fix(compact): harden pruning integration (round 2)

packages/compact/compact-basic/README.md

@@ -15,8 +15,8 @@ This backend owns the compaction policy:
 - **Summarization** — a direct `llm/stream` call uses the configured model and cap without running the loop-only `agent/request` seam. The input transcript preserves non-text blocks as tagged placeholders; only returned text enters the checkpoint, excluding reasoning and tool calls that would leak private reasoning or create an orphaned call.
 - **Framing** — the replacement user message marks established checkpoint context with `<compacted-summary>` tags. The raw summary remains on the provenance event, and later automatic cycles merge the prior checkpoint.
 - **Lifecycle** — `compactRegion()` requires its agent to own the exact target session and rejects mismatch before resolution or mutation; a valid call records its start, summary, replacement, and end. The serial `agent/post-step` listener checks pressure after successful output and tool work are durable but before `step/end`. Canonical provider overflow is handled through `agent/request-error` after the failed step closes.
-- **Overflow recovery** — below-threshold overflow bypasses normal retention and first prunes, then attempts one maximal balanced head reduction while leaving the newest indivisible unit. Retry is authorized whenever `surface.replaceGeneration` advances, including pruning-only progress on an otherwise indivisible surface; no replacement, recovery failure, an exhausted cap, cancellation, or an unknown/noncanonical error preserves the original provider failure.
-- **Failure handling** — an unmatched `compact/start` is an inert crash marker because no replacement landed. Operational post-step failures warn and continue; overflow-recovery failure preserves the original provider error.
+- **Overflow recovery** — below-threshold overflow bypasses normal retention and first prunes, then attempts one maximal balanced head reduction while leaving the newest indivisible unit. Retry is authorized whenever `surface.replaceGeneration` advances, including when pruning lands before later summary work throws. No replacement, an exhausted cap, cancellation, or an unknown/noncanonical error preserves the original provider failure.
+- **Failure handling** — an unmatched `compact/start` is an inert crash marker because no summary replacement landed. Operational post-step failures warn and continue; overflow-recovery failure preserves the original provider error only when no earlier replacement advanced the surface. Cancellation remains authoritative after any progress.
 
 `summarize()` is the sole subclass hook. A template- or remote-summarizer subclass can override it while pressure, retention, provenance, shrink validation, and shadowed-token accounting stay on `ctx.tokenMeter`. The hook returns the summary blocks together with the call envelope it used (`{ summary, model, maxTokens? }`), which is logged on `compact/summary`.
 

packages/compact/compact-basic/src/index.ts

@@ -100,15 +100,28 @@ export class BasicCompactService extends CompactService {
         || retryAttempt >= this.config.maxOverflowRetries
         || signal.aborted) return next()
 
-      let generation: number
+      const generation = agent.session.surface.replaceGeneration
       let result: CompactionResult | null
       try {
-        generation = agent.session.surface.replaceGeneration
         result = await this.compactIfNeeded(agent, 'context-overflow', signal)
       } catch (recoveryError: unknown) {
         const message = recoveryError instanceof Error ? recoveryError.message : String(recoveryError)
+        // A model-free prune can land before later summary work fails. That
+        // durable reduction is sufficient retry proof; do not discard it just
+        // because the optional second phase threw. Cancellation still wins.
+        // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition -- signal can abort while recovery is awaited.
+        if (!signal.aborted && agent.session.surface.replaceGeneration > generation) {
+          ctx.logger.warn(
+            `context-overflow compaction failed after durable surface progress: ${message}; `
+            + 'retrying from the replacement surface',
+          )
+          return { action: 'retry' }
+        }
         ctx.logger.warn(
-          `context-overflow compaction failed: ${message}; preserving the original request error`,
+          // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition -- signal can abort while recovery is awaited.
+          `context-overflow compaction failed: ${message}; ${signal.aborted
+            ? 'cancellation prevents retry'
+            : 'preserving the original request error'}`,
         )
         return next()
       }

packages/compact/compact-basic/tests/compact-basic.spec.ts

@@ -1022,6 +1022,51 @@ describe('automatic listener and loader composition', () => {
     expect(compact.calls[0]!.text).toContain('tool result middle pruned')
   })
 
+  it('retries from a durable prune when later overflow summarization throws', async () => {
+    const ctx = createContext(10_000)
+    const warnings: string[] = []
+    ctx.logger.warn = ((message: string) => void warnings.push(message)) as typeof ctx.logger.warn
+    void new ToolResultPruneService(ctx, {
+      thresholdChars: 100,
+      headChars: 20,
+      tailChars: 10,
+    })
+    const compact = new TestCompactService(ctx, {
+      thresholdRatio: 1,
+      retainTokens: 900,
+    })
+    compact.error = new Error('summary unavailable after prune')
+    const session = oversizedToolResult(3_000, true)
+
+    expect(await recover(ctx, agent(session, MODEL), overflow())).toEqual({ action: 'retry' })
+    expect(session.surface.replaceGeneration).toBe(1)
+    expect(session.events.filter(event => event.type === 'tool/result')).toHaveLength(2)
+    expect(session.events.findLast(event => event.type === 'compact/end')?.data)
+      .toMatchObject({ error: 'summary unavailable after prune' })
+    expect(warnings).toContainEqual(expect.stringContaining('retrying from the replacement surface'))
+  })
+
+  it('lets cancellation win when summary throws after a durable prune', async () => {
+    const ctx = createContext(10_000)
+    const controller = new AbortController()
+    void new ToolResultPruneService(ctx, {
+      thresholdChars: 100,
+      headChars: 20,
+      tailChars: 10,
+    })
+    const compact = new TestCompactService(ctx, {
+      thresholdRatio: 1,
+      retainTokens: 900,
+    })
+    compact.mutateDuringSummary = () => { controller.abort('cancelled during summary') }
+    compact.error = new Error('summary cancelled after prune')
+    const session = oversizedToolResult(3_000, true)
+
+    expect(await recover(ctx, agent(session, MODEL), overflow(), 0, controller.signal))
+      .toEqual({ action: 'fail' })
+    expect(session.surface.replaceGeneration).toBe(1)
+  })
+
   it('preserves the newest whole tool-call/result pair during forced overflow compaction', async () => {
     const ctx = createContext()
     void new TestCompactService(ctx, {

packages/support/invariants/README.md

@@ -31,7 +31,7 @@ Session log (per session):
 - **turns pair and nest** — `turn/start` opens a turn, `turn/end` closes the matching one; no overlapping turns.
 - **steps nest in turns** — `step/start` opens a step in the open turn; `step/end` closes the matching step.
 - **chunks belong to an open step** — `step/start` precedes its `assistant/chunk`s.
-- **an appended `tool/result` needs a prior `tool/call`** — fresh `surfaceOp: 'append'` results name the open step and consume its pending call, while a provenance-backed single-node `replace` is a turn-enclosed surface rewrite of an already-executed result. A `tool/call` may still have no result when the execution pipeline throws.
+- **an appended `tool/result` needs a prior `tool/call`** — fresh `surfaceOp: 'append'` results name the open step and consume its pending call. A replacement exemption applies only to a provenance-backed rewrite of one current `tool/result` node whose complete data is identical except for `content`; it must still be turn-enclosed. A `tool/call` may still have no result when the execution pipeline throws.
 - **provenance sources are valid and unambiguous** — `sourceEventSeqs` contains unique earlier known seqs; only `assistant/message` may carry an explicit empty list, which denotes a known empty provider stream rather than absent legacy provenance.
 
 Agent status (per agent):

packages/support/invariants/src/index.ts

@@ -7,6 +7,7 @@
  * @module @deepseek-ai/dsh-invariants
  */
 
+import { isDeepStrictEqual } from 'node:util'
 import type { Context } from 'cordis'
 import { carrierKeyOf, isScopeCarrier } from '@deepseek-ai/dsh-scope'
 import { assertNever, HarnessError } from '@deepseek-ai/dsh-llm'
@@ -50,13 +51,14 @@ interface SessionTrace {
   pendingCalls: Set<CallId>
   /** Every seq seen so far — validates `sourceEventSeqs` references. */
   knownSeqs: Set<number>
-  /**
-   * The seqs currently on the surface linked list, in linked-list order
-   * (head to tail). A replace reorders this relative to seq order (the new
-   * node takes the replaced range's position), so range validation is
-   * positional, not by seq comparison.
-   */
-  surface: number[]
+  /** Current surface nodes in linked-list order, with immutable event identity. */
+  surface: SurfaceTraceNode[]
+}
+
+/** Immutable identity retained only while an event is on the current surface. */
+interface SurfaceTraceNode {
+  seq: number
+  event: SessionEvent<SurfaceEventType>
 }
 
 /** One accepted event's deferred mutation of a live session trace. */
@@ -70,8 +72,9 @@ interface SessionTraceTransition {
     | { kind: 'clear' }
   /** The event's mutation of the derived surface order. */
   surface:
-    | { kind: 'none' | 'append' }
-    | { kind: 'replace'; start: number; count: number }
+    | { kind: 'none' }
+    | { kind: 'append'; node: SurfaceTraceNode }
+    | { kind: 'replace'; start: number; count: number; node: SurfaceTraceNode }
   /** The committed event sequence to add to the known-sequence set. */
   seq: number
 }
@@ -85,6 +88,18 @@ function requireOpenStep(trace: SessionTrace, kind: string, turn: number, step:
   }
 }
 
+/** Compare future-safe tool-result data while deliberately excluding content. */
+function sameToolResultDataExceptContent(
+  original: SessionEvent<'tool/result'>['data'],
+  replacement: SessionEvent<'tool/result'>['data'],
+): boolean {
+  const originalRest = { ...original } as Record<string, unknown>
+  const replacementRest = { ...replacement } as Record<string, unknown>
+  delete originalRest['content']
+  delete replacementRest['content']
+  return isDeepStrictEqual(originalRest, replacementRest)
+}
+
 /** Validate one candidate event without mutating the committed session trace. */
 function validateEvent(trace: SessionTrace, event: SessionEvent): SessionTraceTransition {
   // seq is strictly monotonic — the spine of replay equivalence. lastSeq
@@ -139,14 +154,14 @@ function validateEvent(trace: SessionTrace, event: SessionEvent): SessionTraceTr
   // positional range — every shadowed node must appear in sourceEventSeqs.
   if (se.surfaceOp !== undefined) {
     if (se.surfaceOp === 'append') {
-      surface = { kind: 'append' }
+      surface = { kind: 'append', node: { seq: event.seq, event: se } }
     } else {
       const { start, end } = se.surfaceOp
-      const startIdx = trace.surface.indexOf(start)
+      const startIdx = trace.surface.findIndex(node => node.seq === start)
       if (startIdx === -1) {
         throw new InvariantError(`surface replace: start seq ${start} is not on the surface`)
       }
-      const endIdx = trace.surface.indexOf(end)
+      const endIdx = trace.surface.findIndex(node => node.seq === end)
       if (endIdx === -1) {
         throw new InvariantError(`surface replace: end seq ${end} is not on the surface`)
       }
@@ -155,13 +170,18 @@ function validateEvent(trace: SessionTrace, event: SessionEvent): SessionTraceTr
       }
       // Every node the replace shadows (surface positions [startIdx, endIdx]
       // inclusive) must appear in sourceEventSeqs — the provenance contract.
-      const shadowed = trace.surface.slice(startIdx, endIdx + 1)
+      const shadowed = trace.surface.slice(startIdx, endIdx + 1).map(node => node.seq)
       const recorded = new Set(se.sourceEventSeqs ?? [])
       const missing = shadowed.filter(seq => !recorded.has(seq))
       if (missing.length > 0) {
         throw new InvariantError(`surface replace: sourceEventSeqs must include every shadowed surface node; missing ${missing.join(', ')}`)
       }
-      surface = { kind: 'replace', start: startIdx, count: shadowed.length }
+      surface = {
+        kind: 'replace',
+        start: startIdx,
+        count: shadowed.length,
+        node: { seq: event.seq, event: se },
+      }
     }
   }
 
@@ -232,15 +252,26 @@ function validateEvent(trace: SessionTrace, event: SessionEvent): SessionTraceTr
       break
     }
     case 'tool/result': {
-      // A replacement rewrites an already-executed result whose recorded
-      // turn/step can be closed. Surface provenance above validates the rewrite;
-      // only fresh appends consume an open step's pending call.
+      // Only a content-only rewrite of one CURRENT tool-result node may bypass
+      // open-step/pending-call checks. The trace retains immutable surface event
+      // identity, so this validation never indexes a mutable or stale session.
       if (se.surfaceOp !== undefined && se.surfaceOp !== 'append') {
         if (trace.openTurn === null) {
           throw new InvariantError(
             'tool/result surface replacement appended outside any open turn',
           )
         }
+        const { start, end } = se.surfaceOp
+        if (start !== end) {
+          throw new InvariantError('tool/result surface replacement must rewrite exactly one current node')
+        }
+        const original = trace.surface.find(node => node.seq === start)?.event
+        if (original?.type !== 'tool/result') {
+          throw new InvariantError('tool/result surface replacement must target a current tool/result')
+        }
+        if (!sameToolResultDataExceptContent(original.data, event.data)) {
+          throw new InvariantError('tool/result surface replacement may change only content')
+        }
         break
       }
       requireOpenStep(trace, 'tool/result', event.data.turn, event.data.step)
@@ -302,10 +333,14 @@ function applyTransition(trace: SessionTrace, transition: SessionTraceTransition
     case 'none':
       break
     case 'append':
-      trace.surface.push(transition.seq)
+      trace.surface.push(transition.surface.node)
       break
     case 'replace':
-      trace.surface.splice(transition.surface.start, transition.surface.count, transition.seq)
+      trace.surface.splice(
+        transition.surface.start,
+        transition.surface.count,
+        transition.surface.node,
+      )
       break
     /* v8 ignore next -- validateEvent produces this closed transition union */
     default:

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

@@ -478,6 +478,39 @@ describe('HMR safety', () => {
 })
 
 describe('surface invariants', () => {
+  async function toolResultRewriteFixture() {
+    const { ctx } = await setup()
+    const session = ctx.sessions.create()
+    session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
+    const unrelated = session.append('user/message', {
+      content: [{ type: 'text', text: 'request' }],
+      source: { kind: 'user' },
+    }, { surfaceOp: 'append' })
+    session.append('step/start', { turn: 1, step: 1 })
+    session.append('tool/call', {
+      turn: 1,
+      step: 1,
+      callId: CallId('rewrite'),
+      name: 'echo',
+      arguments: '{}',
+    })
+    const originalData = {
+      turn: 1,
+      step: 1,
+      callId: CallId('rewrite'),
+      content: [{ type: 'text' as const, text: 'original' }],
+      isError: true,
+      error: { name: 'ExitError', code: 'EXIT_1' },
+      meta: { presentation: { kind: 'terminal', output: 'full output' } },
+      futureField: { nested: ['preserve', 1] },
+    }
+    const original = session.append('tool/result', originalData, { surfaceOp: 'append' })
+    session.append('step/end', { turn: 1, step: 1 })
+    session.append('turn/end', { turn: 1, reason: { kind: 'completed' } })
+    session.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } })
+    return { session, unrelated, original }
+  }
+
   it('accepts well-formed surface metadata', async () => {
     const { ctx } = await setup()
     const session = ctx.sessions.create()
@@ -501,27 +534,7 @@ describe('surface invariants', () => {
   })
 
   it('treats a provenance-backed tool-result replacement as a turn-enclosed rewrite', async () => {
-    const { ctx } = await setup()
-    const session = ctx.sessions.create()
-    session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
-    session.append('step/start', { turn: 1, step: 1 })
-    session.append('tool/call', {
-      turn: 1,
-      step: 1,
-      callId: CallId('rewrite'),
-      name: 'echo',
-      arguments: '{}',
-    })
-    const original = session.append('tool/result', {
-      turn: 1,
-      step: 1,
-      callId: CallId('rewrite'),
-      content: [{ type: 'text', text: 'original' }],
-      isError: false,
-    }, { surfaceOp: 'append' })
-    session.append('step/end', { turn: 1, step: 1 })
-    session.append('turn/end', { turn: 1, reason: { kind: 'completed' } })
-    session.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } })
+    const { session, original } = await toolResultRewriteFixture()
 
     expect(() => session.append('tool/result', {
       ...original.data,
@@ -532,6 +545,47 @@ describe('surface invariants', () => {
     })).not.toThrow()
   })
 
+  it('rejects a tool-result replacement targeting an unrelated current node', async () => {
+    const { session, unrelated, original } = await toolResultRewriteFixture()
+    expect(() => session.append('tool/result', {
+      ...original.data,
+      content: [{ type: 'text', text: 'forged' }],
+    }, {
+      surfaceOp: { op: 'replace', start: unrelated.seq, end: unrelated.seq },
+      sourceEventSeqs: [unrelated.seq],
+    })).toThrow(/must target a current tool\/result/)
+  })
+
+  it('rejects a multi-node tool-result replacement even with complete provenance', async () => {
+    const { session, unrelated, original } = await toolResultRewriteFixture()
+    expect(() => session.append('tool/result', {
+      ...original.data,
+      content: [{ type: 'text', text: 'forged' }],
+    }, {
+      surfaceOp: { op: 'replace', start: unrelated.seq, end: original.seq },
+      sourceEventSeqs: [unrelated.seq, original.seq],
+    })).toThrow(/must rewrite exactly one current node/)
+  })
+
+  it.each([
+    ['callId', { callId: CallId('forged') }],
+    ['turn', { turn: 2 }],
+    ['step', { step: 2 }],
+    ['error', { error: { name: 'ExitError', code: 'DIFFERENT' } }],
+    ['meta', { meta: { presentation: { kind: 'generic' } } }],
+    ['future data', { futureField: { nested: ['changed'] } }],
+  ])('rejects a content rewrite with altered %s', async (_label, altered) => {
+    const { session, original } = await toolResultRewriteFixture()
+    expect(() => session.append('tool/result', {
+      ...original.data,
+      ...altered,
+      content: [{ type: 'text', text: 'pruned' }],
+    }, {
+      surfaceOp: { op: 'replace', start: original.seq, end: original.seq },
+      sourceEventSeqs: [original.seq],
+    })).toThrow(/may change only content/)
+  })
+
   it('accepts known-empty assistant provenance and rejects empty provenance elsewhere', async () => {
     const { ctx } = await setup()
     const session = ctx.sessions.create()

packages/ui/acp/README.md

@@ -99,7 +99,7 @@ The JSON-RPC frames go on stdout, so this plugin MUST run in an example that loa
 
 **What the model sees**: When optional consumers are loaded, ACP form answers become the exact JSON shape documented by `dsh-tool-ask-user`. Failures become `Error: ACP user questions must come from an agent-owned request`, `Error: ACP user question has no matching session`, `Error: ACP elicitation request failed`, `Error: ask_user_question was cancelled by the user`, `Error: ask_user_question returned no answer`, or `Error: ask_user_question was aborted before the user answered`. Permission decisions control whether another tool yields success or denial. ACP tool cards, terminal output, diffs, and streamed session updates are UI-only.
 
-**Token effect**: Answer, error, and denial text enters context only through the owning tool result; presentation metadata adds zero model tokens.
+**Token effect**: Answer, error, and denial text enters context only through the owning tool result; presentation metadata adds zero model tokens. A replacement `tool/result` still changes the model-facing session surface, but live and replayed ACP feeds ignore it as an execution update so the original terminal or diff completion is not overwritten.
 
 ### Permission preset switches
 

packages/ui/acp/acp-feature-support.md

@@ -82,7 +82,7 @@ These are capabilities the bridge would *drive* on the editor. The harness runs
 | `agent_thought_chunk` | S | ✅ | ✅ | ✅ | From `assistant/chunk` reasoning-delta. |
 | `user_message_chunk` | S | ✅ | ✅ | ✅ | Emitted during `session/load` replay to reconstruct the user side. |
 | `tool_call` | S | ✅ | ✅ | ✅ | Tool-owned presentation (`presentCall`); see [§5](#5-tool-call-rendering). |
-| `tool_call_update` | S | ✅ | ✅ | ✅ | From `tool/result` via `presentResult`. |
+| `tool_call_update` | S | ✅ | ✅ | ✅ | From appended `tool/result` via `presentResult`; replacement results rewrite model context and do not duplicate or overwrite execution presentation. |
 | `plan` | S | ❌ | ✅ | ✅ | No agent plan emitted. Both adapters emit real plan entries (Codex's `CodexEventHandler.updatePlan` maps `turn/plan/updated` → `{ sessionUpdate: 'plan', entries }`). |
 | `available_commands_update` | S | ❌ | ✅ | ✅ | No slash commands advertised. |
 | `current_mode_update` | S | ❌ | ✅ | ✅ | No session modes. |

packages/ui/acp/src/index.ts

@@ -904,7 +904,8 @@ function validateMcpServers(params: { mcpServers?: unknown[] }): void {
  *   loaded transcript reconstructs the USER side of each turn without echoing
  *   a live `session/prompt` back to the client
  * - `tool/call`   → `tool_call` (pending)
- * - `tool/result` → `tool_call_update` (completed/failed)
+ * - appended `tool/result` → `tool_call_update` (completed/failed)
+ * - replacement `tool/result` → no update (context rewrite, not execution)
  *
  * Tool-call presentation (title/kind/rawInput, and the completed-state content)
  * is owned by each TOOL via `presentCall`/`presentResult` — the bridge never
@@ -965,6 +966,10 @@ export function streamSessionEventUpdate(
       return
     }
     case 'tool/result': {
+      // Replacements (for example model-free pruning) are transcript rewrites,
+      // not repeated tool executions. Re-presenting one would consume no
+      // pending call and could clobber the original terminal/diff completion.
+      if (event.surfaceOp !== undefined && event.surfaceOp !== 'append') return
       const view = presenter.result(event.data.callId, event.data.content, event.data.isError, event.data.meta)
       notify({ sessionId, update: toolResultUpdate(event.data.callId, view, event.data.isError, terminal) })
       return

packages/ui/acp/tests/load.spec.ts

@@ -162,6 +162,53 @@ describe('acp bridge — session/load replay', () => {
     expect(meta.terminal_exit?.exit_code).toBe(0)
   })
 
+  it('keeps one terminal completion live and on replay when a pruning replacement is logged', async () => {
+    live = await makeBridgeHarness({
+      storageDir,
+      withBash: true,
+      script: [toolCallResponse('c1', 'bash', { command: 'echo full', description: 'Print full output' }), textResponse('done')],
+    })
+    await live.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: { _meta: { terminal_output: true } } })
+    const { sessionId } = await live.client.newSession({ cwd: process.cwd(), mcpServers: [] })
+    await live.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'run it' }] })
+
+    const session = live.ctx.agents.get(AgentId(sessionId))!.session
+    const original = session.events.find(event => event.type === 'tool/result')
+    if (original?.type !== 'tool/result') throw new Error('expected original tool/result')
+    const liveCompletions = () => live!.updates.filter(update =>
+      update.sessionUpdate === 'tool_call_update' && update.toolCallId === 'c1')
+    expect(liveCompletions()).toHaveLength(1)
+    expect((liveCompletions()[0] as { _meta?: { terminal_output?: { data: string } } })._meta?.terminal_output?.data)
+      .toBe('full\n')
+
+    session.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } })
+    session.append('tool/result', {
+      ...original.data,
+      content: [{ type: 'text', text: '[... tool result middle pruned ...]' }],
+    }, {
+      surfaceOp: { op: 'replace', start: original.seq, end: original.seq },
+      sourceEventSeqs: [original.seq],
+    })
+    session.append('turn/end', { turn: 2, reason: { kind: 'completed' } })
+
+    // The replacement is durable but is not another live completion.
+    expect(session.events.filter(event => event.type === 'tool/result')).toHaveLength(2)
+    expect(JSON.stringify(session.deriveMessages())).toContain('tool result middle pruned')
+    expect(liveCompletions()).toHaveLength(1)
+    await live.dispose()
+    live = undefined
+
+    loader = await makeBridgeHarness({ storageDir, withBash: true, script: [] })
+    await loader.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: { _meta: { terminal_output: true } } })
+    await loader.client.loadSession({ sessionId, cwd: process.cwd(), mcpServers: [] })
+
+    const replayed = loader.updates.filter(update =>
+      update.sessionUpdate === 'tool_call_update' && update.toolCallId === 'c1')
+    expect(replayed).toHaveLength(1)
+    expect((replayed[0] as { _meta?: { terminal_output?: { data: string } } })._meta?.terminal_output?.data)
+      .toBe('full\n')
+  })
+
   it('a load whose resume finishes after a client disconnect leaks no live session', async () => {
     // Stall persistence so transport closes while resume is pending. Whether the SDK rejects first
     // or the bridge's post-await guard fires, no agent may survive for the dead connection.

packages/ui/acp/tests/stream-update.spec.ts

@@ -105,6 +105,22 @@ describe('streamSessionEventUpdate', () => {
     expect((failed[0] as { status: string }).status).toBe('failed')
   })
 
+  it('emits no execution update for a tool-result surface replacement', () => {
+    const replacement = {
+      ...evt('tool/result', {
+        turn: 1,
+        step: 1,
+        callId: CallId('c1'),
+        content: [{ type: 'text', text: '[... tool result middle pruned ...]' }],
+        isError: false,
+      }),
+      seq: 2,
+      surfaceOp: { op: 'replace', start: 1, end: 1 },
+      sourceEventSeqs: [1],
+    } as SessionEvent
+    expect(updatesFor(replacement)).toEqual([])
+  })
+
   it('drops non-text tool-result content (text-only)', () => {
     const update = updatesFor(evt('tool/result', {
       turn: 1, step: 1, callId: CallId('c1'),
@@ -450,6 +466,16 @@ describe('terminal-card mapping (capability-gated)', () => {
 
   const callEvent = evt('tool/call', { turn: 1, step: 1, callId: CallId('c1'), name: 'bash', arguments: JSON.stringify({ command: 'echo hi', description: 'Greet' }) })
   const resultEvent = evt('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'hi\n' }], isError: false })
+  const prunedResultEvent = {
+    ...resultEvent,
+    seq: 2,
+    data: {
+      ...resultEvent.data,
+      content: [{ type: 'text', text: '[... tool result middle pruned ...]' }],
+    },
+    surfaceOp: { op: 'replace', start: 1, end: 1 },
+    sourceEventSeqs: [1],
+  } as SessionEvent
 
   function termUpdates(tool: ToolDefinition, enabled: boolean, cwd: string | undefined, ...events: SessionEvent[]): SessionNotification['update'][] {
     const presenter = new ToolPresenter(registryOf(tool))
@@ -477,6 +503,27 @@ describe('terminal-card mapping (capability-gated)', () => {
     })
   })
 
+  it('live/replay translation preserves the original terminal completion across a pruning rewrite', () => {
+    const updates = termUpdates(
+      termTool({ card: 'terminal' }, { output: 'hi\n', exitCode: 0 }),
+      true,
+      '/work/proj',
+      callEvent,
+      resultEvent,
+      prunedResultEvent,
+    )
+    expect(updates).toHaveLength(2)
+    expect(updates[1]).toEqual({
+      sessionUpdate: 'tool_call_update',
+      toolCallId: 'c1',
+      status: 'completed',
+      _meta: {
+        terminal_output: { terminal_id: 'c1', data: 'hi\n' },
+        terminal_exit: { terminal_id: 'c1', exit_code: 0 },
+      },
+    })
+  })
+
   it('capability ON: an ABSOLUTE tool cwd wins; a RELATIVE one resolves against the session cwd', () => {
     const [absCall] = termUpdates(termTool({ card: 'terminal', cwd: '/explicit/abs' }, { output: 'x' }), true, '/work/proj', callEvent)
     expect((absCall as unknown as { _meta: { terminal_info: { cwd: string } } })._meta.terminal_info.cwd).toBe('/explicit/abs')
@@ -633,17 +680,38 @@ describe('result-time diff card (REAL fs edit tool → tool_call_update diff blo
   // call-time snippet, then the tool/result carries the tool's computed applied-hunk `meta`,
   // which presentResult narrows into a `diff` result card the bridge forwards as `{ type:
   // 'diff' }` content blocks. The real tool is required because its result metadata is the contract.
-  it('forwards the applied-hunk meta onto the wire as tool_call_update diff content', async () => {
+  it('live/replay translation keeps the applied diff when a pruning rewrite follows', async () => {
     const ctx = await fsCtx()
     const presenter = new ToolPresenter(ctx.tools)
     const args = JSON.stringify({ file_path: 'src/b.ts', old_string: 'OLD', new_string: 'NEW' })
     // The applied hunk the tool would compute and persist on the result meta.
     const meta = { diffs: [{ path: 'src/b.ts', oldText: 'a\nOLD\nb', newText: 'a\nNEW\nb' }] }
-    const [, resultUpdate] = updatesWith(
+    const originalResult = evt('tool/result', {
+      turn: 1,
+      step: 1,
+      callId: CallId('e1'),
+      content: [{ type: 'text', text: 'ok' }],
+      isError: false,
+      meta,
+    })
+    const replacement = {
+      ...originalResult,
+      seq: 3,
+      data: {
+        ...originalResult.data,
+        content: [{ type: 'text', text: '[... tool result middle pruned ...]' }],
+      },
+      surfaceOp: { op: 'replace', start: 2, end: 2 },
+      sourceEventSeqs: [2],
+    } as SessionEvent
+    const updates = updatesWith(
       presenter,
       evt('tool/call', { turn: 1, step: 1, callId: CallId('e1'), name: 'edit', arguments: args }),
-      evt('tool/result', { turn: 1, step: 1, callId: CallId('e1'), content: [{ type: 'text', text: 'ok' }], isError: false, meta }),
+      originalResult,
+      replacement,
     )
+    expect(updates).toHaveLength(2)
+    const resultUpdate = updates[1]
     expect(resultUpdate).toEqual({
       sessionUpdate: 'tool_call_update',
       toolCallId: 'e1',

packages/ui/stdio/README.md

@@ -27,7 +27,7 @@ The plugin seeds display labels from the live agent registry, then tracks `agent
 
 **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.
+**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. A replacement `tool/result` remains model-visible through the session surface but is not rendered as a second execution; stdio keeps the original full-fidelity result line.
 
 ### Terminal user-interaction answers
 

packages/ui/stdio/src/index.ts

@@ -124,6 +124,10 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt
       inReasoning = false
       output.write(`\n  [tool call] ${toolName}(${args})`)
     } else if (event.type === 'tool/result') {
+      // A surface replacement changes future model context; it is not another
+      // execution. Keep the original full-fidelity terminal presentation and
+      // suppress duplicate output during live delivery or log replay.
+      if (event.surfaceOp !== undefined && event.surfaceOp !== 'append') return
       const { content } = event.data
       const text = content.filter(block => block.type === 'text').map(block => block.text).join('')
       output.write(`\n  [tool result] ${text}\n  `)

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

@@ -288,6 +288,43 @@ describe('createStdioChat rendering', () => {
     expect(out.text()).toContain('[tool result] file.txt')
   })
 
+  it('renders one full-fidelity result whether the event feed is live or replayed', async () => {
+    const { ctx, out } = await setup()
+    const session = makeSession('main')
+    const original = {
+      type: 'tool/result',
+      seq: 2,
+      time: 0,
+      data: {
+        turn: 1,
+        step: 1,
+        callId: 'c1',
+        content: [{ type: 'text', text: 'full terminal output' }],
+        isError: false,
+        meta: { terminal: { output: 'full terminal output' } },
+      },
+      surfaceOp: 'append',
+    } as SessionEvent
+    const replacement = {
+      ...original,
+      seq: 3,
+      data: {
+        ...original.data,
+        content: [{ type: 'text', text: '[... tool result middle pruned ...]' }],
+      },
+      surfaceOp: { op: 'replace', start: 2, end: 2 },
+      sourceEventSeqs: [2],
+    } as SessionEvent
+
+    // Stdio consumes the same session/event shape whether a host forwards a
+    // live append or replays a stored log through the rendering feed.
+    for (const event of [original, replacement]) ctx.emit('session/event', session, event)
+
+    expect(out.text().match(/\[tool result\]/g)).toHaveLength(1)
+    expect(out.text()).toContain('full terminal output')
+    expect(out.text()).not.toContain('tool result middle pruned')
+  })
+
   it('renders a todo/write session event as a glyphed checklist', async () => {
     const { ctx, out } = await setup()
     const session = {} as Session