dsh-xdpool 2.4.6 → 2.5.1

package/package.json

@@ -2,7 +2,7 @@
   "name": "dsh-xdpool",
   "displayName": "DSH XD Pool",
   "description": "One DSH model pool for every free quota you have: merge all locally signed-in WorkBuddy accounts with auto-failover, sign in to 13 vendors by QR/web, aggregate 76 vendors' free tiers, plus a usage dashboard, model routing, a local OpenAI-compatible gateway and a points-automation suite.",
-  "version": "2.4.6",
+  "version": "2.5.1",
   "license": "MIT",
   "author": "XDTrees",
   "homepage": "https://github.com/XDTrees/dsh-xdpool#readme",
@@ -75,9 +75,6 @@
       "platform": "web"
     }
   },
-  "optionalDependencies": {
-    "billion-context": "^0.1.197"
-  },
   "devDependencies": {
     "@deepseek-ai/cordis": "4.0.2",
     "@deepseek-ai/dsh-client-locale": "0.1.5-rc.2",

package/vendor/channel-pack/pack.js

@@ -32970,6 +32970,13 @@ var DsmlContentExtractor = class {
     return { text: remaining, reasoning: "" };
   }
 };
+// CodeArts rejects an oversized max_tokens with an HTTP-200 SSE error frame
+// (`InferHub.4001.200 The request param is invalid`) rather than a 4xx, so it
+// surfaces to the user as an opaque INVALID_REQUEST. 65536 is the measured
+// ceiling; 131072 already produces an empty stream. Keep the advertised default
+// and the final wire request on that same ceiling - TRAE and Cline do the same
+// with clampTraeMaxTokens / clampClineMaxTokens.
+var CODEARTS_MAX_OUTPUT_TOKENS = 65536;
 var CodeArtsAdapter = class extends LlmAdapter {
   constructor(options) {
     super();
@@ -33043,6 +33050,7 @@ var CodeArtsAdapter = class extends LlmAdapter {
         id: m.id,
         name: m.name,
         inputModalities: modalitiesFor(m.id),
+        maxTokens: CODEARTS_MAX_OUTPUT_TOKENS,
         ...contextWindow === void 0 ? {} : { contextWindow }
       };
     });
@@ -33052,7 +33060,15 @@ var CodeArtsAdapter = class extends LlmAdapter {
     const remoteModel = this.remoteModels?.find((m) => m.id === model);
     const name2 = remoteModel?.name ?? model;
     const contextWindow = contextWindowFor(model);
-    const resolved = { provider, id: model, name: name2, inputModalities: modalitiesFor(model) };
+    const resolved = {
+      provider,
+      id: model,
+      name: name2,
+      inputModalities: modalitiesFor(model),
+      // catalogFactsFor() forwards this as fact.maxTokens; without it the host
+      // has no way to learn the ceiling and passes its own catalog value through.
+      defaultMaxTokens: CODEARTS_MAX_OUTPUT_TOKENS
+    };
     if (contextWindow !== void 0) resolved.context = { contextWindow };
     resolved.reasoning = {
       efforts: [
@@ -33134,9 +33150,11 @@ var CodeArtsAdapter = class extends LlmAdapter {
       // 大文件 write 工具参数（如 1000-2000+ 行文档）需要数万 token 的生成空间，
       // 若沿用后端默认输出上限，参数 JSON 会在中途被截断成非法 JSON，harness
       // 工具校验报 `invalid arguments: "arguments" must be an object`。
-      // 参考实现 e2e 实测：65536 可用，131072 反而触发空流被后端拒绝；
-      // 显式传入的 options.maxTokens 优先，未设置时默认 65536。
-      max_tokens: options.maxTokens ?? 65536,
+      // 参考实现 e2e 实测：65536 可用，131072 反而触发空流被后端拒绝。
+      // 因此这是上限而不只是默认值：调用方传来的更大值（宿主模型目录里别的
+      // provider 带 384000）会被原样发出并触发 INVALID_REQUEST，必须收回；
+      // 调用方主动设的较小值保留。
+      max_tokens: Math.min(options.maxTokens ?? CODEARTS_MAX_OUTPUT_TOKENS, CODEARTS_MAX_OUTPUT_TOKENS),
       ...wireTools !== void 0 && wireTools.length > 0 ? { tools: wireTools } : {}
     });
     const url = `${CHAT_API_BASE}/chat/completions`;
@@ -35326,9 +35344,13 @@ var BuddyAdapter = class _BuddyAdapter extends LlmAdapter2 {
     // pair (measured on a live account 2026-10-21; the pool's own copy of this
     // list is BANNED_SYSTEM_PHRASES in src/upstream.ts). Runs AFTER the prepend
     // above, because that is where the host's system text lands.
+    // The third entry is the file-reference guidance DSH adds whenever the
+    // agent has a `read` tool: the "Relative paths…" half is the substring the
+    // gateway lists, and the sentence names no product, so it is rewritten for
+    // its text rather than for claiming another client (measured 2026-10-28).
     for (const message of messages) {
       if ((message.role === "system" || message.role === "assistant") && typeof message.content === "string") {
-        message.content = message.content.replace(/powered by DeepSeek Harness/gi, "running on DeepSeek Harness").replace(/DeepSeek Harness Web GUI/gi, "DeepSeek Harness web interface");
+        message.content = message.content.replace(/powered by DeepSeek Harness/gi, "running on DeepSeek Harness").replace(/DeepSeek Harness Web GUI/gi, "DeepSeek Harness web interface").replace(/Relative paths resolve from the workspace root/gi, "Relative paths are resolved against the workspace root");
       }
     }
     const tools = options.tools?.map((tool) => ({