dsh-plugin-prompt-tool 0.5.0 → 0.6.0

package/preset/creative/skills/editing-cordis-compositions/SKILL.md

@@ -0,0 +1,165 @@
+---
+name: editing-cordis-compositions
+description: Use when creating, changing, or validating a Cordis composition for this harness — writing or editing an agent preset, adding or removing a plugin row, deciding whether something belongs to the host composition or to one session, checking whether a preset you authored actually mounts, or diagnosing a row that mounted but contributed nothing.
+---
+
+# Editing Cordis compositions
+
+Every capability in this harness is a plugin row in a `cordis.yml`. There is no separate configuration language: changing what an agent can do means changing which rows are composed for it.
+
+## Off-limits
+
+**Never edit, delete, or overwrite a preset that ships with the deployment** — the `agent-presets` directory beside the deployment's own config, which supplies `standard`, `code`, `minimal`, and `cordis`. Never escalate the sandbox to reach it, even when a change there looks quicker. An upgrade overwrites that install, and corrupting `cordis` disables preset authoring itself. Reading a shipped composition is the intended way to start; writing to one is not, and neither is editing the host composition to work around a preset limitation.
+
+To change what a shipped preset does, copy it and edit the copy. Locally authored presets under the user root are yours to create, edit, and delete.
+
+## Decide the plane first
+
+Two planes, and the choice is not about how "agent-related" something feels — it is about whether the thing must be shared.
+
+**Host composition.** The registries themselves (`tools`, `systemPrompt`, `agents`, `agent-loop`, `sessions`), anything crossing sessions (persistence, session query, storage, settings, credentials, telemetry), the sandbox and approval stack, the model route, and the subagent registry with its spawn/fork backends. One instance for the process.
+
+**Agent preset.** What one session contributes to those registries: its tool plugins, its persona and prompt sections, its compaction policy. One instance per session, mounted under that session's scope and unwound with it.
+
+**A service with a consumer outside the agent plane cannot move into a preset.** `subagents` is the worked example: the registry answers cross-session queries for the host api-proxy, so a per-session copy both starves that host row — it waits forever for a service nothing provides — and collides on the second session, since a provider name registers once. The preset contributes the delegation *tools*; the registry and its backends stay host-side.
+
+A preset is a directory holding one `agent.cordis.yml`, optionally beside a `preset.yml` carrying display metadata — `name` and `description` (and, for shipped presets, a roster `order`). Write the metadata too: a preset without it shows up in every picker as its bare directory name.
+
+Locally authored presets live one directory per preset under `${DSH_HOME:-$HOME/.dsh}/.agent-presets/`, and the shipped set sits beside the deployment's own config. Use those when the user asks where to look. A deployment can configure other roots, so the path you read or edit comes from `list()` or `resolve()` — which is also where `copy()` reports what it just created.
+
+## The roster service
+
+`ctx.agentPresets` owns discovery, authoring, and mounting. You reach it by mounting a temporary plugin that injects it and registers a tool for yourself — `cordis_mount` returns only the mount acknowledgement, so a registered tool is how a service answer gets back to you, and it becomes callable on your next step.
+
+Read `cordis_inspect what:"api" name:"agentPresets"` for the current signatures before writing the code. What this skill relies on:
+
+- `list()` — every preset with its `id`, `trust` (`system` for the shipped set, `user` for authored ones), and the absolute `path` of its composition file. This is how you locate any composition without knowing the install layout; the directory is that path's parent.
+- `read(id)` — one preset's composition text, without a file tool or a path.
+- `copy(from, id, name?)` — the only authoring write (see below).
+- `standingKeyFor(id)` — mount-validate one preset (see below).
+
+```js
+return {
+  name: 'preset-tools',
+  inject: ['agentPresets', 'tools'],
+  apply(ctx) {
+    harness.registerTool(ctx, harness.defineTool({
+      name: 'preset_check',
+      description: 'Mount-validate one preset by id.',
+      parameters: { id: { type: 'string', required: true } },
+      output: { schema: { type: 'string' }, render(_a, v) { return [{ type: 'text', text: v }] } },
+      async execute(args) {
+        try {
+          await ctx.agentPresets.standingKeyFor(args.id)
+          return 'mounted OK'
+        } catch (error) {
+          return error.message
+        }
+      },
+    }))
+  },
+}
+```
+
+Unmount the plugin with `cordis_unmount` when you are done; it is a probe, not a capability to leave behind.
+
+## Authoring a preset
+
+1. **Start from a copy.** `copy(from, id, name)` copies a whole preset directory into the user root — composition, metadata, skill directories, assets. It validates the id against `[a-z0-9][a-z0-9-]*` (it becomes the directory name, so no leading hyphen), refuses an id any root already supplies, rolls a failed copy back, and rewrites the copy's `preset.yml` to keep the source's description while dropping its name and roster `order`. Prefer it over a shell copy: it needs no sandbox escalation, it lands the copy in whichever root this deployment made writable, and the copy is exactly as loadable as its source. `resolve(id)` then names the file it created — that path, not a guessed one, is what the following edits target. `standard` is the full coding agent and the usual source.
+2. **Expect the file sandbox on every edit after the copy.** The user preset root lies outside the session workspace, so under the default `workspace-write` policy the first write there is denied. Only writes are: reading any composition by absolute path needs no escalation. Retry that exact command once with `sandbox_permissions` escalation and a short justification — the user sees and approves it. Batch your writes (one heredoc per file) rather than escalating many small commands. `copy()` itself runs host-side and needs none of this; the edits do.
+3. **Write the copy's `description`** in `preset.yml`, and its `name` if you passed none to `copy()`.
+4. **Edit `agent.cordis.yml`** row by row, keeping the plane rule and the realm rule.
+5. **Mount-validate the result**, then hand off to the user for a real session — both under *Verifying a change*.
+
+A composition written from scratch usually forgets a group realm or a consumer row; a copy starts loadable.
+
+## The rule that catches people
+
+**A row that publishes a service may not sit loose in a preset.** Registering a service without an isolate realm puts it in the process-global realm, so the second session mounting that preset collides with the first. The mount rejects it rather than letting the collision surface later.
+
+Whether a row publishes a service is not visible from its name, and package READMEs are absent from an installed deployment. Read it off the live runtime instead: `cordis_inspect what:"services"` lists every service with the fiber that owns it, so a service attributed to a fiber other than the row you are adding is one that row consumes rather than provides. For a row not in your current composition, mount-validate and read the rejection — it names the offending service.
+
+When a preset genuinely owns a service, wrap the provider **and every consumer that reaches it** in one group carrying an `isolate` realm. The shipped `standard` composition does this for `workflows`, which nothing outside an agent reads — its `delegation` group, with the delegation tools omitted here:
+
+```yaml
+- id: delegation
+  name: cordis:group
+  group: true
+  isolate:
+    workflows: true
+  config:
+    - id: workflow-worker-thread
+      name: '@deepseek-ai/dsh-workflow-worker-thread'
+      config:
+        provider: spawn
+    - id: tool-workflow
+      name: '@deepseek-ai/dsh-tool-workflow'
+```
+
+`true` means a realm private to each mounting session. A string label instead joins subtrees into one shared realm; `provide()` still throws on the second registration under that symbol, so a label does not pool instances and is not what a preset needs.
+
+A consumer left outside the group resolves the host's registry, which the preset did not populate, and then contributes nothing. Mount-validation catches that as a row that never activated.
+
+Realms are for services a preset owns, not for every group. A host capability the preset only consumes must stay outside a realm, or the row cannot resolve it: `tool-bash`, `tool-jobs`, and `tool-goal` publish nothing and sit loose in `standard`, which explains in comments which host instance each one resolves and why a realm would break it. Wrapping a consumer row in a realm of its own is the same error as leaving one outside its provider's realm.
+
+## Verifying a change
+
+**`standingKeyFor(id)` is the check.** It composes the preset's plugin subtree for real — the same mount a session start performs, minus the agent — and rejects the four ways a composition fails:
+
+- a row whose package does not resolve (`Cannot find package …`);
+- a row whose config is invalid (`invalid config: $.<field> missing required value`);
+- a row that never activated (`N row(s) did not activate: <id>: waiting for <service>`);
+- a service published into the root realm, which arrives as one of two messages. A name the host does not supply lands in the root realm and the mount audit rejects it: `row(s) published process-global service(s) [<name>]; a preset service must sit behind an isolate realm or move to the host composition` — this is the shape a preset's own forgotten realm takes. A name the host already supplies collides before the audit: `service "<name>" has been registered at <Owner>`. Both name the offending service.
+
+It returns normally when the composition mounts. Run it as the final check on a finished edit rather than after every line: a successful mount installs a standing generation that lives until the process exits, while a failed one disposes its subtree and leaves nothing behind.
+
+**Do not treat the roster's `broken` field as validation.** `list()` reports `broken` from a shape check — the file parses in the loader's YAML dialect and holds named rows — which every failure above passes. It catches a damaged file, not an unusable composition.
+
+`cordis_inspect` reports THIS session's composition, so it confirms what a row does in the runtime you are already in, never what your new preset will do.
+
+After a clean mount-validation, ask the user to start a session on the new preset and confirm the tool list; the preset decides tool schemas and prompt sections, and only a real session shows the agent that composition produces.
+
+`cordis_mount` evaluates JavaScript against the live runtime and disappears on restart. It is for probing, not for shipping a capability: a capability belongs in a composition file.
+
+## Native product subagents
+
+Codex and Claude Code providers are independent optional Profile Bundles. Install only the products a Profile needs, then restart the Profile so its Host registers those providers:
+
+```sh
+dsh plugin --profile <name> add @deepseek-ai/dsh-subagent-codex
+dsh plugin --profile <name> add @deepseek-ai/dsh-subagent-claude-code
+dsh plugin --profile <name> remove @deepseek-ai/dsh-subagent-codex
+dsh plugin --profile <name> remove @deepseek-ai/dsh-subagent-claude-code
+```
+
+Each Bundle owns its Host availability; the preset separately grants one Agent its ordinary delegation tool. Never move a product provider into the preset and never add a product-specific settings field. Removing one package withdraws only that provider on the next Profile start.
+
+Copy these disabled templates from a shipped full preset and remove `disabled` only for the products the user requested:
+
+```yaml
+- id: tool-subagent-codex
+  name: '@deepseek-ai/dsh-tool-subagent'
+  disabled: true
+  config:
+    provider: codex
+    toolName: subagent_codex
+    backgroundMode: one-shot
+    maxDepth: provider-managed
+
+- id: tool-subagent-claude-code
+  name: '@deepseek-ai/dsh-tool-subagent'
+  disabled: true
+  config:
+    provider: claude-code
+    toolName: subagent_claude_code
+    backgroundMode: one-shot
+    maxDepth: provider-managed
+```
+
+For additional named Codex or Claude Code instances, mount a separate host-plane provider row for each instance with a unique `providerName`, then add a separate preset tool row whose `provider` exactly matches that name and whose `toolName` is also unique. Keep the shipped rows for the default `codex` and `claude-code` names; do not reuse one tool row for several providers or derive either name from permission or environment settings.
+
+The two rows are independent. Leaving both disabled preserves the copied preset, enabling one exposes only that product tool, and enabling both exposes both. Production `dsh` does not install either optional provider: before enabling a row, install the matching `@deepseek-ai/dsh-subagent-codex` or `@deepseek-ai/dsh-subagent-claude-code` Bundle in the Profile and restart it. Each Bundle registers its dormant default provider and exclusively uses its pinned package-local platform CLI; additional named instances use extra host-plane rows from the same installed package. A preset cannot provide that host dependency. `backgroundMode: one-shot` keeps omitted or `false` calls in the foreground and lets explicit `run_in_background: true` return a generic Job id. Full presets already carry `tool-jobs`, while the base host carries the job registry; retain both so `job_output`, `job_list`, `job_kill`, cancellation, and completion notices stay available. Installing a Bundle or composing a preset row does not start a product, authenticate an account, select a model, probe credentials, or manage native product settings.
+
+## What not to move into a preset
+
+`agent-loop` registers the one agent factory and throws on a second. The registries own the per-session layering and cannot themselves be per-session. Session persistence must stay host-side or the session list fragments. The sandbox, approval, and permission rows are a deliberate boundary: a preset is exactly as privileged as the plugins it names, so letting one relax its own confinement would defeat the confinement.

package/preset/liangshen/preset.yml

@@ -10,11 +10,10 @@ meta:
   name: liangshen
   description: 梁神模式：首轮 Minimal 双工具锚定 + promoteGate 门控晋升 + PTC 单 run_code 呈现。
   order: 4
-modules:
-  - context-gate
-  - persona
-  - tool-bootstrap
-  - official-agent-instructions
+modules:
+  - context-gate
+  - tool-bootstrap
+  - official-agent-instructions
   - persistent-shell
   - custom-bash
   - str-replace-editor
@@ -27,13 +26,11 @@ modules:
   - planning
   - compaction
   - delegation
-  - tool-ask-user
-  - tool-todo
-  - tool-web
-moduleConfigs:
-  persona:
-    text: You are a helpful software engineer assistant.
-  tool-bootstrap:
+  - tool-ask-user
+  - tool-todo
+  - tool-web
+moduleConfigs:
+  tool-bootstrap:
     bootstrapTools: [bash, str_replace_editor]
     includeSubagents: true
     promoteGate: true
@@ -47,10 +44,11 @@ moduleConfigs:
   context-gate:
     messageSources: [user, goal]
     deferredSources: [agent-instructions, skill-catalog]
-    deferredGraceSteps: 1
-    instructionHint: true
-promptConfigs:
-  # 晋升后注入 preset.md 内容（custom-fallback 策略：自定义锚定词命中后注入一次）。
+    deferredGraceSteps: 1
+    instructionHint: true
+params:
+promptConfigs:
+  # 晋升后注入 preset.md 内容（custom-fallback 策略：自定义锚定词命中后注入一次）。
   # phase-1 由 context-gate 的 messageSources 白名单拦截，晋升后随普通注入恢复。
   - id: prompt-injector
     name: preset.md 注入
@@ -62,5 +60,13 @@ promptConfigs:
     role: user
     position: before-all
     dedupe: session
-    promotion: main
-    sourceKind: plugin
+    promotion: main
+    sourceKind: plugin
+  - id: persona-main
+    name: 主会话人设
+    layer: system-section
+    strategy: static
+    order: 0
+    params:
+      sectionName: deployment:persona
+    text: "You are a helpful assistant. Before acting, decide the task type (build or fix) and adopt the matching style: build → hands-on production; fix → inspect-and-plan. Before acting, briefly review what you have already done in this session and continue from where you left off; do not repeat completed steps. Do not run environment checks (echo, whoami, uname, node --version, date) or exhaustive grep/glob scans. Think deeply first, then produce."

package/preset/minimal/preset.yml

@@ -3,27 +3,19 @@ name: 极简模式
 description: 仅提供持久 bash 与 str_replace_editor 的双工具编码 Agent。
 version: 1.0.0
 engineCompat: ">=0.4.2"
-modules:
-  - persona
-  - official-persistent-shell
-  - bootstrap-filesystem
-  - context-gate
-  - tool-bootstrap
-  - router-first-turn
-  - prompt-config-engine
-  - run-code-env
-  - custom-bash
-  - skill-search
-moduleConfigs:
-  persona:
-    text: You are a helpful software engineer assistant.
-    complete: true
-    includeRuntimeContext: false
-params:
-  usePtcMode: true
-  bootstrapMaxTokens: 0
-  mainPersona: "You are a helpful assistant. Before acting, decide the task type (build or fix) and adopt the matching style: build → hands-on production; fix → inspect-and-plan. Before acting, briefly review what you have already done in this session and continue from where you left off; do not repeat completed steps. Do not run environment checks (echo, whoami, uname, node --version, date) or exhaustive grep/glob scans. Think deeply first, then produce."
-  allowKinds: "[skill-invocation, near-anchor, router-guide]"
+modules:
+  - official-persistent-shell
+  - bootstrap-filesystem
+  - context-gate
+  - tool-bootstrap
+  - prompt-config-engine
+  - run-code-env
+  - custom-bash
+  - skill-search
+params:
+  usePtcMode: true
+  bootstrapMaxTokens: 0
+  allowKinds: "[skill-invocation, near-anchor, router-guide]"
   # 模型路由与委派 · 主对话与子代理通用（缺省 = 官方默认 / 继承宿主）
   modelProvider: ""
   modelName: ""
@@ -36,6 +28,17 @@ params:
   subagentTemperature: ""
   subagentMaxTokens: ""
   subagentPersona: ""
-  toolFilterAllow: []
-  toolFilterDeny: []
-  maxDepth: ""
+  toolFilterAllow: []
+  toolFilterDeny: []
+  maxDepth: ""
+promptConfigs:
+  - id: persona-main
+    name: 主会话人设
+    layer: system-section
+    strategy: static
+    order: 0
+    params:
+      sectionName: deployment:persona
+      complete: true
+      suppressRuntimeContext: true
+    text: "You are a helpful software engineer assistant."

package/preset/ptc/preset.yml

@@ -3,9 +3,8 @@ name: PTC 模式
 description: 具备标准模式的全部能力，并通过 Code Mode SDK 呈现工具，让模型用一个 TypeScript 程序组合多步操作。
 version: 1.0.0
 engineCompat: ">=0.4.2"
-modules:
-  - persona
-  - official-agent-instructions
+modules:
+  - official-agent-instructions
   - official-tool-bash
   - tool-pwsh
   - tool-fs
@@ -21,18 +20,16 @@ modules:
   - tool-todo
   - tool-web
   - official-tool-presentation
-  - context-gate
-  - tool-bootstrap
-  - router-first-turn
-  - prompt-config-engine
+  - context-gate
+  - tool-bootstrap
+  - prompt-config-engine
   - run-code-env
-  - custom-bash
-  - skill-search
-params:
-  usePtcMode: true
-  bootstrapMaxTokens: 0
-  mainPersona: "You are a helpful assistant. Before acting, decide the task type (build or fix) and adopt the matching style: build → hands-on production; fix → inspect-and-plan. Before acting, briefly review what you have already done in this session and continue from where you left off; do not repeat completed steps. Do not run environment checks (echo, whoami, uname, node --version, date) or exhaustive grep/glob scans. Think deeply first, then produce."
-  allowKinds: "[skill-invocation, near-anchor, router-guide]"
+  - custom-bash
+  - skill-search
+params:
+  usePtcMode: true
+  bootstrapMaxTokens: 0
+  allowKinds: "[skill-invocation, near-anchor, router-guide]"
   # 模型路由与委派 · 主对话与子代理通用（缺省 = 官方默认 / 继承宿主）
   modelProvider: ""
   modelName: ""
@@ -45,6 +42,15 @@ params:
   subagentTemperature: ""
   subagentMaxTokens: ""
   subagentPersona: ""
-  toolFilterAllow: []
-  toolFilterDeny: []
-  maxDepth: ""
+  toolFilterAllow: []
+  toolFilterDeny: []
+  maxDepth: ""
+promptConfigs:
+  - id: persona-main
+    name: 主会话人设
+    layer: system-section
+    strategy: static
+    order: 0
+    params:
+      sectionName: deployment:persona
+    text: "You are a coding agent powered by the {{model}} model. Your working directory is {{cwd}}."

package/preset/standard/preset.yml

@@ -3,9 +3,8 @@ name: 标准模式
 description: 功能完整的编码 Agent，支持文件编辑、Shell、文件与网页检索、Skills、计划、目标、子代理和工作流。
 version: 1.0.0
 engineCompat: ">=0.4.2"
-modules:
-  - persona
-  - official-agent-instructions
+modules:
+  - official-agent-instructions
   - official-tool-bash
   - tool-pwsh
   - tool-fs
@@ -20,18 +19,16 @@ modules:
   - tool-ask-user
   - tool-todo
   - tool-web
-  - context-gate
-  - tool-bootstrap
-  - router-first-turn
-  - prompt-config-engine
+  - context-gate
+  - tool-bootstrap
+  - prompt-config-engine
   - run-code-env
-  - custom-bash
-  - skill-search
-params:
-  usePtcMode: true
-  bootstrapMaxTokens: 0
-  mainPersona: "You are a helpful assistant. Before acting, decide the task type (build or fix) and adopt the matching style: build → hands-on production; fix → inspect-and-plan. Before acting, briefly review what you have already done in this session and continue from where you left off; do not repeat completed steps. Do not run environment checks (echo, whoami, uname, node --version, date) or exhaustive grep/glob scans. Think deeply first, then produce."
-  allowKinds: "[skill-invocation, near-anchor, router-guide]"
+  - custom-bash
+  - skill-search
+params:
+  usePtcMode: true
+  bootstrapMaxTokens: 0
+  allowKinds: "[skill-invocation, near-anchor, router-guide]"
   # 模型路由与委派 · 主对话与子代理通用（缺省 = 官方默认 / 继承宿主）
   modelProvider: ""
   modelName: ""
@@ -44,6 +41,15 @@ params:
   subagentTemperature: ""
   subagentMaxTokens: ""
   subagentPersona: ""
-  toolFilterAllow: []
-  toolFilterDeny: []
-  maxDepth: ""
+  toolFilterAllow: []
+  toolFilterDeny: []
+  maxDepth: ""
+promptConfigs:
+  - id: persona-main
+    name: 主会话人设
+    layer: system-section
+    strategy: static
+    order: 0
+    params:
+      sectionName: deployment:persona
+    text: "You are a coding agent powered by the {{model}} model. Your working directory is {{cwd}}."

package/templates/20-system-section.yml

@@ -1,5 +1,9 @@
 # 模板：system-section 静态 system 段（缓存友好，静态内容优先放这里）
 # order 参考：-100 身份 / 0 persona / 100-199 工具引导。
+# 人设用法：params.sectionName = deployment:persona 时注册为主会话人设段
+# （同名 shadow 全局 persona，模块列表显示「人设」徽标；子代理经 scope 链继承）。
+#   - complete: true 独占整个 system prompt（预设内互斥，UI 自动收敛，手写冲突官方 fail loud）
+#   - suppressRuntimeContext: true 抑制动态运行时快照（等价官方 includeRuntimeContext:false）
 id: example-system-section
 name: 示例：system 静态段
 layer: system-section
@@ -11,4 +15,5 @@ text: |-
 variables: {}
 params:
   complete: false
+  suppressRuntimeContext: false
   sectionName: ''

package/engine/compositions/library/router-first-turn.yml

@@ -1,9 +0,0 @@
-# module: router-first-turn
-# source: preset/engine/compositions/source/local/router-first-turn.yml (本地附加,非官方模块)
-
-- id: router-first-turn
-  name: ./engine/router-first-turn.mjs
-  config:
-    mainPersona: "__MAIN_PERSONA__"
-    hideSectionPrefixes: ["mnemon:"]
-    includeSubagents: false

package/engine/compositions/source/local/router-first-turn.yml

@@ -1,5 +0,0 @@
-- id: router-first-turn
-  name: ./engine/router-first-turn.mjs
-  config:
-    mainPersona: "__MAIN_PERSONA__"
-    hideSectionPrefixes: [mnemon:]

package/engine/router-first-turn.mjs

@@ -1,85 +0,0 @@
-/**
- * router-first-turn — prompt-tool 本地附加件（最优组合）。
- *
- * 依据 dsh-router-standard 的 router-bootstrap 组装逻辑：
- *   - 只替换 persona 段，保留计划模式段与其他第三方 section；
- *   - 首轮隐藏 mnemon:* 自动注入段，晋升后恢复（contexts 由 context-gate 清空/恢复）；
- *   - 按主会话模型自动选择 persona：
- *       Pro  → 官方训练原句；
- *       Flash → dsh-router-standard 的 Flash 弱路由人设（build/fix 分类 +
- *               回顾锚 + 收敛锚 + 反跑题锚 + 先深想再产出）；
- *   - 子代理（委托深度 > 0）默认直接放行完整结果，保证 dsh-mnemon 等插件
- *     通过工具白名单要求的 mnemon_* 工具首轮可见；includeSubagents=true 时
- *     子代理与主会话一样走首轮 persona 替换与段隐藏。
- *
- * 工具目录裁剪仍由 tool-bootstrap 负责（首轮 = 真实 Minimal 工具对；晋升后
- * 恢复完整目录或切换 PTC），本模块不触碰 tools，避免两层过滤器冲突。
- */
-
-import { createEpochPromotion } from './compaction-epoch.mjs'
-import { isDelegated, isFlashModel, PROMOTE_EVENTS } from './shared.mjs'
-
-/** Cordis 插件名，供 loader 诊断使用。 */
-export const name = 'router-first-turn'
-
-/** 无服务依赖，只监听 system-prompt 组装。 */
-export const inject = []
-
-/** 官方 RL 训练原句（保持与 Minimal 预设逐字节一致）。 */
-const RL_PERSONA = 'You are a helpful software engineer assistant.'
-
-/** 是否为 persona 段：旧 persona 段由本模块替换。 */
-function isPersonaSection(section) {
-  if (section === null || typeof section !== 'object') return false
-  const name = String(section.name ?? '')
-  return name === 'persona' || /persona/i.test(name)
-}
-
-/** 首轮需要隐藏的 mnemon 自动注入段（晋升后恢复）。 */
-function isMnemonSection(section) {
-  if (section === null || typeof section !== 'object') return false
-  return String(section.name ?? '').startsWith('mnemon:')
-}
-
-/**
- * 引擎级 router-first-turn:所有内容(含主对话自定义模型人设 mainPersona)都由预设配置参数传入,
- * 本文件不含任何模板专属文本。
- * config: { mainPersona: string, hideSectionPrefixes?: string[], includeSubagents?: boolean }
- */
-export function apply(ctx, config) {
-  const mainPersona = typeof config?.mainPersona === 'string' && config.mainPersona.trim().length > 0
-    ? config.mainPersona
-    : undefined
-  if (mainPersona === undefined) {
-    throw new TypeError(`${name}: config.mainPersona must be a non-empty string`)
-  }
-  const hidePrefixes = Array.isArray(config?.hideSectionPrefixes)
-    ? config.hideSectionPrefixes.filter((item) => typeof item === 'string' && item.length > 0)
-    : ['mnemon:']
-  const includeSubagents = config?.includeSubagents === true
-
-  const promotion = createEpochPromotion(PROMOTE_EVENTS.either, { includeSubagents: false })
-  ctx.on('session/event', (session, event) => promotion.observe(session, event))
-
-  ctx.on('system-prompt/assemble', async (_assembly, context, next) => {
-    const assembled = await next()
-    const agent = context.agent
-    if (agent === undefined) return assembled
-    const session = agent.session
-    if (session === undefined) return assembled
-
-    // 子代理默认不裁剪任何 section/context：它与宿主白名单子代理协作；
-    // includeSubagents=true 时与主会话同一相位逻辑（首轮替换 + 段隐藏）。
-    if (isDelegated(session) && !includeSubagents) return assembled
-
-    const persona = isFlashModel(agent.options?.model) ? mainPersona : RL_PERSONA
-
-    const sections = assembled.sections ?? []
-    const promoted = promotion.status(agent).promoted
-    const kept = sections.filter((section) =>
-      !isPersonaSection(section)
-      && (promoted || !hidePrefixes.some((prefix) => String(section?.name ?? '').startsWith(prefix))))
-    // contexts 由 context-gate 统一清空/恢复，本模块只替换 persona 与隐藏前缀段。
-    return { ...assembled, sections: [...kept, { name: 'router-persona', text: persona, order: 0 }] }
-  })
-}