Pine/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases 1 Wiki Activity

fix(web): stop leaking ask_user_question into every preset

Browse Source 
`ui-question`'s node half called `ctx.tools.register` on the host context.
`ScopedLayers.merge()` combines the global layer with the agent's exact-scope
layer, and an unscoped registration lands in the global one — so the tool
reached every agent no matter which preset composed it. `core-web`, sold as a
two-tool benchmark surface, really presented three.

Rendering a question is a host UI capability; having the tool is an agent
capability, and only a preset decides that. The node half is now empty and the
`tool-ask-user` row moved into the preset that wants it. The TUI keeps its own
row, having no presets.

The composition tests now assert the global tool layer is EMPTY, which is the
invariant that would have caught this: any tool outside a preset reaches every
agent. The browser lane's composition, seeded-history, and hermetic-skill
assertions address their registries through a composed agent for the same
reason — those services are per session now, and the host cannot resolve an
`isolate` realm by name.
This commit is contained in:
Yichen Jiang
2026-08-07 02:52:41 +08:00
parent 2d1df8a9e2
commit 89ae94d89f
13 changed files with 89 additions and 53 deletions
Download Patch File Download Diff File Expand all files Collapse all files
apps/web/tests/shipped-composition.e2e.ts
+22 -5
View File
@@ -11,6 +11,8 @@ import type {} from '@deepseek-ai/dsh-tools'
import type {} from '@deepseek-ai/dsh-sandbox-policy'
import type {} from '@deepseek-ai/dsh-user-approval'
import type {} from '@deepseek-ai/dsh-permission'
import { SessionId } from '@deepseek-ai/dsh-session'
import type {} from '@deepseek-ai/dsh-agent-presets'
import { launchWebScaffold, type WebScaffold } from './scaffold.ts'
/**
@@ -63,11 +65,26 @@ afterEach(async () => {
it('assembles the shipped Web catalog with the confined access default', async () => {
scaffold = await launchWebScaffold()
const names = scaffold.ctx.tools.schemas().map(schema => schema.name).sort()
expect(names.filter(name => !RIPGREP_TOOLS.includes(name))).toEqual(EXPECTED_TOOLS)
// The packaged ripgrep binary ships with the dependency, so the pair is a
// fixed roster member on every host.
expect(names.filter(name => RIPGREP_TOOLS.includes(name))).toEqual(RIPGREP_TOOLS)
const ctx = scaffold.ctx
// The catalog belongs to an AGENT, not to the process: every model-facing row
// now lives in a preset mounted under one session's scope, so the global
// layer holds nothing and a caller must name the agent to see anything. This
// composes from the deployment default — what a session that names no preset
// gets — which is the shape this test has always been about.
expect(ctx.tools.schemas().map(schema => schema.name)).toEqual([])
const handle = await ctx.agents.create({
sessionId: SessionId('shipped-composition'),
setup: agentCtx => ctx.agentPresets.mount(agentCtx).then(() => undefined),
})
try {
const names = ctx.tools.schemas(handle.agent).map(schema => schema.name).sort()
expect(names.filter(name => !RIPGREP_TOOLS.includes(name))).toEqual(EXPECTED_TOOLS)
// The packaged ripgrep binary ships with the dependency, so the pair is a
// fixed roster member on every host.
expect(names.filter(name => RIPGREP_TOOLS.includes(name))).toEqual(RIPGREP_TOOLS)
} finally {
await handle.dispose()
}
// `workspace-write` is not "the workspace and nothing else": the shared roots
// helper always admits the temp directories too. Pinning it against an
// explicit mode keeps the claim independent of this surface's default, and