mirror of
https://github.com/Tencent/WeKnora.git
synced 2026-09-21 05:43:43 +08:00
Seven bugs surfaced via two audit rounds — parallel reviewer agents
plus a real-server end-to-end demo. Each fix arrives with a
regression test.
1. doc upload --recursive --json corrupted the envelope stream.
Per-file FAIL/OK plain lines printed unconditionally to stdout,
then a Success envelope, then on partial failure a typed error
that the root handler turned into a SECOND Failure envelope —
three outputs where one was expected. Fix: gate the plain lines
behind !opts.JSONOut, and add cmdutil.Error.Silent so the JSON-
path partial-failure preserves its typed exit code without
triggering PrintErrorEnvelope's default Failure-envelope write.
2. auth refresh / AuthRetryTransport misclassified HTTP failures as
network.error. RefreshAndPersist wrapped every refresher error
with CodeNetworkError, but the SDK emits "HTTP error 401: ..."
for a rejected refresh token — which should surface as
auth.token_expired. Switched to WrapHTTP for proper status-
derived classification. Affects both `auth refresh` and the
transport's refresh closure.
3. doc download accepted ".." as a server-suggested filename. The
rejection list covered "" / "." / filepath.Separator but not
bare ".." — filepath.Base("..") is "..", which slipped through
to os.Create and produced a confusing local.file_io wrap. Added
to the rejection set.
4. search chunks / docs / kb / sessions had no lower bound on
--limit. `-L 0` / `-L -1` was forwarded to the server with
undefined behavior. Added a 1..1000 bound at the RunE boundary
across all four (matching doc list / session list page-size
bounds). Internal callers in tests can still pass Limit==0 for
the "no client-side cap" runChunks path — the bound only applies
at the user-input layer.
5. cli/AGENTS.md ADR-3 verb-canon summary listed only v0.2 verbs as
"gh-canonical" and missed v0.3 additions (edit, pin, unpin,
download — all gh-canonical) plus locally-introduced ones
(empty, refresh, add, remove, link). Rewritten as an explicit
gh-canonical / locally-introduced split.
6. kb pin returned 404. Server registers /knowledge-bases/{id}/pin
as PUT (router.go:292); SDK was using POST. gin's router silently
404s on method-mismatch (treats it as path-not-found, not 405),
so the CLI classified the response as resource.not_found and
masked the real failure mode. Switched the SDK to http.MethodPut.
The asymmetry that hid this past round 1: kb unpin on a freshly-
created KB hits the no-op branch in cmd/kb/pin.go that skips the
SDK call entirely, so unpin "worked" without ever exercising the
broken path. Only the real-server demo, where kb pin actually
fires, surfaced it.
7. kb edit clobbered current Name when only --description was
passed. EditOptions used *string to distinguish "unset" from
"set to empty", but sdk.UpdateKnowledgeBaseRequest declares both
fields as plain string (no omitempty), so the JSON body always
carried `"name": ""`. Server requires Name → 400. Fix: runEdit
does fetch-then-update — GetKnowledgeBase first, build the PUT
body with current values, then overlay user-set fields. Same
TOCTOU window as kb pin / unpin.
Audit-flagged items intentionally NOT changed:
- kb pin / unpin check-then-toggle TOCTOU: documented; the clean
fix would be a server-side setter and belongs in a separate API
change.
- AuthRetryTransport singleflight test gap for one concurrency
scenario; v0.4 polish.
- cli/README.md:50 "once v0.2 ships" and CHANGELOG.md:8
"10 top-level commands": v0.2-PR artifacts, not v0.3-introduced.
- kb edit / kb pin are v0.3-new commands, so neither bug needs a
cli/CHANGELOG.md Fixed entry — the v0.3 release ships them
working as the Added bullets advertise.
124 lines
3.9 KiB
Go
124 lines
3.9 KiB
Go
package search
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
"sort"
|
|
"strings"
|
|
"text/tabwriter"
|
|
|
|
"github.com/spf13/cobra"
|
|
|
|
"github.com/Tencent/WeKnora/cli/internal/agent"
|
|
"github.com/Tencent/WeKnora/cli/internal/cmdutil"
|
|
"github.com/Tencent/WeKnora/cli/internal/format"
|
|
"github.com/Tencent/WeKnora/cli/internal/iostreams"
|
|
"github.com/Tencent/WeKnora/cli/internal/text"
|
|
sdk "github.com/Tencent/WeKnora/client"
|
|
)
|
|
|
|
const sessionsPageSize = 200
|
|
|
|
type SessionsSearchOptions struct {
|
|
Query string
|
|
Limit int
|
|
JSONOut bool
|
|
}
|
|
|
|
// SessionsSearchService is the narrow SDK surface this command depends on.
|
|
// Server has no session-search endpoint; CLI pages through and filters by
|
|
// Title / Description client-side.
|
|
type SessionsSearchService interface {
|
|
GetSessionsByTenant(ctx context.Context, page, pageSize int) ([]sdk.Session, int, error)
|
|
}
|
|
|
|
// NewCmdSessions builds `weknora search sessions "<query>"`. Finds chat
|
|
// sessions whose title or description contains the query.
|
|
func NewCmdSessions(f *cmdutil.Factory) *cobra.Command {
|
|
opts := &SessionsSearchOptions{}
|
|
cmd := &cobra.Command{
|
|
Use: `sessions "<query>"`,
|
|
Short: "Find chat sessions by title or description (client-side substring match)",
|
|
Example: ` weknora search sessions "onboarding"
|
|
weknora search sessions "Q3 review" --limit 3 --json`,
|
|
Args: cobra.ExactArgs(1),
|
|
RunE: func(c *cobra.Command, args []string) error {
|
|
opts.Query = strings.TrimSpace(args[0])
|
|
if opts.Query == "" {
|
|
return cmdutil.NewError(cmdutil.CodeInputInvalidArgument, "query argument cannot be empty")
|
|
}
|
|
if opts.Limit < 1 || opts.Limit > 1000 {
|
|
return cmdutil.NewError(cmdutil.CodeInputInvalidArgument, "--limit must be between 1 and 1000")
|
|
}
|
|
cli, err := f.Client()
|
|
if err != nil {
|
|
return err
|
|
}
|
|
return runSessionsSearch(c.Context(), opts, cli)
|
|
},
|
|
}
|
|
cmd.Flags().IntVarP(&opts.Limit, "limit", "L", 20, "Maximum results to return")
|
|
cmd.Flags().BoolVar(&opts.JSONOut, "json", false, "Output JSON envelope")
|
|
agent.SetAgentHelp(cmd, "Lists chat sessions whose title or description contains the query. Pages through the tenant sequentially; stops once limit matches found. Returns full Session objects so agents can pivot to session view/delete by id.")
|
|
return cmd
|
|
}
|
|
|
|
func runSessionsSearch(ctx context.Context, opts *SessionsSearchOptions, svc SessionsSearchService) error {
|
|
needle := strings.ToLower(opts.Query)
|
|
var matches []sdk.Session
|
|
|
|
for page := 1; ; page++ {
|
|
items, total, err := svc.GetSessionsByTenant(ctx, page, sessionsPageSize)
|
|
if err != nil {
|
|
return cmdutil.WrapHTTP(err, "list sessions")
|
|
}
|
|
for _, s := range items {
|
|
if matchSession(s, needle) {
|
|
matches = append(matches, s)
|
|
if opts.Limit > 0 && len(matches) >= opts.Limit {
|
|
goto done
|
|
}
|
|
}
|
|
}
|
|
if page*sessionsPageSize >= total || len(items) == 0 {
|
|
break
|
|
}
|
|
}
|
|
done:
|
|
sortSessionsByRecency(matches)
|
|
|
|
if opts.JSONOut {
|
|
return format.WriteEnvelope(iostreams.IO.Out, format.Success(matches, nil))
|
|
}
|
|
if len(matches) == 0 {
|
|
fmt.Fprintln(iostreams.IO.Out, "(no matches)")
|
|
return nil
|
|
}
|
|
tw := tabwriter.NewWriter(iostreams.IO.Out, 0, 0, 2, ' ', 0)
|
|
fmt.Fprintln(tw, "ID\tTITLE\tUPDATED")
|
|
for _, s := range matches {
|
|
title := text.Truncate(50, s.Title)
|
|
if title == "" {
|
|
title = "-"
|
|
}
|
|
fmt.Fprintf(tw, "%s\t%s\t%s\n", s.ID, title, s.UpdatedAt)
|
|
}
|
|
return tw.Flush()
|
|
}
|
|
|
|
// matchSession reports whether title or description contains needle (already
|
|
// lowercased by caller).
|
|
func matchSession(s sdk.Session, needle string) bool {
|
|
return text.ContainsFold(needle, s.Title, s.Description)
|
|
}
|
|
|
|
// sortSessionsByRecency sorts in place by UpdatedAt desc. Server returns
|
|
// strings; we compare lexically — RFC3339 timestamps sort correctly that
|
|
// way, and a stable order is enough for output determinism even if a
|
|
// non-conforming string slips through.
|
|
func sortSessionsByRecency(items []sdk.Session) {
|
|
sort.SliceStable(items, func(i, j int) bool {
|
|
return items[i].UpdatedAt > items[j].UpdatedAt
|
|
})
|
|
}
|