backend/.env.example

@@ -72,3 +72,9 @@ SMTP_PASSWORD=
 SMTP_FROM=
 SMTP_USE_TLS=true
 SMTP_USE_SSL=false
+
+# Wave 5b evidence verification (vision fact-check of cited sheet text)
+AGENT_VERIFY_MAX_CHECKS=20
+AGENT_VERIFY_SEVERITIES=critical,high
+AGENT_VERIFY_REASONING_EFFORT=low
+VERIFY_MAX_TOKENS=8192

backend/config.py

@@ -47,6 +47,18 @@ AGENT_CONFLICT_CONCURRENCY   = int(os.getenv("AGENT_CONFLICT_CONCURRENCY", "4"))
 AGENT_SPECIALIST_CONCURRENCY = int(os.getenv("AGENT_SPECIALIST_CONCURRENCY", "4"))
 AGENT_RFI_CONCURRENCY        = int(os.getenv("AGENT_RFI_CONCURRENCY", "4"))
 
+# Wave 5b evidence verification (vision fact-check of cited sheet text)
+AGENT_VERIFY_MODEL         = os.getenv("AGENT_VERIFY_MODEL", "") or MODEL
+AGENT_VERIFY_CONCURRENCY   = int(os.getenv("AGENT_VERIFY_CONCURRENCY", "4"))
+AGENT_VERIFY_MAX_CHECKS    = int(os.getenv("AGENT_VERIFY_MAX_CHECKS", "20"))
+AGENT_VERIFY_SEVERITIES    = {
+    s.strip().lower()
+    for s in os.getenv("AGENT_VERIFY_SEVERITIES", "critical,high").split(",")
+    if s.strip()
+}
+AGENT_VERIFY_REASONING_EFFORT = os.getenv("AGENT_VERIFY_REASONING_EFFORT", "low").strip()
+VERIFY_MAX_TOKENS          = int(os.getenv("VERIFY_MAX_TOKENS", "8192"))
+
 # Agent-mode human-review gate. When on (default), Agent runs stop after the
 # Brain merge and wait for human decisions before RFIs/final report/email go
 # out. AGENT_REVIEW_AUDIT_SAMPLE caps how many clean clusters get added to the

backend/prompts.py

@@ -450,6 +450,26 @@ Clustered assertions (evidence):
 {evidence}"""
 
 
+# ---------------------------------------------------------------------------
+# Wave 5b - evidence verification (vision fact-check of cited sheet text)
+# ---------------------------------------------------------------------------
+
+VERIFY_SYSTEM_PROMPT = """You are a meticulous construction document checker verifying machine-extracted evidence against the actual drawing sheet images.
+For each evidence item you are given the sheet it was extracted from and the verbatim text the extractor claims appears there.
+Judge each item against the images:
+- confirmed: the text (or an obvious equivalent) appears on the cited sheet and means what the finding claims.
+- corrected: the sheet shows a DIFFERENT value than the extracted text. Give the actual verbatim text.
+- not_found: nothing like the extracted text appears on the cited sheet.
+Be strict about numbers, quantities, and member sizes: "(2) 2x6" and "(5) 2x6" are different values. HSS16x4 and HSS16x16 are different values.
+Use plain ASCII only.
+Respond only with valid JSON."""
+
+VERIFY_USER_INSTRUCTION = """Verify this finding's evidence against the attached sheet images.
+Respond ONLY with a valid JSON object - no markdown fences, no explanation:
+{ "verdicts": [ { "sheet": "string", "source_text": "the evidence text judged", "verdict": "confirmed | corrected | not_found", "actual_text": "verbatim sheet text when corrected, else null", "notes": "string or null" } ] }
+Finding: {finding}"""
+
+
 # ---------------------------------------------------------------------------
 # Stage 6 - senior architect full-set QAQC review  (NOT WIRED YET)
 # ---------------------------------------------------------------------------