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

Merge remote-tracking branch 'origin/master' into codex/invariant-service-seam

Browse Source 
# Conflicts:
#	.agents/notes/implemented/architecture/2026-07-19-package-owned-invariant-service.i18n.yaml
#	.agents/notes/implemented/architecture/2026-07-19-package-owned-invariant-service.md
#	.agents/notes/implemented/architecture/2026-07-19-package-owned-invariant-service.zh.md
#	.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md
#	.agents/notes/implemented/feature/2026-07-07-session-prefix.md
#	.agents/notes/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.i18n.yaml
#	docs/architecture.md
#	docs/config-catalog.md
#	docs/core-data-structures/session.md
#	docs/rfc/INDEX.md
#	packages/examples/agent-spine-demo/README.md
#	packages/examples/agent-spine-demo/src/index.ts
#	packages/examples/agent-spine-demo/tests/agent-core.spec.ts
#	packages/support/invariants/README.md
#	packages/support/invariants/src/index.ts
#	packages/support/invariants/tests/invariants.spec.ts
This commit is contained in:
Tianyi Cui
2026-07-20 00:25:31 +08:00
parent 2c7822ddee 023bed1a83
commit b46dfe08a2
676 changed files with 6946 additions and 2405 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
packages/examples/acp-demo/README.md
View File

@@ -1,6 +1,6 @@
# @deepseek-ai/dsh-acp-demo
The **ACP server app**: a Cordis app plugin that composes the default agent spine ([`@deepseek-ai/dsh-agent-spine-demo`](../../examples/agent-spine-demo/README.md)) with the front-door cluster an [Agent Client Protocol](../../ui/acp/README.md) server needs, and a `bin` that boots a leaf `cordis.yml` speaking ACP JSON-RPC on stdio.
The **ACP server app**: a Cordis app plugin that composes the default agent spine ([`@deepseek-ai/dsh-agent-spine-demo`](../agent-spine-demo/README.md)) with the front-door cluster an [Agent Client Protocol](../../ui/acp/README.md) server needs, and a `bin` that boots a leaf `cordis.yml` speaking ACP JSON-RPC on stdio.
It is the structured counterpart to [`@deepseek-ai/dsh-stdio-demo`](../stdio-demo/README.md): both consume the same spine, but this one bakes in the OPPOSITE front-door cluster.
@@ -55,6 +55,10 @@ All diagnostics go to **stderr** — stdout is the protocol.
Indirectly, through `dsh-agent-spine-demo` and `dsh-acp`, which compose each ACP agent's prompt, tools, and message history; this app bundle adds no model-bound content itself.
#### KV Cache effect
No direct invalidation; the named consumer owns any request-prefix changes.
## Known Limitations and Deferred Work
- **JSONL persistence is baked in** — config chooses its root but cannot select a different backend; that requires a sibling entry or differently composed app package.

4
packages/examples/acp-demo/src/index.ts
View File

@@ -53,7 +53,7 @@ export interface Config {
skills?: agentCore.SkillConfig
/** Model-facing bash tool config forwarded through agent-core. */
toolBash?: NonNullable<agentCore.Config['toolBash']>
/** Generic background-task control-tool config forwarded through agent-core. */
/** Generic background-task controls forwarded through agent-core; set false to omit their tool surface. */
toolTasks?: NonNullable<agentCore.Config['toolTasks']>
}
@@ -75,7 +75,7 @@ export const Config: z<Config> = z.object({
workspaceContext: z.union([z.const(false), workspaceContext.Config]).required(),
skills: agentCore.SkillConfigSchema,
toolBash: agentCore.ToolBashConfigSchema,
toolTasks: agentCore.ToolTasksConfigSchema,
toolTasks: z.union([z.const(false), agentCore.ToolTasksConfigSchema]),
})
/* jscpd:ignore-end */

12
packages/examples/agent-spine-demo/README.md
View File

@@ -39,9 +39,9 @@ The spine is everything COMMON to every front door. The swappable and front-door
- **the LLM adapter** — the bundle ships the abstract `llm` service; the leaf registers a concrete adapter on `ctx.llm` (`llm-deepseek`, `llm-pi-ai`, `llm-replay`).
- **the bash executor** — the bundle ships `tool-bash` (the consumer schema); the leaf provides `ctx.bash` (`bash-local` or a sandboxed impl).
- **non-local skill providers** — the bundle ships the skill registry, the local filesystem provider, and the `skill` tool; deployments can add other providers such as embedded or remote catalogs as siblings.
- **presentation + per-app infra** — the terminal (`dsh-tui` / `dsh-stdio`) or ACP front door and `hmr`. These form the coupled front-door cluster that the app packages ([`dsh-stdio-demo`](../../examples/stdio-demo/README.md), [`dsh-acp-demo`](../../examples/acp-demo/README.md)) bake in. `timer` is in the spine because it is common and stdout-silent; front doors own stdout and remain outside.
- **presentation + per-app infra** — the terminal (`dsh-tui` / `dsh-stdio`) or ACP front door and `hmr`. These form the coupled front-door cluster that the app packages ([`dsh-stdio-demo`](../stdio-demo/README.md), [`dsh-acp-demo`](../acp-demo/README.md)) bake in. `timer` is in the spine because it is common and stdout-silent; front doors own stdout and remain outside.
This is the [interface/implementation/consumer seam](../../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md) raised to the composition level: the bundle owns the shared spine, the leaf owns the backends, the app package owns the front door.
This is the [interface/implementation/consumer seam](../../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md) raised to the composition level: the bundle owns the shared spine, the leaf owns the backends, the app package owns the front door.
## Config
@@ -51,7 +51,7 @@ import type { Config } from '@deepseek-ai/dsh-agent-spine-demo'
// workspaceContext requires { maxBytes } or false; the other owner schemas supply defaults.
```
The bundle FORWARDS each field to the child that owns it: `agents` and `maxParallelToolCalls` to `agent-loop` (`agents` defaults to `[]`; the cap defaults there), so each app supplies its own pre-created agents — a stdio app pre-creates `main`, while the ACP app creates agents on demand at `session/new`; `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry for its presentation mode; `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer; the required `workspaceContext` choice to `dsh-workspace-context` (`{ maxBytes }` enables loading and `false` disables it); `invariants` to the invariant service; and `toolBash`/`toolTasks` to the two model-facing tool plugins the bundle owns. It resolves `dshHome` once through [`@deepseek-ai/dsh-home`](../../util/home/README.md) and forwards that absolute value to tool-bash's managed environment and local skill discovery. An absent top-level `dshHome` adopts `skills.local.dshHome`; supplying both with different resolved paths fails loudly. `toolBash.enableRunInBackground` controls only the bash producer, while `toolTasks` controls generic `task_output` wait bounds; independently loaded producers keep their own config. Workspace instructions register before the skill catalog so their session-prefix message renders first. App packages use `pickSpineConfig()` to copy only these bundle-owned fields.
The bundle FORWARDS each field to the child that owns it: `agents` and `maxParallelToolCalls` to `agent-loop` (`agents` defaults to `[]`; the cap defaults there), so each app supplies its own pre-created agents — a stdio app pre-creates `main`, while the ACP app creates agents on demand at `session/new`; `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry for its presentation mode; `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer; the required `workspaceContext` choice to `dsh-workspace-context` (`{ maxBytes }` enables loading and `false` disables it); `invariants` to the invariant service; and `toolBash`/`toolTasks` to the two model-facing tool plugins the bundle owns. Set `skills.enabled: false` to omit both the local provider and model-facing skill tool, and set `toolTasks: false` to retain the task service without exposing task-control tools. It resolves `dshHome` once through [`@deepseek-ai/dsh-home`](../../util/home/README.md) and forwards that absolute value to tool-bash's managed environment and enabled local skill discovery. An absent top-level `dshHome` adopts `skills.local.dshHome`; supplying both with different resolved paths fails loudly. `toolBash.enableRunInBackground` controls only the bash producer; independently loaded producers keep their own config. Workspace instructions register before the skill catalog so their session-prefix message renders first. App packages use `pickSpineConfig()` to copy only these bundle-owned fields.
For example, `{ invariants: { enabled: true, package_allowlist: ['^@deepseek-ai/dsh-'], package_blocklist: ['agent-loop$'] } }` keeps the package-owned companions mounted but suppresses the blocked owner. Blocklist matches override allowlist matches; see [`dsh-invariants`](../../support/invariants/README.md) for regex and lifecycle rules.
@@ -63,7 +63,11 @@ A YAML include can deduplicate config but cannot own a bin or provide front-door
Indirectly, through `dsh-system-prompt`, `dsh-tool-skill`, `dsh-tool-bash`, and `dsh-tools`, which this bundle mounts without adding model-bound wrapper content.
#### KV Cache effect
No direct invalidation; the named consumer owns any request-prefix changes.
## Known Limitations and Deferred Work
- **The spine set is fixed in code** — `apply()` mounts every child unconditionally (including `tool-bash`); no config excludes or replaces one, so swapping the loop or dropping a spine member means composing a different bundle.
- **Most of the spine set is fixed in code** — `apply()` always mounts the core services and `tool-bash`; config can omit the bundled skills and task-control tools, but swapping the loop or dropping another spine member means composing a different bundle.
- **The invariant seam and companions remain fixed members** — `invariants.enabled: false` or package filters suppress checks but do not remove the service or companion registrations; Session's always-on validation and freezing are separate.

20
packages/examples/agent-spine-demo/src/index.ts
View File

@@ -35,6 +35,8 @@ export const name = 'agent-spine-demo'
/** Skill bundle config forwarded to the registry, local provider, and model-facing consumer. */
export interface SkillConfig {
/** Mount the bundled local skill provider and model-facing skill tool (default true). */
enabled?: boolean
/** Registry-level discovery cache settings. */
registry?: SkillRegistryConfig
/** Local filesystem skill provider settings. */
@@ -78,14 +80,15 @@ export interface Config {
skills?: SkillConfig
/** Model-facing bash tool config, including this producer's background opt-in. */
toolBash?: toolBash.Config
/** Generic background-task control-tool wait bounds. */
toolTasks?: toolTasks.Config
/** Generic background-task controls; set false to keep the task service without model-facing task tools. */
toolTasks?: toolTasks.Config | false
/** Global enablement and package-name filters for invariant companions. */
invariants?: InvariantConfig
}
/** The skill config schema exported for app packages that forward `skills`. */
export const SkillConfigSchema: z<SkillConfig> = z.object({
enabled: z.boolean().default(true),
registry: SkillService.Config,
local: SkillLocal.Config,
tool: toolSkill.Config,
@@ -107,7 +110,7 @@ export const Config = z.intersect([
skills: SkillConfigSchema,
workspaceContext: z.union([z.const(false), workspaceContext.Config]).required(),
toolBash: ToolBashConfigSchema,
toolTasks: ToolTasksConfigSchema,
toolTasks: z.union([z.const(false), ToolTasksConfigSchema]),
invariants: InvariantService.Config,
}) as unknown as z<Pick<Config, 'tools' | 'dshHome' | 'skills' | 'workspaceContext' | 'toolBash' | 'toolTasks' | 'invariants'>>,
]) as unknown as z<Config>
@@ -159,8 +162,11 @@ export function apply(ctx: Context, config: Config): void {
...config.toolOrder !== undefined ? { toolOrder: config.toolOrder } : {},
})
ctx.plugin(ToolRegistry, config.tools ?? {})
ctx.plugin(SkillService, config.skills?.registry ?? {})
ctx.plugin(SkillLocal, Object.assign({}, config.skills?.local, { dshHome }))
const skillsEnabled = config.skills?.enabled ?? true
if (skillsEnabled) {
ctx.plugin(SkillService, config.skills?.registry ?? {})
ctx.plugin(SkillLocal, Object.assign({}, config.skills?.local, { dshHome }))
}
ctx.plugin(AgentRegistry)
ctx.plugin(TaskService)
ctx.plugin(InvariantService, config.invariants ?? {})
@@ -174,8 +180,8 @@ export function apply(ctx: Context, config: Config): void {
}
// Both plugins prepend session-prefix messages. Registration order is the
// rendered order, so workspace instructions must precede the skill catalog.
ctx.plugin(toolSkill, config.skills?.tool ?? {})
ctx.plugin(toolTasks, config.toolTasks ?? {})
if (skillsEnabled) ctx.plugin(toolSkill, config.skills?.tool ?? {})
if (config.toolTasks !== false) ctx.plugin(toolTasks, config.toolTasks ?? {})
ctx.plugin(AgentLoop, {
agents: config.agents ?? [],
...config.maxParallelToolCalls !== undefined ? { maxParallelToolCalls: config.maxParallelToolCalls } : {},

21
packages/examples/agent-spine-demo/tests/agent-core.spec.ts
View File

@@ -371,6 +371,21 @@ describe('dsh-agent-spine-demo bundle', () => {
await ctx.fiber.dispose()
})
it('can omit skills and model-facing task controls for a foreground-only deployment', async () => {
const ctx = await mount({
workspaceContext: false,
skills: { enabled: false },
toolBash: { enableRunInBackground: false },
toolTasks: false,
}, true)
expect(ctx.tools.schemas().map(tool => tool.name)).toEqual(['bash'])
expect(ctx.get('skills')).toBeUndefined()
expect(ctx.get('tasks')).toBeDefined()
await ctx.fiber.dispose()
})
it('picks shared spine config without leaking front-door fields', () => {
const appConfig = {
model: 'front-door-only',
@@ -379,9 +394,9 @@ describe('dsh-agent-spine-demo bundle', () => {
tools: { mode: 'native' as const },
dshHome: '/tmp/dsh-home',
workspaceContext: false as const,
skills: {},
skills: { enabled: false },
toolBash: { enableRunInBackground: false },
toolTasks: { waitTimeoutMs: 7, maxWaitTimeoutMs: 11 },
toolTasks: false as const,
invariants: { enabled: false },
}
@@ -391,7 +406,7 @@ describe('dsh-agent-spine-demo bundle', () => {
tools: appConfig.tools,
dshHome: appConfig.dshHome,
workspaceContext: false,
skills: {},
skills: appConfig.skills,
toolBash: appConfig.toolBash,
toolTasks: appConfig.toolTasks,
invariants: appConfig.invariants,

12
packages/examples/cli-demo/README.md
View File

@@ -55,9 +55,17 @@ The headless-agent leaf supplies local bash, filesystem, skill, subagent, workfl
### One-shot task turn
**What the model sees**: The positional task becomes one user message. Through `dsh-agent-spine-demo`, the top-level agent also receives configured workspace instructions and persona, the skill catalog, visible tool schemas, and retained tool results needed for later steps in the same turn.
#### What the model sees
**Token effect**: The task, prompt sections, tool schemas, assistant output, and tool results consume tokens on each model step. JSON event streaming and final rendering add no model tokens; delegated child work has its own model usage and is not included in the parent result's `usage` total.
The positional task becomes one user message. Through `dsh-agent-spine-demo`, the top-level agent also receives configured workspace instructions and persona, the skill catalog, visible tool schemas, and retained tool results needed for later steps in the same turn.
#### Token effect
The task, prompt sections, tool schemas, assistant output, and tool results consume tokens on each model step. JSON event streaming and final rendering add no model tokens; delegated child work has its own model usage and is not included in the parent result's `usage` total.
#### KV Cache effect
Tool-round history is append-only while the one-shot agent's prompt, schemas, model route, and session prefix remain fixed. Changing that composition establishes a different request prefix; JSON output mode has no cache effect.
## Known Limitations and Deferred Work

2
packages/examples/cli-demo/src/index.ts
View File

@@ -61,7 +61,7 @@ export const Config: z<Config> = z.object({
toolOrder: z.array(z.string()).default(undefined as unknown as string[]),
tools: ToolRegistry.Config,
toolBash: agentCore.ToolBashConfigSchema,
toolTasks: agentCore.ToolTasksConfigSchema,
toolTasks: z.union([z.const(false), agentCore.ToolTasksConfigSchema]),
workspaceContext: z.union([z.const(false), workspaceContext.Config]).required(),
})
/* jscpd:ignore-end */

15
packages/examples/cli-demo/tests/cli-demo.spec.ts
View File

@@ -146,6 +146,21 @@ describe('dsh-cli-demo app composition', () => {
expect(wait).toHaveBeenCalledWith(id, 7, undefined, undefined)
})
it('accepts false to keep task services without model-facing task controls', async () => {
const ctx = await mount({
provider: 'mock',
model: 'mock',
skills: { enabled: false },
toolTasks: false,
workspaceContext: false,
})
expect(ctx.get('tasks')).toBeDefined()
expect(ctx.get('tools')?.get('task_output')).toBeUndefined()
expect(ctx.get('tools')?.get('task_list')).toBeUndefined()
expect(ctx.get('tools')?.get('task_kill')).toBeUndefined()
})
it('exposes the Loader-safe namespace plugin shape and schema', () => {
expect(cliDemo.name).toBe('cli-demo')
expect(cliDemo.Config).toBeDefined()

8
packages/examples/jsonrpc-demo/README.md
View File

@@ -1,6 +1,6 @@
# @deepseek-ai/dsh-jsonrpc-demo
Bin-only app that boots an external `cordis.yml`; its [`jsonrpc`](../../ui/jsonrpc/README.md) entry serves SDK clients over newline-delimited stdio. The config composes the spine, backends, and serving plugin. `lib/bin.js` is also the [single-executable runtime](../../../docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md) entry.
Bin-only app that boots an external `cordis.yml`; its [`jsonrpc`](../../ui/jsonrpc/README.md) entry serves SDK clients over newline-delimited stdio. The config composes the spine, backends, and serving plugin. `lib/bin.js` is also the [single-executable runtime](../../../.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md) entry.
## Config discovery
@@ -10,7 +10,7 @@ A config without `dsh-jsonrpc` is valid and serves nothing; the bin does not des
## Exit lifecycle
stdin EOF and `SIGTERM` dispose the root to quiescence and exit 0; `SIGINT` exits 130 after the same disposal. EOF may cut off an in-flight turn as documented in the [distribution RFC](../../../docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md). The `jsonrpc` plugin owns response-before-exit protocol shutdown; both paths are idempotent and safe to race.
stdin EOF and `SIGTERM` dispose the root to quiescence and exit 0; `SIGINT` exits 130 after the same disposal. EOF may cut off an in-flight turn as documented in the [distribution Agent Note](../../../.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md). The `jsonrpc` plugin owns response-before-exit protocol shutdown; both paths are idempotent and safe to race.
## stdout is the protocol
@@ -20,6 +20,10 @@ stdout carries only JSON-RPC frames. The bin and boot guards diagnose on stderr,
Indirectly, through the plugins loaded from the external `cordis.yml`, which own every model-bound prompt, schema, message, and result; this bin adds none of its own.
#### KV Cache effect
No direct invalidation; the named consumer owns any request-prefix changes.
## Known Limitations and Deferred Work
- **The bin cannot prove that the config serves JSON-RPC** — a valid config with no `dsh-jsonrpc` entry boots successfully and serves nothing.

26
packages/examples/stdio-demo/README.md
View File

@@ -1,6 +1,6 @@
# @deepseek-ai/dsh-stdio-demo
The **terminal chat app**: a Cordis app plugin that composes the default agent spine ([`@deepseek-ai/dsh-agent-spine-demo`](../../examples/agent-spine-demo/README.md)) with JSONL persistence, human interaction, a pre-created `main` agent, and a TTY-selected pi-tui/readline front door. Its `bin` boots a leaf `cordis.yml`.
The **terminal chat app**: a Cordis app plugin that composes the default agent spine ([`@deepseek-ai/dsh-agent-spine-demo`](../agent-spine-demo/README.md)) with JSONL persistence, human interaction, a pre-created `main` agent, and a TTY-selected pi-tui/readline front door. Its `bin` boots a leaf `cordis.yml`.
It is the terminal counterpart to [`@deepseek-ai/dsh-acp-demo`](../acp-demo/README.md): both consume the same spine, while ACP reserves stdout for JSON-RPC and creates sessions from the client.
@@ -79,15 +79,31 @@ Swap `llm-deepseek` for a `mock-llm` leaf plugin and you have the echo demo —
### Composed terminal agent request
**What the model sees**: Through `dsh-agent-spine-demo`, the `main` agent receives the harness identity, configured persona, skill catalog, and visible tools; this app also composes the generated [`ask_user_question` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tool-ask-user). Each terminal submission becomes a user message; submissions made while the agent runs steer the active turn.
#### What the model sees
**Token effect**: Child prompt and schema costs repeat per request; user input and tool history grow until compaction. Terminal banners, logger output, cards, and rendered transcripts add zero model tokens.
Through `dsh-agent-spine-demo`, the `main` agent receives the harness identity, configured persona, skill catalog, and visible tools; this app also composes the generated [`ask_user_question` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tool-ask-user). Each terminal submission becomes a user message; submissions made while the agent runs steer the active turn.
#### Token effect
Child prompt and schema costs repeat per request; user input and tool history grow until compaction. Terminal banners, logger output, cards, and rendered transcripts add zero model tokens.
#### KV Cache effect
User and tool history is append-only while the composed prompt, schemas, child model route, and session prefix remain fixed. A composition change or compaction may invalidate reuse from its first changed token; terminal rendering has no cache effect.
### Human-answer result
**What the model sees**: Through `dsh-tool-ask-user`, successful terminal answers use that package's exact compact JSON shape. Interruption becomes exactly `Error: ask_user_question was interrupted before the user answered`; a closed stdin becomes `Error: ask_user_question cannot be answered because stdin is closed`.
#### What the model sees
**Token effect**: Only a completed or failed tool call adds retained result tokens; prompts printed while waiting are terminal-only.
Through `dsh-tool-ask-user`, successful terminal answers use that package's exact compact JSON shape. Interruption becomes exactly `Error: ask_user_question was interrupted before the user answered`; a closed stdin becomes `Error: ask_user_question cannot be answered because stdin is closed`.
#### Token effect
Only a completed or failed tool call adds retained result tokens; prompts printed while waiting are terminal-only.
#### KV Cache effect
Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries.
## Known Limitations and Deferred Work

4
packages/examples/stdio-demo/src/index.ts
View File

@@ -97,7 +97,7 @@ export interface Config {
skills?: agentCore.SkillConfig
/** Model-facing bash tool config forwarded through agent-core. */
toolBash?: NonNullable<agentCore.Config['toolBash']>
/** Generic background-task control-tool config forwarded through agent-core. */
/** Generic background-task controls forwarded through agent-core; set false to omit their tool surface. */
toolTasks?: NonNullable<agentCore.Config['toolTasks']>
/**
* If set, the pre-created agent RESUMES this persisted session id instead of
@@ -125,7 +125,7 @@ export const Config: z<Config> = z.object({
ui: UiConfigSchema,
skills: agentCore.SkillConfigSchema,
toolBash: agentCore.ToolBashConfigSchema,
toolTasks: agentCore.ToolTasksConfigSchema,
toolTasks: z.union([z.const(false), agentCore.ToolTasksConfigSchema]),
resumeSessionId: z.string(),
workspaceContext: z.union([z.const(false), workspaceContext.Config]).required(),
})