dsh-plugin-prompt-tool 0.4.2 → 0.6.0

package/engine/compositions/library/compaction.yml

@@ -0,0 +1,52 @@
+# module: compaction
+# source: E:\Documents\GitHub\deepseek-harness/apps/cli/config/agent-presets/standard/agent.cordis.yml
+# local patches: 0
+
+# ── compaction ──────────────────────────────────────────────────────────────
+
+# `compaction-basic` reads `toolResultPrune` through `ctx.get`, so the pruner must
+# share this realm rather than sit outside it.
+#
+# `tokenMeter` is deliberately NOT in this realm: the meter stays on the HOST
+# plane, and the rows here resolve that one instance. It takes no configuration,
+# keys every fold by Session, and owns the context-meter projection units the
+# browser reads for every session — behind a realm those units would come and go
+# with whichever presets happen to be mounted. What a preset chooses is whether
+# its agent compacts at all, which is `compaction-basic` below.
+- id: compaction
+  name: cordis:group
+  group: true
+  isolate:
+    compaction: true
+    toolResultPruner: true
+  config:
+    - id: compaction-basic
+      name: '@deepseek-ai/dsh-compaction-basic'
+
+    - id: command-compact
+      name: '@deepseek-ai/dsh-command-compact'
+
+    - id: tool-result-pruner
+      name: '@deepseek-ai/dsh-compaction-tool-result-pruner'
+      config:
+        thresholdChars: 8192
+        headChars: 4096
+        tailChars: 1024
+
+# ── delegation and workflows ────────────────────────────────────────────────
+
+# The `subagents` registry and its spawn/fork backends live in the HOST
+# composition: the registry is a process singleton whose cross-session queries
+# the api-proxy serves to the browser, and a provider name may only be
+# registered once. This preset contributes the delegation TOOLS, which resolve
+# that host registry.
+#
+# `workflows` is different — nothing outside an agent reads it — so every row
+# that reaches it shares one entry-local realm here, and a consumer left
+# outside would resolve a host registry this preset does not populate.
+#
+# `tool-subagent-report` is host-plane for the same reason as the registry,
+# not because a preset may not want it: it registers a CONTINUABLE SETUP on
+# that singleton rather than a tool this agent calls, and the setup list is
+# not scope-aware — one copy per mounted preset means every child gets
+# `report` registered once per live session, which throws on the second.

package/engine/compositions/library/context-gate.yml

@@ -0,0 +1,40 @@
+# module: context-gate
+# source: preset/engine/compositions/source/local/context-gate.yml (本地附加,非官方模块)
+
+- id: context-gate
+  name: ./engine/context-gate.mjs
+  config:
+    promoteOn: either
+    includeSubagents: false
+    allowKinds: __allowKinds__
+
+# ── bootstrap ───────────────────────────────────────────────────────────────
+
+# Tool catalog control (mode-owned tool-bootstrap.mjs). V4 Pro conditions
+# strongly on the API tool catalog AND the first request output budget:
+# request #1 exposes the OFFICIAL Minimal preset's real tool pair —
+# persistent `bash` + `str_replace_editor` — which anchors at the
+# adapter-default maxTokens (256000) with no output cap needed (issue #11:
+# 5/5 anchored vs 11/11 standard-like for every standard-family schema);
+# after the session records its first durable promotion signal (a tool call OR
+# the first assistant message, default `promoteOn: either`), later steps keep
+# the assembled catalog and usePtcMode optionally switches the wire to Code
+# Mode (PTC). `bootstrapMaxTokens` is
+# opt-in for standard-schema bootstraps; unset, the adapter default flows. See
+# tool-bootstrap.mjs for the other triggers. Context stripping is NOT here —
+# the context-gate row above owns it.
+#
+# POST-PROMOTION (prompt-tool local addition): both modes keep the assembled
+# catalog after promotion. `usePtcMode` switches the wire presentation to Code
+# Mode (PTC, a single run_code backed by the full registry SDK) instead of
+# narrowing the resident set; the pre-promotion and post-compaction controlled
+# phase below still stays on the bootstrap pair + `compactionTools`.
+#
+# COMPACTION (local addition): after `compaction/end` the session falls back
+# to the controlled phase — bootstrap pair + `compactionTools` — until a NEW
+# durable promotion signal exists past the boundary (epoch-aware, see
+# compaction-epoch.mjs).
+#
+# `includeSubagents: true` keeps the subagent phase in sync with the
+# context-gate row: a subagent's first request sees the bootstrap pair, then
+# its own first reply or tool call promotes it to the assembled catalog.

package/engine/compositions/library/custom-bash.yml

@@ -0,0 +1,14 @@
+# module: custom-bash
+# source: preset/engine/compositions/source/local/custom-bash.yml (本地附加,非官方模块)
+
+- id: custom-bash
+  name: ./engine/custom-bash.mjs
+  disabled: !!js process.platform !== 'win32'
+  config:
+    timeoutMs: 120000
+    maxOutputBytes: 64000
+
+# ── filesystem ──────────────────────────────────────────────────────────────
+
+# Both register into the host `tools` registry and provide nothing, so
+# they need no realm. The `fs` service and its policy stay in the host.

package/engine/compositions/library/delegation.yml

@@ -0,0 +1,85 @@
+# module: delegation
+# source: E:\Documents\GitHub\deepseek-harness/apps/cli/config/agent-presets/standard/agent.cordis.yml
+# local patches: 2（SUBAGENT-CONFIG token ×2：子代理完整配置（模型/人设/工具集/深度），随预设参数渲染）
+
+# ── delegation and workflows ────────────────────────────────────────────────
+
+# The `subagents` registry and its spawn/fork backends live in the HOST
+# composition: the registry is a process singleton whose cross-session queries
+# the api-proxy serves to the browser, and a provider name may only be
+# registered once. This preset contributes the delegation TOOLS, which resolve
+# that host registry.
+#
+# `workflows` is different — nothing outside an agent reads it — so every row
+# that reaches it shares one entry-local realm here, and a consumer left
+# outside would resolve a host registry this preset does not populate.
+#
+# `tool-subagent-report` is host-plane for the same reason as the registry,
+# not because a preset may not want it: it registers a CONTINUABLE SETUP on
+# that singleton rather than a tool this agent calls, and the setup list is
+# not scope-aware — one copy per mounted preset means every child gets
+# `report` registered once per live session, which throws on the second.
+- id: delegation
+  name: cordis:group
+  group: true
+  isolate:
+    workflowEngine: true
+  config:
+    - id: tool-subagent-control
+      name: '@deepseek-ai/dsh-tool-subagent-control'
+
+    - id: tool-subagent-list-agents
+      name: '@deepseek-ai/dsh-tool-subagent-control/list-agents'
+
+    - id: tool-subagent
+      name: '@deepseek-ai/dsh-tool-subagent'
+      config:
+        provider: spawn
+        toolName: subagent
+        backgroundMode: continuable
+        __subagentConfig__
+
+    - id: tool-subagent-fork
+      name: '@deepseek-ai/dsh-tool-subagent'
+      config:
+        provider: fork
+        toolName: subagent_fork
+        backgroundMode: continuable
+        __subagentConfig__
+
+    # Production dsh does not install these optional providers. An opting-in
+    # Profile mounts each provider once on the host plane; copy this preset,
+    # then remove `disabled` from the matching tool row.
+    - 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
+
+    - id: workflow-worker-thread
+      name: '@deepseek-ai/dsh-workflow-worker-thread'
+      config:
+        provider: spawn
+
+    - id: tool-workflow
+      name: '@deepseek-ai/dsh-tool-workflow'
+
+    - id: tool-ralph
+      name: '@deepseek-ai/dsh-tool-ralph'
+      config:
+        subagentProvider: spawn
+        maxRounds: 64
+
+# ── remaining model-facing rows ─────────────────────────────────────────────

package/engine/compositions/library/official-agent-instructions.yml

@@ -0,0 +1,17 @@
+# module: official-agent-instructions
+# source: deepseek-harness official standard agent preset (agent-instructions)
+
+- id: agent-instructions
+  name: '@deepseek-ai/dsh-agent-instructions'
+  config:
+    maxBytes: 65536
+
+# ── shell ───────────────────────────────────────────────────────────────────
+
+# `shell-env` stays in the HOST composition: `apps/cli/src/web.ts` injects it to
+# publish `DSH_WEB_URL`/`DSH_WEB_MODE`, and a host row that injects a service is
+# the criterion for host-plane ownership — injection resolves before any session
+# exists, so there is no agent to key by. Behind a preset realm those variables
+# never reached the model's shell at all. Both shell tools consume the host
+# registry from here; their executors (`bash-sandbox`/`pwsh-sandbox`) are
+# host-plane too.

package/engine/compositions/library/official-persistent-shell.yml

@@ -0,0 +1,56 @@
+# module: official-persistent-shell
+# source: deepseek-harness official minimal agent preset (persistent-shell)
+
+- id: persistent-shell
+  name: cordis:group
+  group: true
+  isolate:
+    terminals: true
+  config:
+    - id: pty
+      name: '@deepseek-ai/dsh-terminal'
+
+    - id: terminal-bash
+      name: '@deepseek-ai/dsh-terminal-bash'
+      disabled: !!js process.platform === 'win32'
+      config:
+        timeoutMs: 300000
+
+    - id: persistent-bash
+      name: '@deepseek-ai/dsh-tool-bash-persistent'
+      disabled: !!js process.platform === 'win32'
+      config:
+        timeoutMs: 300000
+        description: |-
+          Run commands in a bash shell
+          * When invoking this tool, the contents of the "command" parameter does NOT need to be XML-escaped.
+          * You don't have access to the internet via this tool.
+          * You do have access to a mirror of common linux and python packages via apt and pip.
+          * State is persistent across command calls and discussions with the user.
+          * To inspect a particular line range of a file, e.g. lines 10-25, try 'sed -n 10,25p /path/to/the/file'.
+          * Please avoid commands that may produce a very large amount of output.
+          * Please run long lived commands in the background, e.g. 'sleep 10 &' or start a server in the background.
+
+    - id: terminal-pwsh
+      name: '@deepseek-ai/dsh-terminal-bash'
+      disabled: !!js process.platform !== 'win32'
+      config:
+        shellDialect: pwsh
+        timeoutMs: 300000
+
+    - id: persistent-pwsh
+      name: '@deepseek-ai/dsh-tool-pwsh-persistent'
+      disabled: !!js process.platform !== 'win32'
+      config:
+        timeoutMs: 300000
+        description: |-
+          Run commands in a PowerShell shell
+          * When invoking this tool, the contents of the "command" parameter does NOT need to be XML-escaped.
+          * You don't have access to the internet via this tool.
+          * State is persistent across command calls and discussions with the user.
+          * Use native Windows paths (C:\...) and $env:NAME variables; this is PowerShell, not bash.
+          * Please avoid commands that may produce a very large amount of output.
+          * Please run long lived commands in the background, e.g. 'Start-Job' or start a server with Start-Process.
+
+# The bare local filesystem shadows the host's sandboxed provider only for this
+# preset. The editor shares that realm and requires absolute paths.

package/engine/compositions/library/official-skill-filesystem-cordis.yml

@@ -0,0 +1,10 @@
+# module: official-skill-filesystem-cordis
+# source: deepseek-harness official cordis agent preset (skill-filesystem)
+# 差异含 !!js 表达式（代码类），无法经 moduleConfigs 参数化（YAML tag 不保真），保留独立文件。
+
+- id: skill-filesystem
+  name: '@deepseek-ai/dsh-skill-filesystem'
+  config:
+    customSkillDirs:
+      - !!js "process.getBuiltinModule('node:url').fileURLToPath(new URL('skills/', baseUrl))"
+

package/engine/compositions/library/official-tool-bash.yml

@@ -0,0 +1,6 @@
+# module: official-tool-bash
+# source: deepseek-harness official standard agent preset (tool-bash)
+
+- id: tool-bash
+  name: '@deepseek-ai/dsh-tool-bash'
+  disabled: !!js process.platform === 'win32'

package/engine/compositions/library/official-tool-cordis.yml

@@ -0,0 +1,13 @@
+# module: official-tool-cordis
+# source: deepseek-harness official cordis agent preset (tool-cordis)
+
+- id: tool-cordis
+  name: '@deepseek-ai/dsh-tool-cordis'
+
+# The composition-authoring skill travels with this preset rather than living
+# in the user's skill root: it documents THIS deployment's two planes, and a
+# preset is the unit that gets copied and edited. `baseUrl` is the preset's
+# own directory, so the root resolves wherever the preset is installed.
+# Both rows register into THIS preset's layer of the host skill registry, so
+# they need no realm; the agent's merged catalog also carries whatever the
+# deployment registered globally (repository plugins).

package/engine/compositions/library/official-tool-presentation.yml

@@ -0,0 +1,7 @@
+# module: official-tool-presentation
+# source: deepseek-harness official code agent preset (tool-presentation)
+
+- id: tool-presentation
+  name: '@deepseek-ai/dsh-agent-tool-presentation'
+  config:
+    mode: code

package/engine/compositions/library/official-tool-skill.yml

@@ -0,0 +1,14 @@
+# module: official-tool-skill
+# source: deepseek-harness official standard agent preset (tool-skill)
+
+- id: tool-skill
+  name: '@deepseek-ai/dsh-tool-skill'
+
+# ── goals ───────────────────────────────────────────────────────────────────
+
+# Only the model-facing tool. The goal SERVICE, its session driver, and the
+# `/goal` command stay on the host plane: the Gateway serves the goal domain as
+# Remote endpoints whose receiver comes from a generated descriptor, so it
+# resolves `goals` on the host and an entry-local realm here would hide it. The
+# registry is keyed by session anyway, so one host instance serves every
+# session. What a preset chooses is whether its agent can call the goal tool.

package/engine/compositions/library/persistent-shell.yml

@@ -0,0 +1,36 @@
+# module: persistent-shell
+# source: E:\Documents\GitHub\deepseek-harness/apps/cli/config/agent-presets/minimal/agent.cordis.yml
+# local patches: 2
+
+- id: persistent-shell
+  name: cordis:group
+  group: true
+  disabled: !!js process.platform === 'win32'
+  isolate:
+    terminals: true
+  config:
+    - id: pty
+      name: '@deepseek-ai/dsh-terminal'
+
+    - id: terminal-bash
+      name: '@deepseek-ai/dsh-terminal-bash'
+      config:
+        shellPath: !!js "process.getBuiltinModule?.('node:fs')?.existsSync('/bin/bash') ? '/bin/bash' : 'bash'"
+        timeoutMs: 300000
+
+    - id: persistent-bash
+      name: '@deepseek-ai/dsh-tool-bash-persistent'
+      config:
+        timeoutMs: 300000
+        description: |-
+          Run commands in a bash shell
+          * When invoking this tool, the contents of the "command" parameter does NOT need to be XML-escaped.
+          * You don't have access to the internet via this tool.
+          * You do have access to a mirror of common linux and python packages via apt and pip.
+          * State is persistent across command calls and discussions with the user.
+          * To inspect a particular line range of a file, e.g. lines 10-25, try 'sed -n 10,25p /path/to/the/file'.
+          * Please avoid commands that may produce a very large amount of output.
+          * Please run long lived commands in the background, e.g. 'sleep 10 &' or start a server in the background.
+
+# The bare local filesystem shadows the host's sandboxed provider only for this
+# preset. The editor shares that realm and requires absolute paths.

package/engine/compositions/library/persona.yml

@@ -0,0 +1,9 @@
+# module: persona
+# source: deepseek-harness official standard agent preset (persona)
+# persona 差异（creative/minimal/anchored）由 preset.yml moduleConfigs 参数传递。
+
+- id: persona
+  name: '@deepseek-ai/dsh-persona'
+  config:
+    text: >-
+      You are a coding agent powered by the {{model}} model. Your working directory is {{cwd}}.

package/engine/compositions/library/planning.yml

@@ -0,0 +1,41 @@
+# module: planning
+# source: E:\Documents\GitHub\deepseek-harness/apps/cli/config/agent-presets/standard/agent.cordis.yml
+# local patches: 0
+
+# ── plan mode ───────────────────────────────────────────────────────────────
+
+# Plan state is per-agent by nature, so an entry-local realm is not a
+# workaround here — it is the correct lifetime.
+- id: planning
+  name: cordis:group
+  group: true
+  isolate:
+    planMode: true
+  config:
+    - id: plan-mode
+      name: '@deepseek-ai/dsh-plan-mode'
+      config:
+        section: |
+              You are in plan mode. Stay in plan mode until exit_plan_mode succeeds or the user switches the session mode. Imperative language to implement changes means plan the implementation, not execute it. A user's conversational agreement — including an answer confirming something you asked — approves nothing and does not end plan mode; fold the confirmed decision into the plan and submit it through exit_plan_mode.
+
+              Explore first. Use non-mutating reads, searches, static analysis, and checks to ground the plan in the actual repository. Do not edit or write files, change configuration, run formatters or code generation that rewrites tracked files, commit, or otherwise carry out the plan. Prefer existing functions and patterns over new machinery.
+
+              The tool catalog stays the same across modes for request-cache stability. These plan-mode rules override any later tool description or guidance that suggests using mutation tools; those tools remain listed to keep the tool catalog unchanged. Do not use todo_write to track this planning phase: it tracks implementation after an approved plan, while the plan itself belongs in exit_plan_mode.
+
+              Resolve discoverable facts by inspection. Use ask_user_question only for user-owned choices or material ambiguity that inspection cannot answer. Do not ask the user where code lives or how current behavior works when you can find out.
+
+              Make the plan decision-complete: state the goal and success criteria; group implementation changes by subsystem; identify public API, schema, and data-flow changes; cover edge cases, failure modes, tests, acceptance criteria, and explicit assumptions. Keep it concise enough to review but detailed enough that another engineer can implement it without making design decisions.
+
+              When ready, call exit_plan_mode with the complete plan markdown, starting with a # title. Make exit_plan_mode the only and final tool call in that assistant response: it presents the plan for approval, and implementation begins only in a later step after approval. Do not paste the final plan as a plain reply or ask "should I proceed?" through prose or ask_user_question. If review rejects it, incorporate the feedback and present again. If the review channel is unavailable or aborted, stay in plan mode and ask the user to switch modes manually; do not proceed with implementation.
+
+# ── compaction ──────────────────────────────────────────────────────────────
+
+# `compaction-basic` reads `toolResultPrune` through `ctx.get`, so the pruner must
+# share this realm rather than sit outside it.
+#
+# `tokenMeter` is deliberately NOT in this realm: the meter stays on the HOST
+# plane, and the rows here resolve that one instance. It takes no configuration,
+# keys every fold by Session, and owns the context-meter projection units the
+# browser reads for every session — behind a realm those units would come and go
+# with whichever presets happen to be mounted. What a preset chooses is whether
+# its agent compacts at all, which is `compaction-basic` below.

package/engine/compositions/library/prompt-config-engine.yml

@@ -0,0 +1,16 @@
+# module: prompt-config-engine
+# source: preset/engine/compositions/source/local/prompt-config-engine.yml (本地附加,非官方模块)
+
+- id: prompt-config-engine
+  name: ./engine/prompt-config-engine.mjs
+  config:
+    configsDir: ../prompt-configs
+
+# ── PTC run_code environment (prompt-tool local addition) ──────────────────
+#
+# Official Code Mode runs the model program in a worker with env={}; the
+# program cannot read system environment. This row patches the reserved
+# run_code transport so every program gets a frozen `env` global containing
+# the whitelisted non-secret host variables below plus managed DSH_* facts
+# and DSH_WORKSPACE. Add deployment-specific names to envKeys as needed.
+# Credential-shaped names (KEY/PASSWORD/SECRET/TOKEN) are always rejected.

package/engine/compositions/library/run-code-env.yml

@@ -0,0 +1,15 @@
+# module: run-code-env
+# source: preset/engine/compositions/source/local/run-code-env.yml (本地附加,非官方模块)
+
+- id: run-code-env
+  name: ./engine/run-code-env.mjs
+  config:
+    enabled: true
+    envKeys: [PATH, PATHEXT, HOME, USERPROFILE, USERNAME, COMPUTERNAME, OS, TEMP, TMP, SystemRoot, ProgramFiles, ProgramFiles(x86), LOCALAPPDATA, APPDATA]
+
+# ── identity ────────────────────────────────────────────────────────────────
+
+# Keep this text byte-identical to the Minimal preset. `complete` prevents the
+# Harness identity and per-tool guidance from changing the system prompt, while
+# runtime-context suppression leaves task and repository rules to user messages
+# and explicit file reads. Tool schemas and their runtime enforcement remain.

package/engine/compositions/library/skill-filesystem.yml

@@ -0,0 +1,13 @@
+# module: skill-filesystem
+# source: E:\Documents\GitHub\deepseek-harness/apps/cli/config/agent-presets/standard/agent.cordis.yml
+# local patches: 0
+
+# ── skills ──────────────────────────────────────────────────────────────────
+
+# The skill REGISTRY lives in the host composition and is layered per scope:
+# these rows register into THIS preset's layer of it, so they need no realm.
+# `skill-filesystem` contributes local-root discovery for agents on this preset, and
+# `tool-skill` gives them the catalog and loader; the merged catalog also
+# carries whatever the deployment registered globally (repository plugins).
+- id: skill-filesystem
+  name: '@deepseek-ai/dsh-skill-filesystem'

package/engine/compositions/library/skill-search.yml

@@ -0,0 +1,14 @@
+# module: skill-search
+# source: preset/engine/compositions/source/local/skill-search.yml (本地附加,非官方模块)
+
+- id: skill-search
+  name: ./engine/skill-search.mjs
+
+# ── goals ───────────────────────────────────────────────────────────────────
+
+# Only the model-facing tool. The goal SERVICE, its session driver, and the
+# `/goal` command stay on the host plane: the Gateway serves the goal domain as
+# Remote endpoints whose receiver comes from a generated descriptor, so it
+# resolves `goals` on the host and an entry-local realm here would hide it. The
+# registry is keyed by session anyway, so one host instance serves every
+# session. What a preset chooses is whether its agent can call the goal tool.

package/engine/compositions/library/str-replace-editor.yml

@@ -0,0 +1,10 @@
+# module: str-replace-editor
+# source: E:\Documents\GitHub\deepseek-harness/apps/cli/config/agent-presets/minimal/agent.cordis.yml
+# 官方 minimal 内置工具（filesystem group 内的 str-replace-editor 行）拆出为独立模块：
+# 复用宿主 sandbox 的 ctx.fs，不挂 fs-local 裸文件系统。
+# maxOutputChars 参数化：params.strReplaceEditorMaxOutputChars（默认官方值 16000）。
+
+- id: str-replace-editor
+  name: '@deepseek-ai/dsh-tool-str-replace-editor'
+  config:
+    maxOutputChars: __strReplaceEditorMaxOutputChars__

package/engine/compositions/library/tool-ask-user.yml

@@ -0,0 +1,8 @@
+# module: tool-ask-user
+# source: E:\Documents\GitHub\deepseek-harness/apps/cli/config/agent-presets/standard/agent.cordis.yml
+# local patches: 0
+
+# ── remaining model-facing rows ─────────────────────────────────────────────
+
+- id: tool-ask-user
+  name: '@deepseek-ai/dsh-tool-ask-user'

package/engine/compositions/library/tool-bash.yml

@@ -0,0 +1,16 @@
+# module: tool-bash
+# source: E:\Documents\GitHub\deepseek-harness/apps/cli/config/agent-presets/standard/agent.cordis.yml
+# local patches: 1
+
+# ── shell ───────────────────────────────────────────────────────────────────
+
+# `shell-env` stays in the HOST composition: `apps/cli/src/web.ts` injects it to
+# publish `DSH_WEB_URL`/`DSH_WEB_MODE`, and a host row that injects a service is
+# the criterion for host-plane ownership — injection resolves before any session
+# exists, so there is no agent to key by. Behind a preset realm those variables
+# never reached the model's shell at all. Both shell tools consume the host
+# registry from here; their executors (`bash-sandbox`/`pwsh-sandbox`) are
+# host-plane too.
+- id: tool-bash
+  name: '@deepseek-ai/dsh-tool-bash'
+  disabled: true

package/engine/compositions/library/tool-bootstrap.yml

@@ -0,0 +1,16 @@
+# module: tool-bootstrap
+# source: preset/engine/compositions/source/local/tool-bootstrap.yml (本地附加,非官方模块)
+
+- id: tool-bootstrap
+  name: ./engine/tool-bootstrap.mjs
+  config:
+    bootstrapTools: [bash, str_replace_editor]
+    promoteOn: either
+    includeSubagents: false
+    usePtcMode: __usePtcMode__
+    __bootstrapMaxTokens__
+    # Post-compaction core work set: the model is mid-task and needs to keep
+    # working, but faces a small catalog instead of the full Standard set.
+    compactionTools: [read, write, edit, glob, grep, todo_write, ask_user_question]
+
+# ── prompt-tool 模板自带行(由 write-preset 按 manifest 变量物化) ─────────────

package/engine/compositions/library/tool-filter.yml

@@ -0,0 +1,12 @@
+# module: tool-filter
+# source: 本地附加（本项目主会话工具过滤；非官方模块）
+# 主会话常驻工具白名单/黑名单：作用于任意注册工具（含第三方插件工具）。
+# allow 非空 = 白名单（只保留列表内工具）；deny 非空 = 黑名单（移除列表内工具）；
+# 两者都空 = 不过滤（官方默认）。includeSubagents=true 时子代理同样过滤。
+
+- id: tool-filter
+  name: ./engine/tool-filter.mjs
+  config:
+    allow: __mainToolFilterAllow__
+    deny: __mainToolFilterDeny__
+    includeSubagents: __mainToolFilterSubagents__

package/engine/compositions/library/tool-fs-search.yml

@@ -0,0 +1,18 @@
+# module: tool-fs-search
+# source: E:\Documents\GitHub\deepseek-harness/apps/cli/config/agent-presets/standard/agent.cordis.yml
+# local patches: 0
+
+- id: tool-fs-search
+  name: '@deepseek-ai/dsh-tool-fs-search'
+  config:
+    sampleOverCapGlobResults: false
+
+# ── background jobs ────────────────────────────────────────────────────────
+
+# Only the model-facing controls. The task REGISTRY stays on the host plane:
+# its producers sit outside any realm this file could put it in — `tool-bash`
+# above resolves it with `ctx.get`, and an entry-local realm here is invisible
+# to every sibling row, so `run_in_background` would answer "background jobs
+# unavailable" while these controls sat in the catalog. The registry is keyed by
+# owning agent anyway, so one host instance serves every session. What a preset
+# chooses is whether its agent can collect and stop background work at all.

package/engine/compositions/library/tool-fs.yml

@@ -0,0 +1,10 @@
+# module: tool-fs
+# source: E:\Documents\GitHub\deepseek-harness/apps/cli/config/agent-presets/standard/agent.cordis.yml
+# local patches: 0
+
+# ── filesystem ──────────────────────────────────────────────────────────────
+
+# Both register into the host `tools` registry and provide nothing, so
+# they need no realm. The `fs` service and its policy stay in the host.
+- id: tool-fs
+  name: '@deepseek-ai/dsh-tool-fs'

package/engine/compositions/library/tool-goal.yml

@@ -0,0 +1,19 @@
+# module: tool-goal
+# source: E:\Documents\GitHub\deepseek-harness/apps/cli/config/agent-presets/standard/agent.cordis.yml
+# local patches: 0
+
+# ── goals ───────────────────────────────────────────────────────────────────
+
+# Only the model-facing tool. The goal SERVICE, its session driver, and the
+# `/goal` command stay on the host plane: the Gateway serves the goal domain as
+# Remote endpoints whose receiver comes from a generated descriptor, so it
+# resolves `goals` on the host and an entry-local realm here would hide it. The
+# registry is keyed by session anyway, so one host instance serves every
+# session. What a preset chooses is whether its agent can call the goal tool.
+- id: tool-goal
+  name: '@deepseek-ai/dsh-tool-goal'
+
+# ── plan mode ───────────────────────────────────────────────────────────────
+
+# Plan state is per-agent by nature, so an entry-local realm is not a
+# workaround here — it is the correct lifetime.

package/engine/compositions/library/tool-jobs.yml

@@ -0,0 +1,23 @@
+# module: tool-jobs
+# source: E:\Documents\GitHub\deepseek-harness/apps/cli/config/agent-presets/standard/agent.cordis.yml
+# local patches: 0
+
+# ── background jobs ────────────────────────────────────────────────────────
+
+# Only the model-facing controls. The task REGISTRY stays on the host plane:
+# its producers sit outside any realm this file could put it in — `tool-bash`
+# above resolves it with `ctx.get`, and an entry-local realm here is invisible
+# to every sibling row, so `run_in_background` would answer "background jobs
+# unavailable" while these controls sat in the catalog. The registry is keyed by
+# owning agent anyway, so one host instance serves every session. What a preset
+# chooses is whether its agent can collect and stop background work at all.
+- id: tool-jobs
+  name: '@deepseek-ai/dsh-tool-jobs'
+
+# ── skills ──────────────────────────────────────────────────────────────────
+
+# The skill REGISTRY lives in the host composition and is layered per scope:
+# these rows register into THIS preset's layer of it, so they need no realm.
+# `skill-filesystem` contributes local-root discovery for agents on this preset, and
+# `tool-skill` gives them the catalog and loader; the merged catalog also
+# carries whatever the deployment registered globally (repository plugins).