From 5d65686c33c43c2716aae043ac5aafbadce7d5e8 Mon Sep 17 00:00:00 2001 From: Chinesezjc Date: Wed, 5 Aug 2026 20:03:39 +0800 Subject: [PATCH] feat(tools): accept Unicode Python identifiers in the Python SDK renderer MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The identifier test was ASCII-only, so an object with a `路径` field degraded to dict[str, Any] -- dropping every sibling field's name, requiredness and type, with no native schema behind it in Code Mode to carry them. Python identifiers are `xid_start xid_continue*`, so match that instead, and widen camelCase's split and head check to the same sets (naming `_` explicitly in the split, since it is XID_Continue). NFKC stability is a second and separate condition. CPython normalizes identifiers at compile time while a JSON key is compared as written, so a U+FB01 ligature key would be declared and reachable under its ASCII expansion, a key the tool never accepts, and two keys that normalize together would collapse into one declaration. Those names take the subscript path. Generated class names are normalized instead of rejected -- they are never matched against a key. Astral characters can now reach the class-name cap, whose slice counts UTF-16 code units, so drop a split surrogate half. Also fix two comment claims. The note said one projection reads the runtime twice per tool; the language-aware getters are installed on run_code's own definition, so it is twice, both for that schema. And the 182-bracket site's reachability is an array reached from the root through oneOf arms alone -- a union spine of any depth, not just one root union; an object ancestor restarts the chain at the 181 site. --- ...7-31-code-mode-language-dispatch.i18n.yaml | 4 +- .../2026-07-31-code-mode-language-dispatch.md | 2 +- ...26-07-31-code-mode-language-dispatch.zh.md | 2 +- packages/core/tools/src/py-types.ts | 75 ++++++++-- packages/core/tools/tests/py-types.spec.ts | 130 ++++++++++++++++-- 5 files changed, 187 insertions(+), 26 deletions(-) diff --git a/.agents/notes/implemented/feature/2026-07-31-code-mode-language-dispatch.i18n.yaml b/.agents/notes/implemented/feature/2026-07-31-code-mode-language-dispatch.i18n.yaml index e95ce168ca..d1977c65cc 100644 --- a/.agents/notes/implemented/feature/2026-07-31-code-mode-language-dispatch.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-31-code-mode-language-dispatch.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-31-code-mode-language-dispatch.md -2026-07-31-code-mode-language-dispatch.md: c2010ec368da82d8c41df8d00a8e32f0064afde3 -2026-07-31-code-mode-language-dispatch.zh.md: 3cc3bae8c683e8434f48dd251b9dd5dd580bc3ce +2026-07-31-code-mode-language-dispatch.md: b999150ae478eef5396e5456e33ffb041f1b161d +2026-07-31-code-mode-language-dispatch.zh.md: 12ef8197e64e9e8a435f852168ab791029534e7d diff --git a/.agents/notes/implemented/feature/2026-07-31-code-mode-language-dispatch.md b/.agents/notes/implemented/feature/2026-07-31-code-mode-language-dispatch.md index c2010ec368..b999150ae4 100644 --- a/.agents/notes/implemented/feature/2026-07-31-code-mode-language-dispatch.md +++ b/.agents/notes/implemented/feature/2026-07-31-code-mode-language-dispatch.md @@ -41,4 +41,4 @@ Adding a backend language is two table entries — an `SDK_RENDERERS` entry and The cost is that the Python branch of both tables is unreachable on this base: `CodeRuntime.language` is set by the loaded backend, the only published backend is `dsh-code-runtime-worker` (`'typescript'`), and the registry reads the loaded runtime rather than a config field, so no assembled application can select `renderToolsSdkPy` or `PYTHON_FLAVOR`. The model-visible surface is therefore unchanged by this note's work until a backend reporting `'python'` is published, and this PR's coverage is unit-level — the renderer output plus the dispatch and rejection paths. The keyless snapshot for the Python model interface belongs to the PR that publishes that backend, because only there does a real `cordis.yml` over published plugins produce a Python assembly; a snapshot example that mounted a fixture runtime here would assert against a test double, which [docs/testing.md](../../../../docs/testing.md) rejects as a substitute for the assembled application transcript. -Two runtime contracts the Python SDK text asserts are owed by that same backend PR. First, the instructions tell the model that exactly `tools` and `ToolCallError` are bound and that the declared `TypedDict` classes are not, so the backend must inject those two names — with `ToolCallError.toolName` populated per the seam's `errorClass` contract — and must NOT bind the declared class names into the program's globals; injecting them "helpfully" would make the SDK text false. Second, the language has to be bound to the request: `requireCodeRuntime` resolves `ctx.codeRuntime` separately at assembly and at `run_code` execution, so a reload that swapped the runtime between those two points would hand a program written against one flavor to the other. The split is finer than those two points — `run_code`'s `description` and `parameters` getters each call `resolveFlavor(peekRuntime())`, and `schemaOf` destructures both per definition, so one projection reads the runtime twice per tool; a reload between those two reads yields a single schema whose two halves name different languages. Neither is reachable here — one published backend means both reads return the same flavor and no program ever runs against this renderer's output — and the cross-language rejection is not testable until a second language exists. +Two runtime contracts the Python SDK text asserts are owed by that same backend PR. First, the instructions tell the model that exactly `tools` and `ToolCallError` are bound and that the declared `TypedDict` classes are not, so the backend must inject those two names — with `ToolCallError.toolName` populated per the seam's `errorClass` contract — and must NOT bind the declared class names into the program's globals; injecting them "helpfully" would make the SDK text false. Second, the language has to be bound to the request: `requireCodeRuntime` resolves `ctx.codeRuntime` separately at assembly and at `run_code` execution, so a reload that swapped the runtime between those two points would hand a program written against one flavor to the other. The split is finer than those two points — `run_code`'s `description` and `parameters` getters each call `resolveFlavor(peekRuntime())`, and `schemaOf` destructures both, so one projection reads the runtime twice; both reads are for `run_code`'s own schema, since the getters are installed on that one definition and every other definition carries plain data properties. A reload between those two reads yields a single schema whose two halves name different languages. Neither is reachable here — one published backend means both reads return the same flavor and no program ever runs against this renderer's output — and the cross-language rejection is not testable until a second language exists. diff --git a/.agents/notes/implemented/feature/2026-07-31-code-mode-language-dispatch.zh.md b/.agents/notes/implemented/feature/2026-07-31-code-mode-language-dispatch.zh.md index 3cc3bae8c6..12ef8197e6 100644 --- a/.agents/notes/implemented/feature/2026-07-31-code-mode-language-dispatch.zh.md +++ b/.agents/notes/implemented/feature/2026-07-31-code-mode-language-dispatch.zh.md @@ -41,4 +41,4 @@ Code Mode 只生成一种 SDK 形态：TypeScript。`ToolRegistry` 为 `tools:sd 代价是两张表的 Python 分支在当前 base 上不可达：`CodeRuntime.language` 由所加载的后端设定，已发布的后端只有 `dsh-code-runtime-worker`（`'typescript'`），而注册表读取的是所加载的运行时而非某个配置字段，因此没有任何一份组装好的应用能选中 `renderToolsSdkPy` 或 `PYTHON_FLAVOR`。也就是说，在报告 `'python'` 的后端发布之前，本 note 的工作不改变模型可见表面，本 PR 的覆盖因此是 unit 级——渲染器输出加分发与拒绝路径。Python 模型界面的 keyless snapshot 归属于发布该后端的那个 PR，因为只有在那里，一份基于已发布插件的真实 `cordis.yml` 才会产出 Python 组装；在此处挂载 fixture 运行时的快照示例断言的是测试替身，而 [docs/testing.md](../../../../docs/testing.md) 明确拒绝以此替代组装好的应用 transcript。 -Python SDK 文本断言的两条运行时契约同样归属那个 backend PR。其一，说明文字告诉模型运行时恰好绑定 `tools` 与 `ToolCallError` 两个名字、所声明的 `TypedDict` 类不绑定，因此后端必须注入这两个名字（并按 seam 的 `errorClass` 契约填充 `ToolCallError.toolName`），且**不得**把所声明的类名绑进程序全局——「好心」注入会使这段 SDK 文本变成假话。其二，语言必须绑定到请求上：`requireCodeRuntime` 在组装时与 `run_code` 执行时分别解析 `ctx.codeRuntime`，若在这两点之间发生重载并换掉运行时，就会把针对一种形态写成的程序交给另一种形态执行。分裂比这两点更细——`run_code` 的 `description` 与 `parameters` 两个 getter 各自调用 `resolveFlavor(peekRuntime())`，而 `schemaOf` 对每个 definition 解构这两个字段，因此一次投影对每个工具读两次运行时；在这两次读取之间重载会产出单个 schema 的两半分属不同语言。两者在此处都不可达——只有一个已发布后端意味着两次读取返回同一形态，且没有任何程序会针对本渲染器的输出运行——而跨语言拒绝在第二门语言存在之前也无法测试。 +Python SDK 文本断言的两条运行时契约同样归属那个 backend PR。其一，说明文字告诉模型运行时恰好绑定 `tools` 与 `ToolCallError` 两个名字、所声明的 `TypedDict` 类不绑定，因此后端必须注入这两个名字（并按 seam 的 `errorClass` 契约填充 `ToolCallError.toolName`），且**不得**把所声明的类名绑进程序全局——「好心」注入会使这段 SDK 文本变成假话。其二，语言必须绑定到请求上：`requireCodeRuntime` 在组装时与 `run_code` 执行时分别解析 `ctx.codeRuntime`，若在这两点之间发生重载并换掉运行时，就会把针对一种形态写成的程序交给另一种形态执行。分裂比这两点更细——`run_code` 的 `description` 与 `parameters` 两个 getter 各自调用 `resolveFlavor(peekRuntime())`，而 `schemaOf` 会解构这两个字段，因此一次投影读两次运行时；两次都属于 `run_code` 自己的 schema，因为这两个 getter 只装在那一个 definition 上，其余 definition 携带的都是普通数据属性。在这两次读取之间重载会产出单个 schema 的两半分属不同语言。两者在此处都不可达——只有一个已发布后端意味着两次读取返回同一形态，且没有任何程序会针对本渲染器的输出运行——而跨语言拒绝在第二门语言存在之前也无法测试。 diff --git a/packages/core/tools/src/py-types.ts b/packages/core/tools/src/py-types.ts index 5021995b09..b0de1b7a0d 100644 --- a/packages/core/tools/src/py-types.ts +++ b/packages/core/tools/src/py-types.ts @@ -17,8 +17,34 @@ import { assertSupportedJsonSchema } from './json-schema.ts' import type { JsonSchemaNode, JsonSchemaScalar } from './json-schema.ts' import type { ToolSdkSchema } from './ts-types.ts' -/** Property names that are valid bare Python identifiers; anything else is subscripted. */ -const IDENTIFIER = /^[A-Za-z_][A-Za-z0-9_]*$/ +/** The reference grammar's `xid_start xid_continue*`, the same set `str.isidentifier()` accepts. */ +const IDENTIFIER = /^[\p{XID_Start}_]\p{XID_Continue}*$/u + +/** + * Whether a name can be emitted as a bare Python identifier rather than + * routed to the subscript/`dict[str, Any]` path. + * + * Python identifiers are not ASCII: `路径` is as legal a field name as `path`, + * and rejecting it would degrade the whole enclosing object, dropping every + * field's name, requiredness, and type — and in Code Mode the native schemas + * are omitted, so this text is the model's only source for them. + * + * NFKC stability is a second and separate condition, because CPython + * normalizes identifiers at compile time while JSON keys are compared as + * written: `field` would be declared and reachable as `field`, so the SDK would + * advertise a key under a spelling the harness never accepts, and two keys + * that normalize together would collapse into one declaration. Those names + * take the subscript path, which carries their exact bytes. + * + * The `ts-types` sibling keeps its own ASCII rule rather than sharing this + * one: ECMAScript identifiers are a different set (`$`, ZWJ/ZWNJ) and are + * never normalized, so one predicate cannot be correct for both. + * @param name - the raw schema field or tool name. + * @returns whether the name can be emitted bare. + */ +function isBareIdentifier(name: string): boolean { + return IDENTIFIER.test(name) && name.normalize('NFKC') === name +} /** * Python hard keywords: reserved everywhere, so a tool or field named @@ -32,8 +58,7 @@ const IDENTIFIER = /^[A-Za-z_][A-Za-z0-9_]*$/ * one syntactic position — a statement head (``match``, ``type``), a ``match`` * statement's clause head (``case``), or a pattern (``_``) — so ``match: str`` * as a field and ``async def match(...)`` as a method are both legal, and - * including - * them would needlessly degrade common search/regex tool fields to + * including them would needlessly degrade common search/regex tool fields to * ``dict[str, Any]``. Underscore-leading names are handled separately, not * here: a non-dunder ``__token`` name-mangles, a dunder present on * ``object``/``type`` resolves before the proxy hook, and implicit @@ -156,14 +181,26 @@ function docLines(description: unknown, indent: number): string[] { return [`${pad(indent)}"""${escaped}"""`] } -/** CamelCase a name into a Python type identifier (non-identifier chars split words; a non-letter head is prefixed). */ +/** + * CamelCase a name into a Python type identifier: non-identifier characters + * split words, `_` splits too (it is `XID_Continue`, so the split set names it + * explicitly), and a head that cannot start an identifier takes a `Tool` + * prefix. Unicode survives, so a `路径` field yields `路径`-based class names + * instead of collapsing to the bare prefix. The result is NFKC-normalized: + * these names are generated, never matched against a JSON key, so normalizing + * is free here and keeps what CPython compiles identical to what is emitted — + * unlike {@link isBareIdentifier}, which must reject unstable names outright. + * @param raw - the schema field or tool name to derive from. + * @returns a class-name segment safe to emit. + */ function camelCase(raw: string): string { const joined = raw - .split(/[^A-Za-z0-9]+/) + .split(/[^\p{XID_Continue}]+|_+/u) .filter(part => part.length > 0) .map(part => `${part.charAt(0).toUpperCase()}${part.slice(1)}`) .join('') - return /^[A-Za-z]/.test(joined) ? joined : `Tool${joined}` + .normalize('NFKC') + return /^\p{XID_Start}/u.test(joined) ? joined : `Tool${joined}` } /** Class-name base cap keeping each emitted name — and total text — linear in schema depth. */ @@ -191,9 +228,11 @@ const MAX_CLASS_NAME_BASE = 120 * - Argument annotation, `async def f(self, args: chain) -> Y:` — the `(` IS * still open around it: 180 `list[` plus `Literal[` plus the paren, 182, the * worst case. Reachable only through a raw `register()` whose `parameters` - * root opens an array chain — rooted at the array, or at an array branch of - * a root `oneOf`, which inherits the enclosing depth because a union adds no - * brackets. `defineTool` compiles an object root, so the annotation is a + * is an array reached from the root through `oneOf` arms alone — the root + * array itself, or one nested under any depth of unions, since an arm + * inherits the enclosing depth unchanged (`A | B` opens no bracket). An + * object ancestor takes it out of this case: its fields restart the chain at + * the 181 site. `defineTool` compiles an object root, so the annotation is a * bare TypedDict class name or a one-bracket `dict[str, Any]` when that * object degrades — never a chain. * @@ -208,9 +247,17 @@ const MAX_CLASS_NAME_BASE = 120 */ const MAX_LIST_NESTING = 180 -/** Cap a class-name base at {@link MAX_CLASS_NAME_BASE} (see the callers for why capping keeps the render linear). */ +/** + * Cap a class-name base at {@link MAX_CLASS_NAME_BASE} (see the callers for + * why capping keeps the render linear). `slice` counts UTF-16 code units, so + * an astral character straddling the boundary would be cut in half and leave a + * lone surrogate — not an identifier character, and not even well-formed text; + * drop it rather than emit it. + */ function capClassNameBase(base: string): string { - return base.length > MAX_CLASS_NAME_BASE ? base.slice(0, MAX_CLASS_NAME_BASE) : base + if (base.length <= MAX_CLASS_NAME_BASE) return base + const capped = base.slice(0, MAX_CLASS_NAME_BASE) + return /[\uD800-\uDBFF]$/.test(capped) ? capped.slice(0, -1) : capped } /** @@ -520,7 +567,7 @@ function renderType(schema: unknown, className: string, state: RenderState): str // NAME-MANGLED inside class syntax (`_ClassName__token`), describing a // different JSON key than the registered schema — degrade like any // other inexpressible field name. - if (className === '' || !entries.every(([name]) => IDENTIFIER.test(name) && !RESERVED.has(name) && !(name.startsWith('__') && !name.endsWith('__')))) { + if (className === '' || !entries.every(([name]) => isBareIdentifier(name) && !RESERVED.has(name) && !(name.startsWith('__') && !name.endsWith('__')))) { state.typing.add('Any') finish('dict[str, Any]') break @@ -623,7 +670,7 @@ export function renderToolsSdkPy(schemas: ToolSdkSchema[]): string { for (const schema of sorted) { const argType = renderType(schema.parameters, `${camelCase(schema.name)}Args`, state) const outputType = renderType(schema.output, `${camelCase(schema.name)}Output`, state) - if (IDENTIFIER.test(schema.name) && !RESERVED.has(schema.name) && !schema.name.startsWith('_')) { + if (isBareIdentifier(schema.name) && !RESERVED.has(schema.name) && !schema.name.startsWith('_')) { // A docstring only documents its method when it is the FIRST statement // of that method's body. Emitted before the `async def` it would instead // become the `Tools` class docstring (for the first tool) or a dead diff --git a/packages/core/tools/tests/py-types.spec.ts b/packages/core/tools/tests/py-types.spec.ts index 60291aa026..ca5ca40ce8 100644 --- a/packages/core/tools/tests/py-types.spec.ts +++ b/packages/core/tools/tests/py-types.spec.ts @@ -398,6 +398,106 @@ describe('renderToolsSdkPy', () => { expect(text).not.toContain('dict[str, Any]') }) + it('keeps a non-ASCII field name as a TypedDict field and derives its class name from it', () => { + // `路径` satisfies `xid_start xid_continue*`, so CPython accepts it as an + // attribute and as the `TypedDict` key. Rejecting it would degrade the + // whole object, dropping every SIBLING field's name, requiredness and type + // too — and Code Mode omits the native schemas, so nothing else carries + // them. The nested class name is derived from the field, so `camelCase` + // has to pass the same characters through instead of splitting on them. + const tool: ToolSdkSchema = { + name: '搜索', + description: 'Unicode identifiers.', + parameters: { + type: 'object', + additionalProperties: false, + properties: { + 路径: { type: 'string' }, + opts: { type: 'object', additionalProperties: false, properties: { 深度: { type: 'number' } } }, + }, + required: ['路径'], + }, + output: { type: 'string' }, + } + const text = renderToolsSdkPy([tool]) + expect(text).toContain('async def 搜索(self, args: 搜索Args) -> str:') + expect(text).toContain('class 搜索Args(TypedDict):') + expect(text).toContain(' 路径: str') + expect(text).toContain('class 搜索ArgsOpts(TypedDict):') + expect(text).toContain(' 深度: NotRequired[float]') + expect(text).not.toContain('dict[str, Any]') + }) + + it('degrades a field name that NFKC-normalizes to something else, which would be declared under another spelling', () => { + // U+FB01 LATIN SMALL LIGATURE FI passes the identifier grammar, but CPython + // normalizes identifiers at compile time while the harness compares the + // JSON key as written: `field: str` would declare and be reachable as + // `field`, a key the tool never accepts. Two keys that normalize together + // would additionally collapse into one declaration. The subscript path + // carries the exact bytes instead. + const text = renderToolsSdkPy([ + { + name: 'ligature', + description: 'Normalizing field name.', + parameters: { type: 'object', additionalProperties: false, properties: { field: { type: 'string' } } }, + output: { type: 'string' }, + }, + ]) + expect(text).toContain('async def ligature(self, args: dict[str, Any]) -> str:') + expect(text).not.toContain('field:') + expect(text).not.toContain('field:') + }) + + it('subscripts a tool name that NFKC-normalizes to something else, while declaring a plain Unicode one', () => { + // Same split at the tool-name site: `路径` becomes an `async def`, the + // ligature name cannot, because `async def find` would define `find`. The + // subscript comment quotes the name, so its exact bytes survive, and its + // TypedDict is still named and referenced — the name is only unusable as a + // method, not as a class-name source (`camelCase` normalizes what it + // derives, since a generated name is never matched against a JSON key). + const of = (name: string): ToolSdkSchema => ({ + name, + description: `Tool ${name}.`, + parameters: { type: 'object', additionalProperties: false, properties: { q: { type: 'string' } }, required: ['q'] }, + output: { type: 'string' }, + }) + const text = renderToolsSdkPy([of('路径'), of('find')]) + expect(text).toContain('async def 路径(self, args: 路径Args) -> str:') + expect(text).toContain('# tools["find"](args: FIndArgs) -> str') + expect(text).toContain('class FIndArgs(TypedDict):') + expect(text).not.toContain('async def find') + expect(text).not.toContain('async def find') + }) + + it('drops a surrogate half rather than cutting a pair when capping an astral class-name base', () => { + // Class-name bases are capped by `slice`, which counts UTF-16 code units, + // so a boundary landing inside an astral pair would leave a lone high + // surrogate — not an identifier character, and not encodable text. Padding + // with one ASCII character shifts the boundary onto the pair. + // U+10330 GOTHIC LETTER AHSA: XID_Start and NFKC-stable, unlike `𝕏`, which + // NFKC-folds to ASCII `X` and so never reaches the boundary at all. + const AHSA = String.fromCodePoint(0x10330) + const className = (pad: string): string => { + const text = renderToolsSdkPy([ + { + name: `${pad}${AHSA.repeat(200)}`, + description: 'Astral name.', + parameters: { type: 'object', additionalProperties: false, properties: { a: { type: 'string' } } }, + output: { type: 'string' }, + }, + ]) + // The base is `${camelCase(name)}Args` capped to 120 code units, so the + // `Args` suffix itself is cut off here; match the declaration instead. + return /^class (.+)\(TypedDict\):$/mu.exec(text)![1]! + } + // Each character is 2 code units, so an unpadded name fills the cap with 60 + // whole characters; one ASCII character of padding puts the boundary inside + // the 60th pair, and that half is dropped rather than emitted. + expect(className('')).toBe(AHSA.repeat(60)) + expect(className('x')).toBe(`X${AHSA.repeat(59)}`) + expect(className('x')).toHaveLength(119) + }) + it('declares a closed empty object with omitted properties as an empty TypedDict, not dict[str, Any]', () => { // `{ type: 'object', additionalProperties: false }` with no `properties` // is a closed empty object — no key accepted — exactly as the validator @@ -580,8 +680,10 @@ describe('renderToolsSdkPy', () => { // The worst of the three emission sites: the parameter list's `(` is still // open around this annotation, so 180 `list[` plus the innermost bracket // plus that paren is 182 of CPython's 200. Only a raw `register()` whose - // `parameters` root opens an array chain reaches it — rooted at the array, - // or at an array branch of a root `oneOf`, since a union adds no brackets. + // `parameters` is an array reached from the root through `oneOf` arms + // alone gets there — the root array itself, or one under any depth of + // unions, since an arm inherits the enclosing depth unchanged. An object + // ancestor takes it out of this case: its fields restart at the 181 site. // `defineTool` compiles an object root, whose annotation is a bare // TypedDict name or a one-bracket `dict[str, Any]`, never a chain. const rooted = (depth: number): ToolSdkSchema => { @@ -602,13 +704,25 @@ describe('renderToolsSdkPy', () => { // rather than on another `list[`, so the count cannot grow past that. expect(renderToolsSdkPy([rooted(181)])) .toContain(`async def rooted(self, args: ${'list['.repeat(180)}Any${']'.repeat(180)}) -> str:`) - // A root union reaches the same 182: its branches inherit the enclosing - // depth because `A | B` opens nothing, so the chain under one of them - // starts at 0 exactly as the array-rooted case does. - const union = { ...rooted(180), parameters: { oneOf: [rooted(180).parameters, { type: 'string' }] } } - const text = renderToolsSdkPy([union]) - expect(text).toContain(`args: ${'list['.repeat(180)}Literal["x"]${']'.repeat(180)} | str) -> str:`) + // A union spine reaches the same 182, at any number of arms deep: each arm + // inherits the enclosing depth because `A | B` opens nothing, so the chain + // under the innermost one still starts at 0. Three unions here, to pin that + // it is the whole `oneOf`-only path and not just a single root union. + let spine: Record = rooted(180).parameters + for (let i = 0; i < 3; i++) spine = { oneOf: [spine, { type: 'string' }] } + const text = renderToolsSdkPy([{ ...rooted(180), parameters: spine }]) + const chain = `${'list['.repeat(180)}Literal["x"]${']'.repeat(180)}` + expect(text).toContain(`args: ${chain} | str | str | str) -> str:`) expect(text.split('async def rooted(self, args: ')[1]!.split(') -> str:')[0]!.split('[').length - 1).toBe(181) + // An object ancestor is the boundary of that path: the field it declares is + // a class-body line, so the same chain lands on the 181 site instead. + const boxed = renderToolsSdkPy([ + { + ...rooted(180), + parameters: { type: 'object', properties: { rows: rooted(180).parameters }, required: ['rows'] }, + }, + ]) + expect(boxed).toContain(` rows: ${'list['.repeat(179)}Any${']'.repeat(179)}`) }) it('renders a deeply nested oneOf chain in linear time (no per-level re-materialization)', () => {