mirror of https://github.com/deepseek-ai/deepseek-harness synced 2026-08-15 21:04:50 +00:00

Files

Tianyi Cui 9db3ce7313 test(acp): assert the patch target's name; state the overlay's true failure modes

Codex review, with its own probes, showed the RFC overclaimed: the
disable patch carried no name assertion despite the text crediting one,
and an id rename is not fail-loud — the skipped patch's warning needs a
logger the replay app deliberately lacks, and the resulting keyless
adapter entry fails inside its fiber without reaching the
unhandled-rejection guard (verified by a subprocess probe of the real
installFailLoud + boot composition). The overlay now asserts
name: dsh-llm-deepseek on the patch (a reused id can never disable the
wrong plugin), and the RFC records the honest residual: an id rename
degrades to config rot with replay output still correct (llm-replay
owns the stream short-circuit), plus the insert-collision last-wins
fact.

2026-07-04 17:54:17 +08:00

acp-agent

test(acp): assert the patch target's name; state the overlay's true failure modes

2026-07-04 17:54:17 +08:00

coding-agent

docs: fix review findings — support-group summary row, smoke-prose export-shape claims

2026-07-04 15:59:12 +08:00

echo-agent

docs: fix review findings — support-group summary row, smoke-prose export-shape claims

2026-07-04 15:59:12 +08:00

AGENTS.md

test(hooks): snapshot the CC + Codex hook matrix end-to-end

2026-07-04 00:40:35 +08:00

CLAUDE.md

refactor(examples): extract reusable logic into tested packages

2026-06-19 12:42:28 +08:00

README.md

docs: rename coding demo to repl

2026-07-04 01:07:26 +08:00

README.md

Examples

Runnable demos (not workspaces) that showcase how the harness is wired. Each example is now 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-agent, @deepseek-ai/dsh-acp-agent) and the @deepseek-ai/dsh-agent-core 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-agent's LLM backend to a local mock-echo adapter and adds a local echo tool. Demonstrates:

A thin leaf cordis.yml loading the @deepseek-ai/dsh-stdio-agent app
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-agent is 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-agent 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.

acp-agent

An agent demo exposed as an Agent Client Protocol (ACP) server over JSON-RPC stdio, via the @deepseek-ai/dsh-acp-agent 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). See acp-agent/README.md for the Zed setup and the snapshot-test design.