From e138c0277e15228a98c1d79eb104b05dac4d1f85 Mon Sep 17 00:00:00 2001
From: Julian lechner <j.lechner@sobit.at>
Date: Thu, 1 Oct 2026 13:13:04 +0200
Subject: [PATCH] feat(retrieval): index markup, style, SQL, and project files

Add HTML, CSS, SCSS, XAML, SQL, XML, project, Razor, Kotlin, Gradle, and
module JavaScript files with SQL and Kotlin symbols, and rebuild the index.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---
 scripts/tests/test-retrieval-server.py |  2 ++
 shared/retrieval/server.py             | 15 +++++++++++----
 2 files changed, 13 insertions(+), 4 deletions(-)

diff --git a/scripts/tests/test-retrieval-server.py b/scripts/tests/test-retrieval-server.py
index 9194b0e..1d6afc5 100644
--- a/scripts/tests/test-retrieval-server.py
+++ b/scripts/tests/test-retrieval-server.py
@@ -411,6 +411,8 @@ class RetrievalServerTests(unittest.TestCase):
             ('service.ts', 'export function load() {\n return 1;\n}\nexport const save = () => 2;\n', ['load', 'save']),
             ('service.cs', 'public class Service\n{\n public void Load()\n {\n }\n}\n', ['Service', 'Load']),
             ('setup.ps1', 'function Get-Result {\n return 1\n}\n', ['Get-Result']),
+            ('schema.sql', 'CREATE TABLE users (id int);\nCREATE OR ALTER PROCEDURE dbo.GetUser AS SELECT 1;\n', ['users', 'dbo.GetUser']),
+            ('Main.kt', 'fun main() {\n println(1)\n}\n', ['main']),
             ('config.toml', '[server]\nport = 1\n[client]\nport = 2\n', ['server', 'client']),
         ]:
             self.assertEqual([symbol for symbol, _ in MODULE.sections(source, path)], symbols)
diff --git a/shared/retrieval/server.py b/shared/retrieval/server.py
index f3038c4..60fba46 100644
--- a/shared/retrieval/server.py
+++ b/shared/retrieval/server.py
@@ -34,9 +34,11 @@ RERANK_CANDIDATES = 50
 FINAL_RESULTS = 5
 CLI_TIMEOUT_SECONDS = 300
 RRF_K = 60
-INDEX_VERSION = 2
+INDEX_VERSION = 3
 RETRIEVAL_INSTRUCTION = "Given a codebase question, retrieve relevant code and documentation that answer the question."
-TEXT_EXTENSIONS = {".c", ".cpp", ".cs", ".go", ".java", ".js", ".json", ".md", ".py", ".ps1", ".rs", ".sh", ".toml", ".ts", ".tsx", ".txt", ".yaml", ".yml"}
+TEXT_EXTENSIONS = {".c", ".cjs", ".cpp", ".cs", ".csproj", ".css", ".go", ".gradle", ".html", ".java", ".js", ".json", ".jsx", ".kt", ".kts",
+                   ".md", ".mjs", ".props", ".ps1", ".psm1", ".py", ".razor", ".rs", ".scss", ".sh", ".sql", ".targets", ".toml", ".ts",
+                   ".tsx", ".txt", ".xaml", ".xml", ".yaml", ".yml"}
 DEFAULT_MAX_FILES = 2000
 MAX_FILES_ENV = "SEMANTIC_RETRIEVAL_MAX_FILES"
 
@@ -111,10 +113,15 @@ def sections(text: str, path: str):
                 heading = re.match(r"^\s*\[\[?([^\]]+)\]\]?\s*(?:#.*)?$", line)
                 if heading:
                     boundaries[number] = heading[1]
-            elif suffix in {".js", ".ts", ".tsx", ".cs", ".java", ".go", ".rs", ".c", ".cpp", ".ps1", ".sh"}:
+            elif suffix == ".sql":
+                heading = re.match(r"^\s*create\s+(?:or\s+(?:alter|replace)\s+)?(?:procedure|proc|function|view|table|trigger|index)\s+([\w.\[\]\"]+)",
+                                   line, re.IGNORECASE)
+                if heading:
+                    boundaries[number] = heading[1]
+            elif suffix in {".js", ".jsx", ".mjs", ".cjs", ".ts", ".tsx", ".cs", ".java", ".kt", ".kts", ".go", ".rs", ".c", ".cpp", ".ps1", ".psm1", ".sh"}:
                 symbol = re.match(
                     r"^\s*(?:(?:export|default|public|private|protected|internal|static|abstract|async|sealed|partial|pub)\s+)*"
-                    r"(?:(?:class|interface|struct|enum|record|function|fn|def)\s+([\w$-]+)"
+                    r"(?:(?:class|interface|struct|enum|record|function|fun|fn|def)\s+([\w$-]+)"
                     r"|func\s+(?:\([^)]*\)\s*)?([\w]+)"
                     r"|(?:const|let|var)\s+([\w$]+)\s*=.*=>"
                     r"|([\w$-]+)\s*\([^;]*\)\s*\{"