Refactor logging statements to use f-strings for improved readability and consistency across the codebase. This change enhances the clarity of log messages by directly embedding variable values, making it easier to trace and debug application behavior.

python/ebook_search/api/bm25_tasks.py

@@ -36,10 +36,7 @@ def schedule_bm25_refresh(app: FastAPI) -> None:
         app.state.bm25_refresh_task = loop.create_task(refresh_bm25_for_app(app))
 
     app.state.bm25_refresh_timer = loop.call_later(app.state.config.bm25_refresh_delay_seconds, start_refresh)
-    logger.info(
-        "ebook_bm25_refresh_scheduled delay_seconds=%s",
-        app.state.config.bm25_refresh_delay_seconds,
-    )
+    logger.info(f"ebook_bm25_refresh_scheduled {app.state.config.bm25_refresh_delay_seconds=}")
 
 
 def cancel_bm25_refresh(app: FastAPI) -> None:

python/ebook_search/api/judge_tasks.py

@@ -65,12 +65,12 @@ def start_book_phrase_judgment(app: FastAPI, background_tasks: BackgroundTasks,
     """
     state = get_judge_task_state(app)
     if source_id in state.running_book_ids:
-        logger.info("ebook_book_phrase_judgment_already_running source_id=%s", source_id)
+        logger.info(f"ebook_book_phrase_judgment_already_running {source_id=}")
         return False
     state.running_book_ids.add(source_id)
     state.outcome_messages.pop(source_id, None)
     background_tasks.add_task(judge_book_phrases_for_app, app, source_id)
-    logger.info("ebook_book_phrase_judgment_queued source_id=%s", source_id)
+    logger.info(f"ebook_book_phrase_judgment_queued {source_id=}")
     return True
 
 
@@ -85,12 +85,8 @@ async def judge_book_phrases_for_app(app: FastAPI, source_id: int) -> None:
     try:
         result = await judge_candidate_phrases_for_books(app.state.engine, app.state.config, source_ids=[source_id])
         logger.info(
-            "ebook_book_phrase_judgment_complete source_id=%s judged=%s protected=%s mentions=%s failed=%s",
-            source_id,
-            result.candidates_judged,
-            result.protected_phrases,
-            result.phrase_mentions,
-            result.books_failed,
+            f"ebook_book_phrase_judgment_complete {source_id=} {result.candidates_judged=} {result.protected_phrases=} "
+            f"{result.phrase_mentions=} {result.books_failed=}"
         )
         if result.books_failed:
             message = "Judging failed; see server logs for details"
@@ -99,7 +95,7 @@ async def judge_book_phrases_for_app(app: FastAPI, source_id: int) -> None:
                 f"Judged {result.candidates_judged} candidates; {result.protected_phrases} protected phrases promoted"
             )
     except Exception:
-        logger.exception("ebook_book_phrase_judgment_task_failed source_id=%s", source_id)
+        logger.exception(f"ebook_book_phrase_judgment_task_failed {source_id=}")
         message = "Judging failed; see server logs for details"
     state.running_book_ids.discard(source_id)
     state.outcome_messages[source_id] = message

python/ebook_search/api/main.py

@@ -37,16 +37,9 @@ async def lifespan(app: FastAPI) -> AsyncIterator[None]:
     config = load_config()
     app.state.config = config
     logger.info(
-        "ebook_search_config_loaded top_k=%s embedding_model=%s embedding_base_url=%s vllm_base_url=%s "
-        "rerank_enabled=%s phrase_matching_enabled=%s answer_enabled=%s library_paths=%s",
-        config.top_k,
-        config.embedding_model,
-        config.embedding_base_url,
-        config.vllm_base_url,
-        config.rerank.enabled,
-        config.phrase_matching_enabled,
-        config.answer_enabled,
-        len(config.library_paths),
+        f"ebook_search_config_loaded {config.top_k=} {config.embedding_model=} {config.embedding_base_url=} "
+        f"{config.vllm_base_url=} {config.rerank.enabled=} {config.phrase_matching_enabled=} {config.answer_enabled=} "
+        f"library_paths={len(config.library_paths)}"
     )
     if not config.library_paths:
         logger.warning("ebook_search_no_library_paths_configured")

python/ebook_search/api/routes/admin.py

@@ -32,10 +32,8 @@ async def admin(request: Request, config: AppConfig, session: AsyncDbSession) ->
     stats = await embedding_model_stats(session)
     phrase_stats = await corpus_phrase_stats(session)
     logger.info(
-        "ebook_admin_page_loaded models=%s candidate_phrases=%s protected_phrases=%s",
-        len(stats),
-        phrase_stats.candidate_phrases,
-        phrase_stats.protected_phrases,
+        f"ebook_admin_page_loaded models={len(stats)} {phrase_stats.candidate_phrases=} "
+        f"{phrase_stats.protected_phrases=}"
     )
     return templates.TemplateResponse(
         request,
@@ -54,7 +52,7 @@ async def scan_library(request: Request, config: AppConfig, session: AsyncDbSess
         logger.exception("ebook_admin_scan_failed")
         return templates.TemplateResponse(request, "partials/error.html", {"message": str(error)}, status_code=500)
 
-    logger.info("ebook_admin_scan_complete changed_files=%s", count)
+    logger.info(f"ebook_admin_scan_complete {count=}")
     if count > 0:
         schedule_bm25_refresh(request.app)
     return templates.TemplateResponse(request, "partials/admin_status.html", {"message": f"Indexed {count} EPUBs"})
@@ -70,10 +68,7 @@ async def generate_all_phrases(request: Request, config: AppConfig, engine: AppE
         return templates.TemplateResponse(request, "partials/error.html", {"message": str(error)}, status_code=500)
 
     logger.info(
-        "ebook_admin_generate_phrases_complete books_seen=%s books_built=%s candidates=%s",
-        result.books_seen,
-        result.books_built,
-        result.candidate_phrases,
+        f"ebook_admin_generate_phrases_complete {result.books_seen=} {result.books_built=} {result.candidate_phrases=}"
     )
     return templates.TemplateResponse(
         request,
@@ -136,14 +131,8 @@ async def run_phrase_judgment(
         return templates.TemplateResponse(request, "partials/error.html", {"message": str(error)}, status_code=500)
 
     logger.info(
-        "ebook_admin_judge_phrases_complete books_seen=%s books_judged=%s books_failed=%s candidates_judged=%s "
-        "protected=%s mentions=%s",
-        result.books_seen,
-        result.books_judged,
-        result.books_failed,
-        result.candidates_judged,
-        result.protected_phrases,
-        result.phrase_mentions,
+        f"ebook_admin_judge_phrases_complete {result.books_seen=} {result.books_judged=} {result.books_failed=} "
+        f"{result.candidates_judged=} {result.protected_phrases=} {result.phrase_mentions=}"
     )
     return templates.TemplateResponse(
         request,
@@ -174,7 +163,7 @@ async def embed_missing(
         logger.exception("ebook_admin_embed_missing_failed")
         return templates.TemplateResponse(request, "partials/error.html", {"message": str(error)}, status_code=500)
 
-    logger.info("ebook_admin_embed_missing_complete chunks=%s", count)
+    logger.info(f"ebook_admin_embed_missing_complete {count=}")
     return templates.TemplateResponse(
         request,
         "partials/admin_status.html",
@@ -200,18 +189,9 @@ async def embed_all(
             await session.commit()
             total += count
             batches += 1
-            logger.info(
-                "ebook_admin_embed_all_batch_complete batch=%s chunks=%s total_chunks=%s",
-                batches,
-                count,
-                total,
-            )
+            logger.info(f"ebook_admin_embed_all_batch_complete {batches=} {count=} {total=}")
     except Exception as error:
-        logger.exception(
-            "ebook_admin_embed_all_failed batches=%s chunks=%s",
-            batches,
-            total,
-        )
+        logger.exception(f"ebook_admin_embed_all_failed {batches=} {total=}")
         return templates.TemplateResponse(
             request,
             "partials/error.html",
@@ -219,7 +199,7 @@ async def embed_all(
             status_code=500,
         )
 
-    logger.info("ebook_admin_embed_all_complete batches=%s chunks=%s", batches, total)
+    logger.info(f"ebook_admin_embed_all_complete {batches=} {total=}")
     return templates.TemplateResponse(
         request,
         "partials/admin_status.html",

python/ebook_search/api/routes/health.py

@@ -60,14 +60,7 @@ async def ready(config: AppConfig, session: AsyncDbSession, client: AppHttpClien
         status = "ready"
         status_code = HTTPStatus.OK
 
-    logger.info(
-        "ebook_ready_check status=%s database=%s embedding=%s chat=%s bm25=%s",
-        status,
-        database_ok,
-        embedding_ok,
-        chat_status,
-        bm25_status,
-    )
+    logger.info(f"ebook_ready_check {status=} {database_ok=} {embedding_ok=} {chat_status=} {bm25_status=}")
     return JSONResponse(content={"status": status, "checks": checks}, status_code=status_code)
 
 
@@ -83,7 +76,7 @@ async def check_database(session: AsyncSession) -> bool:
     try:
         await session.execute(select(literal(1)))
     except SQLAlchemyError as error:
-        logger.warning("ebook_ready_database_unavailable error=%s", error)
+        logger.warning(f"ebook_ready_database_unavailable {error=}")
         return False
     return True
 

python/ebook_search/api/routes/page.py

@@ -36,7 +36,7 @@ async def index(request: Request, config: AppConfig) -> HTMLResponse:
 async def books(request: Request, session: AsyncDbSession) -> HTMLResponse:
     """Render the indexed books page."""
     sources = list((await session.scalars(select(EbookSource).order_by(EbookSource.title))).all())
-    logger.info("ebook_books_page_loaded count=%s", len(sources))
+    logger.info(f"ebook_books_page_loaded count={len(sources)}")
     return templates.TemplateResponse(request, "books.html", {"sources": sources})
 
 
@@ -134,14 +134,8 @@ async def book_detail(source_id: int, request: Request, session: AsyncDbSession)
         candidates = []
         protected_phrases = []
     logger.info(
-        "ebook_book_detail_loaded source_id=%s found=%s chapters=%s chunks=%s candidates=%s judged=%s protected=%s",
-        source_id,
-        source is not None,
-        chapter_count,
-        chunk_count,
-        candidate_count,
-        judged_candidate_count,
-        protected_count,
+        f"ebook_book_detail_loaded {source_id=} found={source is not None} {chapter_count=} {chunk_count=} "
+        f"{candidate_count=} {judged_candidate_count=} {protected_count=}"
     )
     return templates.TemplateResponse(
         request,
@@ -173,14 +167,9 @@ async def recalculate_book_phrases(source_id: int, config: AppConfig, session: A
     except ValueError as error:
         raise HTTPException(status_code=409, detail=str(error)) from error
     logger.info(
-        "ebook_book_phrase_recalculation_complete source_id=%s candidates=%s deleted_candidates=%s "
-        "deleted_protected=%s deleted_aliases=%s deleted_mentions=%s",
-        source_id,
-        result.candidate_phrases,
-        result.deleted_candidates,
-        result.deleted_protected_phrases,
-        result.deleted_aliases,
-        result.deleted_mentions,
+        f"ebook_book_phrase_recalculation_complete {source_id=} {result.candidate_phrases=} "
+        f"{result.deleted_candidates=} {result.deleted_protected_phrases=} {result.deleted_aliases=} "
+        f"{result.deleted_mentions=}"
     )
     return RedirectResponse(
         url=f"/books/{source_id}?phrases_recalculated={result.candidate_phrases}",
@@ -201,5 +190,5 @@ async def judge_book_phrases(
         raise HTTPException(status_code=404, detail="Book not found")
 
     started = start_book_phrase_judgment(request.app, background_tasks, source.id)
-    logger.info("ebook_book_phrase_judgment_requested source_id=%s started=%s", source_id, started)
+    logger.info(f"ebook_book_phrase_judgment_requested {source_id=} {started=}")
     return RedirectResponse(url=f"/books/{source_id}", status_code=303)

python/ebook_search/api/routes/search.py

@@ -49,9 +49,8 @@ async def build_answer(
 
     if not is_confident(response.results, config):
         logger.info(
-            "ebook_answer_low_confidence confidence=%.4f threshold=%.4f",
-            retrieval_confidence(response.results),
-            config.min_retrieval_confidence,
+            f"ebook_answer_low_confidence confidence={retrieval_confidence(response.results):.4f} "
+            f"{config.min_retrieval_confidence=:.4f}"
         )
         answer = (
             "Retrieval confidence is low for this query, so answer generation was skipped. "
@@ -62,18 +61,14 @@ async def build_answer(
     try:
         answer = await answer_query(client, query, response.results, config)
     except RuntimeError as error:
-        logger.warning("ebook_answer_request_failed_falling_back error=%s", error)
+        logger.warning(f"ebook_answer_request_failed_falling_back {error=}")
         return "Answer generation failed. Source chunks are still shown below.", False, None
 
     citation_report = None
     if config.validate_citations_enabled and response.results:
         citation_report = validate_citations(answer, len(response.results))
         if citation_report.invalid or not citation_report.grounded:
-            logger.warning(
-                "ebook_answer_citation_issue invalid=%s grounded=%s",
-                citation_report.invalid,
-                citation_report.grounded,
-            )
+            logger.warning(f"ebook_answer_citation_issue {citation_report.invalid=} {citation_report.grounded=}")
     return answer, False, citation_report
 
 
@@ -110,12 +105,10 @@ async def search(
     )
 
     for step in response.timings:
-        logger.info("ebook_search_timing step=%r runtime_ms=%.1f", step.name, step.duration_ms)
+        logger.info(f"ebook_search_timing {step.name=} {step.duration_ms=:.1f}")
     logger.info(
-        "ebook_search_request_complete results=%s rank_label=%s runtime_ms=%.1f",
-        len(response.results),
-        response.rank_label,
-        response.total_runtime_ms,
+        f"ebook_search_request_complete results={len(response.results)} {response.rank_label=} "
+        f"{response.total_runtime_ms=:.1f}"
     )
     return templates.TemplateResponse(
         request,