feat(mcp): index struct fields and interface method sets (#1)
Minor release. The indexer named composite types but could not describe their shape: every declaration was truncated at the first brace, so a struct symbol carried only its `type X struct` header and an interface symbol only its `type X interface` header. Field names, field types, and — most painfully — struct tags such as `env:"EINHERJAR_PG_HOST"` were dropped, as were the method sets of every port interface. An assistant could be told that `db-postgres` has a `Config` and a `Provider`, but not what env vars configure the one or what methods the other requires. This change captures both. internal/index (schema): - Symbol gains two optional fields. `fields` ([]Field) carries a struct's field set — name, type, raw struct tag (surrounding backticks stripped), doc comment, and an `embedded` marker. `methods` ([]Method) carries an interface's method set — name, signature without the leading `func`, and doc comment, including embedded interfaces. Both are omitempty and absent for every other kind. - SchemaVersion is deliberately unchanged. The two additions are additive and omitempty, so an older consumer parses the new index unchanged; per the existing rule the constant only bumps on a breaking format change. internal/index (builder): - collectSymbols now inspects each type's TypeSpec and, for a *ast.StructType or *ast.InterfaceType, fills the new Symbol members. A grouped field declaration (`x, y int`) yields one Field per name; an embedded field or interface yields an entry with an empty name. - New helpers: typeSpecType (underlying type expr of a lone type spec), extractFields, extractIfaceMethods, fieldDoc (doc comment or trailing line comment), and nodeString — a non-truncating printer used for field types, tags, and method signatures, distinct from formatNode which keeps truncating to produce the one-line header. internal/index (search): - matches() now also tests the query against struct field names, field types, and struct tags, and against interface method names and signatures. A query like an env-var key or a method name now resolves to the type that declares it. internal/tools: - get_symbol and search_symbols descriptions updated to advertise the new struct-field and interface-method coverage. No input/output schema change beyond the additive Symbol fields, which get_symbol already returns whole. internal/index (tests): - New builder_test.go — the package previously had no tests. Builds a temporary module fixture and asserts capture of struct fields (with tags and docs), embedded fields, interface methods (with signatures and docs), embedded interfaces, and discovery of a struct by one of its struct tags (the failure mode that motivated the change). Docs: - CHANGELOG.md gains an [Unreleased] entry; README.md tool table updated to state that get_symbol returns struct fields and interface methods and that search_symbols matches fields, tags, and methods. No new dependencies. The committed data/index.json placeholder is untouched — the index is regenerated at image build (Dockerfile runs cmd/indexer), so a deployment must be rebuilt to serve the richer index; a server still running the prior image keeps serving the older, member-less one. Reviewed-on: #1 Co-authored-by: Rene Nochebuena Guerrero <rene@nochebuena.dev> Co-committed-by: Rene Nochebuena Guerrero <rene@nochebuena.dev>
This commit was merged in pull request #1.
This commit is contained in:
@@ -154,7 +154,14 @@ func collectSymbols(m *Module, sub, modDir string, fset *token.FileSet, p *doc.P
|
||||
if isInterface(t.Decl) {
|
||||
kind = "interface"
|
||||
}
|
||||
m.Symbols = append(m.Symbols, newSymbol(m.Name, sub, kind, t.Name, t.Doc, t.Decl, fset, modDir))
|
||||
sym := newSymbol(m.Name, sub, kind, t.Name, t.Doc, t.Decl, fset, modDir)
|
||||
switch underlying := typeSpecType(t.Decl).(type) {
|
||||
case *ast.StructType:
|
||||
sym.Fields = extractFields(fset, underlying)
|
||||
case *ast.InterfaceType:
|
||||
sym.Methods = extractIfaceMethods(fset, underlying)
|
||||
}
|
||||
m.Symbols = append(m.Symbols, sym)
|
||||
for _, f := range t.Funcs {
|
||||
m.Symbols = append(m.Symbols, newSymbol(m.Name, sub, "func", f.Name, f.Doc, f.Decl, fset, modDir))
|
||||
}
|
||||
@@ -221,6 +228,95 @@ func isInterface(decl *ast.GenDecl) bool {
|
||||
return false
|
||||
}
|
||||
|
||||
// typeSpecType returns the underlying type expression of a single-type GenDecl
|
||||
// (the RHS of `type X = <expr>`), or nil when the declaration is not a lone
|
||||
// type spec. Used to tell struct/interface declarations apart from aliases and
|
||||
// defined primitives so their members can be extracted.
|
||||
func typeSpecType(decl *ast.GenDecl) ast.Expr {
|
||||
if decl == nil {
|
||||
return nil
|
||||
}
|
||||
for _, spec := range decl.Specs {
|
||||
if ts, ok := spec.(*ast.TypeSpec); ok {
|
||||
return ts.Type
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// extractFields flattens a struct's field list into index Fields, preserving
|
||||
// declaration order, struct tags (backticks stripped), embedded markers, and
|
||||
// per-field doc/line comments. A `x, y int` group yields one Field per name.
|
||||
func extractFields(fset *token.FileSet, st *ast.StructType) []Field {
|
||||
if st == nil || st.Fields == nil {
|
||||
return nil
|
||||
}
|
||||
var out []Field
|
||||
for _, f := range st.Fields.List {
|
||||
typeStr := nodeString(fset, f.Type)
|
||||
tag := ""
|
||||
if f.Tag != nil {
|
||||
tag = strings.Trim(f.Tag.Value, "`")
|
||||
}
|
||||
fdoc := fieldDoc(f)
|
||||
if len(f.Names) == 0 {
|
||||
// Embedded field: the type name is also the field name.
|
||||
out = append(out, Field{Type: typeStr, Tag: tag, Doc: fdoc, Embedded: true})
|
||||
continue
|
||||
}
|
||||
for _, n := range f.Names {
|
||||
out = append(out, Field{Name: n.Name, Type: typeStr, Tag: tag, Doc: fdoc})
|
||||
}
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// extractIfaceMethods flattens an interface's method set into index Methods.
|
||||
// Explicit methods carry their name and the signature without the leading
|
||||
// `func`; embedded interfaces carry an empty name and the embedded type's name
|
||||
// as the signature.
|
||||
func extractIfaceMethods(fset *token.FileSet, it *ast.InterfaceType) []Method {
|
||||
if it == nil || it.Methods == nil {
|
||||
return nil
|
||||
}
|
||||
var out []Method
|
||||
for _, f := range it.Methods.List {
|
||||
mdoc := fieldDoc(f)
|
||||
if len(f.Names) == 0 {
|
||||
// Embedded interface (or type constraint element).
|
||||
out = append(out, Method{Signature: nodeString(fset, f.Type), Doc: mdoc})
|
||||
continue
|
||||
}
|
||||
sig := strings.TrimPrefix(nodeString(fset, f.Type), "func")
|
||||
for _, n := range f.Names {
|
||||
out = append(out, Method{Name: n.Name, Signature: n.Name + sig, Doc: mdoc})
|
||||
}
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
func fieldDoc(f *ast.Field) string {
|
||||
switch {
|
||||
case f.Doc != nil:
|
||||
return strings.TrimSpace(f.Doc.Text())
|
||||
case f.Comment != nil:
|
||||
return strings.TrimSpace(f.Comment.Text())
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
// nodeString prints an AST node verbatim with no truncation — unlike
|
||||
// formatNode, which deliberately strips type/func bodies for one-line
|
||||
// signatures. Used for field types, tags, and interface method signatures.
|
||||
func nodeString(fset *token.FileSet, node ast.Node) string {
|
||||
var buf bytes.Buffer
|
||||
cfg := printer.Config{Mode: printer.UseSpaces, Tabwidth: 4}
|
||||
if err := cfg.Fprint(&buf, fset, node); err != nil {
|
||||
return ""
|
||||
}
|
||||
return strings.TrimSpace(buf.String())
|
||||
}
|
||||
|
||||
var (
|
||||
modulePathRe = regexp.MustCompile(`(?m)^module\s+(\S+)`)
|
||||
goVersionRe = regexp.MustCompile(`(?m)^go\s+(\S+)`)
|
||||
|
||||
149
internal/index/builder_test.go
Normal file
149
internal/index/builder_test.go
Normal file
@@ -0,0 +1,149 @@
|
||||
package index
|
||||
|
||||
import (
|
||||
"os"
|
||||
"path/filepath"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// writeFixture lays down a single-module Einherjar-like repo under a temp root
|
||||
// and returns the root path for Build to walk.
|
||||
func writeFixture(t *testing.T) string {
|
||||
t.Helper()
|
||||
root := t.TempDir()
|
||||
modDir := filepath.Join(root, "demo")
|
||||
if err := os.MkdirAll(modDir, 0o755); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
write := func(name, body string) {
|
||||
if err := os.WriteFile(filepath.Join(modDir, name), []byte(body), 0o644); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
write("go.mod", "module example.com/demo\n\ngo 1.26\n")
|
||||
write("demo.go", `// Package demo is a build fixture.
|
||||
package demo
|
||||
|
||||
import "context"
|
||||
|
||||
// Config holds settings.
|
||||
type Config struct {
|
||||
// Host is the bind address.
|
||||
Host string `+"`"+`env:"DEMO_HOST" envDefault:"0.0.0.0"`+"`"+`
|
||||
Port int `+"`"+`env:"DEMO_PORT"`+"`"+`
|
||||
Inner
|
||||
}
|
||||
|
||||
// Inner is embedded into Config.
|
||||
type Inner struct {
|
||||
Name string
|
||||
}
|
||||
|
||||
// Store reads values.
|
||||
type Store interface {
|
||||
// Get fetches one value.
|
||||
Get(ctx context.Context, id string) (string, error)
|
||||
context.Context
|
||||
}
|
||||
`)
|
||||
return root
|
||||
}
|
||||
|
||||
func findSymbol(t *testing.T, idx *Index, mod, name string) Symbol {
|
||||
t.Helper()
|
||||
m := idx.FindModule(mod)
|
||||
if m == nil {
|
||||
t.Fatalf("module %q not found", mod)
|
||||
}
|
||||
for _, s := range m.Symbols {
|
||||
if s.Name == name {
|
||||
return s
|
||||
}
|
||||
}
|
||||
t.Fatalf("symbol %q not found in module %q", name, mod)
|
||||
return Symbol{}
|
||||
}
|
||||
|
||||
func TestBuildCapturesStructFields(t *testing.T) {
|
||||
idx, err := Build(writeFixture(t))
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
cfg := findSymbol(t, idx, "demo", "Config")
|
||||
if cfg.Kind != "type" {
|
||||
t.Errorf("Config kind = %q, want type", cfg.Kind)
|
||||
}
|
||||
if len(cfg.Fields) != 3 {
|
||||
t.Fatalf("Config has %d fields, want 3: %+v", len(cfg.Fields), cfg.Fields)
|
||||
}
|
||||
|
||||
host := cfg.Fields[0]
|
||||
if host.Name != "Host" || host.Type != "string" {
|
||||
t.Errorf("field[0] = %+v, want Host string", host)
|
||||
}
|
||||
if host.Tag != `env:"DEMO_HOST" envDefault:"0.0.0.0"` {
|
||||
t.Errorf("Host tag = %q, want the env/envDefault tag (backticks stripped)", host.Tag)
|
||||
}
|
||||
if host.Doc != "Host is the bind address." {
|
||||
t.Errorf("Host doc = %q", host.Doc)
|
||||
}
|
||||
|
||||
if port := cfg.Fields[1]; port.Name != "Port" || port.Tag != `env:"DEMO_PORT"` {
|
||||
t.Errorf("field[1] = %+v, want Port with env tag", port)
|
||||
}
|
||||
|
||||
if inner := cfg.Fields[2]; !inner.Embedded || inner.Name != "" || inner.Type != "Inner" {
|
||||
t.Errorf("field[2] = %+v, want embedded Inner", inner)
|
||||
}
|
||||
}
|
||||
|
||||
func TestBuildCapturesInterfaceMethods(t *testing.T) {
|
||||
idx, err := Build(writeFixture(t))
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
store := findSymbol(t, idx, "demo", "Store")
|
||||
if store.Kind != "interface" {
|
||||
t.Errorf("Store kind = %q, want interface", store.Kind)
|
||||
}
|
||||
if len(store.Methods) != 2 {
|
||||
t.Fatalf("Store has %d methods, want 2: %+v", len(store.Methods), store.Methods)
|
||||
}
|
||||
|
||||
get := store.Methods[0]
|
||||
if get.Name != "Get" {
|
||||
t.Errorf("method[0] name = %q, want Get", get.Name)
|
||||
}
|
||||
if get.Signature != "Get(ctx context.Context, id string) (string, error)" {
|
||||
t.Errorf("Get signature = %q", get.Signature)
|
||||
}
|
||||
if get.Doc != "Get fetches one value." {
|
||||
t.Errorf("Get doc = %q", get.Doc)
|
||||
}
|
||||
|
||||
if emb := store.Methods[1]; emb.Name != "" || emb.Signature != "context.Context" {
|
||||
t.Errorf("method[1] = %+v, want embedded context.Context", emb)
|
||||
}
|
||||
}
|
||||
|
||||
// A struct must be discoverable by one of its struct tags — the failure mode
|
||||
// that motivated capturing fields in the first place.
|
||||
func TestSearchSymbolsByStructTag(t *testing.T) {
|
||||
idx, err := Build(writeFixture(t))
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
got := idx.SearchSymbols("DEMO_HOST", 10)
|
||||
found := false
|
||||
for _, s := range got {
|
||||
if s.Name == "Config" {
|
||||
found = true
|
||||
}
|
||||
}
|
||||
if !found {
|
||||
t.Errorf("searching a struct tag did not surface its type; got %d results", len(got))
|
||||
}
|
||||
}
|
||||
@@ -77,15 +77,46 @@ type SubPackage struct {
|
||||
}
|
||||
|
||||
// Symbol is one exported declaration (type, func, interface, const, var).
|
||||
//
|
||||
// For struct types Fields carries the field set (the Signature is only the
|
||||
// one-line `type X struct` header, so without Fields the field names, types,
|
||||
// and — crucially — struct tags would be lost). For interface types Methods
|
||||
// carries the method set for the same reason. Both are empty for every other
|
||||
// kind.
|
||||
type Symbol struct {
|
||||
Module string `json:"module"`
|
||||
SubPackage string `json:"subPackage"`
|
||||
Kind string `json:"kind"`
|
||||
Name string `json:"name"`
|
||||
Signature string `json:"signature"`
|
||||
Doc string `json:"doc"`
|
||||
File string `json:"file"`
|
||||
Line int `json:"line"`
|
||||
Module string `json:"module"`
|
||||
SubPackage string `json:"subPackage"`
|
||||
Kind string `json:"kind"`
|
||||
Name string `json:"name"`
|
||||
Signature string `json:"signature"`
|
||||
Doc string `json:"doc"`
|
||||
File string `json:"file"`
|
||||
Line int `json:"line"`
|
||||
Fields []Field `json:"fields,omitempty"`
|
||||
Methods []Method `json:"methods,omitempty"`
|
||||
}
|
||||
|
||||
// Field is one field of a struct-type Symbol. Name is empty for an embedded
|
||||
// field (its type then appears in Type, with Embedded true). Tag is the raw
|
||||
// struct tag with the surrounding backticks stripped (e.g.
|
||||
// `env:"EINHERJAR_PG_HOST" envDefault:"postgres"`) — the single most useful
|
||||
// thing a config consumer needs and the thing the old index dropped.
|
||||
type Field struct {
|
||||
Name string `json:"name,omitempty"`
|
||||
Type string `json:"type"`
|
||||
Tag string `json:"tag,omitempty"`
|
||||
Doc string `json:"doc,omitempty"`
|
||||
Embedded bool `json:"embedded,omitempty"`
|
||||
}
|
||||
|
||||
// Method is one method of an interface-type Symbol. Signature is the method
|
||||
// as written without the leading func keyword (e.g.
|
||||
// `GetExecutor(ctx context.Context) Executor`). For an embedded interface
|
||||
// Name is empty and Signature is the embedded interface's name.
|
||||
type Method struct {
|
||||
Name string `json:"name,omitempty"`
|
||||
Signature string `json:"signature"`
|
||||
Doc string `json:"doc,omitempty"`
|
||||
}
|
||||
|
||||
// ADR is one architectural decision record.
|
||||
@@ -157,8 +188,27 @@ func matches(s Symbol, needle string) bool {
|
||||
if needle == "" {
|
||||
return true
|
||||
}
|
||||
return strings.Contains(strings.ToLower(s.Name), needle) ||
|
||||
if strings.Contains(strings.ToLower(s.Name), needle) ||
|
||||
strings.Contains(strings.ToLower(s.Doc), needle) ||
|
||||
strings.Contains(strings.ToLower(s.SubPackage), needle) ||
|
||||
strings.Contains(strings.ToLower(s.Module), needle)
|
||||
strings.Contains(strings.ToLower(s.Module), needle) {
|
||||
return true
|
||||
}
|
||||
// A struct is also findable by a field name, type, or tag — so a query
|
||||
// like an env-var key or json field resolves to the type that declares it.
|
||||
for _, f := range s.Fields {
|
||||
if strings.Contains(strings.ToLower(f.Name), needle) ||
|
||||
strings.Contains(strings.ToLower(f.Type), needle) ||
|
||||
strings.Contains(strings.ToLower(f.Tag), needle) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
// An interface is findable by a method it requires.
|
||||
for _, mth := range s.Methods {
|
||||
if strings.Contains(strings.ToLower(mth.Name), needle) ||
|
||||
strings.Contains(strings.ToLower(mth.Signature), needle) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user