feat(agent-presets): make the default preset a user setting

`config.default` becomes the composition base of an `agent-presets` settings
namespace, so the user document layers over the deployment's engineering
default and a person can change which preset new sessions get without a
restart.

The value is read per resolution rather than snapshotted: a hot-reloaded
document takes effect on the next session created, and every running session
stays on the preset it was composed from — which is the same rule the
session-header guard enforces from the other side.

`resolve()` read `config.default` directly, which would have made the whole
setting inert; it now goes through `defaultId` like every other caller.

The write-protection test is rewritten against a temp profile root. It was
passing vacuously: the un-overridden Loader REWRITES the composition it read —
stamping `disabled: true` onto the self-disposing row — so the committed
fixture had been mutated by the very run that proved the bug, and every later
run compared against the damaged file and passed. Building the preset in a
temp directory makes the assertion immune to its own failure mode, and it now
fails with a visible `+ disabled: true` when the override is removed.

Review follow-ups on this layer. The exported schema is
`AgentPresetSettingsSchema`, symmetric with the `AgentPresetSettings`
interface it resolves and self-describing at an import site. The `session.create`
JSDoc promised "the deployment's default preset" for an omitted `agentPreset`,
which this layer makes false — it now names the effective default. The
constructor records why it does not use `installSettingsSection`: that helper
re-judges what a consumer DERIVED across attach and detach, and nothing here is
derived. The provider-unload test disposes the fiber `ctx.plugin()` handed back
instead of reaching into `ctx.reflect.store`, and the write-protection wait says
why slack is the right shape for an absence assertion.

The real composition covers the layering too. `apps/cli` boots the shipped
`cordis.yml`, stores `agent-presets.default`, and asserts an unnamed session
composes from it — the package suite proves the layering against a hand-built
context, this proves the roster and the settings provider are wired to each
other. That test also pins the settings row at a temp file: it defaulted to
`$DSH_HOME/settings.yaml`, so a developer's own stored default decided the
outcome of a file whose whole point is that only the shipped root does.

The Agent Note records the per-resolution read and its correspondence with the
session header, and the vacuous-test finding above.
This commit is contained in:
Yichen Jiang
2026-08-04 00:07:11 +08:00
parent 5ed79887fb
commit 8d06b2d576
18 changed files with 378 additions and 30 deletions

View File

@@ -40,6 +40,7 @@
"@deepseek-ai/dsh-host-apiproxy": "workspace:^",
"@deepseek-ai/dsh-host-webserver": "workspace:^",
"@deepseek-ai/dsh-loader-smoke": "workspace:^",
"@deepseek-ai/dsh-settings": "workspace:^",
"@deepseek-ai/dsh-system-prompt": "workspace:^",
"@deepseek-ai/dsh-tools": "workspace:^",
"@types/js-yaml": "^4.0.9",

View File

@@ -1,4 +1,5 @@
import { readFile } from 'node:fs/promises'
import { mkdtemp, readFile, writeFile } from 'node:fs/promises'
import { tmpdir } from 'node:os'
import { fileURLToPath } from 'node:url'
import { join } from 'node:path'
import { Context } from 'cordis'
@@ -7,7 +8,8 @@ import { SessionId } from '@deepseek-ai/dsh-session'
import type { Agent } from '@deepseek-ai/dsh-agent'
import type { PatchOptions } from '@cordisjs/plugin-include'
import { beforeAll, describe, expect, it } from 'vitest'
import type {} from '@deepseek-ai/dsh-agent-presets'
import { settingsNamespace } from '@deepseek-ai/dsh-settings'
import { SETTINGS_NAMESPACE } from '@deepseek-ai/dsh-agent-presets'
import type {} from '@deepseek-ai/dsh-tools'
const CONFIG_DIR = fileURLToPath(new URL('../config/', import.meta.url))
@@ -19,9 +21,15 @@ const WEB_OVERLAY = join(CONFIG_DIR, 'web.cordis.yml')
* touch the network, or write outside the test. Everything that decides an
* agent's capabilities is the real thing, including both shipped presets.
*/
async function bootWeb(): Promise<Context> {
async function bootWeb(settingsFile: string): Promise<Context> {
const patches: PatchOptions[] = [
...loadOverlayPatches('dsh-test', WEB_OVERLAY),
// The settings row defaults to `$DSH_HOME/settings.yaml`. Left alone it
// reads the developer's own document — and since the default preset is a
// setting, a stored `agent-presets.default` would decide this file's
// outcome. Point it at a temp file for the same reason the roster below
// names only the shipped root.
{ id: 'settings', config: { path: settingsFile, watch: false } },
// Host rows with side effects outside this process: a bound port, a
// served asset tree, a telemetry exporter.
{ id: 'webserver', disabled: true },
@@ -37,6 +45,8 @@ async function bootWeb(): Promise<Context> {
{ id: 'directory-picker', disabled: true },
// The roster AppCLIEntry would patch in; only the shipped root, so a
// developer's own `~/.dsh/.preset` cannot change this test's outcome.
// `default` here is the COMPOSITION default — the base layer the settings
// document overrides.
{
id: 'agent-presets',
config: { default: 'standard', roots: [{ path: join(CONFIG_DIR, 'agent-presets'), trust: 'system' }] },
@@ -50,7 +60,9 @@ const toolNames = (ctx: Context, agent?: Agent): string[] =>
let ctx: Context
beforeAll(async () => {
ctx = await bootWeb()
const settingsFile = join(await mkdtemp(join(tmpdir(), 'dsh-web-presets-')), 'settings.yaml')
await writeFile(settingsFile, '{}\n')
ctx = await bootWeb(settingsFile)
}, 120_000)
describe('the shipped Web composition', () => {
@@ -195,6 +207,43 @@ describe('a forked session', () => {
})
})
/**
* Which preset an unnamed session gets is a user setting layered over the
* composition's own default. The package suite proves the layering against a
* hand-built context; this proves it through the shipped `cordis.yml` — that
* the roster and the settings provider are actually wired to each other, and
* that the id the setting names is the one a session composes from.
*/
describe('the default preset as a user setting', () => {
it('composes an unnamed session from the stored default, not the composed one', async () => {
expect(ctx.agentPresets.defaultId).toBe('standard')
await ctx.settings.update(settingsNamespace(SETTINGS_NAMESPACE), { default: 'core-web' })
try {
expect(ctx.agentPresets.defaultId).toBe('core-web')
const handle = await ctx.agents.create({
sessionId: SessionId('preset-user-default'),
setup: agentCtx => ctx.agentPresets.mount(agentCtx).then(() => undefined),
})
try {
// `mount()` with no id resolves the effective default. Two tools, not
// `standard`'s catalog: the setting decided the composition.
expect(toolNames(ctx, handle.agent)).toEqual(['ask_user_question', 'bash', 'str_replace_editor'])
} finally {
await handle.dispose()
}
} finally {
// The context is shared with the rest of the file. `replace({})` drops
// the user section wholesale so the field re-inherits the composition
// base; `update` merges, and would leave the override standing.
await ctx.settings.replace(settingsNamespace(SETTINGS_NAMESPACE), {})
}
expect(ctx.agentPresets.defaultId).toBe('standard')
})
})
describe('a session keeps the preset it was created with', () => {
it('records the preset the gateway guard reads', async () => {
const handle = await ctx.agents.create({