lionagi 0.14.7__tar.gz → 0.14.8__tar.gz

{lionagi-0.14.7 → lionagi-0.14.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: lionagi
-Version: 0.14.7
+Version: 0.14.8
 Summary: An Intelligence Operating System.
 Author-email: HaiyangLi <quantocean.li@gmail.com>, Liangbingyan Luo <llby_luo@outlook.com>
 License:            Apache License
@@ -295,7 +295,9 @@ integrations, and custom validations in a single coherent pipeline.
 ## Installation
 
 ```
-pip install lionagi
+uv add lionagi  # recommended to use pyproject and uv for dependency management
+
+pip install lionagi # or install directly
 ```
 
 ## Quick Start
@@ -304,12 +306,12 @@ pip install lionagi
 from lionagi import Branch, iModel
 
 # Pick a model
-gpt4o = iModel(provider="openai", model="gpt-4o")
+gpt41 = iModel(provider="openai", model="gpt-4.1-mini")
 
 # Create a Branch (conversation context)
 hunter = Branch(
   system="you are a hilarious dragon hunter who responds in 10 words rhymes.",
-  chat_model=gpt4o,
+  chat_model=gpt41,
 )
 
 # Communicate asynchronously
@@ -390,41 +392,75 @@ print(df.tail())
 ```python
 from lionagi import Branch, iModel
 
-gpt4o = iModel(provider="openai", model="gpt-4o")
 sonnet = iModel(
   provider="anthropic",
   model="claude-3-5-sonnet-20241022",
   max_tokens=1000,                    # max_tokens is required for anthropic models
 )
 
-branch = Branch(chat_model=gpt4o)
-# Switch mid-flow
-analysis = await branch.communicate("Analyze these stats", imodel=sonnet)
+branch = Branch(chat_model=gpt41)
+analysis = await branch.communicate("Analyze these stats", chat_model=sonnet) # Switch mid-flow
 ```
 
 Seamlessly route to different models in the same workflow.
 
 ### Claude Code Integration
 
-LionAGI now supports Anthropic's [Claude Code Python SDK](https://github.com/anthropics/claude-code-sdk-python), enabling autonomous coding capabilities with persistent session management:
+LionAGI now supports Anthropic's Claude Code [Python SDK](https://github.com/anthropics/claude-code-sdk-python), and [CLI SDK](https://docs.anthropic.com/en/docs/claude-code/sdk) enabling autonomous coding capabilities with persistent session management. The CLI endpoint
+directly connects to claude code, and is recommended, you can either use it via a [proxy server](https://github.com/khive-ai/lionagi/tree/main/cookbooks/claude_proxy) or directly with `query_cli` endpoint, provided you have already logged onto claude code cli in your terminal.
 
 ```python
 from lionagi import iModel, Branch
 
-# Create a Claude Code model
-model = iModel(
-    provider="claude_code",
-    endpoint="query_cli",
-    model="sonnet",
-    allowed_tools=["Write", "Read", "Edit"],  # Control which tools Claude can use
-    permission_mode = "bypassPermissions", # Bypass tool permission checks (use with caution!),
-    verbose_output=True,  # Enable detailed output for debugging
-)
+def create_cc_model():
+  return iModel(
+      provider="claude_code",
+      endpoint="query_cli",
+      model="sonnet",
+      verbose_output=True,  # Enable detailed output for debugging
+  )
 
 # Start a coding session
-branch = Branch(chat_model=model)
-response = await branch.communicate("Explain the architecture of protocols, operations, and branch")
-response2 = await branch.communicate("how do these parts form lionagi system")
+orchestrator = Branch(chat_model=create_cc_model())
+response = await orchestrator.communicate("Explain the architecture of protocols, operations, and branch")
+
+# continue the session with more queries
+response2 = await orchestrator.communicate("how do these parts form lionagi system")
+```
+
+### Fan out fan in pattern orchestration with claude code
+
+```python
+# use structured outputs with claude code
+from lionagi.fields import LIST_INSTRUCT_FIELD_MODEL, Instruct
+
+response3 = await orchestrator.operate(
+  instruct=Instruct(
+    instruction="create 4 research questions for parallel discovery",
+    guidance="put into `instruct_models` field as part of your structured result message",
+    context="I'd like to create an orchestration system for AI agents using lionagi"
+  ),
+  field_models=[LIST_INSTRUCT_FIELD_MODEL],
+)
+
+len(response3.instruct_models)  # should be 4
+
+async def handle_instruct(instruct):
+  sub_branch = Branch(
+    system="You are an diligent research expert.",
+    chat_model=create_cc_model(),
+  )
+  return await sub_branch.operate(instruct=instruct)
+
+# run in parallel across all instruct models
+from lionagi.utils import alcall
+responses = await alcall(response3.instruct_models, handle_instruct)
+
+# now hand these reports back to the orchestrator
+final_response = await orchestrator.communicate(
+  "please synthesize these research findings into a final report",
+  context=responses,
+)
 ```
 
 Key features:
@@ -436,9 +472,14 @@ Key features:
 ### optional dependencies
 
 ```
-pip install "lionagi[reader]"
-pip install "lionagi[ollama]"
-pip install "lionagi[claude-code]"
+"lionagi[reader]" - Reader tool for any unstructured data and web pages
+"lionagi[ollama]" - Ollama model support for local inference
+"lionagi[claude-code]" - Claude code python SDK integration (cli endpoint does not require this)
+"lionagi[rich]" - Rich output formatting for better console display
+"lionagi[schema]" - Convert pydantic schema to make the Model class persistent
+"lionagi[postgres]" - Postgres database support for storing and retrieving structured data
+"lionagi[graph]" - Graph display for visualizing complex workflows
+"lionagi[sqlite]" - SQLite database support for lightweight data storage (also need `postgres` option)
 ```
 
 ## Community & Contributing

{lionagi-0.14.7 → lionagi-0.14.8}/README.md

@@ -27,7 +27,9 @@ integrations, and custom validations in a single coherent pipeline.
 ## Installation
 
 ```
-pip install lionagi
+uv add lionagi  # recommended to use pyproject and uv for dependency management
+
+pip install lionagi # or install directly
 ```
 
 ## Quick Start
@@ -36,12 +38,12 @@ pip install lionagi
 from lionagi import Branch, iModel
 
 # Pick a model
-gpt4o = iModel(provider="openai", model="gpt-4o")
+gpt41 = iModel(provider="openai", model="gpt-4.1-mini")
 
 # Create a Branch (conversation context)
 hunter = Branch(
   system="you are a hilarious dragon hunter who responds in 10 words rhymes.",
-  chat_model=gpt4o,
+  chat_model=gpt41,
 )
 
 # Communicate asynchronously
@@ -122,41 +124,75 @@ print(df.tail())
 ```python
 from lionagi import Branch, iModel
 
-gpt4o = iModel(provider="openai", model="gpt-4o")
 sonnet = iModel(
   provider="anthropic",
   model="claude-3-5-sonnet-20241022",
   max_tokens=1000,                    # max_tokens is required for anthropic models
 )
 
-branch = Branch(chat_model=gpt4o)
-# Switch mid-flow
-analysis = await branch.communicate("Analyze these stats", imodel=sonnet)
+branch = Branch(chat_model=gpt41)
+analysis = await branch.communicate("Analyze these stats", chat_model=sonnet) # Switch mid-flow
 ```
 
 Seamlessly route to different models in the same workflow.
 
 ### Claude Code Integration
 
-LionAGI now supports Anthropic's [Claude Code Python SDK](https://github.com/anthropics/claude-code-sdk-python), enabling autonomous coding capabilities with persistent session management:
+LionAGI now supports Anthropic's Claude Code [Python SDK](https://github.com/anthropics/claude-code-sdk-python), and [CLI SDK](https://docs.anthropic.com/en/docs/claude-code/sdk) enabling autonomous coding capabilities with persistent session management. The CLI endpoint
+directly connects to claude code, and is recommended, you can either use it via a [proxy server](https://github.com/khive-ai/lionagi/tree/main/cookbooks/claude_proxy) or directly with `query_cli` endpoint, provided you have already logged onto claude code cli in your terminal.
 
 ```python
 from lionagi import iModel, Branch
 
-# Create a Claude Code model
-model = iModel(
-    provider="claude_code",
-    endpoint="query_cli",
-    model="sonnet",
-    allowed_tools=["Write", "Read", "Edit"],  # Control which tools Claude can use
-    permission_mode = "bypassPermissions", # Bypass tool permission checks (use with caution!),
-    verbose_output=True,  # Enable detailed output for debugging
-)
+def create_cc_model():
+  return iModel(
+      provider="claude_code",
+      endpoint="query_cli",
+      model="sonnet",
+      verbose_output=True,  # Enable detailed output for debugging
+  )
 
 # Start a coding session
-branch = Branch(chat_model=model)
-response = await branch.communicate("Explain the architecture of protocols, operations, and branch")
-response2 = await branch.communicate("how do these parts form lionagi system")
+orchestrator = Branch(chat_model=create_cc_model())
+response = await orchestrator.communicate("Explain the architecture of protocols, operations, and branch")
+
+# continue the session with more queries
+response2 = await orchestrator.communicate("how do these parts form lionagi system")
+```
+
+### Fan out fan in pattern orchestration with claude code
+
+```python
+# use structured outputs with claude code
+from lionagi.fields import LIST_INSTRUCT_FIELD_MODEL, Instruct
+
+response3 = await orchestrator.operate(
+  instruct=Instruct(
+    instruction="create 4 research questions for parallel discovery",
+    guidance="put into `instruct_models` field as part of your structured result message",
+    context="I'd like to create an orchestration system for AI agents using lionagi"
+  ),
+  field_models=[LIST_INSTRUCT_FIELD_MODEL],
+)
+
+len(response3.instruct_models)  # should be 4
+
+async def handle_instruct(instruct):
+  sub_branch = Branch(
+    system="You are an diligent research expert.",
+    chat_model=create_cc_model(),
+  )
+  return await sub_branch.operate(instruct=instruct)
+
+# run in parallel across all instruct models
+from lionagi.utils import alcall
+responses = await alcall(response3.instruct_models, handle_instruct)
+
+# now hand these reports back to the orchestrator
+final_response = await orchestrator.communicate(
+  "please synthesize these research findings into a final report",
+  context=responses,
+)
 ```
 
 Key features:
@@ -168,9 +204,14 @@ Key features:
 ### optional dependencies
 
 ```
-pip install "lionagi[reader]"
-pip install "lionagi[ollama]"
-pip install "lionagi[claude-code]"
+"lionagi[reader]" - Reader tool for any unstructured data and web pages
+"lionagi[ollama]" - Ollama model support for local inference
+"lionagi[claude-code]" - Claude code python SDK integration (cli endpoint does not require this)
+"lionagi[rich]" - Rich output formatting for better console display
+"lionagi[schema]" - Convert pydantic schema to make the Model class persistent
+"lionagi[postgres]" - Postgres database support for storing and retrieving structured data
+"lionagi[graph]" - Graph display for visualizing complex workflows
+"lionagi[sqlite]" - SQLite database support for lightweight data storage (also need `postgres` option)
 ```
 
 ## Community & Contributing

{lionagi-0.14.7 → lionagi-0.14.8}/lionagi/fields/instruct.py

@@ -11,7 +11,6 @@ from lionagi.libs.validate.common_field_validators import (
     validate_nullable_jsonvalue_field,
 )
 from lionagi.models import FieldModel, HashableModel
-from lionagi.utils import to_num
 
 __all__ = (
     "Instruct",

{lionagi-0.14.7 → lionagi-0.14.8}/lionagi/service/connections/providers/_claude_code/models.py

@@ -61,6 +61,7 @@ class ClaudeCodeRequest(BaseModel):
     max_thinking_tokens: int | None = None
     mcp_tools: list[str] = Field(default_factory=list)
     mcp_servers: dict[str, Any] = Field(default_factory=dict)
+    mcp_config: str | Path | None = Field(None, exclude=True)
     permission_mode: ClaudePermission | None = None
     permission_prompt_tool_name: str | None = None
     disallowed_tools: list[str] = Field(default_factory=list)
@@ -71,7 +72,7 @@ class ClaudeCodeRequest(BaseModel):
         description="Automatically finish the conversation after the first response",
     )
     verbose_output: bool = Field(default=False)
-    cli_display_theme: Literal["light", "dark"] = "light"
+    cli_display_theme: Literal["light", "dark"] = "dark"
 
     # ------------------------ validators & helpers --------------------------
     @field_validator("permission_mode", mode="before")
@@ -163,6 +164,15 @@ class ClaudeCodeRequest(BaseModel):
         if self.add_dir:
             args += ["--add-dir", self.add_dir]
 
+        if self.permission_prompt_tool_name:
+            args += [
+                "--permission-prompt-tool",
+                self.permission_prompt_tool_name,
+            ]
+
+        if self.mcp_config:
+            args += ["--mcp-config", str(self.mcp_config)]
+
         args += ["--model", self.model or "sonnet", "--verbose"]
         return args
 

lionagi-0.14.8/lionagi/version.py

@@ -0,0 +1 @@
+__version__ = "0.14.8"

{lionagi-0.14.7 → lionagi-0.14.8}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "lionagi"
-version = "0.14.7"
+version = "0.14.8"
 description = "An Intelligence Operating System."
 authors = [
     { name = "HaiyangLi", email = "quantocean.li@gmail.com" },

{lionagi-0.14.7 → lionagi-0.14.8}/uv.lock

@@ -1937,7 +1937,7 @@ wheels = [
 
 [[package]]
 name = "lionagi"
-version = "0.14.7"
+version = "0.14.8"
 source = { editable = "." }
 dependencies = [
     { name = "aiocache" },
@@ -2775,7 +2775,7 @@ name = "nvidia-cudnn-cu12"
 version = "9.5.1.17"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-cublas-cu12" },
+    { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/2a/78/4535c9c7f859a64781e43c969a3a7e84c54634e319a996d43ef32ce46f83/nvidia_cudnn_cu12-9.5.1.17-py3-none-manylinux_2_28_x86_64.whl", hash = "sha256:30ac3869f6db17d170e0e556dd6cc5eee02647abc31ca856634d5a40f82c15b2", size = 570988386, upload-time = "2024-10-25T19:54:26.39Z" },
@@ -2786,7 +2786,7 @@ name = "nvidia-cufft-cu12"
 version = "11.3.0.4"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-nvjitlink-cu12" },
+    { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/8f/16/73727675941ab8e6ffd86ca3a4b7b47065edcca7a997920b831f8147c99d/nvidia_cufft_cu12-11.3.0.4-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:ccba62eb9cef5559abd5e0d54ceed2d9934030f51163df018532142a8ec533e5", size = 200221632, upload-time = "2024-11-20T17:41:32.357Z" },
@@ -2815,9 +2815,9 @@ name = "nvidia-cusolver-cu12"
 version = "11.7.1.2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-cublas-cu12" },
-    { name = "nvidia-cusparse-cu12" },
-    { name = "nvidia-nvjitlink-cu12" },
+    { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "nvidia-cusparse-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
+    { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/f0/6e/c2cf12c9ff8b872e92b4a5740701e51ff17689c4d726fca91875b07f655d/nvidia_cusolver_cu12-11.7.1.2-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:e9e49843a7707e42022babb9bcfa33c29857a93b88020c4e4434656a655b698c", size = 158229790, upload-time = "2024-11-20T17:43:43.211Z" },
@@ -2829,7 +2829,7 @@ name = "nvidia-cusparse-cu12"
 version = "12.5.4.2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-nvjitlink-cu12" },
+    { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/06/1e/b8b7c2f4099a37b96af5c9bb158632ea9e5d9d27d7391d7eb8fc45236674/nvidia_cusparse_cu12-12.5.4.2-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:7556d9eca156e18184b94947ade0fba5bb47d69cec46bf8660fd2c71a4b48b73", size = 216561367, upload-time = "2024-11-20T17:44:54.824Z" },
@@ -5232,7 +5232,7 @@ name = "triton"
 version = "3.3.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "setuptools" },
+    { name = "setuptools", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/8d/a9/549e51e9b1b2c9b854fd761a1d23df0ba2fbc60bd0c13b489ffa518cfcb7/triton-3.3.1-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:b74db445b1c562844d3cfad6e9679c72e93fdfb1a90a24052b03bb5c49d1242e", size = 155600257, upload-time = "2025-05-29T23:39:36.085Z" },

lionagi-0.14.7/lionagi/version.py

@@ -1 +0,0 @@
-__version__ = "0.14.7"