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

Merge remote-tracking branch 'origin/master' into worktree/minimal-no-runtime-context

Browse Source 
# Conflicts:
#	packages/core/system-prompt/README.i18n.yaml
#	packages/core/system-prompt/README.md
#	packages/core/system-prompt/README.zh.md
#	packages/examples/agent-spine-demo/README.i18n.yaml
#	packages/examples/agent-spine-demo/README.md
#	packages/examples/agent-spine-demo/README.zh.md
#	packages/self-modification/tool-cordis/src/api-catalog.ts
This commit is contained in:
Yichen Jiang
2026-08-13 10:24:29 +08:00
parent ece8645080 3083461524
commit 3bcc1a0bf7
3527 changed files with 51881 additions and 31023 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/core/agent-default-model/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 packages/core/agent-default-model/README.md
README.md: e86be7c37a1f994ca52f018144ef6a2409bd1eea
README.zh.md: 00250c28ef8c03d4b33fe1c1bfca138a022f6638
README.md: 4b9e06c1f68150633afa8aad752845f6d96dda85
README.zh.md: f3b8acb1a64e9a80aece87ac71f49a963d573352
packages/core/agent-default-model/README.md
+1 -1
View File
@@ -2,7 +2,7 @@
English | [中文](README.zh.md)
The deployment default used when an entry point creates an Agent that has no session-local model selection. `AgentDefaultModelService` provides `ctx.agentDefaultModel`; direct entry points such as `dsh --profile headless` and Host-backed entry points such as ApiProxy read the same service instead of owning parallel provider/model defaults.
The deployment default used when an entry point creates an Agent that has no session-local model selection. `AgentDefaultModelConfig` provides `ctx.agentDefaultModel`; direct entry points such as `dsh --profile headless` and Host-backed entry points such as ApiProxy read the same service instead of owning parallel provider/model defaults.
The plugin config requires `{ provider, model }`. That composition entry is the base of the `agent-default-model` Settings section; a mounted settings provider layers the user's choice over it and changes are visible on the next `currentSelection()` read. `reasoningEffort` belongs to the Settings section but deliberately not to plugin config: a complete saved selection can clear an effort when the next selected model has none, while a composition value would be inherited again.
packages/core/agent-default-model/README.zh.md
+1 -1
View File
@@ -2,7 +2,7 @@
[English](README.md) | 中文
该部署默认值供入口在创建尚无会话级模型选择的 Agent 时使用。`AgentDefaultModelService` 提供 `ctx.agentDefaultModel`；`dsh --profile headless` 这类直接入口与 ApiProxy 这类由 Host 支撑的入口读取同一服务，而不是分别持有平行的提供方／模型默认值。
该部署默认值供入口在创建尚无会话级模型选择的 Agent 时使用。`AgentDefaultModelConfig` 提供 `ctx.agentDefaultModel`；`dsh --profile headless` 这类直接入口与 ApiProxy 这类由 Host 支撑的入口读取同一服务，而不是分别持有平行的提供方／模型默认值。
插件配置必须提供 `{ provider, model }`。该组合配置项构成 Settings 中 `agent-default-model` 分节的基础层；挂载的设置提供方在其上叠加用户选择，更改会在下一次调用 `currentSelection()` 时可见。`reasoningEffort` 属于该 Settings 分节，但特意不属于插件配置：完整保存的选择必须能在下一个选定模型没有推理（reasoning）强度时清除旧值，而组合配置值会再次被继承。
packages/core/agent-default-model/package.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"name": "@deepseek-ai/dsh-agent-default-model",
"description": "Default model selection shared by Agent entry points",
"version": "0.0.1-rc.2",
"version": "0.0.1-rc.5",
"publishConfig": {
"access": "restricted"
},
packages/core/agent-default-model/src/index.ts
+3 -3
View File
@@ -13,7 +13,7 @@ import { installSettingsSection, settingsNamespace } from '@deepseek-ai/dsh-sett
declare module '@deepseek-ai/cordis' {
interface Context {
/** Default model selection for Agents created without an explicit model. */
agentDefaultModel: AgentDefaultModelService
agentDefaultModel: AgentDefaultModelConfig
}
}
@@ -61,7 +61,7 @@ function selection(settings: AgentDefaultModelSettings): ModelSelection {
* The composition entry remains usable without a settings provider; when one
* is mounted, its user layer is read live.
*/
export class AgentDefaultModelService extends Service {
export class AgentDefaultModelConfig extends Service {
static Config: z<Config> = z.object({
provider: z.string().required(),
model: z.string().required(),
@@ -104,4 +104,4 @@ export class AgentDefaultModelService extends Service {
}
}
export default AgentDefaultModelService
export default AgentDefaultModelConfig
packages/core/agent-default-model/tests/agent-default-model.spec.ts
+7 -7
View File
@@ -2,13 +2,13 @@
import { describe, expect, it } from 'vitest'
import { Context } from '@deepseek-ai/cordis'
import AgentDefaultModelService, { AGENT_DEFAULT_MODEL_SETTINGS_NAMESPACE } from '../src/index.ts'
import { Settings } from '@deepseek-ai/dsh-settings'
import AgentDefaultModelConfig, { AGENT_DEFAULT_MODEL_SETTINGS_NAMESPACE } from '../src/index.ts'
import { SettingsProvider } from '@deepseek-ai/dsh-settings'
import type { SettingsNamespace } from '@deepseek-ai/dsh-settings'
import { ReasoningEffortId } from '@deepseek-ai/dsh-llm'
/** The smallest real provider: one in-memory document, always writable. */
class MemorySettings extends Settings {
class MemorySettings extends SettingsProvider {
doc: Record<string, unknown> = {}
get writable(): boolean {
@@ -28,19 +28,19 @@ class MemorySettings extends Settings {
async function boot(): Promise<{
ctx: Context
settingsFiber: Context['fiber']
defaultModel: AgentDefaultModelService
defaultModel: AgentDefaultModelConfig
}> {
const ctx = new Context()
const settingsFiber = ctx.plugin(MemorySettings)
await settingsFiber.await()
await ctx.plugin(AgentDefaultModelService, {
await ctx.plugin(AgentDefaultModelConfig, {
provider: 'deepseek-official',
model: 'deepseek-v4-flash',
})
return { ctx, settingsFiber, defaultModel: ctx.agentDefaultModel }
}
describe('AgentDefaultModelService', () => {
describe('AgentDefaultModelConfig', () => {
it('resolves the user layer over the composition entry', async () => {
const bench = await boot()
expect(bench.defaultModel.currentSelection()).toEqual({
@@ -90,7 +90,7 @@ describe('AgentDefaultModelService', () => {
it('keeps the composition entry when no settings provider is mounted', async () => {
const ctx = new Context()
await ctx.plugin(AgentDefaultModelService, { provider: 'p', model: 'm' })
await ctx.plugin(AgentDefaultModelConfig, { provider: 'p', model: 'm' })
await ctx.agentDefaultModel.saveSelection({ provider: 'other', model: 'other' })
expect(ctx.agentDefaultModel.currentSelection()).toEqual({ provider: 'p', model: 'm' })
await ctx.fiber.dispose()
packages/core/agent-default-model/tsconfig.json
+1 -1
View File
@@ -24,7 +24,7 @@
"path": "../../settings/settings"
},
{
"path": "../../support/invariants"
"path": "../../runtime-diagnostics/invariants"
}
]
}
packages/core/agent-loop/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 packages/core/agent-loop/README.md
README.md: 13f79b9e70bfb658c459240c97acf39025df2ac0
README.zh.md: 3124acc6c458374e3459837111a4424afb604b29
README.md: 683799d1840c857981d4ff30dd3e8e078be03098
README.zh.md: e2896192078456e424e7df87d77d5a636c11d932
packages/core/agent-loop/README.md
+1 -1
View File
@@ -78,7 +78,7 @@ Everything that goes beyond "call the model, run the tools, repeat" belongs to p
- Compaction: pressure on `agent/pre-step`; canonical overflow repair on `agent/request-error`
- Model-request recovery: `dsh-llm-retry` records and waits exact-provider normal or unbounded backoff on `agent/request-error`, emits non-surface `llm/retry` status, then returns a retry action
- Sandbox, permission, plan mode: `tools/pre-execute` for extensible deny/ask, `tools.guard()` for monotonic owner policy, `tools/post-execute` for result decisions, and `tools/result` for final observation
- Sub-agents: implemented outside the loop as `ctx.subagents` providers; in-process providers use `ctx.agents.create()` and owned `AgentHandle` teardown, while generic [`ctx.tasks`](../../tasks/tasks/) plus [`dsh-tool-subagent`](../../subagent/tool-subagent/) own background collection.
- Sub-agents: implemented outside the loop as `ctx.subagents` providers; in-process providers use `ctx.agents.create()` and owned `AgentHandle` teardown, while generic [`ctx.jobs`](../../jobs/jobs/) plus [`dsh-tool-subagent`](../../subagent/tool-subagent/) own background collection.
- Persistence: eager write-behind from `session/event`; `session/flush` is an explicit observation barrier
- UI: `session/event` (assistant token stream, boundaries, tool activity) + `agent/*` control events (`agent/status`, `agent/created`/`agent/disposed`)
packages/core/agent-loop/README.zh.md
+1 -1
View File
@@ -78,7 +78,7 @@ interface Config {
- 压缩（compaction）：在 `agent/pre-step` 上观测压力；在 `agent/request-error` 上进行规范的溢出修复
- 模型请求恢复：`dsh-llm-retry` 在 `agent/request-error` 上记录并等待按确切提供方配置的 normal 或无界退避，发出不进入表层的 `llm/retry` 状态，然后返回重试动作
- 沙箱、权限、计划模式：使用 `tools/pre-execute` 提供可扩展的拒绝／询问，使用 `tools.guard()` 提供单调拥有方策略，使用 `tools/post-execute` 处理结果决定，并使用 `tools/result` 进行最终观测
- subagent：在循环外部实现为 `ctx.subagents` 提供方；进程内提供方使用 `ctx.agents.create()` 和拥有的 `AgentHandle` 进行 teardown，而通用的 [`ctx.tasks`](../../tasks/tasks/) 与 [`dsh-tool-subagent`](../../subagent/tool-subagent/) 负责后台收集。
- subagent：在循环外部实现为 `ctx.subagents` 提供方；进程内提供方使用 `ctx.agents.create()` 和拥有的 `AgentHandle` 进行 teardown，而通用的 [`ctx.jobs`](../../jobs/jobs/) 与 [`dsh-tool-subagent`](../../subagent/tool-subagent/) 负责后台收集。
- 持久化：从 `session/event` 立即后写；`session/flush` 是显式观测屏障
- UI：`session/event`（assistant token 流、边界、工具活动）+ `agent/*` 控制事件（`agent/status`、`agent/created`/`agent/disposed`）
packages/core/agent-loop/package.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"name": "@deepseek-ai/dsh-agent-loop",
"description": "The concrete agent loop plugin for the DeepSeek Harness",
"version": "0.0.1-rc.2",
"version": "0.0.1-rc.5",
"publishConfig": {
"access": "restricted"
},
packages/core/agent-loop/src/agent.ts
+2 -2
View File
@@ -139,7 +139,7 @@ export class ReactLoopAgent implements Agent {
if (this.phase.kind !== 'idle') this.phase.abort.abort(cause)
}
runMaintenance<T>(task: (signal: AbortSignal) => Promise<T>): Promise<T> {
runMaintenance<T>(job: (signal: AbortSignal) => Promise<T>): Promise<T> {
if (this.phase.kind !== 'idle') throw new Error(`agent "${this.id}" already has active work`)
const done = Promise.withResolvers<void>()
const maintenance: Phase = {
@@ -152,7 +152,7 @@ export class ReactLoopAgent implements Agent {
this.activityDone = done.promise
return (async () => {
try {
return await task(maintenance.abort.signal)
return await job(maintenance.abort.signal)
} finally {
this.setPhase({ kind: 'idle', lastTurn: maintenance.lastTurn })
if (maintenance.wakeRequested && this.inbox.hasPending) this.wakeDriver()
packages/core/agent-loop/src/index.ts
+8 -8
View File
@@ -62,20 +62,20 @@ class FactoryOwnership {
}
/** Join config startup work that begins before an agent exists. */
trackStartup(task: Promise<void>): void {
this.startupTasks.add(task)
const forget = () => { this.startupTasks.delete(task) }
void task.then(forget, forget)
trackStartup(job: Promise<void>): void {
this.startupTasks.add(job)
const forget = () => { this.startupTasks.delete(job) }
void job.then(forget, forget)
}
/** Join one public create/resume continuation; factory dispose awaits its settlement. */
trackWrapper(task: Promise<unknown>): void {
this.trackStartup(task.then(() => undefined, () => undefined))
trackWrapper(job: Promise<unknown>): void {
this.trackStartup(job.then(() => undefined, () => undefined))
}
/** Resolve `task`, or stop waiting when factory teardown begins. */
async waitWhileActive(task: Promise<void>): Promise<void> {
await Promise.race([task, this.inactive.promise])
async waitWhileActive(job: Promise<void>): Promise<void> {
await Promise.race([job, this.inactive.promise])
}
async dispose(): Promise<void> {
packages/core/agent-loop/src/tool-calls.ts
+5 -5
View File
@@ -14,7 +14,7 @@
import type { Context } from '@deepseek-ai/cordis'
import { assertNever, createToolResultMessage, type ToolCallBlock } from '@deepseek-ai/dsh-llm'
import type { Session, UserMessage } from '@deepseek-ai/dsh-session'
import { TOOL_ABORTED_BEFORE_DISPATCH, TOOL_REGISTRY_SCHEDULER, type ToolExecutionInput, type ToolExecutionMode, type ToolExecutionResult, type ToolRunContext } from '@deepseek-ai/dsh-tools'
import { TOOL_ABORTED_BEFORE_DISPATCH, TOOL_RUNTIME_SCHEDULER, type ToolExecutionInput, type ToolExecutionMode, type ToolExecutionResult, type ToolRunContext } from '@deepseek-ai/dsh-tools'
/** One tool call after argument parsing, ready to schedule. */
interface PlannedCall {
@@ -149,8 +149,8 @@ async function runGroup(
if (slot === undefined) break
const call = group[committed]
const result = slot.needsPost
? await ctx.tools[TOOL_REGISTRY_SCHEDULER].finalize(slot.exec, slot.result)
: ctx.tools[TOOL_REGISTRY_SCHEDULER].finish(slot.exec, slot.result)
? await ctx.tools[TOOL_RUNTIME_SCHEDULER].finalize(slot.exec, slot.result)
: ctx.tools[TOOL_RUNTIME_SCHEDULER].finish(slot.exec, slot.result)
// oxlint-disable-next-line typescript/no-non-null-assertion -- bounded index
appendToolResult(session, turn, step, call!.block, result, callSeqs[committed]!)
for (const context of result.additionalContexts ?? []) acceptContext(context)
@@ -166,11 +166,11 @@ async function runGroup(
const call = group[index]!
callSeqs[index] = appendToolCall(session, turn, step, call.block)
started++
const prepared = await ctx.tools[TOOL_REGISTRY_SCHEDULER].prepare(call.exec)
const prepared = await ctx.tools[TOOL_RUNTIME_SCHEDULER].prepare(call.exec)
throwSchedulerFailure()
switch (prepared.kind) {
case 'dispatch': {
const promise = ctx.tools[TOOL_REGISTRY_SCHEDULER].dispatch(prepared.exec).then(
const promise = ctx.tools[TOOL_RUNTIME_SCHEDULER].dispatch(prepared.exec).then(
(outcome) => {
slots[index] = { exec: prepared.exec, result: outcome.result, needsPost: outcome.kind === 'post-result' }
return index
packages/core/agent-loop/tests/agent-initiator.spec.ts
+8 -8
View File
@@ -2,11 +2,11 @@ import { describe, expect, it } from 'vitest'
import { Context, type Fiber } from '@deepseek-ai/cordis'
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import LlmService, { createUserMessage, CallId, LlmAdapter } from '@deepseek-ai/dsh-llm'
import LlmRuntime, { createUserMessage, CallId, LlmAdapter } from '@deepseek-ai/dsh-llm'
import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm'
import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry, { defineContentToolFixture } from '@deepseek-ai/dsh-tools'
import ToolRuntime, { defineContentToolFixture } from '@deepseek-ai/dsh-tools'
import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts'
const testToolSignal = new AbortController().signal
@@ -19,10 +19,10 @@ interface Harness {
async function harness(adapter: LlmAdapter): Promise<Harness> {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
const agentsFiber = await ctx.plugin(AgentRegistry)
const loopFiber = await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], adapter)
@@ -119,10 +119,10 @@ describe('AgentLoop initiator scope', () => {
it('keeps overlapping driver continuations bound to their exact Agents', async () => {
const ctx = new Context()
const adapter = new OverlapAdapter(ctx)
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], adapter)
@@ -378,10 +378,10 @@ describe('AgentLoop initiator scope', () => {
it('keeps ALS readable while root disposal drains sibling AgentLoop fibers', async () => {
const ctx = new Context()
const adapter = new ReloadAdapter()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], adapter)
packages/core/agent-loop/tests/agent.spec.ts
+4 -4
View File
@@ -3,18 +3,18 @@ import { describe, expect, it, vi } from 'vitest'
import { Context } from '@deepseek-ai/cordis'
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import LlmService from '@deepseek-ai/dsh-llm'
import LlmRuntime from '@deepseek-ai/dsh-llm'
import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry from '@deepseek-ai/dsh-tools'
import ToolRuntime from '@deepseek-ai/dsh-tools'
import { MockAdapter, textResponse } from './mock-adapter.ts'
async function harness(adapter: MockAdapter): Promise<Context> {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], adapter)
packages/core/agent-loop/tests/cancel.spec.ts
+6 -6
View File
@@ -9,10 +9,10 @@ import { createUserMessage } from '@deepseek-ai/dsh-llm'
import { describe, expect, it } from 'vitest'
import { Context } from '@deepseek-ai/cordis'
import LlmService from '@deepseek-ai/dsh-llm'
import LlmRuntime from '@deepseek-ai/dsh-llm'
import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry, { defineContentToolFixture, TOOL_ABORTED_BEFORE_DISPATCH } from '@deepseek-ai/dsh-tools'
import ToolRuntime, { defineContentToolFixture, TOOL_ABORTED_BEFORE_DISPATCH } from '@deepseek-ai/dsh-tools'
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts'
@@ -23,10 +23,10 @@ function driverDone(agent: Agent): Promise<void> {
async function harness(adapter: MockAdapter) {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], adapter)
@@ -512,10 +512,10 @@ describe('Agent.cancel()', () => {
it('disposal from a synchronous step/start session-event listener stops before adapter dispatch', async () => {
const adapter = new MockAdapter([textResponse('should not stream')])
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], adapter)
packages/core/agent-loop/tests/config-session-id.spec.ts
+30 -30
View File
@@ -4,13 +4,13 @@ import { Context } from '@deepseek-ai/cordis'
import { mkdtemp, rm } from 'node:fs/promises'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import LlmService from '@deepseek-ai/dsh-llm'
import LlmRuntime from '@deepseek-ai/dsh-llm'
import SessionStore, { SessionId, SessionPreparation } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry from '@deepseek-ai/dsh-tools'
import ToolRuntime from '@deepseek-ai/dsh-tools'
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
import JsonlSessionPersistence from '@deepseek-ai/dsh-session-persistence-jsonl'
import AgentLoop, { CONFIGURED_AGENT_IDENTITIES_KEY } from '@deepseek-ai/dsh-agent-loop'
import { MockAdapter, textResponse } from './mock-adapter.ts'
@@ -27,10 +27,10 @@ function waitForIdle(ctx: Context, agent: Agent): Promise<void> {
async function makeCoreContext(): Promise<Context> {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
return ctx
}
@@ -89,7 +89,7 @@ describe('config-driven session id', () => {
const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-duplicate-'))
dirs.push(root)
const ctx = await makeCoreContext()
await ctx.plugin(SessionPersistenceJsonl, { root })
await ctx.plugin(JsonlSessionPersistence, { root })
const outcome = await ctx.plugin(AgentLoop, {
agents: [
@@ -108,7 +108,7 @@ describe('config-driven session id', () => {
const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-reload-'))
dirs.push(root)
const ctx = await makeCoreContext()
await ctx.plugin(SessionPersistenceJsonl, { root })
await ctx.plugin(JsonlSessionPersistence, { root })
ctx.llm.registerAdapter(['mock'], new MockAdapter([textResponse('first'), textResponse('second')]))
const config = { agents: [{ id: 'main', sessionId: SessionId('config-exact-reload'), provider: 'mock', model: 'mock' }] }
@@ -137,7 +137,7 @@ describe('config-driven session id', () => {
const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-overlap-'))
dirs.push(root)
const ctx = await makeCoreContext()
await ctx.plugin(SessionPersistenceJsonl, { root })
await ctx.plugin(JsonlSessionPersistence, { root })
ctx.llm.registerAdapter(['mock'], new MockAdapter([textResponse('saved')]))
const sessionId = SessionId('config-exact-overlap')
const config = { agents: [{ id: 'main', sessionId, provider: 'mock', model: 'mock' }] }
@@ -184,7 +184,7 @@ describe('config-driven session id', () => {
const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-cancel-'))
dirs.push(root)
const ctx = await makeCoreContext()
await ctx.plugin(SessionPersistenceJsonl, { root })
await ctx.plugin(JsonlSessionPersistence, { root })
const sessionId = SessionId('config-exact-cancel')
const config = { agents: [{ id: 'main', sessionId, model: 'mock' }] }
const firstLoop = await ctx.plugin(AgentLoop, config)
@@ -219,7 +219,7 @@ describe('config-driven session id', () => {
const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-failure-'))
dirs.push(root)
const ctx = await makeCoreContext()
await ctx.plugin(SessionPersistenceJsonl, { root })
await ctx.plugin(JsonlSessionPersistence, { root })
const failure = new Error('persistence index failed')
const listenerFailure = new Error('failure observer failed')
const asyncListenerFailure = new Error('async failure observer failed')
@@ -255,7 +255,7 @@ describe('config-driven session id', () => {
const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-unrenderable-'))
dirs.push(root)
const ctx = await makeCoreContext()
await ctx.plugin(SessionPersistenceJsonl, { root })
await ctx.plugin(JsonlSessionPersistence, { root })
const unrenderable = {
[Symbol.toPrimitive](): never {
throw new Error('coercion escaped')
@@ -293,7 +293,7 @@ describe('config-driven session id', () => {
const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-dispose-'))
dirs.push(root)
const ctx = await makeCoreContext()
await ctx.plugin(SessionPersistenceJsonl, { root })
await ctx.plugin(JsonlSessionPersistence, { root })
const preparing = Promise.withResolvers<SessionPreparation>()
vi.spyOn(ctx.sessionPersistence, 'prepare').mockReturnValue(preparing.promise)
const released = vi.fn()
@@ -325,10 +325,10 @@ describe('config-driven session id', () => {
it('identity-nests the deferred resume fiber under its labeled owner effect', async () => {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
const loopFiber = await ctx.plugin(AgentLoop, {
agents: [{ id: SessionId('main'), provider: 'mock', model: 'mock', resumeSessionId: SessionId('deferred') }],
@@ -350,13 +350,13 @@ describe('config-driven session id', () => {
const idPattern = /^cfg-session-[0-9a-f-]{36}$/
// Run 1: a config agent persists a turn under a generated session id.
const ctx1 = new Context()
await ctx1.plugin(LlmService)
await ctx1.plugin(LlmRuntime)
await ctx1.plugin(SessionStore)
await ctx1.plugin(SystemPrompt)
await ctx1.plugin(ToolRegistry)
await ctx1.plugin(ToolRuntime)
await ctx1.plugin(AgentRegistry)
await ctx1.plugin(AgentLoop, { agents: [{ id: SessionId('cfg'), provider: 'mock', model: 'mock' }] })
await ctx1.plugin(SessionPersistenceJsonl, { root })
await ctx1.plugin(JsonlSessionPersistence, { root })
ctx1.llm.registerAdapter(['mock'], new MockAdapter([textResponse('cfg')]))
const a1 = ctx1.agents.list()[0] as Agent
expect(a1.id).toBe(a1.session.id)
@@ -369,13 +369,13 @@ describe('config-driven session id', () => {
// Run 2 over the SAME root: a fresh id means no on-disk collision (a fixed
// ${id}-session would crash here with "already has a persisted log").
const ctx2 = new Context()
await ctx2.plugin(LlmService)
await ctx2.plugin(LlmRuntime)
await ctx2.plugin(SessionStore)
await ctx2.plugin(SystemPrompt)
await ctx2.plugin(ToolRegistry)
await ctx2.plugin(ToolRuntime)
await ctx2.plugin(AgentRegistry)
await ctx2.plugin(AgentLoop, { agents: [{ id: SessionId('cfg'), provider: 'mock', model: 'mock' }] })
await ctx2.plugin(SessionPersistenceJsonl, { root })
await ctx2.plugin(JsonlSessionPersistence, { root })
ctx2.llm.registerAdapter(['mock'], new MockAdapter([textResponse('cfg2')]))
const a2 = ctx2.agents.list()[0] as Agent
expect(a2.id).toBe(a2.session.id)
@@ -393,13 +393,13 @@ describe('config-driven session id', () => {
// Run 1: a programmatically-created agent on a KNOWN session id persists a
// completed turn, so run 2 has a concrete id to resume.
const ctx1 = new Context()
await ctx1.plugin(LlmService)
await ctx1.plugin(LlmRuntime)
await ctx1.plugin(SessionStore)
await ctx1.plugin(SystemPrompt)
await ctx1.plugin(ToolRegistry)
await ctx1.plugin(ToolRuntime)
await ctx1.plugin(AgentRegistry)
await ctx1.plugin(AgentLoop, { agents: [] })
await ctx1.plugin(SessionPersistenceJsonl, { root })
await ctx1.plugin(JsonlSessionPersistence, { root })
ctx1.llm.registerAdapter(['mock'], new MockAdapter([textResponse('first')]))
const a1 = (await ctx1.agents.create({ sessionId: SessionId('sticky-1') })).agent
a1.followup(createUserMessage({ content: [{ type: 'text', text: 'remember me' }], source: { kind: 'user' } }))
@@ -409,13 +409,13 @@ describe('config-driven session id', () => {
// Resume waits for the injected persistence service, so poll until the
// config-created agent appears with its stored history.
const ctx2 = new Context()
await ctx2.plugin(LlmService)
await ctx2.plugin(LlmRuntime)
await ctx2.plugin(SessionStore)
await ctx2.plugin(SystemPrompt)
await ctx2.plugin(ToolRegistry)
await ctx2.plugin(ToolRuntime)
await ctx2.plugin(AgentRegistry)
await ctx2.plugin(AgentLoop, { agents: [{ id: SessionId('main'), provider: 'mock', model: 'mock', resumeSessionId: SessionId('sticky-1') }] })
await ctx2.plugin(SessionPersistenceJsonl, { root })
await ctx2.plugin(JsonlSessionPersistence, { root })
ctx2.llm.registerAdapter(['mock'], new MockAdapter([textResponse('second')]))
// The deferred resume runs after the backend is available.
@@ -434,15 +434,15 @@ describe('config-driven session id', () => {
const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-resume-miss-'))
dirs.push(root)
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [{ id: SessionId('main'), provider: 'mock', model: 'mock', resumeSessionId: SessionId('does-not-exist') }] })
const warn = vi.spyOn((ctx.agentLoop as unknown as { ctx: { logger: { warn: (...a: unknown[]) => void } } }).ctx.logger, 'warn')
.mockImplementation(() => undefined)
await ctx.plugin(SessionPersistenceJsonl, { root })
await ctx.plugin(JsonlSessionPersistence, { root })
ctx.llm.registerAdapter(['mock'], new MockAdapter([textResponse('x')]))
// The deferred resume fails (no such session on disk). It must be contained:
@@ -460,7 +460,7 @@ describe('startup reporting after factory teardown', () => {
const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-disposed-report-'))
dirs.push(root)
const ctx = await makeCoreContext()
await ctx.plugin(SessionPersistenceJsonl, { root })
await ctx.plugin(JsonlSessionPersistence, { root })
ctx.llm.registerAdapter(['mock'], new MockAdapter([textResponse('x')]))
// A restore lookup that hangs until after the loop is gone: the eventual
packages/core/agent-loop/tests/contract-regressions.spec.ts
+21 -21
View File
@@ -1,20 +1,20 @@
import { describe, expect, it } from 'vitest'
import { Context } from '@deepseek-ai/cordis'
import LlmService, { createUserMessage, CallId, LlmError, MessageSource, ProviderRequestId, StreamChunk } from '@deepseek-ai/dsh-llm'
import LlmRuntime, { createUserMessage, CallId, LlmError, MessageSource, ProviderRequestId, StreamChunk } from '@deepseek-ai/dsh-llm'
import SessionStore, { Session, SessionEvent, SessionId, TurnEndReason, type UserMessage } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry, { defineContentToolFixture, type PostToolDecision } from '@deepseek-ai/dsh-tools'
import ToolRuntime, { defineContentToolFixture, type PostToolDecision } from '@deepseek-ai/dsh-tools'
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import { ReactLoopAgent } from '../src/agent.ts'
import InvariantService from '@deepseek-ai/dsh-invariants'
import InvariantRegistry from '@deepseek-ai/dsh-invariants'
import * as SessionInvariant from '@deepseek-ai/dsh-session/invariant'
import * as AgentInvariant from '@deepseek-ai/dsh-agent/invariant'
import * as AgentLoopInvariant from '@deepseek-ai/dsh-agent-loop/invariant'
import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts'
async function mountInvariants(ctx: Context): Promise<void> {
await ctx.plugin(InvariantService)
await ctx.plugin(InvariantRegistry)
await ctx.plugin(SessionInvariant)
await ctx.plugin(AgentInvariant)
await ctx.plugin(AgentLoopInvariant)
@@ -28,10 +28,10 @@ function driverDone(agent: Agent): Promise<void> {
async function harness(adapter: MockAdapter) {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], adapter)
@@ -427,7 +427,7 @@ describe('disposal leaves the two-state status contract balanced', () => {
describe('adapter registration, routing, and accepted-input ownership', () => {
it('duplicate adapter registration is rejected', async () => {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
const adapter = new MockAdapter([])
ctx.llm.registerAdapter(['m1'], adapter)
expect(() => ctx.llm.registerAdapter(['m1'], new MockAdapter([])))
@@ -523,10 +523,10 @@ describe('turn numbering continues across seeded sessions', () => {
// fork: seed a second context's agent with the first session's log
const second = new MockAdapter([textResponse('turn two')])
const ctx2 = new Context()
await ctx2.plugin(LlmService)
await ctx2.plugin(LlmRuntime)
await ctx2.plugin(SessionStore)
await ctx2.plugin(SystemPrompt)
await ctx2.plugin(ToolRegistry)
await ctx2.plugin(ToolRuntime)
await ctx2.plugin(AgentRegistry)
await ctx2.plugin(AgentLoop, { agents: [] })
ctx2.llm.registerAdapter(['mock'], second)
@@ -674,10 +674,10 @@ describe('turn and step boundary recovery', () => {
// The session invariant companion makes an unbalanced log fail the test.
async function balancedHarness(adapter: MockAdapter) {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
await mountInvariants(ctx)
@@ -1106,10 +1106,10 @@ describe('disposal and cancellation during pre-step assembly', () => {
const blocked = new Promise<void>(r => void (releaseAssemble = r))
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
await mountInvariants(ctx)
@@ -1156,10 +1156,10 @@ describe('disposal and cancellation during pre-step assembly', () => {
const blocker = new Promise<void>(r => void (releaseAssemble = r))
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
await mountInvariants(ctx)
@@ -1206,10 +1206,10 @@ describe('disposal and cancellation during pre-step assembly', () => {
const blocker = new Promise<void>(r => void (releasePreStep = r))
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
await mountInvariants(ctx)
@@ -1252,10 +1252,10 @@ describe('disposal and cancellation during pre-step assembly', () => {
const blocker = new Promise<void>(r => void (releasePreStep = r))
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
await mountInvariants(ctx)
@@ -1300,10 +1300,10 @@ describe('disposal and cancellation during pre-step assembly', () => {
const blocker = new Promise<void>(r => void (releaseAssemble = r))
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
await mountInvariants(ctx)
packages/core/agent-loop/tests/coverage-edges.spec.ts
+4 -4
View File
@@ -1,10 +1,10 @@
import { describe, expect, it } from 'vitest'
import { Context } from '@deepseek-ai/cordis'
import LlmService, { createUserMessage, CallId, LlmError, StreamChunk, errorChain } from '@deepseek-ai/dsh-llm'
import LlmRuntime, { createUserMessage, CallId, LlmError, StreamChunk, errorChain } from '@deepseek-ai/dsh-llm'
import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session'
import type { SessionEvent } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry, { defineContentToolFixture } from '@deepseek-ai/dsh-tools'
import ToolRuntime, { defineContentToolFixture } from '@deepseek-ai/dsh-tools'
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
@@ -16,10 +16,10 @@ function driverDone(agent: Agent): Promise<void> {
async function harness(adapter: MockAdapter) {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], adapter)
packages/core/agent-loop/tests/interception.spec.ts
+4 -4
View File
@@ -1,6 +1,6 @@
import { describe, expect, it, vi } from 'vitest'
import { Context } from '@deepseek-ai/cordis'
import LlmService, { createUserMessage, CallId } from '@deepseek-ai/dsh-llm'
import LlmRuntime, { createUserMessage, CallId } from '@deepseek-ai/dsh-llm'
import SessionStore, {
SessionId,
type SessionEvent,
@@ -8,7 +8,7 @@ import SessionStore, {
type UserMessage,
} from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry, { defineContentToolFixture, type PostToolDecision, type PreToolDecision } from '@deepseek-ai/dsh-tools'
import ToolRuntime, { defineContentToolFixture, type PostToolDecision, type PreToolDecision } from '@deepseek-ai/dsh-tools'
import AgentRegistry, {
type Agent,
type PreStepDecision,
@@ -29,10 +29,10 @@ import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts'
async function harness(adapter: MockAdapter) {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], adapter)
packages/core/agent-loop/tests/invariant.spec.ts
+3 -3
View File
@@ -1,14 +1,14 @@
import { describe, expect, it } from 'vitest'
import { Context } from '@deepseek-ai/cordis'
import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
import InvariantService from '@deepseek-ai/dsh-invariants'
import InvariantRegistry from '@deepseek-ai/dsh-invariants'
import * as AgentLoopInvariant from '@deepseek-ai/dsh-agent-loop/invariant'
import { createUserMessage, markAgentLoopRequest, type GenerateOptions } from '@deepseek-ai/dsh-llm'
async function setup(): Promise<Context> {
const ctx = new Context()
await ctx.plugin(SessionStore)
await ctx.plugin(InvariantService)
await ctx.plugin(InvariantRegistry)
await ctx.plugin(AgentLoopInvariant)
return ctx
}
@@ -123,7 +123,7 @@ describe('request-reconstruction invariant', () => {
const ctx = new Context()
await ctx.plugin(SessionStore)
ctx.on('llm/stream', () => (async function* () {})() as never)
await ctx.plugin(InvariantService)
await ctx.plugin(InvariantRegistry)
await ctx.plugin(AgentLoopInvariant)
const session = ctx.sessions.create(SessionId('prepend-check'))
session.append('turn/start', { turn: 1 })
packages/core/agent-loop/tests/loop.spec.ts
+14 -14
View File
@@ -1,9 +1,9 @@
import { describe, expect, it } from 'vitest'
import { Context } from '@deepseek-ai/cordis'
import LlmService, { createUserMessage, CallId, LlmError, StreamChunk } from '@deepseek-ai/dsh-llm'
import LlmRuntime, { createUserMessage, CallId, LlmError, StreamChunk } from '@deepseek-ai/dsh-llm'
import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry, { defineContentToolFixture } from '@deepseek-ai/dsh-tools'
import ToolRuntime, { defineContentToolFixture } from '@deepseek-ai/dsh-tools'
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
@@ -15,10 +15,10 @@ function driverDone(agent: Agent): Promise<void> {
async function harness(adapter: MockAdapter, persona = '') {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt, { persona })
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], adapter)
@@ -252,7 +252,7 @@ describe('agent loop', () => {
await waitForIdle(ctx, agent)
const request = adapter.requests[0]
expect(request!.system).toBe('You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are a test agent on mock.\n\nUse the noop tool wisely.')
expect(request!.system).toBe('You are an AI agent powered by DeepSeek Harness.\n\nYou are a test agent on mock.\n\nUse the noop tool wisely.')
expect(request!.tools?.map(t => t.name)).toEqual(['noop'])
})
@@ -269,7 +269,7 @@ describe('agent loop', () => {
send(agent, 'hi')
await waitForIdle(ctx, agent)
expect(adapter.requests[0]!.system).toBe('You are an AI agent powered by the DeepSeek Harness SDK.\n\nWorking in /work/space.')
expect(adapter.requests[0]!.system).toBe('You are an AI agent powered by DeepSeek Harness.\n\nWorking in /work/space.')
})
it('contains a strict-variable render failure: the turn errors, the loop keeps serving turns', async () => {
@@ -305,7 +305,7 @@ describe('agent loop', () => {
await waitForIdle(ctx, agent)
expect(adapter.requests).toHaveLength(1)
expect(adapter.requests[0]!.system).toBe('You are an AI agent powered by the DeepSeek Harness SDK.\n\nIn /rescued.')
expect(adapter.requests[0]!.system).toBe('You are an AI agent powered by DeepSeek Harness.\n\nIn /rescued.')
const turnEnds = agent.session.events.filter(e => e.type === 'turn/end')
expect(turnEnds).toHaveLength(2)
expect(turnEnds[1]?.type === 'turn/end' && turnEnds[1].data.reason.kind).toBe('completed')
@@ -335,7 +335,7 @@ describe('agent loop', () => {
expect(adapter.requests).toHaveLength(1)
expect(adapter.requests[0]!.model).toBe('mock')
expect(adapter.requests[0]!.system).toBe('You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou run on mock.')
expect(adapter.requests[0]!.system).toBe('You are an AI agent powered by DeepSeek Harness.\n\nYou run on mock.')
})
it('omits the system field when system-prompt/assemble short-circuits with an empty assembly', async () => {
@@ -671,13 +671,13 @@ describe('agent loop', () => {
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('raw-context'), { provider: 'mock', model: 'mock' })
const text = '<system-reminder>Additional instructions from: pkg/AGENTS.md</system-reminder>'
agent.inject(createUserMessage({ content: [{ type: 'text', text }], source: { kind: 'plugin', plugin: 'workspace-context' } }))
agent.inject(createUserMessage({ content: [{ type: 'text', text }], source: { kind: 'plugin', plugin: 'agent-instructions' } }))
send(agent, 'go')
await waitForIdle(ctx, agent)
const contextEvent = agent.session.events.find(event => event.type === 'user/message' && event.data.source.kind === 'plugin')
expect(contextEvent?.type === 'user/message' && contextEvent.data.source)
.toEqual({ kind: 'plugin', plugin: 'workspace-context' })
.toEqual({ kind: 'plugin', plugin: 'agent-instructions' })
const requestText = JSON.stringify(adapter.requests[0]!.messages)
expect(requestText).toContain('Additional instructions from: pkg/AGENTS.md')
expect(requestText).not.toContain('<context source=')
@@ -1400,10 +1400,10 @@ describe('agent loop', () => {
it('creates agents from config on startup', async () => {
const adapter = new MockAdapter([textResponse('from config')])
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, {
agents: [{ id: SessionId('config-agent'), provider: 'mock', model: 'mock' }],
@@ -1424,10 +1424,10 @@ describe('agent loop', () => {
it('attaches config agent cwd to the fresh session header', async () => {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, {
agents: [{ id: SessionId('config-agent'), provider: 'mock', model: 'mock', cwd: '/work/project' }],
packages/core/agent-loop/tests/properties.spec.ts
+4 -4
View File
@@ -11,12 +11,12 @@
import { describe, expect, it } from 'vitest'
import { Context } from '@deepseek-ai/cordis'
import LlmService from '@deepseek-ai/dsh-llm'
import LlmRuntime from '@deepseek-ai/dsh-llm'
import { createUserMessage, LlmAdapter } from '@deepseek-ai/dsh-llm'
import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm'
import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry from '@deepseek-ai/dsh-tools'
import ToolRuntime from '@deepseek-ai/dsh-tools'
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
@@ -37,10 +37,10 @@ class EchoAdapter extends LlmAdapter {
async function harness() {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], new EchoAdapter())
packages/core/agent-loop/tests/request-cache.e2e.ts
+4 -4
View File
@@ -1,10 +1,10 @@
import { createUserMessage } from '@deepseek-ai/dsh-llm'
import { afterEach, describe, expect, it } from 'vitest'
import { Context } from '@deepseek-ai/cordis'
import LlmService from '@deepseek-ai/dsh-llm'
import LlmRuntime from '@deepseek-ai/dsh-llm'
import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry, { defineContentToolFixture } from '@deepseek-ai/dsh-tools'
import ToolRuntime, { defineContentToolFixture } from '@deepseek-ai/dsh-tools'
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
@@ -39,10 +39,10 @@ afterEach(async () => {
async function loopHarness(): Promise<Context> {
const created = new Context()
await created.plugin(LlmService)
await created.plugin(LlmRuntime)
await created.plugin(SessionStore)
await created.plugin(SystemPrompt, { persona: SYSTEM })
await created.plugin(ToolRegistry)
await created.plugin(ToolRuntime)
await created.plugin(AgentRegistry)
await created.plugin(AgentLoop, { agents: [] })
await created.plugin(LlmDeepSeek)
packages/core/agent-loop/tests/request-error.spec.ts
+4 -4
View File
@@ -2,19 +2,19 @@ import { describe, expect, it } from 'vitest'
import { Context } from '@deepseek-ai/cordis'
import AgentRegistry from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import LlmService, { createUserMessage, LlmError } from '@deepseek-ai/dsh-llm'
import LlmRuntime, { createUserMessage, LlmError } from '@deepseek-ai/dsh-llm'
import type { LlmFailure, ResolvedRetryPolicy } from '@deepseek-ai/dsh-llm'
import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry from '@deepseek-ai/dsh-tools'
import ToolRuntime from '@deepseek-ai/dsh-tools'
import { MockAdapter, textResponse } from './mock-adapter.ts'
async function harness(adapter: MockAdapter): Promise<Context> {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], adapter)
packages/core/agent-loop/tests/request-reconstruction.spec.ts
+8 -8
View File
@@ -7,11 +7,11 @@
import { describe, expect, it } from 'vitest'
import { Context } from '@deepseek-ai/cordis'
import LlmService, { createUserMessage, LlmError, ReasoningEffortId } from '@deepseek-ai/dsh-llm'
import LlmRuntime, { createUserMessage, LlmError, ReasoningEffortId } from '@deepseek-ai/dsh-llm'
import type { GenerateOptions, LlmModelReasoningInfo, LlmResolvedModelInfo, StreamChunk } from '@deepseek-ai/dsh-llm'
import SessionStore, { Session, SessionId, foldRequestHeader } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry, { defineContentToolFixture } from '@deepseek-ai/dsh-tools'
import ToolRuntime, { defineContentToolFixture } from '@deepseek-ai/dsh-tools'
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
@@ -26,10 +26,10 @@ async function harnessRoutes(
persona = 'stable base',
) {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt, { persona })
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
for (const [provider, adapter] of adapters) ctx.llm.registerAdapter([provider], adapter)
@@ -253,10 +253,10 @@ describe('request stability across the loop', () => {
it('keeps exact-model resolution, request logging, and dispatch on one adapter registration', async () => {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt, { persona: 'stable base' })
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
const started = Promise.withResolvers<undefined>()
@@ -371,10 +371,10 @@ describe('request stability across the loop', () => {
it('lets a short-circuiting llm/stream listener own an unregistered route', async () => {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt, { persona: 'stable base' })
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
let observed: GenerateOptions | undefined
packages/core/agent-loop/tests/resume.spec.ts
+38 -38
View File
@@ -4,14 +4,14 @@ import { Context } from '@deepseek-ai/cordis'
import { mkdtemp, rm } from 'node:fs/promises'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import LlmService from '@deepseek-ai/dsh-llm'
import LlmRuntime from '@deepseek-ai/dsh-llm'
import SessionStore, { SESSION_FORMAT_VERSION, Session, SessionId, SessionPreparation } from '@deepseek-ai/dsh-session'
import type { SessionEvent, SessionHeader } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry from '@deepseek-ai/dsh-tools'
import ToolRuntime from '@deepseek-ai/dsh-tools'
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
import JsonlSessionPersistence from '@deepseek-ai/dsh-session-persistence-jsonl'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import { MockAdapter, textResponse } from './mock-adapter.ts'
@@ -26,13 +26,13 @@ async function persistentHarness(adapter: MockAdapter): Promise<{ ctx: Context;
async function mountPersistentHarness(root: string, adapter: MockAdapter): Promise<Context> {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(SessionPersistenceJsonl, { root })
await ctx.plugin(JsonlSessionPersistence, { root })
ctx.llm.registerAdapter(['mock'], adapter)
return ctx
}
@@ -73,11 +73,11 @@ function waitForIdle(ctx: Context, agent: Agent): Promise<void> {
}
/** Fail a lifecycle regression promptly instead of waiting for Vitest's suite timeout. */
async function promptly<T>(task: Promise<T>): Promise<T> {
async function promptly<T>(job: Promise<T>): Promise<T> {
const timeout = Promise.withResolvers<never>()
const timer = setTimeout(() => { timeout.reject(new Error('lifecycle task did not settle promptly')) }, 1000)
try {
return await Promise.race([task, timeout.promise])
return await Promise.race([job, timeout.promise])
} finally {
clearTimeout(timer)
}
@@ -242,13 +242,13 @@ describe('the session-persistence Agent Note: AgentLoop factory create/resume',
// Lifecycle 2: resume it; the header cwd stays undefined (no-cwd branch).
const adapter2 = new MockAdapter([textResponse('b')])
const ctx2 = new Context()
await ctx2.plugin(LlmService)
await ctx2.plugin(LlmRuntime)
await ctx2.plugin(SessionStore)
await ctx2.plugin(SystemPrompt)
await ctx2.plugin(ToolRegistry)
await ctx2.plugin(ToolRuntime)
await ctx2.plugin(AgentRegistry)
await ctx2.plugin(AgentLoop, { agents: [] })
await ctx2.plugin(SessionPersistenceJsonl, { root })
await ctx2.plugin(JsonlSessionPersistence, { root })
ctx2.llm.registerAdapter(['mock'], adapter2)
const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('nocwd-sess') })).agent
expect(a2.session.header.cwd).toBeUndefined()
@@ -270,13 +270,13 @@ describe('the session-persistence Agent Note: AgentLoop factory create/resume',
// Lifecycle 2: resuming the persisted session emits session-start 'resume'.
const adapter2 = new MockAdapter([textResponse('b')])
const ctx2 = new Context()
await ctx2.plugin(LlmService)
await ctx2.plugin(LlmRuntime)
await ctx2.plugin(SessionStore)
await ctx2.plugin(SystemPrompt)
await ctx2.plugin(ToolRegistry)
await ctx2.plugin(ToolRuntime)
await ctx2.plugin(AgentRegistry)
await ctx2.plugin(AgentLoop, { agents: [] })
await ctx2.plugin(SessionPersistenceJsonl, { root })
await ctx2.plugin(JsonlSessionPersistence, { root })
ctx2.llm.registerAdapter(['mock'], adapter2)
const sources2: string[] = []
ctx2.on('agent/session-start', ({ source }) => void sources2.push(source))
@@ -520,13 +520,13 @@ describe('the session-persistence Agent Note: AgentLoop factory create/resume',
const sessionId = SessionId('resume-load-factory-unload')
const root = await persistSession(sessionId)
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
const loopFiber = await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(SessionPersistenceJsonl, { root })
await ctx.plugin(JsonlSessionPersistence, { root })
ctx.llm.registerAdapter(['mock'], new MockAdapter([textResponse('next')]))
const snapshot = await ctx.sessionPersistence.load(sessionId)
@@ -583,13 +583,13 @@ describe('the session-persistence Agent Note: AgentLoop factory create/resume',
// boundary).
const adapter2 = new MockAdapter([textResponse('b')])
const ctx2 = new Context()
await ctx2.plugin(LlmService)
await ctx2.plugin(LlmRuntime)
await ctx2.plugin(SessionStore)
await ctx2.plugin(SystemPrompt)
await ctx2.plugin(ToolRegistry)
await ctx2.plugin(ToolRuntime)
await ctx2.plugin(AgentRegistry)
await ctx2.plugin(AgentLoop, { agents: [] })
await ctx2.plugin(SessionPersistenceJsonl, { root })
await ctx2.plugin(JsonlSessionPersistence, { root })
ctx2.llm.registerAdapter(['mock'], adapter2)
const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('forked-sess') })).agent
expect(a2.session.header.parentSession).toBe('parent-sess')
@@ -607,7 +607,7 @@ describe('the session-persistence Agent Note: AgentLoop factory create/resume',
const a1 = (await ctx1.agents.create({ sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent
a1.followup(createUserMessage({ content: [{ type: 'text', text: 'q' }], source: { kind: 'user' } }))
await waitForIdle(ctx1, a1)
a1.inject(createUserMessage({ content: [{ type: 'text', text: 'background task 42 finished' }], source: { kind: 'plugin', plugin: 'tool-bash' } }))
a1.inject(createUserMessage({ content: [{ type: 'text', text: 'background job 42 finished' }], source: { kind: 'plugin', plugin: 'tool-bash' } }))
await a1.whenIdle()
await ctx1.sessions.flush(a1.session)
@@ -615,23 +615,23 @@ describe('the session-persistence Agent Note: AgentLoop factory create/resume',
// model-visible when the next turn admits it.
const adapter2 = new MockAdapter([textResponse('next')])
const ctx2 = new Context()
await ctx2.plugin(LlmService)
await ctx2.plugin(LlmRuntime)
await ctx2.plugin(SessionStore)
await ctx2.plugin(SystemPrompt)
await ctx2.plugin(ToolRegistry)
await ctx2.plugin(ToolRuntime)
await ctx2.plugin(AgentRegistry)
await ctx2.plugin(AgentLoop, { agents: [] })
await ctx2.plugin(SessionPersistenceJsonl, { root })
await ctx2.plugin(JsonlSessionPersistence, { root })
ctx2.llm.registerAdapter(['mock'], adapter2)
const loaded = await ctx2.sessionPersistence.load(SessionId('inject-sess'))
expect(loaded.events.some(event => event.type === 'agent/inbox/spliced')).toBe(true)
expect(JSON.stringify(loaded.events)).toContain('background task 42 finished')
expect(JSON.stringify(loaded.events)).toContain('background job 42 finished')
const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('inject-sess') })).agent
expect(JSON.stringify(a2.inbox.nextStep)).toContain('background task 42 finished')
expect(JSON.stringify(a2.inbox.nextStep)).toContain('background job 42 finished')
a2.followup(createUserMessage({ content: [{ type: 'text', text: 'continue' }], source: { kind: 'user' } }))
await waitForIdle(ctx2, a2)
const flat = JSON.stringify(a2.session.deriveMessages())
expect(flat).toContain('background task 42 finished')
expect(flat).toContain('background job 42 finished')
await ctx2.fiber.dispose()
await ctx1.fiber.dispose()
})
@@ -651,13 +651,13 @@ describe('the session-persistence Agent Note: AgentLoop factory create/resume',
// Lifecycle 2: a brand-new context over the SAME root; resume the session.
const adapter2 = new MockAdapter([textResponse('second answer')])
const ctx2 = new Context()
await ctx2.plugin(LlmService)
await ctx2.plugin(LlmRuntime)
await ctx2.plugin(SessionStore)
await ctx2.plugin(SystemPrompt)
await ctx2.plugin(ToolRegistry)
await ctx2.plugin(ToolRuntime)
await ctx2.plugin(AgentRegistry)
await ctx2.plugin(AgentLoop, { agents: [] })
await ctx2.plugin(SessionPersistenceJsonl, { root })
await ctx2.plugin(JsonlSessionPersistence, { root })
ctx2.llm.registerAdapter(['mock'], adapter2)
const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('sess-resume') })).agent
@@ -684,10 +684,10 @@ describe('the session-persistence Agent Note: AgentLoop factory create/resume',
// A harness WITHOUT the persistence plugin.
const adapter = new MockAdapter([textResponse('x')])
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], adapter)
@@ -873,12 +873,12 @@ describe('configured-start failure edges', () => {
ctx.sessionPersistence.prepare = () => Promise.reject(new Error('artifact corrupt'))
const configured = new Context()
await configured.plugin(LlmService)
await configured.plugin(LlmRuntime)
await configured.plugin(SessionStore)
await configured.plugin(SystemPrompt)
await configured.plugin(ToolRegistry)
await configured.plugin(ToolRuntime)
await configured.plugin(AgentRegistry)
await configured.plugin(SessionPersistenceJsonl, { root })
await configured.plugin(JsonlSessionPersistence, { root })
configured.llm.registerAdapter(['mock'], new MockAdapter([]))
configured.sessionPersistence.prepare = (id, signal) => ctx.sessionPersistence.prepare(id, signal)
const configFailures: unknown[] = []
@@ -918,12 +918,12 @@ describe('configured-start failure edges', () => {
ctx.on('agent-loop/config-start-failed', ({ error }) => { failures.push(error) })
const configured = new Context()
await configured.plugin(LlmService)
await configured.plugin(LlmRuntime)
await configured.plugin(SessionStore)
await configured.plugin(SystemPrompt)
await configured.plugin(ToolRegistry)
await configured.plugin(ToolRuntime)
await configured.plugin(AgentRegistry)
await configured.plugin(SessionPersistenceJsonl, { root })
await configured.plugin(JsonlSessionPersistence, { root })
configured.llm.registerAdapter(['mock'], new MockAdapter([]))
configured.sessionPersistence.prepare = (id, signal) => ctx.sessionPersistence.prepare(id, signal)
configured.on('agent-loop/config-start-failed', ({ error }) => { failures.push(error) })
packages/core/agent-loop/tests/scope-lifecycle.spec.ts
+5 -5
View File
@@ -1,10 +1,10 @@
import { createUserMessage } from '@deepseek-ai/dsh-llm'
import { describe, expect, it } from 'vitest'
import { Context, symbols, type EffectMeta, type Fiber } from '@deepseek-ai/cordis'
import LlmService from '@deepseek-ai/dsh-llm'
import LlmRuntime from '@deepseek-ai/dsh-llm'
import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry, { defineContentToolFixture } from '@deepseek-ai/dsh-tools'
import ToolRuntime, { defineContentToolFixture } from '@deepseek-ai/dsh-tools'
import AgentRegistry, { agentEvents, assembleContextFor } from '@deepseek-ai/dsh-agent'
import type { Agent } from '@deepseek-ai/dsh-agent'
@@ -15,10 +15,10 @@ import { MockAdapter, textResponse } from './mock-adapter.ts'
async function harnessWithLoop(adapter: MockAdapter = new MockAdapter([textResponse('ok')])): Promise<{ ctx: Context; loopFiber: Fiber }> {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt, { persona: 'You are the deployment.' })
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
const loopFiber = await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], adapter)
@@ -1052,7 +1052,7 @@ describe('agent scope lifecycle', () => {
})
it('drains a run re-entered by cancel\'s own idle transition before removing the scope', async () => {
// Automation shaped like goal-session: the running→idle transition that
// Automation shaped like goal-round-driver: the running→idle transition that
// disposal's cancel produces immediately queues a follow-up prompt. The
// teardown must drain that replacement run to true quiescence instead of
// awaiting only the first captured done and unwinding under a live run.
packages/core/agent-loop/tests/settings.spec.ts
+6 -6
View File
@@ -3,17 +3,17 @@
import { describe, expect, it } from 'vitest'
import { Context } from '@deepseek-ai/cordis'
import type { Fiber } from '@deepseek-ai/cordis'
import LlmService from '@deepseek-ai/dsh-llm'
import LlmRuntime from '@deepseek-ai/dsh-llm'
import SessionStore from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry from '@deepseek-ai/dsh-tools'
import ToolRuntime from '@deepseek-ai/dsh-tools'
import AgentRegistry from '@deepseek-ai/dsh-agent'
import { Settings } from '@deepseek-ai/dsh-settings'
import { SettingsProvider } from '@deepseek-ai/dsh-settings'
import type { SettingsNamespace } from '@deepseek-ai/dsh-settings'
import AgentLoop, { AGENT_LOOP_SETTINGS_NAMESPACE } from '@deepseek-ai/dsh-agent-loop'
/** The smallest real provider: one in-memory document, always writable. */
class MemorySettings extends Settings {
class MemorySettings extends SettingsProvider {
doc: Record<string, unknown> = {}
get writable(): boolean {
@@ -32,10 +32,10 @@ class MemorySettings extends Settings {
async function boot(): Promise<{ ctx: Context; settingsFiber: Fiber; loopFiber: Fiber }> {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
const settingsFiber = ctx.plugin(MemorySettings)
await settingsFiber.await()
packages/core/agent-loop/tests/tool-calls.spec.ts
+11 -11
View File
@@ -8,8 +8,8 @@ import { Context } from '@deepseek-ai/cordis'
import { createUserMessage, CallId, StreamChunk } from '@deepseek-ai/dsh-llm'
import SessionStore, { SessionEvent, SessionId } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import LlmService from '@deepseek-ai/dsh-llm'
import ToolRegistry, { defineContentToolFixture, TOOL_ABORTED_BEFORE_DISPATCH, TOOL_REGISTRY_SCHEDULER, type PostToolDecision, type PreToolDecision } from '@deepseek-ai/dsh-tools'
import LlmRuntime from '@deepseek-ai/dsh-llm'
import ToolRuntime, { defineContentToolFixture, TOOL_ABORTED_BEFORE_DISPATCH, TOOL_RUNTIME_SCHEDULER, type PostToolDecision, type PreToolDecision } from '@deepseek-ai/dsh-tools'
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
import AgentLoop, { DEFAULT_MAX_PARALLEL_TOOL_CALLS } from '@deepseek-ai/dsh-agent-loop'
import { MockAdapter, textResponse } from './mock-adapter.ts'
@@ -18,10 +18,10 @@ import type { CodeRunRequest, CodeRunResult } from '@deepseek-ai/dsh-code-runtim
async function harness(adapter: MockAdapter, maxParallelToolCalls?: number) {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt, { persona: '' })
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, {
agents: [],
@@ -276,10 +276,10 @@ describe('tool-call scheduler: rolling pool honors maxParallelToolCalls', () =>
it('defaults the cap when direct construction bypasses the config schema', async () => {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt, { persona: '' })
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
const loop = new AgentLoop(ctx, { agents: [] })
@@ -344,10 +344,10 @@ describe('tool-call scheduler: rolling pool honors maxParallelToolCalls', () =>
textResponse('done'),
])
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt, { persona: '' })
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [], maxParallelToolCalls: 1 })
ctx.llm.registerAdapter(['mock'], adapter)
@@ -644,7 +644,7 @@ describe('tool-call scheduler: failure quiescence', () => {
ctx.tools.register(gated.tool)
// The registry contains expected failures as results; replace its internal
// view only to inject the invariant violation this boundary must contain.
const scheduler = ctx.tools[TOOL_REGISTRY_SCHEDULER]
const scheduler = ctx.tools[TOOL_RUNTIME_SCHEDULER]
const prepare = scheduler.prepare.bind(scheduler)
const dispatch = scheduler.dispatch.bind(scheduler)
const prepareGate = Promise.withResolvers<undefined>()
@@ -702,10 +702,10 @@ describe('code-mode native-tool denial through the agent loop', () => {
async function codeModeHarness(adapter: MockAdapter) {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt, { persona: '' })
await ctx.plugin(ToolRegistry, { mode: 'code' })
await ctx.plugin(ToolRuntime, { mode: 'code' })
// eslint-disable-next-line @typescript-eslint/no-explicit-any -- FakeCodeRuntime is an internal test helper with an opaque type shape
await ctx.plugin(FakeCodeRuntime as any)
await ctx.plugin(AgentRegistry)
packages/core/agent-loop/tests/tool-order.spec.ts
+4 -4
View File
@@ -9,11 +9,11 @@ import { createUserMessage } from '@deepseek-ai/dsh-llm'
import { describe, expect, it } from 'vitest'
import { Context } from '@deepseek-ai/cordis'
import LlmService from '@deepseek-ai/dsh-llm'
import LlmRuntime from '@deepseek-ai/dsh-llm'
import SessionStore, { SessionId, foldRequestHeader } from '@deepseek-ai/dsh-session'
import SystemPrompt, { TOOL_ORDER_REST } from '@deepseek-ai/dsh-system-prompt'
import type { Config as SystemPromptConfig } from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry, { defineContentToolFixture } from '@deepseek-ai/dsh-tools'
import ToolRuntime, { defineContentToolFixture } from '@deepseek-ai/dsh-tools'
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
@@ -21,10 +21,10 @@ import { MockAdapter, textResponse } from './mock-adapter.ts'
async function harness(adapter: MockAdapter, toolOrder?: SystemPromptConfig['toolOrder']) {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(LlmRuntime)
await ctx.plugin(SessionStore)
await ctx.plugin(SystemPrompt, { persona: 'stable base', ...toolOrder !== undefined ? { toolOrder } : {} })
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
ctx.llm.registerAdapter(['mock'], adapter)
packages/core/agent-loop/tsconfig.json
+1 -1
View File
@@ -42,7 +42,7 @@
"path": "../../settings/settings"
},
{
"path": "../../support/invariants"
"path": "../../runtime-diagnostics/invariants"
}
]
}
packages/core/agent-tool-mode/README.i18n.yaml → packages/core/agent-tool-presentation/README.i18n.yaml
+3 -3
View File
@@ -1,6 +1,6 @@
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
# 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 packages/core/agent-tool-mode/README.md
README.md: f5f2df21285411dbb3b8c5cac18cc3ab0dc8a22b
README.zh.md: 6246892981bb4dc49cf7a6b99f06b4daf0cb3f3e
# pnpm run verify-translation-pairing --write packages/core/agent-tool-presentation/README.md
README.md: a4747d4d95a732f4eccb81ed44b68c961895d773
README.zh.md: 33b33c63cd61893ea68bd2ab5d7242f8cf7d7c27
packages/core/agent-tool-mode/README.md → packages/core/agent-tool-presentation/README.md
+2 -2
View File
@@ -1,4 +1,4 @@
# dsh-agent-tool-mode
# dsh-agent-tool-presentation
English | [中文](README.zh.md)
@@ -12,7 +12,7 @@ What a preset can own is the **presentation** of that registry. `ctx.tools.prese
## What it does
`native` applies immediately. A code mode instead waits for `ctx.codeRuntime`, which is a host-plane service ([`dsh-code-runtime-worker`](../../code-runtime/code-runtime-worker/README.md)): a preset selecting Code Mode against a deployment composing no runtime then holds this row pending, and `dsh-agent-presets` refuses the mount naming this id. The alternative — applying optimistically — moves the failure to the session's first request, where the operator can act on neither the preset nor the composition.
`native` applies immediately. A code mode instead waits for `ctx.codeRuntime`, which is a host-plane service ([`dsh-code-runtime-worker-thread`](../../code-runtime/code-runtime-worker-thread/README.md)): a preset selecting Code Mode against a deployment composing no runtime then holds this row pending, and `dsh-agent-presets` refuses the mount naming this id. The alternative — applying optimistically — moves the failure to the session's first request, where the operator can act on neither the preset nor the composition.
`mode` is required rather than defaulted, because a preset without this row already gets the deployment default; an omitted value would mean the row was composed for nothing.
packages/core/agent-tool-mode/README.zh.md → packages/core/agent-tool-presentation/README.zh.md
+2 -2
View File
@@ -1,4 +1,4 @@
# dsh-agent-tool-mode
# dsh-agent-tool-presentation
[English](README.md) | 中文
@@ -12,7 +12,7 @@ preset 能拥有的是这份注册表的**呈现方式**。`ctx.tools.presentAs(
## 它做什么
`native` 立即生效。code 类模式则等待 `ctx.codeRuntime`——这是一个宿主平面服务（[`dsh-code-runtime-worker`](../../code-runtime/code-runtime-worker/README.md)）：若某个 preset 在未组装运行时的部署上选择 Code Mode，本行就停在 pending，`dsh-agent-presets` 会指名此 id 拒绝挂载。另一种做法——先乐观应用——会把失败推迟到该会话的第一次请求，那时操作者对 preset 和组装都已无从下手。
`native` 立即生效。code 类模式则等待 `ctx.codeRuntime`——这是一个宿主平面服务（[`dsh-code-runtime-worker-thread`](../../code-runtime/code-runtime-worker-thread/README.md)）：若某个 preset 在未组装运行时的部署上选择 Code Mode，本行就停在 pending，`dsh-agent-presets` 会指名此 id 拒绝挂载。另一种做法——先乐观应用——会把失败推迟到该会话的第一次请求，那时操作者对 preset 和组装都已无从下手。
`mode` 是必填而非有默认值：不带这一行的 preset 本来就会拿到部署默认值，省略它等于这一行白组装了。
packages/core/agent-tool-mode/package.json → packages/core/agent-tool-presentation/package.json
+3 -3
View File
@@ -1,14 +1,14 @@
{
"name": "@deepseek-ai/dsh-agent-tool-mode",
"name": "@deepseek-ai/dsh-agent-tool-presentation",
"description": "Agent-plane presentation selector: composes one agent's tools as Code Mode, native, or both",
"version": "0.0.1-rc.2",
"version": "0.0.1-rc.5",
"publishConfig": {
"access": "restricted"
},
"repository": {
"type": "git",
"url": "git+https://github.com/deepseek-ai/deepseek-harness.git",
"directory": "packages/core/agent-tool-mode"
"directory": "packages/core/agent-tool-presentation"
},
"type": "module",
"main": "lib/index.js",
packages/core/agent-tool-mode/src/index.ts → packages/core/agent-tool-presentation/src/index.ts
+3 -3
View File
@@ -11,11 +11,11 @@
* process. One row per composition, not one per session.
*
* A code mode needs a TypeScript code runtime, which is a host-plane service
* ([`dsh-code-runtime-worker`](../../code-runtime/code-runtime-worker/README.md)).
* ([`dsh-code-runtime-worker-thread`](../../code-runtime/code-runtime-worker/README.md)).
* This row therefore waits for it rather than assuming it: a preset selecting
* Code Mode against a deployment that composes no runtime fails at mount, named
* in the preset's own activation audit, instead of at the first prompt.
* @module @deepseek-ai/dsh-agent-tool-mode
* @module @deepseek-ai/dsh-agent-tool-presentation
*/
import type { Context } from '@deepseek-ai/cordis'
@@ -25,7 +25,7 @@ import type { ToolPresentationMode } from '@deepseek-ai/dsh-tools'
import type {} from '@deepseek-ai/dsh-tools'
/** Cordis plugin name. */
export const name = 'tool-mode'
export const name = 'tool-presentation'
/**
* Required services. `codeRuntime` is NOT listed: a `native` row must mount in
packages/core/agent-tool-mode/src/invariant.ts → packages/core/agent-tool-presentation/src/invariant.ts
+4 -4
View File
@@ -1,16 +1,16 @@
/**
* Package-owned invariant companion for `@deepseek-ai/dsh-agent-tool-mode`.
* @module @deepseek-ai/dsh-agent-tool-mode/invariant
* Package-owned invariant companion for `@deepseek-ai/dsh-agent-tool-presentation`.
* @module @deepseek-ai/dsh-agent-tool-presentation/invariant
*/
/* jscpd:ignore-start */
import type { Context } from '@deepseek-ai/cordis'
import type { InvariantInstaller } from '@deepseek-ai/dsh-invariants'
const PACKAGE_NAME = '@deepseek-ai/dsh-agent-tool-mode'
const PACKAGE_NAME = '@deepseek-ai/dsh-agent-tool-presentation'
/** Cordis companion plugin name. */
export const name = 'tool-mode-invariant'
export const name = 'tool-presentation-invariant'
/** Service required before the companion can reserve package ownership. */
export const inject = ['invariants']
packages/core/agent-tool-mode/tests/agent-tool-mode.spec.ts → packages/core/agent-tool-presentation/tests/agent-tool-presentation.spec.ts
+4 -4
View File
@@ -12,10 +12,10 @@ import { createScope } from '@deepseek-ai/dsh-scope'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import { CodeRuntime } from '@deepseek-ai/dsh-code-runtime'
import type { CodeRunRequest, CodeRunResult } from '@deepseek-ai/dsh-code-runtime'
import ToolRegistry, { RUN_CODE_NAME, defineTool } from '@deepseek-ai/dsh-tools'
import ToolRuntime, { RUN_CODE_NAME, defineTool } from '@deepseek-ai/dsh-tools'
import type { Agent } from '@deepseek-ai/dsh-agent'
import { SessionId } from '@deepseek-ai/dsh-session'
import { apply, Config, inject, name } from '@deepseek-ai/dsh-agent-tool-mode'
import { apply, Config, inject, name } from '@deepseek-ai/dsh-agent-tool-presentation'
/** A runtime that never runs anything: presentation never dispatches. */
class StubRuntime extends CodeRuntime {
@@ -31,7 +31,7 @@ class StubRuntime extends CodeRuntime {
async function host(options: { runtime?: boolean } = {}) {
const ctx = new Context()
await ctx.plugin(SystemPrompt, {})
await ctx.plugin(ToolRegistry, {})
await ctx.plugin(ToolRuntime, {})
if (options.runtime !== false) await ctx.plugin(StubRuntime)
ctx.tools.register(defineTool({
name: 'echo',
@@ -56,7 +56,7 @@ async function mount(ctx: Context, config: Config, id = 'agent') {
return { agent, fiber, row }
}
describe('the tool-mode row', () => {
describe('the tool-presentation row', () => {
it('declares the services it uses without holding a code runtime hostage', () => {
// A `native` row must mount where no runtime is composed, so the wait is
// conditional inside apply rather than static metadata.
packages/core/agent-tool-mode/tsconfig.json → packages/core/agent-tool-presentation/tsconfig.json
+1 -1
View File
@@ -21,7 +21,7 @@
"path": "../../core/tools"
},
{
"path": "../../support/invariants"
"path": "../../runtime-diagnostics/invariants"
}
]
}
packages/core/agent/package.json
+3 -3
View File
@@ -1,7 +1,7 @@
{
"name": "@deepseek-ai/dsh-agent",
"description": "Agent interface, registry, initiator scope, and event vocabulary for the DeepSeek Harness",
"version": "0.0.1-rc.2",
"version": "0.0.1-rc.5",
"publishConfig": {
"access": "restricted"
},
@@ -42,7 +42,7 @@
"@deepseek-ai/dsh-scope": "workspace:^",
"@deepseek-ai/dsh-session": "workspace:^",
"@deepseek-ai/dsh-system-prompt": "workspace:^",
"@deepseek-ai/dsh-type-meta": "workspace:^",
"@deepseek-ai/dsh-typert-protocol": "workspace:^",
"@deepseek-ai/cordis": "workspace:^"
},
"devDependencies": {
@@ -51,7 +51,7 @@
"@deepseek-ai/dsh-scope": "workspace:^",
"@deepseek-ai/dsh-session": "workspace:^",
"@deepseek-ai/dsh-system-prompt": "workspace:^",
"@deepseek-ai/dsh-type-meta": "workspace:^",
"@deepseek-ai/dsh-typert-protocol": "workspace:^",
"@deepseek-ai/dsh-typert-registry": "workspace:^",
"@deepseek-ai/cordis": "workspace:^"
}
packages/core/agent/src/index.ts
+6 -6
View File
@@ -12,7 +12,7 @@ import { isPromise } from 'node:util/types'
import { scopeTarget } from '@deepseek-ai/dsh-scope'
import type { Scoped } from '@deepseek-ai/dsh-scope'
import type { SessionEvent, SessionId } from '@deepseek-ai/dsh-session'
import type { TypeRTContext, TypeRTLookup } from '@deepseek-ai/dsh-type-meta'
import type { TypertContext, TypertLookup } from '@deepseek-ai/dsh-typert-protocol'
import type { Agent, AgentOptions } from './runtime-types.ts'
export * from './runtime-types.ts'
@@ -23,13 +23,13 @@ export * from './model-selection.ts'
export { agentCarrier, agentEvents, assembleContextFor, emitAgentEvent } from './dispatch.ts'
export type { AgentEventDispatch, AgentSubjectEvent } from './dispatch.ts'
declare module '@deepseek-ai/dsh-type-meta' {
interface TypeRTLookupMap {
agent: TypeRTLookup<Agent, SessionId>
declare module '@deepseek-ai/dsh-typert-protocol' {
interface TypertLookupMap {
agent: TypertLookup<Agent, SessionId>
}
interface TypeRTContextMap {
agent: TypeRTContext<SessionId>
interface TypertContextMap {
agent: TypertContext<SessionId>
}
}
packages/core/agent/tests/agent.spec.ts
+1 -1
View File
@@ -143,7 +143,7 @@ describe('Inbox', () => {
})
describe('AgentRegistry', () => {
it('contributes Agent lookup and scoped Context providers while TypeRT is live', async () => {
it('contributes Agent lookup and scoped Context providers while Typert is live', async () => {
const ctx = new Context()
const agentFiber = ctx.plugin(AgentRegistry)
await agentFiber
packages/core/agent/tests/invariant.spec.ts
+2 -2
View File
@@ -3,11 +3,11 @@ import { Context } from '@deepseek-ai/cordis'
import type { Agent } from '@deepseek-ai/dsh-agent'
import * as AgentInvariant from '@deepseek-ai/dsh-agent/invariant'
import { scopeTarget } from '@deepseek-ai/dsh-scope'
import InvariantService from '@deepseek-ai/dsh-invariants'
import InvariantRegistry from '@deepseek-ai/dsh-invariants'
async function setup(): Promise<Context> {
const ctx = new Context()
await ctx.plugin(InvariantService)
await ctx.plugin(InvariantRegistry)
await ctx.plugin(AgentInvariant)
return ctx
}
packages/core/agent/tsconfig.json
+2 -2
View File
@@ -27,10 +27,10 @@
"path": "../../core/system-prompt"
},
{
"path": "../../support/invariants"
"path": "../../runtime-diagnostics/invariants"
},
{
"path": "../../typert/type-meta"
"path": "../../typert/protocol"
}
]
}
packages/core/scope/package.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"name": "@deepseek-ai/dsh-scope",
"description": "Scoped-context registration primitive (scope tags, scope-filtered event dispatch) for the DeepSeek Harness",
"version": "0.0.1-rc.2",
"version": "0.0.1-rc.5",
"publishConfig": {
"access": "restricted"
},
packages/core/scope/tests/invariant.spec.ts
+2 -2
View File
@@ -5,11 +5,11 @@ import type { Events } from '@deepseek-ai/cordis'
import type { Agent } from '@deepseek-ai/dsh-agent'
import { scopeTarget } from '@deepseek-ai/dsh-scope'
import * as ScopeInvariant from '@deepseek-ai/dsh-scope/invariant'
import InvariantService from '@deepseek-ai/dsh-invariants'
import InvariantRegistry from '@deepseek-ai/dsh-invariants'
async function setup(): Promise<Context> {
const ctx = new Context()
await ctx.plugin(InvariantService)
await ctx.plugin(InvariantRegistry)
await ctx.plugin(ScopeInvariant)
return ctx
}
packages/core/scope/tsconfig.json
+1 -1
View File
@@ -15,7 +15,7 @@
"path": "../../../vendor/cordis"
},
{
"path": "../../support/invariants"
"path": "../../runtime-diagnostics/invariants"
}
]
}
packages/core/session/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 packages/core/session/README.md
README.md: 57569e9c0dbfa7cb696e3a561a9ff108c2ac981f
README.zh.md: d255e6fa48ef23b89c4d89cd3a0bf260d2858fc6
README.md: 02aae21d71101e626bf2d2ead0bfd5d155723165
README.zh.md: 2da8c5db8fe25d55faafdd6d44ea9090dd232576
packages/core/session/README.md
+2 -2
View File
@@ -70,7 +70,7 @@ A `user/message` stores the complete `UserMessage` directly, including the ident
The generated [persistence log event catalog](../../../docs/persistence-catalog.md) enumerates each append-only event type with its payload, surface badge, and declaration site. Token accounting reads per-step `assistant/chunk { type: 'usage' }` records and treats `assistant/message.usage` as the committed-step fallback when no usage chunk exists; failed model-request attempts have no assistant message. Each `assistant/message` records the provider, model, and optional replay state.
Merge-extensible via `SessionEventMap` — a plugin declaration-merges its own types (the compaction seam's `compact/*`, bounded recovery's non-surface `llm/retry`, the hook bridges' `hook/*`); merged members appear in the same catalog. A plugin owns the relational invariant for its merged events, including whether a log-only event may appear between turns. A producer that requires durability appends through `Session` and then awaits `ctx.sessions.flush(session)` without fabricating an execution turn.
Merge-extensible via `SessionEventMap` — a plugin declaration-merges its own types (the compaction seam's `compaction/*`, bounded recovery's non-surface `llm/retry`, the hook bridges' `hook/*`); merged members appear in the same catalog. A plugin owns the relational invariant for its merged events, including whether a log-only event may appear between turns. A producer that requires durability appends through `Session` and then awaits `ctx.sessions.flush(session)` without fabricating an execution turn.
Also defines `TurnEndReasonMap`, the merge-extensible `kind`-tagged sum type for turn endings. `turn/start` carries only the turn number; the following entered `user/message` batch records its input, while `llm/retry` records request recovery.
@@ -90,7 +90,7 @@ Every `SessionEvent` carries three optional top-level fields (structural metadat
- Persistence plugins: subscribe to `session/event` (write-behind) and drain on `session/flush` (awaited) and fiber dispose. A durable backend reads the log and reloads it into a live session; the metadata contract (`SessionHeader`, `session.header`) is what such a backend stores beside the log.
- Replay/fork: `create(id, { seed })` validates and freezes a contiguous current-format log and rebuilds its surface; request headers require provider/model, and assistant messages require provider/model provenance. Persistence owns read compatibility before constructing this current-format seed. `fork(source, boundary?, childSessionId?)` selects a completed-turn prefix and records lineage.
- Compaction: `dsh-compact-basic` appends a `user/message` replacement for summary checkpoints, while `dsh-compact-tool-result-prune` appends a content-only `tool/result` replacement. Tool-pairing boundary policy and its cache belong to the [`dsh-compact` seam](../../compact/compact/README.md), while this package owns ordered surface membership, replacement validation, and `replaceGeneration`.
- Compaction: `dsh-compaction-basic` appends a `user/message` replacement for summary checkpoints, while `dsh-compaction-tool-result-pruner` appends a content-only `tool/result` replacement. Tool-pairing boundary policy and its cache belong to the [`dsh-compaction` seam](../../compaction/compaction/README.md), while this package owns ordered surface membership, replacement validation, and `replaceGeneration`.
## Model Experience
packages/core/session/README.zh.md
+2 -2
View File
@@ -70,7 +70,7 @@
生成的[持久化日志事件目录](../../../docs/persistence-catalog.md)逐成员列举仅追加日志的事件类型、载荷、surface 标记与声明位置。Token 记账读取每个步骤的 `assistant/chunk { type: 'usage' }` 记录；如果没有用量分片，则将 `assistant/message.usage` 作为已提交步骤的后备。失败的模型请求尝试没有 assistant 消息。每条 `assistant/message` 都会记录提供方、模型和可选回放状态。
`SessionEventMap` 可通过合并扩展：插件使用声明合并添加自身类型（压缩 seam 的 `compact/*`、有界恢复的非 surface `llm/retry`、钩子桥接层的 `hook/*`）；合并成员会出现在同一目录中。插件拥有其合并事件的关系不变量，包括是否允许纯日志事件出现在轮次之间。需要持久性的生产方通过 `Session` 追加，再等待 `ctx.sessions.flush(session)`，无需虚构一个执行轮次。
`SessionEventMap` 可通过合并扩展：插件使用声明合并添加自身类型（压缩 seam 的 `compaction/*`、有界恢复的非 surface `llm/retry`、钩子桥接层的 `hook/*`）；合并成员会出现在同一目录中。插件拥有其合并事件的关系不变量，包括是否允许纯日志事件出现在轮次之间。需要持久性的生产方通过 `Session` 追加，再等待 `ctx.sessions.flush(session)`，无需虚构一个执行轮次。
此包还定义 `TurnEndReasonMap`，即用于轮次结束、可合并扩展且以 `kind` 为标签的和类型。`turn/start` 只携带轮次编号；随后已进入的 `user/message` 批次记录其输入，`llm/retry` 则记录请求恢复。
@@ -90,7 +90,7 @@
- 持久化插件：订阅 `session/event`（延后写入），并在 `session/flush`（受等待）及 fiber dispose（资源释放）时排空。持久后端读取日志并重新加载到实时会话；这类后端会把元数据约定（`SessionHeader`、`session.header`）与日志一同存储。
- 回放／fork：`create(id, { seed })` 校验并冻结连续的当前格式日志，再重建 surface；请求头必须包含提供方／模型，assistant 消息必须包含提供方／模型溯源信息。持久化层在构造该当前格式 seed 前负责读取兼容性处理。`fork(source, boundary?, childSessionId?)` 选择已完成轮次前缀并记录谱系。
- 压缩：`dsh-compact-basic` 为摘要检查点追加一个替换用 `user/message`，而 `dsh-compact-tool-result-prune` 追加仅修改内容的 `tool/result` 替换。工具配对边界策略及其缓存归 [`dsh-compact` seam](../../compact/compact/README.md) 所有；此包拥有有序 surface 成员关系、替换校验与 `replaceGeneration`。
- 压缩：`dsh-compaction-basic` 为摘要检查点追加一个替换用 `user/message`，而 `dsh-compaction-tool-result-pruner` 追加仅修改内容的 `tool/result` 替换。工具配对边界策略及其缓存归 [`dsh-compaction` seam](../../compaction/compaction/README.md) 所有；此包拥有有序 surface 成员关系、替换校验与 `replaceGeneration`。
## 模型体验
packages/core/session/package.json
+3 -3
View File
@@ -1,7 +1,7 @@
{
"name": "@deepseek-ai/dsh-session",
"description": "Event-sourced session store for the DeepSeek Harness",
"version": "0.0.1-rc.2",
"version": "0.0.1-rc.5",
"publishConfig": {
"access": "restricted"
},
@@ -45,7 +45,7 @@
"@deepseek-ai/dsh-invariants": "workspace:^",
"@deepseek-ai/dsh-llm": "workspace:^",
"@deepseek-ai/dsh-scope": "workspace:^",
"@deepseek-ai/dsh-type-meta": "workspace:^",
"@deepseek-ai/dsh-typert-protocol": "workspace:^",
"@deepseek-ai/cordis": "workspace:^"
},
"devDependencies": {
@@ -53,7 +53,7 @@
"@deepseek-ai/dsh-invariants": "workspace:^",
"@deepseek-ai/dsh-llm": "workspace:^",
"@deepseek-ai/dsh-scope": "workspace:^",
"@deepseek-ai/dsh-type-meta": "workspace:^",
"@deepseek-ai/dsh-typert-protocol": "workspace:^",
"@deepseek-ai/dsh-typert-registry": "workspace:^",
"@deepseek-ai/cordis": "workspace:^"
}
packages/core/session/src/index.ts
+5 -5
View File
@@ -13,7 +13,7 @@ import { scopeOf, scopeTarget } from '@deepseek-ai/dsh-scope'
import type { Scoped } from '@deepseek-ai/dsh-scope'
import type { Message } from '@deepseek-ai/dsh-llm'
import { SESSION_FORMAT_VERSION, SessionId } from './types.ts'
import type { TypeRTLookup } from '@deepseek-ai/dsh-type-meta'
import type { TypertLookup } from '@deepseek-ai/dsh-typert-protocol'
import type { CreateSessionOptions, EpochHeader, PrepareSessionOptions, RequestContext, SessionEvent, SessionEventMap, SessionEventType, SessionHeader, SurfaceIntent, SurfaceEventType } from './types.ts'
import { snapshotJsonValue } from './json.ts'
import { deriveEventMessage, SurfaceManager } from './surface.ts'
@@ -86,9 +86,9 @@ declare module '@deepseek-ai/cordis' {
}
}
declare module '@deepseek-ai/dsh-type-meta' {
interface TypeRTLookupMap {
session: TypeRTLookup<Session, SessionId>
declare module '@deepseek-ai/dsh-typert-protocol' {
interface TypertLookupMap {
session: TypertLookup<Session, SessionId>
}
}
@@ -1010,7 +1010,7 @@ export class SessionStore extends Service {
* Dispatch the awaited `session/flush` durability checkpoint for `session`,
* with the carrier captured at {@link enter}. THE flush entry point: the
* store owns the carrier, so callers (the checkpoint policy's per-request
* barrier, goal-session's idle checkpoint, teardown drains, and consumers
* barrier, goal-round-driver's idle checkpoint, teardown drains, and consumers
* that flush themselves before reading storage) must come through here
* rather than dispatch a raw `ctx.parallel('session/flush', …)` — one owner,
* one spelling, and the scoped-dispatch invariant can pin it.
packages/core/session/src/known-event-types.ts
+4 -4
View File
@@ -26,10 +26,10 @@ export const KNOWN_SESSION_EVENT_TYPES: ReadonlySet<string> = new Set([
'assistant/message',
'command/done',
'command/run',
'compact/end',
'compact/prune',
'compact/start',
'compact/summary',
'compaction/end',
'compaction/prune',
'compaction/start',
'compaction/summary',
'feedback/record',
'goal/change',
'hook/invoked',
packages/core/session/src/surface.ts
+1 -1
View File
@@ -88,7 +88,7 @@ export function deriveEventMessage(event: SessionEvent): Message | null {
// Ordinary prompts and injected context project in user role: the event's
// model-facing content stays verbatim. Do NOT re-add per-type framing
// (e.g. `<context>`) here: framing is caller-owned — a producer bakes it
// into `content`, as workspace-context does with `<system-reminder>` — or,
// into `content`, as agent-instructions does with `<system-reminder>` — or,
// if reintroduced, must be driven by the event `meta` map and a dedicated
// renderer, keeping this projection a verbatim pass-through. See the
// deferred design note in
packages/core/session/src/types.ts
+2 -2
View File
@@ -322,8 +322,8 @@ export interface SessionEventMap {
* companion deliberately constrains nothing here, so a plugin appending one
* would silently classify every live bracket before it as seed history.
*
* An owner of a standalone open/close bracket (`compact/start` …
* `compact/end`) reads it because seed history and live work are otherwise
* An owner of a standalone open/close bracket (`compaction/start` …
* `compaction/end`) reads it because seed history and live work are otherwise
* byte-identical: an unmatched opening marker before this event belongs to
* an ended lifecycle, whatever ended it. NOT a liveness signal about other
* writers — a concurrently live session holds its own boundary elsewhere,
packages/core/session/tests/fork.spec.ts
+1 -1
View File
@@ -7,7 +7,7 @@ import type { SessionEvent, TurnEndReason } from '@deepseek-ai/dsh-session'
declare module '@deepseek-ai/dsh-session/types' {
interface SessionEventMap {
'test/log-only': { value: string }
/** Stands in for a plugin's open/close bracket (`compact/start`). */
/** Stands in for a plugin's open/close bracket (`compaction/start`). */
'test/bracket-open': { id: string }
}
}
packages/core/session/tests/invariant.spec.ts
+3 -3
View File
@@ -4,12 +4,12 @@ import { createScope, scopeTarget } from '@deepseek-ai/dsh-scope'
import { createUserMessage, CallId, createMessage, createToolResultMessage, freezeMessage } from '@deepseek-ai/dsh-llm'
import SessionStore, { SessionId, TOOL_NOT_STARTED } from '@deepseek-ai/dsh-session'
import * as SessionInvariant from '@deepseek-ai/dsh-session/invariant'
import InvariantService, { InvariantError } from '@deepseek-ai/dsh-invariants'
import InvariantRegistry, { InvariantError } from '@deepseek-ai/dsh-invariants'
async function setup(): Promise<{ ctx: Context; fiber: Awaited<ReturnType<Context['plugin']>> }> {
const ctx = new Context()
await ctx.plugin(SessionStore)
await ctx.plugin(InvariantService)
await ctx.plugin(InvariantRegistry)
const fiber = await ctx.plugin(SessionInvariant)
return { ctx, fiber }
}
@@ -18,7 +18,7 @@ describe('session-log invariants', () => {
it('keeps registration global when the companion is mounted under a scope', async () => {
const ctx = new Context()
await ctx.plugin(SessionStore)
await ctx.plugin(InvariantService)
await ctx.plugin(InvariantRegistry)
let scopedCtx!: Context
await ctx.plugin(Object.assign((inner: Context) => {
scopedCtx = createScope(inner, {}).ctx
packages/core/session/tests/session.spec.ts
+2 -2
View File
@@ -104,13 +104,13 @@ describe('Session', () => {
const session = Session.create(SessionId('s2-raw'))
const message = createUserMessage({
content: [{ type: 'text', text: '<system-reminder>Additional instructions from: pkg/AGENTS.md</system-reminder>' }],
source: { kind: 'plugin', plugin: 'workspace-context' },
source: { kind: 'plugin', plugin: 'agent-instructions' },
})
session.append('user/message', message, { surfaceOp: 'append' })
expect(session.deriveMessages()).toEqual([message])
const event = session.events[0]
expect(event?.type === 'user/message' && event.data.source).toEqual({ kind: 'plugin', plugin: 'workspace-context' })
expect(event?.type === 'user/message' && event.data.source).toEqual({ kind: 'plugin', plugin: 'agent-instructions' })
})
it('replays identically from a seeded event log', () => {
packages/core/session/tests/typert.spec.ts
+1 -1
View File
@@ -3,7 +3,7 @@ import { Context } from '@deepseek-ai/cordis'
import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
import TypertRegistry from '@deepseek-ai/dsh-typert-registry'
describe('Session TypeRT provider', () => {
describe('Session Typert provider', () => {
it('contributes live Session lookup in either service load order', async () => {
const ctx = new Context()
const sessionFiber = ctx.plugin(SessionStore)
packages/core/session/tsconfig.json
+2 -2
View File
@@ -24,10 +24,10 @@
"path": "../../core/scope"
},
{
"path": "../../support/invariants"
"path": "../../runtime-diagnostics/invariants"
},
{
"path": "../../typert/type-meta"
"path": "../../typert/protocol"
}
]
}
packages/core/system-prompt/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 packages/core/system-prompt/README.md
README.md: 6d0b43322ea0ccf4dddef404c4c862e014819696
README.zh.md: 08da218ef2fe07ffa63f246dff5382474070c4d9
README.md: d750a507e628e7609af542227e4528d4d4934ce8
README.zh.md: 36ee94349b63660ed52eedf7ba098334a6db07fb
packages/core/system-prompt/README.md
+4 -4
View File
@@ -8,7 +8,7 @@ System prompt assembly registry. Plugins contribute ordered sections, tool schem
| Key | Default | Meaning |
|---|---|---|
| `includeHarnessIdentity` | `true` | Include the fixed `You are an AI agent powered by the DeepSeek Harness SDK.` order-−100 opener. Set false only when a compatibility deployment owns the complete system prompt. |
| `includeHarnessIdentity` | `true` | Include the fixed `You are an AI agent powered by DeepSeek Harness.` order-−100 opener. Set false only when a compatibility deployment owns the complete system prompt. |
| `includeRuntimeContext` | `true` | Include ordered dynamic contexts in assembly. When false, context providers are not evaluated and contexts added by `system-prompt/assemble` listeners are discarded after the waterfall; other services and their enforcement remain active. |
| `persona` | `''` | The global deployment-persona default: the ONE config-authored prompt fragment, rendered as the order-0 `deployment:persona` section unless an agent-scoped contribution shadows it. A template — complete `{{…}}` groups are interpreted strictly against the registered variables (the shipped loop registers `{{model}}`/`{{cwd}}`), with no escape syntax for literal braces yet. Empty ⇒ the section is dropped at render. |
| `toolOrder` | — | Explicit model-facing tool order, as a list of `ToolSchema.name`s with one `'<unlisted-tools>'` rest entry (`TOOL_ORDER_REST`): listed tools take their listed position, unlisted tools land at the rest entry in lexicographic name order. Absent ⇒ plain lexicographic name order. Applied to the collected tools BEFORE the `system-prompt/assemble` waterfall — like the sections' `order` sort, it canonicalizes what the registry contributed (registration order is a plugin-load artifact), and a waterfall listener that mutates the list owns the determinism of what it emits. Misconfiguration fails loud: a list without exactly one rest entry, or with duplicates, throws at load; a listed name with no registered tool rejects every `assemble()`; a tool provider returning the reserved rest-entry name also rejects. Under the shipped loop the turn fails before any model request. Why a central list and not per-plugin weights: [Explicit model-facing tool order](../../../.agents/notes/implemented/feature/2026-07-06-explicit-tool-order.md). |
@@ -26,7 +26,7 @@ System prompt assembly registry. Plugins contribute ordered sections, tool schem
### Live events
`system-prompt/assemble` is authoritative for ordinary sections; a complete section is the final prompt constraint applied after the waterfall. Listeners that replace entries must preserve any active Code Mode or structured-output protocol. Use [`ToolRegistry.restrict()`](../tools/README.md) when filtering must stay aligned across presentation, lookup, and execution. Registry-change notifications are unfiltered. The generated region of [system-prompt.md](../../../docs/subsystems/system-prompt.md#cordis-surface) owns signatures and dispatch contracts.
`system-prompt/assemble` is authoritative for ordinary sections; a complete section is the final prompt constraint applied after the waterfall. Listeners that replace entries must preserve any active Code Mode or structured-output protocol. Use [`ToolRuntime.restrict()`](../tools/README.md) when filtering must stay aligned across presentation, lookup, and execution. Registry-change notifications are unfiltered. The generated region of [system-prompt.md](../../../docs/subsystems/system-prompt.md#cordis-surface) owns signatures and dispatch contracts.
### Key types
@@ -41,7 +41,7 @@ Merge-extensible: plugins can declare extra fields on `PromptAssembly` and `Asse
- Section providers: tool packages own their cross-call guidance (`tool:bash`, `tool:read`, …); this plugin owns `harness:identity` and `deployment:persona`.
- Variable providers: the agent loop registers `model` and `cwd`; any plugin can register the facts it owns (a future `date`, git state, …).
- Tool schema providers: `ToolRegistry` registers itself as a tool provider automatically.
- Tool schema providers: `ToolRuntime` registers itself as a tool provider automatically.
- The [`system-prompt/assemble` waterfall](#live-events): cooperatively mutate or replace the assembly per caller before any complete-section constraint is enforced.
Design rationale: [the prompt-variables Agent Note](../../../.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md).
@@ -57,7 +57,7 @@ By default every assembly starts with the harness identity below, then the confi
##### Harness identity
```markdown
You are an AI agent powered by the DeepSeek Harness SDK.
You are an AI agent powered by DeepSeek Harness.
```
#### Token effect
packages/core/system-prompt/README.zh.md
+4 -4
View File
@@ -8,7 +8,7 @@
| 键 | 默认值 | 含义 |
|---|---|---|
| `includeHarnessIdentity` | `true` | 是否包含顺序为 −100 的固定开场白 `You are an AI agent powered by the DeepSeek Harness SDK.`。仅当兼容部署拥有完整系统提示词时设为 false。 |
| `includeHarnessIdentity` | `true` | 是否包含顺序为 −100 的固定开场白 `You are an AI agent powered by DeepSeek Harness.`。仅当兼容部署拥有完整系统提示词时设为 false。 |
| `includeRuntimeContext` | `true` | 是否在组装中包含有序动态上下文。设为 false 时不会求值上下文提供方，并会在 waterfall 后丢弃 `system-prompt/assemble` 监听器添加的上下文；其他服务及其强制机制仍然生效。 |
| `persona` | `''` | 全局部署 persona 默认值：唯一由配置提供的提示词片段，渲染为顺序为 0 的 `deployment:persona` 段，除非 agent 作用域的贡献将其遮蔽。它是模板，完整的 `{{…}}` 组会严格按已注册变量解释（随附循环注册 `{{model}}`/`{{cwd}}`），目前没有表达字面量花括号的转义语法。为空 ⇒ 渲染时删除该段。 |
| `toolOrder` | 无 | 显式的面向模型工具顺序：一个 `ToolSchema.name` 列表，包含一个 `'<unlisted-tools>'` 其余项（`TOOL_ORDER_REST`）。已列工具占据列出的位置；未列工具按名称字典序落在其余项位置。缺席 ⇒ 直接按名称字典序排列。在 `system-prompt/assemble` waterfall（瀑布式事件）之前应用于已收集工具；与段的 `order` 排序一样，它会规范化注册表贡献的内容（注册顺序是插件加载产物），而修改列表的 waterfall 监听器拥有其输出的确定性。配置错误会明确失败：列表没有恰好一个其余项或存在重复项，会在加载时抛出；已列名称没有对应已注册工具，会使每次 `assemble()` 被拒绝；工具提供方返回保留的其余项名称也会被拒绝。在随附循环下，轮次会在任何模型请求前失败。为何采用中心列表而非每插件权重，见[显式面向模型工具顺序](../../../.agents/notes/implemented/feature/2026-07-06-explicit-tool-order.md)。 |
@@ -28,7 +28,7 @@
### 实时事件
`system-prompt/assemble` 对普通段落具有权威性；complete 段是在 waterfall 之后应用的最终提示词约束。替换条目的监听器必须保留任何已启用的 Code Mode 或结构化输出协议。筛选需要在呈现、查找与执行之间保持一致时，应使用 [`ToolRegistry.restrict()`](../tools/README.md)。注册表变更通知不经过筛选。[system-prompt.md](../../../docs/subsystems/system-prompt.md#cordis-surface) 的生成区块拥有签名与分发约定。
`system-prompt/assemble` 对普通段落具有权威性；complete 段是在 waterfall 之后应用的最终提示词约束。替换条目的监听器必须保留任何已启用的 Code Mode 或结构化输出协议。筛选需要在呈现、查找与执行之间保持一致时，应使用 [`ToolRuntime.restrict()`](../tools/README.md)。注册表变更通知不经过筛选。[system-prompt.md](../../../docs/subsystems/system-prompt.md#cordis-surface) 的生成区块拥有签名与分发约定。
### 关键类型
@@ -43,7 +43,7 @@
- 段提供方：工具包拥有跨调用引导（`tool:bash`、`tool:read` 等）；此插件拥有 `harness:identity` 与 `deployment:persona`。
- 变量提供方：agent loop（智能体循环）注册 `model` 与 `cwd`；任何插件都可以注册自己拥有的事实（未来的 `date`、git 状态等）。
- 工具 schema 提供方：`ToolRegistry` 自动将自身注册为工具提供方。
- 工具 schema 提供方：`ToolRuntime` 自动将自身注册为工具提供方。
- [`system-prompt/assemble` waterfall](#live-events)：按调用方协作式修改或替换组装结果，之后再实施 complete 段约束。
设计原理：[提示词变量 Agent Note](../../../.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md)。
@@ -59,7 +59,7 @@
##### harness 身份
```markdown
You are an AI agent powered by the DeepSeek Harness SDK.
You are an AI agent powered by DeepSeek Harness.
```
#### Token 影响
packages/core/system-prompt/package.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"name": "@deepseek-ai/dsh-system-prompt",
"description": "System prompt assembly registry for the DeepSeek Harness",
"version": "0.0.1-rc.2",
"version": "0.0.1-rc.5",
"publishConfig": {
"access": "restricted"
},
packages/core/system-prompt/src/index.ts
+1 -1
View File
@@ -358,7 +358,7 @@ export class SystemPrompt extends Service {
this.section({
name: 'harness:identity',
order: -100,
text: 'You are an AI agent powered by the DeepSeek Harness SDK.',
text: 'You are an AI agent powered by DeepSeek Harness.',
})
}
this.section({
packages/core/system-prompt/tests/invariant.spec.ts
+2 -2
View File
@@ -2,11 +2,11 @@ import { describe, expect, it } from 'vitest'
import { Context } from '@deepseek-ai/cordis'
import type { PromptAssembly } from '@deepseek-ai/dsh-system-prompt'
import * as SystemPromptInvariant from '@deepseek-ai/dsh-system-prompt/invariant'
import InvariantService from '@deepseek-ai/dsh-invariants'
import InvariantRegistry from '@deepseek-ai/dsh-invariants'
async function setup(): Promise<Context> {
const ctx = new Context()
await ctx.plugin(InvariantService)
await ctx.plugin(InvariantRegistry)
await ctx.plugin(SystemPromptInvariant)
return ctx
}
packages/core/system-prompt/tests/system-prompt.spec.ts
+6 -6
View File
@@ -9,7 +9,7 @@ import SystemPrompt, { AssembleContext, PromptAssembly, renderContextSnapshot, r
* their own sections; the built-ins' behavior is pinned by its own describe.
*/
const BUILT_IN = ['harness:identity', 'deployment:persona']
const IDENTITY = 'You are an AI agent powered by the DeepSeek Harness SDK.'
const IDENTITY = 'You are an AI agent powered by DeepSeek Harness.'
function contributed(assembly: PromptAssembly): PromptAssembly['sections'] {
return assembly.sections.filter(section => !BUILT_IN.includes(section.name))
}
@@ -18,14 +18,14 @@ describe('SystemPrompt', () => {
describe('built-in sections', () => {
it('registers the harness identity and the configured deployment persona', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt, { persona: 'You are DeepSeek Harness SDK.' })
await ctx.plugin(SystemPrompt, { persona: 'You are DeepSeek Harness.' })
const assembly = await ctx.systemPrompt.assemble()
expect(assembly.sections.map(s => s.name)).toEqual([
'harness:identity',
'deployment:persona',
])
expect(renderPrompt(assembly)).toBe(`${IDENTITY}\n\nYou are DeepSeek Harness SDK.`)
expect(renderPrompt(assembly)).toBe(`${IDENTITY}\n\nYou are DeepSeek Harness.`)
// The names are reserved by the plugin — one owner per section.
expect(() => ctx.systemPrompt.section({ name: 'deployment:persona', order: 0, text: 'imposter' }))
.toThrow('prompt section "deployment:persona" is already registered')
@@ -79,7 +79,7 @@ describe('SystemPrompt', () => {
it('assembles sections in order with context-resolved text and collected tools', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt, { persona: 'You are DeepSeek Harness SDK.' })
await ctx.plugin(SystemPrompt, { persona: 'You are DeepSeek Harness.' })
ctx.systemPrompt.section({ name: 'cwd', order: 20, text: () => 'cwd: /tmp' })
ctx.systemPrompt.section({ name: 'rules', order: 10, text: 'Be precise.' })
@@ -89,14 +89,14 @@ describe('SystemPrompt', () => {
const assembly = await ctx.systemPrompt.assemble()
expect(assembly.sections.map(s => s.name)).toEqual(['harness:identity', 'deployment:persona', 'rules', 'cwd'])
expect(assembly.sections.map(s => s.text)).toEqual([IDENTITY, 'You are DeepSeek Harness SDK.', 'Be precise.', 'cwd: /tmp'])
expect(assembly.sections.map(s => s.text)).toEqual([IDENTITY, 'You are DeepSeek Harness.', 'Be precise.', 'cwd: /tmp'])
expect(assembly.contexts).toEqual([
{ name: 'earlier', text: 'context 1' },
{ name: 'later', text: 'context 2' },
])
expect(assembly.tools).toEqual([{ name: 'echo', description: 'echo back', parameters: {} }])
expect(assembly.variables).toEqual({})
expect(renderPrompt(assembly)).toBe(`${IDENTITY}\n\nYou are DeepSeek Harness SDK.\n\nBe precise.\n\ncwd: /tmp`)
expect(renderPrompt(assembly)).toBe(`${IDENTITY}\n\nYou are DeepSeek Harness.\n\nBe precise.\n\ncwd: /tmp`)
expect(renderContextSnapshot(assembly)).toBe('Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\ncontext 1\n\ncontext 2')
})
packages/core/system-prompt/tsconfig.json
+1 -1
View File
@@ -24,7 +24,7 @@
"path": "../../core/scope"
},
{
"path": "../../support/invariants"
"path": "../../runtime-diagnostics/invariants"
}
]
}
packages/core/tools/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 packages/core/tools/README.md
README.md: 44eb25b79436a75f08406102fc1e3734e59b1001
README.zh.md: a47e7c54b0cd3fc3c5146a9a8be4d1406f9ef8aa
README.md: 120931c9f4b4f5e1c39c3ddd8da4b8cae42dbe69
README.zh.md: 7a8ca63a607d2fdc841382ace3f7adcbfd721d76
packages/core/tools/README.md
+4 -4
View File
@@ -4,7 +4,7 @@ English | [中文](README.zh.md)
Tool registry and execution pipeline. Tool plugins register their schemas and executors; the agent loop executes each call through `tools/pre-execute` (the extensible allow/deny gate) → monotonic registered guards → `tools/execute` (an around-dispatch wrapper for timeout/retry/metrics plugins) → `tools/post-execute` (inspect/replace the result, attach context) → the definition-owned `finalizeContent` boundary → the observe-only `tools/result` notification. The registry also owns HOW its tools are presented to the model — its `mode` config selects native function calling, [Code Mode](#code-mode), or both, and one agent shadows that default for itself with `presentAs`.
## Service: `ToolRegistry` (ctx key: `tools`)
## Service: `ToolRuntime` (ctx key: `tools`)
### Config
@@ -13,7 +13,7 @@ tools:
mode: native # native (default) | code | both
```
`native` contributes visible tools as function definitions. `code` contributes the reserved `run_code` transport, the generated `tools:sdk` section, and the `tools:code-only` rule stating that only `run_code` may be called directly — which the executor then enforces, resolving a model-direct call naming any other tool to `UNKNOWN_TOOL` before policy runs; `both` contributes both forms and states no such rule, because its native calls do execute. This is the default for agents that declare none of their own — an agent preset selects its own with [`dsh-agent-tool-mode`](../agent-tool-mode/README.md). The reserved transport cannot be registered, shadowed, restricted, or removed, and its name is reserved whatever the configured mode, because any agent may select a code mode. Non-native modes require a `ctx.codeRuntime` whose `language` has a registered SDK renderer — TypeScript ships via [`dsh-code-runtime-worker`](../../code-runtime/code-runtime-worker/README.md); a Python renderer is built in and drives any runtime that reports `language: 'python'` (a first-party `dsh-code-runtime-python` backend is delivered separately). A runtime language with no renderer fails prompt assembly loudly, and a `systemPrompt.toolOrder` entry for a tool the mode does not contribute rejects prompt assembly. A `system-prompt/assemble` listener may replace the registry's contributions; its returned assembly is authoritative, so that listener owns preserving a usable Code Mode protocol.
`native` contributes visible tools as function definitions. `code` contributes the reserved `run_code` transport, the generated `tools:sdk` section, and the `tools:code-only` rule stating that only `run_code` may be called directly — which the executor then enforces, resolving a model-direct call naming any other tool to `UNKNOWN_TOOL` before policy runs; `both` contributes both forms and states no such rule, because its native calls do execute. This is the default for agents that declare none of their own — an agent preset selects its own with [`dsh-agent-tool-presentation`](../agent-tool-presentation/README.md). The reserved transport cannot be registered, shadowed, restricted, or removed, and its name is reserved whatever the configured mode, because any agent may select a code mode. Non-native modes require a `ctx.codeRuntime` whose `language` has a registered SDK renderer — TypeScript ships via [`dsh-code-runtime-worker-thread`](../../code-runtime/code-runtime-worker-thread/README.md); a Python renderer is built in and drives any runtime that reports `language: 'python'` (a first-party `dsh-code-runtime-python` backend is delivered separately). A runtime language with no renderer fails prompt assembly loudly, and a `systemPrompt.toolOrder` entry for a tool the mode does not contribute rejects prompt assembly. A `system-prompt/assemble` listener may replace the registry's contributions; its returned assembly is authoritative, so that listener owns preserving a usable Code Mode protocol.
### Public API
@@ -148,7 +148,7 @@ Prefix-stable while visible definitions and their order are unchanged. Registrat
#### What the model sees
Code Mode exposes the generated [`run_code` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tools), the SDK instructions below, and the generated exact SDK block for the loaded runtime's language (the TypeScript `declare const tools` block, or the Python `tools` declaration). `both` exposes normal schemas and this Code Mode API. Under `code` the prompt also carries the `tools:code-only` rule, ordered ahead of the per-tool guidance band so the model reads which tools it may call before it reads what each one is for; `both` renders it empty. The instructions and SDK block match the loaded runtime's language; the TypeScript version (via [`dsh-code-runtime-worker`](../../code-runtime/code-runtime-worker/README.md)) is shown below, and the Python version (for any runtime reporting `language: 'python'`) has the same operations and types in Python syntax (`await tools.name(args)`, subscript access for exotic names, `print(...)` and top-level `return`).
Code Mode exposes the generated [`run_code` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tools), the SDK instructions below, and the generated exact SDK block for the loaded runtime's language (the TypeScript `declare const tools` block, or the Python `tools` declaration). `both` exposes normal schemas and this Code Mode API. Under `code` the prompt also carries the `tools:code-only` rule, ordered ahead of the per-tool guidance band so the model reads which tools it may call before it reads what each one is for; `both` renders it empty. The instructions and SDK block match the loaded runtime's language; the TypeScript version (via [`dsh-code-runtime-worker-thread`](../../code-runtime/code-runtime-worker-thread/README.md)) is shown below, and the Python version (for any runtime reporting `language: 'python'`) has the same operations and types in Python syntax (`await tools.name(args)`, subscript access for exotic names, `print(...)` and top-level `return`).
##### Code Mode SDK instructions
@@ -192,7 +192,7 @@ Append-only; newly visible content follows the reusable request prefix and does
- **Concurrency policy is not an event gate** — `executionMode()` reads the resolved tool definition directly; plugins can only declare a classifier on definitions they own.
- **`tools/pre-execute` deliberately cannot rewrite `exec.arguments`** — logged and rendered args would desync from what ran; the rewrite design is [a proposed Agent Note](../../../.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.md).
- **Caller-defined subagent and workflow structured outputs remain object-rooted** — this is a consumer-level guard; the shared schema vocabulary and tool outputs support every JSON root.
- **`timeoutMs` on a definition is declarative only** — the registry never enforces deadlines; enforcement requires the `@deepseek-ai/dsh-timeout-policy` wrapper.
- **`timeoutMs` on a definition is declarative only** — the registry never enforces deadlines; enforcement requires the `@deepseek-ai/dsh-tool-call-timeout-policy` wrapper.
- **Code Mode's SDK language follows the one loaded runtime, and a presentation is per agent rather than per tool** — `mode: code`/`both` rejects prompt assembly unless `ctx.codeRuntime.language` has a registered SDK renderer (TypeScript or Python); scoped restrictions/shadows and `presentAs` choose each agent's visible bindings and their form, but within one agent no tool can be native-only while another is code-only.
- **Code Mode intermediate values are execution-local and unbounded by bytes** — the canonical typed values cannot be reconstructed from session replay and may exhaust process or worker memory; only the outer `run_code` output has the worker's configurable hard cap. The durable log copy of each sub-call IS bounded: the `tools/code-dispatch-log` waterfall lets the spill policy replace an oversized `tool/code-dispatch` content with a preview + locator ([rationale](../../../.agents/notes/implemented/feature/2026-07-26-code-dispatch-log-spill.md)).
- **`run_code` state is fresh per run** — a persistent REPL-style kernel is rejected for the MVP (cross-call state would be invisible to the log); see [the Code Mode Agent Note](../../../.agents/notes/implemented/feature/2026-06-15-code-mode.md).
packages/core/tools/README.zh.md
+4 -4
View File
@@ -4,7 +4,7 @@
工具注册表与执行流水线。工具插件注册各自的 schema 和执行器；agent loop（智能体循环）依次让每次调用经过 `tools/pre-execute`（可扩展的允许／拒绝门禁）→ 已注册的单调守卫 → `tools/execute`（供超时／重试／指标插件使用的环绕分发包装层）→ `tools/post-execute`（检查／替换结果、附加上下文）→ 定义自身的 `finalizeContent` 终结步骤 → 仅观测的 `tools/result` 通知。注册表还负责决定如何向模型呈现其工具：`mode` 配置可以选择原生 Function Calling（函数调用）、[Code Mode](#code-mode)，或同时选择两者；单个 agent 可用 `presentAs` 为自己遮蔽该默认值。
## 服务：`ToolRegistry`（ctx 键：`tools`）
## 服务：`ToolRuntime`（ctx 键：`tools`）
### 配置
@@ -13,7 +13,7 @@ tools:
mode: native # native (default) | code | both
```
`native` 以函数定义的形式贡献可见工具。`code` 贡献保留的 `run_code` 传输、生成的 `tools:sdk` 段，以及声明「只有 `run_code` 可被直接调用」的 `tools:code-only` 规则——执行器随后强制该规则，模型直呼其他任何工具名都会在策略运行之前解析为 `UNKNOWN_TOOL`；`both` 同时贡献两种形式，且不声明该规则，因为它的原生调用确实会执行。这是「未作声明的 agent」的默认值——agent preset 用 [`dsh-agent-tool-mode`](../agent-tool-mode/README.md) 为自己选择。不能注册、遮蔽、限制或移除该保留传输，且无论配置何种模式，该名称都是保留的，因为任何 agent 都可能选择 code 模式。非原生模式要求所加载 `ctx.codeRuntime` 的 `language` 有已注册的 SDK 渲染器——TypeScript 经 [`dsh-code-runtime-worker`](../../code-runtime/code-runtime-worker/README.md) 交付；Python 渲染器内置，驱动任何报告 `language: 'python'` 的运行时（第一方 `dsh-code-runtime-python` 后端另行交付）。没有渲染器的运行时语言会导致提示词组装明确失败；如果 `systemPrompt.toolOrder` 条目指向当前模式未贡献的工具，系统会拒绝组装提示词。`system-prompt/assemble` 监听器可以替换注册表贡献；它返回的组装结果具有权威性，因此该监听器负责保留可用的 Code Mode 协议。
`native` 以函数定义的形式贡献可见工具。`code` 贡献保留的 `run_code` 传输、生成的 `tools:sdk` 段，以及声明「只有 `run_code` 可被直接调用」的 `tools:code-only` 规则——执行器随后强制该规则，模型直呼其他任何工具名都会在策略运行之前解析为 `UNKNOWN_TOOL`；`both` 同时贡献两种形式，且不声明该规则，因为它的原生调用确实会执行。这是「未作声明的 agent」的默认值——agent preset 用 [`dsh-agent-tool-presentation`](../agent-tool-presentation/README.md) 为自己选择。不能注册、遮蔽、限制或移除该保留传输，且无论配置何种模式，该名称都是保留的，因为任何 agent 都可能选择 code 模式。非原生模式要求所加载 `ctx.codeRuntime` 的 `language` 有已注册的 SDK 渲染器——TypeScript 经 [`dsh-code-runtime-worker-thread`](../../code-runtime/code-runtime-worker-thread/README.md) 交付；Python 渲染器内置，驱动任何报告 `language: 'python'` 的运行时（第一方 `dsh-code-runtime-python` 后端另行交付）。没有渲染器的运行时语言会导致提示词组装明确失败；如果 `systemPrompt.toolOrder` 条目指向当前模式未贡献的工具，系统会拒绝组装提示词。`system-prompt/assemble` 监听器可以替换注册表贡献；它返回的组装结果具有权威性，因此该监听器负责保留可用的 Code Mode 协议。
### 公开 API
@@ -148,7 +148,7 @@ agent loop 将连续的 `parallel` 调用归入有界滚动池，并把每个 `e
#### 模型看到的内容
Code Mode 会公开生成的 [`run_code` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tools)、下方 SDK 说明，以及按所加载运行时语言生成的精确 SDK 块（TypeScript 的 `declare const tools` 块，或 Python 的 `tools` 声明）。`both` 会同时公开普通 schema 与此 Code Mode API。在 `code` 下，提示词还会带上 `tools:code-only` 规则，其顺序排在逐工具指导段之前，让模型先读到「可以调用哪些工具」再读「每个工具做什么」；`both` 下它渲染为空。说明与 SDK 块随所加载运行时的语言切换；下方展示 TypeScript 版本（经 [`dsh-code-runtime-worker`](../../code-runtime/code-runtime-worker/README.md)），Python 版本（用于任何报告 `language: 'python'` 的运行时）以 Python 语法提供相同操作和类型（`await tools.name(args)`、特殊名称用下标访问、`print(...)` 与顶层 `return`）。
Code Mode 会公开生成的 [`run_code` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tools)、下方 SDK 说明，以及按所加载运行时语言生成的精确 SDK 块（TypeScript 的 `declare const tools` 块，或 Python 的 `tools` 声明）。`both` 会同时公开普通 schema 与此 Code Mode API。在 `code` 下，提示词还会带上 `tools:code-only` 规则，其顺序排在逐工具指导段之前，让模型先读到「可以调用哪些工具」再读「每个工具做什么」；`both` 下它渲染为空。说明与 SDK 块随所加载运行时的语言切换；下方展示 TypeScript 版本（经 [`dsh-code-runtime-worker-thread`](../../code-runtime/code-runtime-worker-thread/README.md)），Python 版本（用于任何报告 `language: 'python'` 的运行时）以 Python 语法提供相同操作和类型（`await tools.name(args)`、特殊名称用下标访问、`print(...)` 与顶层 `return`）。
##### Code Mode SDK 说明
@@ -192,7 +192,7 @@ The available tools:
- **并发策略不是事件门禁**：`executionMode()` 直接读取已解析的工具定义；插件只能在自身拥有的定义上声明分类器。
- **`tools/pre-execute` 有意不允许改写 `exec.arguments`**：否则日志记录和呈现的参数会与实际运行内容失去同步；改写设计记录在[拟议的 Agent Note](../../../.agents/notes/proposed/feature/2026-06-30-pre-tool-input-rewrite.md)中。
- **调用方定义的 subagent 与工作流结构化输出仍要求对象根**：这是消费方层面的守卫；共享 schema 词汇和工具输出支持任意 JSON 根。
- **定义上的 `timeoutMs` 仅为声明**：注册表绝不会强制执行截止时间；要强制执行，必须使用 `@deepseek-ai/dsh-timeout-policy` 包装层。
- **定义上的 `timeoutMs` 仅为声明**：注册表绝不会强制执行截止时间；要强制执行，必须使用 `@deepseek-ai/dsh-tool-call-timeout-policy` 包装层。
- **Code Mode 的 SDK 语言跟随已加载的那个运行时，且呈现方式按 agent 而非按工具**：`mode: code`/`both` 会拒绝组装提示词，除非 `ctx.codeRuntime.language` 有已注册的 SDK 渲染器（TypeScript 或 Python）；作用域限制／遮蔽与 `presentAs` 会选择每个 agent 的可见绑定及其形态，但在同一个 agent 内不能让一个工具仅使用 Native，而另一个仅使用 Code。
- **Code Mode 中间值只存在于执行局部，且没有字节上限**：这些规范的类型化值无法从会话回放重建，并可能耗尽进程或 worker 内存；只有外层 `run_code` 输出受 worker 可配置的硬上限约束。每个子调用的持久日志副本则确实有上限：`tools/code-dispatch-log` waterfall 允许 spill 策略把过大的 `tool/code-dispatch` 内容替换为预览加定位符（[原理](../../../.agents/notes/implemented/feature/2026-07-26-code-dispatch-log-spill.md)）。
- **每次运行都会获得全新的 `run_code` 状态**：MVP 不采用持久 REPL 风格内核（跨调用状态不会出现在日志中）；参见 [Code Mode Agent Note](../../../.agents/notes/implemented/feature/2026-06-15-code-mode.md)。
packages/core/tools/package.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"name": "@deepseek-ai/dsh-tools",
"description": "Tool registry and execution pipeline for the DeepSeek Harness",
"version": "0.0.1-rc.2",
"version": "0.0.1-rc.5",
"publishConfig": {
"access": "restricted"
},
packages/core/tools/src/code-mode.ts
+4 -4
View File
@@ -12,8 +12,8 @@ import type { CodeBindingFunction, CodeRunResult, CodeRuntime } from '@deepseek-
import { snapshotJsonValue } from '@deepseek-ai/dsh-session'
import type { JsonValue } from '@deepseek-ai/dsh-session'
import { defineTool, parameterSchemaSpecToJsonSchema } from './schema.ts'
import { TOOL_REGISTRY_SCHEDULER } from './index.ts'
import type { CodeDispatchLog, ToolDefinition, ToolExecutionResult, ToolRegistry, ToolRunContext } from './index.ts'
import { TOOL_RUNTIME_SCHEDULER } from './index.ts'
import type { CodeDispatchLog, ToolDefinition, ToolExecutionResult, ToolRuntime, ToolRunContext } from './index.ts'
import type {} from './types.ts'
/** The model-facing name of the Code Mode tool. */
@@ -289,7 +289,7 @@ export interface RunCodeBridgeOptions {
* @param options - the registry-private capabilities described above.
* @returns the registry-ready definition.
*/
export function createRunCodeTool(registry: ToolRegistry, options: RunCodeBridgeOptions): ToolDefinition {
export function createRunCodeTool(registry: ToolRuntime, options: RunCodeBridgeOptions): ToolDefinition {
const { requireRuntime, peekRuntime, maxParallel, shapeDispatchLog } = options
const definition = defineTool({
name: RUN_CODE_NAME,
@@ -476,7 +476,7 @@ export function createRunCodeTool(registry: ToolRegistry, options: RunCodeBridge
signal: runController.signal,
}
type DispatchOutcome = { isError: true; message: string } | { isError: false; value: JsonValue }
const scheduler = registry[TOOL_REGISTRY_SCHEDULER]
const scheduler = registry[TOOL_RUNTIME_SCHEDULER]
const outcome = await new Promise<DispatchOutcome>((resolve, reject) => {
// Set by the dispatch stage (or start() for a pre-settled result): what commit() finalizes in submission order.
let parked:
packages/core/tools/src/index.ts
+19 -19
View File
@@ -136,7 +136,7 @@ export type {
declare module '@deepseek-ai/cordis' {
interface Context {
tools: ToolRegistry
tools: ToolRuntime
}
interface Events {
@@ -149,7 +149,7 @@ declare module '@deepseek-ai/cordis' {
* @param exec - the pending call (name, parsed arguments, caller agent).
* @mode waterfall
*/
'tools/pre-execute'(this: Scoped<ToolRegistry>, exec: ToolExecution, next: () => Promise<PreToolDecision>): Promise<PreToolDecision>
'tools/pre-execute'(this: Scoped<ToolRuntime>, exec: ToolExecution, next: () => Promise<PreToolDecision>): Promise<PreToolDecision>
/**
* Around-dispatch waterfall for timeout, retry, or metrics. `next()` returns
* a normalized result; wrappers may change only `exec.signal`, while call
@@ -160,7 +160,7 @@ declare module '@deepseek-ai/cordis' {
* @param exec - the allowed call about to dispatch (name, parsed arguments, caller agent, signal).
* @mode waterfall
*/
'tools/execute'(this: Scoped<ToolRegistry>, exec: ToolDispatchExecution, next: () => Promise<ToolExecutionResult>): Promise<ToolExecutionResult>
'tools/execute'(this: Scoped<ToolRuntime>, exec: ToolDispatchExecution, next: () => Promise<ToolExecutionResult>): Promise<ToolExecutionResult>
/**
* Accept, replace, enrich, or block a normalized dispatch result. `next()`
* accepts it unchanged; thrown tools still reach this waterfall as errors. Async
@@ -172,7 +172,7 @@ declare module '@deepseek-ai/cordis' {
* @param result - the dispatch outcome a listener may accept, replace, or block.
* @mode waterfall
*/
'tools/post-execute'(this: Scoped<ToolRegistry>, exec: ToolExecution, result: Readonly<ToolExecutionResult>, next: () => Promise<PostToolDecision>): Promise<PostToolDecision>
'tools/post-execute'(this: Scoped<ToolRuntime>, exec: ToolExecution, result: Readonly<ToolExecutionResult>, next: () => Promise<PostToolDecision>): Promise<PostToolDecision>
/**
* Allow a listener to replace content in the DURABLE LOG COPY of one
* `run_code` sub-dispatch outcome before the bridge appends its
@@ -186,7 +186,7 @@ declare module '@deepseek-ai/cordis' {
* @param dispatch - the parent execution, sub-call identity, and the settled content to log.
* @mode waterfall
*/
'tools/code-dispatch-log'(this: Scoped<ToolRegistry>, dispatch: CodeDispatchLog, next: () => Promise<ContentBlock[]>): Promise<ContentBlock[]>
'tools/code-dispatch-log'(this: Scoped<ToolRuntime>, dispatch: CodeDispatchLog, next: () => Promise<ContentBlock[]>): Promise<ContentBlock[]>
/**
* Observe the frozen, lossless-JSON final outcome. Listener failures are contained.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): keyed by `exec.agent`.
@@ -194,7 +194,7 @@ declare module '@deepseek-ai/cordis' {
* @param result - a deep-frozen snapshot of the final returned result.
* @mode emit
*/
'tools/result'(this: Scoped<ToolRegistry>, exec: Readonly<ToolExecution>, result: Readonly<ToolExecutionResult>): undefined
'tools/result'(this: Scoped<ToolRuntime>, exec: Readonly<ToolExecution>, result: Readonly<ToolExecutionResult>): undefined
/**
* A tool was registered or unregistered, or a scoped restriction changed
* (the available tool set changed — possibly for one scope only). An
@@ -247,7 +247,7 @@ export interface ToolDefinition extends ToolSchema {
finalizeContent?(exec: Readonly<ToolExecution>, result: Readonly<ToolExecutionResult>): ContentBlock[] | undefined
/**
* Cooperative tool-call timeout budget in milliseconds. Omit for no deadline.
* Enforced by `@deepseek-ai/dsh-timeout-policy` (a `tools/execute` wrapper); it
* Enforced by `@deepseek-ai/dsh-tool-call-timeout-policy` (a `tools/execute` wrapper); it
* is NEVER sent to the model — `schemas()` whitelists only name/description/
* parameters. Declaring it asserts this tool forwards `exec.signal` to a
* cooperative implementation that can reach quiescence when the signal aborts.
@@ -307,7 +307,7 @@ declare const toolExecutionTokenBrand: unique symbol
export type ToolExecutionToken = symbol & { readonly [toolExecutionTokenBrand]: true }
/**
* Caller-supplied description of one tool call. {@link ToolRegistry.execute}
* Caller-supplied description of one tool call. {@link ToolRuntime.execute}
* adds the registry-owned token to form a pipeline {@link ToolExecution};
* callers do not choose that token.
*/
@@ -330,7 +330,7 @@ export interface ToolExecutionInput {
* The token also marks the call as a transport sub-dispatch rather than a
* model-direct call: under `mode: 'code'`, only calls WITH a parent may
* execute a native tool name — a model-direct call (no parent) is denied as
* `UNKNOWN_TOOL` before the policy pipeline. See {@link ToolRegistry.execute}.
* `UNKNOWN_TOOL` before the policy pipeline. See {@link ToolRuntime.execute}.
*/
readonly parent?: ToolExecutionToken
/** Required caller-owned cancellation for this invocation. */
@@ -435,7 +435,7 @@ export type ScheduledToolPreparation =
/**
* Scheduler-only dispatch result. A `post-result` still receives post-execute;
* a `final-result` already matches {@link ToolRegistry.execute} failure semantics.
* a `final-result` already matches {@link ToolRuntime.execute} failure semantics.
* @internal
*/
export type ScheduledToolDispatch =
@@ -444,11 +444,11 @@ export type ScheduledToolDispatch =
/**
* Symbol-keyed scheduler view that keeps pre/post policy ordered while
* overlapping dispatch. Ordinary callers use {@link ToolRegistry.execute};
* overlapping dispatch. Ordinary callers use {@link ToolRuntime.execute};
* this is not a plugin extension point.
* @internal
*/
export interface ToolRegistryScheduler {
export interface ToolRuntimeScheduler {
/** Materialize input, run the ordered pre-execute/guard gate, and decide what stage follows. */
prepare(exec: ToolExecutionInput): Promise<ScheduledToolPreparation>
/** Run only the around-dispatch/body stage. */
@@ -463,7 +463,7 @@ export interface ToolRegistryScheduler {
* Scheduler entry point omitted from the generated named service API.
* @internal
*/
export const TOOL_REGISTRY_SCHEDULER: unique symbol = Symbol('@deepseek-ai/dsh-tools.scheduler')
export const TOOL_RUNTIME_SCHEDULER: unique symbol = Symbol('@deepseek-ai/dsh-tools.scheduler')
/** Canonical error code for cancellation after a tool body was invoked. */
export const TOOL_ABORTED = 'ABORTED'
@@ -784,7 +784,7 @@ function resolveMaxParallelSubCalls(value: number | undefined): number {
* Tool registry and execution pipeline. Scoped registrations shadow globals;
* one visibility resolver feeds presentation, lookup, and dispatch.
*/
export class ToolRegistry extends Service {
export class ToolRuntime extends Service {
static inject = ['systemPrompt']
static Config: z<Config> = z.object({
@@ -793,7 +793,7 @@ export class ToolRegistry extends Service {
})
/** Internal staged view consumed by `dsh-agent-loop`'s parallel scheduler. */
readonly [TOOL_REGISTRY_SCHEDULER]: ToolRegistryScheduler = {
readonly [TOOL_RUNTIME_SCHEDULER]: ToolRuntimeScheduler = {
prepare: exec => this.prepareScheduledExecution(exec),
dispatch: exec => this.dispatchScheduledExecution(exec),
finalize: (exec, result) => this.finalizeScheduledExecution(exec, result),
@@ -948,7 +948,7 @@ export class ToolRegistry extends Service {
if (scopeOf(ctx) === undefined) {
throw new Error('tools.presentAs() requires a scoped context (agent.ctx): a context-global presentation is the `mode` config field on the tools row')
}
const dispose = ctx.effect(function* (this: ToolRegistry) {
const dispose = ctx.effect(function* (this: ToolRuntime) {
yield this.layers.effect(
ctx,
(layer) => {
@@ -1019,7 +1019,7 @@ export class ToolRegistry extends Service {
private requireCodeRuntime(mode: ToolPresentationMode): CodeRuntime {
const runtime = this.ctx.get('codeRuntime')
if (!runtime) {
throw new Error(`dsh-tools: mode "${mode}" requires a code runtime — load a ctx.codeRuntime implementation (e.g. @deepseek-ai/dsh-code-runtime-worker) or set tools mode to "native"`)
throw new Error(`dsh-tools: mode "${mode}" requires a code runtime — load a ctx.codeRuntime implementation (e.g. @deepseek-ai/dsh-code-runtime-worker-thread) or set tools mode to "native"`)
}
if (!Object.hasOwn(SDK_RENDERERS, runtime.language)) {
const known = Object.keys(SDK_RENDERERS).map(name => JSON.stringify(name)).join(', ')
@@ -1314,7 +1314,7 @@ export class ToolRegistry extends Service {
*
* Resolved through {@link modeFor}, NOT `defaultMode`: an agent given `code`
* by an agent preset under a native deployment is the composition
* `dsh-agent-tool-mode` exists for, and reading the deployment default would
* `dsh-agent-tool-presentation` exists for, and reading the deployment default would
* leave exactly that agent uncollapsed — announcing one surface while
* executing another, which is the bypass this collapse closes.
* @param name - the tool name as registered.
@@ -1943,4 +1943,4 @@ function toolAbortedBeforeDispatchResult(prior?: ToolExecutionResult): ToolExecu
}
}
export default ToolRegistry
export default ToolRuntime
packages/core/tools/src/presentation.ts
+1 -1
View File
@@ -61,7 +61,7 @@ export interface GenericCallView {
kind?: ToolCallKind
/**
* The salient input to show in a detail/expanded view (e.g. a background
* task id). Omit to show nothing; a string renders as-is, an object as pretty
* job id). Omit to show nothing; a string renders as-is, an object as pretty
* JSON. NOT the full raw args object unless that is genuinely what a reader wants.
*/
rawInput?: unknown
packages/core/tools/tests/code-mode.spec.ts
+10 -10
View File
@@ -6,7 +6,7 @@ import type { Scope } from '@deepseek-ai/dsh-scope'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import { CodeRuntime } from '@deepseek-ai/dsh-code-runtime'
import type { CodeRunRequest, CodeRunResult } from '@deepseek-ai/dsh-code-runtime'
import ToolRegistry, { CodeRunFailedError, RUN_CODE_NAME, TOOL_ABORTED_BEFORE_DISPATCH, defineContentToolFixture, defineTool } from '@deepseek-ai/dsh-tools'
import ToolRuntime, { CodeRunFailedError, RUN_CODE_NAME, TOOL_ABORTED_BEFORE_DISPATCH, defineContentToolFixture, defineTool } from '@deepseek-ai/dsh-tools'
import type { Config, JsonSchemaNode, PostToolDecision, ToolExecutionResult } from '@deepseek-ai/dsh-tools'
import type { Agent } from '@deepseek-ai/dsh-agent'
import { Session, SessionId } from '@deepseek-ai/dsh-session'
@@ -50,7 +50,7 @@ interface SetupOptions {
async function setup(options: SetupOptions = {}) {
const ctx = new Context()
await ctx.plugin(SystemPrompt, { ...options.toolOrder ? { toolOrder: options.toolOrder } : {} })
await ctx.plugin(ToolRegistry, { mode: options.mode ?? 'code', ...options.maxParallelSubCalls !== undefined ? { maxParallelSubCalls: options.maxParallelSubCalls } : {} })
await ctx.plugin(ToolRuntime, { mode: options.mode ?? 'code', ...options.maxParallelSubCalls !== undefined ? { maxParallelSubCalls: options.maxParallelSubCalls } : {} })
let runtime: FakeRuntime | undefined
if (options.runtime !== false) {
await ctx.plugin(FakeRuntime, options.runtime ?? {})
@@ -456,7 +456,7 @@ describe('mode-aware wire contribution', () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt, {})
await ctx.plugin(FakeRuntime, {})
const fiber = await ctx.plugin(ToolRegistry, { mode: 'code' })
const fiber = await ctx.plugin(ToolRuntime, { mode: 'code' })
expect(ctx.tools.get(RUN_CODE_NAME)).toBeDefined()
await fiber.dispose()
const assembly = await ctx.systemPrompt.assemble()
@@ -1216,7 +1216,7 @@ describe('the run_code dispatch bridge', () => {
it('executing run_code under a missing runtime is a structured isError, not a crash', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt, {})
await ctx.plugin(ToolRegistry, { mode: 'code' })
await ctx.plugin(ToolRuntime, { mode: 'code' })
const result = await runCode(ctx, 'program')
expect(result.isError).toBe(true)
expect((result.content[0] as { text: string }).text).toContain('requires a code runtime')
@@ -1568,21 +1568,21 @@ describe('the run_code dispatch bridge', () => {
it('direct construction rejects a non-positive parallel sub-call cap at load', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt, {})
expect(() => new ToolRegistry(ctx, { mode: 'code', maxParallelSubCalls: 0 }))
expect(() => new ToolRuntime(ctx, { mode: 'code', maxParallelSubCalls: 0 }))
.toThrow('maxParallelSubCalls must be a positive integer')
})
it('direct construction in code mode defaults the parallel sub-call cap', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt, {})
const registry = new ToolRegistry(ctx, { mode: 'code' })
const registry = new ToolRuntime(ctx, { mode: 'code' })
expect(registry.get(RUN_CODE_NAME)).toBeDefined()
})
it('defaults to native mode under direct construction with no config', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt, {})
const registry = new ToolRegistry(ctx)
const registry = new ToolRuntime(ctx)
expect(registry.get(RUN_CODE_NAME)).toBeUndefined()
const assembly = await ctx.systemPrompt.assemble()
expect(assembly.sections.some(section => section.name === 'tools:sdk')).toBe(false)
@@ -1590,7 +1590,7 @@ describe('the run_code dispatch bridge', () => {
it('denies a model-direct native-tool call under code mode as UNKNOWN_TOOL', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt, {})
const registry = new ToolRegistry(ctx, { mode: 'code' })
const registry = new ToolRuntime(ctx, { mode: 'code' })
registerEcho(ctx, 'write')
const result = await registry.execute({
signal: testToolSignal,
@@ -1610,7 +1610,7 @@ describe('the run_code dispatch bridge', () => {
it('routes a pre-aborted collapsed call through ABORTED_BEFORE_DISPATCH', async () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt, {})
const registry = new ToolRegistry(ctx, { mode: 'code' })
const registry = new ToolRuntime(ctx, { mode: 'code' })
registerEcho(ctx, 'write')
const aborted = new AbortController()
aborted.abort()
@@ -1681,7 +1681,7 @@ describe('per-agent presentation', () => {
// `native` here, so a collapse predicate reading it instead of this
// scope's effective mode would announce [run_code] and still execute the
// native call — the bypass, reopened for exactly the preset composition
// `dsh-agent-tool-mode` produces.
// `dsh-agent-tool-presentation` produces.
expect(ctx.tools.executionMode({
signal: testToolSignal,
callId: CallId('preset-coded-schedule'),
packages/core/tools/tests/execution-mode.spec.ts
+3 -3
View File
@@ -4,7 +4,7 @@ import { describe, expect, expectTypeOf, it } from 'vitest'
import { Context } from '@deepseek-ai/cordis'
import { CallId } from '@deepseek-ai/dsh-llm'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry, {
import ToolRuntime, {
defineContentToolFixture,
type ToolDefinition,
type ToolExecutionInput,
@@ -16,7 +16,7 @@ const testToolSignal = new AbortController().signal
async function setup() {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
return ctx
}
@@ -24,7 +24,7 @@ function exec(name: string, args: unknown): ToolExecutionInput {
return { signal: testToolSignal, callId: CallId('c1'), name, arguments: args }
}
describe('ToolRegistry.executionMode', () => {
describe('ToolRuntime.executionMode', () => {
it('returns parallel only for an explicit true classifier', async () => {
const ctx = await setup()
ctx.tools.register(defineContentToolFixture({
packages/core/tools/tests/gen-tool-catalog.spec.ts
+27 -2
View File
@@ -5,9 +5,11 @@
import { describe, expect, it } from 'vitest'
import {
assertManifestComplete,
assertToolsHarvested,
collectToolCatalog,
render,
type ToolCatalog,
type ToolPackage,
} from '../../../../scripts/gen-tool-catalog.ts'
/** JSON Schema shape enough to reach the values AST extraction can't. */
@@ -23,7 +25,7 @@ describe('gen-tool-catalog collectToolCatalog', () => {
it('boots every shipped tool package and harvests its model-facing schemas', async () => {
const catalog = await collectToolCatalog()
const names = catalog.flatMap(entry => entry.schemas.map(s => s.name)).sort()
expect(names).toEqual(['ask_user_question', 'bash', 'bash', 'cordis_inspect', 'cordis_mount', 'cordis_unmount', 'create_goal', 'edit', 'exit_plan_mode', 'get_goal', 'glob', 'grep', 'interrupt_agent', 'list_agents', 'lsp', 'pwsh', 'ralph', 'read', 'read_image', 'report', 'run_code', 'schedule_create', 'schedule_delete', 'schedule_list', 'send_message', 'session_event_read', 'session_event_search', 'session_event_trace', 'session_search', 'session_trace', 'skill', 'str_replace_editor', 'subagent', 'task_kill', 'task_list', 'task_output', 'terminal_close', 'terminal_list', 'terminal_open', 'terminal_read', 'terminal_send', 'terminal_signal', 'todo_write', 'update_goal', 'web_fetch', 'web_search', 'workflow', 'write'])
expect(names).toEqual(['ask_user_question', 'bash', 'bash', 'cordis_define', 'cordis_inspect_list', 'cordis_inspect_query', 'cordis_inspect_self', 'cordis_run', 'cordis_stop', 'cordis_undefine', 'create_goal', 'edit', 'exit_plan_mode', 'get_goal', 'glob', 'grep', 'interrupt_agent', 'job_kill', 'job_list', 'job_output', 'list_agents', 'lsp', 'pwsh', 'ralph', 'read', 'read_image', 'report', 'run_code', 'schedule_create', 'schedule_delete', 'schedule_list', 'send_message', 'session_event_read', 'session_event_search', 'session_event_trace', 'session_search', 'session_trace', 'skill', 'str_replace_editor', 'subagent', 'terminal_close', 'terminal_list', 'terminal_open', 'terminal_read', 'terminal_send', 'terminal_signal', 'todo_write', 'update_goal', 'web_fetch', 'web_search', 'workflow', 'write'])
// Every tool carries a JSON-Schema `parameters` object (what the model sees).
for (const entry of catalog) {
for (const schema of entry.schemas) {
@@ -46,7 +48,7 @@ describe('gen-tool-catalog collectToolCatalog', () => {
it('attributes each harvested tool with its registering plugin source', async () => {
const catalog = await collectToolCatalog()
const bash = catalog.find(entry => entry.pkg === '@deepseek-ai/dsh-tool-bash')
expect(bash?.sources.bash).toBe('packages/bash/tool-bash/src/index.ts')
expect(bash?.sources.bash).toBe('packages/shell/tool-bash/src/index.ts')
const control = catalog.find(entry => entry.pkg === '@deepseek-ai/dsh-tool-subagent-control')
expect(control?.sources).toEqual({
interrupt_agent: 'packages/subagent/tool-subagent-control/src/index.ts',
@@ -91,6 +93,29 @@ describe('gen-tool-catalog assertManifestComplete', () => {
})
})
describe('gen-tool-catalog assertToolsHarvested', () => {
const entry: ToolPackage = {
pkg: '@deepseek-ai/dsh-tool-demo',
dir: 'tool-demo',
source: 'packages/demo/tool-demo/src/index.ts',
requires: ['ctx.tools', 'ctx.somethingUnmounted'],
writes: ['tool/result'],
mount: () => Promise.resolve(),
}
it('accepts a boot that registered at least one tool', () => {
expect(() => { assertToolsHarvested(entry, 1) }).not.toThrow()
})
it('throws, naming the package and its requirements, when a boot registers nothing', () => {
// The failure this guards is silent by construction: the package is in the
// manifest, its plugin merely stays PENDING on an unmounted service, and the
// catalog would ship without its tools while every gate stays green.
expect(() => { assertToolsHarvested(entry, 0) }).toThrow(/@deepseek-ai\/dsh-tool-demo booted without registering a single tool/)
expect(() => { assertToolsHarvested(entry, 0) }).toThrow(/ctx.somethingUnmounted/)
})
})
describe('gen-tool-catalog render', () => {
it('emits a package heading, a tool heading, and a json schema fence', () => {
const catalog: ToolCatalog = [
packages/core/tools/tests/invariant.spec.ts
+4 -4
View File
@@ -5,14 +5,14 @@ import { CallId } from '@deepseek-ai/dsh-llm'
import SessionStore, { Session, SessionId } from '@deepseek-ai/dsh-session'
import type { ToolExecution, ToolExecutionResult, ToolExecutionToken } from '@deepseek-ai/dsh-tools'
import * as ToolsInvariant from '@deepseek-ai/dsh-tools/invariant'
import InvariantService from '@deepseek-ai/dsh-invariants'
import InvariantRegistry from '@deepseek-ai/dsh-invariants'
const testToolSignal = new AbortController().signal
async function setup(): Promise<Context> {
const ctx = new Context()
await ctx.plugin(SessionStore)
await ctx.plugin(InvariantService)
await ctx.plugin(InvariantRegistry)
await ctx.plugin(ToolsInvariant)
return ctx
}
@@ -219,7 +219,7 @@ describe('tool-pipeline invariants', () => {
content: [{ type: 'text', text: 'ok' }],
})
session.append('turn/end', { turn: 1, reason: { kind: 'completed' } })
await ctx.plugin(InvariantService)
await ctx.plugin(InvariantRegistry)
await expect(ctx.plugin(ToolsInvariant).then(() => undefined)).resolves.toBeUndefined()
})
@@ -233,7 +233,7 @@ describe('tool-pipeline invariants', () => {
name: 'echo',
arguments: {},
})
await ctx.plugin(InvariantService)
await ctx.plugin(InvariantRegistry)
await expect(ctx.plugin(ToolsInvariant).then(() => undefined)).rejects.toThrow(/outside any open turn/)
})
})
packages/core/tools/tests/scoped.spec.ts
+2 -2
View File
@@ -4,7 +4,7 @@ import type { Events } from '@deepseek-ai/cordis'
import { bindScopeParent, createScope } from '@deepseek-ai/dsh-scope'
import type { Scope } from '@deepseek-ai/dsh-scope'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry from '@deepseek-ai/dsh-tools'
import ToolRuntime from '@deepseek-ai/dsh-tools'
import type { PreToolDecision, ToolDefinition, ToolExecution, ToolExecutionInput, ToolExecutionToken } from '@deepseek-ai/dsh-tools'
import type { Agent } from '@deepseek-ai/dsh-agent'
@@ -17,7 +17,7 @@ const testToolSignal = new AbortController().signal
async function mount(): Promise<Context> {
const ctx = new Context()
await ctx.plugin(SystemPrompt, {})
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
return ctx
}
packages/core/tools/tests/tools.spec.ts
+4 -4
View File
@@ -4,7 +4,7 @@ import { createUserMessage, CallId, HarnessError, type ContentBlock } from '@de
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import type { Agent } from '@deepseek-ai/dsh-agent'
import ApprovalService, { type ApprovalOutcome, type ApprovalRequest } from '@deepseek-ai/dsh-user-approval'
import ToolRegistry, {
import ToolRuntime, {
defineContentToolFixture, defineTool, JsonSchemaError, parameterSchemaSpecToJsonSchema, validateArgs, ToolArgsError, ToolNotFoundError,
TOOL_ABORTED, TOOL_ABORTED_BEFORE_DISPATCH,
type InferArgs, type JsonValue, type ParameterSchemaSpec, type PreToolDecision, type PostToolDecision,
@@ -16,7 +16,7 @@ const testToolSignal = new AbortController().signal
async function setup() {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(ToolRuntime)
return ctx
}
@@ -33,7 +33,7 @@ const echoTool = defineTool({
},
})
describe('ToolRegistry', () => {
describe('ToolRuntime', () => {
it('registers tools, exposes schemas, and feeds the system-prompt assembly', async () => {
const ctx = await setup()
ctx.tools.register(echoTool)
@@ -2449,7 +2449,7 @@ describe('schema DSL optional and nested contracts', () => {
})
})
describe('ToolRegistry.get', () => {
describe('ToolRuntime.get', () => {
it('get() returns the registered tool definition', async () => {
const ctx = await setup()
ctx.tools.register(echoTool)
packages/core/tools/tsconfig.json
+1 -1
View File
@@ -36,7 +36,7 @@
"path": "../../interaction/user-approval"
},
{
"path": "../../support/invariants"
"path": "../../runtime-diagnostics/invariants"
}
]
}