Deepseek harness的4种模式
DeepSeek Harness 的四种模式，本质上是当前会话加载了哪些工具和配置的不同组合。它们没有绝对的好坏之分，而是为了适配不同的任务场景而设计的。下表汇总了它们的核心区别：
| 模式 | 核心机制 | 工具与能力 | 主要适用场景 |
|---|---|---|---|
| 标准模式 (Standard) | 默认的完整编码 Agent，模型按需逐步调用工具。 | 能力最全：集成文件编辑、Shell、文件/网页检索、Skills、计划模式、子Agent、工作流等20+工具。 | 日常首选。适合大多数编码、文档处理、自动化任务。 |
| PTC 模式 (Programmatic Tool Calling) | 模型不直接调用工具，而是写一段 TypeScript 程序来编排多步操作，将多次工具调用合并为一次执行。 | 标准模式全部能力 + run_code 工具。用代码批量组合工具调用。 |
批量/复杂任务。适合需要多次调用工具、并对结果进行筛选、整理、去重、汇总的任务。 |
| 极简模式 (Minimal) | 一个最小化工具集的编码 Agent，用于测试模型在"裸环境"下的基础能力。 | 仅有2个工具 ：一个持久运行的终端 (bash) 和一个文件编辑器 (str_replace_editor)。 |
基准测试与轻量修改。官方用它进行模型评测；也适合只改一个文件、跑一条命令的简单任务。 |
| 创造模式 (Creator/Cordis) | 一个可自我改装的 Agent，让模型能检查并修改自身运行时的插件配置。 | 标准模式全部能力 + 运行时自检工具。可读写自身的 Harness 组装，试验 Cordis 插件。 | 框架二次开发与高阶定制。适合创建自定义 Agent 预设、试验新插件或模式。 |
💡 如何选择？
-
日常干活，首选标准模式：它提供了最完整、开箱即用的能力，能覆盖绝大多数需求。
-
批量处理，用 PTC 模式提效：当任务需要反复调用工具时，让模型写程序来批量操作，通常比来回对话更高效。
-
跑分或极简任务，用极简模式：它的环境最干净，适合进行基准测试，或处理只需简单终端命令和文件编辑的轻量任务。
-
折腾框架本身，进入创造模式：如果你需要为 DSH 开发新插件、创建自定义工作流，这个模式能让你直接与框架的底层运行时交互。
这四种模式覆盖了从"日常使用"到"框架开发"的完整光谱，你可以根据手头任务的具体需求灵活切换。
Deepseek harness的4种模式配置文件
极简模式
- id: persona
name: '@deepseek-ai/dsh-persona'
config:
prefix: You are a helpful software engineer assistant.
complete: true
includeRuntimeContext: false
- 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.
* Network access depends on the task environment. Prefer configured mirrors/proxies when they are available.
* 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.标准模式
- id: persona
name: '@deepseek-ai/dsh-persona'
config:
suffix: Your working directory is {{cwd}}.
prefix: You are a coding agent powered by the {{model}} model.
- id: agent-instructions
name: '@deepseek-ai/dsh-agent-instructions'
config:
maxBytes: 65536
- id: tool-bash
name: '@deepseek-ai/dsh-tool-bash'
disabled: !!js process.platform === 'win32'
- id: tool-pwsh
name: '@deepseek-ai/dsh-tool-pwsh'
disabled: !!js process.platform !== 'win32'
- id: tool-fs
name: '@deepseek-ai/dsh-tool-fs'
- id: tool-fs-search
name: '@deepseek-ai/dsh-tool-fs-search'
config:
sampleOverCapGlobResults: false
- id: tool-jobs
name: '@deepseek-ai/dsh-tool-jobs'
- id: skill-filesystem
name: '@deepseek-ai/dsh-skill-filesystem'
- id: tool-skill
name: '@deepseek-ai/dsh-tool-skill'
- id: command-goal
name: '@deepseek-ai/dsh-command-goal'
- id: tool-goal
name: '@deepseek-ai/dsh-tool-goal'
- 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.
- 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
- 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
modelSelectionSettings: true
backgroundMode: continuable
- id: tool-subagent-fork
name: '@deepseek-ai/dsh-tool-subagent'
config:
provider: fork
toolName: subagent_fork
backgroundMode: continuable
- 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-ptc
name: '@deepseek-ai/dsh-workflow-ptc'
config:
provider: spawn
- id: tool-workflow
name: '@deepseek-ai/dsh-tool-workflow'
- id: tool-ralph
name: '@deepseek-ai/dsh-tool-ralph'
disabled: true
config:
subagentProvider: spawn
maxRounds: 64
- id: tool-ask-user
name: '@deepseek-ai/dsh-tool-ask-user'
- id: tool-todo
name: '@deepseek-ai/dsh-tool-todo'
config:
allowParallelInProgress: true
- id: tool-web
name: '@deepseek-ai/dsh-tool-web'
config:
fetch: true
searchTimeoutMs: 60000
- id: present
name: '@deepseek-ai/dsh-tool-present'
- id: tool-plugin-manager
name: '@deepseek-ai/dsh-plugin-manager/tools'
disabled: true创造模式
- id: persona
name: '@deepseek-ai/dsh-persona'
config:
suffix: Your working directory is {{cwd}}.
prefix: You are a coding agent powered by the {{model}} model.
- id: agent-instructions
name: '@deepseek-ai/dsh-agent-instructions'
config:
maxBytes: 65536
- id: tool-bash
name: '@deepseek-ai/dsh-tool-bash'
disabled: !!js process.platform === 'win32'
- id: tool-pwsh
name: '@deepseek-ai/dsh-tool-pwsh'
disabled: !!js process.platform !== 'win32'
- id: tool-fs
name: '@deepseek-ai/dsh-tool-fs'
- id: tool-fs-search
name: '@deepseek-ai/dsh-tool-fs-search'
config:
sampleOverCapGlobResults: false
- id: tool-jobs
name: '@deepseek-ai/dsh-tool-jobs'
- id: command-goal
name: '@deepseek-ai/dsh-command-goal'
- id: tool-goal
name: '@deepseek-ai/dsh-tool-goal'
- 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.
- 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
- 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
modelSelectionSettings: true
backgroundMode: continuable
- id: tool-subagent-fork
name: '@deepseek-ai/dsh-tool-subagent'
config:
provider: fork
toolName: subagent_fork
backgroundMode: continuable
- 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-ptc
name: '@deepseek-ai/dsh-workflow-ptc'
config:
provider: spawn
- id: tool-workflow
name: '@deepseek-ai/dsh-tool-workflow'
- id: tool-ralph
name: '@deepseek-ai/dsh-tool-ralph'
disabled: true
config:
subagentProvider: spawn
maxRounds: 64
- id: tool-ask-user
name: '@deepseek-ai/dsh-tool-ask-user'
- id: tool-todo
name: '@deepseek-ai/dsh-tool-todo'
config:
allowParallelInProgress: true
- id: tool-web
name: '@deepseek-ai/dsh-tool-web'
config:
fetch: true
searchTimeoutMs: 60000
- id: tool-cordis
name: '@deepseek-ai/dsh-tool-cordis'
- id: skill-filesystem
name: '@deepseek-ai/dsh-skill-filesystem'
config:
customSkillDirs:
- !!js process.getBuiltinModule('node:path').join(process.getBuiltinModule('node:path').dirname(process.getBuiltinModule('node:module').createRequire(baseUrl).resolve('@deepseek-ai/dsh-agent-preset/package.json')), 'skills')
- id: tool-skill
name: '@deepseek-ai/dsh-tool-skill'
- id: present
name: '@deepseek-ai/dsh-tool-present'
- id: tool-plugin-manager
name: '@deepseek-ai/dsh-plugin-manager/tools'
disabled: !!js '!ctx.get(''profileContext'')'PTC模式
- id: persona
name: '@deepseek-ai/dsh-persona'
config:
suffix: Your working directory is {{cwd}}.
prefix: You are a coding agent powered by the {{model}} model.
- id: agent-instructions
name: '@deepseek-ai/dsh-agent-instructions'
config:
maxBytes: 65536
- id: tool-bash
name: '@deepseek-ai/dsh-tool-bash'
disabled: !!js process.platform === 'win32'
- id: tool-pwsh
name: '@deepseek-ai/dsh-tool-pwsh'
disabled: !!js process.platform !== 'win32'
- id: tool-fs
name: '@deepseek-ai/dsh-tool-fs'
- id: tool-fs-search
name: '@deepseek-ai/dsh-tool-fs-search'
config:
sampleOverCapGlobResults: false
- id: tool-jobs
name: '@deepseek-ai/dsh-tool-jobs'
- id: skill-filesystem
name: '@deepseek-ai/dsh-skill-filesystem'
- id: tool-skill
name: '@deepseek-ai/dsh-tool-skill'
- id: command-goal
name: '@deepseek-ai/dsh-command-goal'
- id: tool-goal
name: '@deepseek-ai/dsh-tool-goal'
- 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.
- 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
- 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
modelSelectionSettings: true
backgroundMode: continuable
- id: tool-subagent-fork
name: '@deepseek-ai/dsh-tool-subagent'
config:
provider: fork
toolName: subagent_fork
backgroundMode: continuable
- 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-ptc
name: '@deepseek-ai/dsh-workflow-ptc'
disabled: true
config:
provider: spawn
- id: tool-workflow
name: '@deepseek-ai/dsh-tool-workflow'
disabled: true
- id: tool-ralph
name: '@deepseek-ai/dsh-tool-ralph'
disabled: true
config:
subagentProvider: spawn
maxRounds: 64
- id: tool-ask-user
name: '@deepseek-ai/dsh-tool-ask-user'
- id: tool-todo
name: '@deepseek-ai/dsh-tool-todo'
config:
allowParallelInProgress: true
- id: tool-web
name: '@deepseek-ai/dsh-tool-web'
config:
fetch: true
searchTimeoutMs: 60000
- id: tool-presentation
name: '@deepseek-ai/dsh-agent-tool-presentation'
config:
mode: ptc
- id: present
name: '@deepseek-ai/dsh-tool-present'
- id: tool-plugin-manager
name: '@deepseek-ai/dsh-plugin-manager/tools'
disabled: true