Add tree-sitter structural diff for code files

Extends the compare_file_contents tool with AST-based structural
diffing for code files using tree-sitter. Instead of line-based diffs,
this shows declaration-level changes (functions, classes, types) which
gives models more concise and semantically meaningful context.

Supported languages: Go, Python, JavaScript, TypeScript, Ruby, Rust,
Java, C/C++.

Requires CGO_ENABLED=1 for the tree-sitter C bindings. Windows builds
are removed from goreleaser as CGO cross-compilation is not supported
without additional toolchain setup.

For unsupported languages, falls back to unified line-based diff.

Author: SamMorrowDrums

.goreleaser.yaml

@@ -7,12 +7,11 @@ before:
 
 builds:
   - env:
-      - CGO_ENABLED=0
+      - CGO_ENABLED=1
     ldflags:
       - -s -w -X main.version={{.Version}} -X main.commit={{.Commit}} -X main.date={{.Date}}
     goos:
       - linux
-      - windows
       - darwin
     main: ./cmd/github-mcp-server
 

Dockerfile

@@ -4,16 +4,16 @@ ARG VERSION="dev"
 # Set the working directory
 WORKDIR /build
 
-# Install git
+# Install git and C compiler for CGO (tree-sitter)
 RUN --mount=type=cache,target=/var/cache/apk \
-    apk add git
+    apk add git gcc musl-dev
 
 # Build the server
 # go build automatically download required module dependencies to /go/pkg/mod
 RUN --mount=type=cache,target=/go/pkg/mod \
     --mount=type=cache,target=/root/.cache/go-build \
     --mount=type=bind,target=. \
-    CGO_ENABLED=0 go build -ldflags="-s -w -X main.version=${VERSION} -X main.commit=$(git rev-parse HEAD) -X main.date=$(date -u +%Y-%m-%dT%H:%M:%SZ)" \
+    CGO_ENABLED=1 go build -ldflags="-s -w -X main.version=${VERSION} -X main.commit=$(git rev-parse HEAD) -X main.date=$(date -u +%Y-%m-%dT%H:%M:%SZ)" \
     -o /bin/github-mcp-server ./cmd/github-mcp-server
 
 # Make a stage to run the app

go.mod

@@ -13,6 +13,8 @@ require (
 	github.com/stretchr/testify v1.11.1
 )
 
+require github.com/smacker/go-tree-sitter v0.0.0-20240827094217-dd81d9e9be82
+
 require (
 	github.com/aymerick/douceur v0.2.0 // indirect
 	github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc // indirect

go.sum

@@ -74,6 +74,8 @@ github.com/shurcooL/githubv4 v0.0.0-20240727222349-48295856cce7 h1:cYCy18SHPKRkv
 github.com/shurcooL/githubv4 v0.0.0-20240727222349-48295856cce7/go.mod h1:zqMwyHmnN/eDOZOdiTohqIUKUrTFX62PNlu7IJdu0q8=
 github.com/shurcooL/graphql v0.0.0-20230722043721-ed46e5a46466 h1:17JxqqJY66GmZVHkmAsGEkcIu0oCe3AM420QDgGwZx0=
 github.com/shurcooL/graphql v0.0.0-20230722043721-ed46e5a46466/go.mod h1:9dIRpgIY7hVhoqfe0/FcYp0bpInZaT7dc3BYOprrIUE=
+github.com/smacker/go-tree-sitter v0.0.0-20240827094217-dd81d9e9be82 h1:6C8qej6f1bStuePVkLSFxoU22XBS165D3klxlzRg8F4=
+github.com/smacker/go-tree-sitter v0.0.0-20240827094217-dd81d9e9be82/go.mod h1:xe4pgH49k4SsmkQq5OT8abwhWmnzkhpgnXeekbx2efw=
 github.com/sourcegraph/conc v0.3.1-0.20240121214520-5f936abd7ae8 h1:+jumHNA0Wrelhe64i8F6HNlS8pkoyMv5sreGx2Ry5Rw=
 github.com/sourcegraph/conc v0.3.1-0.20240121214520-5f936abd7ae8/go.mod h1:3n1Cwaq1E1/1lhQhtRK2ts/ZwZEhjcQeJQ1RuC6Q/8U=
 github.com/spf13/afero v1.15.0 h1:b/YBCLWAJdFWJTN9cLhiXXcD7mzKn9Dm86dNnfyQw1I=

pkg/github/compare_file_contents_test.go

@@ -114,7 +114,7 @@ func Test_CompareFileContents(t *testing.T) {
 			expectDiff:   `host: "localhost" → "production.db"`,
 		},
 		{
-			name: "unsupported format falls back to unified diff",
+			name: "Go file uses structural diff",
 			mockedClient: MockHTTPClientWithHandlers(map[string]http.HandlerFunc{
 				GetReposContentsByOwnerByRepoByPath: mockContentsForRef(map[string]string{
 					"main":    "func main() {}\n",
@@ -128,8 +128,8 @@ func Test_CompareFileContents(t *testing.T) {
 				"base":  "main",
 				"head":  "feature",
 			},
-			expectFormat: "unified",
-			expectDiff:   "--- a/main.go",
+			expectFormat: "structural",
+			expectDiff:   "function_declaration main: modified",
 		},
 		{
 			name:         "missing required parameter - owner",

pkg/github/semantic_diff.go

@@ -80,6 +80,10 @@ func SemanticDiff(path string, base, head []byte) SemanticDiffResult {
 	case ".toml":
 		return semanticDiffTOML(path, base, head)
 	default:
+		// Try tree-sitter structural diff for code files
+		if languageForPath(path) != nil {
+			return structuralDiff(path, base, head)
+		}
 		return SemanticDiffResult{
 			Format: DiffFormatUnified,
 			Diff:   unifiedDiff(path, base, head),
@@ -542,6 +546,9 @@ func DetectDiffFormat(path string) DiffFormat {
 	case ".toml":
 		return DiffFormatTOML
 	default:
+		if languageForPath(path) != nil {
+			return DiffFormatStructural
+		}
 		return DiffFormatUnified
 	}
 }

pkg/github/semantic_diff_test.go

@@ -302,36 +302,17 @@ func TestSemanticDiffTOML(t *testing.T) {
 }
 
 func TestSemanticDiffUnifiedFallback(t *testing.T) {
-	tests := []struct {
-		name         string
-		path         string
-		base         string
-		head         string
-		expectedDiff string
-	}{
-		{
-			name:         "unsupported extension uses unified diff",
-			path:         "main.go",
-			base:         "func main() {\n}\n",
-			head:         "func main() {\n\tfmt.Println(\"hello\")\n}\n",
-			expectedDiff: "--- a/main.go",
-		},
-		{
-			name:         "no extension uses unified diff",
-			path:         "Makefile",
-			base:         "all:\n\techo hello\n",
-			head:         "all:\n\techo world\n",
-			expectedDiff: "--- a/Makefile",
-		},
-	}
+	t.Run("Go file uses structural diff", func(t *testing.T) {
+		result := SemanticDiff("main.go", []byte("func main() {\n}\n"), []byte("func main() {\n\tfmt.Println(\"hello\")\n}\n"))
+		assert.Equal(t, DiffFormatStructural, result.Format)
+		assert.Contains(t, result.Diff, "function_declaration main: modified")
+	})
 
-	for _, tc := range tests {
-		t.Run(tc.name, func(t *testing.T) {
-			result := SemanticDiff(tc.path, []byte(tc.base), []byte(tc.head))
-			assert.Equal(t, DiffFormatUnified, result.Format)
-			assert.Contains(t, result.Diff, tc.expectedDiff)
-		})
-	}
+	t.Run("no extension uses unified diff", func(t *testing.T) {
+		result := SemanticDiff("Makefile", []byte("all:\n\techo hello\n"), []byte("all:\n\techo world\n"))
+		assert.Equal(t, DiffFormatUnified, result.Format)
+		assert.Contains(t, result.Diff, "--- a/Makefile")
+	})
 }
 
 func TestSemanticDiffFileSizeLimit(t *testing.T) {
@@ -373,7 +354,7 @@ func TestSemanticDiffNewAndDeletedFiles(t *testing.T) {
 
 	t.Run("deleted Go file", func(t *testing.T) {
 		result := SemanticDiff("main.go", []byte("package main\n"), nil)
-		assert.Equal(t, DiffFormatUnified, result.Format)
+		assert.Equal(t, DiffFormatStructural, result.Format)
 		assert.Equal(t, "file deleted", result.Diff)
 	})
 
@@ -394,7 +375,7 @@ func TestDetectDiffFormat(t *testing.T) {
 		{"config.yml", DiffFormatYAML},
 		{"data.csv", DiffFormatCSV},
 		{"config.toml", DiffFormatTOML},
-		{"main.go", DiffFormatUnified},
+		{"main.go", DiffFormatStructural},
 		{"README.md", DiffFormatUnified},
 		{"Makefile", DiffFormatUnified},
 	}