fix: Round 15 — 2 HIGH bugs fixed (sql_count citation audit + reader error handling)

H-1: validate_citations counted all SQL rows as 1 source, causing
systematic false "fabricated reference" warnings on multi-row SQL
queries. Now counts each row as a separate citable unit.

H-2: text.py and csv_tab.py were the only readers without try/except
wrappers. A single bad .txt/.csv file would crash the entire ingestion
pipeline. Added matching error handling.

174/174 tests passing. Final line-by-line audit by 3 independent agents
confirmed all 23 source files are clean.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

src/readers/csv_tab.py

@@ -3,47 +3,51 @@ import csv
 MAX_CHUNK_CHARS = 6000
 
 def read_csv_tab(file_path: str, delimiter: str = None) -> list[dict]:
-    from pathlib import Path
-    if delimiter is None:
-        ext = Path(file_path).suffix.lower()
-        delimiter = "\t" if ext in (".tab", ".tsv") else ","
+    try:
+        from pathlib import Path
+        if delimiter is None:
+            ext = Path(file_path).suffix.lower()
+            delimiter = "\t" if ext in (".tab", ".tsv") else ","
 
-    with open(file_path, "r", encoding="utf-8-sig", errors="replace") as f:
-        reader = csv.reader(f, delimiter=delimiter)
-        rows = list(reader)
+        with open(file_path, "r", encoding="utf-8-sig", errors="replace") as f:
+            reader = csv.reader(f, delimiter=delimiter)
+            rows = list(reader)
 
-    if not rows:
-        return []
+        if not rows:
+            return []
+
+        headers = [h.strip().strip('"') for h in rows[0]]
+        row_texts = []
+        for row in rows[1:]:
+            parts = []
+            padded_row = list(row) + [""] * max(0, len(headers) - len(row))
+            for header, val in zip(headers, padded_row[:len(headers)]):
+                val = val.strip().strip('"')
+                if val:
+                    parts.append(f"{header}: {val}")
+            if parts:
+                row_texts.append("; ".join(parts))
 
-    headers = [h.strip().strip('"') for h in rows[0]]
-    row_texts = []
-    for row in rows[1:]:
-        parts = []
-        padded_row = list(row) + [""] * max(0, len(headers) - len(row))
-        for header, val in zip(headers, padded_row[:len(headers)]):
-            val = val.strip().strip('"')
-            if val:
-                parts.append(f"{header}: {val}")
-        if parts:
-            row_texts.append("; ".join(parts))
+        pages = []
+        header_line = f"Columns: {', '.join(headers)}\n"
+        block = []
+        block_chars = len(header_line)
+        block_start = 1
 
-    pages = []
-    header_line = f"Columns: {', '.join(headers)}\n"
-    block = []
-    block_chars = len(header_line)
-    block_start = 1
+        for idx, row_text in enumerate(row_texts):
+            if block and block_chars + len(row_text) + 1 > MAX_CHUNK_CHARS:
+                text = header_line + "\n".join(block)
+                pages.append({"page": f"rows_{block_start}-{block_start + len(block) - 1}", "text": text})
+                block = []
+                block_chars = len(header_line)
+                block_start = idx + 1
+            block.append(row_text)
+            block_chars += len(row_text) + 1
 
-    for idx, row_text in enumerate(row_texts):
-        if block and block_chars + len(row_text) + 1 > MAX_CHUNK_CHARS:
+        if block:
             text = header_line + "\n".join(block)
             pages.append({"page": f"rows_{block_start}-{block_start + len(block) - 1}", "text": text})
-            block = []
-            block_chars = len(header_line)
-            block_start = idx + 1
-        block.append(row_text)
-        block_chars += len(row_text) + 1
-
-    if block:
-        text = header_line + "\n".join(block)
-        pages.append({"page": f"rows_{block_start}-{block_start + len(block) - 1}", "text": text})
-    return pages
+        return pages
+    except Exception as e:
+        print(f"Warning: Could not read {file_path}: {e}")
+        return []

src/readers/text.py

@@ -2,8 +2,12 @@
 
 
 def read_text(file_path: str) -> list[dict]:
-    with open(file_path, "r", encoding="utf-8", errors="replace") as f:
-        text = f.read()
-    if not text.strip():
+    try:
+        with open(file_path, "r", encoding="utf-8", errors="replace") as f:
+            text = f.read()
+        if not text.strip():
+            return []
+        return [{"page": 1, "text": text.strip()}]
+    except Exception as e:
+        print(f"Warning: Could not read {file_path}: {e}")
         return []
-    return [{"page": 1, "text": text.strip()}]

src/verifier.py

@@ -168,7 +168,7 @@ def validate_citations(response: str, retrieval_result: dict) -> list[str]:
     db_results = retrieval_result.get("db_results", [])
     db_count = len(db_results)
     web_count = len(retrieval_result.get("web_results", []))
-    sql_count = 1 if retrieval_result.get("sql_results") else 0
+    sql_count = len(retrieval_result.get("sql_results", []))
     total_sources = db_count + web_count + sql_count
 
     if total_sources == 0: