Merge remote-tracking branch 'origin/master' into session-query-tool

# Conflicts:
#	docs/architecture.i18n.yaml

packages/ui/tui/README.md

@@ -18,9 +18,9 @@ Before model output, session events, tool presenters, questions, configuration,
 
 Typing `@` at a token boundary searches files and directories under the session working directory. A bare fuzzy query uses a reusable bounded workspace index; a query containing `/` lists that directory directly, and selecting a folder keeps completion open for descent. Whitespace-bearing paths are inserted as `@"path with spaces"`. Selecting a file inserts only its path and a trailing space: the TUI does not read it, attach hidden context, or replace it with a reference object. When a model-facing `read` tool is registered, the TUI adds one fixed system-prompt instruction telling the model to read an explicit path when its contents are needed.
 
-When optional `ctx.sessionReferences` is mounted, the same `@` menu also offers metadata-only session candidates, inserts `@[label](dsh-session:<payload>)`, and prepares the selected snapshots before dispatch. Session references remain structured because the model has no filesystem-like tool for retrieving session snapshots later. Preparation disables duplicate submission and restores the editor input on failure. The TUI chooses `agent.steer()` or `agent.send()` from the status after that asynchronous preparation, so idle sends still dispatch `agent/prompt-submit` while in-turn steering joins at a checkpoint without that hook.
+When optional `ctx.sessionReferences` is mounted, the same `@` menu also offers metadata-only session candidates, inserts `@[label](dsh-session:<payload>)`, and prepares the selected snapshots before dispatch. Session references remain structured because the model has no filesystem-like tool for retrieving session snapshots later. Preparation disables duplicate submission and restores the editor input on failure. The TUI chooses `agent.steer()` or `agent.followup()` from the status after that asynchronous preparation, so idle follow-ups still dispatch `agent/prompt-submit` while in-turn steering joins at a checkpoint without that hook.
 
-While the agent is running, ordinary editor submissions call `agent.steer()`; otherwise they call `agent.send()`. A slash at the start of the submitted line enters `ctx.commands` instead: known commands execute directly, unknown commands produce a warning, and neither path automatically reaches the model. A command producer may explicitly schedule agent work; [`dsh-plan-mode`](../../plan/plan-mode/README.md#model-and-human-surfaces) uses that contract for `/plan [message]`. The TUI registers `/help`, `/model`, `/clear`, `/reasoning`, `/tools`, `/redraw`, `/reload`, `/resume`, `/status`, and `/exit` as agent-scoped definitions; every other effective command joins autocomplete and `/help` dynamically, as do `/skill:` completions. A status line above the editor reports the turn phase the TUI derives from session events — waiting for the first token, thinking, responding, or executing tools — with the elapsed time in that phase and the running step total, refreshed each second, and ends with the `Enter sends steering, Esc cancels` hint; while steering messages wait to reach the model it inserts a `N queued ·` badge before the hint that clears as each drains. Ctrl+C or Escape cancels a running turn. Tool cards collapse long bodies into a configurable head/tail preview; Ctrl+O toggles every card between its preview and full output. Ctrl+R toggles reasoning, Ctrl+L redraws, and Ctrl+D exits while idle.
+While the agent is running, ordinary editor submissions call `agent.steer()`; otherwise they call `agent.followup()`. A slash at the start of the submitted line enters `ctx.commands` instead: known commands execute directly, unknown commands produce a warning, and neither path automatically reaches the model. A command producer may explicitly schedule agent work; [`dsh-plan-mode`](../../plan/plan-mode/README.md#model-and-human-surfaces) uses that contract for `/plan [message]`. The TUI registers `/help`, `/model`, `/clear`, `/reasoning`, `/tools`, `/redraw`, `/reload`, `/resume`, `/status`, and `/exit` as agent-scoped definitions; every other effective command joins autocomplete and `/help` dynamically, as do `/skill:` completions. A status line above the editor reports the turn phase the TUI derives from session events — waiting for the first token, thinking, responding, or executing tools — with the elapsed time in that phase and the running step total, refreshed each second, and ends with the `Enter sends steering, Esc cancels` hint; while steering messages wait to reach the model it inserts a `N queued ·` badge before the hint that clears as each drains. Ctrl+C or Escape cancels a running turn. Tool cards collapse long bodies into a configurable head/tail preview; Ctrl+O toggles every card between its preview and full output. Ctrl+R toggles reasoning, Ctrl+L redraws, and Ctrl+D exits while idle.
 
 `/model` opens the advisory `ctx.llm` catalog as a keyboard selector: Up/Down moves, Enter selects, and Escape closes it. `/model <model>` still selects an unambiguous model id directly, while `/model <provider>/<model>` selects an exact target. The configured target or latest logged request header initializes the selector, and an unlisted current model remains visible because catalogs are advisory. Selection is local to this TUI session. Prompt assembly snapshots the target for one step, replaces `{{provider}}` and `{{model}}`, and applies the same pair through `agent/request`; a switch during assembly therefore starts with a later step. The request header durably records targets that reach the model, while an unused selection remains process-local.
 
@@ -80,7 +80,7 @@ The palette uses the standard 16-color ANSI foregrounds and SGR attributes, whic
 
 #### What the model sees
 
-Each non-empty ordinary editor submission becomes one text block, sent with `agent.send()` while the target agent is idle and `agent.steer()` while it is running. A session mention becomes readable `@label` text plus the durable untrusted context defined by [`dsh-session-reference`](../../context/session-reference/README.md); its full JSON is hidden behind a compact reference card. Slash commands and keybindings are TUI-only; command results remain terminal notices. A command producer may schedule a separate agent input, such as the optional message accepted by `/plan [message]`.
+Each non-empty ordinary editor submission becomes one text block, sent with `agent.followup()` while the target agent is idle and `agent.steer()` while it is running. A session mention becomes readable `@label` text plus the durable untrusted context defined by [`dsh-session-reference`](../../context/session-reference/README.md); its full JSON is hidden behind a compact reference card. Slash commands and keybindings are TUI-only; command results remain terminal notices. A command producer may schedule a separate agent input, such as the optional message accepted by `/plan [message]`.
 
 #### Token effect
 
@@ -128,7 +128,7 @@ Changing provider or model enters that target's cache domain; no cache reuse acr
 
 #### What the model sees
 
-A `/skill:<name> [instructions]` submission loads the named skill and delivers one text block: a `<skill name="…">` element wrapping the skill's instructions — preceded, when the provider exposes a resource base, by a line locating the skill's relative resources — followed by any trailing instructions the user typed. Delivery follows the same send-while-idle / steer-while-running rule as ordinary input. The command, not the model, chooses the skill; model-disabled skills are omitted from autocomplete but stay loadable by exact name.
+A `/skill:<name> [instructions]` submission loads the named skill and delivers one text block: a `<skill name="…">` element wrapping the skill's instructions — preceded, when the provider exposes a resource base, by a line locating the skill's relative resources — followed by any trailing instructions the user typed. Delivery follows the same followup-while-idle / steer-while-running rule as ordinary input. The command, not the model, chooses the skill; model-disabled skills are omitted from autocomplete but stay loadable by exact name.
 
 #### Token effect
 

packages/ui/tui/src/index.ts

@@ -1884,14 +1884,15 @@ export function createTuiChat(
   let toolsExpanded = false
   let streaming: StreamingAssistantComponent | undefined
   let runningStatus: RunningStatus | undefined
-  // Steering messages queued during the running turn (`agent/queued`) that the
-  // loop has not yet drained, shown as a badge on the status line. Each entry is
-  // the queued message's serialized source: a drain (`steering/message`) removes
-  // one MATCHING entry, so loop-authored steering — continuation reasons enter
-  // the inbox without an `agent/queued` event — cannot consume a pending user
-  // message's slot. Cleared on leaving `running`, which also absorbs a
-  // cancellation that discards the queue without logging drains; the status
-  // line exists only while running, so idle carries no badge to keep current.
+  // Steering messages queued during the running turn (`agent/inbox/enqueue`
+  // with `info.steering`) that the loop has not yet drained, shown as a badge on
+  // the status line. Each entry is the queued message's serialized source: a
+  // drain (`steering/message`) removes one MATCHING entry, so a loop-authored
+  // continuation reason (which enqueues and drains under its own source) pushes
+  // and pops its own slot and cannot consume a pending user message's slot.
+  // Cleared on leaving `running`, which also absorbs a cancellation that
+  // discards the queue without logging drains; the status line exists only
+  // while running, so idle carries no badge to keep current.
   const pendingSteering: string[] = []
   let disposed = false
   let shuttingDown: Promise<void> | undefined
@@ -2238,6 +2239,29 @@ export function createTuiChat(
   const renderEvent = (event: SessionEvent, options: { addHistory: boolean; renderChunks: boolean }): void => {
     switch (event.type) {
       case 'user/message': {
+        // Injected context (plugin/goal source) renders as a dim context card,
+        // not a human bubble; only a direct human prompt is a user message. The
+        // boolean avoids narrowing `source`, so the label keeps its full union.
+        const source = event.data.source
+        if (source.kind !== 'user') {
+          const references = sessionReferenceCard(event.data.meta)
+          if (references !== undefined) {
+            chat.addChild(new Spacer(1))
+            chat.addChild(new Text(palette.dim(`Referenced sessions · ${references.map(displayText).join(', ')}`), 1, 0))
+            break
+          }
+          const text = displayText(contentText(event.data.content).trim())
+          if (text) {
+            // The tui type view lacks plugin-augmented source kinds (e.g. goal),
+            // so read the display label without narrowing on `kind`.
+            const labelled = source as { kind: string; plugin?: string }
+            const label = labelled.plugin ?? labelled.kind
+            chat.addChild(new Spacer(1))
+            chat.addChild(new Text(palette.dim(`Context · ${displayText(label)}`), 1, 0))
+            chat.addChild(new Text(palette.muted(text), 1, 0))
+          }
+          break
+        }
         const text = displayText(contentText(displayPromptContent(event.data)).trim())
         if (text) {
           chat.addChild(new Spacer(1))
@@ -2262,22 +2286,6 @@ export function createTuiChat(
         }
         break
       }
-      case 'context/message': {
-        const references = sessionReferenceCard(event.data.meta)
-        if (references !== undefined) {
-          chat.addChild(new Spacer(1))
-          chat.addChild(new Text(palette.dim(`Referenced sessions · ${references.map(displayText).join(', ')}`), 1, 0))
-          break
-        }
-        const text = displayText(contentText(event.data.content).trim())
-        if (text) {
-          const source = event.data.source.kind === 'plugin' ? event.data.source.plugin : event.data.source.kind
-          chat.addChild(new Spacer(1))
-          chat.addChild(new Text(palette.dim(`Context · ${displayText(source)}`), 1, 0))
-          chat.addChild(new Text(palette.muted(text), 1, 0))
-        }
-        break
-      }
       case 'prompt/blocked':
         appendNotice(`Prompt blocked: ${event.data.reason}`, 'warning')
         break
@@ -2362,7 +2370,6 @@ export function createTuiChat(
       const isSurface = event.type === 'user/message'
         || event.type === 'assistant/message'
         || event.type === 'tool/result'
-        || event.type === 'context/message'
         || event.type === 'steering/message'
       if (isSurface && !active.has(event.seq)) continue
       if (event.type === 'tool/call' && !activeCalls.has(event.data.callId)) continue
@@ -2804,7 +2811,7 @@ export function createTuiChat(
     } else if (agent.status === 'running') {
       agent.steer(content, { contexts })
     } else {
-      agent.send(content, { contexts })
+      agent.followup(content, { contexts })
     }
   }
 
@@ -3148,9 +3155,9 @@ export function createTuiChat(
     advanceTurnPhase(event)
     if (event.type === 'steering/message') {
       // A queued steering message reached the model as it drained; drop its
-      // entry from the badge. Matching by source keeps loop-authored steering
-      // (e.g. continuation reasons), which logs here without a matching
-      // `agent/queued` increment, from consuming a pending user slot.
+      // entry from the badge. Matching by source keeps a loop-authored
+      // continuation reason popping its own enqueued slot rather than a pending
+      // user message's slot.
       const drained = pendingSteering.indexOf(JSON.stringify(event.data.source))
       if (drained >= 0) {
         pendingSteering.splice(drained, 1)
@@ -3164,7 +3171,7 @@ export function createTuiChat(
     renderEvent(event, { addHistory: false, renderChunks: true })
     requestRender()
   })
-  const disposeQueued = ctx.on('agent/queued', (subject, _content, info) => {
+  const disposeQueued = ctx.on('agent/inbox/enqueue', (subject, info) => {
     if (subject !== agent || !info.steering) return
     pendingSteering.push(JSON.stringify(info.source))
     refreshStatus()

packages/ui/tui/tests/harness.ts

@@ -1,6 +1,7 @@
 import { Context } from 'cordis'
 import type { Terminal } from '@earendil-works/pi-tui'
 import AgentRegistry, {
+  AgentMessageId,
   type Agent,
   type AgentCancelCause,
   type AgentOptions,
@@ -171,15 +172,23 @@ export async function createTuiTestHarness<TerminalType extends Terminal, Exit e
     steered,
     steeredOptions,
     cancelled,
-    send(content, options) {
+    followup(content, options) {
       sent.push(content)
       sentOptions.push(options)
+      return AgentMessageId('stub')
+    },
+    queue(content, options) {
+      sent.push(content)
+      sentOptions.push(options)
+      return AgentMessageId('stub')
     },
     steer(content, options) {
       steered.push(content)
       steeredOptions.push(options)
+      return AgentMessageId('stub')
     },
-    inject() {},
+    inject: () => AgentMessageId('stub'),
+    send: () => AgentMessageId('stub'),
     cancel(cause = { kind: 'user' }) {
       cancelled.push(cause)
     },

packages/ui/tui/tests/session-reference.snapshot.ts

@@ -128,7 +128,7 @@ describe('TUI session-reference snapshot', () => {
       type: 'text',
       text: '\n\n## My request:\n',
     })
-    expect(target.session.events.some(event => event.type === 'context/message')).toBe(false)
+    expect(target.session.events.some(event => event.type === 'user/message' && event.data.source.kind !== 'user')).toBe(false)
 
     const snapshot = await terminal.snapshot({ includeScrollback: true })
     if (REFRESHING) {

packages/ui/tui/tests/tui.snapshot.ts

@@ -471,7 +471,7 @@ describe('TUI terminal-state snapshots', () => {
         session.append('todo/write', {
           todos: [{ content: `Unsafe todo ${CONTROL_PROBE}`, status: 'in_progress' }],
         })
-        session.append('context/message', {
+        session.append('user/message', {
           content: [{ type: 'text', text: `Unsafe context ${CONTROL_PROBE}` }],
           source: { kind: 'plugin', plugin: `unsafe-${CONTROL_PROBE}` },
         }, { surfaceOp: 'append' })
@@ -587,7 +587,7 @@ describe('TUI terminal-state snapshots', () => {
     await checkpoint('surface-before-compaction', harness.terminal, { includeScrollback: true })
 
     await renderAfter(harness, () => {
-      harness.session.append('context/message', {
+      harness.session.append('user/message', {
         content: [{ type: 'text', text: 'Compacted summary: the prior command completed and its details were retired from the active surface.' }],
         source: { kind: 'plugin', plugin: 'compact' },
       }, {

packages/ui/tui/tests/tui.spec.ts

@@ -4,7 +4,7 @@ import { join, resolve } from 'node:path'
 import { describe, expect, it, vi } from 'vitest'
 import { Context } from 'cordis'
 import { CombinedAutocompleteProvider, type Terminal } from '@earendil-works/pi-tui'
-import AgentRegistry, { agentEvents, assembleContextFor, type Agent } from '@deepseek-ai/dsh-agent'
+import AgentRegistry, { agentEvents, assembleContextFor, AgentMessageId, type Agent } from '@deepseek-ai/dsh-agent'
 import { type LlmCallConfig } from '@deepseek-ai/dsh-llm'
 import { GOAL_CHANGE_VERSION, GoalId, renderGoalChange, type GoalSnapshotChangeMeta } from '@deepseek-ai/dsh-goal'
 import CommandService, { type CommandInvocation } from '@deepseek-ai/dsh-commands'
@@ -1073,7 +1073,7 @@ describe('pi-tui chat lifecycle and transcript', () => {
     }
     const result = await setup({
       beforeMount(session) {
-        session.append('context/message', {
+        session.append('user/message', {
           content: renderGoalChange(change),
           source: { kind: 'goal', goalId: change.goal.id, revision: change.goal.revision, round: 0 },
           meta: change as unknown as JsonValue,
@@ -1172,8 +1172,11 @@ describe('pi-tui chat lifecycle and transcript', () => {
     result.session.append('user/message', { content: [{ type: 'text', text: '   ' }], source: { kind: 'user' } }, { surfaceOp: 'append' })
     result.session.append('steering/message', { turn: 2, content: [{ type: 'text', text: 'steering note' }], source: { kind: 'user' } }, { surfaceOp: 'append' })
     result.session.append('steering/message', { turn: 2, content: [{ type: 'text', text: '' }], source: { kind: 'user' } }, { surfaceOp: 'append' })
-    result.session.append('context/message', { content: [{ type: 'text', text: 'user context' }], source: { kind: 'user' } }, { surfaceOp: 'append' })
-    result.session.append('context/message', { content: [{ type: 'text', text: '' }], source: { kind: 'user' } }, { surfaceOp: 'append' })
+    result.session.append('user/message', { content: [{ type: 'text', text: 'user context' }], source: { kind: 'plugin', plugin: 'ctx' } }, { surfaceOp: 'append' })
+    result.session.append('user/message', { content: [{ type: 'text', text: '' }], source: { kind: 'plugin', plugin: 'ctx' } }, { surfaceOp: 'append' })
+    // A non-plugin injected source (goal) has no `plugin` field, so its context
+    // card label falls back to the source kind.
+    result.session.append('user/message', { content: [{ type: 'text', text: 'goal context' }], source: { kind: 'goal', goalId: 'g1', revision: 1, round: 0 } as never }, { surfaceOp: 'append' })
     result.session.append('prompt/blocked', { content: [{ type: 'text', text: 'blocked' }], source: { kind: 'user' }, reason: 'test policy' })
     appendAssistant(result.session, [])
     result.session.append('step/end', { turn: 1, step: 1 })
@@ -1254,6 +1257,7 @@ describe('pi-tui chat lifecycle and transcript', () => {
     expect(result.terminal.output).toContain('Enter sends steering, Esc cancels')
     expect(result.terminal.output).toContain('Steering')
     expect(result.terminal.output).toContain('user context')
+    expect(result.terminal.output).toContain('Context · goal') // goal-sourced injected context labels by kind
     expect(result.terminal.output).toContain('Prompt blocked')
     expect(result.terminal.output).toContain('Turn cancelled')
     expect(result.terminal.progress).toContain(true)
@@ -1350,16 +1354,16 @@ describe('pi-tui chat lifecycle and transcript', () => {
     expect(result.terminal.output).not.toContain('queued')
 
     const queueSteering = (text: string): void => {
-      result.ctx.emit('agent/queued', result.agent, [{ type: 'text', text }], { source: { kind: 'user' }, contexts: [], steering: true })
+      result.ctx.emit('agent/inbox/enqueue', result.agent, { id: AgentMessageId('stub'), content: [{ type: 'text', text }], source: { kind: 'user' }, contexts: [], steering: true, wakeup: true })
     }
     const drainSteering = (text: string): void => {
       result.session.append('steering/message', { turn: 1, content: [{ type: 'text', text }], source: { kind: 'user' } }, { surfaceOp: 'append' })
     }
 
     // A steering queue for a different agent never touches this status line.
-    const other = { ...result.agent, id: SessionId('other') } as Agent
+    const other = { ...result.agent, id: SessionId('other') } as unknown as Agent
     result.terminal.output = ''
-    result.ctx.emit('agent/queued', other, [{ type: 'text', text: 'elsewhere' }], { source: { kind: 'user' }, contexts: [], steering: true })
+    result.ctx.emit('agent/inbox/enqueue', other, { id: AgentMessageId('stub'), content: [{ type: 'text', text: 'elsewhere' }], source: { kind: 'user' }, contexts: [], steering: true, wakeup: true })
     await tick()
     expect(result.terminal.output).not.toContain('queued')
 
@@ -1372,7 +1376,7 @@ describe('pi-tui chat lifecycle and transcript', () => {
 
     // A non-steering queue (an idle-style send) leaves the badge untouched.
     result.terminal.output = ''
-    result.ctx.emit('agent/queued', result.agent, [{ type: 'text', text: 'sent' }], { source: { kind: 'user' }, contexts: [], steering: false })
+    result.ctx.emit('agent/inbox/enqueue', result.agent, { id: AgentMessageId('stub'), content: [{ type: 'text', text: 'sent' }], source: { kind: 'user' }, contexts: [], steering: false, wakeup: true })
     drainSteering('first')
     await tick()
     expect(result.terminal.output).toContain('1 queued')
@@ -1392,8 +1396,9 @@ describe('pi-tui chat lifecycle and transcript', () => {
     await tick()
     expect(result.terminal.output).toContain('1 queued')
 
-    // A loop-authored steering event (plugin source, no matching agent/queued)
-    // cannot consume a pending user slot, even when it drains first.
+    // A steering/message whose source matches no pending badge entry (here a
+    // plugin source with no tracked enqueue) pops nothing, so it cannot consume
+    // a pending user slot even when it drains first.
     result.terminal.output = ''
     result.session.append('steering/message', {
       turn: 1,
@@ -1425,7 +1430,7 @@ describe('pi-tui chat lifecycle and transcript', () => {
     const idle = await setup()
     // A steering queue arriving while idle has no status line to badge, so the
     // refresh is a no-op beyond requesting a render.
-    idle.ctx.emit('agent/queued', idle.agent, [{ type: 'text', text: 'early' }], { source: { kind: 'user' }, contexts: [], steering: true })
+    idle.ctx.emit('agent/inbox/enqueue', idle.agent, { id: AgentMessageId('stub'), content: [{ type: 'text', text: 'early' }], source: { kind: 'user' }, contexts: [], steering: true, wakeup: true })
     idle.session.append('tool/call', { turn: 1, step: 0, callId: 'pre' as never, name: 'bash', arguments: '{}' })
     await tick()
     expect(idle.terminal.output).not.toContain('Executing tools')
@@ -1909,10 +1914,11 @@ describe('pi-tui chat lifecycle and transcript', () => {
         expect(result.terminal.output).toContain('Folder · docs/')
       })
       result.terminal.send('\t')
-      await vi.waitFor(() => {
-        expect(result.terminal.output).toContain('File · design notes.md')
-      })
+      result.terminal.output = ''
       result.terminal.send('\t')
+      await vi.waitFor(() => {
+        expect(result.terminal.output).toContain('@"docs/design notes.md"')
+      })
       await tick()
       result.terminal.send('\r')
       await vi.waitFor(() => { expect(result.agent.sent).toHaveLength(2) })
@@ -2150,7 +2156,7 @@ describe('pi-tui chat lifecycle and transcript', () => {
     expect(result.terminal.output).toContain('Referenced sessions · Steering source (steering-source)')
     expect(result.terminal.output).not.toContain('hidden non-reference prefix')
 
-    result.session.append('context/message', {
+    result.session.append('user/message', {
       content: [{ type: 'text', text: 'secret full snapshot payload' }],
       source: { kind: 'plugin', plugin: 'session-reference' },
       meta: {
@@ -2169,13 +2175,13 @@ describe('pi-tui chat lifecycle and transcript', () => {
       [{ kind: 'session-reference', references: [{}] }, 'invalid-fields'],
     ]
     for (const [meta, text] of invalidCards) {
-      result.session.append('context/message', {
+      result.session.append('user/message', {
         content: [{ type: 'text', text }],
         source: { kind: 'plugin', plugin: 'session-reference' },
         meta,
       }, { surfaceOp: 'append' })
     }
-    result.session.append('context/message', {
+    result.session.append('user/message', {
       content: [{ type: 'text', text: 'same-label snapshot' }],
       source: { kind: 'plugin', plugin: 'session-reference' },
       meta: { kind: 'session-reference', references: [{ sessionId: 'same', label: 'same' }] },
@@ -2609,7 +2615,7 @@ describe('pi-tui chat lifecycle and transcript', () => {
 
     const events = await setup()
     const unrelatedSession = events.ctx.sessions.create(SessionId('unrelated-session'))
-    const unrelatedAgent = { ...events.agent, id: unrelatedSession.id, session: unrelatedSession }
+    const unrelatedAgent = { ...events.agent, id: unrelatedSession.id, session: unrelatedSession } as unknown as Agent
     unrelatedSession.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
     unrelatedSession.append('todo/write', { todos: [{ content: 'hidden', status: 'pending' }] })
     agentEvents(events.ctx, unrelatedAgent).emit('agent/status', 'running')
@@ -2972,7 +2978,7 @@ describe('tool cards and surface replay', () => {
       turn: 1, step: 1, callId: 'old-call' as never, content: [{ type: 'text', text: 'old output' }], isError: false,
     }, { surfaceOp: 'append' })
     const start = result.session.surface.nodes[0] as number
-    result.session.append('context/message', {
+    result.session.append('user/message', {
       content: [{ type: 'text', text: 'summary replacement' }],
       source: { kind: 'plugin', plugin: 'compact' },
     }, {
@@ -3293,7 +3299,7 @@ describe('terminal mounting', () => {
     const session = ctx.sessions.create(SessionId('main'))
     ctx.agents.register({
       id: session.id, options: {}, session, status: 'idle', ctx,
-      send() {}, steer() {}, inject() {}, cancel() {}, whenIdle: () => Promise.resolve(),
+      followup: () => AgentMessageId('stub'), queue: () => AgentMessageId('stub'), steer: () => AgentMessageId('stub'), inject: () => AgentMessageId('stub'), send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(),
     })
     const terminal = new FakeTerminal()
     mountTui(ctx, { color: false }, { terminal, exit: vi.fn() })
@@ -3317,7 +3323,7 @@ describe('terminal mounting', () => {
     const session = ctx.sessions.create(SessionId('main'))
     ctx.agents.register({
       id: session.id, options: {}, session, status: 'idle', ctx,
-      send() {}, steer() {}, inject() {}, cancel() {}, whenIdle: () => Promise.resolve(),
+      followup: () => AgentMessageId('stub'), queue: () => AgentMessageId('stub'), steer: () => AgentMessageId('stub'), inject: () => AgentMessageId('stub'), send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(),
     })
     const terminal = new FakeTerminal()
     // Mirror dsh-tui's own inject (minus loader, the absence under test).
@@ -3351,14 +3357,14 @@ describe('terminal mounting', () => {
     const otherSession = ctx.sessions.create(SessionId('other-session'))
     ctx.agents.register({
       id: otherSession.id, options: {}, session: otherSession, status: 'idle', ctx,
-      send() {}, steer() {}, inject() {}, cancel() {}, whenIdle: () => Promise.resolve(),
+      followup: () => AgentMessageId('stub'), queue: () => AgentMessageId('stub'), steer: () => AgentMessageId('stub'), inject: () => AgentMessageId('stub'), send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(),
     })
     expect(terminal.started).toBe(0)
 
     const session = ctx.sessions.create(SessionId('late-session'))
     const agent = {
       id: session.id, options: {}, session, status: 'idle', ctx,
-      send() {}, steer() {}, inject() {}, cancel() {}, whenIdle: () => Promise.resolve(),
+      followup: () => AgentMessageId('stub'), queue: () => AgentMessageId('stub'), steer: () => AgentMessageId('stub'), inject: () => AgentMessageId('stub'), send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(),
     } as Agent
     ctx.agents.register(agent)
     await tick()
@@ -3388,7 +3394,7 @@ describe('terminal mounting', () => {
     const session = ctx.sessions.create(SessionId('main-session'))
     ctx.agents.register({
       id: session.id, options: {}, session, status: 'idle', ctx,
-      send() {}, steer() {}, inject() {}, cancel() {}, whenIdle: () => Promise.resolve(),
+      followup: () => AgentMessageId('stub'), queue: () => AgentMessageId('stub'), steer: () => AgentMessageId('stub'), inject: () => AgentMessageId('stub'), send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(),
     })
     await tick()
     expect(terminal.started).toBe(0)
@@ -3430,7 +3436,7 @@ describe('terminal mounting', () => {
     session.append('step/start', { turn: 1, step: 1 })
     ctx.agents.register({
       id: session.id, options: {}, session, status: 'running', ctx,
-      send() {}, steer() {}, inject() {}, cancel() {}, whenIdle: () => Promise.resolve(),
+      followup: () => AgentMessageId('stub'), queue: () => AgentMessageId('stub'), steer: () => AgentMessageId('stub'), inject: () => AgentMessageId('stub'), send: () => AgentMessageId('stub'), cancel() {}, whenIdle: () => Promise.resolve(),
     })
     const terminal = new FakeTerminal()
     terminal.start = () => { throw new Error('terminal startup failed') }