Lower search.max_context_chars default to 5000

CHANGELOG.md

@@ -4,6 +4,7 @@
 ### Changed
 
 - Unknown `reranking.model.provider` raises `ValueError` instead of silently disabling reranking.
+- `search.max_context_chars` default lowered from 10000 to 5000.
 
 ### Removed
 

docs/configuration/index.md

@@ -110,7 +110,7 @@ qa:
 
 search:
   limit: 10                    # Default number of results to return
-  max_context_chars: 10000     # Maximum characters in expanded context
+  max_context_chars: 5000     # Maximum characters in expanded context
   vector_index_metric: cosine  # cosine, l2, or dot
   vector_refine_factor: 30
 

docs/configuration/qa.md

@@ -7,11 +7,11 @@ Configure search behavior and context expansion:
 ```yaml
 search:
   limit: 10                    # Default number of results to return
-  max_context_chars: 10000     # Maximum characters in expanded context
+  max_context_chars: 5000     # Maximum characters in expanded context
 ```
 
 - **limit**: Default number of search results to return when no limit is specified. Used by CLI, MCP server, and QA. Default: 10
-- **max_context_chars**: Hard limit on total characters in expanded content. Default: 10000.
+- **max_context_chars**: Hard limit on total characters in expanded content. Default: 5000.
 
 Context expansion is automatic and section-aware. For structured documents (with section headers), expansion includes the entire section containing the match. For sections that exceed the budget or are too small (e.g., a title+authors area), expansion grows outward item-by-item from the match center, skipping noise labels (footnotes, page headers). This naturally crosses into adjacent sections until the budget is filled. Picture and table matches are exempt: they return their enclosing section as-is and never cross section boundaries. For unstructured documents, expansion grows outward item-by-item. Results without `doc_item_refs` (e.g., custom chunks passed to `import_document`) pass through unexpanded.
 

docs/python.md

@@ -302,7 +302,7 @@ Context expansion is automatic and section-aware. For structured documents (with
 
 Configuration:
 
-- **search.max_context_chars**: Maximum characters in expanded context. Default: 10000.
+- **search.max_context_chars**: Maximum characters in expanded context. Default: 5000.
 
 **Smart Merging**: When expanded results overlap within the same document, they are automatically merged into a single result with continuous content and the highest relevance score.
 

docs/skills/rag.md

@@ -165,7 +165,7 @@ qa:
 
 search:
   limit: 5
-  max_context_chars: 10000
+  max_context_chars: 5000
 ```
 
 See [Search and question answering](../configuration/qa.md) for every knob.

haiku_rag_slim/haiku/rag/config/models.py

@@ -229,7 +229,7 @@ class ProcessingConfig(BaseModel):
 
 class SearchConfig(BaseModel):
     limit: int = 5
-    max_context_chars: int = 10000
+    max_context_chars: int = 5000
     vector_index_metric: Literal["cosine", "l2", "dot"] = "cosine"
     vector_refine_factor: int = 30