add criteria-first discovery search provider

apps/api/app/main.py

@@ -15,6 +15,7 @@ if __package__ in (None, ""):
     from app.scoring import DEFAULT_RULES, signals_for_business, evaluate_score, SCORE_VERSION
     from app.ai_assistance import generate as generate_ai, input_fingerprint, provider_status, MAX_INPUT_ITEMS, MAX_OUTPUT_CHARS
     from app.discovery import discover as scoped_discover
+    from app.search_provider import provider_status as search_provider_status
     from app.config import load_config
 else:
     from .domain import deduplication_key, deduplicate_businesses, is_suppressed, normalize_business, score_business, normalize_domain, normalize_phone, match_businesses
@@ -25,6 +26,7 @@ else:
     from .scoring import DEFAULT_RULES, signals_for_business, evaluate_score, SCORE_VERSION
     from .ai_assistance import generate as generate_ai, input_fingerprint, provider_status, MAX_INPUT_ITEMS, MAX_OUTPUT_CHARS
     from .discovery import discover as scoped_discover
+    from .search_provider import provider_status as search_provider_status
 from .config import load_config
 ORGANIZATION_ID = "demo-tenant"
 SCHEMA = Path(__file__).resolve().parents[1] / "schema.sql"
@@ -595,6 +597,7 @@ class ApiHandler(BaseHTTPRequestHandler):
             if path=="/api/v1/sources": return self.list_sources(db,org)
             if path=="/api/v1/discovery-queries": return self.list_queries(db,org)
             if path=="/api/v1/discovery-runs": return self.list_discovery_runs(db,org,parse_qs(parsed.query))
+            if path=="/api/v1/discovery/provider-status": return self.send_json(200, search_provider_status())
             if path=="/api/v1/source-records": return self.list_source_records(db,org,parse_qs(parsed.query))
             if path=="/api/v1/jobs": return self.list_jobs(db,org,parse_qs(parsed.query))
             if path=="/api/v1/domain-checks": return self.list_domain_checks(db,org,parse_qs(parsed.query))
@@ -805,26 +808,33 @@ class ApiHandler(BaseHTTPRequestHandler):
 
     def create_scoped_discovery(self, payload, db, user):
         criteria = payload.get("criteria", {}); seeds = payload.get("seed_urls")
-        if not isinstance(criteria, dict) or not isinstance(seeds, list) or not seeds: return self.send_json(400, {"error": "seed_urls_required"})
+        criteria_only = seeds is None
+        if not isinstance(criteria, dict): return self.send_json(400, {"error": "invalid_criteria"})
+        if not criteria_only and (not isinstance(seeds, list) or not seeds): return self.send_json(400, {"error": "seed_urls_required"})
+        if criteria_only:
+            status = search_provider_status()
+            if status["status"] != "ready": return self.send_json(503, {"error": status["status"], "provider": status["provider"]})
         try:
-            if len(seeds) > 5 or len(json.dumps(criteria).encode()) > 8192: raise ValueError("invalid_criteria")
+            if not criteria_only and len(seeds) > 5: raise ValueError("invalid_criteria")
+            if len(json.dumps(criteria).encode()) > 8192: raise ValueError("invalid_criteria")
             if not isinstance(criteria.get("keywords", criteria.get("keyword", [])), (list, str)): raise ValueError("invalid_criteria")
             max_pages = int(payload.get("max_pages", 20)); max_candidates = int(payload.get("max_candidates", 50))
             if not 1 <= max_pages <= 20 or not 1 <= max_candidates <= 50: raise ValueError("invalid_limits")
         except (ValueError, TypeError) as exc: return self.send_json(400, {"error": str(exc) or "invalid_criteria"})
-        try:
-            for url in seeds: validate_url(url)
-        except (ValueError, TypeError):
-            return self.send_json(400, {"error": "unsafe_seed_url"})
+        if not criteria_only:
+            try:
+                for url in seeds: validate_url(url)
+            except (ValueError, TypeError):
+                return self.send_json(400, {"error": "unsafe_seed_url"})
         key = str(payload.get("idempotency_key", "")).strip()
         if not key or len(key) > 200: return self.send_json(400, {"error": "invalid_idempotency_key"})
-        job_payload = {"criteria": criteria, "seed_urls": seeds, "max_pages": max_pages, "max_candidates": max_candidates}
+        job_payload = {"criteria": criteria, "seed_urls": seeds if not criteria_only else None, "max_pages": max_pages, "max_candidates": max_candidates}
         result = self.create_job({"type": "scoped_discovery", "payload": job_payload, "idempotency_key": key, "_accepted": True, "_defer_wakeup": True}, db, user)
         # create_job has already committed; read its id from the response is not available,
         # so resolve by the tenant-scoped idempotency key.
         job = db.execute("SELECT * FROM jobs WHERE organization_id=? AND idempotency_key=?", (user["organization_id"], key)).fetchone()
         if not db.execute("SELECT id FROM discovery_runs WHERE organization_id=? AND job_id=?", (user["organization_id"], job["id"])).fetchone():
-            db.execute("INSERT INTO discovery_runs(organization_id,job_id,criteria_json,seed_urls_json) VALUES(?,?,?,?)", (user["organization_id"], job["id"], json.dumps(criteria, sort_keys=True), json.dumps(seeds)))
+            db.execute("INSERT INTO discovery_runs(organization_id,job_id,criteria_json,seed_urls_json) VALUES(?,?,?,?)", (user["organization_id"], job["id"], json.dumps(criteria, sort_keys=True), json.dumps(seeds if not criteria_only else [])))
             self.audit(db, user, "discovery.created", str(job["id"])); db.commit()
         getattr(self.server, "job_wakeup", threading.Event()).set()
         return result