fix(budget): cap per-core contribution + lower auto budget to curb over-selection

Author: nikolay-e

diffctx/src/config/budget.rs

@@ -5,15 +5,24 @@ pub struct BudgetConfig {
     pub auto_multiplier: f64,
     pub auto_min: u32,
     pub auto_max: u32,
+    /// Per-core-fragment ceiling when sizing the auto budget. A core fragment
+    /// that is a whole-file `Chunk` (e.g. a 2000-line unparsed template touched
+    /// by one hunk) would otherwise inflate the budget by its entire byte
+    /// weight, dragging in the whole repo as "context". Capping each core
+    /// fragment's budget contribution decouples "how big are the files I edited"
+    /// from "how much of the repo do I pull in". Does not affect whether the
+    /// changed file is included (it always is) — only the context budget it earns.
+    pub core_token_cap_per_fragment: u32,
 }
 
 impl Default for BudgetConfig {
     fn default() -> Self {
         Self {
             unlimited: 10_000_000,
-            auto_multiplier: 5.0,
+            auto_multiplier: 3.0,
             auto_min: 8_000,
-            auto_max: 124_000,
+            auto_max: 48_000,
+            core_token_cap_per_fragment: 1_500,
         }
     }
 }

diffctx/src/pipeline.rs

@@ -341,7 +341,7 @@ pub fn select_with_params(
             .all_fragments
             .iter()
             .filter(|f| state.core_ids.contains(&f.id))
-            .map(|f| f.token_count)
+            .map(|f| f.token_count.min(BUDGET.core_token_cap_per_fragment))
             .sum();
         let auto = (core_tokens as f64 * BUDGET.auto_multiplier) as u32;
         auto.clamp(BUDGET.auto_min, BUDGET.auto_max)