Knowledge completo en contexto: 50K token budget

Budget de 15K dejaba fuera docs críticos (css-js-conventions,
hooks-and-api). Con 42K tokens totales y 128K de contexto,
incluir todo es la mejor estrategia.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

src/context/engine.py

@@ -299,8 +299,8 @@ class ContextEngine:
                 for d in sorted(all_docs, key=lambda d: len(d.content))
             ]
 
-        # Fill token budget with top-ranked docs
-        max_kb_tokens = 15_000
+        # Include ALL docs — 42K tokens fits well within model context (128K)
+        max_kb_tokens = 50_000
         token_budget = max_kb_tokens
         full_docs: list[MemoryDocument] = []