Merge master at 35eeb4a112

This commit is contained in:
pku-xht
2026-08-10 20:25:58 +08:00
879 changed files with 11605 additions and 2942 deletions

View File

@@ -46,6 +46,8 @@ flowchart LR
cfg --> plugin_dsh_base_llm_pi_ai
plugin_dsh_base_session_persistence_jsonl["session-persistence-jsonl<br/>@deepseek-ai/dsh-session-persistence-jsonl"]
cfg --> plugin_dsh_base_session_persistence_jsonl
plugin_dsh_base_attachment_local["attachment-local<br/>@deepseek-ai/dsh-attachment-local"]
cfg --> plugin_dsh_base_attachment_local
plugin_dsh_base_session_query_sqlite["session-query-sqlite<br/>@deepseek-ai/dsh-session-query-sqlite"]
cfg --> plugin_dsh_base_session_query_sqlite
plugin_dsh_base_session_projection["session-projection<br/>@deepseek-ai/dsh-session-projection"]
@@ -187,6 +189,7 @@ flowchart LR
| `credentials` | `@deepseek-ai/dsh-credentials-local` |
| `llm-pi-ai` | `@deepseek-ai/dsh-llm-pi-ai` |
| `session-persistence-jsonl` | `@deepseek-ai/dsh-session-persistence-jsonl` |
| `attachment-local` | `@deepseek-ai/dsh-attachment-local` |
| `session-query-sqlite` | `@deepseek-ai/dsh-session-query-sqlite` |
| `session-projection` | `@deepseek-ai/dsh-session-projection` |
| `telemetry-otel` | `@deepseek-ai/dsh-session-telemetry-otel` |

View File

@@ -70,17 +70,15 @@
# ── background tasks ────────────────────────────────────────────────────────
- id: tasks
name: cordis:group
group: true
isolate:
tasks: true
config:
- id: tasks-local
name: '@deepseek-ai/dsh-tasks-local'
- id: tool-tasks
name: '@deepseek-ai/dsh-tool-tasks'
# Only the model-facing controls. The task REGISTRY stays on the host plane:
# its producers sit outside any realm this file could put it in — `tool-bash`
# above resolves it with `ctx.get`, and an entry-local realm here is invisible
# to every sibling row, so `run_in_background` would answer "background tasks
# unavailable" while these controls sat in the catalog. The registry is keyed by
# owning agent anyway, so one host instance serves every session. What a preset
# chooses is whether its agent can collect and stop background work at all.
- id: tool-tasks
name: '@deepseek-ai/dsh-tool-tasks'
# ── skills ──────────────────────────────────────────────────────────────────
@@ -124,7 +122,7 @@
Explore first. Use non-mutating reads, searches, static analysis, and checks to ground the plan in the actual repository. Do not edit or write files, change configuration, run formatters or code generation that rewrites tracked files, commit, or otherwise carry out the plan. Prefer existing functions and patterns over new machinery.
The tool catalog stays the same across modes for request-cache stability. These plan-mode rules override any later tool description or guidance that suggests using mutation tools; those tools remain listed only to keep the request shape stable. Do not use todo_write to track this planning phase: it tracks implementation after an approved plan, while the plan itself belongs in exit_plan_mode.
The tool catalog stays the same across modes for request-cache stability. These plan-mode rules override any later tool description or guidance that suggests using mutation tools; those tools remain listed to keep the tool catalog unchanged. Do not use todo_write to track this planning phase: it tracks implementation after an approved plan, while the plan itself belongs in exit_plan_mode.
Resolve discoverable facts by inspection. Use ask_user_question only for user-owned choices or material ambiguity that inspection cannot answer. Do not ask the user where code lives or how current behavior works when you can find out.

View File

@@ -64,17 +64,15 @@
# ── background tasks ────────────────────────────────────────────────────────
- id: tasks
name: cordis:group
group: true
isolate:
tasks: true
config:
- id: tasks-local
name: '@deepseek-ai/dsh-tasks-local'
- id: tool-tasks
name: '@deepseek-ai/dsh-tool-tasks'
# Only the model-facing controls. The task REGISTRY stays on the host plane:
# its producers sit outside any realm this file could put it in — `tool-bash`
# above resolves it with `ctx.get`, and an entry-local realm here is invisible
# to every sibling row, so `run_in_background` would answer "background tasks
# unavailable" while these controls sat in the catalog. The registry is keyed by
# owning agent anyway, so one host instance serves every session. What a preset
# chooses is whether its agent can collect and stop background work at all.
- id: tool-tasks
name: '@deepseek-ai/dsh-tool-tasks'
# ── goals ───────────────────────────────────────────────────────────────────
@@ -105,7 +103,7 @@
Explore first. Use non-mutating reads, searches, static analysis, and checks to ground the plan in the actual repository. Do not edit or write files, change configuration, run formatters or code generation that rewrites tracked files, commit, or otherwise carry out the plan. Prefer existing functions and patterns over new machinery.
The tool catalog stays the same across modes for request-cache stability. These plan-mode rules override any later tool description or guidance that suggests using mutation tools; those tools remain listed only to keep the request shape stable. Do not use todo_write to track this planning phase: it tracks implementation after an approved plan, while the plan itself belongs in exit_plan_mode.
The tool catalog stays the same across modes for request-cache stability. These plan-mode rules override any later tool description or guidance that suggests using mutation tools; those tools remain listed to keep the tool catalog unchanged. Do not use todo_write to track this planning phase: it tracks implementation after an approved plan, while the plan itself belongs in exit_plan_mode.
Resolve discoverable facts by inspection. Use ask_user_question only for user-owned choices or material ambiguity that inspection cannot answer. Do not ask the user where code lives or how current behavior works when you can find out.

View File

@@ -81,13 +81,13 @@ When a preset genuinely owns a service, wrap the provider **and every consumer t
A consumer left outside the group resolves the host's registry, which the preset did not populate, and then contributes nothing. That is the quietest failure here: the mount succeeds and a tool is simply missing.
Registry-shaped host capabilities need no realm at all: the host `tools` and `skills` registries are layered per scope, so rows like `skill-local` and `tool-skill` sit loose in the preset and their registrations file into this preset's layer automatically — the agent's catalog merges them with whatever the deployment registered globally.
Host capabilities exposed through registries need no realm: the host `tools` and `skills` registries are layered per scope, so rows like `skill-local` and `tool-skill` sit loose in the preset and their registrations file into this preset's layer automatically — the agent's catalog merges them with whatever the deployment registered globally.
## Verifying a change
Read the live runtime with `cordis_inspect` — it reports the services, the plugin fibers, and the registered tools as they actually are, which is the only reliable check that a row did what its name suggests. Note it shows THIS session's composition: a preset you just wrote is not mounted anywhere until a session starts on it.
To check a preset you authored, re-read the files you wrote and walk the shape: a top-level YAML list, every row a map with a `name`, every group carrying its own list, service-publishing rows behind an `isolate` realm. The settings page's preset roster runs the same shape check and marks an unloadable preset broken in red — point the user there, and ask them to start a session on the new preset to confirm the tool list; you cannot start one yourself.
To check a preset you authored, re-read the files and validate these fields: the top level is a YAML list, every row is a map with a `name`, every group carries its own list, and service-publishing rows sit behind an `isolate` realm. The settings page's preset roster validates the same fields and marks an unloadable preset broken in red — point the user there, and ask them to start a session on the new preset to confirm the tool list; you cannot start one yourself.
`cordis_mount` evaluates JavaScript against the live runtime and disappears on restart. It is for probing, not for shipping a capability: a capability belongs in a composition file.

View File

@@ -22,8 +22,16 @@
# never reached the model's shell at all. `tool-bash` consumes the host registry
# from here; the executor behind it (`bash-sandbox`) is host-plane too, where the
# sandbox policy owns it.
#
# `run_in_background` is off because this preset mounts no `tool-tasks`. The
# host registry already refuses a start for an owner no attached control
# surface serves, so this is not the safety boundary — it is the model-facing
# one: an agent that could never collect a task should not be offered the
# parameter at all, and disabling it drops the parameter from the schema.
- id: tool-bash
name: '@deepseek-ai/dsh-tool-bash'
config:
enableRunInBackground: false
- id: tool-str-replace-editor
name: '@deepseek-ai/dsh-tool-str-replace-editor'

View File

@@ -63,17 +63,15 @@
# ── background tasks ────────────────────────────────────────────────────────
- id: tasks
name: cordis:group
group: true
isolate:
tasks: true
config:
- id: tasks-local
name: '@deepseek-ai/dsh-tasks-local'
- id: tool-tasks
name: '@deepseek-ai/dsh-tool-tasks'
# Only the model-facing controls. The task REGISTRY stays on the host plane:
# its producers sit outside any realm this file could put it in — `tool-bash`
# above resolves it with `ctx.get`, and an entry-local realm here is invisible
# to every sibling row, so `run_in_background` would answer "background tasks
# unavailable" while these controls sat in the catalog. The registry is keyed by
# owning agent anyway, so one host instance serves every session. What a preset
# chooses is whether its agent can collect and stop background work at all.
- id: tool-tasks
name: '@deepseek-ai/dsh-tool-tasks'
# ── skills ──────────────────────────────────────────────────────────────────
@@ -117,7 +115,7 @@
Explore first. Use non-mutating reads, searches, static analysis, and checks to ground the plan in the actual repository. Do not edit or write files, change configuration, run formatters or code generation that rewrites tracked files, commit, or otherwise carry out the plan. Prefer existing functions and patterns over new machinery.
The tool catalog stays the same across modes for request-cache stability. These plan-mode rules override any later tool description or guidance that suggests using mutation tools; those tools remain listed only to keep the request shape stable. Do not use todo_write to track this planning phase: it tracks implementation after an approved plan, while the plan itself belongs in exit_plan_mode.
The tool catalog stays the same across modes for request-cache stability. These plan-mode rules override any later tool description or guidance that suggests using mutation tools; those tools remain listed to keep the tool catalog unchanged. Do not use todo_write to track this planning phase: it tracks implementation after an approved plan, while the plan itself belongs in exit_plan_mode.
Resolve discoverable facts by inspection. Use ask_user_question only for user-owned choices or material ambiguity that inspection cannot answer. Do not ask the user where code lives or how current behavior works when you can find out.

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 apps/cli/reference/README.md
README.md: bb3e1d77f00e03f6a21f4da3c04994f208e84293
README.zh.md: 3802f940ef6663ec215cf09293a9edda5ea4c512
README.md: 0b5faf8993cd8065fffcfec5f240b0084508db91
README.zh.md: b9c48c16dd4be186266d30a438329463c31aca70

View File

@@ -43,7 +43,7 @@ Git-hosted plugins that ship sources build during install through their `prepare
## Web alias
`dsh web` is a hardcoded alias for `--profile web` that additionally accepts the Web flag family. `--host`, `--port`, `--workspace-root`, and repeatable `--trusted-host` values become patches over the composed rows; their owning plugin schemas validate them at boot. `--dev` switches the web-runtime row to development mode and inserts the client-plugin HMR receiver; it expects a separate `pnpm run dev:web` watcher for no-refresh client bundle updates.
`dsh web` is a hardcoded alias for `--profile web` that additionally accepts the Web flag family. `--host`, `--port`, and repeatable `--trusted-host` values become patches over the composed rows; their owning plugin schemas validate them at boot. `--dev` switches the web-runtime row to development mode and inserts the client-plugin HMR receiver; it expects a separate `pnpm run dev:web` watcher for no-refresh client bundle updates.
```sh
dsh web
@@ -61,7 +61,7 @@ New sessions default to the `workspace-write` permission preset. Bash and filesy
`DSH_TOOLS_MODE` selects `native`, `code`, or `both` for the process; another value fails at boot. [`config/core-web.cordis.yml`](../config/core-web.cordis.yml) is an optional RL-compatible `--patch` overlay that pins native mode, renders only `DSH_SYSTEM_PROMPT` or `You are a helpful software engineer assistant.` as the system prompt, disables Workspace instructions and every Web runtime prompt contribution, and exposes only persistent `bash` and `str_replace_editor` while retaining the shipped host, browser, workspace, persistence, and permission composition.
`DSH_SYSTEM_PROMPT` is passed as the system-prompt [`persona`](../../../packages/core/system-prompt/README.md#config): complete `{{…}}` groups use that contract's strict variable interpolation and have no literal-brace escape; any set value, including an empty string, is authoritative and an empty value therefore removes the system prompt, while only an unset variable selects the fallback.
`DSH_SYSTEM_PROMPT` is passed as the system-prompt [`persona`](../../../packages/core/system-prompt/README.md#config): complete `{{…}}` groups use that contract's strict variable interpolation rules and have no literal-brace escape; any set value, including an empty string, is authoritative and an empty value therefore removes the system prompt, while only an unset variable selects the fallback.
## Shared deployment behavior

View File

@@ -43,7 +43,7 @@ Git 托管、随附源码的插件在安装期间通过其 `prepare` 脚本构
## Web 别名
`dsh web``--profile web` 的硬编码别名,并额外接受 Web flag 系列。`--host``--port``--workspace-root` 和可重复的 `--trusted-host` 值会成为作用在组合行之上的 patch负责这些值的插件 schema 会在启动时验证它们。`--dev` 把 web-runtime 行切换到开发模式并插入客户端插件 HMR热模块替换接收器若要无刷新更新客户端 bundle还需单独运行 `pnpm run dev:web` watcher。
`dsh web``--profile web` 的硬编码别名,并额外接受 Web flag 系列。`--host``--port` 和可重复的 `--trusted-host` 值会成为作用在组合行之上的 patch负责这些值的插件 schema 会在启动时验证它们。`--dev` 把 web-runtime 行切换到开发模式并插入客户端插件 HMR热模块替换接收器若要无刷新更新客户端 bundle还需单独运行 `pnpm run dev:web` watcher。
```sh
dsh web

View File

@@ -48,7 +48,6 @@ interface WebInvocation {
host?: string
port?: number
dev: boolean
workspaceRoot?: string
/** Extra authorities for the /api browser-trust fence. */
trustedHosts?: string[]
}
@@ -70,7 +69,6 @@ interface WebOptions {
host?: string
port?: string
dev?: boolean
workspaceRoot?: string
trustedHost?: string[]
dumpConfig?: boolean
dumpDefaultConfig?: boolean
@@ -140,7 +138,7 @@ Examples:
resolved = { mode: 'profile', profile, patches }
})
/** Reject parent options that crossed a subcommand boundary. */
/** Reject parent options supplied before a subcommand. */
const rejectParentOptions = (command: string): void => {
const parent = program.opts<{
profile?: string
@@ -176,7 +174,6 @@ Examples:
.option('--host <host>', 'bind host; pass 0.0.0.0 to reach it from another machine')
.option('--port <port>', 'listen port; pass 0 to let the OS pick a free one')
.option('--dev', 'mount the client-plugin HMR receiver (run pnpm run dev:web separately to rebuild bundles)')
.option('--workspace-root <path>', 'parent directory for workspaces created from the browser UI')
.option('--trusted-host <authority...>', 'extra authority the /api browser-trust fence accepts (host or host:port; repeatable)')
.option('--dump-config', 'print the composed web-profile tree (with the user layer and any --patch) and exit')
.option('--dump-default-config', 'print the web profile\'s bundle layers (no user layer) and exit')
@@ -196,8 +193,8 @@ Examples:
// dropping them would print a tree that differs from the same
// invocation's boot.
if (options.host !== undefined || options.port !== undefined || options.dev === true
|| options.workspaceRoot !== undefined || options.trustedHost !== undefined) {
program.error('error: config dumps take no web flags (--host/--port/--dev/--workspace-root/--trusted-host)')
|| options.trustedHost !== undefined) {
program.error('error: config dumps take no web flags (--host/--port/--dev/--trusted-host)')
}
resolved = { mode: 'dump-config', profile: 'web', defaultOnly, patches }
return
@@ -211,7 +208,6 @@ Examples:
...options.host !== undefined && { host: options.host },
...options.port !== undefined && { port: Number(options.port) },
dev: options.dev === true,
...options.workspaceRoot !== undefined && { workspaceRoot: options.workspaceRoot },
...options.trustedHost !== undefined && { trustedHosts: options.trustedHost },
}
})

View File

@@ -14,8 +14,8 @@ export interface ProcessShutdown {
/**
* Create one process-exit controller around an application disposer.
* @param dispose - Whole-application teardown that resolves at quiescence.
* @param forceExit - Forced process exit boundary, replaceable by tests.
* @param complete - Natural process completion boundary, replaceable by tests.
* @param forceExit - Function that exits the process immediately, replaceable by tests.
* @param complete - Function that records the natural completion code, replaceable by tests.
* @param timeoutMs - Grace before forced exit, replaceable by tests.
* @returns A controller whose normal calls coalesce and whose repeated signal call escalates.
*/

View File

@@ -1,7 +1,7 @@
/**
* `dsh web` — the browser-surface alias over the profile boot: `--profile web`
* plus the Web flag family (`--host/--port/--dev/--workspace-root/
* --trusted-host`), each flag becoming a patch over the composed profile
* plus the Web flag family (`--host/--port/--dev/--trusted-host`), each flag
* becoming a patch over the composed profile
* tree. All web runtime glue (dist serving, prompt section, URL line) lives
* in the `@deepseek-ai/dsh-web-app` bundle; this launcher only derives
* flag patches and the LAN-trust snapshot.
@@ -59,7 +59,6 @@ export interface WebFlags {
host?: string
port?: number
dev: boolean
workspaceRoot?: string
trustedHosts?: string[]
}
@@ -83,7 +82,6 @@ function deriveWebFlagPatches(
}
if (flags.host !== undefined) put('webserver', 'host', flags.host)
if (flags.port !== undefined) put('webserver', 'port', flags.port)
if (flags.workspaceRoot !== undefined) put('api-gateway', 'workspaceRoot', flags.workspaceRoot)
const composedHost = (rows.get('webserver')?.config as { host?: string } | undefined)?.host
const { lanAddresses, trustedHosts } = resolveLanTrust(flags.host ?? composedHost, flags.trustedHosts ?? [])
if (trustedHosts.length > 0) {
@@ -122,8 +120,8 @@ export function webSurfaceContextEnabled(rows: ProfileRows): boolean {
}
/**
* Serve the browser UI from the web profile. Host/port/workspace-root flags
* are passed through only when given (absent, the composed profile values
* Serve the browser UI from the web profile. Host/port flags are passed
* through only when given (absent, the composed profile values
* stand); `web-runtime.mode` and `lanAddresses` are launcher-derived on
* every boot. The URL line is printed by the web-app bundle's runtime row
* after Loader settlement.

View File

@@ -33,8 +33,8 @@ describe('parseDshArgs', () => {
.toEqual({ mode: 'run', profile: 'headless', patches: [], task: '--profile is task text' })
expect(parse(['web'])).toEqual({ mode: 'web', dev: false, patches: [] })
expect(parse(['web', '--patch', 'web.yml'])).toEqual({ mode: 'web', dev: false, patches: ['web.yml'] })
expect(parse(['web', '--host', '0.0.0.0', '--port', '8080', '--dev', '--workspace-root', '/w']))
.toEqual({ mode: 'web', host: '0.0.0.0', port: 8080, dev: true, workspaceRoot: '/w', patches: [] })
expect(parse(['web', '--host', '0.0.0.0', '--port', '8080', '--dev']))
.toEqual({ mode: 'web', host: '0.0.0.0', port: 8080, dev: true, patches: [] })
expect(parse(['web', '--trusted-host', 'harness.internal:3080', 'lab.internal', '--trusted-host', '10.0.0.9']))
.toEqual({ mode: 'web', dev: false, patches: [], trustedHosts: ['harness.internal:3080', 'lab.internal', '10.0.0.9'] })
})

View File

@@ -1,6 +1,6 @@
/**
* The third-party memory examples stay config-only. This suite parses every
* checked-in overlay, verifies its pin/transport/secret boundary, then replaces
* checked-in overlay, verifies its package pin, transport, and secret handling, then replaces
* only the upstream endpoint with the package-owned keyless MCP fixture and
* proves the real Cordis Loader discovers a tool through the generic bridge.
*/
@@ -81,7 +81,7 @@ async function waitForTool(ctx: Context, name: string): Promise<void> {
}
describe('third-party memory MCP example overlays', () => {
it.each(examples)('parses $file with the documented generic boundary', (contract) => {
it.each(examples)('parses $file with the documented generic plugin fields', (contract) => {
const file = resolve(exampleDir, contract.file)
const source = readFileSync(file, 'utf8')
const row = insertedRow(loadOverlayPatches('memory-mcp-config-test', file))

View File

@@ -5,7 +5,7 @@ import { describe, expect, it } from 'vitest'
/**
* Keyless smoke for the SOURCE `dsh` launcher: run `apps/cli/src/bin.ts`
* with the exact production launch vector (`node --import tsx/esm`, the same
* shape as `bin/dsh` and the root `dsh`/`demo:web` scripts) and assert the
* executable and arguments as `bin/dsh` and the root `dsh`/`demo:web` scripts) and assert the
* required-config diagnostic. The Node compatibility matrix runs this
* WHOLE file, so a Node release changing module hooks or TypeScript handling
* breaks this gate instead of every developer's `pnpm dsh`; the built-bin