Files
multica/server/internal/agenttmpl/loader_test.go
Naiyuan Qing 0c4133ef5b feat(agents): rewrite template catalog as 25 lightweight starters (#2587)
* feat(agents): rewrite template catalog as 25 lightweight starters

Replaces every Phase-1 template with a curated set built around the
"persona + intake + scaffold + hard negatives" instruction shape. Cross-
platform survey (Cursor / Cline / Roo / Continue / Custom GPTs) showed
the industry baseline for starter agents is "few but sharp" — single
intent, no methodology buy-in, mostly prompt-only. The original catalog
went the opposite direction (avg 2.5 skills, six-skill Full-stack
methodology stack) and felt heavy for first-time use.

Catalog shape:

- 25 templates across 7 categories: Engineering (8), Product (4),
  Writing (5), Design (3), Communication (2), Team (1), Productivity (2).
  New Product / Design / Communication / Team domains fill gaps the old
  Eng-heavy catalog ignored.
- 16 / 25 are prompt-only (no skill fan-out). Avg 0.56 skill per template
  vs. 2.5 prior. Heaviest is 2 skills, only for templates whose intent
  cannot be expressed in instructions alone (Playwright runner, single-
  file HTML bundlers, design + UX-guidelines pair).
- Universal top-frequency intents that the old catalog missed are now
  covered: Code Explainer (intent #1 across every platform surveyed),
  Translator (中英), Summarizer, Writing Critic, PRD Drafter/Critic,
  RCA Writer, ADR Writer, PR Description Writer, Commit Message Writer.

Loader allows 0-skill templates:

- server/internal/agenttmpl/loader.go drops the "must declare at least
  one skill" validation; comment explains the picker's "Prompt only"
  rendering path.
- loader_test.go: removed the corresponding negative case, added
  TestLoadFromFS_PromptOnlyTemplate as a regression guard.
- agent_template.go handler is unchanged — every len(tmpl.Skills) call
  site was already 0-safe (empty fan-out short-circuits the fetch phase
  and the in-tx loop both skip cleanly).

Frontend:

- template-picker.tsx: 18 new lucide icons (BookOpen, Bug, GitPullRequest,
  GitCommit, AlertTriangle, Scale, ClipboardList, Microscope, UserRound,
  Target, Highlighter, Languages, AlignLeft, GraduationCap, Lightbulb,
  Type, MessageSquare, Briefcase). Card renders a "Prompt only" badge
  when skills.length === 0 instead of "0 skills".
- template-detail.tsx: skill list section is hidden entirely for prompt-
  only templates — a header reading "Includes 0 skills" above an empty
  list was just visual noise. Instructions section below carries the
  agent's identity for these.
- locales/en + zh-Hans agents.json: new create_dialog.template_card.
  prompt_only key ("Prompt only" / "纯指令").

Verification:

- go test ./internal/agenttmpl/ — 9/9 pass, including
  TestLoad_RealTemplates which fails closed if any new JSON is malformed.
- pnpm typecheck — all 6 packages clean.
- pnpm --filter @multica/views test — 482/482 pass.
- pnpm lint — 0 errors.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(agents): add category filter pills to template picker

25 templates across 7 categories made the picker scroll-heavy on first
open. Add a single-select category filter row above the grid so a PM
can isolate Product templates in one click, an engineer can jump
straight to Engineering, etc.

Visual reuses the IssuesHeader scope-toggle pattern verbatim — Button
variant="outline" + active class swap (bg-accent / text-muted-foreground)
— so the affordance reads the same as the existing filter pills in
issues / squads / runtimes / my-issues. flex-wrap keeps the 8 pills
(All + 7 categories) honest on narrow widths.

Counts are inlined into the label ("Engineering (8)") rather than
shown as a separate badge — single-line-tall pills look right next to
the picker grid, and surfacing the per-category density up front
doubles as a hint at the catalog's "less but sharper" intent.

When a specific category is active, the grid renders flat (no
section headers) — the active pill already names what's on screen,
and a header reading "Engineering" above an only-Engineering grid is
visual duplication. "All" falls back to the prior grouped layout.

State is component-local (no URL sync, no persistence) since the
picker is dialog-internal transient state — closing the dialog
naturally resets the filter, which is the expected behaviour for a
"choose from a catalog" surface.

i18n: new `create_dialog.template_picker.filter_all` key in en + zh.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-14 14:12:18 +08:00

169 lines
4.9 KiB
Go

package agenttmpl
import (
"strings"
"testing"
"testing/fstest"
)
func TestLoad_RealTemplates(t *testing.T) {
// Exercises the production go:embed path. If a real template file is
// malformed in main, this test fails — the same failure server boot would
// hit, but in CI before merge.
reg, err := Load()
if err != nil {
t.Fatalf("Load(): %v", err)
}
if len(reg.List()) == 0 {
t.Fatal("expected at least one bundled template, got none")
}
}
func TestLoadFromFS_Valid(t *testing.T) {
fsys := fstest.MapFS{
"templates/alpha.json": &fstest.MapFile{Data: []byte(`{
"slug": "alpha",
"name": "Alpha",
"description": "first",
"instructions": "do alpha",
"skills": [{"source_url": "https://github.com/x/y/tree/main/skills/z"}]
}`)},
"templates/beta.json": &fstest.MapFile{Data: []byte(`{
"slug": "beta",
"name": "Beta",
"description": "second",
"instructions": "do beta",
"skills": [{"source_url": "https://github.com/x/y/tree/main/skills/q"}]
}`)},
}
reg, err := loadFromFS(fsys, "templates")
if err != nil {
t.Fatalf("loadFromFS: %v", err)
}
if got, want := len(reg.List()), 2; got != want {
t.Fatalf("List() len = %d, want %d", got, want)
}
// List() must be deterministic (sorted by filename).
if reg.List()[0].Slug != "alpha" {
t.Errorf("List()[0].Slug = %q, want alpha", reg.List()[0].Slug)
}
if _, ok := reg.Get("alpha"); !ok {
t.Errorf("Get(alpha) = false, want true")
}
if _, ok := reg.Get("nope"); ok {
t.Errorf("Get(nope) = true, want false")
}
}
func TestLoadFromFS_Invalid(t *testing.T) {
tests := []struct {
name string
content string
wantErr string
}{
{
name: "bad json",
content: `{not json`,
wantErr: "parse",
},
{
name: "missing slug",
content: `{"name": "X", "instructions": "do", "skills": [{"source_url":"u"}]}`,
wantErr: "missing slug",
},
{
name: "slug mismatches filename",
content: `{"slug":"other","name":"X","instructions":"do","skills":[{"source_url":"u"}]}`,
wantErr: "does not match filename",
},
{
name: "bad slug",
content: `{"slug":"Bad_Slug","name":"X","instructions":"do","skills":[{"source_url":"u"}]}`,
wantErr: "kebab-case",
},
{
name: "missing name",
content: `{"slug":"x","instructions":"do","skills":[{"source_url":"u"}]}`,
wantErr: "missing name",
},
{
name: "missing instructions",
content: `{"slug":"x","name":"X","skills":[{"source_url":"u"}]}`,
wantErr: "missing instructions",
},
{
name: "skill missing url",
content: `{"slug":"x","name":"X","instructions":"do","skills":[{}]}`,
wantErr: "missing source_url",
},
}
for _, tc := range tests {
t.Run(tc.name, func(t *testing.T) {
filename := "x.json"
if tc.name == "slug mismatches filename" {
filename = "x.json" // slug is "other", file is "x.json" → mismatch
}
fsys := fstest.MapFS{
"templates/" + filename: &fstest.MapFile{Data: []byte(tc.content)},
}
_, err := loadFromFS(fsys, "templates")
if err == nil {
t.Fatalf("expected error containing %q, got nil", tc.wantErr)
}
if !strings.Contains(err.Error(), tc.wantErr) {
t.Errorf("error = %v, want substring %q", err, tc.wantErr)
}
})
}
}
func TestLoadFromFS_PromptOnlyTemplate(t *testing.T) {
// 0-skill templates are legitimate. Most starter templates ship prompt-only
// (no skill fan-out, just an instructions block). Regression guard so the
// "must declare at least one skill" rule doesn't sneak back in.
fsys := fstest.MapFS{
"templates/prompt-only.json": &fstest.MapFile{Data: []byte(`{
"slug":"prompt-only",
"name":"Prompt Only",
"description":"no skills here",
"instructions":"just write good prose",
"skills":[]
}`)},
}
reg, err := loadFromFS(fsys, "templates")
if err != nil {
t.Fatalf("loadFromFS: %v", err)
}
tmpl, ok := reg.Get("prompt-only")
if !ok {
t.Fatal("Get(prompt-only) = false, want true")
}
if len(tmpl.Skills) != 0 {
t.Errorf("len(Skills) = %d, want 0", len(tmpl.Skills))
}
}
func TestLoadFromFS_DuplicateSlug(t *testing.T) {
// Two valid files declaring the same slug — caught by the registry, not
// by validate(). Slugs are unique within the registry.
fsys := fstest.MapFS{
"templates/a.json": &fstest.MapFile{Data: []byte(`{
"slug":"a","name":"A","instructions":"do","skills":[{"source_url":"u"}]
}`)},
"templates/b.json": &fstest.MapFile{Data: []byte(`{
"slug":"a","name":"A2","instructions":"do","skills":[{"source_url":"u"}]
}`)},
}
_, err := loadFromFS(fsys, "templates")
if err == nil || !strings.Contains(err.Error(), "duplicate slug") {
// Note: this test will fail validation first (slug "a" vs filename
// "b.json") because we check filename-slug match before duplicate.
// That's fine — both are errors. Adjust expectation:
if err == nil || !strings.Contains(err.Error(), "does not match filename") {
t.Errorf("expected duplicate slug or filename mismatch, got %v", err)
}
}
}