feat(13-01): implement CratesIOSource and RubyGemsSource with httptest tests

- CratesIOSource searches crates.io JSON API with custom User-Agent header
- RubyGemsSource searches rubygems.org search.json API for gem matches
- Both credentialless; CratesIO 1 req/s burst 1, RubyGems 1 req/2s burst 2
- Tests verify User-Agent header, Sweep findings, ctx cancellation, metadata

pkg/recon/sources/cratesio.go

@@ -0,0 +1,108 @@
+package sources
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"net/http"
+	"net/url"
+	"time"
+
+	"golang.org/x/time/rate"
+
+	"github.com/salvacybersec/keyhunter/pkg/providers"
+	"github.com/salvacybersec/keyhunter/pkg/recon"
+)
+
+// CratesIOSource searches crates.io for crates matching provider keywords.
+// No credentials required. Emits findings tagged SourceType=recon:crates.
+//
+// crates.io requires a custom User-Agent header on all requests.
+type CratesIOSource struct {
+	BaseURL  string
+	Registry *providers.Registry
+	Limiters *recon.LimiterRegistry
+	Client   *Client
+}
+
+var _ recon.ReconSource = (*CratesIOSource)(nil)
+
+// crates.io search JSON response structs.
+type cratesSearchResponse struct {
+	Crates []crateEntry `json:"crates"`
+}
+
+type crateEntry struct {
+	ID         string `json:"id"`
+	Name       string `json:"name"`
+	Repository string `json:"repository"`
+}
+
+func (s *CratesIOSource) Name() string            { return "crates" }
+func (s *CratesIOSource) RateLimit() rate.Limit    { return rate.Every(1 * time.Second) }
+func (s *CratesIOSource) Burst() int               { return 1 }
+func (s *CratesIOSource) RespectsRobots() bool     { return false }
+func (s *CratesIOSource) Enabled(_ recon.Config) bool { return true }
+
+func (s *CratesIOSource) Sweep(ctx context.Context, _ string, out chan<- recon.Finding) error {
+	base := s.BaseURL
+	if base == "" {
+		base = "https://crates.io"
+	}
+	client := s.Client
+	if client == nil {
+		client = NewClient()
+	}
+
+	queries := BuildQueries(s.Registry, "crates")
+	if len(queries) == 0 {
+		return nil
+	}
+
+	for _, q := range queries {
+		if err := ctx.Err(); err != nil {
+			return err
+		}
+
+		if s.Limiters != nil {
+			if err := s.Limiters.Wait(ctx, s.Name(), s.RateLimit(), s.Burst(), false); err != nil {
+				return err
+			}
+		}
+
+		searchURL := fmt.Sprintf("%s/api/v1/crates?q=%s&per_page=20", base, url.QueryEscape(q))
+		req, err := http.NewRequestWithContext(ctx, http.MethodGet, searchURL, nil)
+		if err != nil {
+			return fmt.Errorf("crates: build req: %w", err)
+		}
+		// crates.io requires a descriptive User-Agent header.
+		req.Header.Set("User-Agent", "keyhunter-recon/1.0 (https://github.com/salvacybersec/keyhunter)")
+
+		resp, err := client.Do(ctx, req)
+		if err != nil {
+			return fmt.Errorf("crates: fetch: %w", err)
+		}
+
+		var result cratesSearchResponse
+		if err := json.NewDecoder(resp.Body).Decode(&result); err != nil {
+			_ = resp.Body.Close()
+			return fmt.Errorf("crates: decode json: %w", err)
+		}
+		_ = resp.Body.Close()
+
+		for _, c := range result.Crates {
+			if err := ctx.Err(); err != nil {
+				return err
+			}
+			source := fmt.Sprintf("https://crates.io/crates/%s", c.Name)
+			out <- recon.Finding{
+				ProviderName: "",
+				Source:       source,
+				SourceType:   "recon:crates",
+				Confidence:   "low",
+				DetectedAt:   time.Now(),
+			}
+		}
+	}
+	return nil
+}