feat(api): PDF + DOCX extraction in folder indexer

Add pypdf/python-docx deps, _extract_pdf_text/_extract_docx_text helpers,
and summarize_pdf/summarize_docx wrappers that delegate to summarize_text.

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

app/core/folder_indexer.py

@@ -1,9 +1,13 @@
 """Per-file summarisation for project folder integration."""
 from __future__ import annotations
 
+import base64
+import io
 from dataclasses import dataclass
 
 from langchain_core.messages import HumanMessage, SystemMessage
+from pypdf import PdfReader
+from docx import Document as DocxDocument
 
 from app.core.langfuse_client import (
     compile_prompt,
@@ -98,3 +102,53 @@ async def summarize_text(*, content: str, ext: str, name: str) -> IndexResult:
     usage = extract_usage(response)
     summary = (response.content or "").strip()[:500]
     return IndexResult(summary=summary, tokens_used=usage.get("total", 0))
+
+
+def _extract_pdf_text(pdf_b64: str) -> str:
+    buf = io.BytesIO(base64.b64decode(pdf_b64))
+    reader = PdfReader(buf)
+    parts: list[str] = []
+    for page in reader.pages:
+        try:
+            parts.append(page.extract_text() or "")
+        except Exception:
+            continue
+    return "\n".join(parts).strip()
+
+
+def _extract_docx_text(docx_b64: str) -> str:
+    buf = io.BytesIO(base64.b64decode(docx_b64))
+    doc = DocxDocument(buf)
+    return "\n".join(p.text for p in doc.paragraphs if p.text).strip()
+
+
+async def summarize_pdf(*, pdf_b64: str, name: str) -> IndexResult:
+    """Return a compact summary of a PDF file.
+
+    Parameters
+    ----------
+    pdf_b64:
+        Base64-encoded PDF bytes.
+    name:
+        File name, e.g. ``"report.pdf"``.
+    """
+    text = _extract_pdf_text(pdf_b64)
+    if not text:
+        return IndexResult(summary="Could not extract text", tokens_used=0)
+    return await summarize_text(content=text, ext=".pdf", name=name)
+
+
+async def summarize_docx(*, docx_b64: str, name: str) -> IndexResult:
+    """Return a compact summary of a DOCX file.
+
+    Parameters
+    ----------
+    docx_b64:
+        Base64-encoded DOCX bytes.
+    name:
+        File name, e.g. ``"spec.docx"``.
+    """
+    text = _extract_docx_text(docx_b64)
+    if not text:
+        return IndexResult(summary="Could not extract text", tokens_used=0)
+    return await summarize_text(content=text, ext=".docx", name=name)