careers-llm-extract

jobsource/careers/cascade.py

@@ -1,12 +1,13 @@
 """find_careers_page(): orchestrate the Stage 2 tier cascade.
 
 Cascade order (return early on first success):
-  1. ATS detection → ats.detect_and_fetch()       confidence 0.95
-  2. URL patterns  → heuristics.probe_url_patterns()  0.80
-  3. Homepage scan → heuristics.scan_homepage_links()  0.60
-  4. Sitemap       → heuristics.parse_sitemap()        0.50
-  5. Cheap-LLM     → classify_llm (stub, not implemented in this phase)
-  6. Browser agent → agent_fallback (stub, not implemented in this phase)
+  1.  ATS detection  → ats.detect_and_fetch()              confidence 0.95
+  1b. ATS slug-guess → ats.recover_via_slug_guess()        confidence 0.90
+  2.  URL patterns   → heuristics.probe_url_patterns()     confidence 0.80
+  3.  Homepage scan  → heuristics.scan_homepage_links()    confidence 0.60
+  4.  Sitemap        → heuristics.parse_sitemap()          confidence 0.50
+  5.  Cheap-LLM      → classify_llm.classify_careers_link()  confidence 0.55
+  6.  Browser agent  → agent_fallback (not implemented in this phase)
 
 Returns a CareersResult with the URL, confidence, method string, and — when
 the ATS tier resolves — the first open-position URL for free (Stage-3 shortcut).
@@ -24,6 +25,7 @@ from pydantic import BaseModel
 
 from ..http import build_client, request_with_retries
 from . import ats as _ats
+from . import classify_llm as _classify_llm
 from . import heuristics as _heuristics
 
 logger = logging.getLogger(__name__)
@@ -39,7 +41,7 @@ class CareersResult(BaseModel):
 
     careers_url: str | None = None
     confidence: float = 0.0
-    # method values: "ats:{name}" | "url_pattern" | "homepage_scan" | "sitemap" | "none"
+    # method values: "ats:{name}" | "url_pattern" | "homepage_scan" | "sitemap" | "llm_classify" | "none"
     method: str = "none"
     ats_name: str | None = None
     # Free Stage-3 shortcut: populated when ATS tier resolves (first open job URL).
@@ -145,8 +147,23 @@ def find_careers_page(
         except Exception as exc:
             logger.warning("cascade(%s): sitemap tier error: %s", website, exc)
 
-        # All deterministic tiers missed.
-        logger.info("cascade(%s): all deterministic tiers missed", website)
+        # ------------------------------------------------------------------
+        # Tier 5 — Cheap-LLM careers-link classification
+        # ------------------------------------------------------------------
+        try:
+            if homepage_html:
+                anchors = _classify_llm.extract_anchors(homepage_html, website)
+                res = _classify_llm.classify_careers_link(anchors)
+                if res:
+                    logger.info(
+                        "cascade(%s): resolved via llm_classify careers_url=%s confidence=%.2f",
+                        website, res.careers_url, res.confidence,
+                    )
+                    return _finalize(res.careers_url, "llm_classify", 0.55, website, client)
+        except Exception as exc:
+            logger.warning("cascade(%s): llm_classify tier error: %s", website, exc)
+
+        logger.info("cascade(%s): all tiers missed", website)
         return CareersResult()
 
     finally: