Merge remote-tracking branch 'origin/master' into codex/rfc-subagent-background-tasks

# Conflicts:
#	docs/event-producer-consumer.md

packages/README.md

@@ -29,7 +29,7 @@ Packages live at `packages/<group>/<pkg>/`; groups are containers, while names r
 | [`session-persistence/`](session-persistence/README.md) | Persistence capability family: the seam + JSONL/SQLite backends | Product — stable surface |
 | [`session-query/`](session-query/README.md) | Session retrieval family: logical corpus, surface records, and bounded exact reads | Product — stable surface |
 | [`ui/`](ui/README.md) | Editor/client integration surfaces: ACP bridge, JSON-RPC SDK server, app packages, user-approval and user-interaction seams, ask-user tool | Product — stable surface |
-| [`support/`](support/README.md) | Dev/test/example infrastructure (invariants, replay adapter, subagent mock) | Support — lower compatibility expectations |
+| [`support/`](support/README.md) | Support infrastructure (invariants, replay, Loader smokes) | Support — lower compatibility expectations |
 | [`util/`](util/README.md) | Low-level zero-dependency utilities shared across groups (the `Branded<B>` primitive) | Support — small, stable, harness-dep-free |
 
 Groups distinguish product API from support infrastructure. New packages join an existing group; a new group updates its README and this table.

packages/cordis/tool-cordis/src/api-catalog.ts

@@ -395,18 +395,6 @@ export const EVENT_API: readonly EventApiEntry[] = [
     signature: '\'session/flush\'(this: Scoped<Session>, session: Session): Promise<void> | void',
     summary: 'Awaited parallel durability checkpoint: every listener runs and the caller awaits all of them, with no waterfall veto.',
   },
-  {
-    name: 'skill/provider-added',
-    mode: 'emit',
-    signature: '\'skill/provider-added\'(provider: SkillProvider): void',
-    summary: 'A skill provider became resolvable in the `ctx.skills` registry.',
-  },
-  {
-    name: 'skill/provider-removed',
-    mode: 'emit',
-    signature: '\'skill/provider-removed\'(name: string): void',
-    summary: 'A skill provider left the registry because its plugin fiber was disposed.',
-  },
   {
     name: 'subagent/end',
     mode: 'emit',
@@ -1019,7 +1007,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [
   },
   {
     name: 'ToolExecutionResult',
-    declaration: 'export interface ToolExecutionResult {\n    callId: CallId;\n    content: ContentBlock[];\n    isError: boolean;\n    error?: ToolErrorInfo;\n    additionalContext?: HookContext;\n    meta?: unknown;\n}',
+    declaration: 'export interface ToolExecutionResult {\n    content: ContentBlock[];\n    isError: boolean;\n    error?: ToolErrorInfo;\n    additionalContext?: HookContext;\n    meta?: unknown;\n}',
   },
   {
     name: 'ToolExecutionToken',

packages/core/agent-loop/src/loop.ts

@@ -578,7 +578,8 @@ async function runStep(
     })
     session.append('tool/result', {
       turn, step,
-      // Preserve transcript pairing even if a post-execute listener returns another id.
+      // Correlation comes from the immutable execution input; the result does
+      // not duplicate this authoritative transcript identity.
       callId: call.id,
       content: result.content,
       isError: result.isError,

packages/core/agent-loop/tests/contract-regressions.spec.ts

@@ -1043,8 +1043,7 @@ describe('tool result call identity', () => {
 
     // A post-execute listener transforms the result (accept-with-replacement).
     // The loop must still record the tool/result under the model's authoritative
-    // call.id (the loop ignores result.callId — which the registry always sets to
-    // exec.callId anyway — and uses call.id, the model-transcript id).
+    // call.id, which is the immutable identity carried by the execution input.
     ctx.on('tools/post-execute', (exec, _result) => {
       expect(exec.callId).toBe(CallId('c1')) // the loop passed the real id in
       return Promise.resolve({ kind: 'accept', content: [{ type: 'text', text: 'ok' }] })
@@ -1054,8 +1053,7 @@ describe('tool result call identity', () => {
     send(agent, 'use tool')
     await waitForIdle(ctx, agent)
 
-    // The logged tool/result.callId is the originating call.id, NOT the
-    // listener's wrong id.
+    // The logged tool/result.callId is the originating call.id.
     const resultEvent = [...agent.session.events].find(e => e.type === 'tool/result')
     expect(resultEvent?.type).toBe('tool/result')
     if (resultEvent?.type === 'tool/result') {

packages/core/system-prompt/src/index.ts

@@ -226,7 +226,7 @@ export class SystemPrompt extends Service {
   private scopedVariableProviders = new Map<ScopeKey, Map<string, (context: AssembleContext) => string | undefined>>()
   private readonly toolOrder: string[] | undefined
 
-  constructor(ctx: Context, public config: Config) {
+  constructor(ctx: Context, config: Config) {
     super(ctx, 'systemPrompt')
     this.toolOrder = validateToolOrder(config.toolOrder)
     // Keep harness-owned openers independent of the selected loop plugin.

packages/core/tools/README.md

@@ -36,7 +36,7 @@ The live registry pipeline has three transformable waterfalls followed by the ob
 - `ToolExecutionInput` — the caller-supplied call description: `{ callId, name, arguments, agent?, parent?, signal? }`; callers may pass an enclosing execution's opaque token as `parent` but never choose the new execution's own token.
 - `ToolExecutionToken` — a fresh branded `Symbol` assigned by the registry. It supports equality correlation only and never crosses a model, log, or worker boundary.
 - `ToolExecution` — the pipeline-owned call: immutable `{ token, callId, name, arguments, agent?, parent? }` identity plus optional operational `signal`, which an around wrapper may add, replace, remove, and restore. A nested call's `parent` is a `ToolExecutionToken`, not an execution object.
-- `ToolExecutionResult` — losslessly JSON-serializable outcome: `{ callId, content, isError, error?, additionalContext?, meta? }`. The registry materializes and freezes the complete post-policy value before final observation. On failure with a `HarnessError`, `error: { name, code }` carries the structured failure class alongside the model-facing text.
+- `ToolExecutionResult` — losslessly JSON-serializable outcome: `{ content, isError, error?, additionalContext?, meta? }`. Call identity stays on the immutable `ToolExecution` supplied alongside the result instead of being duplicated on the outcome. The registry materializes and freezes the complete post-policy value before final observation. On failure with a `HarnessError`, `error: { name, code }` carries the structured failure class alongside the model-facing text.
 - `PreToolDecision` — `{kind:'allow'}` | `{kind:'deny', reason}` | `{kind:'ask', reason?}`. Input rewrite is deliberately not offered; `ask` is serviced by [`ctx.approval`](../../ui/user-approval/README.md) when mounted and otherwise degrades to deny.
 - `PostToolDecision` — `{kind:'accept', content?, additionalContext?}` (keep the call successful, optionally replacing the model-facing content) | `{kind:'block', feedback, additionalContext?}` (turn it into an `isError` whose content is the corrective feedback). Output replacement is clean because `tool/result` is logged AFTER `execute()` returns.
 - `ToolGuard` — `(execution) => string | undefined`; the returned string is a final monotonic denial reason evaluated after the reorderable pre-execute waterfall and before dispatch.

packages/core/tools/src/index.ts

@@ -220,7 +220,7 @@ export interface ToolErrorInfo {
  * distinguish it from a tool body's own error.
  */
 export class ToolNotFoundError extends HarnessError {
-  constructor(public readonly toolName: string) {
+  constructor(toolName: string) {
     super(`unknown tool "${toolName}"`, 'UNKNOWN_TOOL')
     this.name = 'ToolNotFoundError'
   }
@@ -228,7 +228,6 @@ export class ToolNotFoundError extends HarnessError {
 
 /** The outcome of one tool call. */
 export interface ToolExecutionResult {
-  callId: CallId
   content: ContentBlock[]
   isError: boolean
   /**
@@ -704,7 +703,7 @@ export class ToolRegistry extends Service {
       }
     } catch (error: unknown) {
       execution = { ...base, arguments: undefined }
-      const result = this.materializeFinalResult(toolErrorResult(callId, error))
+      const result = this.materializeFinalResult(toolErrorResult(error))
       this.notifyResult(execution, result)
       return result
     }
@@ -714,7 +713,7 @@ export class ToolRegistry extends Service {
     } catch (error: unknown) {
       // Outer backstop: a throwing pre/post-execute listener, guard, or the
       // waterfall machinery becomes an isError result, never a turn failure.
-      result = this.materializeFinalResult(toolErrorResult(execution.callId, error))
+      result = this.materializeFinalResult(toolErrorResult(error))
     }
     this.notifyResult(execution, result)
     return result
@@ -739,7 +738,6 @@ export class ToolRegistry extends Service {
       // Every non-grant, including a failed/unavailable approval request, takes
       // the same deny path and still reaches post-policy plus result observers.
       const denied: ToolExecutionResult = {
-        callId: exec.callId,
         content: [{ type: 'text', text: `Error: ${denialReason}` }],
         isError: true,
       }
@@ -770,16 +768,12 @@ export class ToolRegistry extends Service {
           const returned = await tool.execute(exec.arguments, exec)
           const content = Array.isArray(returned) ? returned : returned.content
           const meta = Array.isArray(returned) ? undefined : returned.meta
-          return { callId: exec.callId, content, isError: false, ...meta !== undefined ? { meta } : {} }
+          return { content, isError: false, ...meta !== undefined ? { meta } : {} }
         } catch (error: unknown) {
-          return toolErrorResult(exec.callId, error)
+          return toolErrorResult(error)
         }
       },
     )
-    if (result.callId !== exec.callId) {
-      throw new TypeError(`tools/execute returned callId "${String(result.callId)}" for authoritative call "${exec.callId}"`)
-    }
-
     return await this.postExecute(exec, result)
   }
 
@@ -854,7 +848,6 @@ export class ToolRegistry extends Service {
     const additionalContext = decision.additionalContext
     if (decision.kind === 'block') {
       return {
-        callId: result.callId,
         content: decision.feedback,
         isError: true,
         ...additionalContext ? { additionalContext } : {},
@@ -883,10 +876,9 @@ function createExecutionToken(): ToolExecutionToken {
   return Symbol('dsh.tool.execution') as ToolExecutionToken
 }
 
-function toolErrorResult(callId: ToolExecution['callId'], error: unknown): ToolExecutionResult {
+function toolErrorResult(error: unknown): ToolExecutionResult {
   const info = errorInfo(error)
   return {
-    callId,
     content: [{ type: 'text', text: `Error: ${errorMessage(error)}` }],
     isError: true,
     ...info ? { error: info } : {},

packages/core/tools/tests/scoped.spec.ts

@@ -548,7 +548,6 @@ describe('scoped execution dispatch', () => {
 
     expect(reads).toBe(1)
     expect(result).toEqual({
-      callId: CallId('unstable-arguments'),
       content: [{ type: 'text', text: 'ran:t' }],
       isError: false,
     })
@@ -564,10 +563,9 @@ describe('scoped execution dispatch', () => {
     ctx.on('internal/dispatch', (mode, name) => {
       if (name === 'tools/result') dispatchModes.push(mode)
     })
-    ctx.on('tools/execute', async (exec, next) => {
+    ctx.on('tools/execute', async (_exec, next) => {
       await next()
       return {
-        callId: exec.callId,
         content: [{ type: 'text', text: 'outer failure' }],
         isError: true,
       }

packages/core/tools/tests/tools.spec.ts

@@ -80,7 +80,7 @@ describe('ToolRegistry', () => {
     const ctx = await setup()
     ctx.tools.register(echoTool)
     const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'echo', arguments: { text: 'hi' } })
-    expect(result).toEqual({ callId: CallId('c1'), content: [{ type: 'text', text: 'hi' }], isError: false })
+    expect(result).toEqual({ content: [{ type: 'text', text: 'hi' }], isError: false })
   })
 
   it('threads a tool-attached meta (object return form) onto the result', async () => {
@@ -94,7 +94,6 @@ describe('ToolRegistry', () => {
     })
     const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'meta-tool', arguments: {} })
     expect(result).toEqual({
-      callId: CallId('c1'),
       content: [{ type: 'text', text: 'ok' }],
       isError: false,
       meta: { diffs: [{ path: 'a', oldText: null, newText: 'x' }] },
@@ -111,7 +110,7 @@ describe('ToolRegistry', () => {
       },
     })
     const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'no-meta-tool', arguments: {} })
-    expect(result).toEqual({ callId: CallId('c1'), content: [{ type: 'text', text: 'ok' }], isError: false })
+    expect(result).toEqual({ content: [{ type: 'text', text: 'ok' }], isError: false })
     expect('meta' in result).toBe(false)
   })
 
@@ -178,13 +177,12 @@ describe('ToolRegistry', () => {
     })
   })
 
-  it('ToolNotFoundError carries the tool name and a stable code', async () => {
+  it('ToolNotFoundError carries a stable message and code', async () => {
     const { HarnessError } = await import('@deepseek-ai/dsh-llm')
     const err = new ToolNotFoundError('ghost')
     expect(err).toBeInstanceOf(HarnessError)
     expect(err.name).toBe('ToolNotFoundError')
     expect(err.code).toBe('UNKNOWN_TOOL')
-    expect(err.toolName).toBe('ghost')
     expect(err.message).toBe('unknown tool "ghost"')
   })
 
@@ -425,7 +423,7 @@ describe('ToolRegistry', () => {
     ctx.on('tools/post-execute', async (_exec, _result, next) => { order.push('post'); return next() })
 
     const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'traced', arguments: { text: 'hi' } })
-    expect(result).toEqual({ callId: CallId('c1'), content: [{ type: 'text', text: 'hi' }], isError: false })
+    expect(result).toEqual({ content: [{ type: 'text', text: 'hi' }], isError: false })
     // The around seam wraps dispatch; pre gates before it, post runs over its result.
     expect(order).toEqual(['pre', 'execute:before', 'dispatch', 'execute:after', 'post'])
   })
@@ -526,8 +524,8 @@ describe('ToolRegistry', () => {
       async execute() { dispatched = true; return [] },
     })
 
-    ctx.on('tools/execute', async (exec: ToolExecution, _next: () => Promise<ToolExecutionResult>): Promise<ToolExecutionResult> =>
-      ({ callId: exec.callId, content: [{ type: 'text', text: 'short-circuited' }], isError: false }))
+    ctx.on('tools/execute', async (_exec: ToolExecution, _next: () => Promise<ToolExecutionResult>): Promise<ToolExecutionResult> =>
+      ({ content: [{ type: 'text', text: 'short-circuited' }], isError: false }))
 
     const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'never-runs', arguments: {} })
     expect(dispatched).toBe(false) // returning without next() skips core dispatch
@@ -537,8 +535,7 @@ describe('ToolRegistry', () => {
   it('preserves additionalContext supplied by an around-dispatch result', async () => {
     const ctx = await setup()
     ctx.tools.register(echoTool)
-    ctx.on('tools/execute', async exec => ({
-      callId: exec.callId,
+    ctx.on('tools/execute', async () => ({
       content: [{ type: 'text', text: 'short-circuited with context' }],
       isError: false,
       additionalContext: {
@@ -556,20 +553,6 @@ describe('ToolRegistry', () => {
     })
   })
 
-  it('normalizes a tools/execute result with the wrong call id', async () => {
-    const ctx = await setup()
-    ctx.tools.register(echoTool)
-    ctx.on('tools/execute', async () => ({ callId: CallId('other'), content: [], isError: false }))
-
-    const result = await ctx.tools.execute({
-      callId: CallId('malformed-shape'), name: 'echo', arguments: {},
-    })
-    expect(result.isError).toBe(true)
-    expect(result.content[0]).toMatchObject({
-      text: 'Error: tools/execute returned callId "other" for authoritative call "malformed-shape"',
-    })
-  })
-
   it('returns an isError result when a tools/execute listener throws', async () => {
     const ctx = await setup()
     ctx.tools.register(echoTool)
@@ -577,7 +560,6 @@ describe('ToolRegistry', () => {
 
     const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'echo', arguments: { text: 'hi' } })
     expect(result).toEqual({
-      callId: CallId('c1'),
       content: [{ type: 'text', text: 'Error: wrapper broke' }],
       isError: true,
     })
@@ -593,7 +575,6 @@ describe('ToolRegistry', () => {
     const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'echo', arguments: { text: 'hi' } })
 
     expect(result).toEqual({
-      callId: CallId('c1'),
       content: [{ type: 'text', text: 'Error: permission hook broke' }],
       isError: true,
     })
@@ -609,7 +590,6 @@ describe('ToolRegistry', () => {
     const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'echo', arguments: { text: 'hi' } })
 
     expect(result).toEqual({
-      callId: CallId('c1'),
       content: [{ type: 'text', text: 'Error: post hook broke' }],
       isError: true,
     })
@@ -625,7 +605,6 @@ describe('ToolRegistry', () => {
     const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'echo', arguments: { text: 'hi' } })
 
     expect(result).toMatchObject({
-      callId: CallId('c1'),
       isError: true,
       error: { name: 'HarnessError', code: 'DENIED' },
     })
@@ -1254,7 +1233,7 @@ describe('defineTool validation (the runtime-validation RFC, part 1)', () => {
       },
     }))
     const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'reader', arguments: { path: '/x' } })
-    expect(result).toEqual({ callId: CallId('c1'), content: [{ type: 'text', text: 'read /x' }], isError: false })
+    expect(result).toEqual({ content: [{ type: 'text', text: 'read /x' }], isError: false })
   })
 
   it('ToolArgsError carries a stable code and the violation list', () => {

packages/fs/fs-local/README.md

@@ -19,7 +19,7 @@ await ctx.plugin(LocalFileSystem, { cwd: process.cwd() })
 - **`writeText`** — atomic: writes to a temp file opened exclusively (`wx`, `0o600`) inside a randomly-named private staging dir (`0o700`) next to the target, fsyncs, then renames over the target. An existing file's mode is preserved, while new files default to `0o600`. The `expected` guard is OPTIONAL: omitting it unconditionally creates-or-overwrites; `createIfAbsent` creates a missing target and rejects an existing one (`FS_NOT_OBSERVED`); `replaceIfVersion` replaces only at the observed version (a missing target or mismatch is `FS_STALE_VERSION`).
 - **`editText`** — atomic literal read-modify-write over the same primitive, serialized per target by a mutation lock. The `expected` guard is OPTIONAL: when supplied it verifies the version BEFORE literal matching (a stale edit reports `FS_STALE_VERSION`, never `FS_EDIT_NOT_FOUND`/`FS_AMBIGUOUS_EDIT` against newer content); omitting it edits the current content unconditionally. A missing target reports `FS_STALE_VERSION` either way. LF-normalizes for matching, restores the file's dominant CRLF/LF style, and rejects empty `oldString` / zero matches (`FS_EDIT_NOT_FOUND`) or ambiguous multi-matches without `replace_all` (`FS_AMBIGUOUS_EDIT`).
 
-The raw I/O lives in `src/fsio.ts` (Cordis-free, independently unit-tested); `src/index.ts` is the thin service wiring.
+The package-root SDK surface is the default/named `LocalFileSystem` class plus `Config`. Raw I/O lives in `src/fsio.ts` (Cordis-free, independently unit-tested); `src/index.ts` is the thin service wiring.
 
 ## Model Experience
 

packages/fs/fs-local/src/index.ts

@@ -31,20 +31,6 @@ import {
 } from './fsio.ts'
 import type { FsIoInternals } from './fsio.ts'
 
-export {
-  applyLiteralEdit,
-  listDirectory,
-  probe,
-  readForEdit,
-  readTextForDiff,
-  readWholeText,
-  resolveLocalTarget,
-  restoreLineEndings,
-  streamWholeText,
-  writeFileAtomic,
-} from './fsio.ts'
-export type { FsIoInternals, LineEndings, LocalDirEntry, LocalTarget, PathInfo } from './fsio.ts'
-
 /** Configuration for the local filesystem backend. */
 export interface Config {
   /** Base directory for relative paths. Defaults to `process.cwd()`. */

packages/fs/fs-local/tests/fsio.spec.ts

@@ -20,8 +20,8 @@ import {
   restoreLineEndings,
   streamWholeText,
   writeFileAtomic,
-} from '@deepseek-ai/dsh-fs-local'
-import type { LocalTarget } from '@deepseek-ai/dsh-fs-local'
+} from '../src/fsio.ts'
+import type { LocalTarget } from '../src/fsio.ts'
 import { FsError, FsTargetKey } from '@deepseek-ai/dsh-fs'
 
 let dir: string

packages/fs/tool-fs/README.md

@@ -46,7 +46,7 @@ The tool passes `exec` (the tool-execution context) as the opaque `actor` on eve
 
 `fs/observed` fires AFTER the read/write/edit already succeeded, via a plain `ctx.emit`. A listener is contractually a synchronous, side-effect-only recorder (`@deepseek-ai/dsh-fs-policy`'s is a `WeakMap.set`); the tool does not guard the emit, so a listener that throws would surface as the tool's `isError` result — async or fallible observation does not belong on this event.
 
-The read rendering (line windowing + output formatting) lives in `src/read-render.ts` (Cordis-free, independently unit-tested); `src/read.ts`/`write.ts`/`edit.ts` are the tool executors and `src/index.ts` composes them.
+The package root exports only the Cordis plugin contract (`name`, `inject`, `Config`, and `apply`). Read rendering (line windowing + output formatting) lives in `src/read-render.ts` (Cordis-free, independently unit-tested); `src/read.ts`/`write.ts`/`edit.ts` are the tool executors and `src/index.ts` composes them.
 
 ## Model Experience
 

packages/fs/tool-fs/src/index.ts

@@ -12,15 +12,6 @@ import { applyWriteTool } from './write.ts'
 import { applyEditTool } from './edit.ts'
 import { READ_MAX_BYTES, READ_MAX_LINE_LENGTH } from './read-render.ts'
 
-export { READ_LIMIT, STREAM_MIN_SIZE, applyReadTool, parseReadArgs } from './read.ts'
-export type { ReadToolCaps } from './read.ts'
-export { applyWriteTool, formatWriteOutput, parseWriteArgs } from './write.ts'
-export { applyEditTool, formatEditOutput, parseEditArgs } from './edit.ts'
-export { READ_MAX_BYTES, READ_MAX_LINE_LENGTH, buildWindow, formatReadOutput } from './read-render.ts'
-export type { FileReadOutcome, FileTextLine, ReadWindow, WindowResult } from './read-render.ts'
-export { DIFF_CONTEXT, computeHunkDiffs, diffsFromMeta } from './diff.ts'
-export type { FsDiffMeta } from './diff.ts'
-
 /** Cordis plugin name used by loader diagnostics. */
 export const name = 'tool-fs'
 

packages/fs/tool-fs/tests/diff.spec.ts

@@ -6,7 +6,7 @@
  */
 
 import { describe, expect, it } from 'vitest'
-import { computeHunkDiffs, diffsFromMeta, DIFF_CONTEXT } from '@deepseek-ai/dsh-tool-fs'
+import { computeHunkDiffs, diffsFromMeta, DIFF_CONTEXT } from '../src/diff.ts'
 import type { JsonValue } from '@deepseek-ai/dsh-session'
 
 const lines = (n: number): string => Array.from({ length: n }, (_, i) => `line${i + 1}`).join('\n') + '\n'

packages/fs/tool-fs/tests/read-render.spec.ts

@@ -6,8 +6,8 @@
  */
 
 import { describe, expect, it } from 'vitest'
-import { buildWindow, READ_MAX_BYTES, READ_MAX_LINE_LENGTH } from '@deepseek-ai/dsh-tool-fs'
-import type { ReadWindow } from '@deepseek-ai/dsh-tool-fs'
+import { buildWindow, READ_MAX_BYTES, READ_MAX_LINE_LENGTH } from '../src/read-render.ts'
+import type { ReadWindow } from '../src/read-render.ts'
 
 const DEFAULT_CAPS = { maxLineLength: READ_MAX_LINE_LENGTH, maxBytes: READ_MAX_BYTES }
 const READ_ALL: ReadWindow = { offset: 1, limit: 2000, ...DEFAULT_CAPS }

packages/fs/tool-fs/tests/tools.spec.ts

@@ -20,8 +20,9 @@ import type {
 } from '@deepseek-ai/dsh-fs'
 import * as FsPolicy from '@deepseek-ai/dsh-fs-policy'
 import * as ToolFs from '@deepseek-ai/dsh-tool-fs'
-import { formatReadOutput, STREAM_MIN_SIZE } from '@deepseek-ai/dsh-tool-fs'
-import type { FileReadOutcome } from '@deepseek-ai/dsh-tool-fs'
+import { STREAM_MIN_SIZE } from '../src/read.ts'
+import { formatReadOutput } from '../src/read-render.ts'
+import type { FileReadOutcome } from '../src/read-render.ts'
 
 /** An in-memory fake provider; a test can arm a rejection on any primitive. */
 class FakeFs extends FileSystem {

packages/skill/skill/src/index.ts

@@ -119,23 +119,6 @@ declare module 'cordis' {
   interface Context {
     skills: SkillService
   }
-
-  interface Events {
-    /**
-     * A skill provider became resolvable in the `ctx.skills` registry.
-     * Consumers can observe this instead of depending on Cordis plugin load
-     * order, which is concurrent for sibling plugins.
-     * @param provider - the provider that just registered.
-     * @mode emit
-     */
-    'skill/provider-added'(provider: SkillProvider): void
-    /**
-     * A skill provider left the registry because its plugin fiber was disposed.
-     * @param name - the registry name that no longer resolves.
-     * @mode emit
-     */
-    'skill/provider-removed'(name: string): void
-  }
 }
 
 interface IndexedCandidate {
@@ -191,19 +174,16 @@ export class SkillService extends Service {
       throw new Error(`a skill provider named "${name}" is already registered`)
     }
     const providers = this.providers
-    const ctx = this.ctx
     const order = this.nextProviderOrder
     const invalidateCache = (): void => { this.invalidateCache() }
     this.nextProviderOrder += 1
-    const dispose = ctx.effect(function* () {
+    const dispose = this.ctx.effect(function* () {
       providers.set(name, { provider, order })
       invalidateCache()
       yield () => {
         providers.delete(name)
         invalidateCache()
-        ctx.emit('skill/provider-removed', name)
       }
-      ctx.emit('skill/provider-added', provider)
     }, 'skills.registerProvider()')
     // eslint-disable-next-line @typescript-eslint/no-misused-promises -- synchronous cleanup; direct return preserves disposer identity
     return dispose

packages/support/README.md

@@ -6,7 +6,8 @@ Packages that exist to serve development, testing, and the examples rather than
 |---|---|---|
 | `acp-snapshot/` | ACP snapshot suite kit: subprocess scenario harness + golden normalizers + the `defineAcpSnapshotSuite` factory | (library — imported by example `*.snapshot.ts` suites) |
 | `invariants/` | Runtime event-contract assertions for development diagnostics | (listens on `session/*`, `agent/*`) |
+| `loader-smoke/` | Shared real-Loader subprocess harness for keyless example smokes | (library — imported by example e2e suites) |
 | `llm-replay/` | Record/replay adapter: short-circuits `llm/stream` from a recorded session JSONL (keyless snapshot tests) | (listens on `llm/stream`) |
 | `subagent-mock/` | Scripted `SubagentProvider` for deterministic seam/tool tests | (registers on `ctx.subagents`) |
 
-`invariants` is development support but has no environment guard: it runs wherever registered, and the default `dsh-agent-core` bundle mounts it unconditionally. `llm-replay` backs the demos and the snapshot test tier under the per-file coverage gate. `acp-snapshot` carries the snapshot tier's harness/normalizer/suite machinery so every example's suite is a scenario table over one shared, gate-covered implementation. `subagent-mock` exercises the real `ctx.subagents` load path without a model or child agent. A package graduates OUT of `support/` into a product group only when it gains documented product consumers.
+`invariants` is development support but has no environment guard: it runs wherever registered, and the default `dsh-agent-core` bundle mounts it unconditionally. `llm-replay` backs the demos and the snapshot test tier under the per-file coverage gate. `acp-snapshot` carries the snapshot tier's harness/normalizer/suite machinery, while `loader-smoke` owns the parallel stdio/Loader process boundary used by keyless example e2e suites. `subagent-mock` exercises the real `ctx.subagents` load path without a model or child agent. A package graduates OUT of `support/` into a product group only when it gains documented product consumers.

packages/support/invariants/tests/invariants.spec.ts

@@ -855,9 +855,9 @@ describe('scoped-dispatch invariants', () => {
       ['agent/error', [agent, 1, 0, new Error('x')]],
       ['approval/request', [{ agent, toolName: 'echo' }, () => Promise.resolve('unavailable')]],
       ['tools/pre-execute', [{ callId: 'c', name: 't', arguments: {}, agent }, () => Promise.resolve({ kind: 'allow' })]],
-      ['tools/execute', [{ callId: 'c', name: 't', arguments: {}, agent }, () => Promise.resolve({ callId: 'c', content: [], isError: false })]],
-      ['tools/post-execute', [{ callId: 'c', name: 't', arguments: {}, agent }, { callId: 'c', content: [], isError: false }, () => Promise.resolve({ kind: 'accept' })]],
-      ['tools/result', [{ callId: 'c', name: 't', arguments: {}, agent }, { callId: 'c', content: [], isError: false }]],
+      ['tools/execute', [{ callId: 'c', name: 't', arguments: {}, agent }, () => Promise.resolve({ content: [], isError: false })]],
+      ['tools/post-execute', [{ callId: 'c', name: 't', arguments: {}, agent }, { content: [], isError: false }, () => Promise.resolve({ kind: 'accept' })]],
+      ['tools/result', [{ callId: 'c', name: 't', arguments: {}, agent }, { content: [], isError: false }]],
     ]
     for (const [event, args] of rows) {
       const subject = agent

packages/support/loader-smoke/README.md

@@ -0,0 +1,17 @@
+# `@deepseek-ai/dsh-loader-smoke`
+
+Shared subprocess harness for keyless example smokes that boot the real stdio-agent bin and a real `cordis.yml` through the Cordis Loader. A test supplies absolute bin/config/tsconfig paths, optional environment overrides, and stdin lines; `runLoaderSmoke` owns the isolated cwd, DSH homes, tsx path resolution, 30-second process deadline, captured diagnostics, forced kill, EOF, and cleanup.
+
+Successful runs return stdout and stderr only after a zero exit. Non-zero exits and deadlines reject with both captured streams. `LOADER_SMOKE_TEST_TIMEOUT_MS` leaves Vitest enough room for the process-owned diagnostic timeout to fire first.
+
+This is support-tier test infrastructure, not product API. The consumers are the Loader-path smokes under `examples/{echo-agent,coding-agent,cordis-agent}`.
+
+## Model Experience
+
+None, as this test-only harness boots example processes and inspects their streams without changing an assembled model request.
+
+## Known Limitations and Deferred Work
+
+- **Only the unbuilt tsx/Loader path is exercised** — built-bin artifacts remain the responsibility of their separate e2e smokes.
+- **Captured stdout and stderr are unbounded** — a runaway child can consume memory until the deadline kills it.
+- **Timeout kills only the direct child** — a process tree spawned by a faulty fixture can outlive the smoke and needs external cleanup.

packages/support/loader-smoke/package.json

@@ -0,0 +1,33 @@
+{
+  "name": "@deepseek-ai/dsh-loader-smoke",
+  "description": "Shared subprocess harness for keyless real-Loader example smoke tests",
+  "version": "0.0.1",
+  "private": true,
+  "type": "module",
+  "main": "lib/index.js",
+  "types": "lib/types/index.d.ts",
+  "exports": {
+    ".": {
+      "types": "./lib/types/index.d.ts",
+      "default": "./lib/index.js"
+    },
+    "./src/*": "./src/*",
+    "./package.json": "./package.json"
+  },
+  "files": [
+    "lib/index.js",
+    "lib/types/**/*.d.ts",
+    "lib/types/**/*.d.ts.map",
+    "src"
+  ],
+  "license": "BSD-3-Clause",
+  "dependencies": {
+    "tsx": "^4.22.4"
+  },
+  "peerDependencies": {
+    "cordis": "^4.0.0-rc.6"
+  },
+  "devDependencies": {
+    "cordis": "^4.0.0-rc.6"
+  }
+}

packages/support/loader-smoke/src/index.ts

@@ -0,0 +1,117 @@
+/**
+ * Shared subprocess harness for keyless example smokes that boot a real
+ * `cordis.yml` through the stdio-agent bin and Cordis Loader.
+ *
+ * @module @deepseek-ai/dsh-loader-smoke
+ */
+
+import { spawn } from 'node:child_process'
+import { mkdtemp, rm } from 'node:fs/promises'
+import { tmpdir } from 'node:os'
+import { join } from 'node:path'
+import { fileURLToPath } from 'node:url'
+
+const DEFAULT_PROCESS_TIMEOUT_MS = 30_000
+const TSX_LOADER = fileURLToPath(import.meta.resolve('tsx'))
+
+/** Vitest deadline that leaves room for the subprocess-owned 30-second diagnostic timeout. */
+export const LOADER_SMOKE_TEST_TIMEOUT_MS = DEFAULT_PROCESS_TIMEOUT_MS + 15_000
+
+/** Inputs that vary between real-Loader example smokes. */
+export interface LoaderSmokeOptions {
+  /** Human-readable example name used in failure diagnostics. */
+  readonly label: string
+  /** Prefix for the isolated temporary process cwd. */
+  readonly tempDirPrefix: string
+  /** Absolute stdio-agent bin path. */
+  readonly binScript: string
+  /** Absolute real Loader config path. */
+  readonly configPath: string
+  /** Absolute repo tsconfig path used for unbuilt workspace-package resolution. */
+  readonly tsconfigPath: string
+  /** Environment overrides layered over the parent and isolated DSH homes. */
+  readonly env?: Readonly<NodeJS.ProcessEnv>
+  /** Lines written to stdin before EOF; omitted means immediate EOF. */
+  readonly stdinLines?: readonly string[]
+  /** Process deadline override for harness tests. */
+  readonly processTimeoutMs?: number
+}
+
+/** Captured output from a Loader smoke that exited successfully. */
+export interface LoaderSmokeResult {
+  /** Complete stdout after clean exit. */
+  readonly stdout: string
+  /** Complete stderr after clean exit. */
+  readonly stderr: string
+}
+
+/**
+ * Boot one real Loader tree from an isolated cwd, write the requested stdin
+ * script, close stdin, and await a clean exit. The helper owns process kill and
+ * temp-directory cleanup on every outcome.
+ * @param options - example paths, environment, stdin, and diagnostic identity.
+ * @returns captured stdout and stderr after a zero exit.
+ */
+export async function runLoaderSmoke(options: LoaderSmokeOptions): Promise<LoaderSmokeResult> {
+  const cwd = await mkdtemp(join(tmpdir(), options.tempDirPrefix))
+  const processTimeoutMs = options.processTimeoutMs ?? DEFAULT_PROCESS_TIMEOUT_MS
+  try {
+    return await new Promise((resolve, reject) => {
+      const child = spawn(
+        process.execPath,
+        ['--expose-internals', '--import', TSX_LOADER, options.binScript, options.configPath],
+        {
+          cwd,
+          env: {
+            ...process.env,
+            DSH_HOME: join(cwd, '.dsh'),
+            DSH_AGENTS_HOME: join(cwd, '.agents'),
+            ...options.env,
+            TSX_TSCONFIG_PATH: options.tsconfigPath,
+          },
+          stdio: ['pipe', 'pipe', 'pipe'],
+        },
+      )
+      let stdout = ''
+      let stderr = ''
+      let deferredFailure: Error | undefined
+      child.stdout.setEncoding('utf8')
+      child.stdout.on('data', (chunk: string) => { stdout += chunk })
+      child.stderr.setEncoding('utf8')
+      child.stderr.on('data', (chunk: string) => { stderr += chunk })
+
+      const timer = setTimeout(() => {
+        deferredFailure = new Error(`${options.label} did not exit within ${processTimeoutMs / 1_000}s. stdout:\n${stdout}\nstderr:\n${stderr}`)
+        child.kill('SIGKILL')
+      }, processTimeoutMs)
+
+      child.once('exit', (code) => {
+        clearTimeout(timer)
+        if (deferredFailure !== undefined) {
+          reject(deferredFailure)
+        } else if (code === 0) {
+          resolve({ stdout, stderr })
+        } else {
+          reject(new Error(`${options.label} exited ${String(code)}. stdout:\n${stdout}\nstderr:\n${stderr}`))
+        }
+      })
+
+      // process.execPath and a just-created pipe make these OS-error paths
+      // impractical to induce without replacing the boundary under test.
+      /* v8 ignore start */
+      child.once('error', (error) => {
+        clearTimeout(timer)
+        reject(new Error(`${options.label} failed to start: ${error.message}`))
+      })
+      child.stdin.once('error', (error) => {
+        deferredFailure ??= new Error(`${options.label} stdin failed: ${error.message}`)
+        child.kill('SIGKILL')
+      })
+      /* v8 ignore stop */
+
+      child.stdin.end((options.stdinLines ?? []).map(line => `${line}\n`).join(''))
+    })
+  } finally {
+    await rm(cwd, { recursive: true, force: true })
+  }
+}

packages/support/loader-smoke/tests/fixtures/fail.ts

@@ -0,0 +1,4 @@
+/** Non-zero subprocess fixture for the Loader-smoke harness. */
+
+console.error('fixture failed')
+process.exitCode = 7

packages/support/loader-smoke/tests/fixtures/hang.ts

@@ -0,0 +1,4 @@
+/** Deadline subprocess fixture for the Loader-smoke harness. */
+
+console.log('fixture hanging')
+setInterval(() => {}, 1_000)

packages/support/loader-smoke/tests/fixtures/success.ts

@@ -0,0 +1,16 @@
+/** Successful subprocess fixture for the Loader-smoke harness. */
+
+let input = ''
+process.stdin.setEncoding('utf8')
+process.stdin.on('data', (chunk: string) => { input += chunk })
+process.stdin.on('end', () => {
+  console.log(JSON.stringify({
+    configPath: process.argv[2],
+    cwd: process.cwd(),
+    dshHome: process.env.DSH_HOME,
+    agentsHome: process.env.DSH_AGENTS_HOME,
+    marker: process.env.LOADER_SMOKE_MARKER,
+    input,
+  }))
+  console.error('fixture stderr')
+})

packages/support/loader-smoke/tests/loader-smoke.spec.ts

@@ -0,0 +1,61 @@
+import { existsSync } from 'node:fs'
+import { fileURLToPath } from 'node:url'
+import { describe, expect, it } from 'vitest'
+import { LOADER_SMOKE_TEST_TIMEOUT_MS, runLoaderSmoke } from '@deepseek-ai/dsh-loader-smoke'
+
+const configPath = '/tmp/fixture.cordis.yml'
+const tsconfigPath = fileURLToPath(new URL('../../../../tsconfig.json', import.meta.url))
+const fixture = (name: string): string => fileURLToPath(new URL(`./fixtures/${name}.ts`, import.meta.url))
+const canonicalTempPath = (path: string): string => path.replace(/^\/private(?=\/var\/)/, '')
+
+describe('runLoaderSmoke', () => {
+  it('isolates the process, writes stdin, captures output, and removes the cwd', async () => {
+    const result = await runLoaderSmoke({
+      label: 'success fixture',
+      tempDirPrefix: 'loader-smoke-success-',
+      binScript: fixture('success'),
+      configPath,
+      tsconfigPath,
+      env: { LOADER_SMOKE_MARKER: 'present' },
+      stdinLines: ['one', 'two'],
+    })
+    const output = JSON.parse(result.stdout) as {
+      configPath: string
+      cwd: string
+      dshHome: string
+      agentsHome: string
+      marker: string
+      input: string
+    }
+    expect(output).toMatchObject({
+      configPath,
+      marker: 'present',
+      input: 'one\ntwo\n',
+    })
+    expect(canonicalTempPath(output.dshHome)).toBe(`${canonicalTempPath(output.cwd)}/.dsh`)
+    expect(canonicalTempPath(output.agentsHome)).toBe(`${canonicalTempPath(output.cwd)}/.agents`)
+    expect(result.stderr).toContain('fixture stderr')
+    expect(existsSync(output.cwd)).toBe(false)
+  }, LOADER_SMOKE_TEST_TIMEOUT_MS)
+
+  it('rejects a non-zero exit with captured diagnostics', async () => {
+    await expect(runLoaderSmoke({
+      label: 'failure fixture',
+      tempDirPrefix: 'loader-smoke-fail-',
+      binScript: fixture('fail'),
+      configPath,
+      tsconfigPath,
+    })).rejects.toThrow('failure fixture exited 7. stdout:\n\nstderr:\nfixture failed')
+  })
+
+  it('kills a process at its deadline and reports captured output', async () => {
+    await expect(runLoaderSmoke({
+      label: 'hanging fixture',
+      tempDirPrefix: 'loader-smoke-hang-',
+      binScript: fixture('hang'),
+      configPath,
+      tsconfigPath,
+      processTimeoutMs: 100,
+    })).rejects.toThrow('hanging fixture did not exit within 0.1s.')
+  })
+})

packages/support/loader-smoke/tsconfig.json

@@ -0,0 +1,11 @@
+{
+  "extends": "../../../tsconfig.base.json",
+  "compilerOptions": {
+    "rootDir": "src",
+    "outDir": "lib/types"
+  },
+  "include": [
+    "src"
+  ],
+  "references": []
+}

packages/timeout/timeout-policy/src/index.ts

@@ -6,7 +6,6 @@
  */
 
 import type { Context } from 'cordis'
-import type { CallId } from '@deepseek-ai/dsh-llm'
 import { deadline, timeoutOf } from '@deepseek-ai/dsh-timeout'
 import type { ToolExecutionResult } from '@deepseek-ai/dsh-tools'
 
@@ -30,13 +29,11 @@ export const inject = ['tools']
  * is the model-facing message; `error.code` is the same {@link TOOL_TIMEOUT}
  * this plugin owns, so a retry/sandbox plugin (and replay) can route on it.
  *
- * @param callId - the timed-out call's id, carried onto the replacement result.
  * @param timeoutMs - the elapsed budget, rendered into the model-facing message.
  * @returns the `isError` {@link ToolExecutionResult} with a `TOOL_TIMEOUT` error.
  */
-export function toolTimeoutResult(callId: CallId, timeoutMs: number): ToolExecutionResult {
+function toolTimeoutResult(timeoutMs: number): ToolExecutionResult {
   return {
-    callId,
     content: [{ type: 'text', text: `Error: tool call timed out after ${timeoutMs}ms` }],
     isError: true,
     error: { name: 'ToolTimeoutError', code: TOOL_TIMEOUT },
@@ -68,7 +65,7 @@ export function apply(ctx: Context): void {
       // quiescence; replace whatever it returned (its own abort result) with the
       // structured TOOL_TIMEOUT the model sees.
       if (timeoutOf(d.signal, TOOL_TIMEOUT) !== undefined) {
-        return toolTimeoutResult(exec.callId, timeoutMs)
+        return toolTimeoutResult(timeoutMs)
       }
       return result
     } finally {

packages/timeout/timeout-policy/tests/timeout-policy.spec.ts

@@ -11,9 +11,9 @@ import { Context } from 'cordis'
 import Loader from '@cordisjs/plugin-loader'
 import { CallId, HarnessError } from '@deepseek-ai/dsh-llm'
 import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
-import ToolRegistry, { defineTool, type ToolExecutionInput, type ToolExecutionResult, type PostToolDecision } from '@deepseek-ai/dsh-tools'
+import ToolRegistry, { defineTool, type ToolExecutionInput, type PostToolDecision } from '@deepseek-ai/dsh-tools'
 import * as timeoutPolicy from '@deepseek-ai/dsh-timeout-policy'
-import { TOOL_TIMEOUT, toolTimeoutResult } from '@deepseek-ai/dsh-timeout-policy'
+import { TOOL_TIMEOUT } from '@deepseek-ai/dsh-timeout-policy'
 
 /** Mount the registry + the zero-config timeout-policy enforcer. */
 async function setup() {
@@ -60,7 +60,7 @@ describe('timeout-policy delegation (unconfigured / fast)', () => {
     ctx.tools.register(defineTool({ name: 'fast', description: 'd', parameters: {}, timeoutMs: 10_000,
       async execute() { return [{ type: 'text' as const, text: 'ok' }] } }))
     const result = await ctx.tools.execute({ callId: CallId('c1'), name: 'fast', arguments: {} })
-    expect(result).toEqual({ callId: CallId('c1'), content: [{ type: 'text', text: 'ok' }], isError: false })
+    expect(result).toEqual({ content: [{ type: 'text', text: 'ok' }], isError: false })
   })
 
   it('a budgeted tool receives the DERIVED deadline signal (not the caller signal) during dispatch', async () => {
@@ -109,7 +109,6 @@ describe('timeout-policy TOOL_TIMEOUT replacement (deadline wins)', () => {
     await vi.advanceTimersByTimeAsync(150)
     const result = await pending
     expect(result).toEqual({
-      callId: CallId('c1'),
       content: [{ type: 'text', text: 'Error: tool call timed out after 100ms' }],
       isError: true,
       error: { name: 'ToolTimeoutError', code: 'TOOL_TIMEOUT' },
@@ -140,16 +139,7 @@ describe('timeout-policy TOOL_TIMEOUT replacement (deadline wins)', () => {
   })
 })
 
-describe('toolTimeoutResult', () => {
-  it('builds the structured TOOL_TIMEOUT result', () => {
-    expect(toolTimeoutResult(CallId('c9'), 250)).toEqual({
-      callId: CallId('c9'),
-      content: [{ type: 'text', text: 'Error: tool call timed out after 250ms' }],
-      isError: true,
-      error: { name: 'ToolTimeoutError', code: 'TOOL_TIMEOUT' },
-    } satisfies ToolExecutionResult)
-  })
-
+describe('timeout-policy contract', () => {
   it('exposes the owned code constant', () => {
     expect(TOOL_TIMEOUT).toBe('TOOL_TIMEOUT')
   })

packages/ui/README.md

@@ -9,13 +9,14 @@ Integrations that expose the agent to an external editor or client. These are **
 | `permission/` | User-facing permission presets (`workspace-write`/`danger-full-access`): one product-level select bundling the sandbox-mode and approval-policy knobs, written through to their session events | `ctx.permission` |
 | `user-interaction/` | Abstract human question/answer seam used by UI-backed confirmation tools | `ctx.userInteraction` |
 | `tool-ask-user/` | Model-facing `ask_user_question` tool over `ctx.userInteraction` | (registers on `ctx.tools`) |
+| `stdio/` | Terminal readline channel over `ctx.agents`, `session/event`, and `ctx.userInteraction`; agent lifecycle stays with app/developer code | (drives `ctx.agents`) |
 | `stdio-agent/` | Terminal stdio chat APP: the agent-core spine + console logger + readline UI + a pre-created `main` agent, with a `bin` | (composition + `bin`) |
 | `acp-agent/` | ACP server APP: the agent-core spine + JSONL persistence + the `acp` bridge (no stdout logger), with a `bin` | (composition + `bin`) |
 | `jsonrpc/` | Stdio JSON-RPC server for out-of-process SDK clients | (drives `ctx.agents`) |
 | `jsonrpc-agent/` | Bin-only SDK runtime app that boots an external `cordis.yml` | (`bin` only) |
 | `app-boot/` | Shared boot glue for the app bins: `.env` loading, fail-loud Loader guards, snapshot-aware config resolution, the settle-the-tree boot sequence | (library for the bins) |
 
-A UI integration is a client-driver plugin, not a loop change or capability seam: it consumes the existing `agent/*` events and `dsh-agent` factory. `jsonrpc` is the SDK-client sibling of the `acp` editor bridge. The readline UI lives inside [`stdio-agent/`](stdio-agent/README.md) because it is scaffolding for that front door, not an independently swappable integration.
+A UI integration is a client-driver plugin, not a loop change and not a capability seam: it consumes the existing `agent/*` event taxonomy and the `dsh-agent` factory. The `jsonrpc` plugin is the SDK-client sibling of the `acp` bridge (a JSON-RPC server over `ctx.agents` for out-of-process SDK clients rather than editors). The [`stdio`](stdio/README.md) plugin is the unstructured readline analogue of the `acp` bridge; app bundles and SDK projects compose it explicitly with the services and tools their product profile selects.
 
 `user-approval`, `user-interaction`, and `tool-ask-user` live here because asking a human is a UI-backed product affordance, not part of the providerless core spine. `user-approval` owns the one-shot `ctx.approval` decision mechanism and its policy tier; answerers remain with their UI channel owners. `user-interaction` remains provider-neutral (`ctx.userInteraction`), while `tool-ask-user` is its model-facing consumer and the app/bridge packages provide concrete providers.
 

packages/ui/stdio-agent/README.md

@@ -15,7 +15,7 @@ A terminal chat always wants the same cluster, so the package owns it rather tha
 | `@deepseek-ai/dsh-session-persistence-jsonl` | durable JSONL session log under `persistenceRoot` |
 | `@deepseek-ai/dsh-user-interaction` | the human question/answer seam used by confirmation tools |
 | `@deepseek-ai/dsh-tool-ask-user` | the model-facing `ask_user_question` tool |
-| `stdio-chat` (in-package module) | the readline UI, bound to the `main` agent |
+| `@deepseek-ai/dsh-stdio` | the readline UI, bound to the `main` agent |
 
 `@cordisjs/plugin-hmr` (the dev/demo edit-reload loop) is deliberately a **leaf** entry, NOT baked in here: it is a Loader-only, subprocess-only dev plugin — its constructor throws without `node --expose-internals` + a live `loader`, and the in-process test tier cannot even import it (so a package whose `apply` statically pulled it in could never carry the per-file coverage gate). Unlike the console logger, a stray `hmr` is not a stdout-purity footgun, so leaving it at the leaf costs no safety. The `demo:echo` / `demo:repl` leaves load it and pass `--expose-internals`.
 

packages/ui/stdio-agent/package.json

@@ -38,9 +38,10 @@
     "@deepseek-ai/dsh-llm": "^0.0.1",
     "@deepseek-ai/dsh-agent-core": "^0.0.1",
     "@deepseek-ai/dsh-session": "^0.0.1",
-    "@deepseek-ai/dsh-tools": "^0.0.1",
     "@deepseek-ai/dsh-session-persistence-jsonl": "^0.0.1",
+    "@deepseek-ai/dsh-stdio": "^0.0.1",
     "@deepseek-ai/dsh-tool-ask-user": "^0.0.1",
+    "@deepseek-ai/dsh-tools": "^0.0.1",
     "@deepseek-ai/dsh-user-interaction": "^0.0.1",
     "cordis": "^4.0.0-rc.7",
     "schemastery": "^3.17.0"
@@ -55,9 +56,10 @@
     "@deepseek-ai/dsh-agent-core": "workspace:^",
     "@deepseek-ai/dsh-system-prompt": "workspace:^",
     "@deepseek-ai/dsh-session": "workspace:^",
-    "@deepseek-ai/dsh-tools": "workspace:^",
     "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^",
+    "@deepseek-ai/dsh-stdio": "workspace:^",
     "@deepseek-ai/dsh-tool-ask-user": "workspace:^",
+    "@deepseek-ai/dsh-tools": "workspace:^",
     "@deepseek-ai/dsh-user-interaction": "workspace:^",
     "cordis": "^4.0.0-rc.7",
     "schemastery": "^3.17.0"

packages/ui/stdio-agent/src/index.ts

@@ -1,8 +1,8 @@
 /**
  * The stdio chat app: the default agent spine ({@link @deepseek-ai/dsh-agent-core}) plus the
- * coupled front-door cluster a terminal chat needs — a console logger, the readline UI (the
- * in-package `stdio-chat` module), JSONL session persistence, and a pre-created `main` agent
- * the UI drives.
+ * coupled front-door cluster a terminal chat needs — a console logger, the independently
+ * packaged readline UI, JSONL session persistence, the user-interaction seam with its
+ * `ask_user_question` tool, and a pre-created `main` agent the UI drives.
  * Swappable adapters, executors, optional tools, and HMR stay in the leaf. This
  * Loader plugin intentionally exposes named exports only; a default export
  * would hide its `Config` schema (see docs/postmortem/0001).
@@ -19,7 +19,7 @@ import * as agentCore from '@deepseek-ai/dsh-agent-core'
 import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
 import UserInteractionService from '@deepseek-ai/dsh-user-interaction'
 import * as toolAskUser from '@deepseek-ai/dsh-tool-ask-user'
-import * as uiStdio from './stdio-chat.ts'
+import * as uiStdio from '@deepseek-ai/dsh-stdio'
 
 export const name = 'stdio-agent'
 

packages/ui/stdio-agent/tests/built-bin.e2e.ts

@@ -24,6 +24,7 @@ const dshPackages = [
   'bash/tool-bash', 'support/invariants', 'ui/app-boot',
   'session-persistence/session-persistence',
   'session-persistence/session-persistence-jsonl', 'ui/stdio-agent',
+  'ui/stdio', 'ui/tool-ask-user', 'ui/user-interaction',
 ]
 const vendorPackages = [
   'cordis', 'loader', 'include', 'timer', 'hmr', 'logger-console',

packages/ui/stdio-agent/tsconfig.json

@@ -35,6 +35,9 @@
     {
       "path": "../user-interaction"
     },
+    {
+      "path": "../stdio"
+    },
     {
       "path": "../tool-ask-user"
     },

packages/ui/stdio/README.md

@@ -0,0 +1,42 @@
+# @deepseek-ai/dsh-stdio
+
+The terminal readline front door for DeepSeek Harness agents. It reads prompts from stdin, sends or steers them through `ctx.agents`, renders the durable `session/event` transcript to stdout, and answers `ctx.userInteraction` requests in the same terminal.
+
+This package owns the terminal channel only. It injects `agents` and `userInteraction`, then drives an agent created or resumed by app or developer code. The agent spine, agent lifecycle, console logger, and model-facing [`ask_user_question`](../tool-ask-user/README.md) tool remain separate composition entries.
+
+## Config
+
+| Key | Default | Meaning |
+|---|---|---|
+| `welcome` | `ready.` | Banner printed before the first prompt |
+| `agent` | `main` | Agent id driven by stdin and observed for EOF shutdown |
+
+The plugin seeds display labels from the live agent registry, then tracks `agent/created` and `agent/disposed` so HMR and externally managed agents render consistently. Disposal closes readline and unregisters every listener/provider through Cordis effects.
+
+```yaml
+- id: stdio
+  name: '@deepseek-ai/dsh-stdio'
+  config:
+    welcome: 'agent REPL ready. Give it a coding task.'
+    agent: main
+```
+
+## Model Experience
+
+### Readline prompt input
+
+**What the model sees**: Each non-empty terminal line outside an active question becomes one text block, sent with `agent.send()` while the target agent is idle and `agent.steer()` while it is running.
+
+**Token effect**: Submitted text is retained under the agent loop's normal session-history and compaction rules. The welcome banner, `> ` prompt, rendered transcript, and `[tool call]` / `[tool result]` terminal lines add no tokens.
+
+### Terminal user-interaction answers
+
+**What the model sees**: When a consumer calls `ctx.userInteraction.ask()`, this provider renders the question in the terminal and returns selected option labels or `custom` text. Through `dsh-tool-ask-user`, closed stdin becomes `Error: ask_user_question cannot be answered because stdin is closed`; disposal or abort becomes `Error: ask_user_question was interrupted before the user answered`.
+
+**Token effect**: Waiting and terminal prompts add no tokens; the resolved answer or error is model-visible only through the calling tool or plugin's result.
+
+## Known Limitations and Deferred Work
+
+- **One configured agent receives stdin** — the session/event renderer can print output from any session, but input lines always drive the configured `agent` id rather than routing by the visible label.
+- **Terminal questions are text-only and sequential** — the provider queues asks, supports option labels plus custom text, and has no richer UI shapes such as file pickers or diff previews.
+- **Closed stdin ends the terminal channel** — EOF rejects active or queued questions and exits after submitted work reaches idle; there is no reconnect path for a long-lived process.

packages/ui/stdio/package.json

@@ -0,0 +1,42 @@
+{
+  "name": "@deepseek-ai/dsh-stdio",
+  "description": "Terminal readline front door for driving and rendering DeepSeek Harness agents over stdio",
+  "version": "0.0.1",
+  "private": true,
+  "type": "module",
+  "main": "lib/index.js",
+  "types": "lib/types/index.d.ts",
+  "exports": {
+    ".": {
+      "types": "./lib/types/index.d.ts",
+      "default": "./lib/index.js"
+    },
+    "./src/*": "./src/*",
+    "./package.json": "./package.json"
+  },
+  "files": [
+    "lib/index.js",
+    "lib/types/**/*.d.ts",
+    "lib/types/**/*.d.ts.map",
+    "src"
+  ],
+  "license": "BSD-3-Clause",
+  "peerDependencies": {
+    "@deepseek-ai/dsh-agent": "^0.0.1",
+    "@deepseek-ai/dsh-llm": "^0.0.1",
+    "@deepseek-ai/dsh-session": "^0.0.1",
+    "@deepseek-ai/dsh-user-interaction": "^0.0.1",
+    "cordis": "^4.0.0-rc.6"
+  },
+  "dependencies": {
+    "schemastery": "^3.18.0"
+  },
+  "devDependencies": {
+    "@cordisjs/plugin-loader": "workspace:^",
+    "@deepseek-ai/dsh-agent": "workspace:^",
+    "@deepseek-ai/dsh-llm": "workspace:^",
+    "@deepseek-ai/dsh-session": "workspace:^",
+    "@deepseek-ai/dsh-user-interaction": "workspace:^",
+    "cordis": "^4.0.0-rc.6"
+  }
+}

packages/ui/stdio/src/index.ts

@@ -2,7 +2,11 @@
  * The stdio app's readline UI: reads lines from stdin into `agent.send()` or
  * `steer()`, renders the durable event stream to stdout, and exits piped input
  * only after submitted work reaches idle.
- * @module @deepseek-ai/dsh-stdio-agent/stdio-chat
+ *
+ * This package is the independently composable stdio front door. It establishes
+ * the terminal channel and drives an agent created or resumed by app or
+ * developer code.
+ * @module @deepseek-ai/dsh-stdio
  */
 
 import { createInterface } from 'node:readline'
@@ -26,8 +30,6 @@ export const inject = ['agents', 'userInteraction']
 export interface Config {
   /** Banner printed once on start, before the first `> ` prompt. */
   welcome?: string
-  // TODO(fixed-stdio-agent): this app-internal plugin is mounted only for the
-  // precreated `main` agent; remove configurability and its config-only test.
   /** Id of the agent stdin drives (`send`/`steer`) and whose status gates the EOF exit; rendering is global. Defaults to `'main'`. */
   agent?: string
 }
@@ -350,16 +352,38 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt
   }, 'ui-stdio')
 }
 
+/**
+ * Open the terminal channel once its configured agent exists. Generated stdio
+ * projects boot the Cordis tree first and create or resume the agent from
+ * developer code immediately afterward, so stdin must remain untouched until
+ * the matching `agent/created` notification arrives.
+ * @param ctx - the context supplying the agent registry and event stream.
+ * @param config - presentation and target-agent configuration.
+ * @param runtime - process-I/O seam.
+ */
+export function mountStdio(ctx: Context, config: Config, runtime: StdioRuntime): void {
+  const agentId = AgentId(config.agent ?? 'main')
+  if (ctx.agents.get(agentId) !== undefined) {
+    createStdioChat(ctx, config, runtime)
+    return
+  }
+  const dispose = ctx.on('agent/created', (agent) => {
+    if (agent.id !== agentId) return
+    dispose()
+    createStdioChat(ctx, config, runtime)
+  })
+}
+
 /**
  * Cordis entry point. Binds the real `process` streams and delegates to
- * {@link createStdioChat}; the indirection keeps the side-effecting handles out
+ * {@link mountStdio}; the indirection keeps the side-effecting handles out
  * of the testable core, which is why the unit suite drives `createStdioChat`
  * directly. This thin wrapper is exercised end-to-end by the keyless
  * Loader-path e2e smoke in `examples/echo-agent` (the real product entry).
  */
 /* v8 ignore start -- production stdio wiring; testable core is createStdioChat() (covered), exercised e2e by echo-agent keyless smoke */
 export function apply(ctx: Context, config: Config): void {
-  createStdioChat(ctx, config, {
+  mountStdio(ctx, config, {
     input: process.stdin,
     output: process.stdout,
     exit: code => process.exit(code),

packages/ui/stdio/tests/plugin-shape.spec.ts

@@ -0,0 +1,19 @@
+import { describe, expect, it } from 'vitest'
+import Loader from '@cordisjs/plugin-loader'
+import * as stdio from '../src/index.ts'
+
+/** Real Loader export-path guard for the namespace stdio plugin. */
+describe('dsh-stdio plugin export shape', () => {
+  it('preserves name, inject, Config, and apply through Loader unwrapping', () => {
+    expect('default' in stdio).toBe(false)
+    expect(typeof stdio.apply).toBe('function')
+
+    const loader = Object.create(Loader.prototype) as Loader
+    const unwrapped = loader.unwrapExports(stdio) as Record<string, unknown>
+    expect(unwrapped).toBe(stdio)
+    expect(unwrapped.name).toBe('ui-stdio')
+    expect(unwrapped.inject).toEqual(['agents', 'userInteraction'])
+    expect(unwrapped.Config).toBeDefined()
+    expect(typeof unwrapped.apply).toBe('function')
+  })
+})

packages/ui/stdio/tests/readline.spec.ts

@@ -2,7 +2,7 @@ import { EventEmitter } from 'node:events'
 import type { Readable, Writable } from 'node:stream'
 import { describe, expect, it, vi } from 'vitest'
 import type { Context } from 'cordis'
-import type { StdioRuntime } from '../src/stdio-chat.ts'
+import type { StdioRuntime } from '../src/index.ts'
 
 const createInterface = vi.hoisted(() => vi.fn(() => {
   const reader = new EventEmitter() as EventEmitter & { close(): void }
@@ -33,7 +33,7 @@ function fakeRuntime(inputIsTTY: boolean, outputIsTTY: boolean): StdioRuntime {
 
 describe('createStdioChat readline mode', () => {
   it('enables terminal editing only when both stdio streams are TTYs', async () => {
-    const { createStdioChat } = await import('../src/stdio-chat.ts')
+    const { createStdioChat } = await import('../src/index.ts')
 
     const tty = fakeRuntime(true, true)
     createStdioChat(fakeContext(), {}, tty)

packages/ui/stdio/tests/stdio.spec.ts

@@ -6,7 +6,7 @@ import AgentRegistry from '@deepseek-ai/dsh-agent'
 import type { ContentBlock, StreamChunk } from '@deepseek-ai/dsh-llm'
 import type { Session, SessionEvent } from '@deepseek-ai/dsh-session'
 import UserInteractionService from '@deepseek-ai/dsh-user-interaction'
-import { createStdioChat, type Config, type StdioRuntime } from '../src/stdio-chat.ts'
+import { createStdioChat, mountStdio, type Config, type StdioRuntime } from '../src/index.ts'
 
 /**
  * Unit tests for the stdio UI plugin. They drive the REAL plugin body
@@ -93,6 +93,55 @@ function flushExit(): Promise<void> {
   return new Promise(resolve => setTimeout(resolve, 250))
 }
 
+describe('mountStdio readiness', () => {
+  it('leaves stdin untouched until the configured agent is created', async () => {
+    const ctx = new Context()
+    await ctx.plugin(AgentRegistry)
+    await ctx.plugin(UserInteractionService)
+    const { runtime, out } = makeRuntime()
+    const fiber = await ctx.plugin(Object.assign((inner: Context) => {
+      mountStdio(inner, CONFIG, runtime)
+    }, { inject: ['agents', 'userInteraction'] }))
+
+    expect(out.text()).toBe('')
+    ctx.agents.register(makeAgent('other'))
+    expect(out.text()).toBe('')
+    ctx.agents.register(makeAgent('main'))
+    expect(out.text()).toBe('hi there\n> ')
+    await fiber.dispose()
+  })
+
+  it('opens immediately when the configured agent already exists', async () => {
+    const ctx = new Context()
+    await ctx.plugin(AgentRegistry)
+    await ctx.plugin(UserInteractionService)
+    ctx.agents.register(makeAgent('main'))
+    const { runtime, out } = makeRuntime()
+    const fiber = await ctx.plugin(Object.assign((inner: Context) => {
+      mountStdio(inner, CONFIG, runtime)
+    }, { inject: ['agents', 'userInteraction'] }))
+
+    expect(out.text()).toBe('hi there\n> ')
+    await fiber.dispose()
+  })
+
+  it('waits for main when no target agent is configured', async () => {
+    const ctx = new Context()
+    await ctx.plugin(AgentRegistry)
+    await ctx.plugin(UserInteractionService)
+    const { runtime, out } = makeRuntime()
+    const fiber = await ctx.plugin(Object.assign((inner: Context) => {
+      mountStdio(inner, { welcome: 'ready' }, runtime)
+    }, { inject: ['agents', 'userInteraction'] }))
+
+    ctx.agents.register(makeAgent('other'))
+    expect(out.text()).toBe('')
+    ctx.agents.register(makeAgent('main'))
+    expect(out.text()).toBe('ready\n> ')
+    await fiber.dispose()
+  })
+})
+
 describe('createStdioChat rendering', () => {
   it('writes the welcome banner and prompt on start', async () => {
     const { out } = await setup()

packages/ui/stdio/tsconfig.json

@@ -0,0 +1,30 @@
+{
+  "extends": "../../../tsconfig.base.json",
+  "compilerOptions": {
+    "rootDir": "src",
+    "outDir": "lib/types"
+  },
+  "include": [
+    "src"
+  ],
+  "references": [
+    {
+      "path": "../../../vendor/cordis"
+    },
+    {
+      "path": "../../../vendor/schemastery"
+    },
+    {
+      "path": "../../core/agent"
+    },
+    {
+      "path": "../../core/session"
+    },
+    {
+      "path": "../../llm/llm"
+    },
+    {
+      "path": "../user-interaction"
+    }
+  ]
+}

packages/workflow/workflow-workerthread/README.md

@@ -2,6 +2,8 @@
 
 This package implements `WorkflowService` with one Node worker thread per run. The worker executes the orchestration script; child agents remain on the host and are reached through `ctx.subagents` over a typed host/worker protocol.
 
+The package root exports the default engine plugin and its `Config`; the worker protocol, runtime, and session modules stay private to the implementation. The operational `./worker` entry remains the engine's spawn target.
+
 The split has one primary purpose: a synchronous script loop cannot block the harness event loop, and a script that ignores cancellation can be terminated with its worker. It is not a security sandbox.
 
 ## Trust and isolation boundary

packages/workflow/workflow-workerthread/src/index.ts

@@ -18,11 +18,7 @@ import { validateMeta } from './meta.ts'
 import type { WorkerInit, WorkerLimits } from './types.ts'
 
 export { validateMeta } from './meta.ts'
-export { HostToWorkerType, WorkerToHostType } from './protocol.ts'
-export type { HostToWorkerMessage, HostToWorkerPayloads, WorkerToHostMessage, WorkerToHostPayloads } from './protocol.ts'
 export { materializeFromRealm, MaterializeError } from './realm.ts'
-export { WorkflowExecution, type ExecutionObserver } from './runtime.ts'
-export { requireParentPort, runWorkerSession } from './session.ts'
 export type {
   ChildHandle,
   ChildPort,
@@ -83,7 +79,7 @@ function assertBodyParses(body: string, name: string): void {
  * `result` never rejects; the `workflow/*` events fire around the run per
  * the seam contract.
  */
-export class WorkerWorkflowEngine extends WorkflowService {
+class WorkerWorkflowEngine extends WorkflowService {
   static inject = ['subagents']
 
   static Config: z<Config> = z.object({

packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts

@@ -9,7 +9,8 @@ import SubagentService from '@deepseek-ai/dsh-subagent'
 import type { SubagentCapabilities, SubagentProvider, SubagentResult, SubagentRun, SubagentStartRequest } from '@deepseek-ai/dsh-subagent'
 import type { WorkflowMeta, WorkflowResult, WorkflowResultInfo, WorkflowRunInfo } from '@deepseek-ai/dsh-workflow'
 import * as workerEngineModule from '../src/index.ts'
-import WorkerWorkflowEngine, { HostToWorkerType, WorkerToHostType, type Config } from '../src/index.ts'
+import WorkerWorkflowEngine, { type Config } from '../src/index.ts'
+import { HostToWorkerType, WorkerToHostType } from '../src/protocol.ts'
 
 /** A minimal parent stand-in: the engine only threads it through to the provider. */
 function fakeParent(): Agent {
@@ -1326,6 +1327,7 @@ describe('dsh-workflow-workerthread', () => {
 
     it('has the class-plugin export shape (default = the engine service class)', () => {
       expect(workerEngineModule.default).toBe(WorkerWorkflowEngine)
+      expect('WorkerWorkflowEngine' in workerEngineModule).toBe(false)
       const loader = Object.create(Loader.prototype) as Loader
       const unwrapped: unknown = loader.unwrapExports(workerEngineModule)
       expect(unwrapped).toBe(WorkerWorkflowEngine)