fix(rag): log when index_file silently no-ops on missing file

Per Tier 1 addendum 3 (the 4th red flag): index_file had a silent
`if not os.path.exists(full_path): return` no-op. When the RAG
engine is misconfigured (e.g. stale active_project_path from a prior
test's project switch), the files are not found and index_file
silently returns. The user sees an empty collection with no
indication of why.

Fix: emit a stderr.write with base_dir, file_path, and cwd when the
file is not found. This makes the misconfiguration visible in the
subprocess log (tests/logs/sloppy_py_test.log) instead of invisible.

This would have made the "index_file not called" diagnostic trivial
during the 3-session investigation of test_rag_phase4_final_verify.

Note: the test still fails (RAG search returns 0 chunks) even with
the proper project switch + this log fix. The exact root cause of
the empty collection is still under investigation.

src/rag_engine.py

@@ -335,6 +335,15 @@ class RAGEngine:
    if os.path.exists(cwd_path):
     full_path = cwd_path
    else:
+    # Per Tier 1 addendum 3: log when index_file silently no-ops on a
+    # missing file. This makes misconfigured base_dir visible in the
+    # subprocess log instead of invisible (a real production bug that
+    # made this diagnostic chain 3 sessions long).
+    sys.stderr.write(
+     f"RAG index_file: file not found, base_dir={self.base_dir!r} "
+     f"file_path={file_path!r} cwd={os.getcwd()!r}\n"
+    )
+    sys.stderr.flush()
     return
 
   mtime_result = self._get_file_mtime_result(full_path)