Pine/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases 1 Wiki Activity

Restore Cordis mount and unmount names

Browse Source 
Keep temporary lifecycle descriptions and UI labels explicit.
This commit is contained in:
NI0317
2026-07-27 21:20:06 +08:00
parent 826c6fd243
commit 1ef285d038
80 changed files with 578 additions and 567 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/cordis-agent/README.i18n.yaml
+2 -2
View File
@@ -2,5 +2,5 @@
# side as of the last confirmed-consistent state. Both languages carry equal authority;
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write examples/cordis-agent/README.md
README.md: 45c7d96f672a6dc7703d750f46e2fee08966adfa
README.zh.md: c9991dea8840e1c046f3e0861e65c0d84a81634a
README.md: 55970e932bc16d8361932daa9ea55af83ef73d33
README.zh.md: c2873b6de96a8b47ad8ea4fb2cf03a7501406300
examples/cordis-agent/README.md
+9 -9
View File
@@ -2,7 +2,7 @@
English | [中文](README.zh.md)
The self-referential harness demo: the DeepSeek V4 coding spine on the full-screen TUI plus [`@deepseek-ai/dsh-tool-cordis`](../../packages/cordis/tool-cordis/README.md), which lets the model inspect the current DSH process, try in-memory temporary Plugins, and stop them. Temporary Plugins remain active across turns but disappear on stop, toolset unload, or DSH restart; they create no files or configuration and may affect other sessions in the process. The `ctx.fs` and `ctx.web` services are provider-only capabilities available to those Plugins. The design lives in [the toolset Agent Note](../../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md).
The self-referential harness demo: the DeepSeek V4 coding spine on the full-screen TUI plus [`@deepseek-ai/dsh-tool-cordis`](../../packages/cordis/tool-cordis/README.md), which lets the model inspect the current DSH process, mount in-memory temporary Plugins, and unmount them. Temporary Plugins remain active across turns but disappear on unmount, toolset unload, or DSH restart; they create no files or configuration and may affect other sessions in the process. The `ctx.fs` and `ctx.web` services are provider-only capabilities available to those Plugins. The design lives in [the toolset Agent Note](../../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md).
## Run it
@@ -18,20 +18,20 @@ pnpm run demo:cordis acp # ACP server
The intended demo is staged — verify the listener link first, then let the agent extend itself:
```
> Try a temporary Plugin that listens to the 'agent/status' event and logs every status change, then run `echo hi` with bash.
[tool call] cordis_try({"code": "return { name: 'status-logger', apply(ctx) { ctx.on('agent/status', (agent, status) => console.log('status →', status)) } }"})
[tool result] Temporary Plugin dyn-1 is running (plugin "status-logger"; available until stopped or DSH restarts).
> Mount a temporary Plugin that listens to the 'agent/status' event and logs every status change, then run `echo hi` with bash.
[tool call] cordis_mount({"code": "return { name: 'status-logger', apply(ctx) { ctx.on('agent/status', (agent, status) => console.log('status →', status)) } }"})
[tool result] Temporary Plugin dyn-1 is running (plugin "status-logger"; available until unmounted or DSH restarts).
[tool call] bash({"command": "echo hi"})
[cordis:dyn-1] status → … ← the temporary listener firing, live
> Now give yourself a reverse_text tool and use it on "harness".
[tool call] cordis_try({"code": "return { name: 'reverse-text', inject: ['tools'], apply(ctx) { ctx.tools.register(harness.defineTool({ name: 'reverse_text', … })) } }"})
[tool call] cordis_mount({"code": "return { name: 'reverse-text', inject: ['tools'], apply(ctx) { ctx.tools.register(harness.defineTool({ name: 'reverse_text', … })) } }"})
[tool call] reverse_text({"text": "harness"}) ← a tool the agent built for itself, one step earlier
> Stop both temporary Plugins.
[tool call] cordis_stop({"id": "dyn-1"})
> Unmount both temporary Plugins.
[tool call] cordis_unmount({"id": "dyn-1"})
```
Ask for `cordis_inspect` with `what: "api"` or `what: "events"` to see the generated service/event reference used to write Plugin code, and try two cooperating temporary Plugins (`ctx.provide` in one, `inject` in the other) to watch Cordis park and revive the consumer.
Ask for `cordis_inspect` with `what: "api"` or `what: "events"` to see the generated service/event reference used to write Plugin code, and mount two cooperating temporary Plugins (`ctx.provide` in one, `inject` in the other) to watch Cordis park and revive the consumer.
## End-to-end tests
`tests/keyless-smoke.e2e.ts` boots the real `cordis.yml` through the Loader with a dummy key and asserts the banner, package-name resolution, and clean EOF exit. `tests/cordis-tools.e2e.ts` is the with-key smoke: a real model tries a temporary status listener and the test verifies its tagged console line, creates and uses a `reverse_text` tool, and composes two temporary Plugins through provide/inject. [`packages/cordis/tool-cordis`](../../packages/cordis/tool-cordis) carries the unit coverage under the per-file 100% gate.
`tests/keyless-smoke.e2e.ts` boots the real `cordis.yml` through the Loader with a dummy key and asserts the banner, package-name resolution, and clean EOF exit. `tests/cordis-tools.e2e.ts` is the with-key smoke: a real model mounts a temporary status listener and the test verifies its tagged console line, creates and uses a `reverse_text` tool, and composes two temporary Plugins through provide/inject. [`packages/cordis/tool-cordis`](../../packages/cordis/tool-cordis) carries the unit coverage under the per-file 100% gate.
examples/cordis-agent/README.zh.md
+9 -9
View File
@@ -2,7 +2,7 @@
[English](README.md) | 中文
自指 harness 演示：在全屏 TUI 上运行 DeepSeek V4 编码主干，并加载 [`@deepseek-ai/dsh-tool-cordis`](../../packages/cordis/tool-cordis/README.md)。后者让模型检查当前 DSH 进程、尝试仅存于内存的临时 Plugin，并再次停止它们。临时 Plugin 可跨 turn 保持活跃，但会在 stop、工具集卸载或 DSH 重启后消失；它们不创建文件或配置，也可能影响同一进程中的其他 session。`ctx.fs` 和 `ctx.web` 是这些 Plugin 可用的 provider-only 能力。设计详见[工具集 Agent Note](../../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md)。
自指 harness 演示：在全屏 TUI 上运行 DeepSeek V4 编码主干，并加载 [`@deepseek-ai/dsh-tool-cordis`](../../packages/cordis/tool-cordis/README.md)。后者让模型检查当前 DSH 进程、挂载仅存于内存的临时 Plugin，并再次卸载它们。临时 Plugin 可跨 turn 保持活跃，但会在卸载、工具集卸载或 DSH 重启后消失；它们不创建文件或配置，也可能影响同一进程中的其他 session。`ctx.fs` 和 `ctx.web` 是这些 Plugin 可用的 provider-only 能力。设计详见[工具集 Agent Note](../../.agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md)。
## 运行
@@ -18,20 +18,20 @@ pnpm run demo:cordis acp # ACP server
预期演示分阶段进行：先验证监听器链接，再让 agent 扩展自身：
```
> Try a temporary Plugin that listens to the 'agent/status' event and logs every status change, then run `echo hi` with bash.
[tool call] cordis_try({"code": "return { name: 'status-logger', apply(ctx) { ctx.on('agent/status', (agent, status) => console.log('status →', status)) } }"})
[tool result] Temporary Plugin dyn-1 is running (plugin "status-logger"; available until stopped or DSH restarts).
> Mount a temporary Plugin that listens to the 'agent/status' event and logs every status change, then run `echo hi` with bash.
[tool call] cordis_mount({"code": "return { name: 'status-logger', apply(ctx) { ctx.on('agent/status', (agent, status) => console.log('status →', status)) } }"})
[tool result] Temporary Plugin dyn-1 is running (plugin "status-logger"; available until unmounted or DSH restarts).
[tool call] bash({"command": "echo hi"})
[cordis:dyn-1] status → … ← the temporary listener firing, live
> Now give yourself a reverse_text tool and use it on "harness".
[tool call] cordis_try({"code": "return { name: 'reverse-text', inject: ['tools'], apply(ctx) { ctx.tools.register(harness.defineTool({ name: 'reverse_text', … })) } }"})
[tool call] cordis_mount({"code": "return { name: 'reverse-text', inject: ['tools'], apply(ctx) { ctx.tools.register(harness.defineTool({ name: 'reverse_text', … })) } }"})
[tool call] reverse_text({"text": "harness"}) ← a tool the agent built for itself, one step earlier
> Stop both temporary Plugins.
[tool call] cordis_stop({"id": "dyn-1"})
> Unmount both temporary Plugins.
[tool call] cordis_unmount({"id": "dyn-1"})
```
请求 `cordis_inspect` 并使用 `what: "api"` 或 `what: "events"`，即可查看编写 Plugin 代码所用的生成服务／事件资料。还可尝试两个协作临时 Plugin（一个中调用 `ctx.provide`，另一个中使用 `inject`），观察 Cordis 如何暂停并恢复消费方。
请求 `cordis_inspect` 并使用 `what: "api"` 或 `what: "events"`，即可查看编写 Plugin 代码所用的生成服务／事件资料。还可挂载两个协作临时 Plugin（一个中调用 `ctx.provide`，另一个中使用 `inject`），观察 Cordis 如何暂停并恢复消费方。
## 端到端测试
`tests/keyless-smoke.e2e.ts` 使用虚拟密钥通过 Loader 启动真实 `cordis.yml`，并断言横幅、包名解析和 EOF 后干净退出。`tests/cordis-tools.e2e.ts` 是带密钥的冒烟测试：真实模型尝试一个临时状态 listener，测试验证其带标记的 console 行；然后创建并使用 `reverse_text` 工具，再通过 provide/inject 组合两个临时 Plugin。[`packages/cordis/tool-cordis`](../../packages/cordis/tool-cordis) 在每文件 100% 覆盖率门禁下承载单元覆盖。
`tests/keyless-smoke.e2e.ts` 使用虚拟密钥通过 Loader 启动真实 `cordis.yml`，并断言横幅、包名解析和 EOF 后干净退出。`tests/cordis-tools.e2e.ts` 是带密钥的冒烟测试：真实模型挂载一个临时状态 listener，测试验证其带标记的 console 行；然后创建并使用 `reverse_text` 工具，再通过 provide/inject 组合两个临时 Plugin。[`packages/cordis/tool-cordis`](../../packages/cordis/tool-cordis) 在每文件 100% 覆盖率门禁下承载单元覆盖。
examples/cordis-agent/composition.md
+1 -1
View File
@@ -3,7 +3,7 @@
# Cordis Agent App Composition
The self-referential demo puts @deepseek-ai/dsh-tool-cordis on the coding spine, letting the agent inspect its current-process runtime and try or stop in-memory temporary Plugins.
The self-referential demo puts @deepseek-ai/dsh-tool-cordis on the coding spine, letting the agent inspect its current-process runtime and mount or unmount in-memory temporary Plugins.
```mermaid
flowchart LR
examples/cordis-agent/cordis.yml
+7 -7
View File
@@ -1,6 +1,6 @@
# Self-referential TUI demo: the coding spine plus tools to inspect the live
# service/plugin/tool/temporary/API/event state, try a model-written temporary
# Plugin, and quiescently stop it. The app bin loads the gitignored
# service/plugin/tool/temporary/API/event state, mount a model-written temporary
# Plugin, and quiescently unmount it. The app bin loads the gitignored
# root `.env` before reading the required DeepSeek key and optional base URL.
# Trust stance: the vm and context façade limit accidental global/framework
# access but are not a security boundary; temporary Plugin code reaches live capabilities
@@ -60,7 +60,7 @@
persistenceRoot: './.sessions'
workspaceContext:
maxBytes: 65536
welcome: 'cordis-agent ready. Ask it to inspect its runtime, try a temporary listener, or invent a temporary tool for itself.'
welcome: 'cordis-agent ready. Ask it to inspect its runtime, mount a temporary listener, or invent a temporary tool for itself.'
persona: |
You are cordis-agent, a self-referential harness demo powered by the
{{model}} model.
@@ -68,15 +68,15 @@
You run INSIDE a cordis plugin runtime, and your cordis_* tools operate
on that live runtime: cordis_inspect to look around (its `api` and
`events` sections document the service methods, type shapes, and events
your Plugin code can use), cordis_try to try an in-memory temporary
your Plugin code can use), cordis_mount to mount an in-memory temporary
Plugin (an event listener, a brand-new tool for yourself, or a service
another temporary Plugin injects), cordis_stop to clean one up. These
Plugins remain across turns but disappear on stop, toolset unload, or
another temporary Plugin injects), cordis_unmount to clean one up. These
Plugins remain across turns but disappear on unmount, toolset unload, or
DSH restart and may affect other sessions in this process. In Plugin code, NEVER use Node
built-ins (require/setTimeout/fetch) — use the runtime's cordis services
via inject: fs, web, bash, and timer (ctx.setTimeout). Prefer small
single-purpose plugins, prefer plain notification events over waterfall
events unless you intend to intercept, and stop what you no longer
events unless you intend to intercept, and unmount what you no longer
need. Report results briefly.
# The self-referential cordis toolset (loaded after the app so ctx.tools exists).
examples/cordis-agent/tests/cordis-tools.e2e.ts
+10 -10
View File
@@ -8,7 +8,7 @@ const testToolSignal = new AbortController().signal
/**
* With-key smoke for the self-referential cordis tools: a REAL model drives
* cordis_try/cordis_stop against the live context the test observes.
* cordis_mount/cordis_unmount against the live context the test observes.
* World-verified, not self-reported: the mounted listener must actually WRITE
* its tagged console line, the self-made tool must actually EXIST in the
* registry and appear as a real `tool/call`, the cross-mount service must
@@ -37,14 +37,14 @@ function resultText(result: { content: { type: string; text?: string }[] }): str
}
describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modifies its own runtime', () => {
it('tries a temporary status listener whose tagged output actually fires, then stops it', async () => {
it('mounts a temporary status listener whose tagged output actually fires, then unmounts it', async () => {
ctx = await cordisHarness()
const log = vi.spyOn(console, 'log').mockImplementation(() => {})
const agent = ctx.agentLoop.create(SessionId('cordis-e2e-listener'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
agent.followup([{
type: 'text',
text: 'Use cordis_try to create a temporary Plugin that listens to the \'agent/status\' '
text: 'Use cordis_mount to create a temporary Plugin that listens to the \'agent/status\' '
+ 'Cordis event and logs every change with console.log. Reply "running" once done.',
}])
await waitForIdle(ctx, agent)
@@ -58,7 +58,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif
})
expect(resultText(mid)).toContain('dyn-')
agent.followup([{ type: 'text', text: 'Now stop the temporary Plugin you just tried.' }])
agent.followup([{ type: 'text', text: 'Now unmount the temporary Plugin you just mounted.' }])
await waitForIdle(ctx, agent)
const after = await ctx.tools.execute({
@@ -74,7 +74,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif
agent.followup([{
type: 'text',
text: 'Give yourself a new tool: use cordis_try to create a temporary Plugin with '
text: 'Give yourself a new tool: use cordis_mount to create a temporary Plugin with '
+ 'inject ["tools"] that calls harness.registerTool(ctx, harness.defineTool({...})) '
+ 'to register a tool named reverse_text with one required string parameter '
+ '"text", returning the text reversed. Then CALL reverse_text with the '
@@ -88,7 +88,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif
expect(ctx.tools.get('reverse_text')).toBeDefined()
const events = [...agent.session.events]
const calls = events.filter(event => event.type === 'tool/call')
expect(calls.some(event => event.data.name === 'cordis_try')).toBe(true)
expect(calls.some(event => event.data.name === 'cordis_mount')).toBe(true)
const reverseCalls = calls.filter(event => event.data.name === 'reverse_text')
expect(reverseCalls.length).toBeGreaterThan(0)
const reverseResults = events
@@ -98,7 +98,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif
// On failure, surface what the model actually mounted and what the tool
// returned — an e2e failing at a distance is undebuggable without it.
const mountCode = calls
.filter(event => event.data.name === 'cordis_try')
.filter(event => event.data.name === 'cordis_mount')
.map(event => event.data.arguments)
.join('\n---\n')
const trace = events.map((event) => {
@@ -115,13 +115,13 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif
).toBe(true)
}, 120_000)
it('composes two temporary Plugins through provide/inject, and stopping the provider parks the consumer', async () => {
it('composes two temporary Plugins through provide/inject, and unmounting the provider parks the consumer', async () => {
ctx = await cordisHarness()
const agent = ctx.agentLoop.create(SessionId('cordis-e2e-compose'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
agent.followup([{
type: 'text',
text: 'Try TWO separate temporary Plugins with cordis_try. First a provider: apply calls '
text: 'Mount TWO separate temporary Plugins with cordis_mount. First a provider: apply calls '
+ 'ctx.provide(\'shouter\', { shout: (s) => s.toUpperCase() }). Second a consumer with '
+ 'inject ["shouter", "tools"] that registers (via harness.registerTool + harness.defineTool) '
+ 'a tool named shout_text with one required string parameter "text" whose execute returns '
@@ -144,7 +144,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif
.flatMap(event => event.data.content.filter(block => block.type === 'text').map(block => block.text))
expect(shoutResults.some(text => text.includes('QUIET'))).toBe(true)
agent.followup([{ type: 'text', text: 'Now stop ONLY the provider temporary Plugin (the one that provided shouter).' }])
agent.followup([{ type: 'text', text: 'Now unmount ONLY the provider temporary Plugin (the one that provided shouter).' }])
await waitForIdle(ctx, agent)
// The consumer must have been parked by cordis itself: service gone,
examples/cordis-agent/tests/harness.ts
+2 -2
View File
@@ -15,8 +15,8 @@ import * as ToolCordis from '@deepseek-ai/dsh-tool-cordis'
const PERSONA = 'You are cordis-agent, a self-referential harness demo. '
+ 'Your cordis_* tools operate on the live cordis runtime you run inside: '
+ 'cordis_inspect to look around, cordis_try to try a temporary Plugin, cordis_stop '
+ 'to stop one. Follow the tool descriptions exactly and report results briefly.'
+ 'cordis_inspect to look around, cordis_mount to mount a temporary Plugin, cordis_unmount '
+ 'to unmount one. Follow the tool descriptions exactly and report results briefly.'
export async function cordisHarness(): Promise<Context> {
const ctx = new Context()