kingwl
c0146b9c4a
Review follow-up (tianyicui): plan mode and the sandbox are orthogonal
AXES, not just orthogonal state — entering plan must not change what the
sandbox enforces, matching Codex's separation of Plan/Default
collaboration presets from sandbox and approval settings.
ModeDefinition.access, the bash/resolve-mode clamp, and both cap-derived
guards are removed; a ModeDefinition is exactly { section }, and a mode
now carries only its guidance section plus the exit_plan_mode review.
The bash seam's resolveMode + waterfall go with their only listener:
dsh-bash and dsh-tool-bash revert to master byte-for-byte, and the
dsh-mode → dsh-bash dependency edge is gone. A deployment that wants
kernel-enforced read-only planning pairs the mode picker with the
independent sandbox-mode option, in either order.
The RFC archives this as the second removed enforcement shape (after
the interim allowlist) with the same restart trigger — effects
self-declaration; the orthogonality FAQ now answers with the two-axis
rule. The plan example demonstrates the axes side by side, and the
re-recorded fixtures pin the guidance-only section.
4.5 KiB
Examples
Runnable demos (not workspaces) that showcase how the harness is wired. Each example is a thin leaf: a cordis.yml that picks the swappable backends (an LLM adapter, a bash executor), loads one app package, and may add optional product tools or demo-only mocks. The composition — the spine, the front-door cluster, and the boot glue — lives in the app packages (@deepseek-ai/dsh-stdio-demo, @deepseek-ai/dsh-acp-demo) and the @deepseek-ai/dsh-agent-spine-demo bundle they share. There is no start.ts; the demo:* scripts invoke each app package's bin.
echo-agent
A mock model + echo tool on the stdio chat app — the all-mock skeleton. The leaf swaps dsh-stdio-demo's LLM backend to a local mock-echo adapter and adds a local echo tool. Demonstrates:
- A thin leaf
cordis.ymlloading the@deepseek-ai/dsh-stdio-demoapp - Registering a mock
LlmAdapter(streaming scripted responses) - Registering a tool via
ctx.tools.register() - "Swap the backend, keep the app" — the only difference from
coding-agentis the adapter
Run with: pnpm run demo:echo. When prompted, type "echo " to trigger a tool call round-trip.
coding-agent
A REPL agent demo: DeepSeek V4 + the read/write/edit filesystem tools + the bash tool suite, subagent delegation, and the todo_write task tracker on the same @deepseek-ai/dsh-stdio-demo app. The UI is a terminal readline REPL.
Run with: pnpm run demo:repl (needs DEEPSEEK_API_KEY in the environment or a gitignored repo-root .env). See coding-agent/README.md for details.
Run the Code Mode overlay with pnpm run demo:code-mode, or pass acp for the ACP example. See the Code Mode example for its composition and a sample task.
cordis-agent
The self-referential demo: the coding spine plus @deepseek-ai/dsh-tool-cordis, whose three tools (cordis_inspect / cordis_mount / cordis_unmount) let the agent inspect the live cordis runtime it runs inside, mount model-written plugins into it (an event listener, a brand-new tool for itself, or a service another mount injects), and dispose them again — all dynamic mounts grouped under one cordis-dynamic fiber subtree. The ctx.fs/ctx.web services ride along provider-only, as the capabilities those plugins build on.
Run with: pnpm run demo:cordis (needs DEEPSEEK_API_KEY). See cordis-agent/README.md for the staged demo script and the toolset RFC for the design and sandbox caveats.
acp-agent
An agent demo exposed as an Agent Client Protocol (ACP) server over JSON-RPC stdio, via the @deepseek-ai/dsh-acp-demo app — drive it from Zed or any other ACP client. Also the home of the keyless snapshot tests.
Run with: pnpm run demo:acp (needs DEEPSEEK_API_KEY); pnpm run demo:code-mode acp boots the same server in Code Mode via the code-mode.cordis.yml overlay. See acp-agent/README.md for the Zed setup and the snapshot-test design.
The default cordis.yml composes @deepseek-ai/dsh-sandbox-local, @deepseek-ai/dsh-bash-sandbox, @deepseek-ai/dsh-user-approval, and @deepseek-ai/dsh-permission. A capable client gets one Permissions select: workspace-write confines bash to the configured workspace and asks before a wider retry, while danger-full-access removes file confinement and disables approval prompts. A denied command can therefore surface a one-shot session/request_permission prompt in the editor; "Allow once" runs exactly that retry under the requested wider mode.
plan-acp-agent
The ACP server with session modes composed (@deepseek-ai/dsh-mode) — the editor's mode picker switches the session into plan mode, the model works under the plan guidance section, and it leaves through the user-reviewed exit_plan_mode tool (the review arrives as an elicitation form). The mode picker and the sandbox/approval selects are independent axes on the same session — switching one never disturbs the other.
Run with: pnpm run demo:plan-acp (needs DEEPSEEK_API_KEY). See plan-acp-agent/README.md.