dsh-gateway-provider 1.0.1 → 1.0.3

package/README.md

@@ -50,14 +50,13 @@ re-deploy.
 1. Install the plugin into your profile (published on npm):
 
    ```bash
-   dsh plugin --profile web add dsh-gateway-provider
+   dsh plugin --profile web add dsh-gateway-provider          # latest
+   dsh plugin --profile web add dsh-gateway-provider@<version>  # pinned
    ```
 
-   `dsh plugin add` forwards to `pnpm add` in the profile directory, so any
-   pnpm spec works — e.g. pin a GitHub release with
-   `git+https://github.com/Luck9Star/dsh-gateway-provider.git#v1.0.1` (omit
-   the suffix to track main). The bundle patch (`cordis.patch.yml`) then
-   mounts the `llm-newapi` loader row automatically — no manual patch editing.
+   `dsh plugin add` forwards to `pnpm add` in the profile directory.
+   The bundle patch (`cordis.patch.yml`) then mounts the `llm-newapi`
+   loader row automatically — no manual patch editing.
 
 2. Store your gateway key in `$DSH_HOME/.credentials.yaml` (mode 0600,
    hot-reloaded):
@@ -126,6 +125,21 @@ The **Gateway Models** page exposes the same operations with a UI: search,
 hidden/custom filters with counts, a per-model override editor (placeholders
 show discovered values), connection test, and save/cancel semantics.
 
+> ⚠️ **Hand-editing YAML?** `settings.yaml` is parsed with YAML 1.2 core
+> semantics: an unquoted `true` / `false` (any casing) becomes a boolean and
+> an unquoted digit run becomes a number. Every plain string field of the
+> section (`id`, `name`, `label`, `baseURL`, `apiKeyEnv`, `modelsUrl`,
+> `userId`, `reasoningLevels` / `excludePatterns` / `endpointPriority`
+> entries, …) tolerates the coerced form, but the cleanest habit is quoting
+> intent-significant tokens — write `reasoningLevels: ["off", "low",
+> "high"]`, not `reasoningLevels: [off, low, high]` — and never `false`
+> where a level name is meant (it survives as the junk level `"false"` and
+> is silently dropped from the picker). A structurally invalid section
+> (objects where strings belong, etc.) is refused at registration: the
+> namespace stays unregistered and every settings write from the web UI
+> then answers `settings-rejected: settings namespace "llm-newapi" is not
+> registered`.
+
 ## Configuration reference
 
 Section `llm-newapi:` of `$DSH_HOME/settings.yaml`. The flat fields
@@ -152,6 +166,7 @@ the `gateways` array support most of the same fields per gateway
 | `excludePatterns` | image/speech/embed/… | Regex patterns excluding models from the picker |
 | `endpointPriority` | `["openai-response","anthropic","openai","gemini"]` | Wire-format preference order (first match wins per model) |
 | `userId` | `1` | `New-Api-User` header for the management API |
+| `headers` | – | Extra HTTP headers (name → value) sent with every provider request; attribution headers (`user-agent`) are filtered out |
 | `maxTokens` | `32768` | Output cap fallback when models.dev lacks data |
 | `defaultContextWindow` | `128000` | Context window fallback when models.dev lacks data |
 | `streamIdleTimeoutMs` | `300000` | Stream idle watchdog |

package/docs/README.zh.md

@@ -0,0 +1,230 @@
+# dsh-gateway-provider
+
+[![gitleaks](https://github.com/Luck9Star/dsh-gateway-provider/actions/workflows/gitleaks.yml/badge.svg)](https://github.com/Luck9Star/dsh-gateway-provider/actions/workflows/gitleaks.yml)
+
+> English: [README.md](../README.md)
+
+把任意 LLM 网关 —— **newapi、LiteLLM、Higress 或任何 OpenAI 兼容端点** —— 接入
+DeepSeek Harness。插件自动发现网关的模型列表，用 [models.dev](https://models.dev)
+的真实参数补齐每个模型，并通过 pi-ai SDK 以模型原生协议（OpenAI / Anthropic /
+Gemini）分发请求。
+
+## 为什么需要它
+
+DeepSeek Harness 自带的适配器（`llm-deepseek`、`llm-pi-ai`）各自只服务一个官方
+provider。如果你的模型都在网关后面，就得手工维护一份静态模型清单，上下文窗口、
+输出上限全靠猜。
+
+本插件直接把网关挂进来：**N 个网关 = N 个 provider 路由，零静态清单。** 每个模型
+带着真实参数，网关侧加模型即可生效——无需重新部署。
+
+## 你能得到什么
+
+- **多网关** — 默认 `newapi` 路由 + 每个额外网关一条 `gateway:<id>` 路由，
+  各自独立 catalog 缓存。
+- **自动发现** — 首选 `GET {base}/v1/models`（含每个模型支持的请求格式），
+  管理 API 兜底。
+- **真实参数** — models.dev 补齐上下文窗口、输出上限、推理等级、发布日期；
+  配置默认值只是兜底。
+- **全协议覆盖** — 每个模型路由到自己的协议（`openai-completions` /
+  `openai-responses` / `anthropic-messages` / `google-generative-ai`），
+  无手写 SSE、无手写请求序列化。
+- **图形设置页** — **设置 → 网关模型**：按模板添加/编辑网关、测试连接、
+  隐藏/覆写/自定义添加模型——不用碰 YAML。
+- **干净的选择器** — 按发布日期新到旧排序、只保留对话模型、正则剔除。
+
+## 环境要求
+
+- 装有 profile 的 DeepSeek Harness（`dsh`）
+- 一个可达网关：newapi / LiteLLM / Higress / 任意 OpenAI 兼容端点
+- 该网关的 API Key
+
+## 快速开始
+
+1. 把插件装进 profile（已发布到 npm）：
+
+   ```bash
+   dsh plugin --profile web add dsh-gateway-provider          # 最新版
+   dsh plugin --profile web add dsh-gateway-provider@<version>  # 钉住版本
+   ```
+
+   `dsh plugin add` 会在 profile 目录里转发执行 `pnpm add`。bundle 补丁
+   （`cordis.patch.yml`）随后自动挂载 `llm-newapi` 加载行——无需手工改 patch。
+
+2. 把网关 key 写入 `$DSH_HOME/.credentials.yaml`（权限 0600，热加载）：
+
+   ```yaml
+   NEWAPI_API_KEY: sk-REPLACE_WITH_YOUR_KEY
+   ```
+
+   或在启动环境中导出 `NEWAPI_API_KEY`。
+
+3. 重启 profile，打开 **设置 → 网关模型**。
+
+**成功的样子：** 网关出现并带"已同步 N 个模型"徽标，全部对话模型可选、
+上下文窗口是真实值。基础地址解析顺序：`llm-newapi.baseURL` 设置 →
+`NEWAPI_BASE_URL` / `NEWAPI_API_URL` 环境变量 → 公共默认
+`https://api.newapi.ai`。
+
+## 添加更多网关
+
+额外网关写在 `gateways` 数组——每个成为独立的 `gateway:<id>` provider 路由：
+
+```yaml
+llm-newapi:
+  baseURL: https://your-newapi-instance.com
+  gateways:
+    - id: litellm-prod
+      label: LiteLLM 生产
+      baseURL: https://litellm.example.com
+      apiKeyEnv: LITELLM_API_KEY
+      flavor: litellm            # 表单模板：newapi / litellm / higress / openai-compatible / custom
+
+    # 完全自定义网关：各协议写完整端点地址，不共享基础地址；
+    # 留空的协议不启用。
+    - id: edge
+      label: 边缘网关
+      flavor: custom
+      openaiURL: https://edge.example.com/openai/v1/chat/completions
+      responsesURL: https://edge.example.com/openai/v1/responses
+      anthropicURL: https://edge.example.com/anthropic/v1/messages
+      apiKeyEnv: EDGE_API_KEY
+```
+
+也可以在设置页里用同样的模板添加网关，不必编辑 YAML。
+
+## 按网关控制模型清单
+
+隐藏模型、修正错误元数据、添加网关未列出的模型：
+
+```yaml
+llm-newapi:
+  models:
+    - id: glm-5.2
+      disabled: true              # 从选择器隐藏
+    - id: glm-5.2-highspeed
+      contextWindow: 1000000      # 覆盖发现值
+      protocol: openai            # 强制协议（openai/anthropic/gemini/openai-response）
+    - id: my-internal-model       # 自定义模型（网关未列出）
+      name: 我的内测模型
+      contextWindow: 200000
+```
+
+**网关模型**设置页提供同样的操作：搜索、带计数的已隐藏/自定义筛选、逐模型覆写
+编辑器（placeholder 显示发现值）、连接测试、保存/取消语义。
+
+> ⚠️ **手工编辑 YAML？** `settings.yaml` 按 YAML 1.2 core 语义解析：不带引号的
+> `true` / `false`（任意大小写）会变成布尔值，不带引号的数字串会变成数值。本节
+> 所有纯字符串字段（`id`、`name`、`label`、`baseURL`、`apiKeyEnv`、`modelsUrl`、
+> `userId`，以及 `reasoningLevels` / `excludePatterns` / `endpointPriority` 的
+> 条目……）都可容忍这些被强转的形式，但最稳妥的习惯是给有含义的 token 加引号
+> ——写 `reasoningLevels: ["off", "low", "high"]`，而不是
+> `reasoningLevels: [off, low, high]`——更不要在该写级别名的地方写 `false`（它会
+> 以垃圾级别 `"false"` 存活，并被静默排除出选择器）。结构上非法的分节（比如字符
+> 串位置出现对象）会在注册时被拒绝：namespace 保持未注册状态，Web 设置页的每次
+> 写入都会得到
+> `settings-rejected: settings namespace "llm-newapi" is not registered`。
+
+## 配置参考
+
+`$DSH_HOME/settings.yaml` 的 `llm-newapi:` 节。扁平字段（`baseURL` /
+`apiKeyEnv` 等）构建默认 `newapi` 路由；`gateways` 数组里的每个网关支持
+大部分同名字段（`label` / `apiKeyEnv` / `flavor` / `catalogMode` /
+`endpointPriority` / …）。
+
+| 字段 | 默认 | 说明 |
+|------|------|------|
+| `label` | `NewAPI` | 默认网关路由的显示名 |
+| `apiKeyEnv` | `NEWAPI_API_KEY` | 凭据引用（环境变量名） |
+| `baseURL` | env `NEWAPI_BASE_URL` / `NEWAPI_API_URL` → `https://api.newapi.ai` | 网关地址（配置协议 URL 后不再使用） |
+| `flavor` | `newapi` | 网关模板：`newapi` / `litellm` / `higress` / `openai-compatible` / `custom` |
+| `openaiURL` | – | OpenAI 兼容完整端点地址（自定义模板；留空 = 不启用） |
+| `responsesURL` | – | Responses 完整端点地址（自定义模板；留空 = 不启用） |
+| `anthropicURL` | – | Anthropic messages 完整端点地址（自定义模板；留空 = 不启用） |
+| `modelsUrl` | `https://models.dev/models.json` | models.dev 数据源（`file:` URL 可离线） |
+| `useModelsDev` | `true` | 是否用 models.dev 参数增强模型 |
+| `extendedReasoningLevels` | `false` | 未知模型推理等级兜底放宽到 off~max（默认仅 off/low/medium/high） |
+| `sortModelsByRelease` | `true` | 选择器按发布日期新到旧排列（未知日期排最前） |
+| `catalogMode` | `auto` | 模型列表来源：`auto` / `v1` / `management` |
+| `catalogTtlMs` | `1800000` | 模型列表缓存时长 |
+| `includeChatOnly` | `true` | 仅把对话模型放进选择器 |
+| `excludePatterns` | image/speech/embed/… | 选择器剔除的正则列表 |
+| `endpointPriority` | `["openai-response","anthropic","openai","gemini"]` | wire 格式优先级（每模型取首个匹配） |
+| `userId` | `1` | 管理 API 的 `New-Api-User` 头 |
+| `headers` | – | 随每个 provider 请求附带的额外 HTTP 头（名称 → 值）；归属头（`user-agent`）会被过滤掉 |
+| `maxTokens` | `32768` | 无 models.dev 数据时的输出上限兜底 |
+| `defaultContextWindow` | `128000` | 无 models.dev 数据时的上下文兜底 |
+| `streamIdleTimeoutMs` | `300000` | 流空闲看门狗 |
+| `retryPolicy` | 标准重试 | 与 `llm-deepseek` 同构 |
+
+## 工作原理
+
+所有 wire 格式细节都委托给
+[`@earendil-works/pi-ai`](https://www.npmjs.com/package/@earendil-works/pi-ai)
+—— 官方 `dsh-llm-pi-ai` 适配器用的同一 SDK。每次请求：
+
+```
+harness GenerateOptions
+  → toPiContext()          lib/pi-bridge.js   harness 消息 → pi-ai Context
+  → models.streamSimple()  pi-ai SDK          按每个模型的 `api` 分发协议
+  → toStreamChunks()       lib/pi-bridge.js   pi-ai 事件 → harness chunk
+```
+
+每个发现的模型带一个 `api` 字段，由网关广告的 `supported_endpoint_types`
+映射而来，遵循 `endpointPriority`；pi-ai provider 收到的是 api *映射表*，
+所以每个模型路由到自己的协议实现。`sdkBaseURL()` 为 OpenAI 协议模型补
+`/v1`，Anthropic/Google 的基础地址保持不变。
+
+```
+dsh-gateway-provider/
+├── index.js            # 插件入口：Config 校验、provider 注册、设置/凭据接线
+├── cordis.patch.yml    # dsh.bundle 补丁（经 `dsh plugin add` 自动挂载）
+├── lib/                # adapter、pi-provider、pi-bridge、catalog、modelsdev、thinking、client
+├── test/               # 冒烟（直连网关）+ 离线单元 + 设置页渲染
+└── scripts/link.sh     # 本地检出时链接 profile 的 node_modules
+```
+
+## 从本地检出开发
+
+1. `bash scripts/link.sh` — 把本包 `node_modules` 软链到 profile 的，
+   保证 `@deepseek-ai/*` 裸导入解析到 harness 进程使用的同一份模块实例
+   （单实例 `instanceof` 安全）。
+2. 把检出注册为 profile 的 link 依赖并安装：
+
+   ```bash
+   cd "$DSH_HOME/profiles/web"
+   # package.json dependencies 追加："dsh-gateway-provider": "link:/本包绝对路径/dsh-gateway-provider"
+   # 再把 "dsh-gateway-provider" 加进同一文件的 bundles 列表
+   pnpm install
+   ```
+
+3. 重启 profile。
+
+> ⚠️ **不要**再往 profile 自己的 `cordis.patch.yml` 里插入 `id: llm-newapi`
+> ——bundle 层已挂载，重复会导致启动时报 `duplicate loader entry id`。
+
+客户端 bundle 改动刷新浏览器即生效；宿主侧改动需要重启 profile。
+
+### 测试
+
+```bash
+node test/smoke.mjs            # 直连网关：catalog / openai × 2 / 工具调用 / anthropic / gemini / custom-urls
+node test/smoke.mjs --only custom-urls
+node test/protocol-urls.mjs    # 离线：URL 派生 + 网关解析单元测试
+node test/client-render.mjs    # 离线：设置页渲染树（中/英）
+```
+
+冒烟测试凭据解析顺序：进程环境变量 → 插件目录 `.env` →
+`$NEWAPI_ENV_FILE`（另有一个作者本地遗留兜底路径）。
+
+## 安全说明
+
+- API Key 只经 `$DSH_HOME/.credentials.yaml`（0600）或环境变量解析，
+  绝不写入日志、配置或对话；凭据字段在 Web UI 中以掩码编辑。
+- 无运行时 `dependencies`；`peerDependencies` 复用 harness 已装的
+  `@deepseek-ai/*` 与 `@earendil-works/pi-ai`。提交在本地（pre-commit）
+  与 CI 双层接受 gitleaks 扫描把关。
+
+## License
+
+MIT

package/index.js

@@ -60,12 +60,30 @@ export const DEFAULT_MODELS_URL = "https://models.dev/models.json";
 const DEFAULT_STREAM_IDLE_TIMEOUT_MS = 600_000;
 const DEFAULT_CATALOG_TTL_MS = 30 * 60 * 1000;
 
+/**
+ * String field tolerant of hand-edited YAML scalars. `settings.yaml` is a
+ * user-editable document parsed with YAML 1.2 core semantics: an unquoted
+ * `true` / `false` / `True` / `FALSE` round-trips as a boolean and an
+ * unquoted digit run as a number, long before the value reaches a strict
+ * `z.string()` — and because the settings seam refuses to register a
+ * namespace whose stored section fails its schema, one such scalar anywhere
+ * in the section bricks the whole namespace (the web UI then reports every
+ * write as `settings-rejected: settings namespace "llm-newapi" is not
+ * registered`). Booleans and finite numbers coerce to their string form;
+ * anything else still fails loud with schemastery's own union diagnostic.
+ */
+const coercedString = () => z.union([
+  z.string(),
+  z.transform(z.boolean(), (value) => String(value)),
+  z.transform(z.number(), (value) => String(value)),
+]);
+
 /** Schema for one model-level override on a gateway (all fields optional). */
 const ModelOverrideSchema = z.object({
   /** Model id exactly as the gateway accepts it. */
-  id: z.string(),
+  id: coercedString().required(),
   /** Display name override. */
-  name: z.string(),
+  name: coercedString(),
   /** Hide this model from the picker. */
   disabled: z.boolean(),
   /** Force the wire protocol for this model (openai/anthropic/gemini/…). */
@@ -75,7 +93,7 @@ const ModelOverrideSchema = z.object({
   /** Override the output-token cap. */
   maxTokens: z.number().step(1).min(1),
   /** Reasoning level set (e.g. ["off","low","medium","high"]). */
-  reasoningLevels: z.array(z.string()),
+  reasoningLevels: z.array(coercedString()),
 });
 
 /** Gateway-type templates the settings UI offers (informational labels). */
@@ -88,49 +106,49 @@ const FLAVORS = ["newapi", "litellm", "higress", "openai-compatible", "custom"];
  */
 const GatewaySchema = z.object({
   /** Short stable id; becomes the provider route suffix (`gateway:<id>`). */
-  id: z.string().required(),
+  id: coercedString().required(),
   /** Human-readable gateway name. */
-  label: z.string(),
+  label: coercedString(),
   /** Gateway base URL (unused when protocol URL fields are set). */
-  baseURL: z.string(),
+  baseURL: coercedString(),
   /** Full chat-completions endpoint URL (custom template). */
-  openaiURL: z.string(),
+  openaiURL: coercedString(),
   /** Full Responses endpoint URL (custom template). */
-  responsesURL: z.string(),
+  responsesURL: coercedString(),
   /** Full Anthropic messages endpoint URL (custom template). */
-  anthropicURL: z.string(),
+  anthropicURL: coercedString(),
   /** Environment-variable name (credential ref) holding the API key. */
-  apiKeyEnv: z.string().role("credential-ref"),
+  apiKeyEnv: coercedString().role("credential-ref"),
   /** Gateway type label (newapi/litellm/higress/openai-compatible/custom). */
   flavor: z.union(FLAVORS),
   /** Model-list source: `auto` (prefer /v1/models), `v1`, or `management`. */
   catalogMode: z.union(["auto", "v1", "management"]),
   /** User id sent to the management API when it is used. */
-  userId: z.string(),
+  userId: coercedString(),
   /** Per-model overrides and custom models. */
   models: z.array(ModelOverrideSchema),
   /** Wire-format preference order for this gateway. */
-  endpointPriority: z.array(z.string()),
+  endpointPriority: z.array(coercedString()),
 });
 
 export const Config = z.object({
   // ---- Legacy single-connection fields (build the default `newapi` route) ----
   /** Display name of the default gateway route (defaults to "NewAPI"). */
-  label: z.string(),
+  label: coercedString(),
   /** Environment-variable name (credential ref) holding the default gateway API key. */
-  apiKeyEnv: z.string().role("credential-ref").default(DEFAULT_API_KEY_ENV),
+  apiKeyEnv: coercedString().role("credential-ref").default(DEFAULT_API_KEY_ENV),
   /** Default gateway base URL; resolved from NEWAPI_BASE_URL / NEWAPI_API_URL then the public cloud default. */
-  baseURL: z.string(),
+  baseURL: coercedString(),
   /** Full chat-completions endpoint URL (custom template for the default gateway). */
-  openaiURL: z.string(),
+  openaiURL: coercedString(),
   /** Full Responses endpoint URL (custom template for the default gateway). */
-  responsesURL: z.string(),
+  responsesURL: coercedString(),
   /** Full Anthropic messages endpoint URL (custom template for the default gateway). */
-  anthropicURL: z.string(),
+  anthropicURL: coercedString(),
   /** Gateway type label shown in the UI (newapi/litellm/higress/openai-compatible/custom). */
   flavor: z.union(FLAVORS).default("newapi"),
   /** models.dev catalog URL (any fetch-able URL; file: works for offline mirrors). */
-  modelsUrl: z.string().default(DEFAULT_MODELS_URL),
+  modelsUrl: coercedString().default(DEFAULT_MODELS_URL),
   /** Enrich gateway models with models.dev parameters. */
   useModelsDev: z.boolean().default(true),
   /** Widen the unknown-model reasoning fallback to the full off~max set. */
@@ -144,11 +162,17 @@ export const Config = z.object({
   /** Exclude non-chat model families from the picker. */
   includeChatOnly: z.boolean().default(true),
   /** Regex patterns excluding models from the picker. */
-  excludePatterns: z.array(z.string()).default(DEFAULT_EXCLUDE_PATTERNS),
+  excludePatterns: z.array(coercedString()).default(DEFAULT_EXCLUDE_PATTERNS),
   /** Wire-format preference order, intersected with each model's supported types. */
-  endpointPriority: z.array(z.string()).default(DEFAULT_ENDPOINT_PRIORITY),
+  endpointPriority: z.array(coercedString()).default(DEFAULT_ENDPOINT_PRIORITY),
   /** User id sent to the management API when it is used. */
-  userId: z.string().default("1"),
+  userId: coercedString().default("1"),
+  /**
+   * Extra HTTP headers sent with every provider request to the default
+   * gateway (name → value). Reserved attribution headers (user-agent) are
+   * filtered out at request time; per-request values are unaffected.
+   */
+  headers: z.dict(coercedString()),
   /** Fallback output-token cap for models without models.dev data. */
   maxTokens: z.number().step(1).min(1).default(DEFAULT_MAX_TOKENS),
   /** Fallback context window for models without models.dev data. */

package/lib/pi-bridge.js

@@ -344,10 +344,25 @@ export function toPiContext(options, attachments) {
 // Stream translation (pi-ai EventStream → harness StreamChunks)
 // ---------------------------------------------------------------------------
 
-/** Classify a pi-ai error message into a harness error code. */
+/**
+ * Classify a pi-ai error message into a harness error code.
+ * Lifted from dsh-llm-pi-ai/stream (rc.7): the coarse codes matter because
+ * the harness retry stack (dsh-llm-retry) retries exactly RATE_LIMIT /
+ * SERVER / TIMEOUT / TRANSPORT / EMPTY_RESPONSE — a generic fallback code
+ * would make gateway blips unretryable.
+ */
 function classifyPiAiError(text) {
+  if (/\b(?:401|403)\b/.test(text)) return "AUTH";
   if (isQuotaExceededError(text)) return QUOTA_EXCEEDED_CODE;
-  return "PROVIDER_ERROR";
+  if (/\b429\b|rate.?limit/i.test(text)) return "RATE_LIMIT";
+  if (/\b400\b|invalid.?request/i.test(text)) return "INVALID_REQUEST";
+  if (/\b5\d\d\b/.test(text)) return "SERVER";
+  if (/\btime(?:d)?\s*out\b|timeout/i.test(text)) return "TIMEOUT";
+  if (/stream ended (?:before|without)\b/i.test(text)) return "TRANSPORT";
+  if (/\b(?:network|connection|socket|fetch)\b|\bECONN[A-Z]+\b/i.test(text)
+    || /\b(?:other side closed|HTTP2 request did not get a response|WebSocket closed unexpectedly)\b/i.test(text)
+    || /\bterminated\b|premature close/i.test(text)) return "TRANSPORT";
+  return "PI_AI_ERROR";
 }
 
 /** Map pi-ai usage (reasoning folded into output by pi-ai). */

package/package.json

@@ -1,7 +1,15 @@
 {
   "name": "dsh-gateway-provider",
-  "version": "1.0.1",
+  "version": "1.0.3",
   "description": "Generic LLM gateway model provider plugin for DeepSeek Harness: mounts newapi / LiteLLM / Higress / any OpenAI-compatible gateway as provider routes, auto-discovers the model list, enriches every model with models.dev parameters, and dispatches each model over its native wire protocol (OpenAI / Anthropic / Gemini) via the pi-ai SDK",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/Luck9Star/dsh-gateway-provider.git"
+  },
+  "bugs": {
+    "url": "https://github.com/Luck9Star/dsh-gateway-provider/issues"
+  },
+  "homepage": "https://github.com/Luck9Star/dsh-gateway-provider#readme",
   "type": "module",
   "main": "index.js",
   "exports": {
@@ -12,13 +20,16 @@
   "files": [
     "index.js",
     "lib",
-    "cordis.patch.yml"
+    "cordis.patch.yml",
+    "docs"
   ],
   "scripts": {
     "link": "bash scripts/link.sh",
     "smoke": "node test/smoke.mjs",
     "test:client": "node test/client-render.mjs",
-    "test:urls": "node test/protocol-urls.mjs"
+    "test:urls": "node test/protocol-urls.mjs",
+    "test:schema": "node test/schema-coercion.mjs",
+    "test:errors": "node test/error-codes.mjs"
   },
   "keywords": [
     "deepseek-harness",
@@ -52,12 +63,11 @@
   "dependencies": {},
   "peerDependencies": {
     "@deepseek-ai/cordis": "^4.0.1",
-    "@deepseek-ai/dsh-anonymous-user-id": "^0.1.0-rc.6",
-    "@deepseek-ai/dsh-credentials": "^0.1.0-rc.6",
-    "@deepseek-ai/dsh-launch-environment": "^0.1.0-rc.6",
-    "@deepseek-ai/dsh-llm": "^0.1.0-rc.6",
-    "@deepseek-ai/dsh-settings": "^0.1.0-rc.6",
-    "@deepseek-ai/dsh-timeout": "^0.1.0-rc.6",
+    "@deepseek-ai/dsh-credentials": "^0.1.0-rc.7",
+    "@deepseek-ai/dsh-launch-environment": "^0.1.0-rc.7",
+    "@deepseek-ai/dsh-llm": "^0.1.0-rc.7",
+    "@deepseek-ai/dsh-settings": "^0.1.0-rc.7",
+    "@deepseek-ai/dsh-timeout": "^0.1.0-rc.7",
     "@deepseek-ai/schemastery": "^3.18.1",
     "@earendil-works/pi-ai": "^0.82.1"
   }