DeepSeek Harness

DeepSeek Harness (dsh) is DeepSeek's own coding agent — a plugin-composed harness with filesystem, bash, web and sub-agent tools, available as a web UI, a TUI, and a one-shot headless mode. Pointed at rapid-mlx it runs entirely on your Mac: your code never leaves the machine, and there is no DeepSeek account, API key, or token bill involved.

Install

DSH needs Node's Zstd stream API. Node 22.15 or newer works; the npm manifest does not declare that minimum, so an older Node installs cleanly and then fails at plugin boot with an opaque ESM stack.

$ node --version   # must be >= 22.15
$ npm install -g @deepseek-ai/dsh

Config

Start a server, then let rapid-mlx write the provider block. It previews an exact diff first, so you can see the change before it happens:

$ rapid-mlx serve qwen3.6-35b-8bit

# in another terminal
$ rapid-mlx agents dsh --setup --dry-run   # preview
$ rapid-mlx agents dsh --setup             # apply

--setup discovers which model is running and what context window it advertises, then patches $DSH_HOME/settings.yaml (default ~/.dsh/settings.yaml). It preserves unrelated providers and settings, takes a timestamped backup, writes atomically, and refuses to apply if the file changed after the preview.

Harness's generic OpenAI transport insists on resolving a credential even for an unauthenticated loopback server, so rapid-mlx also adds the non-secret sentinel RAPID_MLX_API_KEY: not-needed to Harness's owner-only .credentials.yaml when that key is absent. An existing value is preserved, and credential values are redacted from the preview — if you keep real remote-provider keys in that file, they are never echoed to your terminal.

Run

$ dsh web                                    # browser UI
$ dsh --profile tui                          # terminal UI
$ dsh --profile headless "summarize this workspace"   # one-shot

Why the generic provider, not deepseek-official

Harness ships a native deepseek-official adapter, and rapid-mlx deliberately does not use it. Pointing it at a loopback server would mean inventing an API key and asserting that your Mac carries the DeepSeek cloud service's model identities, capacity, and rate contract. The generic openai-completions route says exactly what is true: a local OpenAI-compatible endpoint serving whatever model you booted. Reasoning-effort levels are still wired through, so the off/low/medium/high control in the UI reaches reasoning_effort on the wire.

What Tier-1 means here

Tier-1 is a release gate, not a badge. Every version bump runs dsh — the real binary, not a mock — through a real multi-step bug-fix task against a booted 35B model, and grades it by re-running the repository's own test suite. If dsh regresses, the release cannot tag or publish.

The grading deliberately ignores dsh's exit status, because it is not a pass signal: measured on rc.7, a Harness pointed at an unregistered provider prints NO_ADAPTER and still exits 0. Only the work actually landing on disk counts.

You can run the same integration suite yourself:

$ rapid-mlx agents dsh --test

It uses an isolated DSH_HOME and workspace, so it never loads or writes your real Harness sessions or credentials.

Gotchas

• Developer preview. DeepSeek labels Harness a developer preview and may make compatibility-breaking configuration changes. rapid-mlx tracks the contract exercised by 0.1.0-rc.7; the rc.6 → rc.7 upgrade did not change the provider schema.
• Node minimum is undeclared. The package imports Node's Zstd stream API without declaring an engine range, so npm happily installs it on a Node that cannot run it. rapid-mlx agents dsh --test probes for this and reports the runtime mismatch before DSH emits its plugin-loader stack trace.
• dsh exits 0 on hard failure. Do not use its exit status in a script as a success check — assert on the work it was supposed to do.
• Reasoning-only checkpoints cannot drive it. DSH needs real tool_calls, so DeepSeek R1-Distill answers inline instead of calling tools. Use a tool-trained model — Qwen 3.6, Qwen 3.8, Gemma 4 and gpt-oss all work.

See also