Add web capability seam: ctx.web, search/fetch providers, web tools

Introduce web access as a first-class capability seam so the model-facing
web tools stay stable while backends change. dsh-web owns ctx.web as a
provider registry with registration-order-independent selection and the
WebError taxonomy; dsh-web-search-exa, dsh-web-search-perplexity, and
dsh-web-fetch-local register capabilities into it; dsh-tool-web is the sole
owner of the model-facing web_search/web_fetch schemas, prompt sections, and
HTML-to-markdown presentation. Search and fetch are deliberately one seam.

Providers ship as namespace plugins that register into ctx.web (like an
LlmAdapter into ctx.llm), not key-owning services, since multiple search
providers cannot each own the key. Tool registration follows product
enablement, not backend availability, so load order/credentials never enter
the model contract; the seam resolves the provider at execution time and
surfaces a structured WebError otherwise.

Moves the RFC to implemented/ amended to match what shipped. Example/app
configs are intentionally not wired yet (RFC migration step 6).
This commit is contained in:
Dudu-0223
2026-06-25 15:04:12 +08:00
parent a4091daa3d
commit d01f5f73b7
50 changed files with 3610 additions and 8 deletions

View File

@@ -0,0 +1,130 @@
/**
* `ExaSearchProvider`: a `WebSearchProvider` backed by the Exa search API
* (`POST /search` with highlight contents). Maps Exa's flat `results[]` into the
* seam's normalized `WebSearchResult`. Exa returns no provider-generated answer,
* so `content` is omitted; each result maps to a `WebSearchSource` with `url`,
* `title`, the first highlight as `snippet`, and `publishedDate` as
* `publishedAt`.
*
* Network requests use platform-native `fetch` (Node 24), mirroring
* `@deepseek-ai/dsh-llm-deepseek`'s adapter — not a cordis HTTP-client service.
*
* @module @deepseek-ai/dsh-web-search-exa/provider
*/
import { WebError } from '@deepseek-ai/dsh-web'
import type {
WebProviderStatus,
WebSearchProvider,
WebSearchRequest,
WebSearchResult,
WebSearchSource,
} from '@deepseek-ai/dsh-web'
import type { ExaError, ExaResult, ExaSearchResponse } from './types.ts'
/** Stable id this provider registers under. */
export const EXA_PROVIDER_ID = 'exa'
/** Default Exa search endpoint; `/search` is the operation. */
export const EXA_DEFAULT_BASE_URL = 'https://api.exa.ai'
/** Attribution header sent on every request. Bump with the package version. */
const USER_AGENT = 'deepseek-harness/0.0.1'
export interface ExaSearchProviderOptions {
/** Exa API key. Empty/absent → `status()` reports `missing-credential`. */
apiKey: string
/** Endpoint base; `/search` is appended. */
baseURL: string
}
/**
* Map one Exa result to a normalized source, or `undefined` when it carries no
* portable snippet (an entry with no highlight is dropped — the seam has no
* other field to derive a snippet from, and inventing one would lie).
*/
export function mapExaResult(result: ExaResult): WebSearchSource | undefined {
const snippet = result.highlights?.find(highlight => highlight.trim().length > 0)
if (snippet === undefined) return undefined
return {
url: result.url,
...result.title != null && result.title.length > 0 ? { title: result.title } : {},
snippet,
...result.publishedDate != null && result.publishedDate.length > 0 ? { publishedAt: result.publishedDate } : {},
}
}
/** Map an Exa response envelope to a normalized search result. */
export function mapExaResponse(query: string, response: ExaSearchResponse): WebSearchResult {
const sources = (response.results ?? [])
.map(mapExaResult)
.filter((source): source is WebSearchSource => source !== undefined)
// Exa returns no generated answer, so `content` is omitted. The seam owns the
// final `maxResults` truncation, so this provider reports `truncated: false`.
return { providerId: EXA_PROVIDER_ID, query, sources, truncated: false }
}
/** The Exa-backed search provider. */
export class ExaSearchProvider implements WebSearchProvider {
readonly id = EXA_PROVIDER_ID
constructor(private readonly options: ExaSearchProviderOptions) {}
status(): WebProviderStatus {
if (this.options.apiKey.length === 0) return { available: false, reason: 'missing-credential' }
return { available: true }
}
async search(request: WebSearchRequest, exec?: { readonly signal?: AbortSignal }): Promise<WebSearchResult> {
let response: Response
try {
response = await fetch(`${this.options.baseURL}/search`, {
method: 'POST',
headers: {
'authorization': `Bearer ${this.options.apiKey}`,
'content-type': 'application/json',
'accept': 'application/json',
'user-agent': USER_AGENT,
},
body: JSON.stringify({
query: request.query,
contents: { highlights: true },
...request.maxResults !== undefined ? { numResults: request.maxResults } : {},
}),
...exec?.signal ? { signal: exec.signal } : {},
})
} catch (error: unknown) {
if (isAbortError(error)) throw new WebError('Exa search aborted', 'WEB_ABORTED', { cause: error })
throw new WebError(`Exa search request failed: ${String(error)}`, 'WEB_PROVIDER_ERROR', { cause: error })
}
if (!response.ok) {
const status = response.status
let message = `Exa API error (HTTP ${status})`
try {
const parsed = await response.json() as ExaError
const detail = parsed.error ?? parsed.message
if (detail !== undefined && detail.length > 0) message = detail
} catch {
// The HTTP status is already captured in `message` above; a malformed or
// non-JSON error body (normal for gateway 5xx/429s) can only cost a
// richer provider message, never the real error. `response.json()` is
// the sole statement and nothing else of consequence reaches here.
}
throw new WebError(message, 'WEB_PROVIDER_ERROR')
}
let payload: ExaSearchResponse
try {
payload = await response.json() as ExaSearchResponse
} catch (error: unknown) {
throw new WebError(`Exa returned an unparseable response body: ${String(error)}`, 'WEB_PROVIDER_ERROR', { cause: error })
}
return mapExaResponse(request.query, payload)
}
}
/** True for a fetch/`AbortSignal` abort, surfaced as `WEB_ABORTED`. */
function isAbortError(error: unknown): boolean {
return error instanceof DOMException && error.name === 'AbortError'
}