Skip to content

Conversation

@evalstate
Copy link
Owner

Implements an iterable tool runner pattern similar to Anthropic's SDK, allowing users to iterate over each LLM response in the tool call loop.

Features:

  • ToolRunner class with async iterator support
  • until_done() convenience method for simple cases
  • Advanced API for modifying requests between iterations
  • Breaking early from the loop
  • Inspecting pending tool responses

New files:

  • src/fast_agent/agents/tool_runner.py - Main ToolRunner implementation
  • examples/tool-runner/tool_runner_example.py - Usage examples

Implements an iterable tool runner pattern similar to Anthropic's SDK,
allowing users to iterate over each LLM response in the tool call loop.

Features:
- ToolRunner class with async iterator support
- until_done() convenience method for simple cases
- Advanced API for modifying requests between iterations
- Breaking early from the loop
- Inspecting pending tool responses

New files:
- src/fast_agent/agents/tool_runner.py - Main ToolRunner implementation
- examples/tool-runner/tool_runner_example.py - Usage examples
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants