generated provenance: duplicate exception logging sweep (#1612/#1698)

.jules/sentinel.md

@@ -138,3 +138,8 @@
 **Vulnerability:** The `_safe_filename` function in `backend/services/attachment_parser.py` used `pathlib.Path().name` to strip directory components from attachment filenames, but failed to normalize backslashes beforehand. This allowed attackers to use Windows-style path separators (e.g., `..\..\upload`) to bypass path validation on POSIX systems.
 **Learning:** Checking for traversal sequences using `pathlib.Path().name` may leave the result vulnerable if the input path can contain Windows-style path separators but the program interprets it dynamically or decodes payloads using backslashes, because POSIX `pathlib` treats backslashes as valid filename characters, not separators.
 **Prevention:** Always convert backslashes to forward slashes before parsing filenames using `pathlib.Path().name`.
+
+## 2024-05-18 - Prevent Exception String Interpolation in Logs
+**Vulnerability:** String-interpolating exception objects into logs (e.g., `logger.error(f'Error: {e}')`) can leak sensitive information like API keys.
+**Learning:** In Python, printing or string-formatting an exception object can inadvertently expose its underlying variables or message contents, which may contain sensitive credentials that caused the error.
+**Prevention:** Use `logger.error("Generic error message", exc_info=True)` to securely log the stack trace and generic exceptions (`raise MyError("Generic error") from e`) instead of interpolating the exception object directly into the string.

backend/api/emails.py

@@ -772,8 +772,8 @@ async def send_email_endpoint(
         return send_result
     except HTTPException:
         raise
-    except Exception as e:
-        logger.error(f"Error sending email: {e}", exc_info=True)
+    except Exception:
+        logger.error("Error sending email", exc_info=True)
         raise HTTPException(
             status_code=500, detail="An internal error occurred while sending the email"
         )

backend/api/prompts.py

@@ -113,10 +113,10 @@ async def execute_prompt_with_llm(
         )
         content = response.choices[0].message.content
         return {"result": content if content else ""}
-    except Exception as e:
+    except Exception:
         import logging
 
-        logging.getLogger(__name__).error(f"Prompt execution failed: {e}")
+        logging.getLogger(__name__).error("Prompt execution failed", exc_info=True)
         raise HTTPException(
             status_code=502,
             detail="Failed to execute prompt with AI provider. Check provider status.",

backend/import_fixtures.py

@@ -37,8 +37,8 @@ async def generate_fixture_embedding(text: str) -> list[float]:
 async def import_eml_file(session, eml_file: Path) -> bool:
     try:
         parsed = parse_eml(eml_file)
-    except Exception as e:
-        logger.error(f"Failed to parse {eml_file}: {e}")
+    except Exception:
+        logger.error(f"Failed to parse {eml_file}", exc_info=True)
         return False
 
     existing = await session.execute(
@@ -55,8 +55,8 @@ async def import_eml_file(session, eml_file: Path) -> bool:
     body_text = parsed["body"] if parsed["body"].strip() else "Empty body"
     try:
         body_emb = await generate_fixture_embedding(body_text)
-    except Exception as e:
-        logger.error(f"Failed to generate embedding for {eml_file}: {e}")
+    except Exception:
+        logger.error(f"Failed to generate embedding for {eml_file}", exc_info=True)
         return False
 
     thread_id = await assign_thread_id(
@@ -93,15 +93,18 @@ async def import_eml_file(session, eml_file: Path) -> bool:
                     embedding=att_emb,
                 )
             )
-        except Exception as e:
-            logger.error(f"Failed to generate embedding for attachment {att['filename']}: {e}")
+        except Exception:
+            logger.error(
+                f"Failed to generate embedding for attachment {att['filename']}",
+                exc_info=True,
+            )
 
     session.add(email_obj)
     try:
         await session.commit()
-    except Exception as e:
+    except Exception:
         await session.rollback()
-        logger.error(f"Failed to commit {eml_file}: {e}")
+        logger.error(f"Failed to commit {eml_file}", exc_info=True)
         return False
     logger.info(
         f"Imported {eml_file.name} with {len(parsed.get('attachments', []))} attachments."

backend/pyproject.toml

@@ -38,6 +38,7 @@ dependencies = [
   "PyJWT==2.13.0",
   "icalendar==7.2.0",
   "defusedxml==0.7.1",
+  "anyio>=4.14.2",
 ]
 
 [dependency-groups]

backend/scripts/import_fixtures.py

@@ -35,16 +35,15 @@ async def process_zip_file(zip_path: str | Path, session: AsyncSession):
         logger.info(f"Extracting {zip_path}...")
         extracted_files = await extract_backup_async(zip_path, temp_dir)
 
-
         batch_values = []
         for file_path in extracted_files:
             if not str(file_path).endswith(".eml"):
                 continue
 
             try:
                 email_data = parse_eml(file_path)
-            except Exception as e:
-                logger.error(f"Failed to parse {file_path}: {e}")
+            except Exception:
+                logger.error(f"Failed to parse {file_path}", exc_info=True)
                 continue
 
             chunks = chunk_text(email_data["body"])
@@ -70,9 +69,10 @@ async def process_zip_file(zip_path: str | Path, session: AsyncSession):
                             embeddings[0],
                             STORAGE_EMBEDDING_DIMENSION,
                         )
-                except Exception as e:
+                except Exception:
                     logger.error(
-                        f"Failed to generate embedding for {email_data['message_id']}: {e}"
+                        f"Failed to generate embedding for {email_data['message_id']}",
+                        exc_info=True,
                     )
 
             # Upsert into database
@@ -83,21 +83,23 @@ async def process_zip_file(zip_path: str | Path, session: AsyncSession):
                 organization_id=IMPORT_ORGANIZATION_ID,
             )
 
-            batch_values.append(dict(
-                user_id=IMPORT_USER_ID,
-                organization_id=IMPORT_ORGANIZATION_ID,
-                message_id=email_data["message_id"],
-                sender=email_data["sender"],
-                reply_to=email_data.get("reply_to"),
-                recipients=email_data["recipients"],
-                subject=email_data["subject"],
-                in_reply_to=email_data.get("in_reply_to"),
-                references=email_data.get("references"),
-                thread_id=thread_id,
-                date=email_data["date"],
-                body=email_data["body"],
-                embedding=embedding,
-            ))
+            batch_values.append(
+                dict(
+                    user_id=IMPORT_USER_ID,
+                    organization_id=IMPORT_ORGANIZATION_ID,
+                    message_id=email_data["message_id"],
+                    sender=email_data["sender"],
+                    reply_to=email_data.get("reply_to"),
+                    recipients=email_data["recipients"],
+                    subject=email_data["subject"],
+                    in_reply_to=email_data.get("in_reply_to"),
+                    references=email_data.get("references"),
+                    thread_id=thread_id,
+                    date=email_data["date"],
+                    body=email_data["body"],
+                    embedding=embedding,
+                )
+            )
 
         if batch_values:
             stmt = insert(Email)

backend/services/imap_worker.py

@@ -98,6 +98,7 @@ async def process_fetched_email(
         await extract_knowledge_from_self_sent(session, new_email, owner_addresses)
     return new_email
 
+
 logger = logging.getLogger(__name__)
 MAX_IMAP_FETCH_MESSAGES = 10
 
@@ -112,7 +113,11 @@ def flags_indicate_seen(fetch_data) -> bool:
     for item in fetch_data or []:
         parts = item if isinstance(item, (tuple, list)) else (item,)
         for part in parts:
-            raw = part if isinstance(part, bytes) else str(part).encode("utf-8", "replace")
+            raw = (
+                part
+                if isinstance(part, bytes)
+                else str(part).encode("utf-8", "replace")
+            )
             upper = raw.upper()
             if b"FLAGS" in upper and b"\\SEEN" in upper:
                 return True
@@ -162,8 +167,8 @@ async def _run_loop(self):
                 await self._sync()
             except asyncio.CancelledError:
                 break
-            except Exception as e:
-                logger.error(f"Error in ImapSyncWorker loop: {e}", exc_info=True)
+            except Exception:
+                logger.error("Error in ImapSyncWorker loop", exc_info=True)
 
             # Sleep for 1 minute before the next sync
             if self._is_running:
@@ -217,7 +222,7 @@ async def _sync_tenant(self, config: TenantConfig | ImapSyncConfig):
                 config.user_id,
             )
             return 0
-        
+
         logger.info(
             "Connecting to IMAP server %s:%s for user %s",
             imap_server,
@@ -252,6 +257,7 @@ async def _fetch_messages(
         if imap_server is None or imap_port is None:
             imap_server, imap_port = self._validated_destination(config)
         import ssl
+
         ssl_context = ssl.create_default_context()
         imap_client = aioimaplib.IMAP4_SSL(
             imap_server, imap_port, ssl_context=ssl_context
@@ -388,6 +394,4 @@ def _looks_like_rfc822_message(self, value: bytes) -> bool:
         header_block = value.split(b"\r\n\r\n", maxsplit=1)[0]
         if header_block == value:
             header_block = value.split(b"\n\n", maxsplit=1)[0]
-        return b":" in header_block and (
-            b"\r\n\r\n" in value or b"\n\n" in value
-        )
+        return b":" in header_block and (b"\r\n\r\n" in value or b"\n\n" in value)

backend/services/llm_service.py

@@ -62,27 +62,27 @@ async def extract_action_items_and_summary(
         response = await provider_circuit_breaker.call(
             validated_base_url or "openai-default",
             lambda: retry_transient(
-            lambda: client.beta.chat.completions.parse(
-            model=selected_model,
-            messages=[
-                {
-                    "role": "system",
-                    "content": (
-                        "You are a helpful assistant. Summarize the email, "
-                        "extract action items, and include a confidence score "
-                        "from 0 to 100 when enough evidence is available."
-                    ),
-                },
-                {"role": "user", "content": email_body},
-            ],
-            response_format=ExtractionResult,
-            ),
-            operation_name="summary extraction",
+                lambda: client.beta.chat.completions.parse(
+                    model=selected_model,
+                    messages=[
+                        {
+                            "role": "system",
+                            "content": (
+                                "You are a helpful assistant. Summarize the email, "
+                                "extract action items, and include a confidence score "
+                                "from 0 to 100 when enough evidence is available."
+                            ),
+                        },
+                        {"role": "user", "content": email_body},
+                    ],
+                    response_format=ExtractionResult,
+                ),
+                operation_name="summary extraction",
             ),
         )
     except Exception as e:
-        logger.error(f"Error calling LLM API for extraction: {e}")
-        raise LLMServiceError(f"LLM API error during extraction: {e}") from e
+        logger.error("Error calling LLM API for extraction", exc_info=True)
+        raise LLMServiceError("LLM API error during extraction") from e
     finally:
         await client.close()
 
@@ -147,8 +147,8 @@ async def translate_email_body(
             ),
         )
     except Exception as e:
-        logger.error(f"Error calling LLM API for translation: {e}")
-        raise LLMServiceError(f"LLM API error during translation: {e}") from e
+        logger.error("Error calling LLM API for translation", exc_info=True)
+        raise LLMServiceError("LLM API error during translation") from e
     finally:
         await client.close()
 
@@ -189,8 +189,8 @@ async def draft_reply(
                 messages,
             )
         except Exception as e:
-            logger.error(f"Error calling LLM API for drafting: {e}")
-            raise LLMServiceError(f"LLM API error during drafting: {e}") from e
+            logger.error("Error calling LLM API for drafting", exc_info=True)
+            raise LLMServiceError("LLM API error during drafting") from e
         finally:
             await http_client.aclose()
 
@@ -211,8 +211,8 @@ async def draft_reply(
             ),
         )
     except Exception as e:
-        logger.error(f"Error calling LLM API for drafting: {e}")
-        raise LLMServiceError(f"LLM API error during drafting: {e}") from e
+        logger.error("Error calling LLM API for drafting", exc_info=True)
+        raise LLMServiceError("LLM API error during drafting") from e
     finally:
         await client.close()
 

backend/services/pop3_worker.py

@@ -46,8 +46,8 @@ async def _run_loop(self):
                 await self._sync()
             except asyncio.CancelledError:
                 break
-            except Exception as e:
-                logger.error(f"Error in Pop3SyncWorker loop: {e}", exc_info=True)
+            except Exception:
+                logger.error("Error in Pop3SyncWorker loop", exc_info=True)
 
             if self._is_running:
                 try:
@@ -57,16 +57,18 @@ async def _run_loop(self):
 
     async def _sync(self):
         async with AsyncSessionLocal() as session:
-            result = await session.execute(select(TenantConfig).where(TenantConfig.pop3_server.isnot(None)))
+            result = await session.execute(
+                select(TenantConfig).where(TenantConfig.pop3_server.isnot(None))
+            )
             configs = result.scalars().all()
-            
+
         semaphore = asyncio.Semaphore(10)
         tasks = []
         for config in configs:
             if not config.pop3_server or not config.pop3_port:
                 continue
             tasks.append(self._sync_tenant(config, semaphore))
-            
+
         if tasks:
             await asyncio.gather(*tasks, return_exceptions=True)
 
@@ -195,7 +197,5 @@ def _message_number_from_listing(self, listing: bytes | str) -> int | None:
 
     def _bytes_line(self, line: bytes | str) -> bytes:
         return (
-            line
-            if isinstance(line, bytes)
-            else line.encode("utf-8", errors="replace")
+            line if isinstance(line, bytes) else line.encode("utf-8", errors="replace")
         )

frontend/package.json

@@ -22,10 +22,11 @@
     "class-variance-authority": "^0.7.1",
     "clsx": "^2.1.1",
     "lucide-react": "^1.27.0",
-    "next": "16.2.12",
+    "next": "16.3.5",
     "react": "19.2.8",
     "react-dom": "19.2.8",
     "react-resizable-panels": "^4.12.2",
+    "sharp": "0.35.4",
     "tailwind-merge": "^3.5.0",
     "tailwindcss": "^4",
     "tw-animate-css": "^1.4.0",