mirror of
https://github.com/lukaszraczylo/llm-testbench.git
synced 2026-10-12 00:45:19 +00:00
lukaszraczylo
053eeab1bb
Bring agents/tool-routing and agents/planning up to 10 tests each. Add a new agents/delegation subcategory with 10 tests. Split agents.go into agents_toolrouting.go, agents_planning.go, and agents_delegation.go, each with a sibling _test.go file, and reduce agents.go to a thin registration aggregator. Every new prompt is self-contained and forces a JSON or number-only answer. Set-valued answers use JSONStringSet or a custom stage-set evaluator so no arbitrary order is required. Dependency-graph fixtures that force a single valid order are verified unique in the unit tests by brute-force enumeration over every permutation. Numeric ground truth is derived by running the same algorithm the fixture describes, then cross-checked against an independently hand-derived value. MaxTokens is omitted on all 28 new tests per the expansion rules; the 2 existing tests keep their prior value unchanged.
45 lines
1.3 KiB
Go
45 lines
1.3 KiB
Go
package tests
|
|
|
|
import (
|
|
"testing"
|
|
|
|
"github.com/lukaszraczylo/llm-testbench/internal/testkit"
|
|
)
|
|
|
|
// TestRegisterAgentsTests_Wiring checks registerAgentsTests wires up all
|
|
// three agents subcategories - tool-routing, planning, delegation - with
|
|
// 10 tests each, all categorized "agents", and no duplicate IDs across the
|
|
// three sibling files (testkit.Registry.Register panics on a duplicate ID,
|
|
// which would fail this test outright).
|
|
func TestRegisterAgentsTests_Wiring(t *testing.T) {
|
|
r := testkit.NewRegistry()
|
|
registerAgentsTests(r)
|
|
|
|
const wantTotal = 30
|
|
if r.Len() != wantTotal {
|
|
t.Fatalf("registerAgentsTests: registry has %d tests, want %d", r.Len(), wantTotal)
|
|
}
|
|
|
|
counts := map[string]int{}
|
|
for _, tc := range r.All() {
|
|
if tc.Category != "agents" {
|
|
t.Errorf("test %q: Category = %q, want %q", tc.ID, tc.Category, "agents")
|
|
}
|
|
if tc.Prompt == "" {
|
|
t.Errorf("test %q: Prompt is empty", tc.ID)
|
|
}
|
|
if tc.Eval == nil {
|
|
t.Errorf("test %q: Eval is nil", tc.ID)
|
|
}
|
|
if tc.Description == "" {
|
|
t.Errorf("test %q: Description is empty", tc.ID)
|
|
}
|
|
counts[tc.Subcategory]++
|
|
}
|
|
for _, sub := range []string{"tool-routing", "planning", "delegation"} {
|
|
if counts[sub] != 10 {
|
|
t.Errorf("subcategory %q: got %d tests, want 10", sub, counts[sub])
|
|
}
|
|
}
|
|
}
|