feat(agent): create/resume factory seam

Add the agent-creation factory seam on ctx.agents (AgentRegistry): setFactory/create/resume plus the AgentFactory interface and CreateAgentOptions/ResumeAgentOptions. AgentLoop implements AgentFactory and registers itself via ctx.agents.setFactory(this), so plugins create/resume agents through the interface without depending on the concrete loop package. - create({ agentId, sessionId, meta?, agentOptions? }) — programmatic create on a caller-supplied session id (e.g. an ACP-generated id). - resume({ agentId, resumeSessionId, agentOptions? }) — load a persisted session via ctx.sessionPersistence (RFC 009) and resume an agent on it; the live session id is the resumed id, turn numbering and derived history continue from the loaded log. sessionPersistence is NOT hard-injected (non-persistent demos still work); resume rejects with a typed error when it is absent. assertAgentIdFree runs before any session is created (and again after the load await) so a duplicate id never leaves an orphaned live session. Adds the runtime dsh-session-persistence dependency to agent-loop.
2026-06-15 21:12:14 +08:00
parent df4b7d3d9a
commit 9a4006cb2b
13 changed files with 516 additions and 25 deletions
--- a/packages/agent-loop/README.md
+++ b/packages/agent-loop/README.md
@@ -8,7 +8,12 @@ This is the only package in the harness that contains concrete loop logic. Every

 ### Public API

- `ctx.agentLoop.create(id: string, options?: AgentOptions): LoopAgent` — create an agent on a fresh per-run session id `${id}-session-<uuid>`, start its loop, and register it in `ctx.agents`. The per-run uuid avoids colliding with the on-disk log a prior run materialized once a durable persistence backend is loaded; each run is a new session (a deliberate demo simplification — a real resume-or-create policy is a TODO). Disposed with the calling fiber.
+- `ctx.agentLoop.create(id: string, options?: AgentOptions): LoopAgent` — config-driven create: an agent on a fresh per-run session id `${id}-session-<uuid>` (no cwd). Used for `cordis.yml`-configured agents. The per-run uuid avoids colliding with the on-disk log a prior run materialized once a durable persistence backend is loaded; each run is a new session (a deliberate demo simplification — a real resume-or-create policy is a TODO). Disposed with the calling fiber.
+
+`AgentLoop` also implements the `AgentFactory` seam and registers itself via `ctx.agents.setFactory(this)`, so plugins create/resume agents through `ctx.agents` (the interface):
+
+- `ctx.agents.create({ agentId, sessionId, meta?, agentOptions? })` — programmatic create on a caller-supplied `sessionId` (e.g. an ACP-generated id), NOT `${id}-session`.
+- `ctx.agents.resume({ agentId, resumeSessionId, agentOptions? })` — load a persisted session via `ctx.sessionPersistence` (RFC 009) and resume an agent on it. The live session id is the resumed id; turn numbering and derived history continue from the loaded log. Requires a session-persistence backend (NOT hard-injected — non-persistent demos still work; `resume` rejects with a typed error when persistence is absent).

 ### Injected services

--- a/packages/agent-loop/package.json
+++ b/packages/agent-loop/package.json
@@ -23,6 +23,7 @@
    "@deepseek-ai/dsh-agent": "^0.0.1",
    "@deepseek-ai/dsh-llm": "^0.0.1",
    "@deepseek-ai/dsh-session": "^0.0.1",
+    "@deepseek-ai/dsh-session-persistence": "^0.0.1",
    "@deepseek-ai/dsh-system-prompt": "^0.0.1",
    "@deepseek-ai/dsh-tools": "^0.0.1",
    "cordis": "^4.0.0-rc.6"
@@ -35,6 +36,7 @@
    "@deepseek-ai/dsh-invariants": "^0.0.1",
    "@deepseek-ai/dsh-llm": "^0.0.1",
    "@deepseek-ai/dsh-session": "^0.0.1",
+    "@deepseek-ai/dsh-session-persistence": "^0.0.1",
    "@deepseek-ai/dsh-session-persistence-jsonl": "^0.0.1",
    "@deepseek-ai/dsh-system-prompt": "^0.0.1",
    "@deepseek-ai/dsh-tools": "^0.0.1",
--- a/packages/agent-loop/src/index.ts
+++ b/packages/agent-loop/src/index.ts
@@ -11,11 +11,13 @@ import { Context, Service } from 'cordis'
 import { randomUUID } from 'node:crypto'
 import z from 'schemastery'
 import { AgentId } from '@deepseek-ai/dsh-agent'
-import type { AgentOptions } from '@deepseek-ai/dsh-agent'
+import type { Agent, AgentFactory, AgentOptions, CreateAgentOptions, ResumeAgentOptions } from '@deepseek-ai/dsh-agent'
 import type {} from '@deepseek-ai/dsh-llm'
-import type {} from '@deepseek-ai/dsh-session'
+import { SessionId } from '@deepseek-ai/dsh-session'
+import type { Session } from '@deepseek-ai/dsh-session'
 import type {} from '@deepseek-ai/dsh-system-prompt'
 import type {} from '@deepseek-ai/dsh-tools'
+import type {} from '@deepseek-ai/dsh-session-persistence'
 import { LoopAgent } from './agent.ts'

 export { LoopAgent } from './agent.ts'
@@ -35,13 +37,15 @@ export interface Config {

 /**
 * The agent-loop plugin (`ctx.agentLoop`): creates {@link LoopAgent}s, runs
- * their loops, and registers them in `ctx.agents`.
+ * their loops, and registers them in `ctx.agents`. Also implements the
+ * {@link AgentFactory} seam, so plugins create/resume agents through
+ * `ctx.agents` (the interface) without depending on this concrete package.
 *
 * The loop itself is deliberately thin — every behavior beyond "call the
 * model, run the tools, repeat" belongs to plugins listening on the event
 * taxonomy declared in @deepseek-ai/dsh-agent.
 */
-export class AgentLoop extends Service {
+export class AgentLoop extends Service implements AgentFactory {
  static inject = ['agents', 'sessions', 'llm', 'tools', 'systemPrompt']

  static Config: z<Config> = z.object({
@@ -54,20 +58,23 @@ export class AgentLoop extends Service {

  constructor(ctx: Context, public config: Config) {
    super(ctx, 'agentLoop')
+    // Provide the agent-creation factory to the registry (effect-scoped: the
+    // slot is cleared on dispose).
+    ctx.effect(() => this.ctx.agents.setFactory(this), 'agentLoop.setFactory()')
    for (const { id, ...options } of config.agents) {
      this.create(id, options)
    }
  }

  /**
-   * Create an agent, start its loop, and register it. Returns the agent.
-   * Disposed with the calling fiber.
+   * Config-driven create: an agent on a FRESH, non-colliding session id per run
+   * (`${id}-session-<uuid>`, no cwd). Used for `cordis.yml`-configured agents
+   * and as the shared core for the programmatic factory {@link createAgent}.
   *
-   * The session id is per-run (`${id}-session-<uuid>`, no fixed name): once a
-   * durable persistence backend is loaded, a fixed `${id}-session` collides on
-   * the second run — the backend refuses to re-create an id whose log already
-   * exists on disk (the SessionId is the identity). A fresh id means each run
-   * is a new session.
+   * Why a per-run id, not a fixed `${id}-session`: once a durable persistence
+   * backend is loaded, a fixed id collides on the second run — the backend
+   * refuses to re-create an id whose log already exists on disk (the SessionId
+   * is the identity). A fresh id means each run is a new session.
   *
   * TODO(demo): each run starting a brand-new session is fine for demos but is
   * NOT real conversation continuity. A production config-driven agent needs a
@@ -80,14 +87,92 @@ export class AgentLoop extends Service {
   * fresh; the child is returned as a regular Agent handle.
   */
  create(id: string, options: AgentOptions = {}): LoopAgent {
+    this.assertAgentIdFree(id)
    const session = this.ctx.sessions.create(`${id}-session-${randomUUID()}`, { meta: {} })
-    const agent = new LoopAgent(this.ctx, AgentId(id), options, session)
+    return this.start(AgentId(id), options, session)
+  }
+
+  /**
+   * Programmatic factory create ({@link AgentFactory}): an agent on a
+   * caller-supplied `sessionId` (NOT `${id}-session`), with optional session
+   * metadata (validated `cwd`, lineage). The ACP bridge uses this so the
+   * client-generated session id becomes the live/persisted session id.
+   */
+  createAgent(options: CreateAgentOptions): Agent {
+    // Check the agent id BEFORE creating the session: register() would reject a
+    // duplicate id only AFTER sessions.create(), leaving an orphaned live
+    // session (and lazy persistence state) that blocks reuse of that id.
+    this.assertAgentIdFree(options.agentId)
+    const session = this.ctx.sessions.create(options.sessionId, { meta: options.meta ?? {} })
+    return this.start(AgentId(options.agentId), options.agentOptions ?? {}, session)
+  }
+
+  /**
+   * Resume an agent on a persisted session ({@link AgentFactory}). Loads the
+   * session log + metadata via `ctx.sessionPersistence`, reconstructs the live
+   * session with the loaded events (so `lastTurnNumber`/`deriveMessages`
+   * continue), and starts a fresh agent on it. The live session id is the
+   * resumed id, NOT `${agentId}-session`.
+   *
+   * Requires `ctx.sessionPersistence`; throws a typed error if it is not
+   * configured. NOT hard-injected (that would make non-persistent demos pend
+   * forever) — callers that need resume (ACP) inject `sessionPersistence`, so
+   * by the time this runs the service exists.
+   */
+  async resume(options: ResumeAgentOptions): Promise<Agent> {
+    this.assertAgentIdFree(options.agentId)
+    const persistence = this.ctx.sessionPersistence
+    // `sessionPersistence` is declaration-merged onto Context as non-optional,
+    // but the service is only present when a backend plugin is loaded — and
+    // AgentLoop deliberately does NOT inject it (that would pend non-persistent
+    // demos forever). So the runtime value can be undefined; the type cannot.
+    // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition
+    if (persistence === undefined) {
+      throw new Error('cannot resume: session persistence is not configured (load a dsh-session-persistence backend)')
+    }
+    const { meta, events } = await persistence.load(SessionId(options.resumeSessionId))
+    // Re-check the agent id AFTER the await: the pre-load check above can go
+    // stale while load() is pending (a concurrent resume/create may register the
+    // same id). Re-checking immediately before sessions.create() keeps the
+    // "no orphaned session on a duplicate id" guarantee under concurrency.
+    this.assertAgentIdFree(options.agentId)
+    // Reconstruct the live session with the FULL persisted header (createdAt,
+    // cwd, lineage) so resume preserves identity, not just the cwd. The seed
+    // events make lastTurnNumber/deriveMessages continue; the backend already
+    // has state (cursor) from the load above, so onCreated is a no-op and the
+    // seed is not re-persisted.
+    const session = this.ctx.sessions.create(options.resumeSessionId, {
+      seed: events,
+      meta: {
+        createdAt: meta.createdAt,
+        ...meta.cwd !== undefined ? { cwd: meta.cwd } : {},
+        ...meta.parentSession !== undefined ? { parentSession: meta.parentSession } : {},
+      },
+    })
+    return this.start(AgentId(options.agentId), options.agentOptions ?? {}, session)
+  }
+
+  /**
+   * Reject a duplicate agent id BEFORE any session is created, so a failed
+   * factory call never leaves an orphaned live session (and lazy persistence
+   * state) behind. `register()` enforces the same uniqueness, but only after
+   * `sessions.create()` has already run.
+   */
+  private assertAgentIdFree(id: string): void {
+    if (this.ctx.agents.get(id) !== undefined) {
+      throw new Error(`agent "${id}" is already registered`)
+    }
+  }
+
+  /** Shared: construct a LoopAgent, register it, and start its loop (LIFO). */
+  private start(id: AgentId, options: AgentOptions, session: Session): LoopAgent {
+    const agent = new LoopAgent(this.ctx, id, options, session)
    // Generator effect: stop and unregister are independent disposables
    // (LIFO), so a throwing stop() cannot leak the registry entry.
    this.ctx.effect(function* (this: AgentLoop) {
      yield this.ctx.agents.register(agent)
      yield agent.start()
-    }.bind(this), 'agentLoop.create()')
+    }.bind(this), 'agentLoop.start()')
    return agent
  }
 }
--- a/packages/agent-loop/tests/resume.spec.ts
+++ b/packages/agent-loop/tests/resume.spec.ts
@@ -0,0 +1,241 @@
+import { afterEach, describe, expect, it } from 'vitest'
+import { Context } from '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 SessionStore, { Session, SessionId } from '@deepseek-ai/dsh-session'
+import type { SessionEvent } from '@deepseek-ai/dsh-session'
+import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
+import ToolRegistry from '@deepseek-ai/dsh-tools'
+import AgentRegistry from '@deepseek-ai/dsh-agent'
+import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
+import AgentLoop, { LoopAgent } from '@deepseek-ai/dsh-agent-loop'
+import { MockAdapter, textResponse } from './mock-adapter.ts'
+
+const dirs: string[] = []
+afterEach(async () => { for (const d of dirs.splice(0)) await rm(d, { recursive: true, force: true }) })
+
+async function persistentHarness(adapter: MockAdapter): Promise<{ ctx: Context; root: string }> {
+  const root = await mkdtemp(join(tmpdir(), 'dsh-resume-'))
+  dirs.push(root)
+  const ctx = new Context()
+  await ctx.plugin(LlmService)
+  await ctx.plugin(SessionStore)
+  await ctx.plugin(SystemPrompt)
+  await ctx.plugin(ToolRegistry)
+  await ctx.plugin(AgentRegistry)
+  await ctx.plugin(AgentLoop, { agents: [] })
+  await ctx.plugin(SessionPersistenceJsonl, { root })
+  ctx.llm.registerAdapter(['mock'], adapter)
+  return { ctx, root }
+}
+
+function waitForIdle(ctx: Context, agent: LoopAgent): Promise<void> {
+  return new Promise((resolve) => {
+    const dispose = ctx.on('agent/status', (subject, status) => {
+      if (subject === agent && status === 'idle') { dispose(); resolve() }
+    })
+  })
+}
+
+describe('RFC 009: AgentLoop factory create/resume', () => {
+  it('createAgent uses the caller-supplied sessionId (not ${id}-session)', async () => {
+    const adapter = new MockAdapter([textResponse('hi')])
+    const { ctx } = await persistentHarness(adapter)
+    const agent = ctx.agents.create({ agentId: 'a1', sessionId: 'custom-session', meta: { cwd: '/w' } })
+    expect(agent.session.id).toBe('custom-session')
+    expect(agent.session.header.cwd).toBe('/w')
+    await ctx.fiber.dispose()
+  })
+
+  it('createAgent rejects a duplicate agent id BEFORE creating the session (no orphan)', async () => {
+    const adapter = new MockAdapter([textResponse('hi')])
+    const { ctx } = await persistentHarness(adapter)
+    ctx.agents.create({ agentId: 'dup', sessionId: 'sess-a' })
+    // A second create with the SAME agent id but a fresh session id must reject
+    // up front — and must NOT leave an orphaned 'sess-b' session behind.
+    expect(() => ctx.agents.create({ agentId: 'dup', sessionId: 'sess-b' })).toThrow(/already registered/)
+    expect(ctx.sessions.get('sess-b')).toBeUndefined()
+    await ctx.fiber.dispose()
+  })
+
+  it('createAgent works without meta (no cwd)', async () => {
+    const adapter = new MockAdapter([textResponse('hi')])
+    const { ctx } = await persistentHarness(adapter)
+    const agent = ctx.agents.create({ agentId: 'a-nometa', sessionId: 'nometa-session' })
+    expect(agent.session.id).toBe('nometa-session')
+    expect(agent.session.header.cwd).toBeUndefined()
+    await ctx.fiber.dispose()
+  })
+
+  it('resume of a session with no cwd carries an undefined cwd header', async () => {
+    // Lifecycle 1: create a no-cwd session and run a turn.
+    const adapter1 = new MockAdapter([textResponse('a')])
+    const { ctx: ctx1, root } = await persistentHarness(adapter1)
+    const a1 = ctx1.agents.create({ agentId: 'm', sessionId: 'nocwd-sess' }) as LoopAgent
+    a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } })
+    await waitForIdle(ctx1, a1)
+    await ctx1.fiber.dispose()
+
+    // 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(SessionStore)
+    await ctx2.plugin(SystemPrompt)
+    await ctx2.plugin(ToolRegistry)
+    await ctx2.plugin(AgentRegistry)
+    await ctx2.plugin(AgentLoop, { agents: [] })
+    await ctx2.plugin(SessionPersistenceJsonl, { root })
+    ctx2.llm.registerAdapter(['mock'], adapter2)
+    const a2 = await ctx2.agents.resume({ agentId: 'm', resumeSessionId: 'nocwd-sess' }) as LoopAgent
+    expect(a2.session.header.cwd).toBeUndefined()
+    await ctx2.fiber.dispose()
+  })
+
+  it('resume of a forked session preserves the parentSession lineage in the header', async () => {
+    // Lifecycle 1: persist a FORKED session (carries parentSession in its
+    // header) by creating it with a complete-turn seed — the write path
+    // materializes the fork (header + seed) on disk.
+    const seed: SessionEvent[] = [
+      { type: 'turn/start', seq: 0, time: 1, data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } } },
+      { type: 'turn/end', seq: 1, time: 2, data: { turn: 1, reason: { kind: 'completed' } } },
+    ]
+    const adapter1 = new MockAdapter([textResponse('a')])
+    const { ctx: ctx1, root } = await persistentHarness(adapter1)
+    const forked = ctx1.sessions.create('forked-sess', { seed, meta: { cwd: '/w', parentSession: SessionId('parent-sess') } })
+    await ctx1.parallel('session/flush', forked)
+    await ctx1.fiber.dispose()
+
+    // Lifecycle 2: resume it; the parentSession header survives the round-trip
+    // (exercises resume's parentSession-present branch).
+    const adapter2 = new MockAdapter([textResponse('b')])
+    const ctx2 = new Context()
+    await ctx2.plugin(LlmService)
+    await ctx2.plugin(SessionStore)
+    await ctx2.plugin(SystemPrompt)
+    await ctx2.plugin(ToolRegistry)
+    await ctx2.plugin(AgentRegistry)
+    await ctx2.plugin(AgentLoop, { agents: [] })
+    await ctx2.plugin(SessionPersistenceJsonl, { root })
+    ctx2.llm.registerAdapter(['mock'], adapter2)
+    const a2 = await ctx2.agents.resume({ agentId: 'm', resumeSessionId: 'forked-sess' }) as LoopAgent
+    expect(a2.session.header.parentSession).toBe('parent-sess')
+    expect(a2.session.header.cwd).toBe('/w')
+    await ctx2.fiber.dispose()
+  })
+
+  it('an idle inject() is flushed durably on its own (survives without explicit flush/dispose)', async () => {
+    // Lifecycle 1: run a turn, then inject context while idle. The idle inject
+    // wraps its context/message in a one-shot turn AND checkpoints it (ADR 0017)
+    // — without an explicit flush or clean dispose, the notice must still reach
+    // disk, since a crash before the next turn would otherwise lose it.
+    const adapter1 = new MockAdapter([textResponse('answer')])
+    const { ctx: ctx1, root } = await persistentHarness(adapter1)
+    const a1 = ctx1.agents.create({ agentId: 'm', sessionId: 'inject-sess', meta: { cwd: '/w' } }) as LoopAgent
+    a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } })
+    await waitForIdle(ctx1, a1)
+    a1.inject([{ type: 'text', text: 'background task 42 finished' }], { source: { kind: 'plugin', plugin: 'tool-bash' } })
+    // Let inject()'s fire-and-forget flush settle (NO explicit flush/dispose).
+    await new Promise(r => setTimeout(r, 30))
+
+    // A SEPARATE backend reads the on-disk log — proving the inject persisted
+    // itself, not a later dispose drain.
+    const probe = new Context()
+    await probe.plugin(SessionStore)
+    await probe.plugin(SessionPersistenceJsonl, { root })
+    const loaded = await probe.sessionPersistence.load(SessionId('inject-sess'))
+    expect(JSON.stringify(loaded.events)).toContain('background task 42 finished')
+    await probe.fiber.dispose()
+    await ctx1.fiber.dispose()
+  })
+
+  it('an idle inject() survives persist + resume (turn-enclosed, not dropped as crash tail)', async () => {
+    // Lifecycle 1: run a turn, then inject context while idle. The idle inject
+    // wraps its context/message in a one-shot turn so it is turn-enclosed —
+    // otherwise scanLog would treat the trailing context as a crash tail and
+    // drop it on reload (the bug this guards).
+    const adapter1 = new MockAdapter([textResponse('answer')])
+    const { ctx: ctx1, root } = await persistentHarness(adapter1)
+    const a1 = ctx1.agents.create({ agentId: 'm', sessionId: 'inject-sess', meta: { cwd: '/w' } }) as LoopAgent
+    a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } })
+    await waitForIdle(ctx1, a1)
+    a1.inject([{ type: 'text', text: 'background task 42 finished' }], { source: { kind: 'plugin', plugin: 'tool-bash' } })
+    await ctx1.parallel('session/flush', a1.session)
+    await ctx1.fiber.dispose()
+
+    // Lifecycle 2: resume; the injected context is still in the derived history.
+    const adapter2 = new MockAdapter([textResponse('next')])
+    const ctx2 = new Context()
+    await ctx2.plugin(LlmService)
+    await ctx2.plugin(SessionStore)
+    await ctx2.plugin(SystemPrompt)
+    await ctx2.plugin(ToolRegistry)
+    await ctx2.plugin(AgentRegistry)
+    await ctx2.plugin(AgentLoop, { agents: [] })
+    await ctx2.plugin(SessionPersistenceJsonl, { root })
+    ctx2.llm.registerAdapter(['mock'], adapter2)
+    const a2 = await ctx2.agents.resume({ agentId: 'm', resumeSessionId: 'inject-sess' }) as LoopAgent
+    const flat = JSON.stringify(a2.session.deriveMessages())
+    expect(flat).toContain('background task 42 finished')
+    await ctx2.fiber.dispose()
+  })
+
+  it('resume reloads a persisted session: history + turn numbering continue, no duplicate seqs', async () => {
+    // Lifecycle 1: run one full turn, persisting it.
+    const adapter1 = new MockAdapter([textResponse('first answer')])
+    const { ctx: ctx1, root } = await persistentHarness(adapter1)
+    const a1 = ctx1.agents.create({ agentId: 'main', sessionId: 'sess-resume', meta: { cwd: '/w' } }) as LoopAgent
+    a1.send([{ type: 'text', text: 'first question' }], { source: { kind: 'user' } })
+    await waitForIdle(ctx1, a1)
+    const events1 = [...a1.session.events]
+    const seqs1 = events1.map(e => e.seq)
+    expect(seqs1).toEqual([...seqs1].sort((x, y) => x - y)) // contiguous
+    await ctx1.fiber.dispose()
+
+    // 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(SessionStore)
+    await ctx2.plugin(SystemPrompt)
+    await ctx2.plugin(ToolRegistry)
+    await ctx2.plugin(AgentRegistry)
+    await ctx2.plugin(AgentLoop, { agents: [] })
+    await ctx2.plugin(SessionPersistenceJsonl, { root })
+    ctx2.llm.registerAdapter(['mock'], adapter2)
+
+    const a2 = await ctx2.agents.resume({ agentId: 'main', resumeSessionId: 'sess-resume' }) as LoopAgent
+    // The resumed session carries the prior history…
+    expect(a2.session.id).toBe('sess-resume')
+    expect(a2.session.events.length).toBe(events1.length)
+    const replay = new Session(SessionId('replay'), events1)
+    expect(a2.session.deriveMessages()).toEqual(replay.deriveMessages())
+
+    // …and a new turn continues numbering (turn 2) with contiguous seqs.
+    a2.send([{ type: 'text', text: 'second question' }], { source: { kind: 'user' } })
+    await waitForIdle(ctx2, a2)
+    const allSeqs = a2.session.events.map(e => e.seq)
+    expect(allSeqs).toEqual(allSeqs.map((_, i) => i)) // 0..N contiguous, no duplicates
+    const turnStarts = a2.session.events.filter(e => e.type === 'turn/start')
+    expect(turnStarts.map(e => e.type === 'turn/start' && e.data.turn)).toEqual([1, 2])
+    await ctx2.fiber.dispose()
+  })
+
+  it('resume rejects when session persistence is not configured', async () => {
+    // A harness WITHOUT the persistence plugin.
+    const adapter = new MockAdapter([textResponse('x')])
+    const ctx = new Context()
+    await ctx.plugin(LlmService)
+    await ctx.plugin(SessionStore)
+    await ctx.plugin(SystemPrompt)
+    await ctx.plugin(ToolRegistry)
+    await ctx.plugin(AgentRegistry)
+    await ctx.plugin(AgentLoop, { agents: [] })
+    ctx.llm.registerAdapter(['mock'], adapter)
+    await expect(ctx.agents.resume({ agentId: 'm', resumeSessionId: 'nope' }))
+      .rejects.toThrow(/session persistence is not configured/)
+    await ctx.fiber.dispose()
+  })
+})
--- a/packages/agent-loop/tsconfig.json
+++ b/packages/agent-loop/tsconfig.json
@@ -11,6 +11,7 @@
    { "path": "../../vendor/schemastery" },
    { "path": "../llm" },
    { "path": "../session" },
+    { "path": "../session-persistence" },
    { "path": "../system-prompt" },
    { "path": "../tools" },
    { "path": "../agent" }
--- a/packages/agent/README.md
+++ b/packages/agent/README.md
@@ -8,10 +8,18 @@ Tracks live agents so UI, hook, and orchestrator plugins can find them without i

 ### Public API

- `ctx.agents.register(agent: Agent): () => void` Register a live agent. Disposed with the calling fiber.
+- `ctx.agents.register(agent: Agent): () => void` — record an **already-constructed** agent. Disposed with the calling fiber.
 - `ctx.agents.get(id: string): Agent | undefined`
 - `ctx.agents.list(): Agent[]`

+#### Factory seam (creation)
+
+Agent *creation* is provided by whichever plugin implements `AgentFactory` (phase 1: `dsh-agent-loop`), registered via `setFactory`. This keeps creation on the `dsh-agent` interface so consumers (UI, the ACP bridge) program against `ctx.agents` without depending on the concrete loop package.
+
+- `ctx.agents.setFactory(factory: AgentFactory): () => void` — register the creation factory (the loop calls this on construction). Throws on a second factory; the slot clears on dispose.
+- `ctx.agents.create(options: CreateAgentOptions): Agent` — construct, start, AND register a new agent on a caller-supplied `sessionId` (with optional `meta.cwd`). Distinct from `register` (which only records). Throws if no factory is registered.
+- `ctx.agents.resume(options: ResumeAgentOptions): Promise<Agent>` — load a persisted session (RFC 009) and resume an agent on it. Async; rejects if no factory is registered, or if the factory finds session persistence unconfigured.
+
 ### Events

 The full `agent/*` event taxonomy is declared via declaration merging in `dsh-agent` (not `dsh-agent-loop`), so plugins depend only on this package.
@@ -45,7 +53,7 @@ The handle every plugin programs against:

 - `agent.send(content, options?)` — queue a message; starts a turn when idle
 - `agent.steer(content, options?)` — steer a running turn (inject between steps); behaves like `send` when idle
- `agent.inject(content, options?)` — inject in-session context (context/message event); next request sees it. While running it joins the open turn; while idle it is wrapped in a one-shot `injection` turn so every event stays turn-enclosed (ADR 0017)
+- `agent.inject(content, options?)` — inject in-session context without triggering a turn (context/message event); next request sees it
 - `agent.abort(reason?)` — abort the in-flight step
 - `agent.session`, `agent.status`, `agent.options`, `agent.id`

--- a/packages/agent/src/index.ts
+++ b/packages/agent/src/index.ts
@@ -6,7 +6,8 @@
 */

 import { Context, Service } from 'cordis'
-import type { Agent } from './types.ts'
+import type { SessionId } from '@deepseek-ai/dsh-session'
+import type { Agent, AgentOptions } from './types.ts'

 export * from './types.ts'

@@ -16,19 +17,110 @@ declare module 'cordis' {
  }
 }

+/**
+ * Options for programmatically creating an agent through the registry factory
+ * ({@link AgentRegistry.create}). The caller supplies the live `sessionId`
+ * (e.g. an ACP-generated id) and optional session metadata (the validated
+ * `cwd`, fork lineage); the factory creates the session, the agent, and wires
+ * them together.
+ */
+export interface CreateAgentOptions {
+  /** The agent's id (the registry handle). */
+  agentId: string
+  /** The live session's id (NOT derived from agentId). */
+  sessionId: string
+  /**
+   * Session creation metadata: validated absolute `cwd` and `parentSession`
+   * fork lineage. Mirrors the `cwd`/`parentSession` fields of
+   * {@link CreateSessionOptions.meta} in dsh-session (the internal-only
+   * `createdAt`, used when reconstructing a persisted session, is deliberately
+   * excluded — a factory caller never sets it).
+   */
+  meta?: { cwd?: string; parentSession?: SessionId }
+  /** Per-agent options (model, system prompt). */
+  agentOptions?: AgentOptions
+}
+
+/**
+ * Options for resuming an agent on a persisted session
+ * ({@link AgentRegistry.resume}).
+ */
+export interface ResumeAgentOptions {
+  /** The agent's id (the registry handle). */
+  agentId: string
+  /** The persisted session id to load and resume on. */
+  resumeSessionId: string
+  /** Per-agent options (model, system prompt). */
+  agentOptions?: AgentOptions
+}
+
+/**
+ * The agent-creation factory the loop implementation provides to the registry
+ * via {@link AgentRegistry.setFactory}. Kept on the `dsh-agent` interface so
+ * consumers (e.g. the ACP bridge) program against `ctx.agents` without
+ * depending on the concrete `dsh-agent-loop` package.
+ */
+export interface AgentFactory {
+  /** Create, start, and register a new agent on a caller-supplied session id. */
+  createAgent(options: CreateAgentOptions): Agent
+  /**
+   * Load a persisted session and resume an agent on it. Async because it awaits
+   * `ctx.sessionPersistence.load`; must be called after that service exists
+   * (consumers inject `sessionPersistence`).
+   */
+  resume(options: ResumeAgentOptions): Promise<Agent>
+}
+
 /**
 * Agent registry (`ctx.agents`): tracks live agents so UI, hook, and
 * orchestrator plugins can find them without depending on the concrete loop
- * package. Agent *creation* belongs to whichever plugin implements the Agent
- * interface (phase 1: `@deepseek-ai/dsh-agent-loop`).
+ * package. Agent *creation* is provided by whichever plugin implements the
+ * {@link AgentFactory} (phase 1: `@deepseek-ai/dsh-agent-loop`), registered via
+ * {@link setFactory}.
 */
 export class AgentRegistry extends Service {
  private store = new Map<string, Agent>()
+  private factory: AgentFactory | undefined

  constructor(ctx: Context) {
    super(ctx, 'agents')
  }

+  /**
+   * Register the agent-creation factory (the loop calls this on construction,
+   * effect-scoped). Throws if a factory is already registered. Returns the
+   * disposer; on dispose the factory slot is cleared.
+   */
+  setFactory(factory: AgentFactory): () => void {
+    const dispose = this.ctx.effect(() => {
+      if (this.factory !== undefined) throw new Error('an agent factory is already registered')
+      this.factory = factory
+      return () => { this.factory = undefined }
+    }, 'agents.setFactory()')
+    return () => void dispose()
+  }
+
+  /**
+   * Create, start, and register a new agent through the registered factory.
+   * Distinct from {@link register} (which records an already-constructed
+   * agent): this constructs the agent and its session. Throws if no factory is
+   * registered.
+   */
+  create(options: CreateAgentOptions): Agent {
+    if (this.factory === undefined) throw new Error('no agent factory registered (load an agent-loop plugin)')
+    return this.factory.createAgent(options)
+  }
+
+  /**
+   * Load a persisted session and resume an agent on it through the registered
+   * factory. Rejects if no factory is registered; the factory rejects if
+   * session persistence is not configured.
+   */
+  async resume(options: ResumeAgentOptions): Promise<Agent> {
+    if (this.factory === undefined) throw new Error('no agent factory registered (load an agent-loop plugin)')
+    return this.factory.resume(options)
+  }
+
  /**
   * Register a live agent. Throws if an agent with the same id is already
   * registered. Emits `agent/created` on registration and `agent/disposed`
--- a/packages/agent/tests/agent.spec.ts
+++ b/packages/agent/tests/agent.spec.ts
@@ -74,3 +74,58 @@ describe('AgentRegistry', () => {
    expect(ctx.agents.get('main')).toBeUndefined()
  })
 })
+
+describe('AgentRegistry factory seam', () => {
+  /** A stub AgentFactory that records calls and returns a stub agent. */
+  function stubFactory() {
+    const calls: { create: unknown[]; resume: unknown[] } = { create: [], resume: [] }
+    const factory: import('@deepseek-ai/dsh-agent').AgentFactory = {
+      createAgent(options) { calls.create.push(options); return stubAgent(options.agentId) },
+      resume(options) { calls.resume.push(options); return Promise.resolve(stubAgent(options.agentId)) },
+    }
+    return { factory, calls }
+  }
+
+  it('create()/resume() throw when no factory is registered', async () => {
+    const ctx = new Context()
+    await ctx.plugin(AgentRegistry)
+    expect(() => ctx.agents.create({ agentId: 'a', sessionId: 's' })).toThrow(/no agent factory/)
+    await expect(ctx.agents.resume({ agentId: 'a', resumeSessionId: 's' })).rejects.toThrow(/no agent factory/)
+  })
+
+  it('setFactory registers a factory; create/resume delegate to it', async () => {
+    const ctx = new Context()
+    await ctx.plugin(AgentRegistry)
+    const { factory, calls } = stubFactory()
+    ctx.agents.setFactory(factory)
+
+    const created = ctx.agents.create({ agentId: 'c1', sessionId: 'sess-1', meta: { cwd: '/w' } })
+    expect(created.id).toBe('c1')
+    expect(calls.create).toEqual([{ agentId: 'c1', sessionId: 'sess-1', meta: { cwd: '/w' } }])
+
+    const resumed = await ctx.agents.resume({ agentId: 'r1', resumeSessionId: 'old-sess' })
+    expect(resumed.id).toBe('r1')
+    expect(calls.resume).toEqual([{ agentId: 'r1', resumeSessionId: 'old-sess' }])
+  })
+
+  it('setFactory rejects a second factory', async () => {
+    const ctx = new Context()
+    await ctx.plugin(AgentRegistry)
+    ctx.agents.setFactory(stubFactory().factory)
+    expect(() => ctx.agents.setFactory(stubFactory().factory)).toThrow(/already registered/)
+  })
+
+  it('disposing the setFactory fiber clears the factory (HMR safety)', async () => {
+    const ctx = new Context()
+    await ctx.plugin(AgentRegistry)
+    let dispose!: () => void
+    const fiber = await ctx.plugin(Object.assign((inner: Context) => {
+      dispose = inner.agents.setFactory(stubFactory().factory)
+    }, { inject: ['agents'] }))
+    expect(() => ctx.agents.create({ agentId: 'a', sessionId: 's' })).not.toThrow()
+    void dispose
+    await fiber.dispose()
+    // factory slot cleared → create throws again
+    expect(() => ctx.agents.create({ agentId: 'a2', sessionId: 's2' })).toThrow(/no agent factory/)
+  })
+})