fix(tools): cap Python SDK list nesting at CPython's bracket limit
A schema nesting arrays past ~200 levels rendered a `list[list[...]]` chain CPython's tokenizer rejects outright (`too many nested parentheses`), so the SDK block was not valid Python at all — the failure docstring escaping in the same file already guards against. The chain now degrades to `Any` at 180 levels; nesting restarts per TypedDict field, since a field annotation is its own logical line. Unions and nested objects are unaffected: neither accumulates open brackets. Also aligns the unreachable SDK_RENDERERS guard message with the two reachable ones, and corrects a test comment that still said class docstring.
This commit is contained in:
@@ -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: d1fb598e22926eb017f7d3e2a3d1cb14870d4f4d
|
||||
2026-07-31-code-mode-language-dispatch.zh.md: b5fc8b660c32b3ebdd8eef79439d4dedeb75b0c9
|
||||
2026-07-31-code-mode-language-dispatch.md: 6245891651aece73d5a51a6341bc4f76b98fad12
|
||||
2026-07-31-code-mode-language-dispatch.zh.md: 23dbd1c2a9d049d0648109c474b09feaae28886e
|
||||
|
||||
@@ -23,7 +23,7 @@ Both tables are read with `Object.hasOwn` before use so a language named `toStri
|
||||
|
||||
### The Python SDK renderer
|
||||
|
||||
`py-types.ts` renders the same unified tool-schema vocabulary `jsonSchemaToTs` covers, targeting Python: `jsonSchemaToPy` emits a type expression per JSON-schema node, and `renderToolsSdkPy` assembles named `TypedDict`s for each visible tool's arguments and canonical output plus a `tools` object with usage instructions equivalent to the TypeScript flavor. Unsupported raw constructs degrade rather than throwing during assembly, matching the TypeScript renderer's contract. The output is deterministic — lexicographic tool order, byte-identical text for an unchanged tool set — so the prompt stays prefix-cache-friendly. Lexicographic means one ordered member stream: a tool whose name is not a legal attribute is listed as a `tools[name]` comment in its sorted position rather than partitioned to the end, matching how the TypeScript flavor quotes an exotic key in place. Two Python-specific placements follow from that: a description becomes the method's docstring emitted as the FIRST statement of its body (above the `async def` the first one would document the `Tools` class and the rest would be dead expressions, leaving every method undocumented), and because comment lines are not statements, a tool set with no method at all still needs an explicit `pass`.
|
||||
`py-types.ts` renders the same unified tool-schema vocabulary `jsonSchemaToTs` covers, targeting Python: `jsonSchemaToPy` emits a type expression per JSON-schema node, and `renderToolsSdkPy` assembles named `TypedDict`s for each visible tool's arguments and canonical output plus a `tools` object with usage instructions equivalent to the TypeScript flavor. Unsupported raw constructs degrade rather than throwing during assembly, matching the TypeScript renderer's contract. The output is deterministic — lexicographic tool order, byte-identical text for an unchanged tool set — so the prompt stays prefix-cache-friendly. Lexicographic means one ordered member stream: a tool whose name is not a legal attribute is listed as a `tools[name]` comment in its sorted position rather than partitioned to the end, matching how the TypeScript flavor quotes an exotic key in place. That stream forces one thing directly — comment lines are not statements, so a tool set that emits no method at all still needs an explicit `pass`. Two further rules are Python-specific rather than consequences of the ordering. A description becomes the method's docstring emitted as the FIRST statement of its body: above the `async def` the first one would document the `Tools` class and the rest would be dead expressions, leaving every method undocumented. And a `list[…]` chain degrades to `Any` past `MAX_LIST_NESTING`, because CPython's tokenizer rejects a line with more than 200 open brackets and the block must stay parseable Python — the same reason `docLines` escapes quotes and backslashes. `ts-types` needs neither: TypeScript attaches a leading `/** … */` to the member that follows it and bounds nesting nowhere in its grammar.
|
||||
|
||||
`renderType` validates the whole schema once (`assertSupportedJsonSchema`) and then trusts it, wrapping the walk in one `try/catch` that degrades to `Any` — the same trusted-after-validation stance the sibling `ts-types` renderer takes at this typed same-process seam ([Trust TypeScript at typed same-process seams](../../../../AGENTS.md)). It deliberately carries NO defenses against a schema whose accessors mutate between reads (post-validation cycles, TOCTOU on `const`/`enum`, self-referential functions): the input is a first-party registration (a `defineTool` literal or a raw registration) or a wire-derived plain JSON schema — the former is trusted per AGENTS.md, the latter is a `JSON.parse` product that physically cannot carry accessors, and `renderType` re-validates the whole tree on every call regardless — so such inputs are unreachable, and adding per-shape guards here would break symmetry with `ts-types` (which has none) for values the static interface forbids. `jsonSchemaToPy(schema: unknown)` accepts `unknown` and returns `Any` on a malformed schema — the Python counterpart of the TS flavor's `unknown` — but its contract is "degrade an unsupported schema", not "survive an adversarial mutating one".
|
||||
|
||||
|
||||
@@ -23,7 +23,7 @@ Code Mode 只生成一种 SDK 形态:TypeScript。`ToolRegistry` 为 `tools:sd
|
||||
|
||||
### Python SDK 渲染器
|
||||
|
||||
`py-types.ts` 渲染 `jsonSchemaToTs` 所覆盖的同一套统一工具 schema 词汇,目标为 Python:`jsonSchemaToPy` 为每个 JSON-schema 节点发出一个类型表达式,`renderToolsSdkPy` 为每个可见工具的参数与规范输出装配具名 `TypedDict`,再加一个带用法说明的 `tools` 对象,与 TypeScript 形态等价。不支持的原始构造在装配时降级而非抛错,与 TypeScript 渲染器的契约一致。输出是确定性的——工具按字典序排列,工具集不变时文本逐字节相同——因此 prompt 保持 prefix-cache 友好。字典序意味着单一有序的成员流:名字不是合法属性的工具以 `tools[name]` 注释出现在它排序后的位置上,而不是被分拣到末尾,与 TypeScript 形态就地为异常键加引号的做法一致。由此带来两处 Python 特有的位置约定:描述会成为方法的 docstring,且必须作为方法体的**第一条语句**发出(放在 `async def` 之上,第一条会变成 `Tools` 的类文档、其余都是无效果表达式,导致每个方法都没有文档);而注释行不是语句,所以一个没有任何方法的工具集仍需显式 `pass`。
|
||||
`py-types.ts` 渲染 `jsonSchemaToTs` 所覆盖的同一套统一工具 schema 词汇,目标为 Python:`jsonSchemaToPy` 为每个 JSON-schema 节点发出一个类型表达式,`renderToolsSdkPy` 为每个可见工具的参数与规范输出装配具名 `TypedDict`,再加一个带用法说明的 `tools` 对象,与 TypeScript 形态等价。不支持的原始构造在装配时降级而非抛错,与 TypeScript 渲染器的契约一致。输出是确定性的——工具按字典序排列,工具集不变时文本逐字节相同——因此 prompt 保持 prefix-cache 友好。字典序意味着单一有序的成员流:名字不是合法属性的工具以 `tools[name]` 注释出现在它排序后的位置上,而不是被分拣到末尾,与 TypeScript 形态就地为异常键加引号的做法一致。这个成员流直接决定了一件事:注释行不是语句,所以一个不发出任何方法的工具集仍需显式 `pass`。另有两条规则并非源自排序,而是 Python 特有。其一,描述会成为方法的 docstring,且必须作为方法体的**第一条语句**发出:放在 `async def` 之上,第一条会变成 `Tools` 的类文档、其余都是无效果表达式,导致每个方法都没有文档。其二,`list[…]` 链超过 `MAX_LIST_NESTING` 后降级为 `Any`,因为 CPython 的 tokenizer 拒绝一行中超过 200 个同时未闭合的括号,而这个块必须是可解析的 Python——与 `docLines` 转义引号和反斜杠是同一个理由。`ts-types` 两者都不需要:TypeScript 会把前置的 `/** … */` 附着到其后的成员上,其语法也不对嵌套设限。
|
||||
|
||||
`renderType` 先用 `assertSupportedJsonSchema` 整树校验一次、随后信任它,用单个 `try/catch` 把整个遍历兜住并降级为 `Any`——与姊妹渲染器 `ts-types` 在这个 typed 同进程 seam 上采取的「校验后信任」姿态一致([Trust TypeScript at typed same-process seams](../../../../AGENTS.md))。它有意不设任何针对「访问器在多次读取间变值」的防御(校验后成环、`const`/`enum` 的 TOCTOU、自引用函数):输入是第一方注册(`defineTool` 字面量或 raw 注册)或从 wire 桥接而来的纯 JSON——前者按 AGENTS.md 受信任,后者是 `JSON.parse` 产物、物理上不可能携带访问器,且每次调用 `renderType` 都会整树重新校验——这类输入不可达,而在此加逐形态守卫会为静态接口所禁止的值破坏与 `ts-types`(没有这类守卫)的对称。`jsonSchemaToPy(schema: unknown)` 接受 `unknown` 并对畸形 schema 返回 `Any`——TypeScript 形态 `unknown` 的对应物——但它的契约是「降级不支持的 schema」,而非「扛住对抗性的可变 schema」。
|
||||
|
||||
|
||||
Reference in New Issue
Block a user