Merge branch 'stack/agent-profiles-5-web-ui' into stack/agent-profiles-6-cordis-agent

apps/cli/config/core-web.cordis.yml

@@ -1,6 +1,27 @@
-# Opt-in two-tool profile over the shipped Web composition. The default native
-# model surface is exactly persistent `bash` plus `str_replace_editor`; the
-# Web host, browser shell, workspace, persistence, and permission stack remain.
+# Opt-in Web shell for the RL core agent contract. The model receives exactly
+# the configured persona plus the native `bash` and `str_replace_editor`
+# schemas; the Web host, browser shell, persistence, and permission stack stay.
+
+# Match the Claude SWE-compatible RL core prompt. Disabling the Web runtime's
+# surface context removes its GUI orientation, managed shell variables, and the
+# launcher's source-checkout section through one configuration contract.
+# Workspace instructions are model-visible user context rather than a system
+# section, but RL core disables them as part of the same prompt contract.
+- id: system-prompt
+  config:
+    includeHarnessIdentity: false
+    persona: !!js process.env.DSH_SYSTEM_PROMPT ?? 'You are a helpful software engineer assistant.'
+
+- id: web-runtime
+  config:
+    surfaceContext: false
+
+- id: workspace-context
+  disabled: true
+
+- id: tools
+  config:
+    mode: native
 
 # Disable every model-facing consumer in the base/Web tree. plan-mode owns the
 # always-registered exit_plan_mode tool even while the session is not planning.

apps/cli/reference/README.i18n.yaml

@@ -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 apps/cli/reference/README.md
-README.md: 62275139809364d80296433e804ade3d447f37e6
-README.zh.md: e508caaf05622c0c177eaacd070978368ff84af3
+README.md: 8b8a0e7dbebafedd6a4f8d988adb3fd11c7bd026
+README.zh.md: d1d6d5a594596a8be5db30021163f0fcea4a95bf

apps/cli/reference/README.md

@@ -53,7 +53,9 @@ All modes treat the invoking directory as the default workspace root, load appli
 
 New sessions default to the `workspace-write` permission preset. Bash and filesystem mutations are restricted to the session workspace and platform temporary roots; reads, network access, and process visibility are not confined. `DSH_PERMISSION_MODE` changes the process fallback. Stored General-settings permissions affect later Web sessions, not an already-open one.
 
-`DSH_TOOLS_MODE` selects `native`, `code`, or `both` for the process; another value fails at boot. [`config/core-web.cordis.yml`](../config/core-web.cordis.yml) is an optional `--patch` overlay that reduces the native model surface to persistent `bash` and `str_replace_editor` while retaining the shipped host, browser, workspace, persistence, and permission composition.
+`DSH_TOOLS_MODE` selects `native`, `code`, or `both` for the process; another value fails at boot. [`config/core-web.cordis.yml`](../config/core-web.cordis.yml) is an optional RL-compatible `--patch` overlay that pins native mode, renders only `DSH_SYSTEM_PROMPT` or `You are a helpful software engineer assistant.` as the system prompt, disables Workspace instructions and every Web runtime prompt contribution, and exposes only persistent `bash` and `str_replace_editor` while retaining the shipped host, browser, workspace, persistence, and permission composition.
+
+`DSH_SYSTEM_PROMPT` is passed as the system-prompt [`persona`](../../../packages/core/system-prompt/README.md#config): complete `{{…}}` groups use that contract's strict variable interpolation and have no literal-brace escape; any set value, including an empty string, is authoritative and an empty value therefore removes the system prompt, while only an unset variable selects the fallback.
 
 ## Shared deployment behavior
 

apps/cli/reference/README.zh.md

@@ -53,7 +53,9 @@ dsh web --dump-config
 
 新会话默认使用 `workspace-write` 权限预设。Bash 和文件系统修改仅限于会话 workspace 与平台临时根目录；读取、网络访问和进程可见性不受限制。`DSH_PERMISSION_MODE` 更改进程后备值。General settings 中存储的权限影响后续 Web 会话，不改变已打开的会话。
 
-`DSH_TOOLS_MODE` 为进程选择 `native`、`code` 或 `both`；其他值会导致启动失败。[`config/core-web.cordis.yml`](../config/core-web.cordis.yml) 是可选的 `--patch` overlay：它在保留随附宿主、浏览器、workspace、持久化和权限组合的同时，把原生模型 surface 缩减为持久 `bash` 和 `str_replace_editor`。
+`DSH_TOOLS_MODE` 为进程选择 `native`、`code` 或 `both`；其他值会导致启动失败。[`config/core-web.cordis.yml`](../config/core-web.cordis.yml) 是可选的 RL 兼容 `--patch` overlay：它固定使用 `native` 模式，仅将 `DSH_SYSTEM_PROMPT` 或 `You are a helpful software engineer assistant.` 渲染为系统提示词，禁用 Workspace 指令与所有 Web 运行时提示词贡献，并且在保留随附宿主、浏览器、workspace、持久化和权限组合的同时，仅暴露持久 `bash` 和 `str_replace_editor`。
+
+`DSH_SYSTEM_PROMPT` 会传给系统提示词的 [`persona`](../../../packages/core/system-prompt/README.md#config)：完整的 `{{…}}` 分组遵循该契约的严格变量插值规则，且无法转义为字面花括号；任何已设置的值（包括空字符串）都具有权威性，因此空值会移除系统提示词，只有未设置该变量时才会选择后备值。
 
 ## 共享部署行为
 

apps/cli/src/profile-boot.ts

@@ -95,6 +95,9 @@ export function prepareProfile(name: string, userLayer = true): Profile {
   return profile
 }
 
+/** Read-only row index of a profile composition before launcher flag patches. */
+export type ProfileRows = ReadonlyMap<string, { name?: string; config?: unknown }>
+
 /** One profile's patch layers (application order) and the row index of its pre-flag composition. */
 interface ComposedProfile {
   profile: Profile
@@ -109,7 +112,7 @@ interface ComposedProfile {
    * for flag merges and row checks. Flag patches must not insert rows the
    * launcher consults here (they only override values and insert dev glue).
    */
-  rows: Map<string, { name?: string; config?: unknown }>
+  rows: ProfileRows
 }
 
 /** The full patch stack of one composed profile, in application order. */
@@ -155,11 +158,11 @@ export interface RunProfileOptions {
   /** `--patch` overlay paths, in argv order. */
   patchFiles: readonly string[]
   /** Launcher hook turning the pre-flag composed rows into flag patches (the web alias's flag family). */
-  deriveFlagPatches?: (rows: ComposedProfile['rows']) => PatchOptions[]
+  deriveFlagPatches?: (rows: ProfileRows) => PatchOptions[]
   /** One-shot task text; requires the composition to mount the headless runner row. */
   task?: string
   /** Surface setup registered after Loader installation and before any config-tree entry mounts. */
-  prepare?: (ctx: Context) => Promise<void> | void
+  prepare?: (ctx: Context, rows: ProfileRows) => Promise<void> | void
 }
 
 /**
@@ -231,7 +234,7 @@ export async function runProfile(options: RunProfileOptions): Promise<{ ctx: Con
       }
       hostCtx.provide('headlessIo', io)
     }
-    await options.prepare?.(hostCtx)
+    await options.prepare?.(hostCtx, composed.rows)
   })
   app.current = ctx
   // A surface can dispose the whole tree while startup was still in flight

apps/cli/src/web.ts

@@ -14,7 +14,7 @@ import { dshHomePath } from '@deepseek-ai/dsh-paths'
 import type { Context } from 'cordis'
 import type { PatchOptions } from '@cordisjs/plugin-include'
 import { addHarnessSourceSection } from '@deepseek-ai/dsh-app-boot'
-import { runProfile } from './profile-boot.ts'
+import { runProfile, type ProfileRows } from './profile-boot.ts'
 
 const SOURCE_ROOT = fileURLToPath(new URL('../../..', import.meta.url))
 
@@ -78,7 +78,7 @@ export interface WebFlags {
  * @returns the flag patch list, in application order.
  */
 function deriveWebFlagPatches(
-  rows: Map<string, { name?: string; config?: unknown }>,
+  rows: ProfileRows,
   flags: WebFlags,
 ): PatchOptions[] {
   const overrides = new Map<string, Record<string, unknown>>()
@@ -122,6 +122,18 @@ function deriveWebFlagPatches(
   return patches
 }
 
+/**
+ * Whether the composed Web runtime keeps its model- and shell-visible surface
+ * context. The bundle schema defaults the field to true, so only an explicit
+ * false suppresses both the bundle contributions and the launcher-owned
+ * source-checkout section.
+ * @param rows - the composed Web profile rows before launcher flag patches.
+ * @returns true unless the web-runtime row explicitly disables surface context.
+ */
+export function webSurfaceContextEnabled(rows: ProfileRows): boolean {
+  return (rows.get('web-runtime')?.config as { surfaceContext?: boolean } | undefined)?.surfaceContext !== false
+}
+
 /**
  * Serve the browser UI from the web profile. Host/port/workspace-root flags
  * are passed through only when given (absent, the composed profile values
@@ -135,7 +147,8 @@ export async function runWeb(flags: WebFlags): Promise<void> {
     profile: 'web',
     patchFiles: flags.patches,
     deriveFlagPatches: rows => deriveWebFlagPatches(rows, flags),
-    prepare: (ctx: Context) => {
+    prepare: (ctx: Context, rows: ProfileRows) => {
+      if (!webSurfaceContextEnabled(rows)) return
       ctx.inject(['systemPrompt'], (promptCtx) => {
         addHarnessSourceSection(promptCtx, SOURCE_ROOT)
       })

apps/cli/tests/built-bin.e2e.ts

@@ -8,6 +8,7 @@ import { afterEach, beforeEach, describe, expect, it } from 'vitest'
 /** Published-entry acceptance for argument errors, profile lifecycle, and boot-free config dumps. */
 const repoRoot = fileURLToPath(new URL('../../../', import.meta.url))
 const dshBin = join(repoRoot, 'apps/cli/lib/bin.js')
+const coreWebOverlay = fileURLToPath(new URL('../config/core-web.cordis.yml', import.meta.url))
 const invalidProvider = fileURLToPath(new URL('./fixtures/invalid-provider.cordis.yml', import.meta.url))
 
 async function runBuiltBin(
@@ -367,5 +368,16 @@ describe.skipIf(!existsSync(dshBin))('dsh BUILT bin (node lib/bin.js, no tsx)',
       expect(stdout).toContain(`patched by ${profilePatch}, ${overlay}`)
       expect(stderr).toContain('patch: entry "absent-row" not found')
     }, 30_000)
+
+    it('shows the RL Web patch disabling runtime surface context', async () => {
+      const { stdout, code, stderr } = await runBuiltBin(
+        ['web', '--patch', coreWebOverlay, '--dump-config'],
+        { DSH_HOME: home },
+      )
+      expect(code).toBe(0)
+      expect(stderr).toBe('')
+      expect(stdout).toContain("name: '@deepseek-ai/dsh-web-app'")
+      expect(stdout).toContain('surfaceContext: false')
+    }, 30_000)
   })
 })

apps/cli/tests/trusted-hosts.spec.ts

@@ -1,7 +1,7 @@
 /** Single-sample LAN-trust resolution for the /api browser-trust fence (`resolveLanTrust`). */
 
 import { describe, expect, it, vi } from 'vitest'
-import { resolveLanTrust } from '../src/web.ts'
+import { resolveLanTrust, webSurfaceContextEnabled } from '../src/web.ts'
 
 vi.mock('node:os', () => ({
   networkInterfaces: () => ({
@@ -31,3 +31,15 @@ describe('resolveLanTrust', () => {
     expect(resolveLanTrust(undefined, ['lab.internal'])).toEqual({ lanAddresses: [], trustedHosts: ['lab.internal'] })
   })
 })
+
+describe('webSurfaceContextEnabled', () => {
+  it('defaults to enabled and honors an explicit complete-prompt disable', () => {
+    expect(webSurfaceContextEnabled(new Map())).toBe(true)
+    expect(webSurfaceContextEnabled(new Map([
+      ['web-runtime', { config: { mode: 'production' } }],
+    ]))).toBe(true)
+    expect(webSurfaceContextEnabled(new Map([
+      ['web-runtime', { config: { surfaceContext: false } }],
+    ]))).toBe(false)
+  })
+})