@apollo-music/dsh-sidecar-terms 0.1.3 → 0.1.5

package/README.md

@@ -10,6 +10,7 @@
 6. steer 修订后不再审计同一 turn 的后续 assistant 输出，避免规则回执自我触发；下一 turn 自动恢复；
 7. 最终答案前只 steer 尚未交付的 canonical term / Rule delta。
 8. Catalog、Resolver、鉴权或网络不可用时失败关闭，不生成离线替代规则。
+9. 超过 Resolver 单段上限的消息只在术语审计传输层按自然或结构边界无损分段；DSH 交给模型的消息保持完整不变，分段按原事件序号在一次 Resolver 请求中合并命中与 Delta。
 
 插件固定只读 `https://apollomusic-poc1.fde0.com/kb/terminology`。`apiUrl` 不再是运行时配置项，线上服务返回 `degraded` 也会按错误处理；插件不包含本地术语表或 P0 fallback。
 
@@ -18,7 +19,7 @@
 在 DeepSeek Harness 项目中安装：
 
 ```bash
-npm install @apollo-music/dsh-sidecar-terms
+npm install @apollo-music/dsh-sidecar-terms@0.1.5
 ```
 
 ## 配置
@@ -74,7 +75,7 @@ export APOLLO_TERMINOLOGY_READ_API_KEY='<READ_ONLY_API_KEY>'
 
 `auditReasoning: true` 只匹配每个 step 已提交的完整 reasoning block；流式 `reasoning-delta` 不参与匹配。thinking 原文只发送给 Resolver 做瞬时匹配，不会回注给模型。若部署边界不允许 thinking 离开 Harness 进程，可设为 `false`。
 
-该插件声明依赖 `agents`、`sessions` 与 `tools`；Cordis 会等相关服务存在后再加载。官方 Harness 目前仍处于 Developer Preview，本项目锁定并测试 `0.1.0-rc.8` 的公开 `Agent`、`session/event`、`tools/post-execute`、`agent/pre-step`、`agent/turn-stopping` 接口。
+该插件声明依赖 `agents`、`sessions` 与 `tools`；Cordis 会等相关服务存在后再加载。官方 Harness 目前仍处于 Developer Preview，本项目锁定并测试 `0.1.1-rc.2` 的公开 `Agent`、`session/event`、`tools/post-execute`、`agent/pre-step`、`agent/turn-stopping` 接口。包清单显式声明这一组接口的完整 DSH peer 闭包，避免依赖宿主包管理器自动补齐隐式 peer。
 
 配置线上只读凭据后验证：
 

package/dist/coordinator.d.ts

@@ -1,6 +1,13 @@
 import { type UserMessage } from "@deepseek-ai/dsh-llm";
 import { TerminologyApi } from "./api.js";
 import type { AgentPort, LoggerPort, PluginConfig, ResolveResponse } from "./types.js";
+/**
+ * Split one audited message for the resolver transport without changing the
+ * message that DSH sends to the model. Chunks preserve order and concatenate
+ * exactly to the original text; natural or serialized-JSON boundaries are
+ * preferred so a multi-word terminology match is not cut unnecessarily.
+ */
+export declare function splitResolverText(text: string): string[];
 interface AuditItem {
     eventSeq: number;
     source: string;

package/dist/coordinator.js

@@ -1,6 +1,62 @@
 import { createUserMessage } from "@deepseek-ai/dsh-llm";
 import { findCatalogMatches } from "./matcher.js";
 const PLUGIN_NAME = "apollo-terminology-rules";
+const RESOLVER_TEXT_TARGET_CHARS = 90_000;
+const NATURAL_TEXT_BOUNDARIES = [
+    { needle: "\n\n", offset: 2 },
+    { needle: "\n", offset: 1 },
+    { needle: "},{\"", offset: 2 },
+    { needle: "\",\"", offset: 2 },
+    { needle: "。", offset: 1 },
+    { needle: "！", offset: 1 },
+    { needle: "？", offset: 1 },
+    { needle: ". ", offset: 2 },
+    { needle: "! ", offset: 2 },
+    { needle: "? ", offset: 2 },
+    { needle: "; ", offset: 2 },
+    { needle: "；", offset: 1 },
+    { needle: " ", offset: 1 },
+];
+/**
+ * Split one audited message for the resolver transport without changing the
+ * message that DSH sends to the model. Chunks preserve order and concatenate
+ * exactly to the original text; natural or serialized-JSON boundaries are
+ * preferred so a multi-word terminology match is not cut unnecessarily.
+ */
+export function splitResolverText(text) {
+    if (text.length <= RESOLVER_TEXT_TARGET_CHARS)
+        return [text];
+    const chunks = [];
+    let start = 0;
+    while (start < text.length) {
+        const targetEnd = Math.min(start + RESOLVER_TEXT_TARGET_CHARS, text.length);
+        if (targetEnd === text.length) {
+            chunks.push(text.slice(start));
+            break;
+        }
+        const preferredStart = start + Math.floor(RESOLVER_TEXT_TARGET_CHARS * 0.75);
+        let end = 0;
+        for (const boundary of NATURAL_TEXT_BOUNDARIES) {
+            const index = text.lastIndexOf(boundary.needle, targetEnd - boundary.needle.length);
+            const candidate = index + boundary.offset;
+            if (index >= preferredStart && candidate > end)
+                end = candidate;
+        }
+        if (end <= start)
+            end = targetEnd;
+        // JavaScript string limits are measured in UTF-16 code units. Avoid
+        // placing a transport boundary between the halves of a surrogate pair.
+        const before = text.charCodeAt(end - 1);
+        const after = text.charCodeAt(end);
+        if (before >= 0xD800 && before <= 0xDBFF
+            && after >= 0xDC00 && after <= 0xDFFF) {
+            end -= 1;
+        }
+        chunks.push(text.slice(start, end));
+        start = end;
+    }
+    return chunks;
+}
 export class TerminologyCoordinator {
     config;
     api;
@@ -165,6 +221,7 @@ export class TerminologyCoordinator {
     async queryOnce(agent, state, mode, captured) {
         const segments = [...state.pendingSegments.values()].sort((a, b) => a.event_seq - b.event_seq);
         const throughSeq = segments.at(-1).event_seq;
+        const resolverSegments = segments.flatMap(({ event_seq, source, text }) => splitResolverText(text).map((chunk) => ({ event_seq, source, text: chunk })));
         for (const segment of segments)
             state.pendingSegments.delete(segment.event_seq);
         state.lastQueryAt = Date.now();
@@ -172,7 +229,7 @@ export class TerminologyCoordinator {
             const response = await this.api.resolve({
                 session_id: agent.id,
                 audit_through_seq: throughSeq,
-                segments: segments.map(({ event_seq, source, text }) => ({ event_seq, source, text })),
+                segments: resolverSegments,
                 candidate_terms: [...new Set(segments.flatMap((segment) => segment.candidates ?? []))],
                 delivered_rule_ids: this.knownRuleIds(state),
                 delivered_term_ids: this.knownTermIds(state),

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@apollo-music/dsh-sidecar-terms",
-  "version": "0.1.3",
+  "version": "0.1.5",
   "description": "DeepSeek Harness sidecar plugin for incremental Apollo terminology and rule injection",
   "type": "module",
   "main": "dist/index.js",
@@ -41,10 +41,19 @@
   },
   "peerDependencies": {
     "@deepseek-ai/cordis": "^4.0.1",
-    "@deepseek-ai/dsh-agent": "^0.1.0-rc.8",
-    "@deepseek-ai/dsh-llm": "^0.1.0-rc.8",
-    "@deepseek-ai/dsh-session": "^0.1.0-rc.8",
-    "@deepseek-ai/dsh-tools": "0.1.0-rc.8",
+    "@deepseek-ai/dsh-agent": "0.1.1-rc.2",
+    "@deepseek-ai/dsh-attachment": "0.1.1-rc.2",
+    "@deepseek-ai/dsh-brand": "0.1.1-rc.2",
+    "@deepseek-ai/dsh-code-runtime": "0.1.1-rc.2",
+    "@deepseek-ai/dsh-invariants": "0.1.1-rc.2",
+    "@deepseek-ai/dsh-llm": "0.1.1-rc.2",
+    "@deepseek-ai/dsh-scope": "0.1.1-rc.2",
+    "@deepseek-ai/dsh-session": "0.1.1-rc.2",
+    "@deepseek-ai/dsh-system-prompt": "0.1.1-rc.2",
+    "@deepseek-ai/dsh-timeout": "0.1.1-rc.2",
+    "@deepseek-ai/dsh-tools": "0.1.1-rc.2",
+    "@deepseek-ai/dsh-typert-protocol": "0.1.1-rc.2",
+    "@deepseek-ai/dsh-user-approval": "0.1.1-rc.2",
     "@deepseek-ai/schemastery": "^3.18.1"
   }
 }