5adcedf170
Cross-cutting findings surfaced by the branch-completion review. Perf bug: - Factory.Client closure was not memoized. Factory.ResolveKB internally calls f.Client() to resolve --kb name → id, then the command's RunE calls f.Client() again. Two SDK clients, two keyring reads, two AuthRetryTransport allocations per name-resolved invocation, with *independent* token state (a refresh in one was invisible to the other). Switched to sync.Once like Secrets already does. Silent bug bait: - cmdutil.NormalizeHost docstring claimed CodeInputMissingFlag for the empty case; code returned CodeInputInvalidArgument. Aligned doc to code (present-but-empty is a bad value, not a missing flag). Agent contract gaps: - Five user-facing subcommands lacked SetAgentHelp: auth login / logout / list / status and chat. Added concise strings with error- code call-outs so agents can branch without parsing human strings. Helper extraction (≥3 callers): - text.KnowledgeDisplayName(fileName, title, id) — byte-identical formatter that was in both cmd/doc/list.go and cmd/search/docs.go. Takes fields directly so internal/text stays SDK-free. - cmdutil.WrapHTTP(cause, fmt, args...) *Error — replaces the `Wrapf(ClassifyHTTPError(err), err, ...)` pattern across 24 SDK call sites. Sed-driven migration; off-pattern shapes in chat.go (used streamErr) and cmdutil/kb.go (in-package) hand-edited. Contract test gains a comment update: post-migration the dominant pattern is WrapHTTP which the AST scanner skips entirely (only NewError/Wrapf selectors inspected); ClassifyHTTPErrorOutputs() bridge still covers the dynamic codes those paths can yield. UX consistency: - cmd/doc/list.go --page-size help now reads "Items per page (1..1000)" matching cmd/session/list.go. The bounds validation already enforced 1..1000; the help text was the last drift. Comment-discipline sweep: - Deleted the WHAT-only "*Options captures `weknora ...` flag state" docstring across 23 files (context, kb, auth, doc, session, search, chat, doctor, link). Where the line carried a real WHY clause (kb/delete, doc/delete, session/delete, kb/edit), kept the WHY and dropped only the leading WHAT phrase. - Stripped third-party project-name attribution from inline comments and one user-visible flag-help string across ~40 files in cli/cmd and cli/internal (plus 4 test-file comments). Removed phrases like "Mirrors `gh X`", "borrowed from lark-cli", "kubectl-style", "gcloud `--project`", "Stripe pattern", and the embedded GitHub URLs pointing at those projects. Behavioral descriptions and the WHY behind each comment are preserved; only the upstream-name attribution is gone. Inspiration / north-star references belong in cli/AGENTS.md (the design doc) and commit messages, not scattered through every file. Triggered by an audit round that surfaced several false / fragile parity claims (e.g. "Mirrors `gh repo edit`" — gh repo edit has no --name flag; "matches gcloud `--project` id-or-name" — gcloud's --project accepts ID only). Rather than fix them one by one, the whole category of in-comment external-project references was stripped uniformly.
122 lines
4.1 KiB
Go
122 lines
4.1 KiB
Go
package search
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
"errors"
|
|
"testing"
|
|
"time"
|
|
|
|
"github.com/stretchr/testify/assert"
|
|
"github.com/stretchr/testify/require"
|
|
|
|
"github.com/Tencent/WeKnora/cli/internal/cmdutil"
|
|
"github.com/Tencent/WeKnora/cli/internal/format"
|
|
"github.com/Tencent/WeKnora/cli/internal/iostreams"
|
|
sdk "github.com/Tencent/WeKnora/client"
|
|
)
|
|
|
|
// fakeDocsSearchSvc scripts paginated ListKnowledge responses. Pages are
|
|
// indexed 1-based; items keyed by page.
|
|
type fakeDocsSearchSvc struct {
|
|
pages map[int][]sdk.Knowledge
|
|
total int64
|
|
err error
|
|
calls []int // page numbers requested, for assertions
|
|
}
|
|
|
|
func (f *fakeDocsSearchSvc) ListKnowledge(_ context.Context, kbID string, page, pageSize int, tagID string) ([]sdk.Knowledge, int64, error) {
|
|
f.calls = append(f.calls, page)
|
|
if f.err != nil {
|
|
return nil, 0, f.err
|
|
}
|
|
return f.pages[page], f.total, nil
|
|
}
|
|
|
|
func TestDocsSearch_Substring(t *testing.T) {
|
|
out, _ := iostreams.SetForTest(t)
|
|
svc := &fakeDocsSearchSvc{
|
|
pages: map[int][]sdk.Knowledge{
|
|
1: {
|
|
{ID: "d1", Title: "Q3 Forecast", FileName: "q3.pdf", UpdatedAt: mustTime(t, "2026-05-10T00:00:00Z")},
|
|
{ID: "d2", Title: "Random Notes", FileName: "notes.md", UpdatedAt: mustTime(t, "2026-05-12T00:00:00Z")},
|
|
{ID: "d3", Title: "Q3 retro", FileName: "retro.pdf", UpdatedAt: mustTime(t, "2026-05-11T00:00:00Z")},
|
|
},
|
|
},
|
|
total: 3,
|
|
}
|
|
require.NoError(t, runDocsSearch(context.Background(), &DocsSearchOptions{Query: "q3", KBID: "kb1", Limit: 20}, svc))
|
|
got := out.String()
|
|
assert.Contains(t, got, "d1")
|
|
assert.Contains(t, got, "d3")
|
|
assert.NotContains(t, got, "d2") // "Random Notes" doesn't contain q3
|
|
}
|
|
|
|
func TestDocsSearch_MatchesFileName(t *testing.T) {
|
|
out, _ := iostreams.SetForTest(t)
|
|
svc := &fakeDocsSearchSvc{
|
|
pages: map[int][]sdk.Knowledge{1: {{ID: "d1", Title: "Untitled", FileName: "report.pdf"}}},
|
|
total: 1,
|
|
}
|
|
require.NoError(t, runDocsSearch(context.Background(), &DocsSearchOptions{Query: "report", KBID: "kb1", Limit: 20}, svc))
|
|
assert.Contains(t, out.String(), "d1")
|
|
}
|
|
|
|
func TestDocsSearch_PaginatesUntilTotal(t *testing.T) {
|
|
out, _ := iostreams.SetForTest(t)
|
|
page1 := make([]sdk.Knowledge, docsPageSize)
|
|
for i := range page1 {
|
|
page1[i] = sdk.Knowledge{ID: "p1", Title: "no match"}
|
|
}
|
|
page2 := []sdk.Knowledge{{ID: "found", Title: "needle here"}}
|
|
svc := &fakeDocsSearchSvc{
|
|
pages: map[int][]sdk.Knowledge{1: page1, 2: page2},
|
|
total: int64(docsPageSize) + 1,
|
|
}
|
|
require.NoError(t, runDocsSearch(context.Background(), &DocsSearchOptions{Query: "needle", KBID: "kb1", Limit: 20}, svc))
|
|
assert.Contains(t, out.String(), "found")
|
|
assert.Equal(t, []int{1, 2}, svc.calls, "must page past the first batch when no match on page 1")
|
|
}
|
|
|
|
func TestDocsSearch_StopsAtLimit(t *testing.T) {
|
|
_, _ = iostreams.SetForTest(t)
|
|
page1 := make([]sdk.Knowledge, 50)
|
|
for i := range page1 {
|
|
page1[i] = sdk.Knowledge{ID: "match", Title: "needle"}
|
|
}
|
|
svc := &fakeDocsSearchSvc{pages: map[int][]sdk.Knowledge{1: page1}, total: 1000}
|
|
require.NoError(t, runDocsSearch(context.Background(), &DocsSearchOptions{Query: "needle", KBID: "kb1", Limit: 3}, svc))
|
|
// Must not request page 2 because limit was hit mid-page.
|
|
assert.Equal(t, []int{1}, svc.calls)
|
|
}
|
|
|
|
func TestDocsSearch_JSON(t *testing.T) {
|
|
out, _ := iostreams.SetForTest(t)
|
|
svc := &fakeDocsSearchSvc{
|
|
pages: map[int][]sdk.Knowledge{1: {{ID: "d1", Title: "match"}}},
|
|
total: 1,
|
|
}
|
|
require.NoError(t, runDocsSearch(context.Background(), &DocsSearchOptions{Query: "match", KBID: "kb1", Limit: 20, JSONOut: true}, svc))
|
|
var env format.Envelope
|
|
require.NoError(t, json.Unmarshal(out.Bytes(), &env))
|
|
require.True(t, env.OK)
|
|
assert.Contains(t, out.String(), `"id":"d1"`)
|
|
}
|
|
|
|
func TestDocsSearch_NetworkError(t *testing.T) {
|
|
_, _ = iostreams.SetForTest(t)
|
|
svc := &fakeDocsSearchSvc{err: errors.New("HTTP error 404: kb not found")}
|
|
err := runDocsSearch(context.Background(), &DocsSearchOptions{Query: "x", KBID: "missing", Limit: 20}, svc)
|
|
require.Error(t, err)
|
|
var typed *cmdutil.Error
|
|
require.ErrorAs(t, err, &typed)
|
|
assert.Equal(t, cmdutil.CodeResourceNotFound, typed.Code)
|
|
}
|
|
|
|
func mustTime(t *testing.T, s string) time.Time {
|
|
t.Helper()
|
|
v, err := time.Parse(time.RFC3339, s)
|
|
require.NoError(t, err)
|
|
return v
|
|
}
|