agent-fallback

jobsource/extract.py

@@ -10,11 +10,13 @@ Cascade order (return early on first hit):
   3.  Job-like anchors — first <a> whose href matches /job|/position|/opening|/vacanc.
   4.  Cheap-LLM        — classify_job_link() from classify_llm; no-ops gracefully
                         when the LLM is not configured.
-  5.  Miss            — return (None, "none").
+  5.  Browser agent   — agent_fallback.find_and_extract(); fused with Stage-2 so
+                        the same memoized session covers both stages.
+  6.  Miss            — return (None, "none").
 
 Returns (url: str | None, method: str). Never raises — any tier failure logs
 and falls through. method is one of:
-  "ats:{name}" | "json_ld" | "anchor" | "llm_classify" | "none"
+  "ats:{name}" | "json_ld" | "anchor" | "llm_classify" | "browser_agent" | "none"
 """
 from __future__ import annotations
 
@@ -26,8 +28,10 @@ from urllib.parse import urlsplit
 import httpx
 from bs4 import BeautifulSoup
 
+from . import agent_fallback as _agent_fallback
 from .careers import ats as _ats
 from .careers.classify_llm import classify_job_link, extract_anchors
+from .config import get_settings
 from .http import build_client, request_with_retries
 
 logger = logging.getLogger(__name__)
@@ -206,6 +210,20 @@ def extract_open_position(
         except Exception as exc:
             logger.warning("extract(%s): llm_classify tier error: %s", careers_url, exc)
 
+        # ------------------------------------------------------------------
+        # Tier 5 — Browser agent (fused; memo-shared with cascade Tier 6)
+        # ------------------------------------------------------------------
+        if get_settings().enable_browser_agent:
+            try:
+                ag = _agent_fallback.find_and_extract(careers_url)
+                if ag and ag.position_url:
+                    logger.info(
+                        "extract(%s): browser_agent pos=%s", careers_url, ag.position_url
+                    )
+                    return ag.position_url, "browser_agent"
+            except Exception as exc:
+                logger.warning("extract(%s): browser_agent tier error: %s", careers_url, exc)
+
         logger.info("extract(%s): all tiers missed", careers_url)
         return None, "none"