fix(memory): default context_min_score to 0.0 so FTS5 BM25 results aren't dropped on small corpora (#286)

SQLite FTS5 BM25 scores collapse toward zero on small corpora — when
every indexed document contains the query term, IDF approaches zero so
scores return ~1e-6. The default context_min_score = 0.1 silently
filters out every result before injection, so memory is stored but
never reaches the model on a fresh install.

Lowering both defaults to 0.0 lets retrieved context flow through;
users who want strict filtering can still set [memory]
context_min_score in config.toml.

Closes #262

src/openjarvis/core/config.py

@@ -764,7 +764,7 @@ class StorageConfig:
     default_backend: str = "sqlite"
     db_path: str = str(DEFAULT_CONFIG_DIR / "memory.db")
     context_top_k: int = 5
-    context_min_score: float = 0.1
+    context_min_score: float = 0.0
     context_max_tokens: int = 2048
     chunk_size: int = 512
     chunk_overlap: int = 64

src/openjarvis/tools/storage/context.py

@@ -16,7 +16,7 @@ class ContextConfig:
 
     enabled: bool = True
     top_k: int = 5
-    min_score: float = 0.1
+    min_score: float = 0.0
     max_context_tokens: int = 2048