decisiontree

package

v0.0.2 Latest Latest Go to latest Published: Jan 1, 2026 License: MIT Imports: 2 Imported by: 0

Details

Valid go.mod file
Redistributable license
Tagged version
Stable version
Learn more about best practices

Repository

github.com/bgdnvk/clanker

Links

Open Source Insights

Documentation ¶

Overview ¶

Package decisiontree maps user intent to agent execution strategies.

Index ¶

type Node
type Tree
- func New() *Tree
- func (t *Tree) Traverse(query string, ctx *model.AgentContext) []*Node

Constants ¶

This section is empty.

Variables ¶

This section is empty.

Functions ¶

This section is empty.

Types ¶

type Node ¶

type Node struct {
	ID         string        `json:"id"`
	Name       string        `json:"name"`
	Condition  string        `json:"condition"`
	Action     string        `json:"action"`
	Priority   int           `json:"priority"`
	Children   []*Node       `json:"children"`
	AgentTypes []string      `json:"agent_types"`
	Parameters model.AWSData `json:"parameters"`
}

type Tree ¶

type Tree struct {
	Root        *Node
	CurrentPath []string
	Decisions   []Node
}

func New ¶

func New() *Tree

New constructs the default decision tree, wiring root children that match common observability scenarios.

func (*Tree) Traverse ¶

func (t *Tree) Traverse(query string, ctx *model.AgentContext) []*Node

Traverse walks the tree depth-first and returns every node whose condition matches the query/context. The returned slice (applicable nodes) is fed to the coordinator to spawn agents, while CurrentPath/Decisions capture the rules that matched for auditing and metadata.

Source Files ¶

View all Source files

?	: This menu
/	: Search site
f or F	: Jump to
y or Y	: Canonical URL