Revert unneeded changes to AGENTS and evals, and fix weird azd env var name

Author: pamelafox

AGENTS.md

@@ -17,7 +17,6 @@ If necessary, edit this file to ensure it accurately reflects the current state
       * app/backend/approaches/prompts/chat_query_rewrite.prompty: Prompt used to rewrite the query based off search history into a better search query
       * app/backend/approaches/prompts/chat_query_rewrite_tools.json: Tools used by the query rewriting prompt
       * app/backend/approaches/prompts/chat_answer_question.prompty: Prompt used by the Chat approach to actually answer the question based off sources
-      * Agentic retrieval responses populate `DataPoints.citation_activity_details` so the frontend can link citations to query plan activities and display the related step metadata provided by the backend.
     * app/backend/prepdocslib: Contains the document ingestion library used by both local and cloud ingestion
       * app/backend/prepdocslib/blobmanager.py: Manages uploads to Azure Blob Storage
       * app/backend/prepdocslib/cloudingestionstrategy.py: Builds the Azure AI Search indexer and skillset for the cloud ingestion pipeline
@@ -35,14 +34,12 @@ If necessary, edit this file to ensure it accurately reflects the current state
       * app/backend/prepdocslib/parser.py: Base parser interface
       * app/backend/prepdocslib/pdfparser.py: Parses PDFs using Azure Document Intelligence or local parser
       * app/backend/prepdocslib/searchmanager.py: Manages Azure AI Search index creation and updates
-        * Agent knowledge bases are created per source combination: base agent uses only the index, with `-with-web`,
-          `-with-sp`, and `-with-web-and-sp` variants provisioned when optional sources are enabled.
       * app/backend/prepdocslib/servicesetup.py: Shared service setup helpers for OpenAI, embeddings, blob storage, etc.
       * app/backend/prepdocslib/strategy.py: Base strategy interface for document ingestion
       * app/backend/prepdocslib/textparser.py: Parses plain text and markdown files
       * app/backend/prepdocslib/textprocessor.py: Processes text chunks for cloud ingestion (merges figures, generates embeddings)
       * app/backend/prepdocslib/textsplitter.py: Splits text into chunks using different strategies
-    * app/backend/app.py: The main entry point for the backend application. Registers the default and optional (with-web, with-sp, with-web-and-sp) knowledge base clients in the app config for approaches that rely on agentic retrieval.
+    * app/backend/app.py: The main entry point for the backend application.
   * app/functions: Azure Functions used for cloud ingestion custom skills (document extraction, figure processing, text processing). Each function bundles a synchronized copy of `prepdocslib`; run `python scripts/copy_prepdocslib.py` to refresh the local copies if you modify the library.
   * app/frontend: Contains the React frontend code, built with TypeScript, built with vite.
     * app/frontend/src/api: Contains the API client code for communicating with the backend.

docs/agentic_retrieval.md

@@ -33,7 +33,7 @@ This repository includes an optional feature that uses [agentic retrieval from A
    Override the default by setting the following environment variable:
 
    ```shell
-   azd env set AZURE_SEARCH_KNOWLEDGEBASE_NAME_RETRIEVAL_REASONING_EFFORT low
+   azd env set AZURE_SEARCH_KNOWLEDGEBASE_RETRIEVAL_REASONING_EFFORT low
    ```
 
    Use `minimal` for the lightest planning, `low` for additional query expansion, or `medium` for the most exhaustive (and most expensive) retrieval plans.

evals/evaluate_config_multimodal.json

@@ -23,7 +23,7 @@
             "send_text_sources": true,
             "send_image_sources": true,
             "language": "en",
-            "use_agentic_knowledgebase": false,
+            "use_agentic_retrieval": false,
             "seed": 1
         }
     },

evals/results/baseline-ask/config.json

@@ -24,7 +24,7 @@
             "send_text_sources": true,
             "send_image_sources": true,
             "language": "en",
-            "use_agentic_knowledgebase": false,
+            "use_agentic_retrieval": false,
             "seed": 1
         }
     },

evals/results/baseline-ask/evaluate_parameters.json

@@ -24,7 +24,7 @@
             "send_text_sources": true,
             "send_image_sources": true,
             "language": "en",
-            "use_agentic_knowledgebase": false,
+            "use_agentic_retrieval": false,
             "seed": 1
         }
     },

evals/results/gpt5-emb3l/config.json

@@ -23,7 +23,7 @@
             "use_gpt4v": false,
             "gpt4v_input": "textAndImages",
             "language": "en",
-            "use_agentic_knowledgebase": false,
+            "use_agentic_retrieval": false,
             "seed": 1
         }
     },

evals/results/gpt5-emb3l/evaluate_parameters.json

@@ -23,7 +23,7 @@
             "use_gpt4v": false,
             "gpt4v_input": "textAndImages",
             "language": "en",
-            "use_agentic_knowledgebase": false,
+            "use_agentic_retrieval": false,
             "seed": 1
         }
     },

evals/results/gpt5mini-emb3l-2/config.json

@@ -23,7 +23,7 @@
             "use_gpt4v": false,
             "gpt4v_input": "textAndImages",
             "language": "en",
-            "use_agentic_knowledgebase": false,
+            "use_agentic_retrieval": false,
             "seed": 1
         }
     },

evals/results/gpt5mini-emb3l-2/evaluate_parameters.json

@@ -23,7 +23,7 @@
             "use_gpt4v": false,
             "gpt4v_input": "textAndImages",
             "language": "en",
-            "use_agentic_knowledgebase": false,
+            "use_agentic_retrieval": false,
             "seed": 1
         }
     },

evals/results/gpt5mini-emb3l/config.json

@@ -23,7 +23,7 @@
             "use_gpt4v": false,
             "gpt4v_input": "textAndImages",
             "language": "en",
-            "use_agentic_knowledgebase": false,
+            "use_agentic_retrieval": false,
             "seed": 1
         }
     },