opencode-search-plugin 0.0.0-stage → 1.0.0

package/plugins/youcom-search.ts

@@ -0,0 +1,313 @@
+import { Plugin } from "@opencode/plugin/effect"
+import { Effect, Schema, Stream } from "effect"
+
+// You.com returns { results: { web, news }, metadata } with no body-level error
+// envelope: failures are HTTP status codes only. Every result field is
+// optional -- a missing one means "the source provided none", not an error.
+// search_uuid is the only handle support has on a request, so it rides along
+// on decode failures.
+const YouResult = Schema.Struct({
+  url: Schema.optional(Schema.String),
+  title: Schema.optional(Schema.String),
+  description: Schema.optional(Schema.String),
+  snippets: Schema.optional(Schema.Array(Schema.String)),
+  page_age: Schema.optional(Schema.String),
+  contents: Schema.optional(
+    Schema.Struct({
+      html: Schema.optional(Schema.String),
+      markdown: Schema.optional(Schema.String),
+      highlights: Schema.optional(Schema.Array(Schema.String)),
+    }),
+  ),
+})
+
+const YouResponse = Schema.Struct({
+  results: Schema.optional(
+    Schema.Struct({
+      web: Schema.optional(Schema.Array(YouResult)),
+      news: Schema.optional(Schema.Array(YouResult)),
+    }),
+  ),
+  metadata: Schema.optional(
+    Schema.Struct({
+      search_uuid: Schema.optional(Schema.String),
+      query: Schema.optional(Schema.String),
+      latency: Schema.optional(Schema.Number),
+    }),
+  ),
+})
+
+type YouHit = typeof YouResult.Type
+
+// The /connect integration ID, and the websearch provider ID it binds to.
+const ID = "youcom"
+
+function envInt(name: string, fallback: number): number {
+  const raw = (process.env[name] ?? "").trim()
+  if (raw === "") return fallback
+  const value = Number(raw)
+  return Number.isFinite(value) && value >= 0 ? value : fallback
+}
+
+function envStr(name: string): string {
+  return (process.env[name] ?? "").trim()
+}
+
+// Search engines hand out dates in three flavours: relative ("28 minutes ago"),
+// absolute ("Sep 30, 2026" in the US, "31 Mar 2026" elsewhere), and non-English
+// relative ("4天前"). Relative values are rounded upstream, so month/year use
+// 30/365 days. ISO 8601 timestamps are accepted as-is.
+// See https://serpapi.com/blog/how-to-parse-dates-from-google-search/
+const RELATIVE_MS: Record<string, number> = {
+  minute: 60_000,
+  hour: 3_600_000,
+  day: 86_400_000,
+  week: 604_800_000,
+  month: 2_592_000_000,
+  year: 31_536_000_000,
+  分钟: 60_000,
+  小时: 3_600_000,
+  天: 86_400_000,
+  周: 604_800_000,
+  个月: 2_592_000_000,
+  月: 2_592_000_000,
+  年: 31_536_000_000,
+}
+
+const RELATIVE_DATE =
+  /^(\d+)\s*(minute|hour|day|week|month|year|分钟|小时|天|周|个月|月|年)s?\s*(?:ago|前)$/i
+
+const ABSOLUTE_DATE = [
+  /^\d{1,2}\s+[A-Za-z]{3,9}\s+\d{4}$/, // "3 Jan 2022", "31 Mar 2026"
+  /^[A-Za-z]{3,9}\s+\d{1,2},?\s+\d{4}$/, // "Sep 30, 2026", "Jan 27, 2025"
+  /^\d{4}-\d{2}-\d{2}$/, // "2026-10-16"
+  // ISO 8601 with a time component, which some providers return verbatim.
+  /^\d{4}-\d{2}-\d{2}T\d{2}:\d{2}(?::\d{2}(?:\.\d+)?)?(?:Z|[+-]\d{2}:?\d{2})?$/,
+]
+
+function parseSearchDate(value: string | undefined): number {
+  const text = value?.trim()
+  if (!text) return NaN
+
+  const relative = RELATIVE_DATE.exec(text)
+  if (relative) {
+    const unit = relative[2] !== undefined ? RELATIVE_MS[relative[2].toLowerCase()] : undefined
+    const amount = Number(relative[1])
+    if (unit === undefined || !Number.isFinite(amount)) return NaN
+    return Date.now() - amount * unit
+  }
+
+  // Only trust Date.parse on shapes these providers actually emit -- its lenient
+  // parser invents a year for strings like "Nov 1", which would date the result
+  // to 2001.
+  return ABSOLUTE_DATE.some((shape) => shape.test(text)) ? Date.parse(text) : NaN
+}
+
+// Web and news live in separate sections; an agent asking "what's new" wants
+// both, so they merge into one list with web first.
+function toResult(item: YouHit) {
+  const published = parseSearchDate(item.page_age)
+  const extracted =
+    item.contents?.highlights?.join("\n") ??
+    item.contents?.markdown ??
+    item.snippets?.join(" ") ??
+    item.description ??
+    ""
+  return {
+    url: item.url ?? "",
+    title: item.title || item.url || "",
+    content: extracted,
+    time: Number.isFinite(published) ? { published } : {},
+  }
+}
+
+type SearchResult = ReturnType<typeof toResult>
+
+// You.com is pay-as-you-go and has no anonymous tier: $5 per 1k searches, up
+// to 100 results per call. A repeat query is a fresh billed dispatch, so
+// responses are cached per normalized query. Knobs are read once at load time,
+// restart after changing them.
+//
+//   YOUCOM_CACHE_TTL     ms to reuse a response for the same query (0 disables)
+//   YOUCOM_COUNT         results per section (web and news each), clamped 1-100
+//   YOUCOM_EXTRACTION    "highlights" (default) returns the passages that answer
+//                        the query, "none" returns bare snippets, "full_page"
+//                        crawls every hit and is billed per live-fetched page
+//                        ($1 per 1k) on top of the search -- cached pages are free
+//   YOUCOM_LANGUAGE      result language, e.g. "EN", "ZH-HANS"
+//   YOUCOM_COUNTRY       geographic focus, e.g. "US", "CN"
+//   YOUCOM_FRESHNESS     "day" | "week" | "month" | "year" or "YYYY-MM-DDtoYYYY-MM-DD"
+//   YDC_API_KEY          required; You.com's canonical env var, shared with its SDKs
+const CACHE_TTL = envInt("YOUCOM_CACHE_TTL", 600_000)
+const SEARCH_SIZE = Math.min(Math.max(envInt("YOUCOM_COUNT", 10), 1), 100)
+const EXTRACTION = ["none", "highlights", "full_page"].includes(envStr("YOUCOM_EXTRACTION"))
+  ? envStr("YOUCOM_EXTRACTION")
+  : "highlights"
+const LANGUAGE = envStr("YOUCOM_LANGUAGE")
+const COUNTRY = envStr("YOUCOM_COUNTRY")
+const FRESHNESS = envStr("YOUCOM_FRESHNESS")
+
+const CACHE_LIMIT = 200
+const cache = new Map<string, { at: number; results: SearchResult[] }>()
+
+function cacheKey(query: string): string {
+  return query.trim().replace(/\s+/g, " ")
+}
+
+function readCache(queryKey: string): SearchResult[] | undefined {
+  if (CACHE_TTL <= 0) return undefined
+  const hit = cache.get(queryKey)
+  return hit && Date.now() - hit.at < CACHE_TTL ? hit.results : undefined
+}
+
+function writeCache(queryKey: string, results: SearchResult[]): void {
+  if (CACHE_TTL <= 0) return
+  cache.set(queryKey, { at: Date.now(), results })
+  if (cache.size > CACHE_LIMIT) {
+    const oldest = cache.keys().next().value
+    if (oldest !== undefined) cache.delete(oldest)
+  }
+}
+
+export const effect = (ctx: Plugin.Context) =>
+  Effect.gen(function* () {
+    // Make "You.com" show up in /connect with an API-key method.
+    yield* ctx.integration.transform((editor) => {
+      editor.update(ID, (integration) => {
+        integration.name = "You.com"
+      })
+      editor.method.update({
+        integrationID: ID,
+        method: { type: "key", label: "You.com API key" },
+      })
+      editor.method.update({
+        integrationID: ID,
+        method: { type: "env", names: ["YDC_API_KEY"] },
+      })
+    })
+
+    // The host instantiates this API's failure channel as `unknown`, which would
+    // make the whole plugin effect unrunnable. A credential read must never take
+    // the plugin down: a failed read degrades to "no stored key", and the
+    // environment fallback below applies exactly as it does when the credential
+    // simply does not exist.
+    const soften = <A>(read: Effect.Effect<A, unknown>): Effect.Effect<A | undefined, never> =>
+      read.pipe(Effect.catch(() => Effect.succeed(undefined)))
+
+    // The key comes from the /connect credential, falling back to the
+    // environment. Resolved per call so a rotated key needs no restart.
+    const resolveKey = () =>
+      Effect.gen(function* () {
+        const connection = yield* soften(ctx.integration.connection.active(ID))
+        const credential = connection
+          ? yield* soften(ctx.integration.connection.resolve(connection))
+          : undefined
+        return credential?.type === "key" ? credential.key : process.env.YDC_API_KEY
+      })
+
+    // You.com is bound to websearch only while a key exists. Deleting the key
+    // unbinds the provider, so `random` can never pick a keyless You.com.
+    // The transform replays on reload and reads `bound` as it stands then.
+    let bound = Boolean(yield* resolveKey())
+
+    yield* ctx.websearch.transform((editor) => {
+      if (!bound) return
+      editor.add({
+        id: ID,
+        name: "You.com",
+        execute: ({ query }) =>
+          Effect.gen(function* () {
+            const queryKey = cacheKey(query)
+            const cached = readCache(queryKey)
+            if (cached) return cached
+
+            // Rechecked per call: binding can lag a key deletion by the
+            // event round-trip, so this keeps that window explicit.
+            const key = yield* resolveKey()
+            if (!key) {
+              return yield* Effect.fail(
+                new Error("Connect You.com in /connect, or set YDC_API_KEY"),
+              )
+            }
+
+            const extraction =
+              EXTRACTION === "highlights"
+                ? { extraction_mode: "highlights" }
+                : EXTRACTION === "full_page"
+                  ? {
+                      extraction_mode: "full_page",
+                      full_page: { extraction_formats: ["markdown"] },
+                    }
+                  : undefined
+
+            const response = yield* Effect.tryPromise({
+              try: () =>
+                fetch("https://ydc-index.io/v1/search", {
+                  method: "POST",
+                  headers: {
+                    Accept: "application/json",
+                    "Content-Type": "application/json",
+                    "X-API-Key": key,
+                  },
+                  body: JSON.stringify({
+                    query: queryKey,
+                    count: SEARCH_SIZE,
+                    ...(LANGUAGE ? { language: LANGUAGE } : {}),
+                    ...(COUNTRY ? { country: COUNTRY } : {}),
+                    ...(FRESHNESS ? { freshness: FRESHNESS } : {}),
+                    ...(extraction ? { extraction } : {}),
+                  }),
+                }),
+              catch: (error) => new Error("You.com request failed: " + String(error)),
+            })
+
+            if (!response.ok) {
+              const detail = yield* Effect.tryPromise({
+                try: () => response.text(),
+                catch: () => new Error("response body unavailable"),
+              })
+              return yield* Effect.fail(
+                new Error("You.com API error " + response.status + ": " + detail),
+              )
+            }
+
+            const json = yield* Effect.tryPromise({
+              try: () => response.json(),
+              catch: (error) => new Error("Invalid You.com response: " + String(error)),
+            })
+
+            const body = yield* Schema.decodeUnknownEffect(YouResponse)(json)
+            const hits = [...(body.results?.web ?? []), ...(body.results?.news ?? [])]
+            const results = hits.flatMap((item) => (item.url ? [toResult(item)] : []))
+
+            writeCache(queryKey, results)
+            return results
+          }),
+      })
+    })
+
+    // Rebind on credential changes: connect, delete, or rotate a key and the
+    // provider joins or leaves the websearch pool without a restart. Env-var
+    // keys cannot change under a running process, so they bind at startup.
+    yield* Effect.forkScoped(
+      ctx.event.subscribe().pipe(
+        Stream.filter(
+          (event) =>
+            event.type === "credential.updated" ||
+            event.type === "credential.switched" ||
+            event.type === "integration.updated",
+        ),
+        Stream.mapEffect(() =>
+          Effect.gen(function* () {
+            const next = Boolean(yield* resolveKey())
+            if (next === bound) return
+            bound = next
+            yield* ctx.websearch.reload()
+          }),
+        ),
+        Stream.runDrain,
+      ),
+    )
+  })
+
+export default Plugin.define({ id: "youcom-search", effect })