Austin Welch

[feature request] boto3 bedrock_agent_runtime_client.invoke_inline_agent

2

**Is your feature request related to a problem? Please describe.** Support for bedrock agents (and inline agents) tracing

Inline Agents fails with Sonnet 3.5

1

`agents-and-function-calling/bedrock-agents/features-examples/15-invoke-inline-agents/inline-agent-api-usage.ipynb` fails with when attempting to use Sonnet 3.5 instead of Sonnet 3.0: ``` { "name": "EventStreamError", "message": "An error occurred (validationException) when calling the InvokeInlineAgent operation: Validation failed for...

DOC: OpenMemory with Claude Desktop (without OpenAI)

4

### Issue with current documentation: Is this possible currently?

Hi, do you have any benchmarks comparing the performance of the LLMs you support for browser tasks?

Hi, I'd like to submit a feature request for an `llms.txt` file. This is a new standard that LangChain, LangGraph, and many other libraries are adopting to standardize documentation and...

I'm using Composio with LangGraph and want to define tools using the App enum pattern: ```python composio_toolset = ComposioToolSet() tools = composio_toolset.get_tools(apps=[App.GOOGLEDRIVE]) ``` Currently, I need to provide an `entity_id`...

[Question] CodeAct Architectures

2

Hi, I'm curious how you see [CodeAct architectures](https://arxiv.org/abs/2402.01030) fitting into MCP? CodeAct has seen some recent buzz with the introduction of Manus and other chat agents which use it and...

Specify default messages

2

How can I prepopulate messages (e.g. a system message) so I don't need to paste them into the Studio UI each I test running my graph?

TypeError: Type is not JSON serializable: ModelMetaclass

1

Hi, I am using tool calling functions with dynamically created Pydantic BaseModel's as type hints. For example: ```python def configure_workout_plan_template(state: AgentState, config: dict) -> AgentState: num_weeks = config.get("configurable", {}).get("num_weeks", 4)...

Incorrect input token counting for Llama 3.2 with image inputs

3

### Describe the bug The boto3 bedrock-runtime client appears to incorrectly report input token counts for Llama 3.2 models when processing images. While other Bedrock models correctly report varying token...