wingetCollections
  • Auto
  • Search
  • Awesome Collections
  • Awesome Programs
  • My Favorite Collections
  • My Collections
  • Account / Settings
  • Terms of Service
  • Privacy
  • About

© 2026 winget.ragerworks.com

Loading...
Install DingTalk Workspace CLI using Winget - wingetCollections
  1. Go back
  2. Packages
  3. DingTalk Workspace CLI
DingTalk Workspace CLI logo

DingTalk Workspace CLI DingTalk (Singapore) Private Limited

dingding dingtalk
Use this command to install DingTalk Workspace CLI:
winget install --id=Alibaba.DingTalkWorkspaceCLI -e

DingTalk Workspace CLI (dws) Description

Primary Purpose: DingTalk Workspace CLI (dws) is a command-line tool designed to manage DingTalk workspace operations efficiently. It serves as an interface for developers and AI agents, enabling seamless interaction with DingTalk's ecosystem.

Key Features:

  • For Humans: The tool offers intuitive commands such as --help for usage guidance, --dry-run to preview actions without execution, and flexible output formats (-f table/json/raw) for data presentation.
  • For AI Agents: It provides structured JSON responses and built-in Agent Skills, facilitating integration with AI tools like Claude Code and Cursor.
  • For Enterprise Admins: The tool features a zero-trust architecture with OAuth device-flow authentication, domain allowlisting, and least-privilege scoping, ensuring robust security.

Audience & Benefit: Ideal for developers seeking efficient workspace management, AI agents requiring direct interaction, and enterprise admins prioritizing secure access. Benefits include enhanced productivity through command-line efficiency, secure access mechanisms, and seamless integration with AI tools, all underpinned by a zero-trust security model.

This tool can be installed via winget, offering a straightforward setup process for users.

README

DingTalk Workspace CLI (dws)

dws — DingTalk Workspace on the command line, built for humans and AI agents.

中文版 · English · Reference · Changelog

> [!IMPORTANT] > Co-creation Phase: This project accesses DingTalk enterprise data and requires enterprise admin authorization. Join the DingTalk DWS co-creation group for support and updates. See Getting Started below. > >

Table of Contents

  • Why dws?
  • Installation
  • Upgrade
  • Getting Started
  • Quick Start
  • Using with Agents
Versions
1.0.43
1.0.42
1.0.41
1.0.40
1.0.39
1.0.38
1.0.37
1.0.36
1.0.35
1.0.34
show 30 more
Website
github.com
License
Last updated
6/27/2026
Download latest version
  • Features
  • Key Services
  • Security by Design
  • Reference & Docs
  • Contributing

    • Why dws?

    • For humans — --help for usage, --dry-run to preview requests, -f table/json/raw for output formats.
    • For AI agents — structured JSON responses + built-in Agent Skills, ready out of the box.
    • For enterprise admins — zero-trust architecture: OAuth device-flow auth + domain allowlisting + least-privilege scoping. Not a single byte can bypass authentication and audit.

    Installation

    macOS / Linux:

    curl -fsSL https://raw.githubusercontent.com/DingTalk-Real-AI/dingtalk-workspace-cli/main/scripts/install.sh | sh

    Windows (PowerShell):

    irm https://raw.githubusercontent.com/DingTalk-Real-AI/dingtalk-workspace-cli/main/scripts/install.ps1 | iex

    Skill mode: mono vs multi

    The installer ships skills in one of two layouts. CLI commands (dws aitable ..., dws calendar ...) are identical in both modes — only the agent-side skill layout differs.

    ModeWhat gets installedBest for
    mono (stable, default)One dws skill covering all productsCross-product workflows; single entry point
    multi 🧪 EXPERIMENTAL18 per-product skills (dingtalk-aitable, dingtalk-calendar, dingtalk-chat, ...)Single-product tasks; smaller context per call

    > 🧪 multi is currently EXPERIMENTAL / preview. 18 product-scoped skills all pass the dispatch verifier, but interface, naming and cross-skill references may change in future releases. For production / shared environments, prefer mono. File issues if you hit problems.

    How to pick:

    • Quick install (one-liner above): non-interactive, installs mono.
    • TTY install (download then run): curl -O .../install.sh && bash install.sh — prompts 1) mono 2) multi (default 1).
    • Override via env: DWS_SKILL_MODE=multi curl -fsSL ... | sh.
    • Switch later: dws skill setup --mode multi (or --mode mono) — re-run any time.

    Other install methods

    npm (requires Node.js (npm/npx)):

    npm install -g dingtalk-workspace-cli

    Pre-built binary: download from GitHub Releases.

    > macOS users: If you see "cannot be opened because Apple cannot check it for malicious software", run: > bash > xattr -d com.apple.quarantine /path/to/dws >

    Build from source:

    git clone https://github.com/DingTalk-Real-AI/dingtalk-workspace-cli.git
cd dingtalk-workspace-cli
go build -o dws ./cmd       # build to current directory
cp dws ~/.local/bin/         # install to PATH

    > Requires Go 1.25+. Use make package to cross-compile for all platforms (macOS / Linux / Windows x amd64 / arm64).

    China mirror

    For users in mainland China, the following channels avoid GitHub network issues. By default (without setting these environment variables) the installer pulls from GitHub.

    1. Install script + pre-built binary (Gitee mirror):

    Repository mirror: https://gitee.com/DingTalk-Real-AI/dingtalk-workspace-cli

    DWS_GITEE_REPO=DingTalk-Real-AI/dingtalk-workspace-cli curl -fsSL https://gitee.com/DingTalk-Real-AI/dingtalk-workspace-cli/raw/main/scripts/install.sh | sh

    > With DWS_GITEE_REPO set, the installer resolves the latest version and every release asset (binary, checksums, skills) from the Gitee API instead of GitHub. If it is unset, installation defaults to GitHub.

    2. npm package (npmmirror mirror):

    npm install -g dingtalk-workspace-cli --registry=https://registry.npmmirror.com

    > npmmirror automatically syncs public packages from the public npm registry, so this works directly in China.

    3. Skills only (Gitee mirror):

    DWS_GITEE_REPO=DingTalk-Real-AI/dingtalk-workspace-cli curl -fsSL https://gitee.com/DingTalk-Real-AI/dingtalk-workspace-cli/raw/main/scripts/install-skills.sh | sh

    > With DWS_GITEE_REPO set, install-skills.sh resolves the version and skills package from Gitee; it also auto-falls back to the Gitee mirror when GitHub is unreachable.

    Upgrade

    > Requires v1.0.7 or later. For earlier versions, please re-run the install script to upgrade.

    dws has built-in self-upgrade capability. Updates are pulled directly from GitHub Releases with SHA256 integrity verification and automatic backup.

    dws upgrade                    # interactive upgrade to latest version
dws upgrade --check            # check for new versions without installing
dws upgrade --list             # list all available versions
dws upgrade --version v1.0.7   # upgrade to a specific version
dws upgrade --rollback         # rollback to the previous version
dws upgrade -y                 # skip confirmation prompt

    How it works

    The upgrade process follows a two-phase atomic flow to ensure consistency:

    1. Prepare — downloads the platform-specific binary and skill packages to a temporary directory, verifies SHA256 checksums, and extracts/validates all files. If any step fails, the upgrade aborts without modifying the existing installation.
    2. Apply — only after all preparations succeed, the binary is replaced and skill packages are installed to all detected agent directories (~/.agents/skills/dws, ~/.claude/skills/dws, ~/.cursor/skills/dws, etc.).

    A backup of the current version is automatically created before each upgrade. Use dws upgrade --rollback to restore the previous version if needed.

    FlagDescription
    --checkCheck for updates without installing
    --listList all available versions with changelogs
    --versionUpgrade to a specific version (e.g. v1.0.7)
    --rollbackRollback to the previous backed-up version
    --forceForce reinstall even if already on the latest version
    --skip-skillsSkip skill package update
    -ySkip confirmation prompt

    Getting Started

    dws auth login            # browser opens automatically
dws auth login --device   # for headless environments (Docker, SSH, CI)

    Select your organization and authorize. That's it.

    > If your organization hasn't enabled CLI access, you'll be prompted to send an access request to your admin. Once approved, re-run dws auth login.

    Organization hasn't enabled CLI access?

    1. After selecting your organization, click "Apply Now" to notify the admin
    2. The admin receives a request card and can approve with one click
    3. Once approved, re-run dws auth login

    Admin: Enable CLI access for your organization

    Go to Developer Platform → "CLI Access Management" → Enable.

    Custom App mode (CI/CD, ISV integration)

    For enterprise-managed scenarios, create your own DingTalk app:

    1. Open Platform Console → Create App
    2. Security Settings → Add redirect URLs: http://127.0.0.1,https://login.dingtalk.com
    3. Publish the app
    4. Login:
    dws auth login --client-id  --client-secret

    Credentials are securely persisted after first login (Keychain). Subsequent runs auto-refresh tokens.

    Migrate auth between Linux sandboxes

    Copying only ~/.dws/app.json does not carry the refresh token; access tokens expire after ~2 hours. Use the official export/import flow:

    # Sandbox A (already logged in)
dws auth export -o /tmp/dws-auth.tar.gz
# Or for copy/paste: dws auth export --base64 -o /tmp/dws-auth.b64

# Sandbox B
dws auth import -i /tmp/dws-auth.tar.gz
# Or: dws auth import -i /tmp/dws-auth.b64 --base64
dws auth status   # confirm "Refresh Token: valid"

    The bundle includes the encrypted keychain under ~/.local/share/dws-cli (with auth-token.enc and dek) plus required ~/.dws config files.

    Quick Start

    dws contact user search --query "engineering"      # search contacts
dws calendar event list                            # list today's calendar events
dws doc search --query "quarterly"                 # search DingTalk Docs
dws minutes list mine                              # list AI meeting notes I created
dws drive list                                     # list DingTalk drive files
dws todo task create --title "Quarterly report" --executors ""   # create a todo (replace )
dws todo task list --dry-run                       # preview without executing

    > Full command list: docs/command-index.md — all commands with descriptions and when-to-use guidance.

    Using with Agents

    dws is designed as an AI-native CLI. Complete Installation and Getting Started first, then configure your agent:

    Agent Invocation Patterns

    # Use --yes to skip confirmation prompts (required for agents)
dws todo task create --title "Review PR" --executors "" --yes

# Use --dry-run to preview operations (safe execution)
dws contact user search --query "engineering" --dry-run

# Use --jq to extract precisely (save tokens)
dws contact user get-self --jq '.result[0].orgEmployeeModel | {name: .orgUserName, dept: .depts[0].deptName, userId}'

    Schema Discovery

    Agents don't need pre-built knowledge of every command. Use dws schema to dynamically discover capabilities:

    # Step 1: Discover all available products
dws schema --jq '.products[] | {id, tool_count: (.tools | length)}'

# Step 2: Inspect target tool's parameter schema
dws schema aitable.query_records --jq '.tool.parameters'

# Optional: inspect DingTalk authorization metadata for PAT planning
dws schema aitable.query_records --jq '.tool.auth'

# Step 3: Construct the correct call
dws aitable record query --base-id BASE_ID --table-id TABLE_ID --limit 10

    Agent Skills

    The repo ships a complete Agent Skill system under skills/, now organized into two layouts:

    • skills/mono/ — single-skill layout (one SKILL.md + references/products/), recommended default.
    • skills/multi/ — per-product skills (dingtalk-aitable/, dingtalk-calendar/, dingtalk-chat/, ... 20 products in total), each with its own SKILL.md. 🧪 EXPERIMENTAL / preview — see banner in each multi SKILL.md for caveats.

    After installing, AI tools like Claude Code / Cursor can operate DingTalk directly through natural language:

    # Install skills into current project (defaults to mono)
curl -fsSL https://raw.githubusercontent.com/DingTalk-Real-AI/dingtalk-workspace-cli/main/scripts/install-skills.sh | sh

    > install.sh installs to $HOME/.agents/skills/dws (global); install-skills.sh installs to ./.agents/skills/dws (current project). > > China users: prefix DWS_GITEE_REPO to use the Gitee mirror — see China mirror.

    Switching or re-installing with dws skill setup:

    # Interactive: prompts for mode + target agents
dws skill setup

# Install mono skill to every detected agent home (claude / cursor / codex / opencode / qoder)
dws skill setup --mode mono --target all --yes

# Install multi skills to a single agent home
dws skill setup --mode multi --target cursor --yes

# Point at a local source tree (e.g. a fork or work-in-progress)
DWS_SKILL_SOURCE=/path/to/skills dws skill setup --mode multi
    FlagValuesDescription
    --modemono | multiSkill layout; defaults to interactive prompt
    --targetall | claude | cursor | codex | opencode | qoderWhere to install; all covers every detected agent home
    --sourcepathLocal source directory (overrides bundled skills)
    --yes—Skip confirmation prompts

    Env vars: DWS_SKILL_MODE=mono|multi (also honored by install.sh / install.ps1), DWS_SKILL_SOURCE=.

    What's included (mono layout):

    ComponentPathDescription
    Master Skillskills/mono/SKILL.mdIntent routing, decision tree, safety rules, error handling
    Product referencesskills/mono/references/products/*.mdPer-product command reference (aitable, chat, calendar, etc.)
    Intent guideskills/mono/references/intent-guide.mdDisambiguation for confusing scenarios (e.g. report vs todo)
    Global referenceskills/mono/references/global-reference.mdAuth, output formats, global flags
    Error codesskills/mono/references/error-codes.mdError codes + debugging workflows
    Recovery guideskills/mono/references/recovery-guide.mdRECOVERY_EVENT_ID handling
    Ready-made scriptsskills/mono/scripts/*.py13 batch operation scripts (see below)

    Ready-made scripts — 13 Python scripts for common multi-step workflows

    ScriptDescription
    calendar_schedule_meeting.pyCreate event + add participants + find & book available meeting room
    calendar_free_slot_finder.pyFind common free slots across multiple people, recommend best meeting time
    calendar_today_agenda.pyView today/tomorrow/this week's schedule
    import_records.pyBatch import records from CSV/JSON into AITable
    bulk_add_fields.pyBatch add fields to an AITable data table
    upload_attachment.pyUpload attachment to AITable attachment field
    todo_batch_create.pyBatch create todos from JSON (with priority, due date, executors)
    todo_daily_summary.pySummarize today/this week's incomplete todos
    todo_overdue_check.pyScan overdue todos and output overdue list
    contact_dept_members.pySearch department by name and list all members
    attendance_my_record.pyView my attendance records for today/this week/specific date
    attendance_team_shift.pyQuery team shift schedules and attendance statistics
    report_inbox_today.pyView today's received reports with details

    ISV Integration: Author your own Agent Skills and orchestrate them with dws skills for cross-product workflows: ISV Skill → dws Skill → DingTalk Open Platform API (enforced auth + full audit).

    Features

    Raw API Access — call any DingTalk OpenAPI directly

    dws api lets you call any DingTalk OpenAPI without an SDK. Tokens are automatically acquired and refreshed.

    > Prerequisite: Must login with your own app credentials (see Custom App mode). Encrypted tokens from MCP default-credential login are not supported for raw API calls.

    # Login (first time only)
dws auth login --client-id  --client-secret 

# === api.dingtalk.com ===

# List all enterprise apps
dws api GET /v1.0/microApp/allApps

# Search users (POST + JSON body)
dws api POST /v1.0/contact/users/search \
  --data '{"queryWord":"engineering","offset":0,"size":10}'

# === oapi.dingtalk.com ===

# Get user details (use --base-url to specify domain)
dws api POST /topapi/v2/user/get \
  --base-url https://oapi.dingtalk.com \
  --data '{"userid":""}'

# Or use the full URL directly
dws api POST https://oapi.dingtalk.com/topapi/v2/user/get \
  --data '{"userid":""}'

# === General ===
dws api GET /v1.0/microApp/allApps --page-all   # auto-paginate
dws api GET /v1.0/microApp/allApps --dry-run     # preview request
dws api GET /v1.0/microApp/allApps --jq '.agentId'  # jq filtering
    FeatureDetails
    Dual-form auto-detectionAutomatically selects api.dingtalk.com (header auth) or oapi.dingtalk.com (query-param auth) based on URL
    Automatic token managementApp-level accessToken is fetched on first call, cached while valid, auto-refreshed on expiry
    Domain allowlistOnly api.dingtalk.com and oapi.dingtalk.com permitted — prevents token leakage
    Auto-pagination--page-all iterates all pages. --page-limit caps the maximum (default 10, set to 0 for unlimited, hard cap at 500 to prevent infinite loops)

    Smart Input Correction — auto-corrects common AI model parameter mistakes

    Built-in pipeline engine that normalizes flag names, splits sticky arguments, and fuzzy-matches typos:

    # Naming convention auto-conversion (camelCase / snake_case / UPPER -> kebab-case)
dws aitable record query --baseId BASE_ID --tableId TABLE_ID         # auto-corrected to --base-id --table-id

# Sticky argument splitting
dws contact user search --query "engineering" --timeout30           # auto-split to --timeout 30

# Fuzzy flag name matching
dws aitable record query --base-id BASE_ID --tabel-id TABLE_ID       # --tabel-id -> --table-id

# Value normalization (boolean / number / date / enum)
# "yes" -> true, "1,000" -> 1000, "2024/03/29" -> "2024-03-29", "ACTIVE" -> "active"
    Agent Outputdws Auto-Corrects To
    --userId--user-id
    --limit100--limit 100
    --tabel-id--table-id
    --USER-ID--user-id
    --user_name--user-name

    jq Filtering & Field Selection — fine-grained output control to reduce token consumption

    # Built-in jq expressions
dws aitable record query --base-id BASE_ID --table-id TABLE_ID --jq '.invocation.params'
dws schema --jq '.products[] | {id, tools: (.tools | length)}'

# Return only specific fields
dws aitable record query --base-id BASE_ID --table-id TABLE_ID --fields invocation,response

    Schema Introspection — query parameter schemas before making calls

    dws schema                                              # list all products and tools
dws schema aitable.query_records                        # view parameter schema
dws schema aitable.query_records --jq '.tool.required'   # view required fields
dws schema aitable.query_records --jq '.tool.auth'       # view authorization metadata
dws schema --jq '.products[].id'                        # extract all product IDs

    Pipe & File Input — read flag values from files or stdin

    # Read message body from a file
dws chat message send-by-bot --robot-code BOT_CODE --group GROUP_ID \
  --title "Weekly Report" --text @report.md

# Pipe content via stdin
cat report.md | dws chat message send-by-bot --robot-code BOT_CODE --group GROUP_ID \
  --title "Weekly Report"

# Read from stdin explicitly
dws chat message send-by-bot --robot-code BOT_CODE --group GROUP_ID \
  --title "Weekly Report" --text @-

    > Note: @ is treated as the @ file-injection prefix only when the next character is an ASCII path-shaped character (A-Z / a-z / 0-9 / . / / / ~ / _ / -), or @- for stdin. Chat-bot payloads like --text "@所有人 周报" or --text "@张三 看一下" pass through unchanged, so literal mentions reach the API as-is.

    DingTalk bot — connect a robot to your local AI

    dws dev connect bridges a DingTalk robot to a local AI CLI (Claude Code / Codex / opencode / Qoder / Gemini, or any tool via --agent-cmd): @-mention the bot in a chat and it answers using your local agent, keeping per-conversation multi-turn memory.

    dws dev connect --channel auto --robot-client-id  --robot-client-secret

    In-chat session commands (send the bare command as the whole message — no agent turn, no tokens):

    CommandEffect
    /new (aliases /start, /reset)Start a fresh session; the previous one is left intact (resumable where the agent supports it)
    /clearWipe the current session — disposed through the agent's real session op (opencode issues DELETE /session/:id); channels whose agent exposes no delete primitive fall back to a reset

    See docs/robot-quickstart.md for the full 4-step walkthrough (install → create robot → connect → add to a group).

    Key Services

    ServiceCommandCommandsSubcommandsDescription
    Contactcontact15user dept label relationSearch users by name / mobile / job-number, batch query, departments, labels & roles, person relations, roster profile & dismissions, current user
    Chat / IMchat (alias im)65message group bot conversation-info search search-common list-top-conversations group-mute group-mute-member mute set-top list-categories list-conversationsMessages (send / reply / list / list-all / by-sender / mentions / focused / unread / topic replies / search / advanced search / forward / cards / emoji & text-emotion reactions / recall / read & send status queries), group CRUD + member management (members add / remove / list / add-bot, member-role CRUD, invite URL, icon, settings, transfer-owner, set-admin, quit), bot-identity messaging (send-by-bot / recall-by-bot / send-by-webhook), conversation info, common-groups lookup, group/member/conversation mute, conversation set-top, conversation categories
    Calendarcalendar23event book acl attendee participant room busy attachmentEvents CRUD + suggested times + attachments, calendar books (get / search / primary via --id primary), access-control list, attendee management (wukong-aligned naming, --calendar-id aware), meeting room booking, free-busy query
    Todotodo16task commentCreate / list / update / done / get / delete tasks, plus task comments
    Approvaloa15approvalApprove / reject / revoke / redirect tasks, pending / initiated / submitted / executed / cc instances, process forms, comments, operation records
    Attendanceattendance4record shift summary rulesClock-in records, shift schedules, attendance summary, group rules
    Dingding2messageSend / recall DING messages
    Reportreport20create submit list detail template stats inbox outbox entryCreate / submit reports, sent & received (inbox / outbox) lists, templates (get / list), statistics, single-entry get
    AI Tablesaitable102base table record field view section advperm workflow dashboard chart import export attachment template formFull CRUD for Bases / datasheets / records / fields / views; node (section) management, advanced permission & roles, automation workflows; record upsert / share-url / history / primary-doc; view lock / duplicate / frozen-cols / row-height / fill-color-rule / card / timebar; charts & dashboards; import/export; attachments; forms; templates
    Docdoc29search list info read create update upload download copy move rename file folder block comment permission mediaSearch / read / write docs, file & folder create, block-level editing, comments (list / create / reply / create-inline), permission management, media, upload / download
    Drivedrive17list list-spaces info download mkdir upload upload-info commit delete copy move rename search permissionDingTalk drive file ops: list / search / info / download, create folders, upload (one-shot or two-phase), copy / move / rename, permission management (list / mutation / remove), doc-transfer, delete
    Minutesminutes31list get tag update mind-graph speaker permission hot-word record upload replace-textList AI meeting notes (mine / shared / all), tags (list / query by tag), details (info / summary / keywords / transcription / todos / batch), title/summary updates, mind map, speaker, member permission, hot-word, recording control, upload session
    Mailmail33mailbox message send draft folder template contact tag thread attachment userList mailboxes, KQL search + folder-scoped message list, read & send messages, drafts, folder CRUD, message templates (CRUD), mail contacts (CRUD), tags, threads, attachments, address-book user search
    Sheetsheet60range filter filter-view cond-format (+ dimension, float-image, dropdown, csv, merge, find/replace, write-image, …)Online spreadsheet (contentType=ALIDOC, extension=axls): worksheet CRUD, range read / write / copy / fill / sort / style, dimension ops, filters & filter views, conditional formatting, float images, dropdowns, CSV get/put, cell merge / unmerge, find / replace, image write
    Wikiwiki27space member node doc fileKnowledge base management: spaces (create / get / list / search / delete), members (add / list / update / remove), node tree (create / delete / list / search / move / copy / transfer), docs & files
    DevDocdevdoc2article errorSearch the DingTalk Open Platform documentation and diagnose API errors
    AI Searchaisearch3personEnterprise people search by name / department / position / duty / supervisor / subordinate / phone / job-number (single command, multi-dimension filter)
    Livelive1streamDingTalk live streaming: list my lives
    Raw APIapi1—Call any DingTalk OpenAPI directly (api / oapi dual-form), with automatic app-level token management

    > 466 commands across 18 products (after the dws-wukong alignment in 1.0.43). Full listing with descriptions and usage scenarios: docs/command-index.md. Run dws --help for the top-level tree, or dws --help for subcommands.

    > Note on chat bot: bot capabilities (send-by-bot / recall-by-bot / add-bot / send-by-webhook / bot search) are merged into the relevant chat subtrees (e.g. dws chat message send-by-bot, dws chat group members add-bot) so the agent-facing command surface stays flat and discoverable. There is no longer a separate top-level bot product.

    Coming soon

    • conference (video meetings)
    • Multi-skill mode (experimental) — per-product skills under skills/multi/; opt in via dws skill setup --mode multi

    Security by Design

    dws treats security as a first-class architectural concern, not an afterthought. Credentials never touch disk, tokens never leave trusted domains, permissions never exceed grants, operations never escape audit — every API call must pass through DingTalk Open Platform's authentication and audit chain, no exceptions.

    For Developers

    MechanismDetails
    Encrypted token storagePBKDF2 + AES-256-GCM encryption, keyed by device physical MAC address; cross-platform Keychain/DPAPI integration provides additional protection — tokens cannot be decrypted on another machine
    Input securityPath traversal protection (symlink resolution + working directory containment), CRLF injection blocking, Unicode visual spoofing filtering — prevents AI Agents from being tricked by malicious instructions
    Domain allowlistDWS_TRUSTED_DOMAINS defaults to *.dingtalk.com; bearer tokens are never sent to non-allowlisted domains
    HTTPS enforcedAll requests require TLS; HTTP only permitted for loopback during development
    Dry-run preview--dry-run shows call parameters without executing, preventing accidental mutations
    Zero credential persistenceClient ID / Secret used in memory only — never written to config files or logs

    For Enterprise Admins

    MechanismDetails
    OAuth device-flow authUsers must authenticate through an admin-authorized DingTalk application
    Least-privilege scopingCLI can only invoke APIs granted to the application — no privilege escalation
    Allowlist gatingAdmin confirmation required during co-creation phase; self-service approval planned
    Full-chain auditEvery data read/write passes through the DingTalk Open Platform API — enterprise admins can trace complete call logs in real time; no anomalous operation can hide

    For ISVs

    MechanismDetails
    Tenant data isolationOperates under authorized app identity; cross-tenant access is impossible
    Skill sandboxAgent Skills are Markdown documents (SKILL.md) — prompt descriptions only, no arbitrary code execution
    Zero blind spotsEvery API call during ISV–dws skill orchestration is forced through DingTalk Open Platform authentication — full call chain is traceable with no bypass path

    > Found a vulnerability? Report via GitHub Security Advisories. See SECURITY.md.

    Reference & Docs

    • Command Index — every runtime command with description and when-to-use guidance
    • Reference — environment variables, exit codes, output formats, shell completion
    • Architecture — discovery-driven pipeline, IR, transport layer
    • Open Platform App Command Routing — yulan dev app command design, MCP overlay, permission flow, and Agent routing
    • Changelog — release history and migration notes

    Contributing

    See CONTRIBUTING.md for build instructions, testing, and development workflow.

    License

    Apache-2.0