ZiyaZhang
fc558c2db8
Four Context-page enhancements (lane-ctx-deep, F1-F4): - F1 context window breakdown: replace percentage-only card header with a stacked-bar breakdown of input / cached / output token buckets, plus a right-side gauge showing the live window occupancy ratio. - F2 compact Config tab: fold the sprawling profile Config editor into a Config tab on the Context page card, with the same yml-leaf ordering as the top-of-window profile picker. - F3 intervention marker: on the intervention timeline, emit a marker glyph at each user-intervention row (turn-flow-glyph-style) so the card scans as a single stream instead of a header + separate list. - F4 subagent drilldown: when a turn's tool trace hits a subagent, the Trace panel's Config + Output tabs get a second row of Subagent Config / Subagent Output tabs immediately below, driven by the same fold-in-place shape the parent panel already uses. 4 new renderer modules (compact-config-model / context-window-breakdown / intervention-timeline / subagent-drilldown), 6 new test files (41 tests, all node --test style), 4 QA shoot scripts for CDP-driven regression screenshots.
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.