feat: fold the Code Mode demos into demo:code-mode with a UI argument
Code Mode is the point; the UI is just the surface it happens to wear. demo:code and demo:acp-code collapse into one dispatcher (scripts/demo-code-mode.mjs): `pnpm run demo:code-mode [repl|acp]` — repl (default) boots the stdio REPL over examples/code-agent, acp serves examples/acp-agent's code-mode overlay; each UI runs the exact node invocation its standalone script ran, and an unknown argument fails loud with usage. All nine references across READMEs, the RFC, the overlay header, and the keyless-smoke comment renamed. Smoked all three paths: usage exit 2, ACP initialize handshake, REPL boot + EOF.
This commit is contained in:
Tianyi Cui
@@ -23,10 +23,10 @@ Run with: `pnpm run demo:repl` (needs `DEEPSEEK_API_KEY` in the environment or a
|
||||
|
||||
The coding agent flipped to **Code Mode**: the worker-thread code runtime is loaded and the tool registry runs `mode: code`, so the model gets exactly one wire tool — `run_code` — plus a generated TypeScript SDK section, and composes bash/read/write/edit/todo_write by writing a program whose output it curates.
|
||||
|
||||
Run with: `pnpm run demo:code` (needs `DEEPSEEK_API_KEY`). See [code-agent/README.md](code-agent/README.md) for what to try and how it differs from coding-agent.
|
||||
Run with: `pnpm run demo:code-mode` (needs `DEEPSEEK_API_KEY`; the REPL is the default UI — `acp` as the argument serves the acp-agent example's Code Mode overlay instead). See [code-agent/README.md](code-agent/README.md) for what to try and how it differs from coding-agent.
|
||||
|
||||
## acp-agent
|
||||
|
||||
An agent demo exposed as an **Agent Client Protocol (ACP)** server over JSON-RPC stdio, via the [`@deepseek-ai/dsh-acp-agent`](../packages/ui/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`); `pnpm run demo:acp-code` boots the same server in Code Mode via the `code-mode.cordis.yml` overlay. See [acp-agent/README.md](acp-agent/README.md) for the Zed setup and the snapshot-test design.
|
||||
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](acp-agent/README.md) for the Zed setup and the snapshot-test design.
|
||||
|
||||
@@ -4,10 +4,10 @@ The DeepSeek Harness SDK agent demo exposed as an **Agent Client Protocol (ACP)*
|
||||
|
||||
```sh
|
||||
pnpm run demo:acp # needs DEEPSEEK_API_KEY (repo-root .env or env)
|
||||
pnpm run demo:acp-code # the same server in Code Mode: one wire tool, run_code
|
||||
pnpm run demo:code-mode acp # the same server in Code Mode: one wire tool, run_code
|
||||
```
|
||||
|
||||
This example is just a leaf `cordis.yml`: it loads the [`@deepseek-ai/dsh-acp-agent`](../../packages/ui/acp-agent) app (which bundles the [`@deepseek-ai/dsh-agent-core`](../../packages/core/agent-core) spine, JSONL session persistence, and the `@deepseek-ai/dsh-acp` bridge — with **no pre-created agents**, since ACP `session/new` creates them on demand), the swappable DeepSeek, bash, and filesystem backends, the model-facing `read`/`write`/`edit`/`subagent`/`subagent_fork`/`todo_write` tool entries, and the advisory `repeat-tool-guard` loop-hygiene plugin. The app package bakes in the no-stdout-logger cluster, so a leaf has no logger entry to get wrong by default — keeping stdout pure for JSON-RPC. `demo:acp-code` boots the same tree through the [`code-mode.cordis.yml`](code-mode.cordis.yml) overlay — the tool surface collapses to `run_code` + the generated TypeScript SDK, dispatching through the worker-thread code runtime (see the [dsh-tools Code Mode section](../../packages/core/tools/README.md#code-mode)).
|
||||
This example is just a leaf `cordis.yml`: it loads the [`@deepseek-ai/dsh-acp-agent`](../../packages/ui/acp-agent) app (which bundles the [`@deepseek-ai/dsh-agent-core`](../../packages/core/agent-core) spine, JSONL session persistence, and the `@deepseek-ai/dsh-acp` bridge — with **no pre-created agents**, since ACP `session/new` creates them on demand), the swappable DeepSeek, bash, and filesystem backends, the model-facing `read`/`write`/`edit`/`subagent`/`subagent_fork`/`todo_write` tool entries, and the advisory `repeat-tool-guard` loop-hygiene plugin. The app package bakes in the no-stdout-logger cluster, so a leaf has no logger entry to get wrong by default — keeping stdout pure for JSON-RPC. `demo:code-mode acp` boots the same tree through the [`code-mode.cordis.yml`](code-mode.cordis.yml) overlay — the tool surface collapses to `run_code` + the generated TypeScript SDK, dispatching through the worker-thread code runtime (see the [dsh-tools Code Mode section](../../packages/core/tools/README.md#code-mode)).
|
||||
|
||||
## stdout is the protocol
|
||||
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
# (the registry offers exactly one wire tool, run_code, plus the generated
|
||||
# TypeScript SDK prompt section) and the worker-thread code runtime joins the
|
||||
# tree as `ctx.codeRuntime`. The dsh-acp-agent bin boots this file for
|
||||
# `pnpm run demo:acp-code` and when the snapshot harness records the
|
||||
# `pnpm run demo:code-mode acp` and when the snapshot harness records the
|
||||
# code-mode scenarios; DSH_SNAPSHOT=replay swaps it for the sibling
|
||||
# code-mode.cordis.snapshot.yml. A config patch REPLACES the entry's whole
|
||||
# config, so the base entry's fields are restated verbatim.
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
The [Code Mode](../../docs/rfc/implemented/feature/2026-06-15-code-mode.md) form of the coding agent: instead of one native tool call per step, the model is offered exactly ONE wire tool — `run_code` — plus a generated TypeScript SDK section declaring every other registered tool (`bash`, `read`, `write`, `edit`, `todo_write`). The model composes tools by writing a program; the program runs in a fresh worker thread (`@deepseek-ai/dsh-code-runtime-worker`), its tool calls bridge back through the ordinary `tools/pre-execute`/`post-execute` pipeline one at a time, each is logged as a `tool/code-dispatch` session event, and ONLY what the program prints or returns re-enters the model's context.
|
||||
|
||||
```sh
|
||||
pnpm run demo:code # needs DEEPSEEK_API_KEY (repo-root .env works)
|
||||
pnpm run demo:code-mode # needs DEEPSEEK_API_KEY (repo-root .env works)
|
||||
```
|
||||
|
||||
Try a task that spans several tool calls, e.g.:
|
||||
|
||||
@@ -42,7 +42,7 @@ async function bootAndEof(): Promise<{ stdout: string; code: number }> {
|
||||
return new Promise((resolve, reject) => {
|
||||
const proc = spawn(
|
||||
process.execPath,
|
||||
// --expose-internals: cordis.yml loads the HMR plugin (mirrors demo:code).
|
||||
// --expose-internals: cordis.yml loads the HMR plugin (mirrors demo:code-mode).
|
||||
['--expose-internals', '--import', tsxLoader, binScript, configPath],
|
||||
{
|
||||
cwd,
|
||||
|
||||
Reference in New Issue
Block a user