MCP bridge that lets ChatGPT create, view, continue, and control DeepSeek Harness (DSH) agent sessions.
Pending human review — the facts below come from the source repository.
MCP bridge that lets ChatGPT create, view, continue, and control DeepSeek Harness (DSH) agent sessions.
Users who want this capability in DSH; check the source and docs before installing.
dsh plugin --profile web add github:jiezeng2004-design/dsh-chatgpt-bridge No supported platforms were declared.
0.1.0-rc.6) and verified end-to-end against a live local DSH > runtime with the official MCP SDK client. --- # Quick Start This gets a new user from zero to a verified ChatGPT ↔ DSH connection. Deep architecture and configuration details follow below — you do not need them to install and verify. ## Requirements - Node.js >= 22 installed and on your PATH. - A working DeepSeek Harness (DSH) installation — dsh on your PATH (or use pnpm dlx @deepseek-ai/dsh@0.1.0-rc.6 in place of dsh in every command below). - A web profile is recommended. The Web UI and the Bridge should run in the same web profile/runtime so that ChatGPT-created sessions appear live in DSH Web. - ChatGPT-side MCP and write-action availability depends on your current plan/workspace. Check OpenAI's current official documentation before setup. - This plugin includes write/action tools (dsh_send_message, dsh_start_goal, dsh_approve, ...), not just read-only MCP. It drives a real DSH agent that can modify files inside registered workspaces under DSH's approval/sandbox policy. Treat it accordingly. ## 1. Install Recommended — install the plugin into the web profile (from the published npm package): bash dsh plugin --profile web add dsh-chatgpt-bridge npm install dsh-chatgpt-bridge alone is not enough: the plugin must be added to a DSH profile bundle, which dsh plugin ... add does for you. See Detailed install for source, headless, and manual variants. ## 2. Start one shared DSH runtime bash dsh web Run the DSH Web UI and the Bridge in the same web profile/runtime. ChatGPT-created sessions are native DSH sessions; they only stream live in DSH Web when both share one runtime. | Endpoint | URL | | --- | --- | | DSH Web | http://127.0.0.1:3080 | | Bridge MCP | http://127.0.0.1:3456/mcp | ## 3. Read the authentication token On first boot the bridge generates a token and persists it to $DSH_HOME/chatgpt-bridge.token. Read it with: Windows (PowerShell): powershell Get-Content "$HOME\.dsh\chatgpt-bridge.token" macOS / Linux: bash cat ~/.dsh/chatgpt-bridge.token > Never commit this token to GitHub or paste it into a public chat. It > authorizes MCP access to your DSH runtime. Alternatively, set > DSH_CHATGPT_BRIDGE_TOKEN yourself and the bridge uses it instead of the > generated file. ## 4. Connect ChatGPT ChatGPT Web cannot open a plain localhost MCP endpoint. A URL like http://127.0.0.1:3456/mcp exists only on your machine; ChatGPT Web is a remote MCP client and cannot reach it directly. - If the Bridge runs on your machine, connect ChatGPT through the Secure MCP Tunnel / secure tunneling mechanism that OpenAI currently supports for MCP/custom apps. The tunnel forwards ChatGPT's requests to the loopback endpoint. - Use the token from step 3 as the MCP Authorization Bearer token for the connector/tunnel. - The Bridge keeps its localhost-first design: it binds 127.0.0.1, never exposes a public interface, and never self-hosts a tunnel. - The stdio transport is not the ChatGPT Web quick path — ChatGPT Web does not launch local processes. See Advanced / other MCP clients for stdio and non-ChatGPT MCP clients. ## 5. Scan / refresh tools After the MCP connection is established, scan / refresh the MCP tools in ChatGPT. v0.3.0 exposes 15 tools, and dsh_update_goal must be present (it is the 15th). If the tool list looks stale, refresh/rescan the connector (see Tool count is stale). ## 6. First verification Give ChatGPT this read-only acceptance prompt: text 请使用已连接的 DSH App，只做只读检查： 1. 调用 dsh_health 2. 调用 dsh_list_workspaces 3. 不修改任何文件 4. 返回 bridge version、health 和 workspace 名称 Expected: text health = ok bridge version = 0.3.0 Then a minimal Goal Supervision example (still read-only): text 使用 dsh_start_goal 创建一个只读检查目标（workspace 用 dsh_list_workspaces 查到的名称），goal 描述为“只读检查项目”，plan 为列出项目结构并总结 README，constraints 使用 {"read_only": true}。然后反复调用 dsh_wait_goal 直到 terminal，最后只汇报 health、goal revision 和总结，不修改任何文件。 --- ## Troubleshooting ### ChatGPT cannot connect http://127.0.0.1:3456/mcp is a loopback address on your machine — ChatGPT Web cannot reach it as a remote MCP server. Check the Secure MCP Tunnel / currently supported secure connection method for MCP/custom apps: the tunnel must forward to the loopback endpoint with the bearer token. ### 401 Unauthorized - Read the token: Get-Content "$HOME\.dsh\chatgpt-bridge.token" (PowerShell) or cat ~/.dsh/chatgpt-bridge.token (macOS/Linux). - The connector must send it as the Authorization: Bearer <token> header. - The token belongs to the runtime that generated it. A different $DSH_HOME, a regenerated token, or a mismatched DSH_CHATGPT_BRIDGE_TOKEN all cause 401 — make sure the token matches the currently running runtime. ### dsh_health works but no workspace appears dsh_list_workspaces only lists workspaces already registered in DSH. The bridge never auto-registers arbitrary paths; dsh_create_session with an unregistered path fails with WORKSPACE_NOT_FOUND on purpose. Register the workspace in DSH (Web profile workspace settings / DSH configuration) first. ### Session exists but does not appear live in DSH Web The Bridge and DSH Web must run in the same web profile/runtime. Do not run a separate chatgpt-bridge runtime and a separate web runtime and expect live parity — sessions persist and can be resumed, but they will not stream in real time. ### Tool count is stale / dsh_update_goal missing after upgrade Re-scan / refresh the MCP tools on the ChatGPT side after upgrading the plugin and restarting the profile. v0.3.0 exposes 15 tools; dsh_update_goal is the 15th. ### Port 3456 already in use Identify the process first — never auto-kill an unknown process. On Windows (PowerShell): powershell Get-NetTCPConnection -LocalPort 3456 | Select-Object LocalAddress, LocalPort, OwningProcess Get-Process -Id <OwningProcess> | Select-Object Id, ProcessName, Path On macOS/Linux: bash lsof -iTCP:3456 -sTCP:LISTEN # or: ss -ltnp 'sport = :3456' If it is an old dsh/bridge process, stop it cleanly. Otherwise change the bridge port in the profile config (see DSH configuration) or free the port. ### Bridge error codes | Symptom | Cause / fix | | --- | --- | | WORKSPACE_NOT_FOUND | The workspace is not registered in DSH; dsh_list_workspaces shows what is allowed. | | SESSION_NOT_FOUND | Unknown session id (never created, or persistence not mounted). | | SESSION_NOT_LIVE on cancel | The session is not loaded in this process; only live sessions can be cancelled. | | APPROVAL_NOT_FOUND / QUESTION_NOT_FOUND | The decision was already taken or the bridge restarted (parked decisions are in-memory). | | question provider slot taken (log) | A web UI is attached and owns user questions; answer them in the UI. | | Cold sessions show no title in dsh_list_sessions | Cold titles come from the projection cache; concurrent DSH profiles sharing the cache can clobber rows. Single-profile deployments get titles. | --- ## 60-second smoke test After completing Quick Start steps 1–3: 1. dsh web — one shared runtime. 2. Establish the MCP tunnel to http://127.0.0.1:3456/mcp. 3. In ChatGPT: Scan Tools. 4. Ask ChatGPT to call dsh_health. 5. Confirm: - health = ok - bridge version = 0.3.0 - tool count = 15 - dsh_update_goal exists in the tool list 6. Optionally call dsh_list_workspaces to confirm your workspace is visible. --- ## Architecture text ChatGPT Web | | MCP (Streamable HTTP / stdio) v dsh-chatgpt-bridge <- a DSH (Cordis) plugin row | v DeepSeek Harness <- sessions, agents, tools, approvals, sandbox, workspace | +----+--------------+ | | | Session Agent Workflow | | | +----+------+-------+ v Local Workspace The bridge uses DSH's public plugin seams — it never re-implements DSH: | DSH capability seam | Usage in the bridge | | --- | --- | | ctx.agents (AgentRegistry) | create() / resume() / get() — live agent lookup, session creation, and resume of persisted sessions after restarts | | ctx.sessions (SessionStore) | live session listing, flush() durability | | ctx.sessionPersistence | list() / inspect() — the DSH session log is the authority for session identity across ChatGPT conversations | | ctx.sessionTitle | title read/write (plus the session/title log fold) | | ctx.workspaceRegistry | list + resolve — only registered workspaces can host sessions | | ctx.approval (approval/request waterfall) | the bridge is an answerer: approvals park as waiting_for_approval and are decided one-by-one | | ctx.userQuestions (registerProvider) | the bridge is the question provider: questions park as waiting_for_user | | ctx.agentDefaultModel | default provider/model selection for created sessions | | ctx.agentPresets (mount) | same per-session preset composition the Web UI uses, when a roster exists | | installModelSelection (dsh-agent) | per-agent model selection with log-derived fallback on resume | | createUserMessage + agent.followup() | the canonical way to continue a session's durable log | ### MCP facts | Item | Value | | --- | --- | | Transport | Streamable HTTP (default, http://127.0.0.1:3456/mcp) or stdio | | Protocol version | negotiated by @modelcontextprotocol/sdk 1.30.0 (official MCP SDK) | | Authentication | Bearer token (default): config token → DSH_CHATGPT_BRIDGE_TOKEN env → generated token persisted to $DSH_HOME/chatgpt-bridge.token | | Local endpoint | http://127.0.0.1:3456/mcp (loopback only by default) | | ChatGPT connection | any official MCP client: a local connector at the endpoint with the token, or a remote connector tunneled to the loopback endpoint (e.g. OpenAI's supported Secure MCP Tunnel). The bridge never exposes anything public by itself. | --- ## Detailed install The plugin is a standard DSH profile bundle. It currently targets DSH 0.1.0-rc.6. Recommended: one DSH runtime for both Web :3080 and the MCP bridge :3456. ChatGPT-created sessions are native DSH sessions. The Web UI only sees them live if it shares ctx.agents / ctx.sessions with the bridge. Do not run a headless chatgpt-bridge profile and a separate web profile at the same time — that is two runtimes and live Web parity will fail. ### Install into the Web profile (recommended) The Quick Start uses dsh plugin --profile web add dsh-chatgpt-bridge. If dsh is not on your PATH, the equivalent is: bash pnpm dlx @deepseek-ai/dsh@0.1.0-rc.6 plugin --profile web add dsh-chatgpt-bridge # published: ... add dsh-chatgpt-bridge@0.3.0 # boot ONE process — Web :3080 and MCP :3456 pnpm dlx @deepseek-ai/dsh@0.1.0-rc.6 --profile web dsh_health.capabilities.webSurface is true when the Web gateway is in this process. ### Headless-only (optional) A dedicated chatgpt-bridge profile (no Web) still works. Sessions persist and can be resumed later, but DSH Web :3080 will not stream them in real time. bash pnpm dlx @deepseek-ai/dsh@0.1.0-rc.6 plugin --profile chatgpt-bridge add dsh-chatgpt-bridge@0.3.0 pnpm dlx @deepseek-ai/dsh@0.1.0-rc.6 --profile chatgpt-bridge The published npm package is available at dsh-chatgpt-bridge. ### Install from source bash git clone https://github.com/jiezeng2004-design/dsh-chatgpt-bridge.git cd dsh-chatgpt-bridge npm ci npm run build pnpm dlx @deepseek-ai/dsh@0.1.0-rc.6 plugin --profile web add "file:$PWD" pnpm dlx @deepseek-ai/dsh@0.1.0-rc.6 --profile web For either installation method, dsh plugin installs the package into the profile and, because the package declares dsh.bundle.patch, appends it to the profile's bundle list. The bundle patch inserts only the chatgpt-bridge row so it can sit on top of dsh-web-app without duplicating storage / workspace ids. A headless profile (no web-app) still needs those host rows. Copy cordis.headless.patch.yml into that profile's own cordis.patch.yml. If pnpm cannot run in your environment (e.g. symlinks blocked), install manually: create $DSH_HOME/profiles/chatgpt-bridge/ with package.json (dsh.profile.bundles: ["@deepseek-ai/dsh-base", "dsh-chatgpt-bridge"]), empty cordis.yml / cordis.patch.yml, and a node_modules/dsh-chatgpt-bridge link to this checkout. The checkout's own node_modules may be a junction to the DSH installation's hoisted node_modules so both sides share one module instance. ### DSH configuration Only the plugin's own row config (defaults shown): yaml - id: chatgpt-bridge name: dsh-chatgpt-bridge config: transport: http # http | stdio host: 127.0.0.1 # loopback only by default port: 3456 authMode: token # token | none (loopback only, not recommended) authToken: '' # static token; empty falls back to env, then generated file authTokenEnv: DSH_CHATGPT_BRIDGE_TOKEN tokenFile: '' # default $DSH_HOME/chatgpt-bridge.token resultMaxChars: 8000 resultMaxItems: 50 sessionMaxItems: 20 sessionMaxChars: 4000 logLevel: info Logs go to $DSH_HOME/chatgpt-bridge.log (redacted) and never to stdout, so the stdio transport stays clean. --- ## Advanced / other MCP clients The Bridge supports two MCP transports: | Transport | When to use | | --- | --- | | Streamable HTTP (default) | ChatGPT Web via a secure tunnel, and any HTTP-capable MCP client that can reach the loopback endpoint. | | stdio | Local MCP clients that launch a child process on the same machine as the bridge. | The stdio transport is not the ChatGPT Web quick path: ChatGPT Web does not launch local processes, so it cannot use a stdio connector. Use stdio only with clients that run on the same machine as the bridge. To use stdio, set transport: stdio in the profile config (see DSH configuration) and point the client at the command that boots the bridge profile (dsh --profile chatgpt-bridge). The boot process must not print to stdout; bridge logs go to $DSH_HOME/chatgpt-bridge.log only. No ChatGPT cookies, logins, or web sessions are ever touched: ChatGPT is strictly an MCP client of the bridge. --- ## MCP tool catalog | Tool | Purpose | | --- | --- | | dsh_health | Bridge/DSH status, versions, session counts, capabilities. Never contains tokens/keys/cookies. | | dsh_list_workspaces | Workspaces DSH already registered (id, title, path, counts). | | dsh_create_session | Create a real DSH session bound to a registered workspace (id/path/title). Optional title and initial_message. | | dsh_list_sessions | Live + persisted sessions, newest first, paged (limit/offset), optional workspace filter. | | dsh_get_session | Status, workspace, bounded recent-message summary (max_items/max_chars), pending work, waiting approvals/questions, todos. | | dsh_send_message | Continue an existing DSH session (live agent, or resume from persistence). Returns immediately; long tasks run in the background. | | dsh_get_task_status | idle, queued, running, waiting_for_user, waiting_for_approval, completed, failed, cancelled, blocked, max-tokens, interrupted (DSH-native turn-end reasons). | | dsh_get_result | Last turn's assistant text, status, tool calls, changed files (from the session log), structured error. | | dsh_cancel_task | Cancel through DSH's own agent.cancel() — no PID killing. | | dsh_answer_question | Answer a parked user question (waiting_for_user). | | dsh_approve | Decide one parked approval (waiting_for_approval) — requires the exact approval_id and an explicit approve/reject. No approve-all. | | dsh_start_goal | Hand DSH a multi-step goal/plan (new or existing session). Existing session_id revises the Goal (revision +1). Optional execution_mode / constraints. | | dsh_update_goal | Revise / defer / resume an existing Goal. session_id required; never creates a session. | | dsh_wait_goal | Bounded long-poll (default 25s). If continuation_required is true, call again immediately. | | dsh_stop_goal | Idempotent stop/cancel/interrupt of the supervised goal. Fails closed pending approvals/questions. | ### Goal Supervision (recommended for plans) text ChatGPT plans the work | v dsh_start_goal(workspace, goal, plan?) | | continuation_required=true v dsh_wait_goal(session_id) ---- still running ----+ | | | continuation_required=true | +--------------------------------------------+ | +-- waiting_for_approval --> ask user --> dsh_approve --> wait again +-- waiting_for_user --> ask user --> dsh_answer_question --> wait again +-- completed / failed / cancelled --> done (result is in the wait payload) - continuation_required is an MCP client contract: ChatGPT should call dsh_wait_goal again in the same assistant turn until the loop stops. Do not reply "the task is running in the background" and end the turn. - One MCP call waits internally (≈500ms polls, up to 25s). Do not spam dsh_get_task_status every few hundred milliseconds. - waiting_for_approval / waiting_for_user set needs_user_action and do not continue. Never auto-approve; never guess the answer. - dsh_stop_goal is the user-facing "stop DSH" tool. It is idempotent (already_stopped=true if the session is already terminal). - Optional request_id on dsh_start_goal makes connector retries in the same process idempotent. It is an in-memory map (cap 256), not a Goal DB. After a process restart, continue with session_id. - dsh_health.capabilities.goalSupervision is always true in v0.2+. - The stabilization work originally tracked as "0.2.1" (never released) is folded into v0.3.0: reconciled todos (from tool/result facts, not assistant text), progress_delta on dsh_wait_goal, structured blocked + remaining_runnable_steps, and fail-safe cleanup of goal-owned temps. - v0.3.0 adds dsh_update_goal (15 tools) and a Goal Control Plane: revisions, execution modes, structured constraints, deferred/resume, bounded history. Low-level tools remain for inspection and one-shot messages. ### Goal lifecycle text create dsh_start_goal(workspace, goal, plan?, execution_mode?, constraints?) -> revision 1, session_id run DSH agent works; ChatGPT calls dsh_wait_goal wait continuation_required → wait again waiting_for_user / waiting_for_approval → ask human, then continue revise dsh_update_goal(action=revise) or dsh_start_goal(..., session_id) -> revision +1, previous snapshot kept defer dsh_update_goal(action=defer, defer_steps=["npm_publish"]) -> step is deferred (not failed); independent branches stay runnable resume dsh_update_goal(action=resume, resume_steps=["npm_publish"]) -> same session_id + goal_id; completed steps are not replayed complete wait returns terminal + result; deferred_steps may still be listed stop dsh_stop_goal (no revision bump; goal_cancelled event) Approval and question answers do not increment revision. ### Execution modes | Mode | When | Behaviour | | --- | --- | --- | | standard | default, omitted | Current v0.2 agent instructions. Reasonable analysis/tests allowed. | | minimal | "only wait 35s", smoke, no extra work | Only actions strictly required. Default constraints: no workspace scan, max_changed_files=0. | | strict | user-supplied plan/constraints | Follow the plan/constraints; do not expand scope. | ### Constraints (examples) json { "read_only": true, "allow_workspace_scan": false, "max_changed_files": 0, "forbidden_actions": ["filesystem.scan", "filesystem.write"] } Constraints can only tighten DSH sandbox/approval. read_only=false does not grant write. Runtime enforcement uses the approval waterfall (toolName + optional callId lookup of the logged tool/call) plus post-hoc fact checks. A bash command that never asks approval can only be caught after the fact. Action classes: filesystem.read, filesystem.write, filesystem.scan, process.exec, git.mutate, npm.publish, github.release, network. ### Dependency-aware Goal (npm + GitHub Release) text commit → verify → push → tag ├─ npm publish (may defer on 2FA) └─ GitHub Release (still runnable) When npm hits 2FA: dsh_update_goal({ action: "defer", defer_steps: ["npm_publish"] }). GitHub Release continues on the same session. Later action: "resume" reactivates npm without retagging or repushing. ### Deliberately NOT exposed (first version) execute_shell, run_command, read_any_file, write_any_file, delete_file, git_push, install_package, run_arbitrary_tool. ChatGPT never gets a direct shell: it talks to the DSH agent, and the DSH agent uses DSH tools under DSH's approval/sandbox/workspace policy. --- ## Session lifecycle Preferred (v0.2 Goal Supervision): text ChatGPT: dsh_start_goal(workspace, goal, plan) -> { session_id, continuation_required, next_tool_call: dsh_wait_goal } ChatGPT: dsh_wait_goal(session_id) (repeat while continuation_required) -> { terminal: true, result: { summary, changed_files, todos } } Low-level Session API (still supported): text ChatGPT: dsh_create_session(workspace) -> session_id (e.g. session-034daf61-...) ChatGPT: dsh_send_message(session_id, "帮我分析这个项目，不修改文件。") -> {accepted: true} # returns immediately DSH: agent.followup() -> turn runs in the background ChatGPT: dsh_get_task_status(session_id) -> running -> completed ChatGPT: dsh_get_result(session_id) -> analysis text ChatGPT: dsh_send_message(session_id, "刚才第 2 项不错，现在实现它。") -> same session, same agent loop, same durable log DSH is the authority for session identity. Sessions persist as $DSH_HOME/sessions/<workspace>/<session-id>/session.jsonl.zstd (event log) and survive bridge restarts, ChatGPT conversations, and DSH restarts: dsh_send_message on a cold session resumes it through ctx.agents.resume(), which replays the log into the model context (verified: a marker learned before a process restart was still remembered afterwards). --- ## Security model - No arbitrary shell tool — see the tool catalog. - Workspace boundary — sessions can only be created in workspaces DSH already registered (ctx.workspaceRegistry). Arbitrary paths are never opened or auto-registered; dsh_create_session with C:\Users\..., /, ~, etc. is rejected with WORKSPACE_NOT_FOUND. - Approval is never bypassed — if DSH asks for approval, the bridge parks the request (waiting_for_approval) and only dsh_approve with the exact approval id can grNot by stars — picked by hand, one at a time.
A visual settings dashboard for DeepSeek Harness: every registered settings namespace — including third-party plugin ones the official UI never covers — rendered as editable, schema-driven forms. Early, but the right direction: stop hand-editing YAML.
A DIY trajectory visualizer for DeepSeek Harness: watch the agent’s plan and execution unfold as a graph instead of scrolling raw logs. Early, but it fills a real gap — understanding at a glance what the agent is doing.
Dispatch DSH work from Claude Code / Codex: spin up in-host DSH agent sessions with per-tier presets, watch native subagent progress, and borrow a multimodal bridge that lends the text-only harness vision and image generation. An orchestration plugin that turns DSH into a backend for other coding agents.