chore: ran linting

surfsense_backend/app/indexing_pipeline/connector_document.py

@@ -5,6 +5,7 @@ from app.db import DocumentType
 
 class ConnectorDocument(BaseModel):
     """Canonical data transfer object produced by connector adapters and consumed by the indexing pipeline."""
+
     title: str
     source_markdown: str
     unique_id: str

surfsense_backend/app/indexing_pipeline/document_chunker.py

@@ -3,5 +3,7 @@ from app.config import config
 
 def chunk_text(text: str, use_code_chunker: bool = False) -> list[str]:
     """Chunk a text string using the configured chunker and return the chunk texts."""
-    chunker = config.code_chunker_instance if use_code_chunker else config.chunker_instance
+    chunker = (
+        config.code_chunker_instance if use_code_chunker else config.chunker_instance
+    )
     return [c.text for c in chunker.chunk(text)]

surfsense_backend/app/indexing_pipeline/document_summarizer.py

@@ -2,7 +2,9 @@ from app.prompts import SUMMARY_PROMPT_TEMPLATE
 from app.utils.document_converters import optimize_content_for_context_window
 
 
-async def summarize_document(source_markdown: str, llm, metadata: dict | None = None) -> str:
+async def summarize_document(
+    source_markdown: str, llm, metadata: dict | None = None
+) -> str:
     """Generate a text summary of a document using an LLM, prefixed with metadata when provided."""
     model_name = getattr(llm, "model", "gpt-3.5-turbo")
     optimized_content = optimize_content_for_context_window(

surfsense_backend/app/indexing_pipeline/exceptions.py

@@ -12,7 +12,6 @@ from litellm.exceptions import (
     Timeout,
     UnprocessableEntityError,
 )
-from sqlalchemy.exc import IntegrityError
 
 # Tuples for use directly in except clauses.
 RETRYABLE_LLM_ERRORS = (
@@ -36,29 +35,33 @@ PERMANENT_LLM_ERRORS = (
 # (LiteLLMEmbeddings, CohereEmbeddings, GeminiEmbeddings all normalize to RuntimeError).
 EMBEDDING_ERRORS = (
     RuntimeError,  # local device failure or API backend normalization
-    OSError,       # model files missing or corrupted (local backends)
-    MemoryError,   # document too large for available RAM
+    OSError,  # model files missing or corrupted (local backends)
+    MemoryError,  # document too large for available RAM
 )
 
 
 class PipelineMessages:
-    RATE_LIMIT        = "LLM rate limit exceeded. Will retry on next sync."
-    LLM_TIMEOUT       = "LLM request timed out. Will retry on next sync."
-    LLM_UNAVAILABLE   = "LLM service temporarily unavailable. Will retry on next sync."
-    LLM_BAD_GATEWAY   = "LLM gateway error. Will retry on next sync."
-    LLM_SERVER_ERROR  = "LLM internal server error. Will retry on next sync."
-    LLM_CONNECTION    = "Could not reach the LLM service. Check network connectivity."
+    RATE_LIMIT = "LLM rate limit exceeded. Will retry on next sync."
+    LLM_TIMEOUT = "LLM request timed out. Will retry on next sync."
+    LLM_UNAVAILABLE = "LLM service temporarily unavailable. Will retry on next sync."
+    LLM_BAD_GATEWAY = "LLM gateway error. Will retry on next sync."
+    LLM_SERVER_ERROR = "LLM internal server error. Will retry on next sync."
+    LLM_CONNECTION = "Could not reach the LLM service. Check network connectivity."
 
-    LLM_AUTH          = "LLM authentication failed. Check your API key."
-    LLM_PERMISSION    = "LLM request denied. Check your account permissions."
-    LLM_NOT_FOUND     = "LLM model not found. Check your model configuration."
-    LLM_BAD_REQUEST   = "LLM rejected the request. Document content may be invalid."
-    LLM_UNPROCESSABLE = "Document exceeds the LLM context window even after optimization."
-    LLM_RESPONSE      = "LLM returned an invalid response."
+    LLM_AUTH = "LLM authentication failed. Check your API key."
+    LLM_PERMISSION = "LLM request denied. Check your account permissions."
+    LLM_NOT_FOUND = "LLM model not found. Check your model configuration."
+    LLM_BAD_REQUEST = "LLM rejected the request. Document content may be invalid."
+    LLM_UNPROCESSABLE = (
+        "Document exceeds the LLM context window even after optimization."
+    )
+    LLM_RESPONSE = "LLM returned an invalid response."
 
-    EMBEDDING_FAILED  = "Embedding failed. Check your embedding model configuration or service."
-    EMBEDDING_MODEL   = "Embedding model files are missing or corrupted."
-    EMBEDDING_MEMORY  = "Not enough memory to embed this document."
+    EMBEDDING_FAILED = (
+        "Embedding failed. Check your embedding model configuration or service."
+    )
+    EMBEDDING_MODEL = "Embedding model files are missing or corrupted."
+    EMBEDDING_MEMORY = "Not enough memory to embed this document."
 
     CHUNKING_OVERFLOW = "Document structure is too deeply nested to chunk."
 

surfsense_backend/app/indexing_pipeline/indexing_pipeline_service.py

@@ -2,6 +2,7 @@ import contextlib
 from datetime import UTC, datetime
 
 from sqlalchemy import delete, select
+from sqlalchemy.exc import IntegrityError
 from sqlalchemy.ext.asyncio import AsyncSession
 
 from app.db import Chunk, Document, DocumentStatus
@@ -21,7 +22,6 @@ from app.indexing_pipeline.exceptions import (
     EMBEDDING_ERRORS,
     PERMANENT_LLM_ERRORS,
     RETRYABLE_LLM_ERRORS,
-    IntegrityError,
     PipelineMessages,
     embedding_message,
     llm_permanent_message,

surfsense_backend/app/indexing_pipeline/pipeline_logger.py

@@ -8,27 +8,29 @@ logger = logging.getLogger(__name__)
 class PipelineLogContext:
     connector_id: int | None
     search_space_id: int
-    unique_id: str            # always available from ConnectorDocument
-    doc_id: int | None = None # set once the DB row exists (index phase only)
+    unique_id: str  # always available from ConnectorDocument
+    doc_id: int | None = None  # set once the DB row exists (index phase only)
 
 
 class LogMessages:
     # prepare_for_indexing
-    DOCUMENT_QUEUED     = "New document queued for indexing."
-    DOCUMENT_UPDATED    = "Document content changed, re-queued for indexing."
-    DOCUMENT_REQUEUED   = "Stuck document re-queued for indexing."
+    DOCUMENT_QUEUED = "New document queued for indexing."
+    DOCUMENT_UPDATED = "Document content changed, re-queued for indexing."
+    DOCUMENT_REQUEUED = "Stuck document re-queued for indexing."
     DOC_SKIPPED_UNKNOWN = "Unexpected error — document skipped."
-    BATCH_ABORTED       = "Fatal DB error — aborting prepare batch."
-    RACE_CONDITION      = "Concurrent worker beat us to the commit — rolling back batch."
+    BATCH_ABORTED = "Fatal DB error — aborting prepare batch."
+    RACE_CONDITION = "Concurrent worker beat us to the commit — rolling back batch."
 
     # index
-    INDEX_STARTED       = "Document indexing started."
-    INDEX_SUCCESS       = "Document indexed successfully."
-    LLM_RETRYABLE       = "Retryable LLM error — document marked failed, will retry on next sync."
-    LLM_PERMANENT       = "Permanent LLM error — document marked failed."
-    EMBEDDING_FAILED    = "Embedding error — document marked failed."
-    CHUNKING_OVERFLOW   = "Chunking overflow — document marked failed."
-    UNEXPECTED          = "Unexpected error — document marked failed."
+    INDEX_STARTED = "Document indexing started."
+    INDEX_SUCCESS = "Document indexed successfully."
+    LLM_RETRYABLE = (
+        "Retryable LLM error — document marked failed, will retry on next sync."
+    )
+    LLM_PERMANENT = "Permanent LLM error — document marked failed."
+    EMBEDDING_FAILED = "Embedding error — document marked failed."
+    CHUNKING_OVERFLOW = "Chunking overflow — document marked failed."
+    UNEXPECTED = "Unexpected error — document marked failed."
 
 
 def _format_context(ctx: PipelineLogContext) -> str:
@@ -52,7 +54,9 @@ def _build_message(msg: str, ctx: PipelineLogContext, **extra) -> str:
         return msg
 
 
-def _safe_log(level_fn, msg: str, ctx: PipelineLogContext, exc_info=None, **extra) -> None:
+def _safe_log(
+    level_fn, msg: str, ctx: PipelineLogContext, exc_info=None, **extra
+) -> None:
     # Logging must never raise — a broken log call inside an except block would
     # chain with the original exception and mask it entirely.
     try:
@@ -64,6 +68,7 @@ def _safe_log(level_fn, msg: str, ctx: PipelineLogContext, exc_info=None, **extr
 
 # ── prepare_for_indexing ──────────────────────────────────────────────────────
 
+
 def log_document_queued(ctx: PipelineLogContext) -> None:
     _safe_log(logger.info, LogMessages.DOCUMENT_QUEUED, ctx)
 
@@ -77,7 +82,9 @@ def log_document_requeued(ctx: PipelineLogContext) -> None:
 
 
 def log_doc_skipped_unknown(ctx: PipelineLogContext, exc: Exception) -> None:
-    _safe_log(logger.warning, LogMessages.DOC_SKIPPED_UNKNOWN, ctx, exc_info=exc, error=exc)
+    _safe_log(
+        logger.warning, LogMessages.DOC_SKIPPED_UNKNOWN, ctx, exc_info=exc, error=exc
+    )
 
 
 def log_race_condition(ctx: PipelineLogContext) -> None:
@@ -90,6 +97,7 @@ def log_batch_aborted(ctx: PipelineLogContext, exc: Exception) -> None:
 
 # ── index ─────────────────────────────────────────────────────────────────────
 
+
 def log_index_started(ctx: PipelineLogContext) -> None:
     _safe_log(logger.info, LogMessages.INDEX_STARTED, ctx)