fix: coordinate overlapping configured reloads

packages/core/agent-loop/README.md

@@ -41,7 +41,7 @@ interface Config {
 }
 ```
 
-Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. While the factory is active, a declarative lookup, resume, setup, or publication failure is contained, logged, and emitted as `agent-loop/config-start-failed(sessionId, error)` because no live `Agent` exists for an `agent/*` signal; cancellation caused by factory teardown is silent. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin.
+Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. An overlapping remount waits for an already-disposed same-id agent to finish detaching both registries before it inspects persistence, so asynchronous teardown cannot strand the configured identity. While the factory is active, a declarative lookup, resume, setup, or publication failure is contained, logged, and emitted as `agent-loop/config-start-failed(sessionId, error)` because no live `Agent` exists for an `agent/*` signal; cancellation caused by factory teardown is silent. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin.
 
 ### Exported concrete class
 

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

@@ -53,6 +53,7 @@ function renderThrown(value: unknown): string {
 /** Factory-level ownership of every preparing or live transaction. */
 class FactoryOwnership {
   private accepting = true
+  private readonly inactive = Promise.withResolvers<void>()
   private transactions = new Set<AgentCreationTransaction>()
   private startupTasks = new Set<Promise<void>>()
 
@@ -74,8 +75,14 @@ class FactoryOwnership {
     void task.then(forget, forget)
   }
 
+  /** Resolve `task`, or stop waiting when factory teardown begins. */
+  async waitWhileActive(task: Promise<void>): Promise<void> {
+    await Promise.race([task, this.inactive.promise])
+  }
+
   async dispose(): Promise<void> {
     this.accepting = false
+    this.inactive.resolve()
     const reason = new Error('agent loop is not active')
     await Promise.all([
       ...[...this.transactions].map(transaction => transaction.disposeForFactory(reason)),
@@ -455,6 +462,8 @@ export class AgentLoop extends Service implements AgentFactory {
     agentOptions: AgentOptions,
     meta: Pick<SessionHeader, 'cwd'>,
   ): Promise<void> {
+    await this.waitForDrainingConfiguredIdentity(ownerCtx, sessionId)
+    if (!this.ownership.isActive()) return
     const exists = (await persistence.list()).some(header => header.id === sessionId)
     if (!this.ownership.isActive()) return
     if (exists) {
@@ -464,6 +473,32 @@ export class AgentLoop extends Service implements AgentFactory {
     this.create(sessionId, agentOptions, meta)
   }
 
+  /** Wait for an already-disposed same-id lifecycle to finish registry teardown. */
+  private async waitForDrainingConfiguredIdentity(ownerCtx: Context, sessionId: SessionId): Promise<void> {
+    const current = ownerCtx.agents.get(sessionId)
+    if (current?.status !== 'disposed') return
+
+    const released = Promise.withResolvers<void>()
+    const checkReleased = (): void => {
+      if (ownerCtx.agents.get(sessionId) === undefined && ownerCtx.sessions.get(sessionId) === undefined) {
+        released.resolve()
+      }
+    }
+    const disposeAgentListener = ownerCtx.on('agent/disposed', (agent) => {
+      if (agent.id === sessionId) checkReleased()
+    })
+    const disposeSessionListener = ownerCtx.on('session/disposed', (session) => {
+      if (session.id === sessionId) checkReleased()
+    })
+    try {
+      checkReleased()
+      await this.ownership.waitWhileActive(released.promise)
+    } finally {
+      disposeAgentListener()
+      disposeSessionListener()
+    }
+  }
+
   /**
    * Create an agent and session under one caller-supplied identity, owned by
    * the accessing fiber. Constructor-driven config calls mint a fresh combined

packages/core/agent-loop/tests/config-session-id.spec.ts

@@ -92,6 +92,50 @@ describe('config-driven session id', () => {
     await ctx.fiber.dispose()
   })
 
+  it('waits for a draining exact-id lifecycle during an overlapping reload', async () => {
+    const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-overlap-'))
+    dirs.push(root)
+    const ctx = await makeCoreContext()
+    await ctx.plugin(SessionPersistenceJsonl, { root })
+    const sessionId = SessionId('stdio-exact-overlap')
+    const config = { agents: [{ id: 'main', sessionId, model: 'mock' }] }
+    const firstLoop = await ctx.plugin(AgentLoop, config)
+    await expect.poll(() => ctx.agents.get(sessionId)).toBeDefined()
+    const first = ctx.agents.get(sessionId) as ReactLoopAgent
+
+    const flushGate = Promise.withResolvers<undefined>()
+    let flushStarted = false
+    ctx.on('session/flush', (session) => {
+      if (session !== first.session) return
+      flushStarted = true
+      return flushGate.promise
+    })
+    first.inject([{ type: 'text', text: 'persist before replacement' }], {
+      source: { kind: 'plugin', plugin: 'test' },
+    })
+    expect(flushStarted).toBe(true)
+
+    const firstDisposal = firstLoop.dispose()
+    await expect.poll(() => first.status).toBe('disposed')
+    const failures: unknown[] = []
+    ctx.on('agent-loop/config-start-failed', (_id, error) => { failures.push(error) })
+    const secondLoop = await ctx.plugin(AgentLoop, config)
+    await new Promise(resolve => setTimeout(resolve, 0))
+    expect(ctx.agents.get(sessionId)).toBe(first)
+    expect(failures).toEqual([])
+
+    flushGate.resolve(undefined)
+    await firstDisposal
+    await expect.poll(() => ctx.agents.get(sessionId)).toBeDefined()
+    const second = ctx.agents.get(sessionId) as ReactLoopAgent
+    expect(second).not.toBe(first)
+    expect(JSON.stringify(second.session.deriveMessages())).toContain('persist before replacement')
+    expect(failures).toEqual([])
+
+    await secondLoop.dispose()
+    await ctx.fiber.dispose()
+  })
+
   it('contains an exact-id persistence lookup failure', async () => {
     const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-failure-'))
     dirs.push(root)