feat(context): enhance performance, caching, and settings management

- Replace hard-coded limits with configurable settings (e.g., cache memory size, truncation strategy, relevance settings).
- Optimize parallel execution in token counting, scoring, and reranking for source diversity.
- Improve caching logic:
  - Add per-context locks for safe parallel scoring.
  - Reuse precomputed fingerprints for cache efficiency.
- Make truncation, scoring, and ranker behaviors fully configurable via settings.
- Add support for middle truncation, context hash-based hashing, and dynamic token limiting.
- Refactor methods for scalability and better error handling.

Tests: Updated all affected components with additional test cases.

backend/app/services/context/engine.py

@@ -214,6 +214,7 @@ class ContextEngine:
             contexts.extend(custom_contexts)
 
         # Check cache if enabled
+        fingerprint: str | None = None
         if use_cache and self._cache.is_enabled:
             fingerprint = self._cache.compute_fingerprint(contexts, query, model)
             cached = await self._cache.get_assembled(fingerprint)
@@ -232,9 +233,8 @@ class ContextEngine:
             format_output=format_output,
         )
 
-        # Cache result if enabled
-        if use_cache and self._cache.is_enabled:
-            fingerprint = self._cache.compute_fingerprint(contexts, query, model)
+        # Cache result if enabled (reuse fingerprint computed above)
+        if use_cache and self._cache.is_enabled and fingerprint is not None:
             await self._cache.set_assembled(fingerprint, result)
 
         return result
@@ -275,7 +275,8 @@ class ContextEngine:
             )
 
             contexts = []
-            for chunk in result.data.get("results", []):
+            results = result.data.get("results", []) if isinstance(result.data, dict) else []
+            for chunk in results:
                 contexts.append(
                     KnowledgeContext(
                         content=chunk.get("content", ""),