diff --git a/.agents/notes/implemented/architecture/2026-07-31-code-runtime-python-fd3-protocol.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-31-code-runtime-python-fd3-protocol.i18n.yaml new file mode 100644 index 0000000000..bd811f506e --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-31-code-runtime-python-fd3-protocol.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# 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/architecture/2026-07-31-code-runtime-python-fd3-protocol.md +2026-07-31-code-runtime-python-fd3-protocol.md: 32cc80278af6b5f894c8d972854dae8c92ac63b7 +2026-07-31-code-runtime-python-fd3-protocol.zh.md: e7cf551b1dc84656c1eaf49280052c732839942b diff --git a/.agents/notes/implemented/architecture/2026-07-31-code-runtime-python-fd3-protocol.md b/.agents/notes/implemented/architecture/2026-07-31-code-runtime-python-fd3-protocol.md new file mode 100644 index 0000000000..32cc80278a --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-31-code-runtime-python-fd3-protocol.md @@ -0,0 +1,43 @@ +# Agent Note: the code-runtime-python fd-3 frame protocol + +Status: implemented + +English | [中文](2026-07-31-code-runtime-python-fd3-protocol.zh.md) + +## Problem + +The CPython code-runtime backend (`@deepseek-ai/dsh-code-runtime-python`, arriving across a PR stack) runs each model program in a fresh `python3 -I` subprocess and bridges binding calls and completion values over the child's fd 3. That channel needs a wire protocol both sides agree on, and the host cannot trust it: model code has full access to fd 3 and can forge any frame, so every inbound frame is hostile input the host must validate and rebuild before reading. The protocol also has to carry lossless JSON without the depth limit `JSON.stringify`/`json.dumps` impose, because the seam's `CodeJsonValue` is depth-unbounded. + +This layer of the stack delivers only that protocol, so the large `PythonCodeRuntime` implementation and its real-subprocess integration suite land on a reviewed wire contract instead of arriving fused with it. The parent stack splits [#436](https://github.com/deepseek-harness/deepseek-harness/pull/436) — a 9000-line single PR — into reviewable layers; this is the protocol layer, based on the [seam extension](2026-07-31-code-runtime-portable-identifier-seam.md). + +## Decision + +`src/protocol.ts` is the host side of the wire vocabulary and its hostile-frame codec: + +- **`validateChildFrame`** shape-validates and REBUILDS every inbound frame. The compile-time union means nothing on fd 3 — a forged frame can carry `null`, poisoned fields, or omit required ones — so each accepted frame is reconstructed field by field: forged extras never ride along, a non-finite call id can never be echoed into a reply, and junk returns `undefined` to be dropped rather than throwing in the host's message handler. +- **`encodeJsonPlain` / `checkDoneValue` / `hasUnsafeIntegerToken` / `hasNonLosslessNumber`** are the lossless-JSON codec and meters. They traverse iteratively (an explicit stack, not recursion) so a deep value below the byte budget crosses intact; `checkDoneValue` folds byte-metering and number-losslessness into one bounded walk that rejects an over-budget payload BEFORE enqueuing its children, keeping a forged below-frame-ceiling value from forcing a hundreds-of-megabytes host allocation. Beyond-safe-range integral doubles serialize through `BigInt` digits so the exact integer crosses, not `String()`'s rounded form. +- **`logTruncationMarker`** produces the in-band marker text a log ledger emits when it exhausts its byte budget. + +`py/protocol.py` mirrors the message shapes as `TypedDict`s and re-declares the two surfaces both sides EXECUTE against — `PROTOCOL_FD = 3` and `log_truncation_marker` — with byte-identical text. + +The package skeleton (`package.json`, `tsconfig.json`, `tsdown.config.ts`, `src/index.ts`, `src/invariant.ts`, README triplet) ships here rather than in a later stack layer: `check-workspace-constraints` reads every `packages//` package.json unconditionally, and the coverage and invariant-topology gates require the package to exist and build the moment its directory does. The later backend-core PR extends `src/index.ts` with `PythonCodeRuntime` and grows `package.json`'s dependencies; because it bases on this branch, those are edits, not conflicts. + +## Wire contract + +Frames are JSON-lines on fd 3, one object per line, leaving stdout/stderr free for the program's own output. Child → host: `boot-ack`, `call`, `log`, `done`. Host → child: `boot` (first frame), `run` (after `boot-ack`), and one `reply` per `call`. The `log` frame's `truncated` flag marks the frame that IS the child ledger's own truncation marker, so the host stops capturing at the same point the child did instead of inferring it from its own budget. `done.error.kind` is one of `exception`, `invalid-output`, `output-limit`; wall/CPU budgets, aborts, and substrate death are observed host-side, not carried as frames. + +## Mirror alignment + +Round-12 review of #436 found `py/protocol.py` stale against `src/protocol.ts` in three declarations — `LogMessage` lacked `truncated`, `DoneMessage.error` lacked `kind`, and `Namespace` lacked the optional `errorClass`. This PR aligns all three when lifting the file, so the stale mirror is not carried forward. Because the declarations are `TypedDict`s (no runtime enforcement on the trusted Python side), an automated guard covers only what both sides execute: `tests/protocol-mirror.e2e.ts` spawns a real `python3`, reads `PROTOCOL_FD` and `log_truncation_marker` from `py/protocol.py`, and asserts they equal the TypeScript constants across several byte budgets. + +## Alternatives considered + +**Move the Python JSON codec (`_encode_json_plain` / `_decode_json_plain`) into `py/protocol.py` for cross-side symmetry with `protocol.ts`.** Rejected. The repository's "prefer symmetry for parallel values" rule points at genuinely parallel values; these are not. The host-side codec in `protocol.ts` validates HOSTILE input and is self-contained. The Python codec produces output on the TRUSTED side and is coupled to bootstrap-internal helpers (`_Emit`, `_dump_scalar`/`_dump_string`/`_dump_float`, `LogBuffer`'s cost accounting, `_check_done_value`, `_lossless_json_violation`); lifting only the two entry points would drag that web into `protocol.py` or create a `bootstrap.py` ↔ `protocol.py` import cycle. The real cross-side parallel is "host validates inbound (`protocol.ts`) ↔ child trusts host and emits (`bootstrap.py`)", and that symmetry is preserved: `protocol.py` stays the pure wire-vocabulary mirror it is on the TS side. The Python codec stays in `bootstrap.py`, delivered by the backend-core PR. + +**Defer the package skeleton to the backend-core PR that "owns" package.json.** Rejected: the workspace-constraint, coverage, and invariant-topology gates fail the instant the `code-runtime-python` directory exists without a buildable package. A stacked split cannot create source files in a package that does not yet compile. + +## Consequences + +Bought: the fd-3 protocol and its hostile-input codec land as a self-contained, fully unit-covered layer, and the py/ts mirror drift the round-12 review found is fixed with an executing guard against its recurrence. The backend-core PR builds on a reviewed wire contract. + +Cost: `src/index.ts` and `package.json` are introduced minimally here and edited (not created) by the backend-core PR. The `TypedDict` shapes in `py/protocol.py` beyond the two executed surfaces remain guarded by review plus the backend's real-subprocess suite, not by the mirror e2e test — an inherent limit of comparing type declarations across languages. diff --git a/.agents/notes/implemented/architecture/2026-07-31-code-runtime-python-fd3-protocol.zh.md b/.agents/notes/implemented/architecture/2026-07-31-code-runtime-python-fd3-protocol.zh.md new file mode 100644 index 0000000000..e7cf551b1d --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-31-code-runtime-python-fd3-protocol.zh.md @@ -0,0 +1,43 @@ +# Agent Note: the code-runtime-python fd-3 frame protocol + +Status: implemented + +[English](2026-07-31-code-runtime-python-fd3-protocol.md) | 中文 + +## Problem + +CPython code-runtime 后端(`@deepseek-ai/dsh-code-runtime-python`,分多个 PR 落地)在一个全新的 `python3 -I` 子进程里运行每个模型程序,并把 binding 调用和完成值通过子进程的 fd 3 桥接。这条通道需要两侧一致的 wire protocol,而 host 不能信任它:模型代码对 fd 3 有完全访问权、可以伪造任意帧,所以每个入站帧都是 host 必须先校验并重建才能读取的敌意输入。协议还必须承载无深度限制的 lossless JSON,因为 seam 的 `CodeJsonValue` 深度无界,而 `JSON.stringify`/`json.dumps` 都有递归深度限制。 + +本层只交付这个协议,使得庞大的 `PythonCodeRuntime` 实现及其真子进程集成测试能落在一个已 review 的 wire contract 之上,而不是与它揉在一起到达。父 stack 把 [#436](https://github.com/deepseek-harness/deepseek-harness/pull/436)——一个 9000 行的单一 PR——拆成可 review 的层;本 PR 是协议层,base 是 [seam 扩展](2026-07-31-code-runtime-portable-identifier-seam.zh.md)。 + +## Decision + +`src/protocol.ts` 是 wire vocabulary 的 host 侧及其敌意帧编解码: + +- **`validateChildFrame`** 对每个入站帧做形状校验并重建。编译期 union 在 fd 3 上毫无意义——伪造帧可携带 `null`、被污染的字段,或省略必需字段——所以每个被接受的帧都逐字段重建:伪造的额外字段绝不随行,非有限的 call id 绝不会被回显进 reply,垃圾返回 `undefined` 被丢弃,而不是在 host 的 message handler 里抛错。 +- **`encodeJsonPlain` / `checkDoneValue` / `hasUnsafeIntegerToken` / `hasNonLosslessNumber`** 是 lossless-JSON 编解码器与计量器。它们迭代遍历(显式栈,非递归),使低于字节预算的深层值能完整穿越;`checkDoneValue` 把字节计量和数字无损性折进一次有界遍历,在把子节点入栈之前就拒绝超预算 payload,防止一个低于帧上限的伪造值迫使 host 分配数百 MB。超出安全范围的整数型 double 通过 `BigInt` 数字序列化,穿越的是精确整数而非 `String()` 的舍入形式。 +- **`logTruncationMarker`** 产出日志 ledger 耗尽字节预算时发出的带内标记文本。 + +`py/protocol.py` 用 `TypedDict` 镜像消息形状,并重新声明两侧都会 EXECUTE 的两个面——`PROTOCOL_FD = 3` 与 `log_truncation_marker`——文本逐字节一致。 + +包骨架(`package.json`、`tsconfig.json`、`tsdown.config.ts`、`src/index.ts`、`src/invariant.ts`、README 三件套)在此交付,而非放到后续 stack 层:`check-workspace-constraints` 无条件读取每个 `packages//` 的 package.json,coverage 与 invariant-topology gate 也要求包在其目录出现的那一刻即存在且可构建。后续的 backend-core PR 会用 `PythonCodeRuntime` 扩展 `src/index.ts` 并增补 `package.json` 的依赖;因为它 base 在本分支上,那些是编辑,不是冲突。 + +## Wire contract + +帧是 fd 3 上的 JSON-lines,每行一个对象,让 stdout/stderr 空出给程序自己的输出。Child → host:`boot-ack`、`call`、`log`、`done`。Host → child:`boot`(首帧)、`run`(在 `boot-ack` 之后)、以及每个 `call` 对应一个 `reply`。`log` 帧的 `truncated` 标志标记那个本身就是子进程 ledger 截断标记的帧,使 host 在与子进程相同的点停止捕获,而不是从自己的预算去推断。`done.error.kind` 是 `exception`、`invalid-output`、`output-limit` 之一;wall/CPU 预算、abort、substrate 死亡都在 host 侧观测,不作为帧携带。 + +## Mirror alignment + +#436 的 round-12 review 发现 `py/protocol.py` 相对 `src/protocol.ts` 有三处声明陈旧——`LogMessage` 缺 `truncated`、`DoneMessage.error` 缺 `kind`、`Namespace` 缺可选的 `errorClass`。本 PR 在搬运该文件时对齐了这三处,不把陈旧镜像带过来。由于这些声明是 `TypedDict`(在受信任的 Python 侧无运行时强制),自动化 guard 只覆盖两侧都会执行的部分:`tests/protocol-mirror.e2e.ts` 启动一个真实 `python3`,从 `py/protocol.py` 读取 `PROTOCOL_FD` 与 `log_truncation_marker`,并在若干字节预算下断言它们等于 TypeScript 常量。 + +## Alternatives considered + +**把 Python JSON codec(`_encode_json_plain` / `_decode_json_plain`)挪进 `py/protocol.py` 以与 `protocol.ts` 跨侧对称。** 拒绝。仓库的 "prefer symmetry for parallel values" 规则指向真正平行的值;这两者不是。`protocol.ts` 里的 host 侧 codec 校验的是敌意输入,自包含。Python codec 在受信任侧产出输出,且耦合于 bootstrap 内部 helper(`_Emit`、`_dump_scalar`/`_dump_string`/`_dump_float`、`LogBuffer` 的成本核算、`_check_done_value`、`_lossless_json_violation`);只把两个入口挪过去会把这一整片拖进 `protocol.py`,或制造 `bootstrap.py` ↔ `protocol.py` 的 import 环。真正的跨侧平行是 "host 校验入站(`protocol.ts`) ↔ child 信任 host 并发出(`bootstrap.py`)",这个对称性被保留:`protocol.py` 保持它在 TS 侧一样的纯 wire-vocabulary 镜像定位。Python codec 留在 `bootstrap.py`,由 backend-core PR 交付。 + +**把包骨架推迟到"拥有" package.json 的 backend-core PR。** 拒绝:workspace-constraint、coverage、invariant-topology gate 会在 `code-runtime-python` 目录一存在而包不可构建时立即失败。stacked 拆分无法在一个尚不能编译的包里创建源文件。 + +## Consequences + +收获:fd-3 协议及其敌意输入 codec 作为自包含、unit 全覆盖的一层落地,round-12 review 发现的 py/ts 镜像漂移被修复,并有一个执行中的 guard 防其复发。backend-core PR 建立在已 review 的 wire contract 之上。 + +代价:`src/index.ts` 与 `package.json` 在此以最小形态引入,并由 backend-core PR 编辑(而非创建)。`py/protocol.py` 中两个可执行面之外的 `TypedDict` 形状仍由 review 加后端真子进程套件守护,而非 mirror e2e 测试——这是跨语言比较类型声明的固有局限。 diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 13ebcc5b32..5f2b9ac346 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -2574,6 +2574,7 @@ Imported as libraries by other packages; a `cordis.yml` cannot load them. - `@deepseek-ai/dsh-client-ui-slots` ([`packages/client/ui-slots/src/index.ts`](../packages/client/ui-slots/src/index.ts)) - `@deepseek-ai/dsh-client-web` ([`packages/client/web/src/index.ts`](../packages/client/web/src/index.ts)) - `@deepseek-ai/dsh-client-web-react` ([`packages/client/web-react/src/index.ts`](../packages/client/web-react/src/index.ts)) +- `@deepseek-ai/dsh-code-runtime-python` ([`packages/code-runtime/code-runtime-python/src/index.ts`](../packages/code-runtime/code-runtime-python/src/index.ts)) - `@deepseek-ai/dsh-helper` ([`packages/sdk/helper/src/index.ts`](../packages/sdk/helper/src/index.ts)) - `@deepseek-ai/dsh-hook-protocol` ([`packages/hooks/hook-protocol/src/index.ts`](../packages/hooks/hook-protocol/src/index.ts)) - `@deepseek-ai/dsh-jsonrpc-demo` ([`packages/examples/jsonrpc-demo/src/index.ts`](../packages/examples/jsonrpc-demo/src/index.ts)) diff --git a/docs/module-graph.md b/docs/module-graph.md index a50b658e2a..3884c4b58b 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -184,6 +184,7 @@ flowchart TD end subgraph group_code_runtime["packages/code-runtime"] pkg_code_runtime["code-runtime"] + pkg_code_runtime_python["code-runtime-python"] pkg_code_runtime_worker["code-runtime-worker"] end subgraph group_context["packages/context"] @@ -333,6 +334,8 @@ flowchart TD pkg_client_ui_trajectory --> pkg_client_runtime pkg_client_ui_trajectory --> pkg_client_ui_primitives pkg_client_ui_trajectory --> pkg_invariants + pkg_code_runtime_python --> pkg_code_runtime + pkg_code_runtime_python --> pkg_invariants pkg_credentials --> pkg_brand pkg_credentials --> pkg_invariants pkg_frontend_static --> pkg_host_webserver @@ -1147,6 +1150,7 @@ flowchart TD | [`client-test-runtime`](../packages/client/test-runtime) | `client` | [`client-runtime`](../packages/client/runtime), [`client-ui-slots`](../packages/client/ui-slots), [`client-web-react`](../packages/client/web-react), [`host-apiproxy`](../packages/host/apiproxy), [`invariants`](../packages/support/invariants) | | [`client-ui-settings`](../packages/client/ui-settings) | `client` | [`client-runtime`](../packages/client/runtime), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slots`](../packages/client/ui-slots), [`invariants`](../packages/support/invariants) | | [`client-ui-trajectory`](../packages/client/ui-trajectory) | `client` | [`client-runtime`](../packages/client/runtime), [`client-ui-primitives`](../packages/client/ui-primitives), [`invariants`](../packages/support/invariants) | +| [`code-runtime-python`](../packages/code-runtime/code-runtime-python) | `code-runtime` | [`code-runtime`](../packages/code-runtime/code-runtime), [`invariants`](../packages/support/invariants) | | [`credentials`](../packages/credentials/credentials) | `credentials` | [`brand`](../packages/util/brand), [`invariants`](../packages/support/invariants) | | [`frontend-static`](../packages/host/frontend-static) | `host` | [`host-webserver`](../packages/host/webserver), [`invariants`](../packages/support/invariants) | | [`helper`](../packages/sdk/helper) | `sdk` | [`brand`](../packages/util/brand), [`invariants`](../packages/support/invariants), [`subprocess`](../packages/subprocess/subprocess) | diff --git a/knip.json b/knip.json index 6dc4b56dcd..a09e4b37da 100644 --- a/knip.json +++ b/knip.json @@ -360,6 +360,16 @@ "tests/**/*.ts" ] }, + "packages/code-runtime/code-runtime-python": { + "entry": [ + "tests/**/*.spec.ts", + "tests/**/*.e2e.ts" + ], + "project": [ + "src/**/*.ts", + "tests/**/*.ts" + ] + }, "packages/llm/llm-deepseek": { "entry": [ "tests/**/*.spec.ts", diff --git a/packages/code-runtime/code-runtime-python/README.i18n.yaml b/packages/code-runtime/code-runtime-python/README.i18n.yaml new file mode 100644 index 0000000000..d13849f8b0 --- /dev/null +++ b/packages/code-runtime/code-runtime-python/README.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# 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 packages/code-runtime/code-runtime-python/README.md +README.md: 8a394f18f8e27addf0f4a7530cbdb31b9d629bb9 +README.zh.md: 1c246c952492eb574b6fc6c6bc6c76fffcabe01e diff --git a/packages/code-runtime/code-runtime-python/README.md b/packages/code-runtime/code-runtime-python/README.md new file mode 100644 index 0000000000..8a394f18f8 --- /dev/null +++ b/packages/code-runtime/code-runtime-python/README.md @@ -0,0 +1,24 @@ +# @deepseek-ai/dsh-code-runtime-python + +English | [中文](README.zh.md) + +CPython-subprocess implementation of the [`@deepseek-ai/dsh-code-runtime`](../code-runtime/README.md) seam. Companion to [`@deepseek-ai/dsh-code-runtime-worker`](../code-runtime-worker/README.md); trades the Node worker thread for a fresh `python3` subprocess so model code is Python instead of TypeScript. + +This package is built up across the code-runtime-python PR stack. This layer ships the wire protocol; the `PythonCodeRuntime` implementation that drives a `python3 -I` process over it lands on top of it. + +## Wire protocol + +The host and the CPython subprocess exchange a versionless, JSON-lines protocol on the child's fd 3 — one JSON object per line, leaving stdout/stderr free for the program's own output. `src/protocol.ts` is the host side; `py/protocol.py` mirrors its message shapes and the shared truncation-marker text on the Python side. + +- **fd 3, not stdout** — Node pins the channel positionally with `stdio: ['pipe','pipe','pipe','pipe']`; the Python bootstrap reads the same `PROTOCOL_FD` constant. JSON-lines framing. +- **Host treats every inbound frame as hostile** — model code has full access to fd 3 and can post anything through it, so `validateChildFrame` shape-validates and REBUILDS each frame before the host reads it: forged extra fields never ride along, a non-number call id can never be echoed into a reply, and junk drops to `undefined` rather than throwing in the host's message handler. The Python side trusts host replies (the host is not model-controlled). +- **Lossless-JSON crossing** — completion values and binding arguments cross as exact JSON. `encodeJsonPlain` serializes a `JSON.parse`-produced value without recursion, so a deep value below the byte budget crosses intact instead of dying on `JSON.stringify`'s stack limit; `checkDoneValue` meters a forged completion value's byte length AND number losslessness in one bounded traversal that rejects an over-budget payload before enqueuing its children; `hasUnsafeIntegerToken` reads the raw frame text to catch an integer token that `JSON.parse` would silently round; `hasNonLosslessNumber` rejects a non-finite or negative-zero number in unbounded `call.args`. Beyond-safe-range integral doubles serialize through `BigInt` digits so the exact integer crosses, not the rounded `String()` form. +- **Shared truncation marker** — `logTruncationMarker(maxBytes)` produces byte-identical text on both sides, so a truncated log run reads the same however the cap was hit. The `log` frame's `truncated` flag distinguishes the child ledger's own marker from program output. + +## Model Experience + +Indirectly, through Code Mode in [`dsh-tools`](../../core/tools/README.md), which renders this backend's exact completion value when it fits (or an explicit `invalid-output` / `output-limit` failure), plus the exact `[dsh-code-runtime-python] log capture truncated at bytes` log marker, into a retained `run_code` result. + +#### KV Cache effect + +No direct invalidation; the named consumer owns any request-prefix changes. diff --git a/packages/code-runtime/code-runtime-python/README.zh.md b/packages/code-runtime/code-runtime-python/README.zh.md new file mode 100644 index 0000000000..1c246c9524 --- /dev/null +++ b/packages/code-runtime/code-runtime-python/README.zh.md @@ -0,0 +1,24 @@ +# @deepseek-ai/dsh-code-runtime-python + +[English](README.md) | 中文 + +[`@deepseek-ai/dsh-code-runtime`](../code-runtime/README.md) seam 的 CPython 子进程实现。与 [`@deepseek-ai/dsh-code-runtime-worker`](../code-runtime-worker/README.md) 配套;以全新的 `python3` 子进程取代 Node worker 线程,让模型代码从 TypeScript 换成 Python。 + +本包分多个 code-runtime-python PR 逐层搭建。本层交付 wire protocol;在其之上驱动 `python3 -I` 进程的 `PythonCodeRuntime` 实现随后落地。 + +## Wire protocol + +host 与 CPython 子进程在子进程的 fd 3 上交换一个无版本号的 JSON-lines 协议——每行一个 JSON 对象,让 stdout/stderr 空出给程序自己的输出。`src/protocol.ts` 是 host 侧;`py/protocol.py` 在 Python 侧镜像其帧词汇与共享的截断标记文本。 + +- **fd 3,而非 stdout** —— Node 通过 `stdio: ['pipe','pipe','pipe','pipe']` 按位置钉住通道;Python bootstrap 读取相同的 `PROTOCOL_FD` 常量。JSON-lines 帧。 +- **host 把每个入站帧当作敌意输入** —— 模型代码对 fd 3 有完全访问权、可通过它发送任意内容,所以 `validateChildFrame` 在 host 读取前对每个帧做形状校验并重建:伪造的额外字段绝不随行,非数字的 call id 绝不会被回显进 reply,垃圾降为 `undefined` 被丢弃,而不是在 host 的 message handler 里抛错。Python 侧信任 host 回复(host 不受模型控制)。 +- **lossless-JSON 穿越** —— 完成值与 binding 参数以精确 JSON 穿越。`encodeJsonPlain` 无递归地序列化一个 `JSON.parse` 产出的值,使低于字节预算的深层值能完整穿越,而不是死在 `JSON.stringify` 的栈限制上;`checkDoneValue` 在一次有界遍历中同时计量伪造完成值的字节长度与数字无损性,在把子节点入栈之前就拒绝超预算 payload;`hasUnsafeIntegerToken` 读取原始帧文本,捕获 `JSON.parse` 会静默舍入的整数 token;`hasNonLosslessNumber` 拒绝无字节上限的 `call.args` 中的非有限数或负零。超出安全范围的整数型 double 通过 `BigInt` 数字序列化,穿越的是精确整数而非 `String()` 的舍入形式。 +- **共享截断标记** —— `logTruncationMarker(maxBytes)` 在两侧产出逐字节一致的文本,使被截断的日志运行无论从哪侧触达上限都读起来一致。`log` 帧的 `truncated` 标志把子进程 ledger 自身的标记与程序输出区分开。 + +## Model Experience + +Indirectly, through Code Mode in [`dsh-tools`](../../core/tools/README.md), which renders this backend's exact completion value when it fits (or an explicit `invalid-output` / `output-limit` failure), plus the exact `[dsh-code-runtime-python] log capture truncated at bytes` log marker, into a retained `run_code` result. + +#### KV Cache effect + +No direct invalidation; the named consumer owns any request-prefix changes. diff --git a/packages/code-runtime/code-runtime-python/package.json b/packages/code-runtime/code-runtime-python/package.json new file mode 100644 index 0000000000..dc72d0c749 --- /dev/null +++ b/packages/code-runtime/code-runtime-python/package.json @@ -0,0 +1,39 @@ +{ + "name": "@deepseek-ai/dsh-code-runtime-python", + "description": "CPython subprocess implementation of the DeepSeek Harness code-execution seam", + "version": "0.0.1", + "private": true, + "type": "module", + "main": "lib/index.js", + "types": "lib/types/index.d.ts", + "exports": { + ".": { + "types": "./lib/types/index.d.ts", + "default": "./lib/index.js" + }, + "./invariant": { + "types": "./lib/types/invariant.d.ts", + "default": "./lib/invariant.js" + }, + "./package.json": "./package.json" + }, + "files": [ + "lib/index.js", + "lib/invariant.js", + "py/**/*.py", + "lib/types/**/*.d.ts", + "lib/types/**/*.d.ts.map", + "src" + ], + "license": "BSD-3-Clause", + "peerDependencies": { + "@deepseek-ai/dsh-code-runtime": "^0.0.1", + "@deepseek-ai/dsh-invariants": "^0.0.1", + "cordis": "^4.0.0-rc.7" + }, + "devDependencies": { + "@deepseek-ai/dsh-code-runtime": "workspace:^", + "@deepseek-ai/dsh-invariants": "workspace:^", + "cordis": "^4.0.0-rc.7" + } +} diff --git a/packages/code-runtime/code-runtime-python/py/protocol.py b/packages/code-runtime/code-runtime-python/py/protocol.py new file mode 100644 index 0000000000..0445726cac --- /dev/null +++ b/packages/code-runtime/code-runtime-python/py/protocol.py @@ -0,0 +1,126 @@ +"""Wire protocol vocabulary for the Python side of dsh-code-runtime-python. + +Mirrors ``src/protocol.ts``. Frames travel on fd 3 as JSON-lines (one JSON +object per line). The host validates every inbound frame; this side trusts +host replies. +""" + +from __future__ import annotations + +from typing import Any, Literal, TypedDict, Union + +# The protocol fd from the child's perspective. Node passes +# ``stdio: [pipe, pipe, pipe, pipe]`` so the fourth entry (fd 3) is the +# framed-JSON channel; stdout/stderr stay clear for the program's own output. +PROTOCOL_FD = 3 + + +class BootMessage(TypedDict): + """Host → child, first frame on fd 3. Carries every cap and the namespaces.""" + + type: Literal["boot"] + cpuSeconds: int + addressSpaceBytes: int + maxLogBytes: int + maxValueBytes: int + namespaces: list["Namespace"] + + +class ErrorClass(TypedDict): + """A namespace's program-visible exception class: rejected calls raise its + instances carrying the failed member name on ``memberNameProperty``.""" + + name: str + memberNameProperty: str + + +class Namespace(TypedDict, total=False): + """One binding namespace declaration: the global name, its function names, + and an optional program-visible ``errorClass`` for rejected calls.""" + + global_: str # required; renamed on the wire: JSON field is ``global`` (Python keyword collision) + names: list[str] # required + errorClass: ErrorClass # optional — mirrors the TS `errorClass?` + + +class RunMessage(TypedDict): + """Host → child, sent after ``boot-ack``. Carries only the program body.""" + + type: Literal["run"] + program: str + + +class BootAckMessage(TypedDict): + """Child → host: resource limits applied, ready for the run message.""" + + type: Literal["boot-ack"] + + +class CallMessage(TypedDict): + """Child → host: one bridged binding call from the model program.""" + + type: Literal["call"] + id: int + global_: str # wire field is ``global`` + name: str + args: Any + + +class LogMessage(TypedDict, total=False): + """Child → host: one captured text chunk, streamed eagerly. + + ``truncated`` is set only on the frame that IS the child ledger's truncation + marker (not program output), so the host stops capturing at the same point + the child did — mirrors the TS `truncated?`. + """ + + type: Literal["log"] # required + text: str # required + truncated: bool # optional + + +class DoneErrorField(TypedDict): + """Child → host: the failure carried on a ``done`` frame. ``kind`` is one of + the three the host validates; ``message`` is the traceback or diagnostic.""" + + kind: Literal["exception", "invalid-output", "output-limit"] + message: str + + +class DoneMessage(TypedDict, total=False): + """Child → host: the program settled. ``value`` and ``error`` are optional per the TS mirror.""" + + type: Literal["done"] # required — TypedDict(total=False) allows this via a required subclass in Py 3.11+; MVP keeps it flat + value: Any + error: DoneErrorField + + +ChildToHost = Union[BootAckMessage, CallMessage, LogMessage, DoneMessage] + + +class ReplyOk(TypedDict): + type: Literal["reply"] + id: int + ok: Literal[True] + value: Any + + +class ReplyErr(TypedDict): + type: Literal["reply"] + id: int + ok: Literal[False] + message: str + + +ReplyMessage = Union[ReplyOk, ReplyErr] +HostToChild = ReplyMessage + + +def log_truncation_marker(max_bytes: int) -> str: + """Return the in-band marker for a log ledger that exhausted its budget. + + Byte-identical text on both sides of the wire so a truncated run reads the + same however the cap was hit. + """ + + return f"[dsh-code-runtime-python] log capture truncated at {max_bytes} bytes" diff --git a/packages/code-runtime/code-runtime-python/src/index.ts b/packages/code-runtime/code-runtime-python/src/index.ts new file mode 100644 index 0000000000..625576f220 --- /dev/null +++ b/packages/code-runtime/code-runtime-python/src/index.ts @@ -0,0 +1,20 @@ +/** + * CPython subprocess code runtime for the DeepSeek Harness code-execution seam. + * + * This layer of the package ships the versionless fd-3 wire protocol between the + * Node host and the CPython subprocess; the `PythonCodeRuntime` implementation + * that drives a `python3 -I` process over it lands on top of this seam. The + * protocol's host-side codec and hostile-frame validators are re-exported so the + * runtime and its tests share one wire vocabulary. + * @module @deepseek-ai/dsh-code-runtime-python + */ + +export type { BootMessage, ChildToHost, ReplyMessage } from './protocol.ts' +export { + checkDoneValue, + encodeJsonPlain, + hasNonLosslessNumber, + hasUnsafeIntegerToken, + logTruncationMarker, + validateChildFrame, +} from './protocol.ts' diff --git a/packages/code-runtime/code-runtime-python/src/invariant.ts b/packages/code-runtime/code-runtime-python/src/invariant.ts new file mode 100644 index 0000000000..48441ad875 --- /dev/null +++ b/packages/code-runtime/code-runtime-python/src/invariant.ts @@ -0,0 +1,30 @@ +/** + * Package-owned invariant companion for `@deepseek-ai/dsh-code-runtime-python`. + * @module @deepseek-ai/dsh-code-runtime-python/invariant + */ + +/* jscpd:ignore-start */ +import type { Context } from 'cordis' +import type { InvariantInstaller } from '@deepseek-ai/dsh-invariants' + +const PACKAGE_NAME = '@deepseek-ai/dsh-code-runtime-python' + +/** Cordis companion plugin name. */ +export const name = 'code-runtime-python-invariant' +/** Service required before the companion can reserve package ownership. */ +export const inject = ['invariants'] + +/** + * No runtime invariant: this process-boundary implementation exposes no same-process event relation; + * the fd-3 protocol and real-subprocess integration tests cover it. + */ +const install: InvariantInstaller = () => {} + +/** + * Register this package's invariant companion. + * @param ctx - Cordis context carrying the invariant service. + * @returns the installed registration's disposer after setup succeeds. + */ +export const apply = (ctx: Context): Promise<() => void> => + Promise.resolve(ctx.invariants.register(PACKAGE_NAME, install)) +/* jscpd:ignore-end */ diff --git a/packages/code-runtime/code-runtime-python/src/protocol.ts b/packages/code-runtime/code-runtime-python/src/protocol.ts new file mode 100644 index 0000000000..c935a1153a --- /dev/null +++ b/packages/code-runtime/code-runtime-python/src/protocol.ts @@ -0,0 +1,420 @@ +/** + * Versionless, JSON-lines wire protocol between the Node host and the CPython subprocess. Frames + * travel on the child's fd 3 (one JSON object per line), leaving stdout/stderr free for the + * program's own output. Host treats every inbound frame as hostile because model code can post + * anything through the same fd; the Python bootstrap trusts host replies. + * @module @deepseek-ai/dsh-code-runtime-python/src/protocol + */ + +// The protocol channel is fd 3 from the child's perspective — the host pins it +// positionally via `stdio: ['pipe','pipe','pipe','pipe']` (index.ts), and the +// Python bootstrap reads the same constant from its own protocol.py. + +/** + * What the host sends immediately after spawn, as the first line on fd 3. The + * Python bootstrap reads this, applies resource limits, then waits for the + * subsequent run frame. Separated from the run so the run message stays + * pure model input. + */ +export interface BootMessage { + type: 'boot' + /** RLIMIT_CPU seconds; the Python bootstrap sets this on itself before executing model code. */ + cpuSeconds: number + /** RLIMIT_AS bytes; caps address space so a runaway allocation fails cleanly. */ + addressSpaceBytes: number + /** Shared byte budget for captured log text (Python-side ledger). */ + maxLogBytes: number + /** Byte cap for the rendered completion value. */ + maxValueBytes: number + /** + * The namespaces to materialize inside the program (globals + names; + * functions stay host-side). `errorClass` asks the bootstrap to mint a + * program-visible exception class under that global: rejected calls raise + * its instances carrying the member name on `memberNameProperty`. + */ + namespaces: { global: string; names: string[]; errorClass?: { name: string; memberNameProperty: string } }[] +} + +// The run request `{ type: 'run', program }` follows BootMessage once the +// child acknowledges with `boot-ack`; the host sends it as an inline literal +// (it carries only the model's program body — caps and bindings crossed on boot). + +/** Python → host: acknowledges boot completed and resource limits are in place. */ +interface BootAckMessage { + type: 'boot-ack' +} + +/** Python → host: one bridged binding call (`await tools.name(args)` inside the program). */ +interface CallMessage { + type: 'call' + /** Python-issued correlation id; the host answers each id at most once and ignores duplicates. */ + id: number + /** The namespace global the call targets. */ + global: string + /** The function name within the namespace. */ + name: string + /** The JSON-safe argument the model program passed. */ + args: unknown +} + +/** + * Python → host: captured text, streamed eagerly so output survives a + * mid-run termination (RLIMIT_CPU, SIGTERM/SIGKILL, host wall-timeout). + */ +interface LogMessage { + type: 'log' + text: string + /** + * Set when this frame IS the child ledger's truncation marker rather than + * program output. The two ledgers can exhaust at different points — one + * child entry larger than `maxLogBytes` sends only the marker while the host + * ledger is still nearly empty — so the host cannot infer the child's state + * from its own budget, and comparing the text against the marker string + * would also honour a program that printed that string itself. Carrying it + * as a field lets the host stop capturing at the same point the child did + * and keeps exactly one marker in `logs`. + */ + truncated?: boolean +} + +/** + * Python → host: the program settled. `error` carries a program exception + * (traceback text), an `invalid-output` (completion value was not lossless + * JSON), or an `output-limit` (serialized completion exceeded the configured + * cap); wall/CPU budgets, aborts, and substrate death are observed host-side. + * `value` is present only on a clean completion that produced one, and crosses + * as exact lossless JSON — never substituted or truncated. + */ +interface DoneMessage { + type: 'done' + value?: unknown + error?: { kind: 'exception' | 'invalid-output' | 'output-limit'; message: string } +} + +/** + * Every message the Python side sends. The member interfaces stay module- + * private: consumers match on the union's discriminant; the host sends the + * boot and run frames as inline literals. + */ +export type ChildToHost = BootAckMessage | CallMessage | LogMessage | DoneMessage + +/** Host → Python: the answer to one {@link CallMessage}. */ +export type ReplyMessage = + | { type: 'reply'; id: number; ok: true; value: unknown } + | { type: 'reply'; id: number; ok: false; message: string } + +/** + * The in-band marker text announcing that log capture stopped at the byte + * budget. Shared wire vocabulary: the Python-side LogBuffer emits it when ITS + * ledger exhausts, and the host emits identical text when its own ledger drops + * a frame first (forged fd-3 traffic, stray stdout bytes) — a truncated run + * reads the same however the cap was hit. + * @param maxBytes - the configured `maxLogBytes` the marker names. + * @returns the marker line. + */ +export function logTruncationMarker(maxBytes: number): string { + return `[dsh-code-runtime-python] log capture truncated at ${maxBytes} bytes` +} + +/** + * Serialize one JSON-parse-produced value without recursion. `JSON.stringify` + * recurses per nesting level and throws `RangeError` a few thousand levels + * deep, but the seam's `CodeJsonValue` has no depth limit — an honest deep + * completion or binding resolution below the byte budget must cross intact + * (the worker backend's wire is equally stack-safe). Callers must pass a value + * produced by `JSON.parse` (or equally JSON-plain): only `null`, finite + * numbers, booleans, strings, dense arrays, and plain objects — this encoder + * validates nothing. Output is byte-identical to compact `JSON.stringify`. + * @param value - a JSON-plain value (e.g. straight from `JSON.parse`). + * @returns the compact JSON encoding. + */ +export function encodeJsonPlain(value: unknown): string { + type Task = { text: string } | { value: unknown } + const chunks: string[] = [] + const tasks: Task[] = [{ value }] + for (let task = tasks.pop(); task !== undefined; task = tasks.pop()) { + if ('text' in task) { + chunks.push(task.text) + continue + } + const current = task.value + if (typeof current === 'string') { + chunks.push(JSON.stringify(current)) + } else if (Array.isArray(current)) { + chunks.push('[') + tasks.push({ text: ']' }) + for (let index = current.length - 1; index >= 0; index--) { + if (index < current.length - 1) tasks.push({ text: ',' }) + tasks.push({ value: current[index] }) + } + } else if (typeof current === 'object' && current !== null) { + const record = current as Record + chunks.push('{') + tasks.push({ text: '}' }) + const keys = Object.keys(record) + for (let index = keys.length - 1; index >= 0; index--) { + const key = keys[index] as string + if (index < keys.length - 1) tasks.push({ text: ',' }) + tasks.push({ value: record[key] }) + tasks.push({ text: `${JSON.stringify(key)}:` }) + } + } else { + chunks.push(scalarJson(current)) + } + } + return chunks.join('') +} + +/** + * One scalar (null, boolean, finite number) as JSON text. A beyond-safe-range + * integral double needs BigInt digits: `String(2 ** 60)` emits the ROUNDED + * `...847000` form, and echoing that to the child would silently change the + * integer the seam promised to carry losslessly — `BigInt(2 ** 60)` prints the + * exact `...846976` the double actually holds. + * @param current - a JSON-plain scalar (JSON.parse emits nothing else). + * @returns its JSON encoding. + */ +function scalarJson(current: unknown): string { + if (typeof current === 'number' && Number.isInteger(current) && !Number.isSafeInteger(current)) { + return BigInt(current).toString() + } + return String(current) +} + +/** + * Meter a forged done value's compact-JSON byte length AND its number + * losslessness in one bounded traversal, stopping the instant `maxBytes` is + * crossed. A forged `done.value` arrives straight off fd 3 and can sit anywhere + * below the 256 MiB frame ceiling while `maxValueBytes` defaults to 32 KiB. The + * previous split — an unbounded `hasNonLosslessNumber` scan in + * {@link validateChildFrame} followed by a separate byte meter — pushed every + * member of a wide flat payload onto a scan stack before any cap check ran, so + * a below-ceiling forgery could still force a hundreds-of-megabytes host + * allocation. Folding both jobs here rejects over-budget BEFORE enqueuing an + * array's or object's children, keeping the traversal O(cap). A non-lossless + * number (non-finite, negative zero) is caught only when the value fits the + * budget — an over-budget value is rejected regardless, so the distinction is + * moot. Same JSON-plain precondition and traversal shape as + * {@link encodeJsonPlain}; per-scalar encoding delegates to `JSON.stringify`. + * @param value - a JSON-plain value (e.g. straight from `JSON.parse`). + * @param maxBytes - the completion-value budget in bytes. + * @returns `{ ok: true, bytes }` with the exact serialized size, or + * `{ ok: false, reason }` — `over-budget` once the size exceeds `maxBytes`, + * `non-lossless` on a non-finite or negative-zero number. + */ +export function checkDoneValue(value: unknown, maxBytes: number): { ok: true; bytes: number } | { ok: false; reason: 'over-budget' | 'non-lossless' } { + let bytes = 0 + const stack: unknown[] = [value] + while (stack.length > 0) { + const current = stack.pop() + if (typeof current === 'number') { + if (!Number.isFinite(current) || Object.is(current, -0)) return { ok: false, reason: 'non-lossless' } + bytes += Buffer.byteLength(scalarJson(current), 'utf8') + } else if (typeof current === 'string') { + // Lower-bound BEFORE materializing the escaped form: every UTF-16 code + // unit is at least one UTF-8 byte plus the two quotes, so a huge or + // control-heavy forged string (whose escaped copy expands severalfold) + // is rejected without allocating that copy. + if (bytes + current.length + 2 > maxBytes) return { ok: false, reason: 'over-budget' } + bytes += Buffer.byteLength(JSON.stringify(current), 'utf8') + } else if (Array.isArray(current)) { + // Brackets plus one comma per gap; elements add themselves. Reject + // BEFORE enqueuing children: every element serializes to at least one + // byte, so a forged flat array below the frame ceiling but far above + // the budget fails here without growing the host stack by millions of + // entries first. + bytes += 2 + (current.length > 1 ? current.length - 1 : 0) + if (bytes + current.length > maxBytes) return { ok: false, reason: 'over-budget' } + for (const item of current) stack.push(item) + } else if (typeof current === 'object' && current !== null) { + const record = current as Record + // Count own keys WITHOUT Object.entries/Object.keys: either would + // allocate one slot (entries: one pair array) per member before the + // bound below could run, recreating the spike the bound exists to stop. + let count = 0 + for (const key in record) if (Object.hasOwn(record, key)) count += 1 + bytes += 2 + (count > 1 ? count - 1 : 0) + // Same pre-enqueue bound: each entry contributes its quoted key (>= 2 + // bytes), the colon, and a >= 1-byte value. + if (bytes + count * 4 > maxBytes) return { ok: false, reason: 'over-budget' } + for (const key in record) { + if (!Object.hasOwn(record, key)) continue + // The same string lower bound, before escaping the key. + if (bytes + key.length + 3 > maxBytes) return { ok: false, reason: 'over-budget' } + bytes += Buffer.byteLength(JSON.stringify(key), 'utf8') + 1 + stack.push(record[key]) + } + } else { + bytes += Buffer.byteLength(scalarJson(current), 'utf8') + } + if (bytes > maxBytes) return { ok: false, reason: 'over-budget' } + } + return { ok: true, bytes } +} + +/** + * Whether a raw JSON line contains an integer token that would lose precision + * as a JavaScript number. `JSON.parse` silently rounds such a token + * (`9007199254740993` becomes `...992`) BEFORE any validation can see it, so + * the check must read the source text; a beyond-safe-range token whose double + * parse round-trips exactly (`2**53`, `2**60`) is lossless and passes. The scan walks the line skipping string literals (a digit run + * inside a string is data, not a number token) and tests every number token + * in plain integer form — no fraction or exponent, which parse as doubles by + * intent. A reviver cannot do this job: the reviver walk recurses per nesting + * level and would reintroduce the depth limit `encodeJsonPlain` removes. + * @param line - the raw UTF-8 text of one JSON-lines frame. + * @returns true when an unsafe integer token is present outside strings. + */ +export function hasUnsafeIntegerToken(line: string): boolean { + for (let index = 0; index < line.length; index++) { + const char = line[index] + if (char === '"') { + // Skip the string literal, honoring backslash escapes. + for (index++; index < line.length; index++) { + if (line[index] === '\\') index++ + else if (line[index] === '"') break + } + continue + } + if (char === '-' || (char !== undefined && char >= '0' && char <= '9')) { + let end = index + 1 + while (end < line.length) { + const c = line[end] as string + if ((c >= '0' && c <= '9') || c === '.' || c === 'e' || c === 'E' || c === '+' || c === '-') end++ + else break + } + const token = line.slice(index, end) + // Beyond the safe range an integer token is still lossless IFF the + // double parse round-trips exactly (2**53 does; 2**53+1 rounds) — the + // canonical boundary accepts every JS-double-exact value, so only a + // genuinely rounding token marks the frame as forged. + if (/^-?\d+$/.test(token)) { + const parsed = Number(token) + // A token that parses to Infinity is trivially lossy; a finite + // beyond-safe-range one is lossy only when the BigInt round-trip + // disagrees. + if (!Number.isFinite(parsed)) return true + if (!Number.isSafeInteger(parsed) && BigInt(token) !== BigInt(parsed)) return true + } + index = end - 1 + } + } + return false +} + +/** + * Lazily yield one plain object's own enumerable property values. A generator + * (not `Object.values`/`Object.entries`) because {@link hasNonLosslessNumber} + * traverses breadth it cannot bound: those helpers copy the whole member list + * up front, so a wide forged object would cost a second full-breadth + * allocation before a single value is examined. + * @param record - a JSON-parse-produced object. + * @yields each own enumerable property value, in key order. + */ +function* ownValues(record: object): Generator { + for (const key in record) { + if (Object.hasOwn(record, key)) yield (record as Record)[key] + } +} + +/** + * Whether a JSON.parse-produced value contains a number outside lossless + * JSON: non-finite (`1e400` parses to `Infinity`) or negative zero (`-0.0` + * parses to JS `-0`, whose sign bit a re-serialization drops). The honest + * child's validator rejects these before sending, so a frame carrying one is + * forged. + * + * Runs on `call.args`, which — unlike a completion value — has NO seam byte + * cap, so there is no budget to reject a wide payload against the way + * {@link checkDoneValue} does. The traversal therefore holds ONE cursor per + * NESTING LEVEL (an array or {@link ownValues} iterator) instead of one entry + * per member: a forged flat `args` just below the 256 MiB frame ceiling would + * otherwise push tens of millions of stack entries — and `Object.values` would + * copy each object's full breadth — allocating hundreds of megabytes beyond + * what `JSON.parse` already holds. Iterative either way, so a deep frame + * cannot overflow the host stack. + * @param value - a JSON-parse-produced value from an fd-3 frame. + * @returns true when any contained number is non-finite or negative zero. + */ +export function hasNonLosslessNumber(value: unknown): boolean { + const cursors: Iterator[] = [[value].values()] + while (cursors.length > 0) { + // The loop condition guarantees a top cursor. + const cursor = cursors.at(-1) as Iterator + const step = cursor.next() + if (step.done === true) { + cursors.pop() + continue + } + const current = step.value + if (typeof current === 'number') { + if (!Number.isFinite(current) || Object.is(current, -0)) return true + } else if (Array.isArray(current)) { + cursors.push((current as unknown[]).values()) + } else if (typeof current === 'object' && current !== null) { + cursors.push(ownValues(current)) + } + } + return false +} + +/** + * Runtime shape gate for inbound fd-3 traffic. Model code has full access to + * fd 3 and can post anything — `null`, primitives, poisoned fields — so the + * compile-time union means nothing here: every field is validated and REBUILT + * before the host reads it (forged extras never ride along; a non-number id + * can never be echoed into a reply). Junk returns `undefined` and is dropped + * so a throw in the host's `message` handler cannot crash the host process. + * @param raw - one JSON-parsed frame from fd 3. + * @returns the rebuilt frame, or `undefined` to drop it silently. + */ +export function validateChildFrame(raw: unknown): ChildToHost | undefined { + if (typeof raw !== 'object' || raw === null) return undefined + const m = raw as Record + switch (m.type) { + case 'boot-ack': + return { type: 'boot-ack' } + case 'log': + if (typeof m.text !== 'string') return undefined + // Rebuilt, not passed through: a forged `truncated` of any other type + // would reach the host as a truthy value and silence capture for the + // rest of the run. Only the literal `true` counts. + return { type: 'log', text: m.text, ...m.truncated === true ? { truncated: true } : {} } + case 'call': { + // The id must be a finite number: it is echoed verbatim into the reply + // frame, and a forged `1e400` id (Infinity after JSON.parse) would make + // the reply unencodable as strict JSON. + if (typeof m.id !== 'number' || !Number.isFinite(m.id) || typeof m.global !== 'string' || typeof m.name !== 'string') return undefined + // A forged frame can omit `args` entirely; rebuilding it as `undefined` + // would invoke the binding with a non-JSON value, bypassing the + // lossless-JSON argument boundary. Any PRESENT value is JSON-plain by + // construction (the frame came from JSON.parse), so presence is the + // whole check. + if (!Object.hasOwn(m, 'args')) return undefined + // JSON.parse yields Infinity for 1e400 and preserves -0; both are + // outside lossless JSON, and the honest child never sends them. + if (hasNonLosslessNumber(m.args)) return undefined + return { type: 'call', id: m.id, global: m.global, name: m.name, args: m.args } + } + case 'done': { + // The value passes through untouched here: scanning it for non-lossless + // numbers would push every member of a wide forged payload before any + // byte cap runs. The done handler's bounded `checkDoneValue` folds the + // losslessness check into the metered traversal, rejecting over-budget + // before it enqueues children. + const err = m.error + if (err === undefined) { + return m.value === undefined ? { type: 'done' } : { type: 'done', value: m.value } + } + if (typeof err !== 'object' || err === null) return undefined + const { kind, message } = err as Record + if (typeof message !== 'string') return undefined + if (kind !== 'exception' && kind !== 'invalid-output' && kind !== 'output-limit') return undefined + return m.value === undefined + ? { type: 'done', error: { kind, message } } + : { type: 'done', value: m.value, error: { kind, message } } + } + default: + return undefined + } +} diff --git a/packages/code-runtime/code-runtime-python/tests/protocol-mirror.e2e.ts b/packages/code-runtime/code-runtime-python/tests/protocol-mirror.e2e.ts new file mode 100644 index 0000000000..9ec1091286 --- /dev/null +++ b/packages/code-runtime/code-runtime-python/tests/protocol-mirror.e2e.ts @@ -0,0 +1,60 @@ +import { execFile } from 'node:child_process' +import { existsSync } from 'node:fs' +import { fileURLToPath } from 'node:url' +import { promisify } from 'node:util' +import { describe, expect, it } from 'vitest' +import { logTruncationMarker } from '../src/protocol.ts' + +/** + * Cross-language mirror check for the two protocol surfaces the host and the + * CPython subprocess share at runtime, spawning a real `python3` to read them + * from `py/protocol.py`. `src/protocol.ts` and `py/protocol.py` declare the same + * frame vocabulary on two sides of the wire; the only values both sides EXECUTE + * against are `PROTOCOL_FD` (the fd the channel is pinned to) and the log + * truncation marker text (emitted verbatim by whichever ledger exhausts first), + * so a drift there silently corrupts a live run. Self-skips when no `python3` is + * on PATH — CI provides one; the pure-TS `protocol.spec.ts` covers the host + * codec unconditionally. + */ + +const execFileAsync = promisify(execFile) +const pyDir = fileURLToPath(new URL('../py', import.meta.url)) + +async function hasPython3(): Promise { + try { + await execFileAsync('python3', ['--version']) + return true + } catch { + return false + } +} + +const python3Available = await hasPython3() + +describe.skipIf(!python3Available)('protocol.py mirrors protocol.ts at runtime', () => { + it('agrees on PROTOCOL_FD and the log truncation marker across byte budgets', async () => { + const budgets = [1, 65536, 1048576] + const probe = [ + 'import json, sys', + `sys.path.insert(0, ${JSON.stringify(pyDir)})`, + 'from protocol import PROTOCOL_FD, log_truncation_marker', + `budgets = ${JSON.stringify(budgets)}`, + 'print(json.dumps({', + ' "fd": PROTOCOL_FD,', + ' "markers": [log_truncation_marker(b) for b in budgets],', + '}))', + ].join('\n') + const { stdout } = await execFileAsync('python3', ['-I', '-c', probe]) + const seen = JSON.parse(stdout) as { fd: number; markers: string[] } + // fd 3 is the wire contract, not a tunable: index.ts pins it positionally. + expect(seen.fd).toBe(3) + expect(seen.markers).toEqual(budgets.map(budget => logTruncationMarker(budget))) + }) +}) + +it('names the py/ directory that ships with the package', () => { + // The package.json `files` list ships `py/**/*.py`; the mirror test resolves + // the marker source relative to the built package, so the directory must exist + // beside the tests even when python3 is absent from the runner. + expect(existsSync(pyDir)).toBe(true) +}) diff --git a/packages/code-runtime/code-runtime-python/tests/protocol.spec.ts b/packages/code-runtime/code-runtime-python/tests/protocol.spec.ts new file mode 100644 index 0000000000..d3782b6c95 --- /dev/null +++ b/packages/code-runtime/code-runtime-python/tests/protocol.spec.ts @@ -0,0 +1,239 @@ +import { describe, expect, it } from 'vitest' +import { checkDoneValue, encodeJsonPlain, hasNonLosslessNumber, hasUnsafeIntegerToken, logTruncationMarker, validateChildFrame } from '../src/index.ts' + +describe('logTruncationMarker', () => { + it('names the configured byte budget', () => { + expect(logTruncationMarker(65536)).toBe('[dsh-code-runtime-python] log capture truncated at 65536 bytes') + expect(logTruncationMarker(1)).toBe('[dsh-code-runtime-python] log capture truncated at 1 bytes') + }) +}) + +describe('validateChildFrame', () => { + it('rebuilds boot-ack frames without extra fields', () => { + expect(validateChildFrame({ type: 'boot-ack' })).toEqual({ type: 'boot-ack' }) + // Forged extras never ride along. + expect(validateChildFrame({ type: 'boot-ack', extra: 'x' })).toEqual({ type: 'boot-ack' }) + }) + + it('rebuilds log frames when the text field is a string', () => { + expect(validateChildFrame({ type: 'log', text: 'hi' })).toEqual({ type: 'log', text: 'hi' }) + // Non-string text drops. + expect(validateChildFrame({ type: 'log', text: 42 })).toBeUndefined() + expect(validateChildFrame({ type: 'log' })).toBeUndefined() + }) + + it('rebuilds call frames with a numeric id, string global, and string name', () => { + expect(validateChildFrame({ type: 'call', id: 1, global: 'tools', name: 'echo', args: { x: 1 } })) + .toEqual({ type: 'call', id: 1, global: 'tools', name: 'echo', args: { x: 1 } }) + // A frame with NO args key drops whole: rebuilding it as `undefined` + // would invoke the binding with a non-JSON value, bypassing the + // lossless-JSON argument boundary. Any present value is JSON-plain by + // construction (frames arrive via JSON.parse), so null passes. + expect(validateChildFrame({ type: 'call', id: 2, global: 'tools', name: 'echo' })).toBeUndefined() + expect(validateChildFrame({ type: 'call', id: 2, global: 'tools', name: 'echo', args: null })) + .toEqual({ type: 'call', id: 2, global: 'tools', name: 'echo', args: null }) + // A missing/mistyped required field drops. + expect(validateChildFrame({ type: 'call', id: '1', global: 'tools', name: 'echo' })).toBeUndefined() + expect(validateChildFrame({ type: 'call', id: 1, global: 7, name: 'echo' })).toBeUndefined() + expect(validateChildFrame({ type: 'call', id: 1, global: 'tools' })).toBeUndefined() + }) + + it('rebuilds done frames with optional value/error', () => { + expect(validateChildFrame({ type: 'done' })).toEqual({ type: 'done' }) + expect(validateChildFrame({ type: 'done', value: 42 })).toEqual({ type: 'done', value: 42 }) + expect(validateChildFrame({ type: 'done', error: { kind: 'exception', message: 'boom' } })) + .toEqual({ type: 'done', error: { kind: 'exception', message: 'boom' } }) + expect(validateChildFrame({ type: 'done', error: { kind: 'invalid-output', message: 'lossy' } })) + .toEqual({ type: 'done', error: { kind: 'invalid-output', message: 'lossy' } }) + expect(validateChildFrame({ type: 'done', error: { kind: 'output-limit', message: 'big' } })) + .toEqual({ type: 'done', error: { kind: 'output-limit', message: 'big' } }) + expect(validateChildFrame({ type: 'done', value: 1, error: { kind: 'exception', message: 'boom' } })) + .toEqual({ type: 'done', value: 1, error: { kind: 'exception', message: 'boom' } }) + // A `value: undefined` field is dropped (JSON never carries it, but a forged + // shape might; the rebuild coalesces to the absent case). + expect(validateChildFrame({ type: 'done', value: undefined })).toEqual({ type: 'done' }) + // A missing or unrecognized kind drops the frame: the child always sends + // one of the three, so anything else is a forgery. + expect(validateChildFrame({ type: 'done', error: { message: 'boom' } })).toBeUndefined() + expect(validateChildFrame({ type: 'done', error: { kind: 'timeout', message: 'x' } })).toBeUndefined() + }) + + it('rejects malformed done frames', () => { + // error must be an object. + expect(validateChildFrame({ type: 'done', error: 'boom' })).toBeUndefined() + expect(validateChildFrame({ type: 'done', error: null })).toBeUndefined() + // error.message must be a string. + expect(validateChildFrame({ type: 'done', error: {} })).toBeUndefined() + expect(validateChildFrame({ type: 'done', error: { message: 42 } })).toBeUndefined() + }) + + it('drops non-object inputs and unknown types silently', () => { + expect(validateChildFrame(null)).toBeUndefined() + expect(validateChildFrame(undefined)).toBeUndefined() + expect(validateChildFrame(42)).toBeUndefined() + expect(validateChildFrame('str')).toBeUndefined() + expect(validateChildFrame({})).toBeUndefined() + expect(validateChildFrame({ type: 'unknown' })).toBeUndefined() + }) + + it('drops CALL frames whose args are non-finite or negative zero', () => { + // JSON.parse turns 1e400 into Infinity and preserves -0; the honest child + // rejects both before sending, so a call frame carrying one is forged. + expect(validateChildFrame({ type: 'call', id: 1, global: 'tools', name: 'x', args: { n: Infinity } })).toBeUndefined() + expect(validateChildFrame({ type: 'call', id: Infinity, global: 'tools', name: 'x', args: null })).toBeUndefined() + // Plain zero and ordinary floats pass. + expect(validateChildFrame({ type: 'call', id: 1, global: 'tools', name: 'x', args: [0, 1.5] })) + .toEqual({ type: 'call', id: 1, global: 'tools', name: 'x', args: [0, 1.5] }) + }) + + it('passes DONE values through untouched — losslessness is metered later', () => { + // validateChildFrame no longer scans done.value: an unbounded scan would + // push every member of a wide forged payload before any byte cap ran. The + // done handler's checkDoneValue folds losslessness into the metered walk. + expect(validateChildFrame({ type: 'done', value: Infinity })).toEqual({ type: 'done', value: Infinity }) + expect(validateChildFrame({ type: 'done', value: [{ x: -0 }] })).toEqual({ type: 'done', value: [{ x: -0 }] }) + expect(validateChildFrame({ type: 'done', value: [0, 1.5] })).toEqual({ type: 'done', value: [0, 1.5] }) + }) +}) + +describe('lossless-number scan', () => { + it('finds non-finite and negative-zero numbers at any depth, iteratively', () => { + expect(hasNonLosslessNumber(Infinity)).toBe(true) + expect(hasNonLosslessNumber(-Infinity)).toBe(true) + expect(hasNonLosslessNumber(NaN)).toBe(true) + expect(hasNonLosslessNumber(-0)).toBe(true) + expect(hasNonLosslessNumber({ a: [1, { b: -0 }] })).toBe(true) + expect(hasNonLosslessNumber({ a: [0, 1.5, 'x', null, true] })).toBe(false) + // Deep nesting must not overflow the stack. + let deep: unknown = 0 + for (let i = 0; i < 100000; i++) deep = [deep] + expect(hasNonLosslessNumber(deep)).toBe(false) + }) + + it('walks wide arrays and objects one member at a time', () => { + // `call.args` carries no seam byte cap, so a wide forged payload has no + // budget to be rejected against — the walk must hold one cursor per + // NESTING LEVEL, not one entry per member, or a flat payload just below + // the 256 MiB frame ceiling would allocate tens of millions of stack + // entries (and `Object.values` a second full-breadth copy). Observable + // through the boundary: a wide payload whose per-member cost the old shape + // would have paid still scans, and a violation ANYWHERE in it is found + // wherever it sits. + const wideArray = new Array(2_000_000).fill(0) as unknown[] + expect(hasNonLosslessNumber(wideArray)).toBe(false) + // Last element, so the cursor must run the whole breadth lazily. + wideArray[wideArray.length - 1] = -0 + expect(hasNonLosslessNumber(wideArray)).toBe(true) + const wideObject: Record = {} + for (let i = 0; i < 200_000; i++) wideObject[`k${i}`] = i + expect(hasNonLosslessNumber(wideObject)).toBe(false) + wideObject.last = Infinity + expect(hasNonLosslessNumber(wideObject)).toBe(true) + // Interleaved nesting: a per-level cursor must resume its parent after a + // child level ends, so a violation after a nested container is still seen. + expect(hasNonLosslessNumber([[1], { a: 2 }, NaN])).toBe(true) + }) + + it('scans only own enumerable properties', () => { + // The per-level cursor filters own keys (a prototype-carrying frame is + // impossible off JSON.parse, but the filter is what keeps the walk equal + // to what the encoder would serialize). + const withProto = Object.create({ inherited: -0 }) as Record + withProto.own = 1 + expect(hasNonLosslessNumber(withProto)).toBe(false) + }) +}) + +describe('unsafe-integer token scan', () => { + it('flags integer tokens outside the safe range, skipping strings and float forms', () => { + expect(hasUnsafeIntegerToken('{"v":9007199254740993}')).toBe(true) + // Exact beyond-safe-range tokens are lossless and pass (2**53, 2**64). + expect(hasUnsafeIntegerToken('{"v":9007199254740992}')).toBe(false) + expect(hasUnsafeIntegerToken('{"v":18446744073709551616}')).toBe(false) + // A token that parses to Infinity is trivially lossy. + expect(hasUnsafeIntegerToken(`{"v":${'9'.repeat(400)}}`)).toBe(true) + expect(hasUnsafeIntegerToken('{"v":-9007199254740993}')).toBe(true) + expect(hasUnsafeIntegerToken('{"v":9007199254740991}')).toBe(false) + expect(hasUnsafeIntegerToken('{"v":"9007199254740993"}')).toBe(false) + expect(hasUnsafeIntegerToken(String.raw`{"v":"esc\"9007199254740993"}`)).toBe(false) + expect(hasUnsafeIntegerToken('{"v":9007199254740993.0}')).toBe(false) + expect(hasUnsafeIntegerToken('{"v":9e99}')).toBe(false) + }) +}) + +describe('checkDoneValue', () => { + it('matches the exact encoded size and rejects one byte over', () => { + const cases: unknown[] = [null, true, false, 0, -1.5, 'a"b\\', [], {}, [1, 'x', null], { a: [1, 2], b: { c: 'd' } }] + for (const value of cases) { + const exact = Buffer.byteLength(JSON.stringify(value), 'utf8') + expect(checkDoneValue(value, exact), JSON.stringify(value)).toEqual({ ok: true, bytes: exact }) + expect(checkDoneValue(value, exact - 1), JSON.stringify(value)).toEqual({ ok: false, reason: 'over-budget' }) + expect(encodeJsonPlain(value)).toBe(JSON.stringify(value)) + } + }) + + it('stops early on a huge value instead of measuring it whole', () => { + const huge = { data: 'x'.repeat(1_000_000), tail: 'y' } + expect(checkDoneValue(huge, 1024)).toEqual({ ok: false, reason: 'over-budget' }) + // A forged flat array below the frame ceiling must fail BEFORE its + // elements are enqueued — the pre-enqueue bound keeps the walk O(cap). + const flat = new Array(10_000_000).fill(0) + expect(checkDoneValue(flat, 1024)).toEqual({ ok: false, reason: 'over-budget' }) + // Same bound for a wide object: braces+commas fit the cap, but the + // per-entry lower bound (quoted key + colon + value) does not, so it fails + // before any key is metered or any value enqueued. + const wide: Record = {} + for (let i = 0; i < 10; i++) wide[`k${i}`] = i + expect(checkDoneValue(wide, 12)).toEqual({ ok: false, reason: 'over-budget' }) + }) + + it('rejects an over-budget string on its length before escaping it', () => { + // A control-heavy forged string escapes to ~6x its length; the walk must + // refuse it on the cheap `length + 2` lower bound so the escaped copy is + // never allocated. Observable through the boundary: a string whose LENGTH + // already exceeds the cap fails even though every character is 1 byte. + expect(checkDoneValue(''.repeat(4096), 1024)).toEqual({ ok: false, reason: 'over-budget' }) + // The bound is a lower bound, never a false rejection: a string that fits + // exactly still passes with its exact escaped size. + expect(checkDoneValue('', 8)).toEqual({ ok: true, bytes: 8 }) + expect(checkDoneValue('', 7)).toEqual({ ok: false, reason: 'over-budget' }) + // Same lower bound for keys, checked before the key is escaped. + expect(checkDoneValue({ [''.repeat(4096)]: 1 }, 1024)).toEqual({ ok: false, reason: 'over-budget' }) + }) + + it('meters only own enumerable keys', () => { + // The walk counts keys with a `for...in` + hasOwn pass rather than + // Object.keys/entries (which allocate per member before the bound). A + // prototype-carrying forgery is impossible off JSON.parse, but the own-key + // filter is what keeps the count equal to the encoder's. + const withProto = Object.create({ inherited: 'x' }) as Record + withProto.own = 1 + expect(checkDoneValue(withProto, 1024)).toEqual({ ok: true, bytes: Buffer.byteLength('{"own":1}', 'utf8') }) + }) + + it('rejects non-finite and negative-zero numbers at any depth as non-lossless', () => { + expect(checkDoneValue(Infinity, 1024)).toEqual({ ok: false, reason: 'non-lossless' }) + expect(checkDoneValue(-Infinity, 1024)).toEqual({ ok: false, reason: 'non-lossless' }) + expect(checkDoneValue(NaN, 1024)).toEqual({ ok: false, reason: 'non-lossless' }) + expect(checkDoneValue(-0, 1024)).toEqual({ ok: false, reason: 'non-lossless' }) + expect(checkDoneValue({ a: [1, { b: -0 }] }, 1024)).toEqual({ ok: false, reason: 'non-lossless' }) + // An ordinary finite value within budget passes with its exact byte count. + const clean = { a: [0, 1.5, 'x', null, true] } + expect(checkDoneValue(clean, 1024)).toEqual({ ok: true, bytes: Buffer.byteLength(JSON.stringify(clean), 'utf8') }) + }) + + it('meters deep nesting iteratively without overflowing the stack', () => { + let deep: unknown = 0 + for (let i = 0; i < 100_000; i++) deep = [deep] + // 100000 '[' + '0' + 100000 ']' = 200001 bytes. + expect(checkDoneValue(deep, 1_000_000)).toEqual({ ok: true, bytes: 200_001 }) + }) + + it('emits exact digits for beyond-safe integral doubles', () => { + // String(2**60) prints the ROUNDED ...847000; echoing that to the child + // would change the integer. BigInt digits give the exact ...846976. + const v = JSON.parse('[1152921504606846976]') as unknown + expect(encodeJsonPlain(v)).toBe('[1152921504606846976]') + expect(checkDoneValue(v, 100)).toEqual({ ok: true, bytes: Buffer.byteLength('[1152921504606846976]', 'utf8') }) + }) +}) diff --git a/packages/code-runtime/code-runtime-python/tsconfig.json b/packages/code-runtime/code-runtime-python/tsconfig.json new file mode 100644 index 0000000000..9966c8ca8a --- /dev/null +++ b/packages/code-runtime/code-runtime-python/tsconfig.json @@ -0,0 +1,21 @@ +{ + "extends": "../../../tsconfig.base.json", + "compilerOptions": { + "rootDir": "src", + "outDir": "lib/types" + }, + "include": [ + "src" + ], + "references": [ + { + "path": "../../../vendor/cosmokit" + }, + { + "path": "../../../vendor/cordis" + }, + { + "path": "../../support/invariants" + } + ] +} diff --git a/packages/code-runtime/code-runtime-python/tsdown.config.ts b/packages/code-runtime/code-runtime-python/tsdown.config.ts new file mode 100644 index 0000000000..df5bdeae1e --- /dev/null +++ b/packages/code-runtime/code-runtime-python/tsdown.config.ts @@ -0,0 +1,16 @@ +import { defineConfig } from 'tsdown' + +/** + * Single ESM bundle. The Python-side code is not TypeScript and ships verbatim + * under `py/` (whitelisted in package.json `files`) — no build step needed. + */ +export default defineConfig({ + entry: ['lib/types/index.js', 'lib/types/invariant.js'], + outDir: 'lib', + format: ['esm'], + platform: 'node', + target: 'es2024', + fixedExtension: false, + dts: false, + clean: false, +}) diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 8f34b3587b..072d5674a3 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -2337,6 +2337,18 @@ importers: specifier: ^4.0.0-rc.7 version: link:../../../vendor/cordis + packages/code-runtime/code-runtime-python: + devDependencies: + '@deepseek-ai/dsh-code-runtime': + specifier: workspace:^ + version: link:../code-runtime + '@deepseek-ai/dsh-invariants': + specifier: workspace:^ + version: link:../../support/invariants + cordis: + specifier: ^4.0.0-rc.7 + version: link:../../../vendor/cordis + packages/code-runtime/code-runtime-worker: dependencies: schemastery: diff --git a/scripts/check-workspace-constraints.ts b/scripts/check-workspace-constraints.ts index e0b9344cdf..0b0069ffde 100644 --- a/scripts/check-workspace-constraints.ts +++ b/scripts/check-workspace-constraints.ts @@ -107,6 +107,8 @@ const packageFileExtras: Readonly> = { '@deepseek-ai/dsh-web-app': ['cordis.patch.yml'], '@deepseek-ai/dsh-headless': ['cordis.patch.yml'], '@deepseek-ai/dsh-client-ui-theme': ['lib/styles'], + // The CPython bootstrap ships as source .py files the host spawns by path. + '@deepseek-ai/dsh-code-runtime-python': ['py/**/*.py'], '@deepseek-ai/dsh-helper': ['lib/assets'], '@deepseek-ai/dsh-pty-local': ['scripts/ensure-spawn-helper.mjs'], '@deepseek-ai/dsh-scripts': [ diff --git a/scripts/verify-package-readme-model-experience.ts b/scripts/verify-package-readme-model-experience.ts index 316a4233de..e873b3df78 100644 --- a/scripts/verify-package-readme-model-experience.ts +++ b/scripts/verify-package-readme-model-experience.ts @@ -47,6 +47,7 @@ const SENTENCE_MODEL_EXPERIENCE: Readonly> = { 'packages/bash/pwsh-local': { kind: 'indirect', reason: 'The executor backend delegates model rendering to dsh-tool-pwsh.' }, 'packages/code-runtime/code-runtime': { kind: 'indirect', reason: 'The service interface delegates model rendering to Code Mode in dsh-tools.' }, 'packages/code-runtime/code-runtime-worker': { kind: 'indirect', reason: 'The worker backend delegates model rendering to Code Mode in dsh-tools.' }, + 'packages/code-runtime/code-runtime-python': { kind: 'indirect', reason: 'The CPython subprocess backend delegates model rendering to Code Mode in dsh-tools.' }, 'packages/typert/registry': { kind: 'none', reason: 'Runtime type registry; consumers (cordis_inspect, wire faces, gates) own any model-visible projection of registry contents.' }, 'packages/typert/loader': { kind: 'none', reason: 'Loader integration only registers generated artifacts; consumers own any model-visible projection.' }, 'packages/client/hmr': { kind: 'none', reason: 'Browser-side UI plugin layer; registers no model surface.' }, diff --git a/tsconfig.host.json b/tsconfig.host.json index 5772905a9e..8962016791 100644 --- a/tsconfig.host.json +++ b/tsconfig.host.json @@ -154,6 +154,7 @@ { "path": "./packages/pty/tool-bash-persistent" }, { "path": "./packages/pty/tool-pty" }, { "path": "./packages/code-runtime/code-runtime" }, + { "path": "./packages/code-runtime/code-runtime-python" }, { "path": "./packages/code-runtime/code-runtime-worker" }, { "path": "./packages/llm/llm-deepseek" }, { "path": "./packages/llm/llm-pi-ai" },