From 91272ddfc457755590305d75b2a49aadcf9d56b1 Mon Sep 17 00:00:00 2001
From: oabrivard <olivier@abrivard.fr>
Date: Thu, 26 Mar 2026 15:01:37 +0100
Subject: [PATCH] feat: dynamic summary length and body snippet size based on
 setting

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---
 backend/src/services/prompts.rs   | 25 +++++++++++++++++++++++--
 backend/src/services/synthesis.rs | 18 ++++++++++++++----
 2 files changed, 37 insertions(+), 6 deletions(-)

diff --git a/backend/src/services/prompts.rs b/backend/src/services/prompts.rs
index 8149a54..9f93ee0 100644
--- a/backend/src/services/prompts.rs
+++ b/backend/src/services/prompts.rs
@@ -150,6 +150,7 @@ pub fn build_article_classify_prompt(
     title: &str,
     body_snippet: &str,
     categories: &[String],
+    summary_length: i32,
 ) -> (String, String) {
     let system_prompt =
         "Tu es un assistant qui analyse des articles d'actualite. \
@@ -163,6 +164,12 @@ pub fn build_article_classify_prompt(
         .collect::<Vec<_>>()
         .join("\n");
 
+    let summary_instruction = match summary_length {
+        1 => "Genere un titre clair et un resume de 3 a 4 lignes.",
+        2 => "Genere un titre clair et un resume de 6 a 8 lignes.",
+        _ => "Genere un titre clair et un resume detaille de 12 a 15 lignes.",
+    };
+
     let user_prompt = format!(
         "Voici un article d'actualite.\n\n\
          Titre : {title}\n\n\
@@ -170,11 +177,12 @@ pub fn build_article_classify_prompt(
          Categories disponibles :\n{categories}\n\n\
          Classe cet article dans la categorie la plus appropriee.\n\
          Si aucune categorie ne correspond, utilise \"Autre\".\n\
-         Genere un titre clair et un resume de 4 a 5 lignes.\n\
+         {summary_instruction}\n\
          Si le titre fourni est vide, genere un titre a partir du contenu.",
         title = if title.is_empty() { "(pas de titre)" } else { title },
         body = body_snippet,
         categories = categories_list,
+        summary_instruction = summary_instruction,
     );
 
     (system_prompt, user_prompt)
@@ -375,6 +383,7 @@ mod tests {
             "GPT-5 Released",
             "OpenAI released GPT-5 today",
             &["AI News".into(), "Autre".into()],
+            3,
         );
         assert!(user.contains("GPT-5 Released"));
         assert!(user.contains("AI News"));
@@ -384,8 +393,20 @@ mod tests {
 
     #[test]
     fn article_classify_prompt_handles_empty_title() {
-        let (_, user) = build_article_classify_prompt("", "Some content", &["Tech".into(), "Autre".into()]);
+        let (_, user) = build_article_classify_prompt("", "Some content", &["Tech".into(), "Autre".into()], 3);
         assert!(user.contains("(pas de titre)"));
     }
 
+    #[test]
+    fn article_classify_prompt_short_summary() {
+        let (_, user) = build_article_classify_prompt("Title", "Content", &["AI".into()], 1);
+        assert!(user.contains("3 a 4 lignes"));
+    }
+
+    #[test]
+    fn article_classify_prompt_detailed_summary() {
+        let (_, user) = build_article_classify_prompt("Title", "Content", &["AI".into()], 3);
+        assert!(user.contains("12 a 15 lignes"));
+    }
+
 }
diff --git a/backend/src/services/synthesis.rs b/backend/src/services/synthesis.rs
index 6afd49f..9bd2180 100644
--- a/backend/src/services/synthesis.rs
+++ b/backend/src/services/synthesis.rs
@@ -484,7 +484,12 @@ pub async fn run_generation_inner(
                 let model = Arc::clone(&model_research);
                 let schema = Arc::clone(&classify_schema);
                 let cats = Arc::clone(&classification_categories);
-                let body_snippet: String = body_text.chars().take(500).collect();
+                let snippet_size = match settings.summary_length {
+                    1 => 500,
+                    2 => 2000,
+                    _ => 4000,
+                };
+                let body_snippet: String = body_text.chars().take(snippet_size).collect();
                 let title = page_title.clone();
                 let url = final_url.clone();
                 let su = source_url.clone();
@@ -492,7 +497,7 @@ pub async fn run_generation_inner(
                 let uid = user_id;
                 let jid = job_id;
 
-                let (sys, usr) = crate::services::prompts::build_article_classify_prompt(&title, &body_snippet, &cats);
+                let (sys, usr) = crate::services::prompts::build_article_classify_prompt(&title, &body_snippet, &cats, settings.summary_length);
 
                 classify_set.spawn(async move {
                     let llm_start = std::time::Instant::now();
@@ -662,14 +667,19 @@ pub async fn run_generation_inner(
                         let model = Arc::clone(&model_research);
                         let schema = Arc::clone(&classify_schema);
                         let cats = Arc::clone(&classification_categories);
-                        let body_snippet: String = body_text.chars().take(500).collect();
+                        let snippet_size = match settings.summary_length {
+                            1 => 500,
+                            2 => 2000,
+                            _ => 4000,
+                        };
+                        let body_snippet: String = body_text.chars().take(snippet_size).collect();
                         let title = page_title.clone();
                         let url = final_url.clone();
                         let pool = state.pool.clone();
                         let uid = user_id;
                         let jid = job_id;
 
-                        let (sys, usr) = crate::services::prompts::build_article_classify_prompt(&title, &body_snippet, &cats);
+                        let (sys, usr) = crate::services::prompts::build_article_classify_prompt(&title, &body_snippet, &cats, settings.summary_length);
 
                         classify_set.spawn(async move {
                             let llm_start = std::time::Instant::now();