Add bulk operations and remove collections abstraction

- Add bulk delete, bulk tags, and bulk set-tags engine endpoints
  (POST /api/v1/bulk/delete, /bulk/tags, /bulk/set-tags)
- Filter-based selection: by tags, doc_type, ID list, ID range
- Safety threshold (KB_BULK_SAFETY_PERCENT, default 70%) prevents
  accidental mass operations unless force=true
- Synchronous execution with audit trail via jobs table
- Add kb_bulk_delete, kb_bulk_tags, kb_bulk_set_tags MCP tools
- Add kb bulk-remove, bulk-tag, bulk-set-tags CLI commands
- Remove collection abstraction from MCP server (use tags instead)
- Remove kb_set_collection MCP tool
- Update SKILL.md, MCP.md, README.md documentation

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-04-04 22:34:47 +01:00
parent 0c124c4ab7
commit b5a203d2aa
21 changed files with 1619 additions and 112 deletions
+186
View File
@@ -0,0 +1,186 @@
package cmd
import (
"bufio"
"fmt"
"os"
"strconv"
"strings"
"github.com/kb-search/kb/internal/api"
"github.com/kb-search/kb/internal/output"
"github.com/spf13/cobra"
)
var bulkRemoveCmd = &cobra.Command{
Use: "bulk-remove",
Short: "Delete multiple documents matching a filter",
RunE: runBulkRemove,
}
func init() {
addBulkFilterFlags(bulkRemoveCmd)
rootCmd.AddCommand(bulkRemoveCmd)
}
func runBulkRemove(cmd *cobra.Command, args []string) error {
body, err := buildBulkBody(cmd)
if err != nil {
return err
}
yes, _ := cmd.Flags().GetBool("yes")
if !yes {
desc := describeBulkFilter(cmd)
fmt.Printf("This will delete documents matching: %s\nProceed? [y/N] ", desc)
reader := bufio.NewReader(os.Stdin)
answer, _ := reader.ReadString('\n')
answer = strings.TrimSpace(strings.ToLower(answer))
if answer != "y" && answer != "yes" {
fmt.Println("Cancelled.")
return nil
}
}
client := api.NewClient()
resp, err := client.Post("/api/v1/bulk/delete", body)
if err != nil {
fmt.Fprintln(os.Stderr, err)
os.Exit(1)
}
if err := api.CheckError(resp); err != nil {
fmt.Fprintln(os.Stderr, err)
os.Exit(1)
}
var result map[string]interface{}
if err := api.DecodeJSON(resp, &result); err != nil {
return fmt.Errorf("failed to decode response: %w", err)
}
if output.IsJSON() {
output.PrintJSON(result)
} else {
printBulkResult("Deleted", result)
}
return nil
}
// ---------------------------------------------------------------------------
// Shared helpers for all bulk commands
// ---------------------------------------------------------------------------
func addBulkFilterFlags(cmd *cobra.Command) {
cmd.Flags().String("tags", "", "filter by tags (comma-separated)")
cmd.Flags().String("type", "", "filter by document type")
cmd.Flags().String("ids", "", "filter by document IDs (comma-separated)")
cmd.Flags().Int("from-id", 0, "filter by id >= value")
cmd.Flags().Int("to-id", 0, "filter by id <= value")
cmd.Flags().BoolP("force", "f", false, "override safety threshold")
cmd.Flags().BoolP("yes", "y", false, "skip confirmation prompt")
}
func buildBulkBody(cmd *cobra.Command) (map[string]interface{}, error) {
body := map[string]interface{}{}
tagsStr, _ := cmd.Flags().GetString("tags")
if tagsStr != "" {
body["tags"] = splitTags(tagsStr)
}
docType, _ := cmd.Flags().GetString("type")
if docType != "" {
body["doc_type"] = docType
}
idsStr, _ := cmd.Flags().GetString("ids")
if idsStr != "" {
ids, err := parseIntList(idsStr)
if err != nil {
return nil, fmt.Errorf("invalid --ids: %w", err)
}
body["document_ids"] = ids
}
fromID, _ := cmd.Flags().GetInt("from-id")
if fromID > 0 {
body["from_id"] = fromID
}
toID, _ := cmd.Flags().GetInt("to-id")
if toID > 0 {
body["to_id"] = toID
}
force, _ := cmd.Flags().GetBool("force")
if force {
body["force"] = true
}
// Ensure at least one filter
hasFilter := tagsStr != "" || docType != "" || idsStr != "" || fromID > 0 || toID > 0
if !hasFilter {
return nil, fmt.Errorf("at least one filter is required (--tags, --type, --ids, --from-id, --to-id)")
}
return body, nil
}
func describeBulkFilter(cmd *cobra.Command) string {
var parts []string
tagsStr, _ := cmd.Flags().GetString("tags")
if tagsStr != "" {
parts = append(parts, fmt.Sprintf("tags=[%s]", tagsStr))
}
docType, _ := cmd.Flags().GetString("type")
if docType != "" {
parts = append(parts, fmt.Sprintf("type=%s", docType))
}
idsStr, _ := cmd.Flags().GetString("ids")
if idsStr != "" {
parts = append(parts, fmt.Sprintf("ids=[%s]", idsStr))
}
fromID, _ := cmd.Flags().GetInt("from-id")
if fromID > 0 {
parts = append(parts, fmt.Sprintf("from_id=%d", fromID))
}
toID, _ := cmd.Flags().GetInt("to-id")
if toID > 0 {
parts = append(parts, fmt.Sprintf("to_id=%d", toID))
}
return strings.Join(parts, " ")
}
func printBulkResult(action string, result map[string]interface{}) {
matched := int(result["matched"].(float64))
succeeded := int(result["succeeded"].(float64))
failed := int(result["failed"].(float64))
fmt.Printf("%s %d of %d documents", action, succeeded, matched)
if failed > 0 {
fmt.Printf(" (%d failed)", failed)
}
fmt.Println()
}
func parseIntList(s string) ([]int, error) {
var ids []int
for _, part := range strings.Split(s, ",") {
part = strings.TrimSpace(part)
if part == "" {
continue
}
id, err := strconv.Atoi(part)
if err != nil {
return nil, fmt.Errorf("invalid ID %q: %w", part, err)
}
ids = append(ids, id)
}
return ids, nil
}