perf(tools): cap propagated class names so deep oneOf-object chains stay linear

The oneOf perf fix left a second Θ(depth²): a deep oneOf chain whose branches
are named objects propagated an ever-growing ConsString as the class-name
base, which allocateClassName then re-materialized (.length/.slice) at every
level. A childClassName helper now caps the base AT PROPAGATION, so each level
is O(1) and the walk is linear; the collision counter still makes truncated
bases unique. Also reword the oneOf comment (it said `+` but the code uses a
template literal — both are ConsString) and strengthen the tests: the deep
oneOf test now runs 100k levels (a quadratic regression trips the 5s timeout),
plus a 60k oneOf-object chain and a >120-char tool-name cap case. py-types.ts
stays at 100% per-file coverage.
This commit is contained in:
Chinesezjc
2026-08-02 17:36:04 +08:00
parent b0e405a679
commit 345375747e
2 changed files with 61 additions and 12 deletions

View File

@@ -149,6 +149,19 @@ function allocateClassName(base: string, state: RenderState): string {
return name
}
/**
* Append a child-name segment to a parent class-name base, capping the result
* at {@link MAX_CLASS_NAME_BASE}. Capping AT PROPAGATION (not only inside
* {@link allocateClassName}) keeps each level O(1): a deep `oneOf`- or
* object-chain would otherwise carry an ever-growing ConsString down the tree
* and re-materialize it (via `.length`/`.slice`) at every level — Θ(depth²).
* The bounded base plus the collision counter still yields unique names.
*/
function childClassName(base: string, segment: string): string {
const joined = `${base}${segment}`
return joined.length > MAX_CLASS_NAME_BASE ? joined.slice(0, MAX_CLASS_NAME_BASE) : joined
}
/**
* Render one validated scalar as Python literal text (`True`/`False`,
* JSON-quoted strings, bare numbers). `null` cannot reach here: the `null`
@@ -259,12 +272,12 @@ function renderType(schema: unknown, className: string, state: RenderState): str
continue
}
if (frame.kind === 'oneOf') {
// Concatenate with `+` (not `Array.join`): V8 builds a lazy
// ConsString, so a deep oneOf chain materializes once at the root
// instead of re-materializing the accumulated string at every level
// (which `join` would, making it Θ(depth²)). This matches the array
// arm's template-literal laziness and ts-types' composable-document
// approach — the whole walk stays linear in schema depth.
// Concatenate incrementally (template literal, not `Array.join`): V8
// builds a lazy ConsString, so a deep oneOf chain materializes once
// at the root instead of re-materializing the accumulated string at
// every level (which `join` would, making it Θ(depth²)). This matches
// the array arm's template-literal laziness and ts-types' composable-
// document approach — the whole walk stays linear in schema depth.
let union = ''
for (const [index, childType] of frame.childTypes.entries()) {
union = index === 0 ? childType : `${union} | ${childType}`
@@ -324,7 +337,7 @@ function renderType(schema: unknown, className: string, state: RenderState): str
const node = frame.schema
if (node.oneOf !== undefined) {
frame.kind = 'oneOf'
frame.children = node.oneOf.map((branch, index) => ({ schema: branch, className: `${frame.className}${index + 1}` }))
frame.children = node.oneOf.map((branch, index) => ({ schema: branch, className: childClassName(frame.className, `${index + 1}`) }))
continue
}
if (node.type === undefined) {
@@ -383,7 +396,7 @@ function renderType(schema: unknown, className: string, state: RenderState): str
frame.entries = entries
// frame.allocated was assigned two statements up; the ?? arm is for the type system only.
/* v8 ignore next -- allocated is always set before children are built. */
frame.children = entries.map(([field, child]) => ({ schema: child, className: `${frame.allocated ?? ''}${camelCase(field)}` }))
frame.children = entries.map(([field, child]) => ({ schema: child, className: childClassName(frame.allocated ?? '', camelCase(field)) }))
break
}
/* v8 ignore next 4 -- assertSupportedJsonSchema narrowed this closed type union. */

View File

@@ -471,18 +471,54 @@ describe('renderToolsSdkPy', () => {
it('renders a deeply nested oneOf chain in linear time (no per-level re-materialization)', () => {
// Each level is a two-branch oneOf whose first branch recurses; joining the
// accumulated union string at every level would be Theta(depth^2). The `+`
// (ConsString) concatenation keeps it linear, like the array arm.
const depth = 20000
// accumulated union string at every level would be Theta(depth^2). At this
// depth the quadratic path (~100,000^2 char copies) blows past vitest's 5s
// default, so this fails loud on a regression; the `+`/ConsString path is
// milliseconds. (Guard the depth explicitly so the assertions stay exact.)
const depth = 100000
let deep: Record<string, unknown> = { type: 'string' }
for (let i = 0; i < depth; i++) deep = { oneOf: [deep, { type: 'null' }] }
const type = jsonSchemaToPy(deep)
// depth levels of ` | None` appended to the innermost `str`.
expect(type.startsWith('str | None')).toBe(true)
expect(type.endsWith(' | None')).toBe(true)
expect(type.length).toBe('str'.length + ' | None'.length * depth)
})
it('names a deep oneOf-of-object chain in linear time (bounded propagated class names)', () => {
// Every level is a oneOf whose first branch is a closed empty object (a
// named TypedDict) and recurses. Propagating the full ancestor path as the
// class name and slicing it in allocateClassName at every level would be
// Theta(depth^2); childClassName caps the propagated base so it stays
// linear. The quadratic path at this depth exceeds the 5s default.
const depth = 60000
let deep: Record<string, unknown> = { type: 'object', additionalProperties: false, properties: {} }
for (let i = 0; i < depth; i++) {
deep = { oneOf: [deep, { type: 'null' }] }
}
const tool: ToolSdkSchema = { name: 'deep', description: 'Deep oneOf-object chain.', parameters: { type: 'object', additionalProperties: false, properties: { root: deep }, required: ['root'] }, output: { type: 'string' } }
const text = renderToolsSdkPy([tool])
// No emitted class name exceeds the cap (plus a short collision suffix).
const longest = [...text.matchAll(/^class (\w+)\(TypedDict\):/gm)].reduce((max, m) => Math.max(max, m[1]?.length ?? 0), 0)
expect(longest).toBeLessThanOrEqual(140)
expect(text).toContain('class Tools(Protocol):')
})
it('caps the class name for a tool whose name exceeds the base length limit', () => {
// The root class base is `${CamelCase(name)}Args`; a very long tool name
// makes it exceed MAX_CLASS_NAME_BASE, so allocateClassName caps it.
const longName = `x_${'a'.repeat(200)}`
const tool: ToolSdkSchema = {
name: longName,
description: 'Long name.',
parameters: { type: 'object', additionalProperties: false, properties: { f: { type: 'string' } }, required: ['f'] },
output: { type: 'string' },
}
const text = renderToolsSdkPy([tool])
const longest = [...text.matchAll(/^class (\w+)\(TypedDict\):/gm)].reduce((max, m) => Math.max(max, m[1]?.length ?? 0), 0)
expect(longest).toBeLessThanOrEqual(140)
expect(text).toContain('class Tools(Protocol):')
})
it('emits pass for a subscript-only tool set (comments are not statements)', () => {
const t: ToolSdkSchema = {
name: 'my-exotic.tool',