dsh-connect-trae 2.0.2 → 2.0.4

package/CHANGELOG.md

@@ -1,5 +1,29 @@
 # Changelog
 
+## 2.0.4 (2026-09-16)
+
+### Fixes
+
+- **修复「某个区域没有实时模型目录时，该区域的 provider 整个加载失败」**（issue #8：未安装国际版的用户看到 `Trae Global 加载失败：adapter returned invalid context metadata for provider "trae-global" model "gemini-3.1-pro"`）：
+  - **根因**：两个区域的内置兜底目录里，每个模型都缺少 `contextWindow`。DSH 要求它必须是正整数（`INVALID_MODEL_CONTEXT`），而 `dsh-llm-pi-ai` 的回退链是 `entry.contextWindow → 已安装 catalog → request.defaultContextWindow`——本插件既没传 `defaultContextWindow`，兜底模型也不在已安装 catalog 里，三条全空，于是校验失败。
+  - **失败粒度是 provider 级**：不是丢单个模型，而是**整个区域不可用**。触发场景包括未安装该区客户端、未登录、目录拉取失败（该端点有已知的间歇性 401）、以及首次安装尚未刷新过目录。因此这不是「没装国际版拖累国内版」，而是**两个区域各自独立地有这个缺陷**。
+  - **修复**：(1) 兜底目录补上实测 `contextWindow`——国际版依据 2026-09-15 实测目录（`gemini-3.1-pro`/`gemini-3-flash-solo`/`minimax-m3`/`minimax-m2.7`/`kimi-k2.5` = 200000，`gpt-5.4`/`gpt-5.2` = 272000），国内版依据 SOLO 通道实测（200000）；(2) adapter 传 `defaultContextWindow` 作为最终防线，将来任何来源的条目不慎缺字段时降级为「一个保守尺寸的模型」而非「整区不可用」。
+  - 新增不变量测试：**两个区域的兜底行都必须带正整数 `contextWindow`**。原先有一条测试断言「兜底条目没有 `contextWindow`」——它固化的正是这个 bug，已改正。
+
+## 2.0.3 (2026-09-16)
+
+### Fixes
+
+- **修复内置兜底目录里存在「不可调用模型」的问题**——插件在首次实时刷新落地前会先提供一份内置兜底模型列表，且这份列表**故意不经过「死 config_name」过滤**（过滤依赖实时目录，会把兜底本身误删）。因此它的 id 必须在源头就是正确的 `llm_utils_chat` config_name，而它此前不是：
+  - `auto` 不是任何 Trae 的 config_name，选中后会以 `4001` 失败——已移除。该条目会在「尚未刷新目录」时（未登录 / 网络抖动 / 卡片未刷新）被真正提供给用户，因此并非理论问题。
+  - `DeepSeek-V4-Flash` / `DeepSeek-V4-Pro` 缺少 `-Official` 后缀，不是真实 wire id——已更正为 `DeepSeek-V4-Flash-Official` / `DeepSeek-V4-Pro-Official`（依据 2026-09-15 实测目录，`docs/DS41_CALLABILITY.md`）。
+  - 新增回归测试锁定三条不变量：兜底 id 必须是真实 config_name（显式禁 `auto` 与裸名）、两个区域的兜底都不得出现 TraeCode 独占模型、`mergeTraeModelSources` 确实丢弃无 wire 匹配的目录行。
+
+### Docs
+
+- **README 新增「模型覆盖范围」一节（中英同步）**——说明插件提供的是 Trae SOLO 通道的模型，而 TraeCode 通道的 4 个模型（`deepseek-v4.1-flash`、`glm-5.3-flash`、`kimi-k2.8-preview`、`qwen3.8-flash`）尚未开放到 SOLO 通道，因此暂不支持，**需要等官方开放到 SOLO 后才能支持**；并区分了 `GLM-5.3`（支持）与 `glm-5.3-flash`（不支持）。
+- 新增 TraeCode / agent-task 通道与 TraeCLI 的可行性取证（`docs/CODEC_CHANNEL_FEASIBILITY.md`、`docs/TRAECLI_FEASIBILITY.md`、`docs/TRAE_ECOSYSTEM_RESEARCH.md`）：四条路径逐一实测均不通，且阻塞原因互相独立（协议 / 配额 / 同机 / 登录态与 agent 归属），据此确认这批模型属上游授权边界而非插件可绕过的技术问题。
+
 ## 2.0.2 (2026-09-15)
 
 ### Fixes

package/README.en.md

@@ -10,6 +10,7 @@
   <a href="README.md">中文</a> ·
   <a href="#install">Install</a> ·
   <a href="#how-it-works">How it works</a> ·
+  <a href="#model-coverage">Model coverage</a> ·
   <a href="CHANGELOG.md">Changelog</a> ·
   <a href="https://github.com/dingminhua/dsh-connect-trae/issues">Issues</a>
 </p>
@@ -56,6 +57,25 @@ Usage overview hits the read-only `https://api.trae.cn/trae/api/v2/pay/*` and `/
 
 > See `docs/IMPLEMENTATION_PLAN.md`, `docs/SOLO_ROUTE_DECISION.md`, `docs/USAGE_API_RESEARCH.md`.
 
+## Model coverage
+
+This plugin serves models from Trae's **SOLO channel** (`DeepSeek-V4-Flash-Official`, `DeepSeek-V4-Pro-Official`, `GLM-5.3`, `GLM-5.2`, `Kimi-K3`, `MiniMax-M3`, `Qwen3.8-Max`, `Doubao-Seed-*`, …), for both the domestic and international sides.
+
+The following four models currently come from the **TraeCode (Trae IDE) channel** and have **not** been opened up to the SOLO channel, so this plugin does **not** support them yet:
+
+| Model |
+| --- |
+| `deepseek-v4.1-flash` |
+| `glm-5.3-flash` |
+| `kimi-k2.8-preview` |
+| `qwen3.8-flash` |
+
+These four are reachable only inside the Trae IDE client; there is no callable channel for them on the plugin side. **They can only be supported once Trae officially opens them up to the SOLO channel.**
+
+> Note the distinction: **`GLM-5.3` is supported** (it goes through the SOLO channel), but **`glm-5.3-flash` is not** — they are different models.
+
+To use these four models today, use the **Trae IDE itself**.
+
 ## Install
 
 ```sh

package/README.md

@@ -10,6 +10,7 @@
   <a href="README.en.md">English</a> ·
   <a href="#安装">安装</a> ·
   <a href="#工作原理">工作原理</a> ·
+  <a href="#模型覆盖范围">模型覆盖范围</a> ·
   <a href="CHANGELOG.md">更新日志</a> ·
   <a href="https://github.com/dingminhua/dsh-connect-trae/issues">问题反馈</a>
 </p>
@@ -56,6 +57,25 @@ DSH PiAiAdapter（每个 provider 一套）
 
 > 详见 `docs/IMPLEMENTATION_PLAN.md`、`docs/SOLO_ROUTE_DECISION.md`、`docs/USAGE_API_RESEARCH.md`。
 
+## 模型覆盖范围
+
+插件提供的是 Trae **SOLO 通道**的模型（`DeepSeek-V4-Flash-Official`、`DeepSeek-V4-Pro-Official`、`GLM-5.3`、`GLM-5.2`、`Kimi-K3`、`MiniMax-M3`、`Qwen3.8-Max`、`Doubao-Seed-*` 等），国内版与国际版均走这条通道。
+
+以下 4 个模型目前来自 **TraeCode（Trae IDE）通道**，尚未开放到 SOLO 通道，因此本插件**暂不支持**：
+
+| 模型 |
+| --- |
+| `deepseek-v4.1-flash` |
+| `glm-5.3-flash` |
+| `kimi-k2.8-preview` |
+| `qwen3.8-flash` |
+
+这 4 个模型只在 Trae IDE 客户端内可用，插件侧没有可调用的通道。**需要等官方把它们开放到 SOLO 通道后，插件才能支持。**
+
+> 注意区分：**`GLM-5.3` 是支持的**（走 SOLO 通道），但 **`glm-5.3-flash` 不支持**——两者是不同的模型。
+
+如果你现在就要用这 4 个模型，请直接在 **Trae IDE 本体**中使用。
+
 ## 安装
 
 推荐使用 DSH 插件命令安装 npm 已发布版本：

package/lib/index.d.ts

@@ -112,7 +112,29 @@ interface TraeModelInfo {
   /** The directory function this model must be called through (see {@link TraeWireModel.function}). */
   wireFunction?: string;
 }
-/** Bootstrap catalog: identity only where current Trae metadata has not been fetched yet. */
+/**
+ * Bootstrap catalog: identity only where current Trae metadata has not been
+ * fetched yet.
+ *
+ * Every id here must be a `config_name` that `llm_utils_chat` actually accepts,
+ * because this list is served verbatim before the first live refresh lands and
+ * it is NOT filtered against the wire map (the wire map can only confirm ids it
+ * happens to know, so filtering would delete the safety net exactly when it is
+ * needed — see `fallbackModels` in index.ts). The current CN roster was
+ * verified against the live remote directory on 2026-09-15
+ * (docs/DS41_CALLABILITY.md): `DeepSeek-V4-Flash-Official` and
+ * `DeepSeek-V4-Pro-Official` carry the `-Official` suffix, and there is no
+ * `auto` config_name — an `auto` row was previously served here and would have
+ * failed on selection.
+ *
+ * Every row MUST also carry a positive-integer `contextWindow`. DSH rejects an
+ * adapter whose model has no usable context (`INVALID_MODEL_CONTEXT`), and that
+ * failure is per-provider — one bad row takes the whole region offline. These
+ * rows are exactly the ones served when no live directory is available (no
+ * install for that region, signed out, or a failed refresh), which is precisely
+ * when the fallback is doing its job, so a missing field here is fatal rather
+ * than cosmetic. See docs/ISSUE8_DIAGNOSIS.md.
+ */
 declare const FALLBACK_TRAE_MODELS: readonly TraeModelInfo[];
 /**
  * Bootstrap catalog for the international (ai) region, captured from the
@@ -121,6 +143,10 @@ declare const FALLBACK_TRAE_MODELS: readonly TraeModelInfo[];
  * has no Gemini/GPT/MiniMax entries), so an international account must never
  * be seeded with the CN list. Like the CN fallback it is replaced by the live
  * refresh; image input stays the user's explicit opt-in (`imageModelIds`).
+ *
+ * The `contextWindow` values are the measured ones from that same capture
+ * (`docs/INTL_SG_EVIDENCE.md` §3) and are required for the same reason as the
+ * CN fallback: without them the whole `trae-global` provider fails to load.
  */
 declare const FALLBACK_TRAE_MODELS_AI: readonly TraeModelInfo[];
 /**
@@ -174,8 +200,8 @@ interface TraeWireModel {
  *
  * Joining is two-tier, in priority order:
  *  1. `wire.id` (the `config_name`) equals the remote id — the model's display
- *     id is already its wire id (the common case: glm-5.2, DeepSeek-V4-Flash,
- *     kimi-k3, …).
+ *     id is already its wire id (the common case: glm-5.2,
+ *     DeepSeek-V4-Flash-Official, kimi-k3, …).
  *  2. `wire.name` (the `display_name`) equals the remote display name — for
  *     models whose display id differs from the wire id across Trae versions.
  * When the matched wire `config_name` differs from the remote id it is recorded

package/lib/index.js

@@ -15,27 +15,49 @@ import { Readable } from "node:stream";
 import { execFile } from "node:child_process";
 import { promisify } from "node:util";
 //#region src/catalog.ts
-/** Bootstrap catalog: identity only where current Trae metadata has not been fetched yet. */
+/**
+* Bootstrap catalog: identity only where current Trae metadata has not been
+* fetched yet.
+*
+* Every id here must be a `config_name` that `llm_utils_chat` actually accepts,
+* because this list is served verbatim before the first live refresh lands and
+* it is NOT filtered against the wire map (the wire map can only confirm ids it
+* happens to know, so filtering would delete the safety net exactly when it is
+* needed — see `fallbackModels` in index.ts). The current CN roster was
+* verified against the live remote directory on 2026-09-15
+* (docs/DS41_CALLABILITY.md): `DeepSeek-V4-Flash-Official` and
+* `DeepSeek-V4-Pro-Official` carry the `-Official` suffix, and there is no
+* `auto` config_name — an `auto` row was previously served here and would have
+* failed on selection.
+*
+* Every row MUST also carry a positive-integer `contextWindow`. DSH rejects an
+* adapter whose model has no usable context (`INVALID_MODEL_CONTEXT`), and that
+* failure is per-provider — one bad row takes the whole region offline. These
+* rows are exactly the ones served when no live directory is available (no
+* install for that region, signed out, or a failed refresh), which is precisely
+* when the fallback is doing its job, so a missing field here is fatal rather
+* than cosmetic. See docs/ISSUE8_DIAGNOSIS.md.
+*/
 const FALLBACK_TRAE_MODELS = [
 	{
-		id: "auto",
-		name: "Auto"
+		id: "DeepSeek-V4-Flash-Official",
+		name: "DeepSeek-V4-Flash",
+		contextWindow: 2e5
 	},
 	{
-		id: "DeepSeek-V4-Flash",
-		name: "DeepSeek-V4-Flash"
-	},
-	{
-		id: "DeepSeek-V4-Pro",
-		name: "DeepSeek-V4-Pro"
+		id: "DeepSeek-V4-Pro-Official",
+		name: "DeepSeek-V4-Pro",
+		contextWindow: 2e5
 	},
 	{
 		id: "glm-5.2",
-		name: "GLM-5.2"
+		name: "GLM-5.2",
+		contextWindow: 2e5
 	},
 	{
 		id: "kimi-k2.6",
-		name: "Kimi-K2.6"
+		name: "Kimi-K2.6",
+		contextWindow: 2e5
 	}
 ];
 /**
@@ -45,35 +67,46 @@ const FALLBACK_TRAE_MODELS = [
 * has no Gemini/GPT/MiniMax entries), so an international account must never
 * be seeded with the CN list. Like the CN fallback it is replaced by the live
 * refresh; image input stays the user's explicit opt-in (`imageModelIds`).
+*
+* The `contextWindow` values are the measured ones from that same capture
+* (`docs/INTL_SG_EVIDENCE.md` §3) and are required for the same reason as the
+* CN fallback: without them the whole `trae-global` provider fails to load.
 */
 const FALLBACK_TRAE_MODELS_AI = [
 	{
 		id: "gemini-3.1-pro",
-		name: "Gemini-3.1-Pro-Preview"
+		name: "Gemini-3.1-Pro-Preview",
+		contextWindow: 2e5
 	},
 	{
 		id: "gemini-3-flash-solo",
-		name: "Gemini-3-Flash-Preview"
+		name: "Gemini-3-Flash-Preview",
+		contextWindow: 2e5
 	},
 	{
 		id: "minimax-m3",
-		name: "MiniMax-M3"
+		name: "MiniMax-M3",
+		contextWindow: 2e5
 	},
 	{
 		id: "minimax-m2.7",
-		name: "MiniMax-M2.7"
+		name: "MiniMax-M2.7",
+		contextWindow: 2e5
 	},
 	{
 		id: "kimi-k2.5",
-		name: "Kimi-K2.5"
+		name: "Kimi-K2.5",
+		contextWindow: 2e5
 	},
 	{
 		id: "gpt-5.4",
-		name: "GPT-5.4"
+		name: "GPT-5.4",
+		contextWindow: 272e3
 	},
 	{
 		id: "gpt-5.2",
-		name: "GPT-5.2"
+		name: "GPT-5.2",
+		contextWindow: 272e3
 	}
 ];
 /**
@@ -126,8 +159,8 @@ function displayKey(name) {
 *
 * Joining is two-tier, in priority order:
 *  1. `wire.id` (the `config_name`) equals the remote id — the model's display
-*     id is already its wire id (the common case: glm-5.2, DeepSeek-V4-Flash,
-*     kimi-k3, …).
+*     id is already its wire id (the common case: glm-5.2,
+*     DeepSeek-V4-Flash-Official, kimi-k3, …).
 *  2. `wire.name` (the `display_name`) equals the remote display name — for
 *     models whose display id differs from the wire id across Trae versions.
 * When the matched wire `config_name` differs from the remote id it is recorded
@@ -282,6 +315,13 @@ const REQUEST_IMAGE_BUDGETS = {
 	requestImagePixelBudget: 4194304,
 	requestImageMaxBytes: 1048576
 };
+/**
+* Conservative context capacity used only when a served model row carries no
+* window of its own. Every fallback row and every live Trae row is expected to
+* state its real window; this is the backstop that keeps one unsized row from
+* failing the entire provider route (`INVALID_MODEL_CONTEXT`).
+*/
+const FALLBACK_CONTEXT_WINDOW = 2e5;
 function toPiModel(info, baseUrl, providerId) {
 	return {
 		id: info.id,
@@ -341,6 +381,7 @@ function createTraeAdapter(options) {
 		retryPolicy: resolveRetryPolicy(void 0, "dsh-connect-trae retryPolicy"),
 		configuredMaxTokens: /* @__PURE__ */ new Map(),
 		modelErrors: /* @__PURE__ */ new Map(),
+		defaultContextWindow: FALLBACK_CONTEXT_WINDOW,
 		...REQUEST_IMAGE_BUDGETS,
 		piProvider: provider
 	};

package/package.json

@@ -2,7 +2,7 @@
   "name": "dsh-connect-trae",
   "displayName": "DSH Connect Trae",
   "description": "Connect locally signed-in Trae models to DeepSeek Harness, plus a read-only usage/credits summary.",
-  "version": "2.0.2",
+  "version": "2.0.4",
   "author": "dingminhua",
   "copyright": "Copyright (c) 2026 LaoDing",
   "license": "MIT",