feat: reduce context 65k -> 59k

Author: KacemMathlouthi

backend/app/services/vcelldb_service.py

@@ -344,6 +344,7 @@ async def fetch_publications() -> List[dict]:
                         sanitized_pub = pub.copy()
                         sanitized_pub.pop('wittid', None)
                         sanitized_pub.pop('date', None)
+                        sanitized_pub.pop('url', None)
                         sanitized_pub.pop('endnoteid', None)
                         sanitized_publications.append(sanitized_pub)
                     else:

backend/app/utils/system_prompt.py

@@ -21,7 +21,7 @@
 * When the user query is about: "Describe parameters", "Describe species", "Describe reactions", or "What Applications are used?" — specifically in the context of model analysis: Make sure to use the `get_vcml_file` tool to retrieve the VCML file for the biomodel. This file contains detailed information about the model's structure and behavior, which is essential for providing accurate descriptions of parameters, species, reactions, and applications. Use also the "fetch_biomodels" tool to gather additional context about the biomodel, and Try when asked these questions to focus on the asked aspects,  Do not provide general summaries, model structure, or unrelated metadata unless explicitly requested. Keep the focus tightly on the requested element and be as technically precise as possible. Elaborate as much as you can on the requested aspect, providing detailed descriptions and explanations based on the VCML content.
 
 ### Publications Guidelines
-* If asked for publications, research papers, pubmed articles, etc. use the `fetch_publications` tool. After fetching, extract the relevant information, filter by user's specific needs, format publication links using markdown `[Title](URL)`, provide context (date, authors, description), and clearly communicate if no relevant publications are found.
-* When using the `fetch_publications` tool, the response contains the full list of VCell related publications with fields: `pubKey` (unique identifier), `title`, `authors` (array), `year`, `citation` (full citation string in journal format), `pubmedid` (PubMed ID), `doi` (DOI link to the publication), `url` (Publication URL), `biomodelReferences` (array of related biomodels), and `mathmodelReferences` (array of related mathematical models).
+* If asked for publications, research papers, pubmed articles, etc. use the `fetch_publications` tool. After fetching, extract the relevant information, filter by user's specific needs, format publication links using markdown `[Title](DOI_URL)`, provide context (date, authors, description), and clearly communicate if no relevant publications are found.
+* When using the `fetch_publications` tool, the response contains the full list of VCell related publications with fields: `pubKey` (unique identifier), `title`, `authors` (array), `year`, `citation` (full citation string in journal format), `pubmedid` (PubMed ID), `doi` (DOI link to the publication), `biomodelReferences` (array of related biomodels), and `mathmodelReferences` (array of related mathematical models).
 * When presenting publications, always provide elaborate, fact-based responses based solely on the available tool results.
 """