gitea-mcp/internal/tools/tool.go

package tools

import (
	"bytes"
	"encoding/json"
	"errors"
	"fmt"
	"reflect"
	"regexp"
	"strings"
	"unicode"

	"git.d-ma.be/mathias/gitea-mcp/internal/gitea"
	"git.d-ma.be/mathias/gitea-mcp/internal/registry"
)

// Tool implements registry.Tool.
type Tool = registry.Tool

func textOK(v any) (json.RawMessage, error) {
	return json.Marshal(v)
}

func parseArgs(raw json.RawMessage, dst any) error {
	if len(raw) == 0 {
		if err := json.Unmarshal([]byte("{}"), dst); err != nil {
			return err
		}
	} else {
		// Reject ambiguity BEFORE alias normalisation: re-marshalling through a
		// map would otherwise silently collapse exact duplicates (#65).
		if err := rejectAmbiguousKeys(raw, dst); err != nil {
			return err
		}
		if err := json.Unmarshal(normalizeAliases(raw), dst); err != nil {
			return err
		}
	}
	return validateRequiredIdentifiers(dst)
}

// rejectAmbiguousKeys refuses input whose meaning depends on encoding/json's
// case-insensitive, last-key-wins matching (#65). A client-side check that reads
// `branch` must see the value the server acts on, so: no object at any depth may
// carry two keys equal under strings.EqualFold (exact duplicates included), and
// no top-level key may differ from a field of dst only in case.
func rejectAmbiguousKeys(raw json.RawMessage, dst any) error {
	dec := json.NewDecoder(bytes.NewReader(raw))
	// UseNumber: without it Token() fails on a number outside float64 range,
	// which json.Unmarshal ignores in an unknown key — a decoy that would end
	// the scan before the duplicate (PR #66 review).
	dec.UseNumber()
	if err := scanJSONValue(dec); err != nil {
		if errors.Is(err, gitea.ErrValidation) {
			return err
		}
		// Fail closed: input the scanner cannot read is input it cannot vouch for.
		return fmt.Errorf("arguments are not valid JSON: %v: %w", err, gitea.ErrValidation)
	}
	var top map[string]json.RawMessage
	if err := json.Unmarshal(raw, &top); err != nil {
		return nil // not an object; nothing to compare against the schema
	}
	fields := jsonFieldNames(dst)
	for k := range top {
		for _, f := range fields {
			if k != f && strings.EqualFold(k, f) {
				return fmt.Errorf("argument %q does not match field %q exactly (keys are case-sensitive): %w", k, f, gitea.ErrValidation)
			}
		}
	}
	return nil
}

// scanJSONValue consumes one JSON value from dec, failing with ErrValidation if
// any object within it has two keys that are equal under strings.EqualFold.
func scanJSONValue(dec *json.Decoder) error {
	tok, err := dec.Token()
	if err != nil {
		return err
	}
	d, ok := tok.(json.Delim)
	if !ok {
		return nil
	}
	switch d {
	case '{':
		seen := map[string]string{}
		for dec.More() {
			kt, err := dec.Token()
			if err != nil {
				return err
			}
			k, _ := kt.(string)
			fk := foldKey(k)
			if prev, dup := seen[fk]; dup {
				return fmt.Errorf("duplicate argument keys %q and %q (keys must be unique ignoring case): %w", prev, k, gitea.ErrValidation)
			}
			seen[fk] = k
			if err := scanJSONValue(dec); err != nil {
				return err
			}
		}
	case '[':
		for dec.More() {
			if err := scanJSONValue(dec); err != nil {
				return err
			}
		}
	}
	_, err = dec.Token() // closing delimiter
	return err
}

// foldKey maps every rune to the smallest member of its unicode.SimpleFold
// orbit, so foldKey(a) == foldKey(b) exactly when strings.EqualFold(a, b) —
// the folding encoding/json uses (long s == s, Kelvin sign == k). A map keyed
// on it keeps the duplicate scan linear (PR #66 review: a pairwise EqualFold
// loop cost 7s of CPU on ~90k keys).
func foldKey(s string) string {
	var b strings.Builder
	for _, r := range s {
		min := r
		for f := unicode.SimpleFold(r); f != r; f = unicode.SimpleFold(f) {
			if f < min {
				min = f
			}
		}
		b.WriteRune(min)
	}
	return b.String()
}

// jsonFieldNames returns the json tag names of dst's top-level struct fields.
func jsonFieldNames(dst any) []string {
	v := reflect.ValueOf(dst)
	if v.Kind() != reflect.Pointer || v.IsNil() || v.Elem().Kind() != reflect.Struct {
		return nil
	}
	t := v.Elem().Type()
	names := make([]string, 0, t.NumField())
	for i := 0; i < t.NumField(); i++ {
		name, _, _ := strings.Cut(t.Field(i).Tag.Get("json"), ",")
		if name == "" || name == "-" {
			name = t.Field(i).Name
		}
		names = append(names, name)
	}
	return names
}

// branchNameRe is the shape the skills mcp-destructive-guard hook enforces.
var branchNameRe = regexp.MustCompile(`^[A-Za-z0-9][A-Za-z0-9._/-]*$`)

// ValidateBranchName rejects branch names that Gitea would turn into a ref
// other than refs/heads/<name> as the caller meant it. `refs/heads/main` in
// particular creates refs/heads/refs/heads/main, after which every API write to
// main fails with "matches more than one" until the ref is deleted by hand
// (#65). Beyond the shape regexp it applies git's own check-ref-format rules
// that the regexp admits.
func ValidateBranchName(b string) error {
	bad := !branchNameRe.MatchString(b) ||
		strings.HasPrefix(b, "refs/") ||
		b == "HEAD" ||
		strings.Contains(b, "..") ||
		strings.Contains(b, "//") ||
		strings.Contains(b, "/.") ||
		strings.HasSuffix(b, "/") ||
		strings.HasSuffix(b, ".") ||
		strings.HasSuffix(b, ".lock")
	if bad {
		return fmt.Errorf("invalid branch name %q (want a short name like feat/x, no refs/ prefix): %w", b, gitea.ErrValidation)
	}
	return nil
}

// validateRequiredIdentifiers rejects an empty repo identifier at the tool layer
// before it reaches the client, where it would build a trailing-empty path
// segment (`/api/v1/repos/{owner}/`) and leak gitea's bare 404 (#37). `repo` and
// `name` are always required where present — the per-repo identifier tools and
// the two create tools respectively; `owner` is already enforced by the
// allowlist check. Returns a typed ErrValidation naming the missing field.
func validateRequiredIdentifiers(dst any) error {
	v := reflect.ValueOf(dst)
	if v.Kind() != reflect.Pointer || v.IsNil() {
		return nil
	}
	v = v.Elem()
	if v.Kind() != reflect.Struct {
		return nil
	}
	t := v.Type()
	for i := 0; i < t.NumField(); i++ {
		base, opts, _ := strings.Cut(t.Field(i).Tag.Get("json"), ",")
		if base != "repo" && base != "name" {
			continue
		}
		// An optional identifier (e.g. code_search's `repo`, empty => owner-wide
		// fan-out) opts out by carrying `,omitempty`.
		if strings.Contains(opts, "omitempty") {
			continue
		}
		if v.Field(i).Kind() == reflect.String && v.Field(i).String() == "" {
			return fmt.Errorf("%q is required: %w", base, gitea.ErrValidation)
		}
	}
	return nil
}

// normalizeAliases reconciles the two spellings of the repo identifier so a tool
// works whichever the caller sends. `repo` is the canonical, idiomatic name that
// identifier tools now advertise (#38); `name` is kept as a back-compat alias.
// The mapping is bidirectional: `name`->`repo` fills the new canonical for old
// callers, and `repo`->`name` still fills the two create tools (repo_create,
// create_project_from_template) whose `name` legitimately means "name of the new
// repo". `index`->`number` is kept for the issue tools whose canonical is
// `number`. An explicit canonical value always wins over its alias.
func normalizeAliases(raw json.RawMessage) json.RawMessage {
	var m map[string]json.RawMessage
	if err := json.Unmarshal(raw, &m); err != nil {
		return raw // not a JSON object — leave untouched
	}
	changed := aliasInto(m, "name", "repo")
	changed = aliasInto(m, "repo", "name") || changed
	changed = aliasInto(m, "number", "index") || changed
	if !changed {
		return raw
	}
	if patched, err := json.Marshal(m); err == nil {
		return patched
	}
	return raw
}

// aliasInto copies m[alias] into m[canonical] when canonical is absent or an
// empty/zero JSON value and alias carries a usable one. An explicit canonical
// value always wins. Returns true if it wrote canonical.
func aliasInto(m map[string]json.RawMessage, canonical, alias string) bool {
	av, ok := m[alias]
	if !ok || isEmptyJSON(av) {
		return false
	}
	if cv, ok := m[canonical]; ok && !isEmptyJSON(cv) {
		return false
	}
	m[canonical] = av
	return true
}

func isEmptyJSON(v json.RawMessage) bool {
	switch strings.TrimSpace(string(v)) {
	case "", `""`, "null", "0":
		return true
	default:
		return false
	}
}

// capLimit returns a sane page size: 0 or negative → def, > 50 → 50.
func capLimit(in, def int) int {
	if in <= 0 {
		return def
	}
	if in > 50 {
		return 50
	}
	return in
}