agent-fallback

jobsource/careers/cascade.py

@@ -7,10 +7,11 @@ Cascade order (return early on first success):
   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)
+  6.  Browser agent  → agent_fallback.find_and_extract()   confidence 0.50
 
 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).
+the ATS tier or browser-agent tier resolves — the first open-position URL for
+free (Stage-3 shortcut).
 
 The optional *client* parameter follows the managed-client pattern from
 resolve.py: supply an existing httpx.Client to reuse connections; otherwise a
@@ -23,7 +24,9 @@ import logging
 import httpx
 from pydantic import BaseModel
 
+from ..config import get_settings
 from ..http import build_client, request_with_retries
+from .. import agent_fallback as _agent_fallback
 from . import ats as _ats
 from . import classify_llm as _classify_llm
 from . import heuristics as _heuristics
@@ -41,7 +44,7 @@ class CareersResult(BaseModel):
 
     careers_url: str | None = None
     confidence: float = 0.0
-    # method values: "ats:{name}" | "url_pattern" | "homepage_scan" | "sitemap" | "llm_classify" | "none"
+    # method values: "ats:{name}" | "url_pattern" | "homepage_scan" | "sitemap" | "llm_classify" | "browser_agent" | "none"
     method: str = "none"
     ats_name: str | None = None
     # Free Stage-3 shortcut: populated when ATS tier resolves (first open job URL).
@@ -163,6 +166,26 @@ def find_careers_page(
         except Exception as exc:
             logger.warning("cascade(%s): llm_classify tier error: %s", website, exc)
 
+        # ------------------------------------------------------------------
+        # Tier 6 — Browser agent (fused Stage-2 + Stage-3 fallback)
+        # ------------------------------------------------------------------
+        if get_settings().enable_browser_agent:
+            try:
+                ag = _agent_fallback.find_and_extract(website)
+                if ag and ag.careers_url:
+                    logger.info(
+                        "cascade(%s): resolved via browser_agent careers_url=%s",
+                        website, ag.careers_url,
+                    )
+                    return CareersResult(
+                        careers_url=ag.careers_url,
+                        confidence=0.50,
+                        method="browser_agent",
+                        position_url=ag.position_url,
+                    )
+            except Exception as exc:
+                logger.warning("cascade(%s): browser_agent tier error: %s", website, exc)
+
         logger.info("cascade(%s): all tiers missed", website)
         return CareersResult()