Reorganize packages into a modular hierarchy
Move the 18 flat packages/<name> packages into role-grouped dirs: core/, llm/, bash/, session-persistence/, ui/, support/. Group dirs are pure containers; each package keeps its @deepseek-ai/dsh-* name. Collapse the per-package tsconfig paths maps (base + typecheck) into one @deepseek-ai/dsh-* wildcard with a candidate per group, and derive the publint list from the hierarchy. Update all depth-coupled globs/configs (workspace, tsdown, vitest, eslint, knip, tsconfig includes/refs, per-package tsconfigs, generators, doc-script scopes, type-equiv manifest) and the cross-package/script relative imports in tests. Fix doc-typecheck's workspacePaths() to parse tsconfig JSONC via the TypeScript API instead of a regex comment-strip, which corrupted the new wildcard `/*/` path candidates. WIP: doc cross-links and package/RFC docs still to update.
This commit is contained in:
Tianyi Cui
@@ -0,0 +1,376 @@
|
||||
/**
|
||||
* Tool registry and execution waterfall. Plugins register tools; the registry
|
||||
* feeds schemas into the system prompt, and `execute()` dispatches each call
|
||||
* through the `tools/execute` waterfall for sandbox, permission, and hook
|
||||
* plugins to wrap or veto.
|
||||
*
|
||||
* @module @deepseek-ai/dsh-tools
|
||||
*/
|
||||
|
||||
import { Context, Service } from 'cordis'
|
||||
import type { CallId, ContentBlock, ToolSchema } from '@deepseek-ai/dsh-llm'
|
||||
import { HarnessError } from '@deepseek-ai/dsh-llm'
|
||||
import type { Agent } from '@deepseek-ai/dsh-agent'
|
||||
import type {} from '@deepseek-ai/dsh-system-prompt'
|
||||
|
||||
export {
|
||||
defineTool,
|
||||
schemaSpecToJsonSchema,
|
||||
validateArgs,
|
||||
ToolArgsError,
|
||||
type SchemaSpec,
|
||||
type SchemaProp,
|
||||
type SchemaType,
|
||||
type InferArgs,
|
||||
type DefineToolOptions,
|
||||
type JsonSchemaObject,
|
||||
} from './schema.ts'
|
||||
|
||||
declare module 'cordis' {
|
||||
interface Context {
|
||||
tools: ToolRegistry
|
||||
}
|
||||
|
||||
interface Events {
|
||||
/**
|
||||
* Waterfall around every tool execution — the single seam where sandbox,
|
||||
* permission, hook, and plan-mode plugins wrap or veto a call. Listeners
|
||||
* receive `(exec, next)`: call `next()` to proceed (possibly around your
|
||||
* own logic), or return a {@link ToolExecutionResult} without calling
|
||||
* `next()` to short-circuit (veto).
|
||||
* @mode waterfall
|
||||
*/
|
||||
'tools/execute'(this: ToolRegistry, exec: ToolExecution, next: () => Promise<ToolExecutionResult>): Promise<ToolExecutionResult>
|
||||
/**
|
||||
* A tool was registered or unregistered (the available tool set changed).
|
||||
* @mode emit
|
||||
*/
|
||||
'tools/change'(): void
|
||||
}
|
||||
}
|
||||
|
||||
// TODO(review): revisit these shapes when the first real tools and
|
||||
// sandbox/permission plugins land (e.g. a concurrency-safety hint for
|
||||
// parallel execution — Claude Code partitions read-only tools; phase 1
|
||||
// executes sequentially).
|
||||
|
||||
/**
|
||||
* Category of a tool call, used by a UI to pick an icon / treatment. A neutral
|
||||
* vocabulary owned here (NOT an ACP type) so tools describe themselves without
|
||||
* depending on any client protocol; a UI bridge maps it to its own enum. The
|
||||
* member set mirrors the common ACP `ToolKind` values; `other` is the default.
|
||||
*/
|
||||
export type ToolCallKind = 'read' | 'edit' | 'delete' | 'move' | 'search' | 'execute' | 'fetch' | 'other'
|
||||
|
||||
// FIXME(tool-presentation): the ToolCallPresentation / ToolResultPresentation /
|
||||
// ToolTerminal shapes need a rethink. They grew incrementally (title/kind/
|
||||
// rawInput, then a `content` block, then a `terminal` sub-shape carrying cwd/
|
||||
// output/exit) and the split of responsibility is now muddy: the call vs result
|
||||
// terminal fields overlap, the bridge has to reconcile a `content` block AND a
|
||||
// `terminal` block AND `rawInput` per call, and the "pending vs completed"
|
||||
// boundary doesn't cleanly map to how editors actually render (terminal card,
|
||||
// diff, generic card). Before more tools/UIs depend on this, redesign the type
|
||||
// so a tool declares its render INTENT once (e.g. a tagged union over card
|
||||
// kinds) rather than a bag of optional fields the bridge stitches together.
|
||||
// Pin the design in an RFC and migrate dsh-tool-bash + the ACP bridge together.
|
||||
|
||||
/**
|
||||
* How a tool wants ONE of its calls shown in a UI (an editor's tool-call card,
|
||||
* a CLI log line) BEFORE the result is known — the *pending* state. Provider-
|
||||
* neutral: a tool returns this from {@link ToolDefinition.presentCall} and a UI
|
||||
* plugin (e.g. the ACP bridge) maps it to its own wire shape. The tool owns its
|
||||
* own presentation — the UI must not special-case tool names.
|
||||
*/
|
||||
export interface ToolCallPresentation {
|
||||
/**
|
||||
* Human-readable, always-visible label describing what THIS call does (e.g.
|
||||
* the model-written one-line summary of a bash command). Keep it short — a UI
|
||||
* shows it as a card header / log line. Required: a presentation must have a
|
||||
* title (a UI falls back to the tool name only when `presentCall` is absent).
|
||||
*/
|
||||
title: string
|
||||
/** Category for icon/treatment; defaults to `other` when omitted. */
|
||||
kind?: ToolCallKind
|
||||
/**
|
||||
* The salient input to surface in a detail/expanded view — e.g. the bash
|
||||
* COMMAND itself (as a string), so the title can stay a readable summary
|
||||
* while the exact command is still visible. Omit to show nothing; a string is
|
||||
* rendered as-is, an object as pretty JSON. NOT the full raw args object
|
||||
* unless that is genuinely what a reader wants.
|
||||
*/
|
||||
rawInput?: unknown
|
||||
/**
|
||||
* UI-facing content to show on the PENDING call alongside the title/card —
|
||||
* harness {@link ContentBlock}s, in render order. A terminal tool uses this to
|
||||
* surface its human-readable `description` as a text block ABOVE the terminal
|
||||
* card (the card itself is requested via {@link terminal} and labelled by the
|
||||
* command in `title`), since the card has no description slot. Omit to show no
|
||||
* extra content. A UI maps these to its own content blocks and renders a
|
||||
* {@link terminal} block (if any) as a terminal card.
|
||||
*/
|
||||
content?: ContentBlock[]
|
||||
/**
|
||||
* Ask a capable UI to render this call as a TERMINAL (a command running in a
|
||||
* working directory), not a generic tool card — set by a tool whose call IS a
|
||||
* shell command (e.g. `bash`). Provider-neutral; a UI bridge maps it to its
|
||||
* own terminal affordance and a UI that can't falls back to the normal card.
|
||||
* Pair with {@link ToolResultPresentation.terminal} for the output/exit.
|
||||
*/
|
||||
terminal?: ToolTerminal
|
||||
}
|
||||
|
||||
/**
|
||||
* A request to render a tool call as a terminal. The pending presentation
|
||||
* supplies the working directory; the result presentation (see
|
||||
* {@link ToolResultPresentation.terminal}) supplies the captured output and exit
|
||||
* status. Provider-neutral — no client-protocol types. A UI that supports
|
||||
* terminals shows a cwd-headed terminal card with the command, its output, and
|
||||
* an exit-status pill; a UI that does not ignores this and renders the ordinary
|
||||
* card/content.
|
||||
*/
|
||||
export interface ToolTerminal {
|
||||
/**
|
||||
* Working directory the command ran in, shown as the terminal header. An
|
||||
* ABSOLUTE path is used as-is; a RELATIVE path is resolved by the UI bridge
|
||||
* against the session workspace (the pure tool presenter can't see the
|
||||
* session cwd). Omit entirely to let the bridge use the session workspace.
|
||||
*/
|
||||
cwd?: string
|
||||
/** Captured command output (stdout+stderr as the tool chooses to combine them). Result-state only. */
|
||||
output?: string
|
||||
/**
|
||||
* Process exit code, when the run ended by exiting (not a signal). Result-state
|
||||
* only; lets a capable UI show an exit-status pill on the terminal card. Omit
|
||||
* when the command was killed by a signal or the exit code is unknown.
|
||||
*/
|
||||
exitCode?: number
|
||||
/**
|
||||
* Signal name that killed the process (e.g. `SIGTERM`), when it died by signal
|
||||
* rather than exiting. Result-state only; mutually exclusive with `exitCode`.
|
||||
*/
|
||||
signal?: string
|
||||
}
|
||||
|
||||
/**
|
||||
* How a tool wants the COMPLETED call shown — the *result* state, after
|
||||
* `execute` returns. Lets the tool reformat its result for a UI distinctly from
|
||||
* the model-facing text it returned from `execute` (e.g. wrap command output in
|
||||
* a fenced ```console block for monospace rendering, which the model-facing
|
||||
* result must NOT carry). All fields optional: a UI keeps the pending-state
|
||||
* title and renders the raw result content for anything left unset.
|
||||
*/
|
||||
export interface ToolResultPresentation {
|
||||
/** Replacement title for the completed call (e.g. append an exit status). Omit to keep the pending-state title. */
|
||||
title?: string
|
||||
/**
|
||||
* UI-facing result content (harness {@link ContentBlock}s), reformatted from
|
||||
* the model-facing result. Omit to let the UI render the raw result content.
|
||||
* Stays in harness vocabulary; the UI maps these to its own content blocks.
|
||||
*/
|
||||
content?: ContentBlock[]
|
||||
/**
|
||||
* Terminal output/exit for a call the pending presentation marked as a
|
||||
* terminal (see {@link ToolCallPresentation.terminal}). A capable UI renders
|
||||
* `output` in the terminal card and shows the exit status; an incapable UI
|
||||
* uses `content` (the tool should supply a text fallback there too).
|
||||
*/
|
||||
terminal?: ToolTerminal
|
||||
}
|
||||
|
||||
/** A registered tool: its schema plus the execution function. */
|
||||
export interface ToolDefinition extends ToolSchema {
|
||||
execute(args: unknown, exec: ToolExecution): Promise<ContentBlock[]>
|
||||
/**
|
||||
* Optional: how to present the PENDING state of one call in a UI, derived
|
||||
* from the call's `args` (parsed arguments, `unknown` — the tool validates/
|
||||
* narrows its own input). Returning `undefined` (or omitting the method) tells
|
||||
* a UI to fall back to a generic presentation (title = tool name, raw args as
|
||||
* input). Pure and side-effect-free: a UI may call it during live streaming
|
||||
* AND a session-log replay, so it must depend only on `args`.
|
||||
*/
|
||||
presentCall?(args: unknown): ToolCallPresentation | undefined
|
||||
/**
|
||||
* Optional: how to present the COMPLETED state, given the same `args` and the
|
||||
* `result` (`execute`'s content + whether it errored). Returning `undefined`
|
||||
* (or omitting the method) tells a UI to keep the pending title and render the
|
||||
* raw result content. Pure and side-effect-free for the same replay reason.
|
||||
*/
|
||||
presentResult?(args: unknown, result: ToolResult): ToolResultPresentation | undefined
|
||||
}
|
||||
|
||||
/** The completed outcome handed to {@link ToolDefinition.presentResult}. */
|
||||
export interface ToolResult {
|
||||
/** The model-facing content `execute` returned (or the error text on failure). */
|
||||
content: ContentBlock[]
|
||||
/** Whether the call failed. */
|
||||
isError: boolean
|
||||
}
|
||||
|
||||
/** One pending tool call, as it flows through the execution waterfall. */
|
||||
export interface ToolExecution {
|
||||
callId: CallId
|
||||
name: string
|
||||
/** Parsed JSON arguments (unknown — tools validate their own input). */
|
||||
arguments: unknown
|
||||
/** The agent on whose behalf the call runs (set by the agent loop). */
|
||||
agent?: Agent
|
||||
signal?: AbortSignal
|
||||
}
|
||||
|
||||
/** Structured error metadata for a failed tool call (alongside the model-facing text). */
|
||||
export interface ToolErrorInfo {
|
||||
name: string
|
||||
code: string
|
||||
}
|
||||
|
||||
/**
|
||||
* Thrown (internally) when the model requests a tool that isn't registered.
|
||||
* Extends {@link HarnessError} (`code: 'UNKNOWN_TOOL'`) so an unknown-tool
|
||||
* failure is as routable as a tool-thrown one — retry/sandbox/replay code can
|
||||
* distinguish it from a tool body's own error.
|
||||
*/
|
||||
export class ToolNotFoundError extends HarnessError {
|
||||
constructor(public readonly toolName: string) {
|
||||
super(`unknown tool "${toolName}"`, 'UNKNOWN_TOOL')
|
||||
this.name = 'ToolNotFoundError'
|
||||
}
|
||||
}
|
||||
|
||||
/** The outcome of one tool call. */
|
||||
export interface ToolExecutionResult {
|
||||
callId: CallId
|
||||
content: ContentBlock[]
|
||||
isError: boolean
|
||||
/**
|
||||
* Set when the call failed with a {@link HarnessError}: machine-routable
|
||||
* `{ name, code }` for retry/sandbox plugins and replay. The model-facing
|
||||
* text in `content` is always present; this is extra structure for code.
|
||||
*/
|
||||
error?: ToolErrorInfo
|
||||
}
|
||||
|
||||
/**
|
||||
* Best-effort human-readable message from an arbitrary thrown value: Error
|
||||
* instances use `.message`; non-Error objects with a string `message`
|
||||
* property (e.g. `throw { message: 'denied' }`) use it too; everything else
|
||||
* is stringified.
|
||||
*/
|
||||
function errorMessage(error: unknown): string {
|
||||
if (error instanceof Error) return error.message
|
||||
if (typeof error === 'object' && error !== null
|
||||
&& 'message' in error && typeof error.message === 'string') {
|
||||
return error.message
|
||||
}
|
||||
return String(error)
|
||||
}
|
||||
|
||||
/** Structured `{ name, code }` for a thrown HarnessError, else undefined. */
|
||||
function errorInfo(error: unknown): ToolErrorInfo | undefined {
|
||||
return error instanceof HarnessError ? { name: error.name, code: error.code } : undefined
|
||||
}
|
||||
|
||||
/**
|
||||
* Tool registry (`ctx.tools`): tool plugins register definitions; the agent
|
||||
* loop executes calls through the `tools/execute` waterfall. The registry
|
||||
* contributes its schemas into the system-prompt assembly.
|
||||
*/
|
||||
export class ToolRegistry extends Service {
|
||||
static inject = ['systemPrompt']
|
||||
|
||||
private store = new Map<string, ToolDefinition>()
|
||||
|
||||
constructor(ctx: Context) {
|
||||
super(ctx, 'tools')
|
||||
ctx.systemPrompt.tools(() => this.schemas())
|
||||
}
|
||||
|
||||
/**
|
||||
* Register a tool. Throws if a tool with the same name is already
|
||||
* registered. The tool's schema (minus the `execute` function) is
|
||||
* automatically contributed to the system-prompt assembly. Disposed
|
||||
* with the calling fiber. Emits `tools/change` on register/unregister.
|
||||
*/
|
||||
register(definition: ToolDefinition): () => void {
|
||||
const dispose = this.ctx.effect(function* (this: ToolRegistry) {
|
||||
if (this.store.has(definition.name)) {
|
||||
throw new Error(`tool "${definition.name}" is already registered`)
|
||||
}
|
||||
this.store.set(definition.name, definition)
|
||||
// Yield the rollback BEFORE emitting `tools/change`: a generator effect
|
||||
// collects each yielded disposer before the next step runs, so a throwing
|
||||
// `tools/change` listener removes the tool instead of leaking it (a leak
|
||||
// would wedge the duplicate-name check until restart). The duplicate
|
||||
// throw above fires before any mutation — it leaks nothing.
|
||||
yield () => {
|
||||
this.store.delete(definition.name)
|
||||
this.ctx.emit('tools/change')
|
||||
}
|
||||
this.ctx.emit('tools/change')
|
||||
}.bind(this), 'tools.register()')
|
||||
// ctx.effect's disposer returns Promise<void>; our disposer API is
|
||||
// synchronous fire-and-forget — discard the (always-resolved) promise.
|
||||
return () => void dispose()
|
||||
}
|
||||
|
||||
get(name: string): ToolDefinition | undefined {
|
||||
return this.store.get(name)
|
||||
}
|
||||
|
||||
/**
|
||||
* Return all registered tool schemas — exactly the model-facing fields
|
||||
* (`name`, `description`, `parameters`, and `strict` when set), as sent to the
|
||||
* model via the system-prompt assembly. Constructed EXPLICITLY rather than by
|
||||
* stripping known non-schema members: a `ToolDefinition` also carries
|
||||
* `execute` and the optional `presentCall`/`presentResult` UI callbacks, and
|
||||
* those (especially the functions) must never leak into a model request. An
|
||||
* allowlist can't drift when a new non-schema member is added to the
|
||||
* definition; a denylist (rest-destructure) would silently leak it.
|
||||
*/
|
||||
schemas(): ToolSchema[] {
|
||||
return [...this.store.values()].map(({ name, description, parameters, strict }): ToolSchema => ({
|
||||
name,
|
||||
description,
|
||||
parameters: structuredClone(parameters),
|
||||
...strict !== undefined ? { strict } : {},
|
||||
}))
|
||||
}
|
||||
|
||||
/**
|
||||
* Execute one tool call through the `tools/execute` waterfall. If the tool is
|
||||
* not registered, the result is an `isError` carrying a `UNKNOWN_TOOL`
|
||||
* structured error. If the tool or a waterfall listener throws, the error is
|
||||
* caught and returned as an `isError` result so the loop records a failed tool
|
||||
* call instead of failing the whole turn; a thrown {@link HarnessError}
|
||||
* surfaces its `{ name, code }` on the result.
|
||||
*/
|
||||
async execute(exec: ToolExecution): Promise<ToolExecutionResult> {
|
||||
try {
|
||||
return await this.ctx.waterfall(this, 'tools/execute', exec, async (): Promise<ToolExecutionResult> => {
|
||||
try {
|
||||
const tool = this.store.get(exec.name)
|
||||
// Unknown tool routes through the same catch as a tool-thrown error, so
|
||||
// both failure classes get structured `{ name, code }` from one path.
|
||||
if (!tool) throw new ToolNotFoundError(exec.name)
|
||||
const content = await tool.execute(exec.arguments, exec)
|
||||
return { callId: exec.callId, content, isError: false }
|
||||
} catch (error: unknown) {
|
||||
return toolErrorResult(exec.callId, error)
|
||||
}
|
||||
})
|
||||
} catch (error: unknown) {
|
||||
return toolErrorResult(exec.callId, error)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
function toolErrorResult(callId: ToolExecution['callId'], error: unknown): ToolExecutionResult {
|
||||
const info = errorInfo(error)
|
||||
return {
|
||||
callId,
|
||||
content: [{ type: 'text', text: `Error: ${errorMessage(error)}` }],
|
||||
isError: true,
|
||||
...info ? { error: info } : {},
|
||||
}
|
||||
}
|
||||
|
||||
export default ToolRegistry
|
||||
@@ -0,0 +1,384 @@
|
||||
/**
|
||||
* Typed tool-parameter schema DSL.
|
||||
*
|
||||
* Plugin authors write per-property specs with `required: true` as a boolean
|
||||
* (the `SchemaSpec` type). A type-level helper (`InferArgs`) maps a SchemaSpec
|
||||
* to the TS argument type. At runtime, `schemaSpecToJsonSchema()` converts a
|
||||
* SchemaSpec to standard JSON Schema (`type: 'object'`, `properties`,
|
||||
* `required` array) for the wire format sent to the model.
|
||||
*
|
||||
* # Why a custom DSL and not schemastery?
|
||||
*
|
||||
* Schemastery is a validation/transformation library (StandardSchema v1) used
|
||||
* for plugin Config. Tool parameters need JSON Schema specifically (the LLM
|
||||
* wire format), not validation. A lightweight DSL focused on JSON Schema
|
||||
* generation, with type inference for the tool's `execute` args, gives plugin
|
||||
* authors the best DX with the smallest surface area. Schemastery would add
|
||||
* unnecessary indirection and wouldn't cleanly produce JSON Schema.
|
||||
*
|
||||
* @module dsh-tools/schema
|
||||
*/
|
||||
|
||||
import type { ContentBlock } from '@deepseek-ai/dsh-llm'
|
||||
import { assertNever, HarnessError } from '@deepseek-ai/dsh-llm'
|
||||
import type { ToolCallPresentation, ToolDefinition, ToolExecution, ToolResult, ToolResultPresentation } from './index.ts'
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// SchemaSpec — the author-facing per-property type
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
/** Valid JSON Schema primitive types for tool parameters. */
|
||||
export type SchemaType = 'string' | 'number' | 'boolean' | 'object' | 'array'
|
||||
|
||||
/** One schema-spec property entry. */
|
||||
export interface SchemaProp {
|
||||
type: SchemaType
|
||||
/** Per-property required flag (NOT the JSON Schema top-level required array). */
|
||||
required?: true
|
||||
/** Human-readable description, surfaced in the JSON Schema as well. */
|
||||
description?: string
|
||||
/** Enum of allowed values (strings only). */
|
||||
enum?: string[]
|
||||
/**
|
||||
* Default value, emitted into the JSON Schema only (validation never applies
|
||||
* it — see the validator note below).
|
||||
*
|
||||
* XXX(unused-default): no tool definition in the repo sets `default`; it rides
|
||||
* into the wire schema for a model that no tool surfaces it to. Drop the field
|
||||
* and its converter line unless a real tool needs a model-visible default.
|
||||
*/
|
||||
default?: unknown
|
||||
/** Nested properties for type: 'object'. */
|
||||
properties?: SchemaSpec
|
||||
/** Items schema for type: 'array'. */
|
||||
items?: SchemaProp
|
||||
}
|
||||
|
||||
/**
|
||||
* The author-facing parameter schema: a shallow map of property name to
|
||||
* {@link SchemaProp}. Required-ness is a per-property boolean (`required:
|
||||
* true`), not a separate array.
|
||||
*/
|
||||
export type SchemaSpec = Record<string, SchemaProp>
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// InferArgs — type-level mapping from SchemaSpec to TS argument type
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
/** Map a {@link SchemaType} to its TS primitive type. */
|
||||
type TypeOf<T extends SchemaType> =
|
||||
T extends 'string' ? string :
|
||||
T extends 'number' ? number :
|
||||
T extends 'boolean' ? boolean :
|
||||
T extends 'object' ? Record<string, unknown> :
|
||||
T extends 'array' ? unknown[] :
|
||||
never
|
||||
|
||||
/** Flatten an intersection into one object type for readable hovers. */
|
||||
type Simplify<T> = { [K in keyof T]: T[K] } & {}
|
||||
|
||||
/** Keys of `S` whose prop is marked `required: true`. */
|
||||
type RequiredKeys<S extends SchemaSpec> =
|
||||
{ [K in keyof S]: S[K] extends { required: true } ? K : never }[keyof S]
|
||||
|
||||
/**
|
||||
* The VALUE type of one {@link SchemaProp} — optionality is handled at the
|
||||
* key level by {@link InferArgs}, never here.
|
||||
* - `properties` on 'object' → recurse into the nested SchemaSpec
|
||||
* - `items` on 'array' → recurse into the item prop (arrays of objects work)
|
||||
* - otherwise → the primitive for `type`
|
||||
*/
|
||||
type InferPropValue<P extends SchemaProp> =
|
||||
P extends { type: 'object'; properties: infer Sub extends SchemaSpec } ? InferArgs<Sub> :
|
||||
P extends { type: 'array'; items: infer Item extends SchemaProp } ? InferPropValue<Item>[] :
|
||||
TypeOf<P['type']>
|
||||
|
||||
/**
|
||||
* Infer the TS argument type for a complete {@link SchemaSpec}.
|
||||
*
|
||||
* Properties marked `required: true` are required keys; all others are
|
||||
* genuinely optional keys (`?`), so callers may omit them entirely.
|
||||
*
|
||||
* Example:
|
||||
* ```ts
|
||||
* type Args = InferArgs<{ path: { type: 'string'; required: true }; limit: { type: 'number' } }>
|
||||
* // → { path: string; limit?: number }
|
||||
* ```
|
||||
*/
|
||||
export type InferArgs<S extends SchemaSpec> = Simplify<
|
||||
& { [K in RequiredKeys<S>]: InferPropValue<S[K]> }
|
||||
& { [K in Exclude<keyof S, RequiredKeys<S>>]?: InferPropValue<S[K]> }
|
||||
>
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// Runtime conversion: SchemaSpec → JSON Schema
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
/**
|
||||
* Convert a single {@link SchemaProp} to its JSON Schema `properties` entry.
|
||||
* The per-property `required` flag is collected; the caller builds the
|
||||
* top-level `required` array.
|
||||
*/
|
||||
function propToJsonSchema(prop: SchemaProp): { schema: Record<string, unknown>; required: boolean } {
|
||||
const result: Record<string, unknown> = { type: prop.type }
|
||||
if (prop.description) result.description = prop.description
|
||||
if (prop.enum) result.enum = prop.enum
|
||||
if (prop.default !== undefined) result.default = prop.default
|
||||
|
||||
const required = prop.required === true
|
||||
|
||||
if (prop.type === 'object' && prop.properties) {
|
||||
const nested = schemaSpecToJsonSchema(prop.properties)
|
||||
result.properties = nested.properties
|
||||
if (nested.required && nested.required.length > 0) {
|
||||
result.required = nested.required
|
||||
}
|
||||
}
|
||||
|
||||
if (prop.type === 'array' && prop.items) {
|
||||
const { schema: itemsSchema } = propToJsonSchema(prop.items)
|
||||
result.items = itemsSchema
|
||||
}
|
||||
|
||||
return { schema: result, required }
|
||||
}
|
||||
|
||||
/** The return type of {@link schemaSpecToJsonSchema}. */
|
||||
export interface JsonSchemaObject {
|
||||
type: 'object'
|
||||
properties: Record<string, unknown>
|
||||
required?: string[]
|
||||
}
|
||||
|
||||
/**
|
||||
* Convert a {@link SchemaSpec} to standard JSON Schema (`type: 'object'`,
|
||||
* `properties`, `required` array).
|
||||
*
|
||||
* This is a plain function — no schemastery or other framework dependency.
|
||||
*/
|
||||
export function schemaSpecToJsonSchema(spec: SchemaSpec): JsonSchemaObject {
|
||||
const properties: Record<string, unknown> = {}
|
||||
const required: string[] = []
|
||||
|
||||
for (const [key, prop] of Object.entries(spec)) {
|
||||
const { schema, required: isRequired } = propToJsonSchema(prop)
|
||||
properties[key] = schema
|
||||
if (isRequired) required.push(key)
|
||||
}
|
||||
|
||||
const result: JsonSchemaObject = {
|
||||
type: 'object',
|
||||
properties,
|
||||
}
|
||||
if (required.length > 0) result.required = required
|
||||
|
||||
return result
|
||||
}
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// Runtime validation: model-generated args ↔ SchemaSpec
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
/**
|
||||
* Thrown by a {@link defineTool} tool when the model-generated arguments don't
|
||||
* match the declared {@link SchemaSpec}. Extends {@link HarnessError}
|
||||
* (`code: 'INVALID_ARGS'`); the registry's execute waterfall catches it and
|
||||
* returns an `isError` ToolExecutionResult carrying the structured error, so
|
||||
* the model can self-correct and downstream plugins can route on the code.
|
||||
*/
|
||||
export class ToolArgsError extends HarnessError {
|
||||
/** The individual violation messages, in declaration order. */
|
||||
readonly violations: string[]
|
||||
|
||||
constructor(violations: string[]) {
|
||||
super(`invalid arguments: ${violations.join('; ')}`, 'INVALID_ARGS')
|
||||
this.name = 'ToolArgsError'
|
||||
this.violations = violations
|
||||
}
|
||||
}
|
||||
|
||||
/** Whether a value is a non-null, non-array object (a JSON Schema `object`). */
|
||||
function isPlainObject(value: unknown): value is Record<string, unknown> {
|
||||
return typeof value === 'object' && value !== null && !Array.isArray(value)
|
||||
}
|
||||
|
||||
/** Collect violations for one property value against its {@link SchemaProp}. */
|
||||
function checkValue(prop: SchemaProp, value: unknown, path: string): string[] {
|
||||
switch (prop.type) {
|
||||
case 'string': {
|
||||
if (typeof value !== 'string') return [`"${path}" must be a string`]
|
||||
break
|
||||
}
|
||||
case 'number': {
|
||||
if (typeof value !== 'number') return [`"${path}" must be a number`]
|
||||
break
|
||||
}
|
||||
case 'boolean': {
|
||||
if (typeof value !== 'boolean') return [`"${path}" must be a boolean`]
|
||||
break
|
||||
}
|
||||
case 'object': {
|
||||
if (!isPlainObject(value)) return [`"${path}" must be an object`]
|
||||
// Mirror the converter: an object without `properties` only type-checks.
|
||||
return prop.properties ? checkSpec(prop.properties, value, path) : []
|
||||
}
|
||||
case 'array': {
|
||||
if (!Array.isArray(value)) return [`"${path}" must be an array`]
|
||||
// Mirror the converter: an array without `items` only type-checks.
|
||||
if (!prop.items) return []
|
||||
const items = prop.items
|
||||
return value.flatMap((el, i) => checkValue(items, el, `${path}[${i}]`))
|
||||
}
|
||||
default: return assertNever(prop.type, 'validateArgs')
|
||||
}
|
||||
// Enum membership, checked uniformly: the converter emits `enum` for any
|
||||
// type ([prop.enum]), so the validator must too. `enum` is `string[]`, so a
|
||||
// non-string value can never be a member — it falls out here, consistent
|
||||
// with the schema the model was given.
|
||||
if (prop.enum && !(prop.enum as unknown[]).includes(value)) {
|
||||
return [`"${path}" must be one of ${JSON.stringify(prop.enum)}`]
|
||||
}
|
||||
return []
|
||||
}
|
||||
|
||||
/** Collect violations for an object value against a {@link SchemaSpec}. */
|
||||
function checkSpec(spec: SchemaSpec, value: unknown, path: string): string[] {
|
||||
if (!isPlainObject(value)) return [`"${path || 'arguments'}" must be an object`]
|
||||
const violations: string[] = []
|
||||
for (const [key, prop] of Object.entries(spec)) {
|
||||
const propPath = path ? `${path}.${key}` : key
|
||||
const v = value[key]
|
||||
if (v === undefined) {
|
||||
// A required key absent OR present-but-undefined is a violation; an
|
||||
// optional absent key is fine. `default` is NOT applied (validation only).
|
||||
if (prop.required === true) violations.push(`missing required property "${propPath}"`)
|
||||
continue
|
||||
}
|
||||
violations.push(...checkValue(prop, v, propPath))
|
||||
}
|
||||
return violations
|
||||
}
|
||||
|
||||
/**
|
||||
* Validate model-generated `args` against a {@link SchemaSpec}, returning a
|
||||
* list of human-readable violation messages (empty = valid). Total — never
|
||||
* throws, regardless of how malformed `args` is.
|
||||
*
|
||||
* Semantics mirror {@link schemaSpecToJsonSchema} exactly: the top level must
|
||||
* be a non-array object; required keys come only from `required: true`; extra
|
||||
* keys are allowed (no `additionalProperties: false`); `default` is not
|
||||
* applied; an `object`/`array` prop without `properties`/`items` only
|
||||
* type-checks; `enum` is membership (strings only).
|
||||
*/
|
||||
export function validateArgs(spec: SchemaSpec, args: unknown): string[] {
|
||||
return checkSpec(spec, args, '')
|
||||
}
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// defineTool — typed helper for first-party plugin authors
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
/** Options for {@link defineTool}. */
|
||||
export interface DefineToolOptions<S extends SchemaSpec> {
|
||||
/** Tool name (must be unique). */
|
||||
name: string
|
||||
/** Human-readable description sent to the model. */
|
||||
description: string
|
||||
/**
|
||||
* Parameter schema using the per-property-required DSL. Converted to
|
||||
* standard JSON Schema at runtime.
|
||||
*/
|
||||
parameters: S
|
||||
/**
|
||||
* Tool execution function. `args` is typed as {@link InferArgs<S>} — zero
|
||||
* casts needed.
|
||||
*/
|
||||
execute(args: InferArgs<S>, exec: ToolExecution): Promise<ContentBlock[]>
|
||||
/**
|
||||
* Optional: how to present the PENDING state of one call in a UI (an editor
|
||||
* tool-call card, a CLI log line). `args` is the typed, schema-validated
|
||||
* argument shape — zero casts. Pure and side-effect-free: a UI may call it
|
||||
* during live streaming AND a session-log replay, so depend only on `args`.
|
||||
* The tool owns its presentation so a UI never special-cases tool names. See
|
||||
* {@link ToolCallPresentation}.
|
||||
*/
|
||||
presentCall?(args: InferArgs<S>): ToolCallPresentation | undefined
|
||||
/**
|
||||
* Optional: how to present the COMPLETED state, given the typed `args` and the
|
||||
* `result`. Use it to reformat result content for a UI distinctly from the
|
||||
* model-facing text (e.g. a fenced ```console block). Pure and side-effect-
|
||||
* free for the same replay reason. See {@link ToolResultPresentation}.
|
||||
*/
|
||||
presentResult?(args: InferArgs<S>, result: ToolResult): ToolResultPresentation | undefined
|
||||
/** Whether the tool requires structured output (default false). */
|
||||
strict?: boolean
|
||||
}
|
||||
|
||||
/**
|
||||
* Define a tool with a typed parameter schema.
|
||||
*
|
||||
* Use this instead of constructing a raw {@link ToolDefinition} for all
|
||||
* first-party tools. The `parameters` use the boolean-required style
|
||||
* (`required: true` as a per-property flag), and `execute` receives typed
|
||||
* args derived from the schema.
|
||||
*
|
||||
* ```ts
|
||||
* const tool = defineTool({
|
||||
* name: 'read_file',
|
||||
* description: 'Read a file from disk.',
|
||||
* parameters: {
|
||||
* path: { type: 'string', required: true, description: 'Absolute file path' },
|
||||
* offset: { type: 'number' },
|
||||
* limit: { type: 'number', description: 'Max lines to read' },
|
||||
* },
|
||||
* async execute(args) {
|
||||
* // args: { path: string; offset?: number; limit?: number }
|
||||
* },
|
||||
* })
|
||||
* ```
|
||||
*
|
||||
* Raw JSON-Schema tool definitions (from MCP servers) are still accepted
|
||||
* by `ToolRegistry.register()` directly — `defineTool` is sugar for
|
||||
* first-party plugin authors.
|
||||
*/
|
||||
export function defineTool<S extends SchemaSpec>(options: DefineToolOptions<S>): ToolDefinition {
|
||||
// Object-literal execute methods don't use `this`; the reference is safe.
|
||||
// eslint-disable-next-line @typescript-eslint/unbound-method
|
||||
const userExecute = options.execute
|
||||
// eslint-disable-next-line @typescript-eslint/unbound-method
|
||||
const userPresentCall = options.presentCall
|
||||
// eslint-disable-next-line @typescript-eslint/unbound-method
|
||||
const userPresentResult = options.presentResult
|
||||
const tool: ToolDefinition = {
|
||||
name: options.name,
|
||||
description: options.description,
|
||||
parameters: schemaSpecToJsonSchema(options.parameters) as unknown as Record<string, unknown>,
|
||||
...options.strict !== undefined ? { strict: options.strict } : {},
|
||||
async execute(args: unknown, exec: ToolExecution): Promise<ContentBlock[]> {
|
||||
// Validate the model-generated args before the typed body runs. On
|
||||
// mismatch we throw ToolArgsError; the registry turns it into an
|
||||
// isError result so the model can self-correct. After this guard, the
|
||||
// cast to InferArgs<S> reflects the validated shape.
|
||||
const violations = validateArgs(options.parameters, args)
|
||||
if (violations.length > 0) throw new ToolArgsError(violations)
|
||||
return userExecute(args as InferArgs<S>, exec)
|
||||
},
|
||||
}
|
||||
// Presentation is display-only and may run on REPLAY of arbitrary logged args
|
||||
// (possibly from an older schema), so it must never throw: validate softly and
|
||||
// fall back to `undefined` (a generic UI presentation) on any mismatch, rather
|
||||
// than the hard `ToolArgsError` the execute path raises.
|
||||
if (userPresentCall) {
|
||||
tool.presentCall = (args: unknown): ToolCallPresentation | undefined => {
|
||||
if (validateArgs(options.parameters, args).length > 0) return undefined
|
||||
return userPresentCall(args as InferArgs<S>)
|
||||
}
|
||||
}
|
||||
if (userPresentResult) {
|
||||
tool.presentResult = (args: unknown, result: ToolResult): ToolResultPresentation | undefined => {
|
||||
if (validateArgs(options.parameters, args).length > 0) return undefined
|
||||
return userPresentResult(args as InferArgs<S>, result)
|
||||
}
|
||||
}
|
||||
return tool
|
||||
}
|
||||
Reference in New Issue
Block a user