Set search limit to 10

CHANGELOG.md

@@ -4,6 +4,7 @@
 ### Changed
 
 - **QA search cap**: Replace dead `max_iterations`/`max_concurrency` config with `max_searches` (default: 3). The QA agent now enforces a per-run search limit, reducing average response time from ~30s to ~15s while maintaining accuracy. The limit resets per agent run so toolsets can be safely reused.
+- **Default search limit**: Increased from 5 to 10 results per search query for better coverage.
 
 ## [0.33.1] - 2026-03-06
 

docs/configuration/index.md

@@ -98,7 +98,7 @@ research:
   max_concurrency: 1
 
 search:
-  limit: 5                     # Default number of results to return
+  limit: 10                    # Default number of results to return
   context_radius: 0            # DocItems before/after to include for text content
   max_context_items: 10        # Maximum items in expanded context
   max_context_chars: 10000     # Maximum characters in expanded context

docs/configuration/qa-research.md

@@ -6,13 +6,13 @@ Configure search behavior and context expansion:
 
 ```yaml
 search:
-  limit: 5                     # Default number of results to return
+  limit: 10                    # Default number of results to return
   context_radius: 0            # DocItems before/after to include for text content
   max_context_items: 10        # Maximum items in expanded context
   max_context_chars: 10000     # Maximum characters in expanded context
 ```
 
-- **limit**: Default number of search results to return when no limit is specified. Used by CLI, MCP server, QA, and research workflows. Default: 5
+- **limit**: Default number of search results to return when no limit is specified. Used by CLI, MCP server, QA, and research workflows. Default: 10
 - **context_radius**: For text content (paragraphs), includes N DocItems before and after. Set to 0 to disable expansion (default).
 - **max_context_items**: Limits how many document items (paragraphs, list items, etc.) can be included in expanded context. Default: 10.
 - **max_context_chars**: Hard limit on total characters in expanded content. Default: 10000.

haiku_rag_slim/haiku/rag/config/models.py

@@ -172,7 +172,7 @@ class ProcessingConfig(BaseModel):
 
 
 class SearchConfig(BaseModel):
-    limit: int = 5
+    limit: int = 10
     context_radius: int = 0
     max_context_items: int = 10
     max_context_chars: int = 10000