feat: coverage-driven extraction retry ladder (agent path)

backend/config.py

@@ -112,6 +112,15 @@ EXTRACT_REASONING_EFFORT = os.getenv("EXTRACT_REASONING_EFFORT", "low").strip()
 # the budget into visible output. 0 disables -> falls back to the effort knob.
 # Mutually exclusive with effort when set (OpenRouter rejects both together).
 EXTRACT_REASONING_MAX_TOKENS = int(os.getenv("EXTRACT_REASONING_MAX_TOKENS", "2048"))
+# Coverage-driven extraction retry ladder. After the vision pass, the fraction
+# of meaningful text-layer lines represented in extracted objects is measured;
+# below EXTRACT_COVERAGE_FLOOR the page climbs the ladder: text-only
+# structuring pass (rung 2), then deterministic text-layer fallback stubs
+# (rung 3) so no text-bearing page goes dark.
+EXTRACT_COVERAGE_FLOOR = float(os.getenv("EXTRACT_COVERAGE_FLOOR", "0.6"))
+EXTRACT_TEXT_RETRY_ENABLED = os.getenv("EXTRACT_TEXT_RETRY_ENABLED", "true").lower() == "true"
+EXTRACT_FALLBACK_ENABLED = os.getenv("EXTRACT_FALLBACK_ENABLED", "true").lower() == "true"
+EXTRACT_FALLBACK_MAX_OBJECTS = int(os.getenv("EXTRACT_FALLBACK_MAX_OBJECTS", "200"))
 REASON_MAX_TOKENS  = int(os.getenv("REASON_MAX_TOKENS",  "4096"))
 
 # -- QAQC stage knobs (Stages 0-1, 3, 6-11) -------------------------