Documentation
¶
Overview ¶
Package tsrender produces TypeScript declarations for agent capabilities.
Index ¶
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
func RenderNestedRoot ¶
func RenderNestedRoot(root string, namespaces []NamespaceRender) string
RenderNestedRoot emits one declaration for a nested MCP or agent root.
func RenderToolDecls ¶
func RenderToolDecls(tools []ToolRender) string
RenderToolDecls emits a TypeScript .d.ts-style block describing each tool. Output is suitable for direct inclusion in an LLM prompt.
Types ¶
type MCPToolRender ¶
type MCPToolRender struct {
Path binding.Path
Name string
Description string
InputSchema json.RawMessage
}
MCPToolRender carries the bits Airlock has cached about an MCP tool. Only the input shape is typed — MCP doesn't define an output schema, so the rendered return type is always `unknown` (caller does runtime parsing).
type NamespaceRender ¶
type NamespaceRender struct {
Namespace string
Tools []MCPToolRender
}
NamespaceRender describes one namespace beneath an external capability root.
type ToolRender ¶
type ToolRender struct {
Path binding.Path
Name string
Description string
LLMHint string
InputSchema json.RawMessage
OutputSchema json.RawMessage
InputExamples []json.RawMessage
}
ToolRender is the data RenderToolDecls consumes. Airlock builds this from the hydrated DB/sync payload; the agent assembles it from the registered-tool schemas in tests. Both paths go through the same renderer so the LLM sees one format.
LLMHint is optional model-only guidance that pairs with Description (which may also surface in member-facing UIs). When non-empty it's appended to the JSDoc block in `[brackets]` so the LLM gets the extra steer without polluting the user-visible description.
Source Files