Files
ARTEX/agent/finding_reasoning_test.go
BaaRai 8c9c1fc0ab feat(findings): optional counterevidence and confidence_rationale
Add two optional free-text fields to findings so a reporter can record
what was tested and did not work (counterevidence) and why the
conclusion holds (confidence_rationale).

- db: idempotent ADD COLUMN IF NOT EXISTS, TEXT NOT NULL DEFAULT '',
  no CHECK; RecordFindingInput, the INSERT, the shared select list and
  all three scan sites carry them.
- agent: report_finding accepts both as optional strings; the worker
  and pentest prompts say to fill them when confidence is not high.
- server: FindingDTO (list and detail) carries both, omitted when empty;
  existing databases get the two schema properties added to the stored
  report_finding row once, without overwriting user edits.
- web: the finding detail page shows each section only when non-empty.

Both fields stay optional: a missing field never refuses a finding.
2026-11-11 23:43:12 +01:00

71 lines
2.5 KiB
Go

package agent
import (
"encoding/json"
"slices"
"strings"
"testing"
"github.com/Autumn-27/artex/db"
)
// Pure: report_finding advertises counterevidence / confidence_rationale as
// optional string properties.
func TestReportFindingSchemaReasoningFieldsOptional(t *testing.T) {
schema := NewToolSet(nil, "").addFinding().InputSchema()
props, _ := schema["properties"].(map[string]any)
required, _ := schema["required"].([]string)
if !slices.Contains(required, "vulnclass") {
t.Fatalf("unexpected required list shape: %#v", schema["required"])
}
for _, name := range []string{"counterevidence", "confidence_rationale"} {
p, ok := props[name].(map[string]any)
if !ok {
t.Fatalf("report_finding schema missing %s", name)
}
if p["type"] != "string" {
t.Fatalf("%s type = %v, want string", name, p["type"])
}
if desc, _ := p["description"].(string); !strings.HasPrefix(desc, "optional") {
t.Fatalf("%s description should say optional: %q", name, desc)
}
if slices.Contains(required, name) {
t.Fatalf("%s must not be required: %v", name, required)
}
}
}
// PG: the tool passes both fields into storage, and omitting them never blocks
// a finding.
func TestReportFindingStoresReasoningFields(t *testing.T) {
d := testDB(t)
defer d.Close()
task, err := d.CreateTask("reasoning fields", "fixture", nil, 0, 0)
if err != nil {
t.Fatal(err)
}
defer d.DeleteTask(task.ID)
ts := NewToolSet(nil, "")
ts.ts, ts.taskID = d.Exploration(task.ExplorationID), task.ID
for _, tc := range []struct{ extra, counter, rationale string }{
{`,"counterevidence":"WAF blocked 4 of 5 encodings","confidence_rationale":"the 5th returned the other tenant's row"`, "WAF blocked 4 of 5 encodings", "the 5th returned the other tenant's row"},
{"", "", ""},
} {
res, err := ts.addFinding().Call(t.Context(), json.RawMessage(`{"vulnclass":"SQLI","severity":"high","summary":"reasoning fixture","evidence":"output"`+tc.extra+`}`), nil)
if err != nil || !strings.HasPrefix(res.Flatten(), "finding recorded: ") {
t.Fatalf("report_finding rejected: %v %s", err, res.Flatten())
}
var out db.RecordedFinding
if err := json.Unmarshal([]byte(strings.SplitN(res.Flatten(), "\n", 2)[1]), &out); err != nil {
t.Fatal(err)
}
f, err := d.GetFinding(out.FindingID)
if err != nil || f == nil {
t.Fatalf("GetFinding: %v %v", f, err)
}
if f.Counterevidence != tc.counter || f.ConfidenceRationale != tc.rationale {
t.Fatalf("stored (%q, %q), want (%q, %q)", f.Counterevidence, f.ConfidenceRationale, tc.counter, tc.rationale)
}
}
}