refactor(core): move static Code Mode guidance (#38746)

This commit is contained in:
Aiden Cline 2026-07-24 14:46:59 -05:00 committed by GitHub
commit d1d97014b4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 22 additions and 27 deletions

View file

@ -6,17 +6,13 @@ import { Instructions } from "../instructions/index"
import { CodeModeCatalog } from "./catalog"
// prettier-ignore
const prompt = (hasMoreTools: boolean) => `Run JavaScript to orchestrate tool calls and compose their results. Imports, direct filesystem access, and timers are unavailable. Do not use \`fetch\`; all external access goes through \`tools\`.
const prompt = (hasMoreTools: boolean) => `The Code Mode tool catalog below is ${hasMoreTools ? "partial" : "complete"}.
Inside Code Mode, \`tools\` contains only the tools shown below${hasMoreTools ? " or returned by `search`" : ""}; surrounding top-level agent tools are not available and must not be called from the code.
Prefer an explicit \`return\`; if omitted, the final top-level expression becomes the result. Await tool calls before returning; any calls still pending when execution ends are interrupted. Run independent calls concurrently with \`Promise.all\`.
Do not infer or normalize tool names; use only the exact signatures shown below${hasMoreTools ? " or returned by `search`" : ""}, preserving bracket notation such as \`tools.<namespace>["tool-name"](input)\`.${hasMoreTools ? `
Inside Code Mode, \`tools\` contains only the tools shown below${hasMoreTools ? " or returned by `search`" : ""}; surrounding top-level agent tools are not available and must not be called from the code.${hasMoreTools ? `
## Search
Only some tool signatures are shown. Use \`search\` to discover exact paths and signatures for additional tools:
Use \`search\` to discover exact paths and signatures for additional tools:
- ${searchSignature}` : ""}

View file

@ -34,10 +34,11 @@ type CollectedFiles = {
// Invariant model-facing guidance; the changing tool catalog is delivered through Instructions.
const description = [
"Run JavaScript in a confined Code Mode runtime through { code }.",
"Call Code Mode tools through `tools` using the exact paths and signatures from the instructions.",
"Use `search({ query })` to discover exact signatures when needed.",
"Await important calls and use `Promise.all` for independent calls.",
"Run JavaScript to orchestrate tool calls and compose their results through `{ code }` in a confined Code Mode runtime.",
"Imports, direct filesystem access, and timers are unavailable. Do not use `fetch`; all external access goes through `tools`.",
'Call Code Mode tools through `tools` using only exact paths and signatures from the current catalog or `search`. Do not infer or normalize tool names; preserve bracket notation such as `tools.<namespace>["tool-name"](input)`.',
"Prefer an explicit `return`; if omitted, the final top-level expression becomes the result.",
"Await every call whose completion matters; pending calls are interrupted when execution ends. Run independent calls concurrently with `Promise.all`.",
].join("\n")
export const create = (registrations: ReadonlyMap<string, Registration>) => {

View file

@ -66,37 +66,23 @@ describe("CodeModeInstructions.render", () => {
expect(instructions).toContain("- orders (1 tool)")
expect(instructions).toContain(` - ${lookup.signature} // Look up an order by ID`)
expect(instructions).not.toContain("## Search")
expect(instructions).toContain("Do not infer or normalize tool names")
expect(instructions).toContain('`tools.<namespace>["tool-name"](input)`')
expect(instructions).toContain("The Code Mode tool catalog below is complete.")
expect(instructions).toContain(
"`tools` contains only the tools shown below; surrounding top-level agent tools are not available and must not be called from the code.",
)
})
test("describes the runtime and execution lifecycle concisely", () => {
const instructions = render([lookup])
expect(instructions).toContain("Run JavaScript to orchestrate tool calls and compose their results.")
expect(instructions).toContain("Imports, direct filesystem access, and timers are unavailable.")
expect(instructions).toContain("Do not use `fetch`; all external access goes through `tools`.")
expect(instructions).toContain(
"Prefer an explicit `return`; if omitted, the final top-level expression becomes the result.",
)
expect(instructions).toContain("any calls still pending when execution ends are interrupted")
expect(instructions).toContain("Run independent calls concurrently with `Promise.all`.")
})
test("adds search guidance when the catalog exceeds the budget", () => {
const partial = render([lookup], 0)
expect(partial).toContain("## Available tools")
expect(partial).toContain("- orders (1 tool, none shown)")
expect(partial).toContain("## Search")
expect(partial).toContain("Only some tool signatures are shown.")
expect(partial).toContain("The Code Mode tool catalog below is partial.")
expect(partial).toContain(
"`tools` contains only the tools shown below or returned by `search`; surrounding top-level agent tools are not available and must not be called from the code.",
)
expect(partial).toContain("- search(input: {")
expect(partial).toContain(" limit?: number,\n offset?: number,")
expect(partial).toContain("or returned by `search`")
expect(partial).not.toContain("tools.orders.lookup(input:")
})

View file

@ -14,6 +14,18 @@ const context = {
progress: () => Effect.void,
}
test("execute describes invariant Code Mode behavior", () => {
expect(ExecuteTool.create(new Map()).description).toBe(
[
"Run JavaScript to orchestrate tool calls and compose their results through `{ code }` in a confined Code Mode runtime.",
"Imports, direct filesystem access, and timers are unavailable. Do not use `fetch`; all external access goes through `tools`.",
'Call Code Mode tools through `tools` using only exact paths and signatures from the current catalog or `search`. Do not infer or normalize tool names; preserve bracket notation such as `tools.<namespace>["tool-name"](input)`.',
"Prefer an explicit `return`; if omitted, the final top-level expression becomes the result.",
"Await every call whose completion matters; pending calls are interrupted when execution ends. Run independent calls concurrently with `Promise.all`.",
].join("\n"),
)
})
test("canonical execution distinguishes declared, model-only, and raw schema outputs", async () => {
const declared = Tool.make({
description: "Declared",