+Thinking (the AI model calls) happens on this machine.
+Tools run on a Docker container.
+Your own tools (check_db) still run on this machine -- only shell, file and
+code tools move. They read and write this machine's files.
+```
+
+Naming a place that cannot do the job is a typo, not a preference, so it says so:
+
+```python
+>>> Agent(name="x", instructions="i", run_on="e2b")
+TypeError: Agent(run_on='e2b') is not valid: run_on= places the whole agent
+-- model calls, loop and tools -- on a managed runtime, and 'e2b' runs
+commands but cannot host an agent loop.
+  To run only the tools there:  Agent(tools_run_on='e2b')
+```
+
+To run one block of code somewhere else, name the place on that call:
+
+```python
+agent.execute_code_sync("print(6 * 7)", run_in="sandlock")   # kernel-enforced
+```
+
 See what is running and reclaim strays:
 
 ```bash

{praisonai-4.6.164 → praisonai-4.7.0}/praisonai/__init__.py

@@ -217,8 +217,17 @@ def __getattr__(name):
 
     try:
         import praisonaiagents
-    except ModuleNotFoundError:
-        raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
+    except ModuleNotFoundError as e:
+        if e.name == "praisonaiagents":
+            # Genuinely not installed — this is a real attribute miss.
+            raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
+        # praisonaiagents IS installed but a transitive dep is missing.
+        # Surface the real cause instead of a misleading attribute error.
+        _praisonaiagents_import_error = e
+        raise AttributeError(
+            f"module {__name__!r} has no attribute {name!r}: praisonaiagents is "
+            f"installed but failed to import ({e})"
+        ) from e
     except ImportError as e:
         _praisonaiagents_import_error = e
         raise AttributeError(