noodlbox

Context Search

Natural language code search

Search your codebase with natural language. Results are ranked by relevance.

Parameters

ParameterTypeRequiredDescription
repositorystringYesRepository name (e.g., "owner/repo")
qstringYesNatural language search query
task_contextstringYesContext about what you're working on
current_goalstringYesYour immediate objective
search_intentionstringYesWhy you're searching and what you plan to do
include_contentbooleanNoInclude full symbol content (default: true)

Context Fields

The context fields help the search algorithm understand your intent:

FieldPurposeExample
task_contextWhat you're working on"Implementing user authentication"
current_goalWhat you want to find"Find login validation logic"
search_intentionWhy you're searching"Understand how auth works to add OAuth"

Example

Ask your agent:

"Find code related to user authentication"

Or provide context for better results:

"I'm adding OAuth support. Find the existing authentication code so I can understand how to integrate with it."

Results

Results include relevant code symbols, matching documentation, and standalone definitions. Matches include source locations and, when requested, signatures and source content.

Tips

  • Be specific: "stripe webhook handler" beats "payment code"
  • Provide context: Better task descriptions = better results
  • Start broad, then narrow: Search "payments", then "refund processing"
  • Use include_content: false for faster responses when you only need locations

On this page