docs: purge chain-of-thought leakage from prose
Delete design-session citations (decision/audit/plan ordinals, stack positions), change narration, review choreography, and reviewer-addressed justification from comments, JSDoc, docs, READMEs, Agent Notes, tests, and generator templates; restate every affected fact as current-state contract prose. Fix generated docs at their sources and regenerate the catalogs and cordis-surface regions; re-paste type-equiv blocks; update every bilingual counterpart and re-record the pairs. Record the citation rule in the committed-artifact-citations Agent Note.
This commit is contained in:
Tianyi Cui
@@ -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/web/web-search-deepseek/README.md
|
||||
README.md: 95340314fe08d0963b899f4a1d704a98f85963a5
|
||||
README.zh.md: cf83426f70d6d2a77fd9acf5e927d1b13ec345eb
|
||||
README.md: fb9e528633954b8eb9fd0fec8d19e24381a63f12
|
||||
README.zh.md: 4e761aa6ef1a67ce17fbc1cabf595af7f24e15e6
|
||||
|
||||
@@ -10,7 +10,7 @@ This is an **implementation** package: it registers a provider into `ctx.web`, r
|
||||
|
||||
Exa and Perplexity expose dedicated search endpoints; DeepSeek does not. Instead this provider issues a **full Messages model call** carrying the `web_search` server tool, so one search costs a complete model turn in latency and tokens — heavier than a pure retrieval endpoint. DeepSeek runs the search server-side and returns **structured** `web_search_tool_result` blocks; the provider parses those blocks and **never scrapes URLs out of model prose**.
|
||||
|
||||
**Strict mode**: if the response carries no `web_search_tool_result` block (native search did not trigger), the provider throws `WebError` `WEB_PROVIDER_ERROR` rather than degrading to prose-scraping — honest and debuggable.
|
||||
**Strict mode**: if the response carries no `web_search_tool_result` block (native search did not trigger), the provider throws `WebError` `WEB_PROVIDER_ERROR` rather than degrading to prose-scraping.
|
||||
|
||||
It reuses the `DEEPSEEK_API_KEY` credential reference (no new secret) but **not** `$DEEPSEEK_BASE_URL`: the search endpoint is the Anthropic-compatible base (`https://api.deepseek.com/anthropic/v1`), distinct from the chat-completions base (`https://api.deepseek.com`) the LLM adapter uses. A mounted credentials service is authoritative; without one, the provider falls back to the launching process environment. The reference is resolved for each search, so a key stored or rotated by the Web Models page reaches the next call without a restart.
|
||||
|
||||
|
||||
@@ -10,7 +10,7 @@
|
||||
|
||||
Exa 和 Perplexity 提供专用搜索端点，DeepSeek 则没有。该提供方改为发起一次携带 `web_search` 服务器工具的**完整 Messages 模型调用**，因此一次搜索会消耗完整模型轮次的延迟与 token，比纯检索端点更重。DeepSeek 在服务器侧执行搜索，返回**结构化** `web_search_tool_result` 块；提供方解析这些块，**绝不会从模型文本中抓取 URL**。
|
||||
|
||||
**严格模式**：如果响应不含 `web_search_tool_result` 块（未触发原生搜索），提供方会抛出 `WebError` `WEB_PROVIDER_ERROR`，而非降级为文本抓取；这种行为诚实且可诊断。
|
||||
**严格模式**：如果响应不含 `web_search_tool_result` 块（未触发原生搜索），提供方会抛出 `WebError` `WEB_PROVIDER_ERROR`，而非降级为文本抓取。
|
||||
|
||||
它复用 `DEEPSEEK_API_KEY` 凭据引用（不增加密钥），但**不会**复用 `$DEEPSEEK_BASE_URL`：搜索端点使用 Anthropic 兼容基址（`https://api.deepseek.com/anthropic/v1`），不同于大语言模型（LLM）适配器使用的 chat-completions 基址（`https://api.deepseek.com`）。已挂载的凭据服务具有权威性；没有该服务时，提供方会回退到启动进程的环境变量。每次搜索都会解析该引用，因此在 Web 的 Models 页中存储或轮换的密钥无需重启，即可用于下一次调用。
|
||||
|
||||
|
||||
@@ -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/web/web/README.md
|
||||
README.md: 22301a144b2e06ab42e1d503e8f8c554f7886330
|
||||
README.zh.md: 027b863cd7835f378de5f5c5d41166938b8cfe1a
|
||||
README.md: 2acb5022a83c08c33a26be626a93b7355c07a0ed
|
||||
README.zh.md: b77b0a897082dba01e10be3f7b0ca3b3f0260a9f
|
||||
|
||||
@@ -14,7 +14,7 @@ This package owns the Service Definition role of the web capability. Unlike bash
|
||||
| `@deepseek-ai/dsh-web-fetch-local` | Fetch provider: anonymous public HTTP(S) |
|
||||
| `@deepseek-ai/dsh-tool-web` | Consumer: the model-facing `web_search` / `web_fetch` tool schemas over `ctx.web` |
|
||||
|
||||
Search and fetch share no request schema and no business logic, but they are deliberately one seam: `ctx.web` is a single web-access middle layer with one provider-selection policy owner, one abort/error vocabulary, and one product-facing "how this harness reaches the web" config surface. The cost is the parallel `Search`/`Fetch` method pairs; that parallelism is intentional, not a missed extraction.
|
||||
Search and fetch share no request schema and no business logic, but they are deliberately one seam: `ctx.web` is a single web-access middle layer with one provider-selection policy owner, one abort/error vocabulary, and one product-facing "how this harness reaches the web" config surface. The `Search`/`Fetch` method pairs are deliberately parallel.
|
||||
|
||||
## Service API (`ctx.web`)
|
||||
|
||||
|
||||
@@ -14,7 +14,7 @@
|
||||
| `@deepseek-ai/dsh-web-fetch-local` | 抓取提供方：匿名公共 HTTP(S) |
|
||||
| `@deepseek-ai/dsh-tool-web` | Consumer：面向模型的 `web_search`／`web_fetch` 工具 schema，构建于 `ctx.web` 之上 |
|
||||
|
||||
搜索与抓取没有共享请求 schema 或业务逻辑，但有意共用一个 seam：`ctx.web` 是单一 web 访问中间层，拥有一项提供方选择策略、一套中止／错误词汇和一个面向产品的「该 harness 如何访问 web」配置接口。代价是成对的并行 `Search`／`Fetch` 方法；这种并行是有意设计，并非遗漏了可抽取的共性。
|
||||
搜索与抓取没有共享请求 schema 或业务逻辑，但有意共用一个 seam：`ctx.web` 是单一 web 访问中间层，拥有一项提供方选择策略、一套中止／错误词汇和一个面向产品的「该 harness 如何访问 web」配置接口。成对的 `Search`／`Fetch` 方法保持并行是有意为之。
|
||||
|
||||
## 服务 API（`ctx.web`）
|
||||
|
||||
|
||||
@@ -26,7 +26,8 @@ export interface WebSearchRequest {
|
||||
|
||||
/**
|
||||
* Normalized search outcome. `content` is optional provider-generated answer
|
||||
* text or summary (Exa returns none; Perplexity returns a generated answer).
|
||||
* text or summary (Exa and DeepSeek return none; Perplexity returns a
|
||||
* generated answer).
|
||||
* `sources[]` is the portable citation surface. `truncated` is set by the seam
|
||||
* when it cut `sources[]` down to `maxResults`.
|
||||
*/
|
||||
@@ -86,8 +87,8 @@ export interface WebFetchResult {
|
||||
* new kind is a coordinated change across known packages, not a plugin
|
||||
* extension. Consumers `switch` on `kind` ending in `default: assertNever(...)`
|
||||
* so adding a kind breaks compilation at every consumer until handled. Each arm
|
||||
* stays its own object literal even where fields coincide today, leaving room
|
||||
* for arm-specific fields later (a `pdf` body's `pageCount`).
|
||||
* stays its own object literal even where fields coincide, so an arm can gain
|
||||
* fields the others lack.
|
||||
*/
|
||||
export type WebFetchBody =
|
||||
| { readonly kind: 'html'; readonly content: string }
|
||||
|
||||
Reference in New Issue
Block a user