Merge remote-tracking branch 'origin/master' into worktree/web-multimodal-image-input

# Conflicts:
#	.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.i18n.yaml
#	docs/config-catalog.md
#	docs/cordis-catalog/events.md
#	docs/cordis-catalog/services.md
#	docs/core-data-structures/core.md
#	docs/core-data-structures/core.zh.md
#	docs/core-data-structures/llm-streaming.i18n.yaml
#	docs/core-data-structures/llm-streaming.md
#	docs/core-data-structures/llm-streaming.zh.md
#	docs/event-producer-consumer.md
#	docs/module-graph.md
#	docs/subsystems/attachment.i18n.yaml
#	docs/subsystems/attachment.md
#	docs/subsystems/attachment.zh.md
#	docs/subsystems/core.i18n.yaml
#	examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl
#	packages/README.i18n.yaml
#	packages/README.md
#	packages/README.zh.md
#	packages/client/runtime/package.json
#	packages/client/ui-conversation/package.json
#	packages/client/ui-conversation/src/client/chat/AssistantMarkdown.tsx
#	packages/client/ui-conversation/src/client/chat/ChatView.tsx
#	packages/client/ui-conversation/src/client/chat/MessageItem.tsx
#	packages/client/ui-conversation/src/client/index.ts
#	packages/client/ui-conversation/tests/input-bar.spec.tsx
#	packages/compact/compact-basic/README.i18n.yaml
#	packages/compact/compact-basic/README.md
#	packages/compact/compact-basic/README.zh.md
#	packages/host/apiproxy/src/api-proxy.ts
#	packages/host/apiproxy/src/api/index.ts
#	packages/host/apiproxy/src/api/sessions.ts
#	packages/host/apiproxy/src/index.ts
#	packages/host/apiproxy/tests/api-proxy-models.spec.ts
#	packages/self-modification/tool-cordis/src/api-catalog.ts
#	pnpm-lock.yaml
#	scripts/type-equiv.manifest.json

packages/llm/token-meter/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/llm/token-meter/README.md
-README.md: 8f868f25f3c4caf1fdab5b50965aab41efecf5af
-README.zh.md: 3621105ff35606b62b0587063038116b4772c6cf
+README.md: 6cbbefa69fd4dd108d4c4ff717647e173922d7b2
+README.zh.md: 572409324e910f4b38ad48b2ec5fb2c85d4fd088

packages/llm/token-meter/README.md

@@ -6,7 +6,7 @@ Replay-aware token measurement through the singleton `ctx.tokenMeter` service. I
 
 ## Configuration
 
-The estimator has no settings. It intentionally uses one fixed heuristic: four characters per token plus structural overhead for roles, blocks, and request-envelope fields. Any key is rejected, including the obsolete global `contextWindow`; model capacity belongs to the adapter that owns an exact provider/model route and is available through `ctx.llm.resolveModelInfo().context`.
+The estimator has no settings. It intentionally uses one fixed heuristic: four characters per token plus structural overhead for roles, blocks, and request-envelope fields. Any key is rejected; model capacity belongs to the adapter that owns an exact provider/model route and is available through `ctx.llm.resolveModelInfo().context`.
 
 ## Measurement contract
 
@@ -17,9 +17,9 @@ The estimator has no settings. It intentionally uses one fixed heuristic: four c
 
 `measure()` synchronizes once and returns one detached, deeply immutable snapshot. `totalTokens` is request-and-response pressure, while `surfaceTokens` is the surface-only heuristic total and equals the sum of `nodes[].tokens`. A `requestHeader` override affects pressure fields only; the surface fields still describe the current session. Every call clones the positional nodes, so measurement is O(surface).
 
-The fold tracks full request-header snapshots, step boundaries, surface appends and replacements, successful assistant messages, provider usage, and assistant-chunk provenance. Provider usage is reused only when the latest successful call's canonical request envelope matches the measured envelope and its total is no lower than that call's full heuristic anchor; a later success replaces the earlier anchor. Otherwise the complete current envelope and surface are estimated. Surface changes remain signed relative to a matching anchor, including negative deltas after shrinking replacements.
+The fold tracks full request-header snapshots, step boundaries, surface appends and replacements, successful assistant messages, provider usage, and the chunk seqs cited by each assistant message. Provider usage is reused only when the latest successful call's canonical request envelope matches the measured envelope and its total is no lower than that call's full heuristic anchor; a later success replaces the earlier anchor. Otherwise the complete current envelope and surface are estimated. Surface changes remain signed relative to a matching anchor, including negative deltas after shrinking replacements.
 
-Usage accounting sums disjoint input, cache-read, cache-write, and output buckets; reasoning is not added again. Every successful call records an assistant anchor, including content-less calls. An explicit empty provenance list means a known empty provider stream, while absent legacy provenance conservatively treats the durable assistant output as provider output.
+Usage accounting sums disjoint input, cache-read, cache-write, and output buckets; reasoning is not added again. Every successful call records an assistant anchor, including content-less calls. An explicit empty `sourceEventSeqs` list means a known empty provider stream, while an absent legacy list conservatively treats the durable assistant output as provider output.
 
 ## Session projections
 
@@ -41,7 +41,7 @@ The occupancy fields are independent last-wins records and are **not** one atomi
 
 This is deliberate. An occupancy percentage is a user-facing reference figure, not a billing record or a gating input — nothing in the harness makes decisions from it, and compaction reads `measure()` instead. A UI computes occupancy by dividing measured pressure by the separately resolved capacity for the selected model.
 
-Making the pair atomic was tried and rejected: it required a transient non-replayable wire frame, which needed lifecycle fencing against cross-stream reordering and left occupancy blank after every reconnect. The [Agent Note](../../../.agents/notes/implemented/architecture/2026-07-29-projected-token-usage-and-request-context.md) records that comparison. Consumers that need an exact same-boundary figure should call `measure()` at their own request boundary rather than read this projection.
+The [Agent Note](../../../.agents/notes/implemented/architecture/2026-07-29-projected-token-usage-and-request-context.md) records the rejected atomic-pair comparison. Consumers that need an exact same-boundary figure should call `measure()` at their own request boundary rather than read this projection.
 
 ## Composition
 
@@ -65,4 +65,4 @@ No direct invalidation; the named consumer owns any request-prefix changes.
 - **The fixed heuristic is approximate** — content without reusable provider usage is priced by character count plus structural overhead, not an exact provider tokenizer or request serializer.
 - **Every measurement clones the current surface** — coherent immutable snapshots make reads O(surface), including below-threshold pressure checks.
 - **Provider usage is only reusable for an identical canonical envelope** — prompt, prefix, tools, provider, model, or call-config changes deliberately fall back to full heuristic estimation.
-- **Legacy provenance is conservative** — assistant messages without `sourceEventSeqs` cannot distinguish provider output from listener rewrites, so the fold avoids claiming a known empty or exact chunk stream.
+- **Missing legacy source seqs are handled conservatively** — assistant messages without `sourceEventSeqs` cannot distinguish provider output from listener rewrites, so the fold avoids claiming a known empty or exact chunk stream.

packages/llm/token-meter/README.zh.md

@@ -6,9 +6,9 @@
 
 ## 配置
 
-估算器没有配置项。它有意使用一项固定启发式规则：每个 token 按四个字符估算，再加上角色、块与请求 envelope 字段的结构开销。任何配置键都会被拒绝，包括已废弃的全局 `contextWindow`；模型容量属于拥有精确提供方／模型路由的适配器，可通过 `ctx.llm.resolveModelInfo().context` 获取。
+估算器没有配置项。它有意使用一项固定启发式规则：每个 token 按四个字符估算，再加上角色、块与请求 envelope 字段的结构开销。任何配置键都会被拒绝；模型容量属于拥有精确提供方／模型路由的适配器，可通过 `ctx.llm.resolveModelInfo().context` 获取。
 
-## 测量契约
+## 测量约定
 
 `ctx.tokenMeter` 直接公开两个操作：
 
@@ -17,9 +17,9 @@
 
 `measure()` 会同步一次，并返回一个独立且深度不可变的快照。`totalTokens` 是请求与响应压力，`surfaceTokens` 是仅表层启发式总量，等于 `nodes[].tokens` 之和。`requestHeader` 覆盖只影响压力字段；表层字段仍描述当前会话。每次调用都会克隆带位置的节点，因此测量是 O(surface)。
 
-fold 跟踪完整请求标头快照、步骤边界、表层追加与替换、成功 assistant 消息、提供方用量和 assistant 分片溯源。只有当最新成功调用的规范请求 envelope 与已测量 envelope 匹配，且其总量不低于该调用的完整启发式锚点时，才会复用提供方用量；后续成功会替换较早锚点。否则会对当前 envelope 与表层进行完整估算。表层变更保持相对于匹配锚点的带符号值，包括缩减替换后的负 delta。
+fold 跟踪完整请求标头快照、步骤边界、表层追加与替换、成功 assistant 消息、提供方用量，以及每条 assistant 消息引用的分片 seq。只有当最新成功调用的规范请求 envelope 与已测量 envelope 匹配，且其总量不低于该调用的完整启发式锚点时，才会复用提供方用量；后续成功会替换较早锚点。否则会对当前 envelope 与表层进行完整估算。表层变更保持相对于匹配锚点的带符号值，包括缩减替换后的负 delta。
 
-用量计量会求和不重叠的输入、cache-read、cache-write 与输出 bucket；不会再次添加推理（reasoning）。每次成功调用都会记录一个 assistant 锚点，包括无内容调用。显式空溯源列表表示已知空提供方流，而遗留溯源缺失时，fold 会保守地将持久 assistant 输出视为提供方输出。
+用量计量会求和不重叠的输入、cache-read、cache-write 与输出 bucket；不会再次添加推理（reasoning）。每次成功调用都会记录一个 assistant 锚点，包括无内容调用。显式的空 `sourceEventSeqs` 列表表示已知空提供方流；遗留记录缺少该列表时，fold 会保守地将持久 assistant 输出视为提供方输出。
 
 ## 会话投影
 
@@ -29,9 +29,9 @@ fold 跟踪完整请求标头快照、步骤边界、表层追加与替换、成
 
 `contextPressure` 携带可选的 `pressureTokens`（提供方报告的最新提示词规模，为未缓存输入加缓存读取与写入之和）、可选的 `projectedTokens`，以及来自最新一条 `request/context` 记录的可选 `contextWindow`。提供方报告用量前两个数字都保持缺失；路由适配器未公布容量时容量也保持缺失。输出不计入其中，因此轮次流式输出期间 `pressureTokens` 保持不动，等到下一个请求报告用量时才前进。
 
-`projectedTokens` 是「下一个请求的提示词要花多少」：在该样本之上，加上自取样以来表层增减部分的启发式重新计价，下界钳制为零，折叠走的是测量服务重放的同一份 `surface-fold.ts`。只有增量部分是估算的，因此这个数字既锚定在提供方读数上，又能在内容落地——或压缩遮蔽一段区间——的瞬间做出反应。最后这种情况正是该字段存在的理由：压缩通过直连的 `ctx.llm.stream()` 调用生成摘要，自身不追加任何用量，所以仅凭 `pressureTokens` 会一直报告压缩前的提示词规模，直到又跑完一整轮为止。占用率展示读取 `projectedTokens`。
+`projectedTokens` 是「下一个请求的提示词要花多少」：在该样本之上，加上自取样以来表层增减部分的启发式重新计价，下界钳制为零，折叠走的是测量服务重放的同一份 `surface-fold.ts`。只有增量部分是估算的，因此这个数字既锚定在提供方读数上，又能在内容落地——或压缩遮蔽一段区间——的瞬间做出反应。最后这种情况正是该字段存在的理由：压缩通过直连的 `ctx.llm.stream()` 调用生成摘要，自身不追加任何用量，所以仅凭 `pressureTokens` 会一直报告压缩前的提示词规模，直到再完成一整个轮次为止。占用率展示读取 `projectedTokens`。
 
-`contextBreakdown` 携带启发式的 `systemTokens`、`toolsTokens` 与 `messageTokens`，描述上下文的组成而非提供方计费规模。envelope 数字在每条 `request/header` 上按后者胜重新计价；消息数字重放 `surface-fold.ts`——与 `measure()` 运行的位置折叠是同一份——因此它在每个事件边界上都等于 `measure().surfaceTokens`，压缩会像缩小下一个请求那样缩小它。三个数字都使用测量服务的固定启发式规则，属于估算值：它们加起来不等于 `projectedTokens`——后者的提供方锚点恰好把这些明细行仍然带着的误差排除在外（按「4 字符 ≈ 1 token」计价，CJK 文本与 JSON schema 会被严重低估）。请把它们当作近似的**组成**呈现，而不是总量。
+`contextBreakdown` 携带启发式的 `systemTokens`、`toolsTokens` 与 `messageTokens`，描述上下文的组成而非提供方计费规模。envelope 数字在每条 `request/header` 上按后者胜重新计价；消息数字重放 `surface-fold.ts`——也就是 `measure()` 运行的同一个带位置 fold——因此它在每个事件边界上都等于 `measure().surfaceTokens`，压缩会像缩小下一个请求那样缩小它。三个数字都使用测量服务的固定启发式规则，属于估算值：它们加起来不等于 `projectedTokens`——后者的提供方锚点所体现的恰好是这些明细行仍然带着的误差（按「4 字符 ≈ 1 token」计价，CJK 文本与 JSON schema 会被严重低估）。请把它们当作近似的**组成**呈现，而不是总量。
 
 三个单元都使用标准的投影基线、实时帧、seq 高者胜值仓和 JSON 检查点路径。卸载 token-meter 会移除这三个键。不带投影 seam 的组合会保留测量服务的既有行为。
 
@@ -41,7 +41,7 @@ fold 跟踪完整请求标头快照、步骤边界、表层追加与替换、成
 
 这是刻意的选择。占用率百分比是面向用户的参考数字，既不是计费记录，也不是门控输入：harness 中没有任何环节依据它做决策，压缩改为直接读取 `measure()`。UI 用测得的压力除以为所选模型单独解析出的容量来计算占用率。
 
-让这对值保持原子已经尝试过并被否决：它需要一个临时且不可回放的协议帧，进而需要针对跨流重排序的生命周期栅栏，还会让占用率在每次重连后变为空白。[Agent Note](../../../.agents/notes/implemented/architecture/2026-07-29-projected-token-usage-and-request-context.md)记录了这项对比。需要同一边界精确数字的消费方应在自己的请求边界调用 `measure()`，而不是读取该投影。
+[Agent Note](../../../.agents/notes/implemented/architecture/2026-07-29-projected-token-usage-and-request-context.md)记录了否决「让这对值保持原子」方案的那次对比。需要同一边界精确数字的消费方应在自己的请求边界调用 `measure()`，而不是读取该投影。
 
 ## 组合
 
@@ -65,4 +65,4 @@ fold 跟踪完整请求标头快照、步骤边界、表层追加与替换、成
 - **固定启发式规则是近似值**：没有可复用提供方用量的内容按字符数加结构开销计价，而不是使用精确提供方 tokenizer 或请求 serializer。
 - **每次测量都会克隆当前表层**：一致且不可变的快照使读取成为 O(surface)，包括低于阈值的压力检查。
 - **提供方用量只能为完全相同的规范 envelope 复用**：提示词、前缀、工具、提供方、模型或调用配置变更都会有意回退到完整启发式估算。
-- **遗留溯源采取保守策略**：没有 `sourceEventSeqs` 的 assistant 消息无法区分提供方输出与 listener 改写，因此 fold 不会声称已知空流或精确分片流。
+- **保守处理缺少源事件 seq 的遗留记录**：没有 `sourceEventSeqs` 的 assistant 消息无法区分提供方输出与 listener 改写，因此 fold 不会声称已知空流或精确分片流。

packages/llm/token-meter/src/index.ts

@@ -10,7 +10,7 @@ import { BlockAssembler, deepFreeze } from '@deepseek-ai/dsh-llm'
 import type { Message, TokenUsage } from '@deepseek-ai/dsh-llm'
 import type { EpochHeader, Session, SessionEvent } from '@deepseek-ai/dsh-session'
 import { canonicalHeader, headerEquals, isSurfaceEvent } from '@deepseek-ai/dsh-session'
-// Type-only: resolves the optional projection registry Context seam.
+// Type-only: resolves the optional projection registry Context declaration.
 import type {} from '@deepseek-ai/dsh-session-projection'
 import type {
   TokenMeasurement,
@@ -270,9 +270,9 @@ export class TokenMeterService extends Service {
   }
 
   /**
-   * Reassemble provider output from exact chunk provenance for a usage anchor.
-   * Missing legacy provenance conservatively treats the durable output as the
-   * provider output; explicit empty provenance prices a known empty stream.
+   * Reassemble provider output from the exact cited chunk seqs for a usage anchor.
+   * Missing legacy source seqs conservatively treat the durable output as the
+   * provider output; an explicit empty list prices a known empty stream.
    */
   private _estimateProviderAssistant(
     session: Session,

packages/llm/token-meter/tests/context-breakdown-projection.spec.ts

@@ -10,6 +10,7 @@ import type { Session, SessionEvent } from '@deepseek-ai/dsh-session'
 import SessionProjectionRegistry from '@deepseek-ai/dsh-session-projection'
 import TokenMeterService from '@deepseek-ai/dsh-token-meter'
 import type { ContextBreakdownProjection } from '@deepseek-ai/dsh-token-meter/client'
+import { CompactionId } from '@deepseek-ai/dsh-compact'
 import { contextBreakdownProjectionDefinition } from '../src/breakdown-projection.ts'
 import {
   estimateContent,
@@ -59,6 +60,7 @@ function appendSummaryMeter(ctx: Context, session: Session, start: number, end:
   const endIdx = nodes.findIndex(node => node.seq === end)
   const shadowed = nodes.slice(startIdx, endIdx + 1)
   session.append('compact/summary', {
+    compactionId: CompactionId('context-breakdown-summary'),
     summary: [{ type: 'text', text: 'summary' }],
     shadowedRange: { start, end },
     shadowedSeqs: shadowed.map(node => node.seq),

packages/llm/token-meter/tests/token-meter.spec.ts

@@ -313,7 +313,7 @@ describe('replay anchors and surface folds', () => {
     expect(advanced.surfaceDeltaTokens).toBeGreaterThan(0)
   })
 
-  it('distinguishes explicit empty provenance from absent legacy provenance', () => {
+  it('distinguishes an explicit empty source-event list from an absent legacy list', () => {
     const explicit = Session.create(SessionId('explicit-empty'))
     const legacy = Session.create(SessionId('legacy-absent'))
     appendSuccessfulCall(explicit, header('deepseek-v4-flash'), {
@@ -503,7 +503,7 @@ describe('malformed replay and listener lifecycle', () => {
     )
   })
 
-  it('rejects invalid assistant provenance', () => {
+  it('rejects invalid assistant source-event references', () => {
     const cases: Array<{
       name: string
       appendSource(session: Session): number[]
@@ -553,7 +553,7 @@ describe('malformed replay and listener lifecycle', () => {
     }
   })
 
-  it('rejects repeated and non-earlier assistant provenance', () => {
+  it('rejects repeated and non-earlier assistant source-event references', () => {
     const duplicate = Session.create(SessionId('duplicate-source'))
     duplicate.append('step/start', { turn: 1, step: 1 })
     appendHeader(duplicate, header('deepseek-v4-flash'))

packages/llm/token-meter/tests/token-usage-projection.spec.ts

@@ -7,6 +7,7 @@ import type { Session } from '@deepseek-ai/dsh-session'
 import SessionProjectionRegistry from '@deepseek-ai/dsh-session-projection'
 import TokenMeterService from '@deepseek-ai/dsh-token-meter'
 import type { ContextPressureProjection, TokenUsageProjection } from '@deepseek-ai/dsh-token-meter/client'
+import { CompactionId } from '@deepseek-ai/dsh-compact'
 
 const ZERO: TokenUsageProjection = {
   uncachedInputTokens: 0,
@@ -81,6 +82,7 @@ function appendSummaryMeter(ctx: Context, session: Session, start: number, end:
   const endIdx = nodes.findIndex(node => node.seq === end)
   const shadowed = nodes.slice(startIdx, endIdx + 1)
   session.append('compact/summary', {
+    compactionId: CompactionId('token-usage-summary'),
     summary: [{ type: 'text', text: 'summary' }],
     shadowedRange: { start, end },
     shadowedSeqs: shadowed.map(node => node.seq),

packages/llm/token-meter/tsconfig.json

@@ -27,7 +27,7 @@
       "path": "../../compact/compact"
     },
     {
-      "path": "../../session-projection/session-projection"
+      "path": "../../session/session-projection"
     },
     {
       "path": "../../support/invariants"