Files
ARTEX/agent/toolrag_test.go

164 lines
5.8 KiB
Go

package agent
import (
"context"
"errors"
"fmt"
"slices"
"testing"
actool "github.com/Autumn-27/norma/tool"
)
func ragTool(name, desc string, params ...string) actool.CoreTool {
props := map[string]any{}
for _, p := range params {
props[p] = map[string]any{"type": "string"}
}
return actool.Build(actool.Spec{Name: name, Description: desc, Schema: map[string]any{"type": "object", "properties": props}})
}
// ragCatalog: two core tools, three meaningful fixtures, and filler up to n tools.
func ragCatalog(n int) []actool.CoreTool {
tools := []actool.CoreTool{
ragTool("record_fact", "Record a fact"),
ragTool("port_scan", "Scan TCP ports on a host, nmap-like service discovery", "host", "ports"),
ragTool("sqli_probe", "Probe web parameters for SQL injection", "url", "param"),
ragTool("http_request", "Send an HTTP request to a web endpoint", "url", "method"),
ragTool("list_assets", "List assets"),
}
for i := len(tools); i < n; i++ {
tools = append(tools, ragTool(fmt.Sprintf("filler_%02d", i), "Unrelated helper"))
}
return tools
}
func ragNames(tools []actool.CoreTool) (out []string) {
for _, t := range tools {
out = append(out, t.Name())
}
return out
}
const ragQuery = "Find SQL injection in the web login form"
func TestToolRAGRanksInjectionAboveScan(t *testing.T) {
ranked, err := rankTools(ragQuery, ragCatalog(5), bm25Score)
if err != nil {
t.Fatal(err)
}
n := ragNames(ranked)
if scan := slices.Index(n, "port_scan"); slices.Index(n, "sqli_probe") > scan || slices.Index(n, "http_request") > scan {
t.Fatalf("ranking = %v, want sqli_probe and http_request above port_scan", n)
}
if n[0] != "sqli_probe" {
t.Fatalf("top = %s, want sqli_probe", n[0])
}
}
func TestToolRAGCoreKeptAndKRespected(t *testing.T) {
keep := toolRAGKeep(nil)
for _, k := range []int{1, 3} {
out, projected, err := projectTools(ragQuery, ragCatalog(25), keep, k, bm25Score)
if err != nil || !projected {
t.Fatalf("k=%d: projected=%v err=%v", k, projected, err)
}
n := ragNames(out)
if !slices.Contains(n, "record_fact") || !slices.Contains(n, "list_assets") {
t.Fatalf("k=%d: core tool hidden: %v", k, n)
}
if slices.Contains(n, "goal_met") {
t.Fatalf("k=%d: unbound core tool added: %v", k, n)
}
if nonCore := len(out) - 2; nonCore > k {
t.Fatalf("k=%d: %d non-core tools selected: %v", k, nonCore, n)
}
if !slices.Contains(n, "sqli_probe") {
t.Fatalf("k=%d: best match missing: %v", k, n)
}
}
}
// The projection runs after ToolResolve, so a tool the binding/enabled filter
// dropped is never selected even when it is the best lexical match.
func TestToolRAGNeverSelectsUnboundOrDisabled(t *testing.T) {
oldResolve, oldAugment, oldPolicy := ToolResolve, ToolAugment, FindingTrafficBindingEnabled
t.Cleanup(func() { ToolResolve, ToolAugment, FindingTrafficBindingEnabled = oldResolve, oldAugment, oldPolicy })
ToolAugment, FindingTrafficBindingEnabled = nil, nil
t.Setenv(toolRAGEnv, "on")
t.Setenv(toolRAGTopKEnv, "2")
ToolResolve = func(_ context.Context, _ string, in []actool.CoreTool) []actool.CoreTool {
var out []actool.CoreTool
for _, tool := range in {
if tool.Name() != "sql_injection_exploit" {
out = append(out, tool)
}
}
return out
}
base := append(ragCatalog(25), ragTool("sql_injection_exploit", "Exploit SQL injection in web login form", "url"))
out, _, cleanup := AugmentTools(WithToolQuery(t.Context(), ragQuery), "worker", base)
defer cleanup()
n := ragNames(out)
if slices.Contains(n, "sql_injection_exploit") {
t.Fatalf("unbound tool selected: %v", n)
}
if len(out) != 4 || !slices.Contains(n, "sqli_probe") {
t.Fatalf("got %v, want 2 core + top 2", n)
}
}
func TestToolRAGFallbacks(t *testing.T) {
keep := toolRAGKeep(nil)
failing := func(string, []actool.CoreTool) ([]float64, error) { return nil, errors.New("boom") }
for name, c := range map[string]struct {
query string
n int
score ToolScorer
}{"empty query": {" ", 25, bm25Score}, "catalog under 20": {ragQuery, 19, bm25Score}, "scoring error": {ragQuery, 25, failing}} {
in := ragCatalog(c.n)
out, projected, err := projectTools(c.query, in, keep, 1, c.score)
if projected || (err != nil) != (name == "scoring error") || !slices.Equal(ragNames(out), ragNames(in)) {
t.Errorf("%s: projected=%v err=%v out=%v", name, projected, err, ragNames(out))
}
}
}
func TestToolRAGDeterministic(t *testing.T) {
keep := toolRAGKeep(nil)
// "zzz" matches nothing: every candidate ties at 0 and the name tie-break decides.
for _, q := range []string{ragQuery, "zzz"} {
first, _, _ := projectTools(q, ragCatalog(30), keep, 4, bm25Score)
for i := 0; i < 20; i++ {
again, _, _ := projectTools(q, ragCatalog(30), keep, 4, bm25Score)
if !slices.Equal(ragNames(first), ragNames(again)) {
t.Fatalf("%q: run %d = %v, want %v", q, i, ragNames(again), ragNames(first))
}
}
}
ranked, _ := rankTools("zzz", ragCatalog(8), bm25Score)
if n := ragNames(ranked); !slices.IsSorted(n) {
t.Fatalf("ties not ordered by name: %v", n)
}
}
// Pins the keep set beyond the core list: harness tools, Skill and deferred names
// are never hidden, even when the query matches something else.
func TestToolRAGKeepsHarnessSkillAndDeferred(t *testing.T) {
in := append(ragCatalog(15), actool.DefaultTools()...)
in = append(in, ragTool("Skill", "Load a skill"), ragTool("mcp__srv__crawl", "Crawl pages"))
out, projected, err := projectTools(ragQuery, in, toolRAGKeep([]string{"mcp__srv__crawl"}), 1, bm25Score)
if err != nil || !projected || len(in) <= 20 {
t.Fatalf("projected=%v err=%v n=%d", projected, err, len(in))
}
n := ragNames(out)
for _, want := range append(ragNames(actool.DefaultTools()), "Skill", "mcp__srv__crawl", "sqli_probe") {
if !slices.Contains(n, want) {
t.Fatalf("%s hidden: %v", want, n)
}
}
if slices.Contains(n, "http_request") {
t.Fatalf("k=1 exceeded: %v", n)
}
}