Directories
¶
| Path | Synopsis |
|---|---|
|
agent
|
|
|
basic
command
Command basic demonstrates the smallest stateful agent: one tool, one prompt.
|
Command basic demonstrates the smallest stateful agent: one tool, one prompt. |
|
hooks
command
Command hooks demonstrates the agent's interception points: a policy gate that blocks a tool (BeforeToolCall), an annotation applied to results (AfterToolCall), a model switch between turns across wire protocols (PrepareNextTurn), and a turn guard (ShouldStopAfterTurn).
|
Command hooks demonstrates the agent's interception points: a policy gate that blocks a tool (BeforeToolCall), an annotation applied to results (AfterToolCall), a model switch between turns across wire protocols (PrepareNextTurn), and a turn guard (ShouldStopAfterTurn). |
|
tool
command
Command tool demonstrates an interactive stateful agent with tool use.
|
Command tool demonstrates an interactive stateful agent with tool use. |
|
llm
|
|
|
complete
command
Command complete demonstrates the smallest non-streaming model request.
|
Command complete demonstrates the smallest non-streaming model request. |
|
image
command
Command image sends a local image to a multimodal model.
|
Command image sends a local image to a multimodal model. |
|
model-switching
command
Command model-switching reuses one provider-neutral conversation across two models that speak different wire protocols.
|
Command model-switching reuses one provider-neutral conversation across two models that speak different wire protocols. |
|
stream
command
Command stream demonstrates incremental reasoning and text events.
|
Command stream demonstrates incremental reasoning and text events. |
|
tool
command
Command tool demonstrates a complete typed-tool execution loop.
|
Command tool demonstrates a complete typed-tool execution loop. |
Click to show internal directories.
Click to hide internal directories.