fix(replay): mark local compaction calls

packages/compact/compact-basic/README.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write packages/compact/compact-basic/README.md
-README.md: 0c7b009255dc2d41dc81cf2c7ff745e02ef28b9a
-README.zh.md: 4af584a059c99725882afd6206bdf9c984c7d4e3
+README.md: d1c1dfb509ae0750e1237532a829a35de5084c5e
+README.zh.md: a78887daad04d534ffed9cbd0357b76bdd908f5e

packages/compact/compact-basic/README.md

@@ -21,7 +21,7 @@ This backend owns the compaction policy:
 - **Overflow recovery** — provider-confirmed overflow needs no capacity metadata: it bypasses normal pressure and retention, 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 target-specific cap, cancellation, or an unknown/noncanonical error preserves the original provider failure.
 - **Failure handling** — a live unmatched `compact/start` is the durable lock. An unmatched marker before a newer `session/end-seed` is stale evidence from a prior lifecycle and does not block; one after that boundary reports `busy`. Summary and changed-span failures close with an error and leave the conversation surface untouched, though the attempt remains in the log. A failed close deliberately leaves a blocking orphan. Operational pressure failures warn and continue, while overflow-recovery failure preserves the original provider error only when no earlier replacement advanced the surface. Cancellation remains authoritative after cleanup and durability.
 
-The protected `summarize()` method 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 safe summary plus the complete provider output, call envelope, and usage when available (`{ summary, rawOutput?, provider, model, maxTokens?, usage? }`); the transaction preserves those fields on `compact/summary`.
+The protected `summarize()` method 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 safe summary plus the complete provider output, call envelope, and usage when available (`{ summary, rawOutput?, llmStreamCall?, provider, model, maxTokens?, usage? }`); `llmStreamCall: true` means producing that result consumed exactly one call through this context's `ctx.llm.stream()`, while `rawOutput` alone does not identify the call path. The transaction preserves those fields on `compact/summary`.
 
 ## Config (`BasicCompactConfig`)
 

packages/compact/compact-basic/README.zh.md

@@ -21,7 +21,7 @@
 - **溢出恢复**：提供方已确认的溢出不需容量元数据。它会绕过常规压力与保留，执行剪枝，再尝试一次最大平衡头部缩减，并留下最新不可分单元。只要 `surface.replaceGeneration` 前进，就允许重试，包括剪枝在后续摘要工作抛出异常前已落地的情况。如果没有替换、目标特定上限已耗尽、已取消，或遇到未知／非规范错误，则保留原始提供方失败。
 - **失败处理**：活动的未匹配 `compact/start` 是持久锁。位于较新 `session/end-seed` 之前的未匹配标记，是先前生命周期留下的陈旧证据，不会阻塞；位于该边界之后的标记报告 `busy`。摘要和 span 变更失败会以错误闭合，并保持会话表层不变，但日志中仍保留该尝试。闭合失败会有意留下阻塞性的未匹配标记。压力检查中的运行故障会发出警告并继续；只有此前没有替换推进表层时，溢出恢复失败才保留原始提供方错误。完成清理与持久化后，取消仍具有最终决定权。
 
-受保护的 `summarize()` 方法是唯一的子类钩子。基于模板或远程摘要器的子类可以覆盖该方法，同时压力、保留、溯源、缩减验证与已遮蔽 token 计量仍由 `ctx.tokenMeter` 负责。钩子返回安全摘要，以及完整提供方输出、调用 envelope 和可用时的 usage（`{ summary, rawOutput?, provider, model, maxTokens?, usage? }`）；事务会在 `compact/summary` 上保留这些字段。
+受保护的 `summarize()` 方法是唯一的子类钩子。基于模板或远程摘要器的子类可以覆盖该方法，同时压力、保留、溯源、缩减验证与已遮蔽 token 计量仍由 `ctx.tokenMeter` 负责。钩子返回安全摘要，以及完整提供方输出、调用 envelope 和可用时的 usage（`{ summary, rawOutput?, llmStreamCall?, provider, model, maxTokens?, usage? }`）；`llmStreamCall: true` 表示生成该结果时恰好通过此上下文的 `ctx.llm.stream()` 发起了一次调用，而单有 `rawOutput` 并不能判定调用路径。事务会在 `compact/summary` 上保留这些字段。
 
 ## 配置（`BasicCompactConfig`）
 

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

@@ -416,6 +416,7 @@ function commitCompactionBody(
     shadowedTokenCount,
     summary,
     rawOutput,
+    llmStreamCall,
     provider,
     model,
     maxTokens,
@@ -425,6 +426,7 @@ function commitCompactionBody(
   const summaryEvent = session.append('compact/summary', {
     summary,
     ...rawOutput === undefined ? {} : { rawOutput },
+    ...llmStreamCall === undefined ? {} : { llmStreamCall },
     shadowedRange: { start, end },
     shadowedSeqs: [...shadowedSeqs],
     shadowedTokenCount,

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

@@ -87,8 +87,16 @@ export interface SummarizationInput {
 /** Safe summary content plus the exact auxiliary call envelope recorded in provenance. */
 export interface SummaryResult {
   summary: ContentBlock[]
-  /** Complete provider output before the text-only summary projection. */
+  /**
+   * Complete provider output before the text-only summary projection; this
+   * alone does not identify the call path.
+   */
   rawOutput?: ContentBlock[]
+  /**
+   * Present only when producing the summary consumed exactly one call through
+   * this context's `ctx.llm.stream()`.
+   */
+  llmStreamCall?: true
   provider: string
   model: string
   maxTokens?: number
@@ -162,6 +170,7 @@ export async function summarizeWithLlm(
   return {
     summary,
     rawOutput,
+    llmStreamCall: true,
     provider: options.provider,
     model: options.model,
     maxTokens: config.maxTokens,

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

@@ -868,6 +868,7 @@ describe('compaction region transaction', () => {
       rawOutput: compact.rawOutput,
       usage: compact.usage,
     })
+    expect(summary?.data).not.toHaveProperty('llmStreamCall')
     const head = session.deriveMessages()[0]!
     expect(head.content[0]?.type).toBe('text')
     expect(head.content[0]?.type === 'text' ? head.content[0].text : '').toContain('<compacted-summary>')
@@ -1187,6 +1188,7 @@ describe('default one-shot summarizer', () => {
         { type: 'text', text: 'public summary' },
         { type: 'tool-call', id: CallId('unexpected'), name: 'x', arguments: '{}' },
       ],
+      llmStreamCall: true,
       provider: MODEL,
       model: MODEL,
       maxTokens: 321,
@@ -1300,6 +1302,7 @@ describe('default one-shot summarizer', () => {
     await compact.compactRegion(nodes[0]!, nodes[3]!, agent(session, MODEL), SIGNAL)
     expect(session.events.findLast(event => event.type === 'compact/summary')?.data).toMatchObject({
       summary: [{ type: 'text', text: 'routed summary' }],
+      llmStreamCall: true,
       provider: 'routed-summary-provider',
       model: 'routed-summary-model',
     })

packages/compact/compact/src/types.ts

@@ -28,8 +28,16 @@ declare module '@deepseek-ai/dsh-session' {
      */
     'compact/summary': {
       summary: ContentBlock[]
-      /** Complete provider output before the backend's safe summary projection. */
+      /**
+       * Complete provider output before the backend's safe summary projection;
+       * this alone does not identify the call path.
+       */
       rawOutput?: ContentBlock[]
+      /**
+       * Present only when producing the summary consumed exactly one call
+       * through this context's `ctx.llm.stream()`.
+       */
+      llmStreamCall?: true
       shadowedRange: { start: number; end: number }
       shadowedSeqs: number[]
       shadowedTokenCount: number

packages/support/llm-replay/README.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write packages/support/llm-replay/README.md
-README.md: 46d391970f320708914d11f0868cbbc5361ae196
-README.zh.md: a67b078a1396968dc3ddecb0e616a832c4faaf3a
+README.md: a6c087778b8e64124590fb6be7a652b58e1b6343
+README.zh.md: 241edb9c9b2400519155ccd7161eb7f34b9f5bbe

packages/support/llm-replay/README.md

@@ -8,7 +8,7 @@ Its consumers are the ACP and headless `stream-json` snapshot suites plus the We
 
 ## How the fixture works
 
-The fixture IS the persisted session log (`<scenario>/session.jsonl`). Its `assistant/chunk` events carry every `StreamChunk`, so grouping them by `(turn, step)` reconstructs each agent-loop `stream()` call's chunk sequence. A successful compaction summarizer is logged differently: when `compact/summary` carries its complete `rawOutput`, replay reconstructs a canonical successful stream at that event's position using one `block-start`/`block-end` pair per block, the recorded usage when present, and a terminal `stop`. Exact provider delta partitioning is not part of the durable compaction result. A summary without `rawOutput` does not imply an LLM call because template and remote summarizers may produce it without the local adapter.
+The fixture IS the persisted session log (`<scenario>/session.jsonl`). Its `assistant/chunk` events carry every `StreamChunk`, so grouping them by `(turn, step)` reconstructs each agent-loop `stream()` call's chunk sequence. A successful compaction summarizer is logged differently: when `compact/summary` carries `llmStreamCall: true` and its complete `rawOutput`, replay reconstructs a canonical successful stream at that event's position using one `block-start`/`block-end` pair per block, the recorded usage when present, and a terminal `stop`. Exact provider delta partitioning is not part of the durable compaction result. `rawOutput` without the marker does not imply a local LLM call because template and remote summarizers may retain complete output without using this context's adapter.
 
 Recording is therefore "run the real agent once and harvest the `.jsonl`", done by the snapshot harness — this plugin does not record. A fixture may carry its `request/header` content tokenized to `{{system}}`/`{{tools}}` (the harness pins that content in one scenario and scrubs the rest); replay is indifferent — derivation reads only `assistant/chunk` and `compact/summary` events plus the line-0 session header.
 
@@ -59,7 +59,7 @@ Replay keys every call by its calling session id (`GenerateOptions.sessionId`, s
 - `installLlmReplay(ctx, config)` — install the configured replay adapter or catch-all `llm/stream` listener; returns a `ReplayHandle` (`dispose()` for HMR safety plus `assertConsumed()`, the teardown check that every recorded script bound to a live session and every bound cursor drained — turning a scenario that silently drove fewer model calls than recorded into a crisp diagnostic). Use this in tests to drive replay without the Loader or env vars.
 - `loadSessionScripts(config)` — resolve the ordered `SessionScript[]` (primary + children) for a scenario, ready to bind to live sessions in first-call order.
 - `loadReplayScript(config)` — resolve the `ReplayEntry[]` for the primary session only (validated sidecar replacement/patches if present, else derived from the JSONL; fail-loud if the fixture is missing).
-- `deriveReplayScript(events)` / `parseSessionLog(text)` / `parseSessionHeader(text)` / `resolveScriptedEntry(entry, messages)` — the pure helpers that turn ordinary loop chunks and complete compaction outputs in a recorded session log into a script, read its header `id`/`createdAt`, and resolve `{{fromRequest:...}}` placeholders against one live request. A derived assistant group must end in a `finish` chunk; a group without one is the fingerprint of a thrown `stream()` and must instead be expressed via an override sidecar.
+- `deriveReplayScript(events)` / `parseSessionLog(text)` / `parseSessionHeader(text)` / `resolveScriptedEntry(entry, messages)` — the pure helpers that turn ordinary loop chunks and explicitly marked local compaction outputs in a recorded session log into a script, read its header `id`/`createdAt`, and resolve `{{fromRequest:...}}` placeholders against one live request. A derived assistant group must end in a `finish` chunk; a group without one is the fingerprint of a thrown `stream()` and must instead be expressed via an override sidecar.
 - Types `ReplayEntry` / `ReplayOverrideDoc` / `ReplayOverridePatch` / `SessionScript` / `ReplayConfig` / `ReplayProviderConfig` / `ReplayModelConfig` / `ReplayHandle` / `Config`.
 
 ## Plugin export shape
@@ -77,4 +77,4 @@ None; this package neither assembles nor sends a provider request.
 ## Known Limitations and Deferred Work
 
 - **First-call-order script binding assumes sequential delegation** — a cut that runs sibling subagents concurrently would bind live sessions to recorded scripts non-deterministically; a stronger keying is deferred until such a scenario exists (`XXX(concurrent-subagents)`).
-- **Only ordinary loop chunks and completed compaction outputs are derivable** — a pure pre-chunk throw or a cancel/hang scenario needs the `replay.override.json` sidecar. Replacement and patch forms affect only the primary session; child scripts still derive from their logs.
+- **Only ordinary loop chunks and marked local compaction outputs are derivable** — a pure pre-chunk throw, a cancel/hang, or an unmarked external summarizer call needs the `replay.override.json` sidecar. Replacement and patch forms affect only the primary session; child scripts still derive from their logs.

packages/support/llm-replay/README.zh.md

@@ -8,7 +8,7 @@
 
 ## fixture 的工作方式
 
-fixture 就是持久化的会话日志（`<scenario>/session.jsonl`）。其 `assistant/chunk` 事件包含每个 `StreamChunk`，因此按 `(turn, step)` 分组即可重建每次 agent-loop `stream()` 调用的分片序列。压缩（compaction）摘要器成功时，日志记录方式有所不同：当 `compact/summary` 携带完整的 `rawOutput` 时，回放会在该事件的位置重建一条规范成功流，其中每个块各使用一对 `block-start`/`block-end`，带上已记录的 usage（如有），并以 `stop` 终止。提供方增量的精确切分不属于持久压缩结果。不带 `rawOutput` 的摘要并不意味着发生了 LLM 调用，因为模板摘要器和远程摘要器可能不经本地适配器生成该摘要。
+fixture 就是持久化的会话日志（`<scenario>/session.jsonl`）。其 `assistant/chunk` 事件包含每个 `StreamChunk`，因此按 `(turn, step)` 分组即可重建每次 agent-loop `stream()` 调用的分片序列。压缩（compaction）摘要器成功时，日志记录方式有所不同：当 `compact/summary` 携带 `llmStreamCall: true` 和完整的 `rawOutput` 时，回放会在该事件的位置重建一条规范成功流，其中每个块各使用一对 `block-start`/`block-end`，带上已记录的 usage（如有），并以 `stop` 终止。提供方增量的精确切分不属于持久压缩结果。不带该标记的 `rawOutput` 并不意味着发生了本地 LLM 调用，因为模板摘要器和远程摘要器即使未使用此上下文的适配器，也可能保留完整输出。
 
 因此，录制就是「运行一次真实 agent 并收集 `.jsonl`」，由快照 harness 完成；该插件本身不录制。fixture 的 `request/header` 内容可能被标记化为 `{{system}}`/`{{tools}}`（harness 会在一个场景中固定该内容，并清除其余场景中的内容）；回放不受影响，因为派生过程只读取 `assistant/chunk` 和 `compact/summary` 事件以及第 0 行的会话 header。
 
@@ -59,7 +59,7 @@ fixture 就是持久化的会话日志（`<scenario>/session.jsonl`）。其 `as
 - `installLlmReplay(ctx, config)`：安装已配置回放适配器或 catch-all `llm/stream` 监听器；返回 `ReplayHandle`（包含用于保证 HMR（热模块替换）安全的 `dispose()`，以及清理阶段执行的 `assertConsumed()` 检查；后者确保每个已记录脚本都绑定到实时会话，且每个已绑定游标都已耗尽，从而将场景静默驱动的模型调用少于记录数转换为明确诊断）。在测试中使用它，可以不通过 Loader 或 env var 驱动回放。
 - `loadSessionScripts(config)`：解析场景中有序的 `SessionScript[]`（主会话 + 子会话），准备按首次调用顺序绑定到实时会话。
 - `loadReplayScript(config)`：只解析主会话的 `ReplayEntry[]`（如果伴随文件存在，则使用经校验的替换或补丁；否则从 JSONL 派生；fixture 缺失时明确报错）。
-- `deriveReplayScript(events)` / `parseSessionLog(text)` / `parseSessionHeader(text)` / `resolveScriptedEntry(entry, messages)`：将已记录会话日志中的普通 loop 分片和完整压缩输出转换为脚本、读取其 header `id`/`createdAt`、并针对单次实时请求解析 `{{fromRequest:...}}` 占位符的纯辅助工具。派生的 assistant 分组必须以 `finish` 分片结束；没有该分片的分组是 `stream()` 抛出异常的指纹，必须改用 override 伴随文件表达。
+- `deriveReplayScript(events)` / `parseSessionLog(text)` / `parseSessionHeader(text)` / `resolveScriptedEntry(entry, messages)`：将已记录会话日志中的普通 loop 分片和显式标记的本地压缩输出转换为脚本、读取其 header `id`/`createdAt`、并针对单次实时请求解析 `{{fromRequest:...}}` 占位符的纯辅助工具。派生的 assistant 分组必须以 `finish` 分片结束；没有该分片的分组是 `stream()` 抛出异常的指纹，必须改用 override 伴随文件表达。
 - 类型 `ReplayEntry` / `ReplayOverrideDoc` / `ReplayOverridePatch` / `SessionScript` / `ReplayConfig` / `ReplayProviderConfig` / `ReplayModelConfig` / `ReplayHandle` / `Config`。
 
 ## 插件导出形态
@@ -77,4 +77,4 @@ fixture 就是持久化的会话日志（`<scenario>/session.jsonl`）。其 `as
 ## 已知限制与暂缓事项
 
 - **首次调用顺序脚本绑定假设串行委托**：并发运行同级 subagent 的 cut 会非确定性地将实时会话绑定到已记录脚本；在这种场景出现前暂不实现更强的键控（`XXX(concurrent-subagents)`）。
-- **只有普通 loop 分片和已完成的压缩输出才能派生**：在产生分片前直接抛出异常或取消/挂起的场景需要 `replay.override.json` 伴随文件。替换和补丁两种形式都只影响主会话；子会话脚本仍从各自日志派生。
+- **只有普通 loop 分片和带标记的本地压缩输出才能派生**：在产生分片前直接抛出异常、取消/挂起，或未标记的外部摘要器调用场景需要 `replay.override.json` 伴随文件。替换和补丁两种形式都只影响主会话；子会话脚本仍从各自日志派生。

packages/support/llm-replay/src/index.ts

@@ -177,8 +177,9 @@ export function parseSessionHeader(text: string): { id: string; createdAt: numbe
  * Reconstruct the per-`stream()` replay script from a recorded session log.
  *
  * Splits `assistant/chunk` events at every `finish`, using turn and step changes
- * to detect an unterminated prior call. A complete `compact/summary.rawOutput`
- * becomes a canonical successful stream at the summary's log position. A
+ * to detect an unterminated prior call. A `compact/summary` explicitly marked
+ * as one local LLM-stream call becomes a canonical successful stream from its
+ * complete `rawOutput` at the summary's log position. A
  * missing assistant terminator means the live stream threw, so derivation
  * rejects and the scenario must provide an explicit override. Multiple calls
  * may share one turn and step when the loop retries.
@@ -204,7 +205,10 @@ export function deriveReplayScript(events: SessionEvent[]): ReplayEntry[] {
       close(currentKey, current)
       currentKey = undefined
       current = []
-      if (event.data.rawOutput !== undefined) {
+      if (event.data.llmStreamCall === true) {
+        if (event.data.rawOutput === undefined) {
+          throw new Error('llm-replay: compact/summary marks an LLM stream call without rawOutput')
+        }
         const chunks: StreamChunk[] = []
         for (const [index, block] of event.data.rawOutput.entries()) {
           chunks.push({ type: 'block-start', index, blockType: block.type })

packages/support/llm-replay/tests/llm-replay.spec.ts

@@ -202,6 +202,7 @@ describe('deriveReplayScript', () => {
         data: {
           summary: rawOutput,
           rawOutput,
+          llmStreamCall: true,
           shadowedRange: { start: 1, end: 1 },
           shadowedSeqs: [1],
           shadowedTokenCount: 20,
@@ -238,6 +239,45 @@ describe('deriveReplayScript', () => {
     expect(deriveReplayScript([event])).toEqual([])
   })
 
+  it('does not infer a local LLM call from external compact output', () => {
+    const block = { type: 'text' as const, text: 'remote summary' }
+    const event: SessionEvent<'compact/summary'> = {
+      type: 'compact/summary',
+      seq: 1,
+      time: 0,
+      data: {
+        summary: [block],
+        rawOutput: [block],
+        shadowedRange: { start: 1, end: 1 },
+        shadowedSeqs: [1],
+        shadowedTokenCount: 20,
+        provider: 'remote',
+        model: 'remote',
+      },
+    }
+
+    expect(deriveReplayScript([event])).toEqual([])
+  })
+
+  it('rejects a marked compact LLM call without its complete output', () => {
+    const event: SessionEvent<'compact/summary'> = {
+      type: 'compact/summary',
+      seq: 1,
+      time: 0,
+      data: {
+        summary: [{ type: 'text', text: 'incomplete provenance' }],
+        llmStreamCall: true,
+        shadowedRange: { start: 1, end: 1 },
+        shadowedSeqs: [1],
+        shadowedTokenCount: 20,
+        provider: 'mock',
+        model: 'mock',
+      },
+    }
+
+    expect(() => deriveReplayScript([event])).toThrow(/LLM stream call without rawOutput/)
+  })
+
   it('derives a compact/summary stream when usage is unavailable', () => {
     const block = { type: 'text' as const, text: 'summary without usage' }
     const event: SessionEvent<'compact/summary'> = {
@@ -247,6 +287,7 @@ describe('deriveReplayScript', () => {
       data: {
         summary: [block],
         rawOutput: [block],
+        llmStreamCall: true,
         shadowedRange: { start: 1, end: 1 },
         shadowedSeqs: [1],
         shadowedTokenCount: 20,
@@ -289,6 +330,27 @@ describe('deriveReplayScript', () => {
     ]
     expect(() => deriveReplayScript(events)).toThrow(/model call 1\/1 ended without a finish chunk/)
   })
+
+  it('rejects an unfinished call at a compact summary boundary', () => {
+    const events: SessionEvent[] = [
+      chunkEvent(1, 1, 1, { type: 'block-start', index: 0, blockType: 'text' }),
+      {
+        type: 'compact/summary',
+        seq: 2,
+        time: 0,
+        data: {
+          summary: [{ type: 'text', text: 'external checkpoint' }],
+          shadowedRange: { start: 1, end: 1 },
+          shadowedSeqs: [1],
+          shadowedTokenCount: 20,
+          provider: 'external',
+          model: 'external',
+        },
+      },
+    ]
+
+    expect(() => deriveReplayScript(events)).toThrow(/model call 1\/1 ended without a finish chunk/)
+  })
 })
 
 describe('loadReplayScript', () => {