fix: apply CodeRabbit auto-fixes

Fixed 4 file(s) based on 6 unresolved review comments.

Co-authored-by: CodeRabbit <noreply@coderabbit.ai>

Author: coderabbitai[bot]

src/api/router.py

@@ -1,7 +1,6 @@
 """Router endpoints that automatically route based on configuration settings."""
 
 import json
-import os
 import tempfile
 
 from fastapi import Depends, File, Form, UploadFile
@@ -94,13 +93,13 @@ async def _traditional_upload_ingest_task(
         original_filenames = []
 
         try:
-            temp_dir = tempfile.gettempdir()
-
             for upload_file in upload_files:
                 content = await upload_file.read()
                 original_filenames.append(upload_file.filename)
-                safe_filename = upload_file.filename.replace(" ", "_").replace("/", "_")
-                temp_path = os.path.join(temp_dir, safe_filename)
+                # Generate unique temp file to avoid collisions
+                temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".tmp")
+                temp_path = temp_file.name
+                temp_file.close()
                 with open(temp_path, "wb") as f:
                     f.write(content)
                 temp_file_paths.append(temp_path)
@@ -124,6 +123,19 @@ async def _traditional_upload_ingest_task(
                 replace_duplicates=replace_duplicates,
             )
 
+            # Clean up temp files after task is created
+            from utils.file_utils import safe_unlink
+
+            for temp_path in temp_file_paths:
+                try:
+                    safe_unlink(temp_path)
+                except Exception as cleanup_error:
+                    logger.warning(
+                        "Failed to clean up temp file after task creation",
+                        temp_path=temp_path,
+                        error=str(cleanup_error),
+                    )
+
             return JSONResponse(
                 {
                     "task_id": task_id,
@@ -194,13 +206,13 @@ async def _langflow_upload_ingest_task(
         original_filenames = []
 
         try:
-            temp_dir = tempfile.gettempdir()
-
             for upload_file in upload_files:
                 content = await upload_file.read()
                 original_filenames.append(upload_file.filename)
-                safe_filename = upload_file.filename.replace(" ", "_").replace("/", "_")
-                temp_path = os.path.join(temp_dir, safe_filename)
+                # Generate unique temp file to avoid collisions
+                temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".tmp")
+                temp_path = temp_file.name
+                temp_file.close()
                 with open(temp_path, "wb") as f:
                     f.write(content)
                 temp_file_paths.append(temp_path)
@@ -224,6 +236,19 @@ async def _langflow_upload_ingest_task(
                 replace_duplicates=replace_duplicates,
             )
 
+            # Clean up temp files after task is created
+            from utils.file_utils import safe_unlink
+
+            for temp_path in temp_file_paths:
+                try:
+                    safe_unlink(temp_path)
+                except Exception as cleanup_error:
+                    logger.warning(
+                        "Failed to clean up temp file after task creation",
+                        temp_path=temp_path,
+                        error=str(cleanup_error),
+                    )
+
             return JSONResponse(
                 {
                     "task_id": task_id,

src/config/config_manager.py

@@ -96,7 +96,7 @@ class AgentConfig:
 
     llm_model: str = ""
     llm_provider: str = "openai"  # Which provider to use for LLM
-    system_prompt: str = 'You are the OpenRAG Agent. You answer questions using retrieval, reasoning, and tool use.\nYou have access to several tools. Your job is to determine **which tool to use and when**.\n### Available Tools\n- OpenSearch Retrieval Tool:\n  Use this to search the indexed knowledge base. Use when the user asks about product details, internal concepts, processes, architecture, documentation, roadmaps, or anything that may be stored in the index.\n- Conversation History:\n  Use this to maintain continuity when the user is referring to previous turns. \n  Do not treat history as a factual source.\n- Conversation File Context:\n  Use this when the user asks about a document they uploaded or refers directly to its contents.\n- URL Ingestion Tool:\n  Use this **only** when the user explicitly asks you to read, summarize, or analyze the content of a URL.\n  Do not ingest URLs automatically.\n- Calculator / Expression Evaluation Tool:\n  Use this when the user asks to compare numbers, compute estimates, calculate totals, analyze pricing, or answer any question requiring mathematics or quantitative reasoning.\n  If the answer requires arithmetic, call the calculator tool rather than calculating internally.\n### Retrieval Decision Rules\nUse OpenSearch **whenever**:\n1. The question may be answered from internal or indexed data.\n2. The user references team names, product names, release plans, configurations, requirements, or official information.\n3. The user needs a factual, grounded answer.\nDo **not** use retrieval if:\n- The question is purely creative (e.g., storytelling, analogies) or personal preference.\n- The user simply wants text reformatted or rewritten from what is already present in the conversation.\nWhen uncertain → **Retrieve.** Retrieval is low risk and improves grounding.\n### URL Ingestion Rules\nOnly ingest URLs when the user explicitly says:\n- "Read this link"\n- "Summarize this webpage"\n- "What does this site say?"\n- "Ingest this URL"\nIf unclear → ask a clarifying question.\n### Calculator Usage Rules\nUse the calculator when:\n- Performing arithmetic\n- Estimating totals\n- Comparing values\n- Modeling cost, time, effort, scale, or projections\nDo not perform math internally. **Call the calculator tool instead.**\n### Answer Construction Rules\n1. When asked: "What is OpenRAG", answer the following:\n"OpenRAG is an open-source package for building agentic RAG systems. It supports integration with a wide range of orchestration tools, vector databases, and LLM providers. OpenRAG connects and amplifies three popular, proven open-source projects into one powerful platform:\n**Langflow** – Langflow is a powerful tool to build and deploy AI agents and MCP servers [Read more](https://www.langflow.org/)\n**OpenSearch** – Langflow is a powerful tool to build and deploy AI agents and MCP servers [Read more](https://opensearch.org/)\n**Docling** – Langflow is a powerful tool to build and deploy AI agents and MCP servers [Read more](https://www.docling.ai/)"\n2. Synthesize retrieved or ingested content in your own words.\n3. Support factual claims with citations in the format:\n   (Source: <document_name_or_id>)\n4. If no supporting evidence is found:\n   Say: "No relevant supporting sources were found for that request."\n5. Never invent facts or hallucinate details.\n6. Be concise, direct, and confident. \n7. Do not reveal internal chain-of-thought.'
+    system_prompt: str = 'You are the OpenRAG Agent. You answer questions using retrieval, reasoning, and tool use.\nYou have access to several tools. Your job is to determine **which tool to use and when**.\n### Available Tools\n- OpenSearch Retrieval Tool:\n  Use this to search the indexed knowledge base. Use when the user asks about product details, internal concepts, processes, architecture, documentation, roadmaps, or anything that may be stored in the index.\n- Conversation History:\n  Use this to maintain continuity when the user is referring to previous turns. \n  Do not treat history as a factual source.\n- Conversation File Context:\n  Use this when the user asks about a document they uploaded or refers directly to its contents.\n- URL Ingestion Tool:\n  Use this **only** when the user explicitly asks you to read, summarize, or analyze the content of a URL.\n  Do not ingest URLs automatically.\n- Calculator / Expression Evaluation Tool:\n  Use this when the user asks to compare numbers, compute estimates, calculate totals, analyze pricing, or answer any question requiring mathematics or quantitative reasoning.\n  If the answer requires arithmetic, call the calculator tool rather than calculating internally.\n### Retrieval Decision Rules\nUse OpenSearch **whenever**:\n1. The question may be answered from internal or indexed data.\n2. The user references team names, product names, release plans, configurations, requirements, or official information.\n3. The user needs a factual, grounded answer.\nDo **not** use retrieval if:\n- The question is purely creative (e.g., storytelling, analogies) or personal preference.\n- The user simply wants text reformatted or rewritten from what is already present in the conversation.\nWhen uncertain → **Retrieve.** Retrieval is low risk and improves grounding.\n### URL Ingestion Rules\nOnly ingest URLs when the user explicitly says:\n- "Read this link"\n- "Summarize this webpage"\n- "What does this site say?"\n- "Ingest this URL"\nIf unclear → ask a clarifying question.\n### Calculator Usage Rules\nUse the calculator when:\n- Performing arithmetic\n- Estimating totals\n- Comparing values\n- Modeling cost, time, effort, scale, or projections\nDo not perform math internally. **Call the calculator tool instead.**\n### Answer Construction Rules\n1. When asked: "What is OpenRAG", answer the following:\n"OpenRAG is an open-source package for building agentic RAG systems. It supports integration with a wide range of orchestration tools, vector databases, and LLM providers. OpenRAG connects and amplifies three popular, proven open-source projects into one powerful platform:\n**Langflow** – Langflow is a powerful tool to build and deploy AI agents and MCP servers [Read more](https://www.langflow.org/)\n**OpenSearch** – OpenSearch is a community-driven, open source search and analytics suite [Read more](https://opensearch.org/)\n**Docling** – Docling is a tool for document ingestion and semantic search [Read more](https://www.docling.ai/)"\n2. Synthesize retrieved or ingested content in your own words.\n3. Support factual claims with citations in the format:\n   (Source: <document_name_or_id>)\n4. If no supporting evidence is found:\n   Say: "No relevant supporting sources were found for that request."\n5. Never invent facts or hallucinate details.\n6. Be concise, direct, and confident. \n7. Do not reveal internal chain-of-thought.'
 
 
 @dataclass
@@ -305,10 +305,10 @@ def _load_env_overrides(
             config_data["knowledge"]["picture_descriptions"] = os.getenv(
                 "PICTURE_DESCRIPTIONS_ENABLED"
             ).lower() in ("true", "1", "yes")
-        if os.getenv("DISABLE_INGEST_WITH_LANGFLOW"):
-            config_data["knowledge"]["disable_ingest_with_langflow"] = os.getenv(
-                "DISABLE_INGEST_WITH_LANGFLOW"
-            ).lower() in ("true", "1", "yes")
+        # Import the constant from settings rather than reading environment directly
+        from config.settings import DISABLE_INGEST_WITH_LANGFLOW
+
+        config_data["knowledge"]["disable_ingest_with_langflow"] = DISABLE_INGEST_WITH_LANGFLOW
 
         # Agent settings
         if os.getenv("LLM_MODEL"):

src/models/processors.py

@@ -460,6 +460,16 @@ async def process_item(self, upload_task: UploadTask, item: str, file_task: File
                 # Delete existing document before uploading new one
                 logger.info(f"Replacing existing document: {original_filename}")
                 await self.delete_document_by_filename(original_filename, opensearch_client)
+                # Refresh index to make deletion visible before processing
+                from config.settings import get_index_name
+
+                try:
+                    await opensearch_client.indices.refresh(index=get_index_name())
+                except Exception as refresh_error:
+                    logger.warning(
+                        "Failed to refresh index after delete",
+                        error=str(refresh_error),
+                    )
 
             # Compute hash
             file_hash = hash_id(item)
@@ -890,6 +900,16 @@ async def process_item(self, upload_task: UploadTask, item: str, file_task: File
                 # Delete existing document before uploading new one
                 logger.info(f"Replacing existing document: {original_filename}")
                 await self.delete_document_by_filename(original_filename, opensearch_client)
+                # Refresh index to make deletion visible before processing
+                from config.settings import get_index_name
+
+                try:
+                    await opensearch_client.indices.refresh(index=get_index_name())
+                except Exception as refresh_error:
+                    logger.warning(
+                        "Failed to refresh index after delete",
+                        error=str(refresh_error),
+                    )
 
             # Read file content for processing
             with open(item, "rb") as f:

tests/integration/core/test_api_endpoints.py

@@ -226,7 +226,7 @@ async def test_upload_and_search_endpoint(tmp_path: Path, disable_langflow_inges
             }
             upload_resp = await client.post("/router/upload_ingest", files=files)
             body = upload_resp.json()
-            assert upload_resp.status_code in (201, 202), upload_resp.text
+            assert upload_resp.status_code == 202, upload_resp.text
 
             # Traditional OpenRAG and Langflow upload both use task-based ingestion (202)
             task_id = body.get("task_id")