Files
Enterprise-Knowledge-Base/cli/cmd/chunk/view_test.go
T
nullkey 5b07c9ab87 feat(cli): chunk subtree + MCP chunk_list tool + curation rationale
New subtree (chunk list / view / delete) exposes RAG retrieval
debugging primitives with SDK-grounded field set (23 Chunk fields).
Pagination follows v0.4 canon: --limit / --page-size (1..1000) /
--all-pages.

- chunk list --doc <id>: enumerate by ChunkIndex (separate from
  search chunks which is hybrid retrieval; Long help documents the
  distinction)
- chunk view <id>: scope-less render via /chunks/by-id route; full
  content verbatim
- chunk delete <id> --doc <id>: scope-flag + scope-id; L-13
  destructive; 404 NOT idempotent; resource.not_found /
  auth.forbidden / input.confirmation_required typed exit codes
  documented in Long help

MCP server gains chunk_list as 10th curated tool. Schema deliberately
exposes only doc_id + limit (no pagination workflow on MCP); response
includes truncated_at_limit flag when total > limit.

cli/AGENTS.md MCP curation rationale rewritten: curated read-only is
a deliberate product call because the server side does not yet
enforce per-token scope. When server scope ships, mutation tools can
land in the MCP surface.

Shared helper cli/internal/text/timeago_string.go (FuzzyAgoStr)
extracted from session list during the C2 quality-review pass.
2026-05-16 16:56:33 +08:00

101 lines
3.4 KiB
Go

package chunkcmd
import (
"context"
"encoding/json"
"errors"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"github.com/Tencent/WeKnora/cli/internal/cmdutil"
"github.com/Tencent/WeKnora/cli/internal/iostreams"
sdk "github.com/Tencent/WeKnora/client"
)
type fakeViewSvc struct {
resp *sdk.Chunk
err error
}
func (f *fakeViewSvc) GetChunkByIDOnly(_ context.Context, _ string) (*sdk.Chunk, error) {
return f.resp, f.err
}
func TestView_Happy_RendersAllFields(t *testing.T) {
out, _ := iostreams.SetForTest(t)
svc := &fakeViewSvc{resp: &sdk.Chunk{
ID: "c1",
SeqID: 42,
ChunkIndex: 0,
KnowledgeID: "doc_abc",
KnowledgeBaseID: "kb_abc",
ChunkType: "text",
IsEnabled: true,
Content: "the quick brown fox",
CreatedAt: "2026-05-15T11:00:00Z",
UpdatedAt: "2026-05-15T12:00:00Z",
}}
require.NoError(t, runView(context.Background(), &ViewOptions{ChunkID: "c1"}, nil, svc))
body := out.String()
assert.Contains(t, body, "c1")
assert.Contains(t, body, "doc_abc")
assert.Contains(t, body, "kb_abc")
assert.Contains(t, body, "text")
assert.Contains(t, body, "the quick brown fox", "content must render in full")
}
func TestView_HumanLabels_DocAndKB(t *testing.T) {
out, _ := iostreams.SetForTest(t)
svc := &fakeViewSvc{resp: &sdk.Chunk{
ID: "c1", KnowledgeID: "doc_abc", KnowledgeBaseID: "kb_abc",
}}
require.NoError(t, runView(context.Background(), &ViewOptions{ChunkID: "c1"}, nil, svc))
body := out.String()
// Human KV must use friendlier DOC_ID / KB_ID labels (spec §1.5.2), not raw SDK names.
assert.Contains(t, body, "doc_id")
assert.Contains(t, body, "kb_id")
assert.NotContains(t, body, "knowledge_id")
assert.NotContains(t, body, "knowledge_base_id")
}
func TestView_OmitsZeroOrEmpty(t *testing.T) {
out, _ := iostreams.SetForTest(t)
svc := &fakeViewSvc{resp: &sdk.Chunk{ID: "c_min", Content: "x"}}
require.NoError(t, runView(context.Background(), &ViewOptions{ChunkID: "c_min"}, nil, svc))
body := out.String()
// status / start_at / end_at all zero → must be omitted from the human KV.
assert.NotContains(t, body, "status:")
assert.NotContains(t, body, "start_at:")
assert.NotContains(t, body, "end_at:")
// tag_id / image_info empty → omitted.
assert.NotContains(t, body, "tag_id:")
assert.NotContains(t, body, "image_info:")
}
func TestView_JSON_BareSDKShape(t *testing.T) {
out, _ := iostreams.SetForTest(t)
svc := &fakeViewSvc{resp: &sdk.Chunk{
ID: "c_json", KnowledgeID: "doc_abc", KnowledgeBaseID: "kb_abc",
}}
require.NoError(t, runView(context.Background(), &ViewOptions{ChunkID: "c_json"}, &cmdutil.JSONOptions{}, svc))
var got sdk.Chunk
require.NoError(t, json.Unmarshal(out.Bytes(), &got))
assert.Equal(t, "c_json", got.ID)
assert.Equal(t, "doc_abc", got.KnowledgeID)
// JSON uses SDK snake_case keys (knowledge_id), not human relabel doc_id.
assert.Contains(t, out.String(), `"knowledge_id":"doc_abc"`)
assert.Contains(t, out.String(), `"knowledge_base_id":"kb_abc"`)
assert.NotContains(t, out.String(), `"doc_id"`)
assert.NotContains(t, out.String(), `"kb_id"`)
}
func TestView_404(t *testing.T) {
_, _ = iostreams.SetForTest(t)
svc := &fakeViewSvc{err: errors.New("HTTP error 404: not found")}
err := runView(context.Background(), &ViewOptions{ChunkID: "missing"}, nil, svc)
require.Error(t, err)
assert.Contains(t, err.Error(), "resource.not_found")
}