add criteria-first discovery search provider

apps/api/app/discovery.py

@@ -1,8 +1,9 @@
-"""Bounded, public-only prospect discovery using an explicit seed allowlist.
+"""Bounded, public-only prospect discovery with optional criteria search.
 
 There is deliberately no general web search or arbitrary URL input here: callers provide
-at most a small set of public seed pages. Only links found on those seeds become candidate
-sites, and subsequent crawling is same-origin, bounded, and SSRF-checked by the scanner.
+at most a small set of public seed pages. When seeds are omitted, a configured search
+provider supplies bounded seed URLs. Links found on those seeds become candidate sites,
+and subsequent crawling is same-origin, bounded, and SSRF-checked by the scanner.
 """
 from __future__ import annotations
 
@@ -12,6 +13,7 @@ from urllib.parse import urljoin, urldefrag, urlparse
 
 from .contact_extractor import extract_contacts
 from .website_scanner import MAX_BYTES, MAX_REDIRECTS, _fetch, validate_url
+from .search_provider import search as search_provider
 
 MAX_SEEDS = 5
 MAX_PAGES = 20
@@ -61,14 +63,21 @@ def _criteria_match(text, criteria):
     return not keywords or all(str(k).strip().lower() in haystack for k in keywords if str(k).strip())
 
 
-def discover(criteria, seed_urls, *, max_pages=MAX_PAGES, max_candidates=MAX_CANDIDATES):
+def discover(criteria, seed_urls=None, *, max_pages=MAX_PAGES, max_candidates=MAX_CANDIDATES):
     if not isinstance(criteria, dict) or len(criteria) > 20: raise ValueError("invalid_criteria")
-    if not isinstance(seed_urls, list) or not 0 < len(seed_urls) <= MAX_SEEDS: raise ValueError("seed_urls_required")
     try: max_pages = int(max_pages); max_candidates = int(max_candidates)
     except (TypeError, ValueError): raise ValueError("invalid_limits")
     if not 1 <= max_pages <= MAX_PAGES or not 1 <= max_candidates <= MAX_CANDIDATES: raise ValueError("invalid_limits")
+    if seed_urls is None:
+        seeds = search_provider(criteria, max_candidates)
+        mechanism = "criteria_search_provider"
+    else:
+        if not isinstance(seed_urls, list) or not 0 < len(seed_urls) <= MAX_SEEDS: raise ValueError("seed_urls_required")
+        seeds = list(seed_urls)
+        mechanism = "explicit_seed_allowlist"
+    raw_seeds = list(seeds)
     seeds = []
-    for raw in seed_urls:
+    for raw in raw_seeds:
         try: safe = validate_url(raw)
         except ValueError as exc: raise ValueError("unsafe_seed_url") from exc
         if safe not in seeds: seeds.append(safe)
@@ -125,5 +134,5 @@ def discover(criteria, seed_urls, *, max_pages=MAX_PAGES, max_candidates=MAX_CAN
             evidence.append({"kind": "discovery_page", "url": page["url"], "claim": claim, "provenance": "scoped_discovery"})
         deduped = {(x["kind"], x["value"]): x for x in contacts}
         name = next((x["headings"][0] for x in pages if x["headings"]), next((x["title"] for x in pages if x["title"]), domain))
-        results.append({"name": name[:200], "website": root, "website_domain": domain, "description": text[:1000], "contacts": list(deduped.values())[:100], "evidence": evidence, "pages": pages, "pages_crawled": len(pages), "provenance": {"mechanism": "explicit_seed_allowlist", "seed_urls": seeds, "root_url": root}})
+        results.append({"name": name[:200], "website": root, "website_domain": domain, "description": text[:1000], "contacts": list(deduped.values())[:100], "evidence": evidence, "pages": pages, "pages_crawled": len(pages), "provenance": {"mechanism": mechanism, "seed_urls": seeds, "root_url": root}})
     return {"candidates": results, "seeds": seeds, "pages_limit": max_pages, "candidate_limit": max_candidates}