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).
2026-06-25 15:04:12 +08:00
parent a4091daa3d
commit d01f5f73b7
50 changed files with 3610 additions and 8 deletions
@@ -0,0 +1,85 @@
+/**
+ * Minimal, dependency-free HTML→markdown-ish text conversion for `web_fetch`
+ * presentation. This is intentionally NOT a full HTML parser: it strips
+ * script/style/noscript, drops tags, decodes the common named/numeric entities,
+ * and collapses whitespace into a readable plain-text approximation with a few
+ * markdown affordances (headings, list bullets, links). A heavier converter can
+ * replace this without touching the seam or the tool schema.
+ *
+ * @module @deepseek-ai/dsh-tool-web/html
+ */
+
+/** Decode the handful of HTML entities common in textual content. */
+function decodeEntities(text: string): string {
+  return text
+    .replace(/&(#[xX][0-9a-fA-F]+|#[0-9]+|[a-zA-Z]+);/g, (match, entity: string) => {
+      if (entity.startsWith('#x') || entity.startsWith('#X')) {
+        const code = Number.parseInt(entity.slice(2), 16)
+        return safeFromCodePoint(code, match)
+      }
+      if (entity.startsWith('#')) {
+        const code = Number.parseInt(entity.slice(1), 10)
+        return safeFromCodePoint(code, match)
+      }
+      return NAMED_ENTITIES[entity] ?? match
+    })
+}
+
+const NAMED_ENTITIES: Record<string, string> = {
+  amp: '&', lt: '<', gt: '>', quot: '"', apos: "'", nbsp: ' ',
+  copy: '©', reg: '®', trade: '™', hellip: '…', mdash: '—', ndash: '–',
+}
+
+function safeFromCodePoint(code: number, fallback: string): string {
+  try {
+    return String.fromCodePoint(code)
+  } catch {
+    // An out-of-range code point (RangeError) is the only failure here; keep the
+    // original entity text rather than throwing out of pure presentation.
+    return fallback
+  }
+}
+
+/**
+ * Convert an HTML document to a readable markdown-ish text approximation.
+ * Best-effort and lossy by design — fidelity is the job of a future heavier
+ * converter, not this fallback.
+ */
+export function htmlToMarkdown(html: string): string {
+  let text = html
+    // Drop non-content elements entirely (including their contents).
+    .replace(/<script\b[^>]*>[\s\S]*?<\/script>/gi, '')
+    .replace(/<style\b[^>]*>[\s\S]*?<\/style>/gi, '')
+    .replace(/<noscript\b[^>]*>[\s\S]*?<\/noscript>/gi, '')
+    .replace(/<!--[\s\S]*?-->/g, '')
+
+  // Convert links to markdown before stripping tags.
+  text = text.replace(/<a\b[^>]*\bhref\s*=\s*["']([^"']*)["'][^>]*>([\s\S]*?)<\/a>/gi, (_match, href: string, label: string) => {
+    const cleanLabel = label.replace(/<[^>]+>/g, '').trim()
+    return cleanLabel.length > 0 ? `[${cleanLabel}](${href})` : href
+  })
+
+  // Headings → markdown hashes.
+  text = text.replace(/<h([1-6])\b[^>]*>([\s\S]*?)<\/h\1>/gi, (_match, level: string, body: string) => {
+    const hashes = '#'.repeat(Number(level))
+    return `\n\n${hashes} ${body.replace(/<[^>]+>/g, '').trim()}\n\n`
+  })
+
+  // List items → bullets.
+  text = text.replace(/<li\b[^>]*>([\s\S]*?)<\/li>/gi, (_match, body: string) => `\n- ${body.replace(/<[^>]+>/g, '').trim()}`)
+
+  // Block-level breaks become paragraph breaks.
+  text = text
+    .replace(/<\/(p|div|section|article|header|footer|tr|table|ul|ol|blockquote)>/gi, '\n\n')
+    .replace(/<br\s*\/?>/gi, '\n')
+
+  // Drop all remaining tags, decode entities, collapse whitespace.
+  text = text.replace(/<[^>]+>/g, '')
+  text = decodeEntities(text)
+  text = text
+    .replace(/[ \t\f\v]+/g, ' ')
+    .replace(/ *\n */g, '\n')
+    .replace(/\n{3,}/g, '\n\n')
+    .trim()
+  return text
+}