fix(tools): forward nested image results in code mode
This commit is contained in:
Tianyi Cui
@@ -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 packages/core/tools/README.md
|
||||
README.md: 44eb25b79436a75f08406102fc1e3734e59b1001
|
||||
README.zh.md: 35142d8186b21b2930ccc40386bed8cc677d77c3
|
||||
README.md: 88fe6660f169f69a70e5630f853104a7c83a5b3c
|
||||
README.zh.md: b65892caa86c64971bf4483c21d5fc765183c6e6
|
||||
|
||||
@@ -115,12 +115,12 @@ Returning `undefined` selects generic fallback. Presenters depend only on their
|
||||
|
||||
### Code Mode
|
||||
|
||||
Under `code` or `both`, the registry exposes the reserved `run_code` transport and a deterministic SDK for the current scope, generated in the loaded runtime's language — the registry selects the renderer by `ctx.codeRuntime.language` (`typescript` → the TypeScript SDK below, `python` → the Python SDK). Only the program's outer logs and return value re-enter model context. The SDK declares exact per-tool argument and canonical-output types for every visible tool (`ToolArgsMap`/`ToolOutputMap` in TypeScript, named `TypedDict`s in Python), and each binding resolves to the tool's canonical JSON value. Each lossless-JSON binding call re-enters the complete tool pipeline under the native scheduling contract (concurrency-safe calls may overlap up to `maxParallelSubCalls`; exclusive calls run alone as ordering barriers) with logged correlation to the outer call. Denials and other failed results reject with the real program-visible `ToolCallError` carrying only `toolName` and `message`; Native content and internal error codes stay outside the Code contract. Ordinary side effects are not rolled back, and sub-call `additionalContexts` are deferred through the parent result to preserve call/result adjacency. Run settlement aborts and drains outstanding bindings; runtime failures surface as `CodeRunFailedError`.
|
||||
Under `code` or `both`, the registry exposes the reserved `run_code` transport and a deterministic SDK for the current scope, generated in the loaded runtime's language — the registry selects the renderer by `ctx.codeRuntime.language` (`typescript` → the TypeScript SDK below, `python` → the Python SDK). The SDK declares exact per-tool argument and canonical-output types for every visible tool (`ToolArgsMap`/`ToolOutputMap` in TypeScript, named `TypedDict`s in Python), and each binding resolves to the tool's canonical JSON value. Each lossless-JSON binding call re-enters the complete tool pipeline under the native scheduling contract (concurrency-safe calls may overlap up to `maxParallelSubCalls`; exclusive calls run alone as ordering barriers) with logged correlation to the outer call. Denials and other failed results reject with the real program-visible `ToolCallError` carrying only `toolName` and `message`; Native content and internal error codes stay outside the Code contract. The program's outer logs and return value re-enter model context; when a successfully settled sub-call's final Native content contains an image, the bridge also defers that complete ordered content through the parent result so the image is not lost behind the JSON-only binding. Final post-execute blocking or content replacement is authoritative. Ordinary side effects are not rolled back, and sub-call `additionalContexts` are deferred through the parent result to preserve call/result adjacency. Run settlement aborts and drains outstanding bindings; runtime failures surface as `CodeRunFailedError`.
|
||||
|
||||
Under `code` — not `both` — the transport is also the only entry the model may use: a model-direct call naming any other visible tool resolves to `UNKNOWN_TOOL` at execution creation, before `tools/pre-execute`, approval `ask`, and guards, so nothing observes or approves a call that can only fail. The denial names the route back (`only \`run_code\` is callable directly — call \`<name>\` from inside a \`run_code\` program instead`), because the same prompt declares that tool and a bare `unknown tool` reads as a broken deployment. SDK sub-dispatches carry the outer execution's `parent` token and are exempt, so programs keep every binding the SDK declared. See the [executor-collapse note](../../../.agents/notes/implemented/bug-fix/2026-08-07-code-mode-executor-collapse.md), the [Code Mode foundation](../../../.agents/notes/implemented/feature/2026-06-15-code-mode.md), [typed-return contract](../../../.agents/notes/implemented/feature/2026-07-20-code-mode-typed-tool-returns.md), and [code-runtime seam](../../code-runtime/README.md). Try `pnpm run demo:code-mode`.
|
||||
|
||||
- **The SDK section** (`tools:sdk`, order 150): a lazy prompt section regenerating the language-appropriate SDK text at each assembly. In the TypeScript flavor it emits `JsonValue`, exact `ToolArgsMap` / `ToolOutputMap`, `ToolName`, the `ToolCallError` declaration, and a mapped `tools` namespace for the calling scope's visible end capabilities (exotic names via quoted keys), plus fixed usage instructions; the Python flavor (`ctx.codeRuntime.language === 'python'`) emits the equivalent named `TypedDict`s and a `tools` object with matching usage instructions. Deterministic — lexicographic tool order, byte-identical text for an unchanged tool set (prefix-cache-friendly). Both codegens are exported and never throw during prompt assembly: `jsonSchemaToTs` handles every unified schema construct and degrades unsupported raw constructs to `unknown`; `jsonSchemaToPy` does the same, degrading to `Any` (and a whole object to `dict[str, Any]` when a field name is not a legal `TypedDict` attribute, or whenever it is called outside the SDK render, which supplies the naming context a `TypedDict` declaration needs).
|
||||
- **The dispatch bridge** (`run_code`'s execute): every binding call is snapshotted as lossless JSON before dispatch (`undefined`, `BigInt`, cycles, sparse arrays, `-0`, and exotic objects reject that one call), scheduled through a per-run pool that reuses the native concurrency contract — calls start strictly in submission order, consecutive `isConcurrencySafe` calls overlap up to the validated `maxParallelSubCalls` config (default 10; `1` restores serial dispatch), and an exclusive-classified call drains the pool, runs alone, and bars later calls — given the outer execution's opaque token as `parent`, and run through the complete pre-execute → guards → execute → post-execute → result pipeline. A success returns the final canonical value after policy; a failure reaches the worker as one message and becomes `ToolCallError(toolName, message)`. Each started sub-call logs a `tool/code-dispatch-start` event (deterministic id `<parent>:code:<n>`, numbered by submission) at pipeline entry and settles with one `tool/code-dispatch` event carrying the complete model-facing `content`/`isError` outcome (the `tool/result` vocabulary, so UIs render sub-calls through the native path — the pair's `time` fields carry per-sub-call timing); a queued call abandoned by run settlement logs neither. `deriveMessages()` surfaces neither event nor persists the canonical value. Token correlation lets commit-style observers defer an inner success until the final `run_code` result without exposing the live outer execution; ordinary tool side effects are not rolled back. Every sub-call `additionalContexts` entry is deferred through the outer `ToolRunContext` in dispatch order; the loop appends those contexts only after the parent `run_code` result, preserving adjacency and retaining each source/meta even when the program later fails.
|
||||
- **The dispatch bridge** (`run_code`'s execute): every binding call is snapshotted as lossless JSON before dispatch (`undefined`, `BigInt`, cycles, sparse arrays, `-0`, and exotic objects reject that one call), scheduled through a per-run pool that reuses the native concurrency contract — calls start strictly in submission order, consecutive `isConcurrencySafe` calls overlap up to the validated `maxParallelSubCalls` config (default 10; `1` restores serial dispatch), and an exclusive-classified call drains the pool, runs alone, and bars later calls — given the outer execution's opaque token as `parent`, and run through the complete pre-execute → guards → execute → post-execute → result pipeline. A success returns the final canonical value after policy; a failure reaches the worker as one message and becomes `ToolCallError(toolName, message)`. Each started sub-call logs a `tool/code-dispatch-start` event (deterministic id `<parent>:code:<n>`, numbered by submission) at pipeline entry and settles with one `tool/code-dispatch` event carrying the complete model-facing `content`/`isError` outcome (the `tool/result` vocabulary, so UIs render sub-calls through the native path — the pair's `time` fields carry per-sub-call timing); a queued call abandoned by run settlement logs neither. `deriveMessages()` surfaces neither event nor persists the canonical value. Token correlation lets commit-style observers defer an inner success until the final `run_code` result without exposing the live outer execution; ordinary tool side effects are not rolled back. Every sub-call `additionalContexts` entry and every successful final content sequence containing an image is deferred through the outer `ToolRunContext` in dispatch order; the loop appends those contexts only after the parent `run_code` result, preserving adjacency and source attribution even when the program later fails.
|
||||
- **Settlement discipline**: the bridge owns a run-scoped abort that follows the outer signal in and fires when the run settles for any reason, so a budget expiry aborts an in-flight sub-tool instead of orphaning it; the bridge then drains its queue BEFORE returning, so every `tool/code-dispatch` lands inside the open turn. A failed run throws `CodeRunFailedError` (`code: 'CODE_RUN_FAILED'`, message = the failure kind + captured logs), which the pipeline converts to a structured `isError` the model self-corrects from.
|
||||
- **Result size**: intermediate binding values cross the worker process whole and have no per-binding byte cap. `run_code` returns canonical `{ logs: string[], result?: JsonValue }`; strings render raw, every other present JSON root renders through a stack-safe pretty JSON traversal whose total indentation is capped at ten characters (deeper subtrees stay compact), `null` remains explicit, and absent `result` means the program returned `undefined`. The worker's configurable `maxOutputBytes` (default 64 MiB) applies only to the combined serialized outer log-array, completion-value, or failure-message payloads; fixed result-envelope syntax and presentation whitespace are outside that limit. Invalid and over-limit completions fail explicitly, and only this outer result is eligible for ordinary spill.
|
||||
|
||||
@@ -177,7 +177,7 @@ Prefix-stable while the Code Mode selection, generated SDK, transport schema, an
|
||||
|
||||
#### What the model sees
|
||||
|
||||
The loop retains model-emitted arguments and the registry's final content. Any thrown or denied call becomes exactly `Error: <message>`. Code Mode returns only the outer program's printed lines and rendered return value, `(run_code completed with no output)` when both are empty, or `Error: code run failed (<kind>): <message>` followed conditionally by `Captured output:` and the captured lines. Inner dispatch events stay log-only; post-execute listeners may append source-attributed context after the result.
|
||||
The loop retains model-emitted arguments and the registry's final content. Any thrown or denied call becomes exactly `Error: <message>`. Code Mode renders the outer program's printed lines and return value, `(run_code completed with no output)` when both are empty, or `Error: code run failed (<kind>): <message>` followed conditionally by `Captured output:` and the captured lines. Inner dispatch events stay log-only, while a successful image-bearing sub-result is appended after the outer result as source-attributed context; post-execute listeners may append other source-attributed context at the same boundary.
|
||||
|
||||
#### Token effect
|
||||
|
||||
|
||||
@@ -115,12 +115,12 @@ ctx.tools.register(defineTool({
|
||||
|
||||
### Code Mode
|
||||
|
||||
在 `code` 或 `both` 模式下，注册表为当前作用域公开保留的 `run_code` 传输和按所加载运行时语言生成的确定性 SDK——注册表按 `ctx.codeRuntime.language` 选择渲染器（`typescript` → 下方的 TypeScript SDK，`python` → Python SDK）。只有程序的外层日志与返回值会重新进入模型上下文。SDK 为每个可见工具声明精确的参数与规范输出类型（TypeScript 为 `ToolArgsMap`/`ToolOutputMap`，Python 为具名 `TypedDict`），每个绑定都会解析为该工具的规范 JSON 值。每个无损 JSON 绑定调用都会在原生调度约定下重新进入完整工具流水线（并发安全的调用最多可重叠 `maxParallelSubCalls` 个；独占调用单独运行并构成排序屏障），并在日志中与外层调用建立关联。拒绝及其他失败结果会以程序实际可见的 `ToolCallError` 形式拒绝，且只携带 `toolName` 和 `message`；Native 内容和内部错误码留在 Code 约定之外。普通副作用不会回滚，子调用的 `additionalContexts` 会通过父结果延迟，以保持调用／结果相邻。运行结算会中止并排空尚未完成的绑定；运行时失败以 `CodeRunFailedError` 形式出现。
|
||||
在 `code` 或 `both` 模式下，注册表为当前作用域公开保留的 `run_code` 传输和按所加载运行时语言生成的确定性 SDK——注册表按 `ctx.codeRuntime.language` 选择渲染器（`typescript` → 下方的 TypeScript SDK，`python` → Python SDK）。SDK 为每个可见工具声明精确的参数与规范输出类型（TypeScript 为 `ToolArgsMap`/`ToolOutputMap`，Python 为具名 `TypedDict`），每个绑定都会解析为该工具的规范 JSON 值。每个无损 JSON 绑定调用都会在原生调度约定下重新进入完整工具流水线（并发安全的调用最多可重叠 `maxParallelSubCalls` 个；独占调用单独运行并构成排序屏障），并在日志中与外层调用建立关联。拒绝及其他失败结果会以程序实际可见的 `ToolCallError` 形式拒绝，且只携带 `toolName` 和 `message`；Native 内容和内部错误码留在 Code 约定之外。程序的外层日志与返回值会重新进入模型上下文；当成功结算的子调用最终 Native 内容包含图片时，桥接层还会经父结果延后完整有序内容，避免图片被 JSON 专用绑定遮蔽。最终 post-execute 阻止或内容替换具有权威性。普通副作用不会回滚，子调用的 `additionalContexts` 会通过父结果延迟，以保持调用／结果相邻。运行结算会中止并排空尚未完成的绑定；运行时失败以 `CodeRunFailedError` 形式出现。
|
||||
|
||||
在 `code`（而非 `both`）下，该传输同时也是模型唯一可用的入口：模型直呼其他任何可见工具名，都会在创建执行时、早于 `tools/pre-execute`、审批 `ask` 和 guards 解析为 `UNKNOWN_TOOL`，因此没有任何一方会观察或批准一个注定失败的调用。拒绝信息会给出正确路径（`only \`run_code\` is callable directly — call \`<name>\` from inside a \`run_code\` program instead`），因为同一份提示词刚刚声明过那个工具，只说 `unknown tool` 会被读成部署损坏。SDK 子分发携带外层执行的 `parent` token，不受此限制，因此程序保留 SDK 声明的全部绑定。参见[执行器塌缩 note](../../../.agents/notes/implemented/bug-fix/2026-08-07-code-mode-executor-collapse.md)、[Code Mode 基础](../../../.agents/notes/implemented/feature/2026-06-15-code-mode.md)、[类型化返回约定](../../../.agents/notes/implemented/feature/2026-07-20-code-mode-typed-tool-returns.md)和[代码运行时 seam](../../code-runtime/README.md)。可以运行 `pnpm run demo:code-mode` 试用。
|
||||
|
||||
- **SDK 段**（`tools:sdk`，顺序 150）：一个惰性提示词段，每次组装时都会重新生成与所加载运行时语言相符的 SDK 文本。TypeScript 形态发出 `JsonValue`、精确的 `ToolArgsMap` / `ToolOutputMap`、`ToolName`、`ToolCallError` 声明、面向调用作用域可见最终能力的映射 `tools` 命名空间（特殊名称使用带引号的键），以及固定用法说明；Python 形态（`ctx.codeRuntime.language === 'python'`）发出等价的具名 `TypedDict` 与一个带相同用法说明的 `tools` 对象。其输出具有确定性：工具按字典序排列；工具集合不变时，文本逐字节相同（有利于前缀 cache）。两个代码生成器都已导出，且绝不会在提示词组装期间抛出：`jsonSchemaToTs` 处理统一 schema 的每种构造并将不受支持的原始构造降级为 `unknown`；`jsonSchemaToPy` 同理，降级为 `Any`（当某字段名不是合法的 `TypedDict` 属性时，或在 SDK 渲染之外被调用时——`TypedDict` 声明所需的命名上下文由该渲染提供——整个对象降级为 `dict[str, Any]`）。
|
||||
- **分发桥接层**（`run_code` 的 execute）：每个绑定调用都会在分发前快照为无损 JSON（`undefined`、`BigInt`、循环、稀疏数组、`-0` 和特殊对象会使该次调用被拒绝），经由每次运行独有、复用原生并发约定的池调度——调用严格按提交顺序启动，连续的 `isConcurrencySafe` 调用最多可重叠经校验的 `maxParallelSubCalls` 配置个（默认 10；设为 `1` 即恢复串行分发），被分类为独占的调用先排空池、单独运行并阻挡其后的调用——以外层执行的不透明 token 作为 `parent`，并经过完整的 pre-execute → guards → execute → post-execute → result 流水线。成功会返回策略处理后的最终规范值；失败以一条消息到达 worker，并成为 `ToolCallError(toolName, message)`。每个已启动的子调用在进入流水线时记录一条 `tool/code-dispatch-start` 事件（确定性 id `<parent>:code:<n>`，按提交顺序编号），并以一条携带完整模型可见 `content`/`isError` 结果的 `tool/code-dispatch` 事件完结（采用 `tool/result` 词汇，因此 UI 会沿原生路径呈现子调用——这对事件的 `time` 字段承载每个子调用的计时）；因 run 结算而被放弃的排队调用两者都不记录。`deriveMessages()` 既不公开这两个事件，也不持久化规范值。token 关联让以提交为语义的观察器能够把内部成功延迟到最终 `run_code` 结果，而无需公开实时外层执行；普通工具副作用不会回滚。每个子调用的 `additionalContexts` 条目都会按分发顺序通过外层 `ToolRunContext` 延迟；循环只在父级 `run_code` 结果之后追加这些上下文，从而保持相邻关系，并且即使程序后来失败，也会保留各自的来源／元数据。
|
||||
- **分发桥接层**（`run_code` 的 execute）：每个绑定调用都会在分发前快照为无损 JSON（`undefined`、`BigInt`、循环、稀疏数组、`-0` 和特殊对象会使该次调用被拒绝），经由每次运行独有、复用原生并发约定的池调度——调用严格按提交顺序启动，连续的 `isConcurrencySafe` 调用最多可重叠经校验的 `maxParallelSubCalls` 配置个（默认 10；设为 `1` 即恢复串行分发），被分类为独占的调用先排空池、单独运行并阻挡其后的调用——以外层执行的不透明 token 作为 `parent`，并经过完整的 pre-execute → guards → execute → post-execute → result 流水线。成功会返回策略处理后的最终规范值；失败以一条消息到达 worker，并成为 `ToolCallError(toolName, message)`。每个已启动的子调用在进入流水线时记录一条 `tool/code-dispatch-start` 事件（确定性 id `<parent>:code:<n>`，按提交顺序编号），并以一条携带完整模型可见 `content`/`isError` 结果的 `tool/code-dispatch` 事件完结（采用 `tool/result` 词汇，因此 UI 会沿原生路径呈现子调用——这对事件的 `time` 字段承载每个子调用的计时）；因 run 结算而被放弃的排队调用两者都不记录。`deriveMessages()` 既不公开这两个事件，也不持久化规范值。token 关联让以提交为语义的观察器能够把内部成功延迟到最终 `run_code` 结果，而无需公开实时外层执行；普通工具副作用不会回滚。每个子调用的 `additionalContexts` 条目以及每份包含图片的成功最终内容序列都会按分发顺序通过外层 `ToolRunContext` 延迟；循环只在父级 `run_code` 结果之后追加这些上下文，从而保持相邻关系和来源归属，即使程序后来失败也不例外。
|
||||
- **结算纪律**：桥接层拥有一个运行作用域的中止机制；该中止会跟随传入的外层信号，并在运行因任何原因结算时触发，因此预算耗尽会中止正在运行的子工具，而不会将其遗留。桥接层随后会在返回之前排空队列，使每个 `tool/code-dispatch` 都落在仍打开的轮次内。失败的运行会抛出 `CodeRunFailedError`（`code: 'CODE_RUN_FAILED'`，message = 失败类型 + 已捕获日志），流水线会将其转换为模型可据以自我修正的结构化 `isError`。
|
||||
- **结果大小**：中间绑定值会完整传入 worker 进程，且没有逐绑定字节上限。`run_code` 返回规范的 `{ logs: string[], result?: JsonValue }`；字符串原样呈现，其他所有存在的 JSON 根都通过栈安全的美化 JSON 遍历呈现，总缩进最多为 10 个字符（更深的子树保持紧凑），`null` 保持显式，而缺少 `result` 表示程序返回 `undefined`。worker 可配置的 `maxOutputBytes`（默认 64 MiB）只应用于组合序列化后的外层日志数组、完成值或失败消息载荷；固定的结果 envelope 语法和呈现空白不计入该上限。无效和超限的完成会明确失败，只有此外层结果可以使用普通 spill。
|
||||
|
||||
@@ -177,7 +177,7 @@ The available tools:
|
||||
|
||||
#### 模型看到的内容
|
||||
|
||||
循环会保留模型发出的参数和注册表的最终内容。任何抛出或被拒绝的调用都会恰好变为 `Error: <message>`。Code Mode 只返回外层程序打印的行和呈现后的返回值；两者都为空时返回 `(run_code completed with no output)`；失败时返回 `Error: code run failed (<kind>): <message>`，并根据是否存在已捕获内容，在其后附加 `Captured output:` 与捕获的行。内部分发事件只保留在日志中；后置执行监听器可以在结果之后追加带来源归属的上下文。
|
||||
循环会保留模型发出的参数和注册表的最终内容。任何抛出或被拒绝的调用都会恰好变为 `Error: <message>`。Code Mode 会渲染外层程序打印的行和返回值；两者都为空时返回 `(run_code completed with no output)`；失败时返回 `Error: code run failed (<kind>): <message>`，并根据是否存在已捕获内容，在其后附加 `Captured output:` 与捕获的行。内部分发事件只保留在日志中，而成功且含图片的子结果会在外层结果之后作为带来源归属的上下文追加；后置执行监听器也可以在同一边界追加其他带来源归属的上下文。
|
||||
|
||||
#### Token 影响
|
||||
|
||||
|
||||
@@ -6,7 +6,7 @@
|
||||
* @module @deepseek-ai/dsh-tools/src/code-mode
|
||||
*/
|
||||
|
||||
import { CallId, HarnessError } from '@deepseek-ai/dsh-llm'
|
||||
import { CallId, createUserMessage, HarnessError } from '@deepseek-ai/dsh-llm'
|
||||
import type { ContentBlock } from '@deepseek-ai/dsh-llm'
|
||||
import type { CodeBindingFunction, CodeRunResult, CodeRuntime } from '@deepseek-ai/dsh-code-runtime'
|
||||
import { snapshotJsonValue } from '@deepseek-ai/dsh-session'
|
||||
@@ -48,7 +48,7 @@ const TYPESCRIPT_FLAVOR: RunCodeFlavor = {
|
||||
'Execute a TypeScript program against the available tools. Write the BODY of an '
|
||||
+ 'async function (erasable syntax only; top-level `await` and `return` work) and '
|
||||
+ 'call tools as `await tools.name(args)` per the declarations in the system prompt. '
|
||||
+ 'Only what you print or return comes back — curate it.',
|
||||
+ 'Only what you print or return is program output; image-bearing subtool results are attached after the run.',
|
||||
codeDescription: 'The program: the body of an async TypeScript function.',
|
||||
}
|
||||
|
||||
@@ -61,8 +61,9 @@ const PYTHON_FLAVOR: RunCodeFlavor = {
|
||||
description:
|
||||
'Execute a Python program against the available tools. Write the BODY of an '
|
||||
+ 'async function (top-level `await` and `return` work) and call tools as '
|
||||
+ '`await tools.name(args)` per the declarations in the system prompt. Answer '
|
||||
+ 'with `print(...)` and/or `return <value>` — only that comes back, so curate it.',
|
||||
+ '`await tools.name(args)` per the declarations in the system prompt. Use '
|
||||
+ '`print(...)` and/or `return <value>` for program output; image-bearing '
|
||||
+ 'subtool results attach after the run.',
|
||||
codeDescription: 'The program: the body of an async Python function.',
|
||||
}
|
||||
|
||||
@@ -557,6 +558,12 @@ export function createRunCodeTool(registry: ToolRegistry, options: RunCodeBridge
|
||||
const result = parked.kind === 'post-result'
|
||||
? await scheduler.finalize(parked.exec, parked.result)
|
||||
: scheduler.finish(parked.exec, parked.result)
|
||||
if (!result.isError && result.content.some(block => block.type === 'image')) {
|
||||
exec.deferContext(createUserMessage({
|
||||
content: result.content,
|
||||
source: { kind: 'plugin', plugin: 'tools-code-mode' },
|
||||
}))
|
||||
}
|
||||
for (const context of result.additionalContexts ?? []) {
|
||||
exec.deferContext(context)
|
||||
}
|
||||
|
||||
@@ -738,7 +738,7 @@ Pass \`run_code\` the body of an async Python function (top-level \`await\` and
|
||||
- Call tools as \`await tools.name(args)\` — subscript access for exotic, reserved, or underscore-leading names: \`await tools["my-tool"](args)\`. Every call resolves to the tool's typed canonical JSON value (each method's return type below). Tool arguments must be lossless JSON.
|
||||
- A FAILED tool call raises \`ToolCallError\`, whose \`toolName\` identifies the failed tool and whose message is human-readable — wrap in \`try/except\` to handle and continue.
|
||||
- Independent read-only calls MAY overlap under \`asyncio.gather\` (safe calls run concurrently; mutating calls run alone, in submission order). Sequence dependent work with \`await\`.
|
||||
- Emit the run's answer with \`print(...)\` and/or a top-level \`return <value>\`; the returned value must be lossless JSON. ONLY what you print and the returned value come back — intermediate tool results never enter the conversation, so extract just what you need.
|
||||
- Emit the run's answer with \`print(...)\` and/or a top-level \`return <value>\`; the returned value must be lossless JSON. Only what you print and return is program output. A successful tool result containing an image is attached after the run so you can inspect it on the next step; every other intermediate result stays out of the conversation, so extract just what you need.
|
||||
|
||||
The available tools:`
|
||||
|
||||
|
||||
@@ -254,7 +254,7 @@ Pass \`run_code\` the body of an async TypeScript function (erasable syntax only
|
||||
- Call tools as \`await tools.name(args)\` — quoted access for exotic names: \`tools["my-tool"](args)\`. Every call resolves to the tool's typed canonical JSON value. Tool arguments must be lossless JSON.
|
||||
- A FAILED tool call rejects with \`ToolCallError\`, whose \`toolName\` identifies the failed tool and whose \`message\` is human-readable — \`try/catch\` it to handle and continue.
|
||||
- Independent read-only calls MAY overlap under \`Promise.all\` (safe calls run concurrently; mutating calls run alone, in submission order). Sequence dependent work with \`await\`.
|
||||
- Emit results with \`return\` and/or \`console.log(...)\`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.
|
||||
- Emit results with \`return\` and/or \`console.log(...)\`. Only what you print or return is program output. A successful tool result containing an image is attached after the run so you can inspect it on the next step; every other intermediate result stays out of the conversation, so extract just what you need.
|
||||
|
||||
The available tools:`
|
||||
|
||||
|
||||
@@ -1082,6 +1082,73 @@ describe('the run_code dispatch bridge', () => {
|
||||
])
|
||||
})
|
||||
|
||||
it('defers image-bearing final sub-call content onto the outer run_code result', async () => {
|
||||
const { ctx, runtime } = await setup({ mode: 'code' })
|
||||
ctx.tools.register(defineContentToolFixture({
|
||||
name: 'image_result',
|
||||
description: 'Return one durable image.',
|
||||
parameters: {},
|
||||
execute: () => Promise.resolve([
|
||||
{ type: 'text', text: 'image result' },
|
||||
{
|
||||
type: 'image',
|
||||
attachment: {
|
||||
attachmentId: 'sha256:aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa' as never,
|
||||
mediaType: 'image/png', bytes: 1, width: 1, height: 1,
|
||||
},
|
||||
},
|
||||
]),
|
||||
}))
|
||||
runtime.behavior = async (request) => {
|
||||
await request.bindings[0]!.functions.image_result!({})
|
||||
return { logs: [], value: 'done' }
|
||||
}
|
||||
|
||||
const result = await runCode(ctx, 'program')
|
||||
|
||||
expect(result.additionalContexts).toMatchObject([{
|
||||
role: 'user',
|
||||
source: { kind: 'plugin', plugin: 'tools-code-mode' },
|
||||
content: [
|
||||
{ type: 'text', text: 'image result' },
|
||||
{ type: 'image', attachment: { mediaType: 'image/png', bytes: 1, width: 1, height: 1 } },
|
||||
],
|
||||
}])
|
||||
})
|
||||
|
||||
it('does not defer images removed by a nested post-execute decision', async () => {
|
||||
for (const decision of ['block', 'replace'] as const) {
|
||||
const { ctx, runtime } = await setup({ mode: 'code' })
|
||||
ctx.tools.register(defineContentToolFixture({
|
||||
name: 'image_result',
|
||||
description: 'Return one durable image.',
|
||||
parameters: {},
|
||||
execute: () => Promise.resolve([{
|
||||
type: 'image',
|
||||
attachment: {
|
||||
attachmentId: 'sha256:bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb' as never,
|
||||
mediaType: 'image/png', bytes: 1, width: 1, height: 1,
|
||||
},
|
||||
}]),
|
||||
}))
|
||||
ctx.on('tools/post-execute', (exec, _result, next): Promise<PostToolDecision> => {
|
||||
if (exec.name !== 'image_result') return next()
|
||||
return Promise.resolve(decision === 'block'
|
||||
? { kind: 'block', feedback: [{ type: 'text', text: 'blocked' }] }
|
||||
: { kind: 'accept', content: [{ type: 'text', text: 'replaced' }] })
|
||||
})
|
||||
runtime.behavior = async (request) => {
|
||||
await request.bindings[0]!.functions.image_result!({}).catch(() => undefined)
|
||||
return { logs: [], value: 'done' }
|
||||
}
|
||||
|
||||
const result = await runCode(ctx, 'program')
|
||||
|
||||
expect(result.additionalContexts).toBeUndefined()
|
||||
await ctx.fiber.dispose()
|
||||
}
|
||||
})
|
||||
|
||||
it('keeps sub-call contexts when run_code fails after the nested dispatch', async () => {
|
||||
const { ctx, runtime } = await setup({ mode: 'both' })
|
||||
registerEcho(ctx)
|
||||
|
||||
@@ -15,7 +15,6 @@ import { basename, extname } from 'node:path'
|
||||
import type { Context } from '@deepseek-ai/cordis'
|
||||
import { AttachmentError, AttachmentId } from '@deepseek-ai/dsh-attachment'
|
||||
import type { ImageAttachmentRef, ImageMediaType } from '@deepseek-ai/dsh-attachment'
|
||||
import { createUserMessage } from '@deepseek-ai/dsh-llm'
|
||||
import type { ContentBlock } from '@deepseek-ai/dsh-llm'
|
||||
import { defineTool } from '@deepseek-ai/dsh-tools'
|
||||
import type { GenericCallView, ToolExecution } from '@deepseek-ai/dsh-tools'
|
||||
@@ -209,12 +208,6 @@ export function applyReadImageTool(ctx: Context): void {
|
||||
...ref.name === undefined ? {} : { name: ref.name },
|
||||
},
|
||||
}
|
||||
if (exec.parent !== undefined) {
|
||||
exec.deferContext(createUserMessage({
|
||||
content: imageReadContent(value),
|
||||
source: { kind: 'plugin', plugin: 'tool-fs' },
|
||||
}))
|
||||
}
|
||||
return value
|
||||
},
|
||||
// Pure display: a generic card in the read family with a follow-along
|
||||
|
||||
Reference in New Issue
Block a user