@deepseek-ai/dsh-session-reference 0.0.1-rc.2 → 0.0.1-rc.3

package/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/context/session-reference/README.md
-README.md: 145ec112d6b9cce9e9eb1567c60cde41c6d6eb3c
-README.zh.md: 5d528a296ee77dc64b584d0683395cb4df67936a
+README.md: 1f7df17f512b109e0e29bebf3f7931516914c368
+README.zh.md: 380f1c613621a8e1fd5b4ee27b70f40f4072197b

package/README.md

@@ -2,7 +2,7 @@
 
 English | [中文](README.zh.md)
 
-`ctx.sessionReferences` prepares bounded, read-only snapshots of other sessions as sourced model-facing context. It consumes `ctx.sessionQuery` and the backend-independent compact checkpoint marker; SQLite FTS is not required. Hosts that support cross-session mentions may opt into the service.
+`ctx.sessionReferenceResolver` prepares bounded, read-only snapshots of other sessions as sourced model-facing context. It consumes `ctx.sessionQuery` and the backend-independent compact checkpoint marker; SQLite FTS is not required. Hosts that support cross-session mentions may opt into the service.
 
 ## Public API
 
@@ -12,7 +12,7 @@ English | [中文](README.zh.md)
 
 ## Snapshot semantics
 
-Preparation calls `ctx.sessionQuery.readSurface()` once per distinct source and never rereads it after enqueue. It projects only direct-user `user/message`, assistant text, and `user/message` checkpoints carrying the canonical `dsh-compact` source marker from the folded current surface. For a source prompt that already contains baked prefix context, projection reads only its model-hidden display content, preventing recursive snapshot propagation. Shadowed pre-compaction events, tools, reasoning, context, plugin-generated user messages other than marked compact checkpoints, and unfinished assistant chunks are excluded. A compacted source therefore contributes its latest checkpoint plus retained later conversation, not restored shadowed text.
+Preparation calls `ctx.sessionQuery.readSurface()` once per distinct source and never rereads it after enqueue. It projects only direct-user `user/message`, assistant text, and `user/message` checkpoints carrying the canonical `dsh-compaction` source marker from the folded current surface. For a source prompt that already contains baked prefix context, projection reads only its model-hidden display content, preventing recursive snapshot propagation. Shadowed pre-compaction events, tools, reasoning, context, plugin-generated user messages other than marked compact checkpoints, and unfinished assistant chunks are excluded. A compacted source therefore contributes its latest checkpoint plus retained later conversation, not restored shadowed text.
 
 The context source is `{ kind: 'session-reference', version: 1, references }`; each reference records its source id and label, capture seq, compact presence, retained/omitted message counts, omitted UTF-8 bytes, and truncation state. When the agent is idle, the standard TUI installs a one-shot `agent/pre-step` wrapper that adds the snapshot only to an `enter` decision containing the claimed direct prompt. While the agent is running, it calls `inject()` immediately before `steer()`, placing both messages in the next-step inbox for the same later claim. The target log therefore records a sourced context `user/message` followed by the readable direct `user/message`. Later source mutation, compaction, or deletion cannot change target replay.
 
@@ -24,7 +24,7 @@ The context source is `{ kind: 'session-reference', version: 1, references }`; e
 | `candidateLimit` | `50` | Default candidate count returned to a host. |
 | `maxReferenceBytes` | `65536` | Maximum serialized JSON bytes for one reference object. |
 
-Retention applies `maxReferenceBytes` independently to each source, keeps compact checkpoints and the newest message before dropping older non-checkpoint units, and uses `dsh-retention` head/tail truncation with an exact UTF-8 omission notice. If one source's fixed serialized fields cannot fit, preparation fails with `SESSION_REFERENCE_BUDGET_EXCEEDED` instead of returning a partial context.
+Retention applies `maxReferenceBytes` independently to each source, keeps compact checkpoints and the newest message before dropping older non-checkpoint units, and uses `dsh-output-retention` head/tail truncation with an exact UTF-8 omission notice. If one source's fixed serialized fields cannot fit, preparation fails with `SESSION_REFERENCE_BUDGET_EXCEEDED` instead of returning a partial context.
 
 ## Model Experience
 

package/README.zh.md

@@ -2,7 +2,7 @@
 
 [English](README.md) | 中文
 
-`ctx.sessionReferences` 会把其他会话准备为有界、只读快照，作为带来源信息、面向模型的上下文。它消费 `ctx.sessionQuery` 与后端无关的 compact 检查点标记；不需要 SQLite FTS。支持跨会话 mention 的宿主可以主动启用该服务。
+`ctx.sessionReferenceResolver` 会把其他会话准备为有界、只读快照，作为带来源信息、面向模型的上下文。它消费 `ctx.sessionQuery` 与后端无关的 compact 检查点标记；不需要 SQLite FTS。支持跨会话 mention 的宿主可以主动启用该服务。
 
 ## 公开 API
 
@@ -12,7 +12,7 @@
 
 ## 快照语义
 
-准备阶段会对每个不同源调用一次 `ctx.sessionQuery.readSurface()`，入队后绝不重读。它仅投影折叠后当前表层中的用户直接发出的 `user/message`、assistant 文本，以及 `user/message` 检查点；这类检查点携带规范 `dsh-compact` 源标记。对于已经包含固化前缀上下文的源提示词，投影只读取其对模型隐藏的显示内容，以防止快照递归传播。已遮蔽的压缩（compaction）前事件、工具、推理（reasoning）、上下文、除已标记 compact 检查点外的插件生成 user 消息，以及未完成的 assistant 分片均会被排除。因此，已压缩源只会提供最新检查点及其后保留的会话内容，不会还原已遮蔽的文本。
+准备阶段会对每个不同源调用一次 `ctx.sessionQuery.readSurface()`，入队后绝不重读。它仅投影折叠后当前表层中的用户直接发出的 `user/message`、assistant 文本，以及 `user/message` 检查点；这类检查点携带规范 `dsh-compaction` 源标记。对于已经包含固化前缀上下文的源提示词，投影只读取其对模型隐藏的显示内容，以防止快照递归传播。已遮蔽的压缩（compaction）前事件、工具、推理（reasoning）、上下文、除已标记 compact 检查点外的插件生成 user 消息，以及未完成的 assistant 分片均会被排除。因此，已压缩源只会提供最新检查点及其后保留的会话内容，不会还原已遮蔽的文本。
 
 上下文源为 `{ kind: 'session-reference', version: 1, references }`；每条引用会记录其源 id 与 label、捕获 seq、是否存在 compact、已保留／已省略消息数、已省略 UTF-8 字节数与截断状态。agent 空闲时，标准 TUI 会安装一次性的 `agent/pre-step` 包装层，只把快照添加到包含已领取直接提示词的 `enter` 决策。agent 运行时，它会紧接着调用 `inject()` 和 `steer()`，把两条消息放入 next-step inbox，等待后续同一次领取。目标日志因此会先记录一条带来源信息的上下文 `user/message`，再记录可读的直接 `user/message`。后续源变更、压缩或删除都无法改变目标回放。
 
@@ -24,7 +24,7 @@
 | `candidateLimit` | `50` | 返回给宿主的默认候选数量。 |
 | `maxReferenceBytes` | `65536` | 一个引用对象的最大序列化 JSON 字节数。 |
 
-保留会对每个源独立应用 `maxReferenceBytes`，保留 compact 检查点与最新消息，再丢弃较旧的非检查点单元，并使用 `dsh-retention` 头部／尾部截断和精确 UTF-8 省略通知。如果某个源的固定序列化字段本身就超出限额，准备会以 `SESSION_REFERENCE_BUDGET_EXCEEDED` 失败，而不返回部分上下文。
+保留会对每个源独立应用 `maxReferenceBytes`，保留 compact 检查点与最新消息，再丢弃较旧的非检查点单元，并使用 `dsh-output-retention` 头部／尾部截断和精确 UTF-8 省略通知。如果某个源的固定序列化字段本身就超出限额，准备会以 `SESSION_REFERENCE_BUDGET_EXCEEDED` 失败，而不返回部分上下文。
 
 ## 模型体验
 

package/lib/index.js

@@ -1,8 +1,8 @@
 import { Service } from "@deepseek-ai/cordis";
 import z from "@deepseek-ai/schemastery";
 import { assertNever, createUserMessage } from "@deepseek-ai/dsh-llm";
-import { isCompactCheckpointSource } from "@deepseek-ai/dsh-compact";
-import { TextRetainer } from "@deepseek-ai/dsh-retention";
+import { isCompactCheckpointSource } from "@deepseek-ai/dsh-compaction";
+import { TextRetainer } from "@deepseek-ai/dsh-output-retention";
 import { SessionId } from "@deepseek-ai/dsh-session";
 //#region lib/types/config.js
 /** Configuration and stable diagnostics for session references. */
@@ -276,7 +276,7 @@ user explicitly repeats them.
 `;
 const PROMPT_SUFFIX = "\n</referenced-sessions>";
 /** Exact-read consumer that prepares immutable cross-session message context. */
-var SessionReferenceService = class extends Service {
+var SessionReferenceResolver = class extends Service {
 	static inject = ["sessionQuery"];
 	static Config = z.object({
 		maxReferences: z.number().step(1).min(1).max(3).default(3),
@@ -285,7 +285,7 @@ var SessionReferenceService = class extends Service {
 	});
 	config;
 	constructor(ctx, config = {}) {
-		super(ctx, "sessionReferences");
+		super(ctx, "sessionReferenceResolver");
 		this.config = {
 			maxReferences: config.maxReferences ?? 3,
 			candidateLimit: config.candidateLimit ?? 50,
@@ -438,4 +438,4 @@ function cancelled(signal) {
 	return new SessionReferenceError("session reference preparation was cancelled", "SESSION_REFERENCE_CANCELLED", { cause: signal.reason });
 }
 //#endregion
-export { DEFAULT_CANDIDATE_LIMIT, DEFAULT_MAX_REFERENCE_BYTES, MAX_REFERENCES, SESSION_REFERENCE_SCHEME, SessionReferenceError, SessionReferenceService, SessionReferenceService as default, decodeSessionReferenceUri, encodeSessionReferenceUri, formatSessionReferenceMention, parseSessionReferenceText };
+export { DEFAULT_CANDIDATE_LIMIT, DEFAULT_MAX_REFERENCE_BYTES, MAX_REFERENCES, SESSION_REFERENCE_SCHEME, SessionReferenceError, SessionReferenceResolver, SessionReferenceResolver as default, decodeSessionReferenceUri, encodeSessionReferenceUri, formatSessionReferenceMention, parseSessionReferenceText };

package/lib/types/index.d.ts

@@ -16,11 +16,11 @@ export { DEFAULT_CANDIDATE_LIMIT, DEFAULT_MAX_REFERENCE_BYTES, MAX_REFERENCES, S
 export { SESSION_REFERENCE_SCHEME, decodeSessionReferenceUri, encodeSessionReferenceUri, formatSessionReferenceMention, parseSessionReferenceText, } from './uri.ts';
 declare module '@deepseek-ai/cordis' {
     interface Context {
-        sessionReferences: SessionReferenceService;
+        sessionReferenceResolver: SessionReferenceResolver;
     }
 }
 /** Exact-read consumer that prepares immutable cross-session message context. */
-export declare class SessionReferenceService extends Service {
+export declare class SessionReferenceResolver extends Service {
     static inject: string[];
     static Config: z<Config>;
     private readonly config;
@@ -45,5 +45,5 @@ export declare class SessionReferenceService extends Service {
     prepare(agent: Agent, content: ContentBlock[], references: SessionReferenceInput[], signal?: AbortSignal): Promise<PreparedReferencedMessage>;
     private renderSources;
 }
-export default SessionReferenceService;
+export default SessionReferenceResolver;
 //# sourceMappingURL=index.d.ts.map

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@deepseek-ai/dsh-session-reference",
-  "description": "Cross-session snapshot references and durable untrusted model context (ctx.sessionReferences)",
-  "version": "0.0.1-rc.2",
+  "description": "Cross-session snapshot references and durable untrusted model context (ctx.sessionReferenceResolver)",
+  "version": "0.0.1-rc.3",
   "publishConfig": {
     "access": "restricted"
   },
@@ -35,23 +35,23 @@
     "@deepseek-ai/schemastery": "^3.18.1-rc.1"
   },
   "peerDependencies": {
-    "@deepseek-ai/dsh-agent": "^0.0.1-rc.2",
-    "@deepseek-ai/dsh-invariants": "^0.0.1-rc.2",
-    "@deepseek-ai/dsh-llm": "^0.0.1-rc.2",
-    "@deepseek-ai/dsh-compact": "^0.0.1-rc.2",
-    "@deepseek-ai/dsh-retention": "^0.0.1-rc.2",
-    "@deepseek-ai/dsh-session": "^0.0.1-rc.2",
-    "@deepseek-ai/dsh-session-query": "^0.0.1-rc.2",
+    "@deepseek-ai/dsh-compaction": "^0.0.1-rc.3",
+    "@deepseek-ai/dsh-invariants": "^0.0.1-rc.3",
+    "@deepseek-ai/dsh-agent": "^0.0.1-rc.3",
+    "@deepseek-ai/dsh-llm": "^0.0.1-rc.3",
+    "@deepseek-ai/dsh-output-retention": "^0.0.1-rc.3",
+    "@deepseek-ai/dsh-session": "^0.0.1-rc.3",
+    "@deepseek-ai/dsh-session-query": "^0.0.1-rc.3",
     "@deepseek-ai/cordis": "^4.0.1-rc.1"
   },
   "devDependencies": {
-    "@deepseek-ai/dsh-agent": "^0.0.1-rc.2",
-    "@deepseek-ai/dsh-compact": "^0.0.1-rc.2",
-    "@deepseek-ai/dsh-llm": "^0.0.1-rc.2",
-    "@deepseek-ai/dsh-invariants": "^0.0.1-rc.2",
-    "@deepseek-ai/dsh-retention": "^0.0.1-rc.2",
-    "@deepseek-ai/dsh-session-query": "^0.0.1-rc.2",
-    "@deepseek-ai/cordis": "^4.0.1-rc.1",
-    "@deepseek-ai/dsh-session": "^0.0.1-rc.2"
+    "@deepseek-ai/dsh-compaction": "^0.0.1-rc.3",
+    "@deepseek-ai/dsh-invariants": "^0.0.1-rc.3",
+    "@deepseek-ai/dsh-llm": "^0.0.1-rc.3",
+    "@deepseek-ai/dsh-output-retention": "^0.0.1-rc.3",
+    "@deepseek-ai/dsh-agent": "^0.0.1-rc.3",
+    "@deepseek-ai/dsh-session": "^0.0.1-rc.3",
+    "@deepseek-ai/dsh-session-query": "^0.0.1-rc.3",
+    "@deepseek-ai/cordis": "^4.0.1-rc.1"
   }
 }