feat: verified findings backend (S1)

Add a machine-checked verification state to findings, separate from the
human disposition (status). A finding is verified only when a proof or
verification traffic body is bound, the agent declares POE L3 or higher,
and every evidence quote appears verbatim, after whitespace
normalization, in one of those response bodies.

- schema: poe_level, verification_status, verification_note on findings
  (idempotent ADD COLUMN IF NOT EXISTS, no CHECK, no backfill).
- db: SetFindingVerification validates status and POE 0-4; the three
  fields are scanned with the finding rows and exposed in the DTO.
- update_finding_report: optional poe_level and evidence_quotes. The
  report is always saved; verification only decides the status. Read
  failures give not_assessed, never unverified.
- report agent guidance: declare POE and exact quotes from the bound body.

Not in this change: UI badges and filters, the blocked and false_positive
transitions, and the stored default report prompt for existing databases
(the guidance is appended at run time).

agent/finding_workflow.go

@@ -76,6 +76,9 @@ func findingWorkflowTools(agentKey string, tools []actool.CoreTool) ([]actool.Co
 	if has["update_finding_report"] && has["bind_finding_traffic"] && has["get_finding_traffic"] {
 		guidance += "\n\n**Auto-link traffic before reporting (enabled)**: you are responsible for verifying and binding traffic for the vulnerability that triggered this run, then writing the report. First obtain the unambiguous finding_id and finding_node_id from the report_finding return JSON or get_task_node_detail / list_task_findings. Read the vulnerability details, the corresponding intent's execution records, and the existing evidence list, preferring the real IDs handed off by the reporter. If this verification is HTTP and the traffic tools are available, use traffic_search to filter candidates, then traffic_get to verify item by item that the request/response truly supports the vulnerability; domains and times are only for filtering and do not prove attribution. Bind the confirmed evidence in reproduction order via bind_finding_traffic(finding_id, traffic_refs), choosing baseline / proof / verification / supporting and stating the purpose. Operate only on this vulnerability — do not recreate vulnerabilities or re-probe the target. After a successful bind, call get_finding_traffic again for the latest version, read the bodies you need, then pass the version you actually read as evidence_version to update_finding_report (whose finding_id parameter still takes finding_node_id). Do not re-append existing bindings. For TCP, no-capture, unavailable tools, or no exact match, skip auto-binding, write the report from textual/command evidence with the reason stated, and never guess to force traffic in. Do not claim success when binding fails; keep the existing evidence and explain in the report why nothing was bound."
 	}
+	if has["update_finding_report"] {
+		guidance += findingVerificationGuidance
+	}
 	if guidance != "" || has["get_finding_traffic"] || has["update_finding_report"] {
 		guidance += findingIDGuidance
 	}
@@ -126,3 +129,8 @@ func (t *ToolSet) findingRefsFromHint(hintID int64, explicit []db.TrafficRef) ([
 	}
 	return db.NormalizeTrafficRefs(append(append([]db.TrafficRef{}, explicit...), payload.Refs...))
 }
+
+// findingVerificationGuidance tells the report writer how to declare proof
+// (S1). The server downgrades any finding whose declaration does not hold up,
+// so the agent must never state a level or quote it cannot read in the bound body.
+const findingVerificationGuidance = "\n\n**Verification (S1)**: when you call update_finding_report, also declare poe_level (0-4) and evidence_quotes. poe_level 1 = error, timing or response variation; 2 = structural manipulation (boolean, UNION, parser difference); 3 = actual data extracted; 4 = critical impact (admin credentials, code execution). L3 is the minimum for a verified finding. evidence_quotes must be exact lines copied from a bound proof or verification response body (read it with get_finding_traffic first), never from memory or from the report text; the server checks each quote verbatim after whitespace normalization. If you cannot quote the proof, omit the quotes: the finding then stays unverified, which is acceptable. Do not raise poe_level to get a verified status."

db/finding_verification.go

@@ -0,0 +1,50 @@
+package db
+
+import (
+	"fmt"
+)
+
+// Machine-checked verification state of a finding (S1). Kept apart from
+// findings.status, which is the human disposition. Values are validated here
+// (server-side), not by a CHECK constraint, like the other findings columns.
+const (
+	VerificationVerified      = "verified"
+	VerificationUnverified    = "unverified"
+	VerificationBlocked       = "blocked"
+	VerificationNotAssessed   = "not_assessed"
+	VerificationFalsePositive = "false_positive"
+)
+
+// ValidVerificationStatus reports whether s is a known verification state.
+func ValidVerificationStatus(s string) bool {
+	switch s {
+	case VerificationVerified, VerificationUnverified, VerificationBlocked,
+		VerificationNotAssessed, VerificationFalsePositive:
+		return true
+	}
+	return false
+}
+
+// SetFindingVerification records the verification state, POE level and note on
+// the standalone findings row. It does not touch status, report or evidence.
+func (d *DB) SetFindingVerification(findingID int64, status string, poe int, note string) error {
+	if !ValidVerificationStatus(status) {
+		return fmt.Errorf("invalid verification status %q", status)
+	}
+	if poe < 0 || poe > 4 {
+		return fmt.Errorf("invalid POE level %d (want 0-4)", poe)
+	}
+	res, err := d.Exec(`UPDATE findings SET verification_status=$2, poe_level=$3, verification_note=$4 WHERE id=$1`,
+		findingID, status, poe, note)
+	if err != nil {
+		return err
+	}
+	n, err := res.RowsAffected()
+	if err != nil {
+		return err
+	}
+	if n == 0 {
+		return ErrFindingNotFound
+	}
+	return nil
+}

db/findings.go

@@ -20,20 +20,23 @@ type DBFinding struct {
 	ReportEvidenceVersion int64
 	TrafficBindings       []FindingTrafficBinding // populated only for export
 
-	ID              int64
-	TaskID          *int64
-	NodeID          *int64
-	VulnClass       string
-	Name            string // vulnerability name (readable title); when empty the frontend falls back to VulnClass
-	Severity        string
-	Summary         string
-	Evidence        string
-	Worker          string
-	AssetIDs        []int64
-	Status          string
-	Report          string // detailed report (Markdown); only populated by GetFinding, not by list queries
-	CreatedAt       time.Time
-	TaskDescription string // populated via LEFT JOIN on tasks
+	ID                 int64
+	TaskID             *int64
+	NodeID             *int64
+	VulnClass          string
+	Name               string // vulnerability name (readable title); when empty the frontend falls back to VulnClass
+	Severity           string
+	Summary            string
+	Evidence           string
+	Worker             string
+	AssetIDs           []int64
+	Status             string
+	PoELevel           int    // proof-of-exploitation level 0-4 (S1); 0 = none declared
+	VerificationStatus string // verified / unverified / blocked / not_assessed / false_positive
+	VerificationNote   string // why the status was reached; empty when verified
+	Report             string // detailed report (Markdown); only populated by GetFinding, not by list queries
+	CreatedAt          time.Time
+	TaskDescription    string // populated via LEFT JOIN on tasks
 }
 
 // Finding triage states (findings.status).
@@ -105,6 +108,7 @@ func (d *DB) AddFinding(taskID, nodeID int64, vulnclass, name, severity, summary
 const findingSelectCols = `f.id, f.task_id, f.node_id, f.vulnclass, COALESCE(f.name, ''), f.severity, f.summary,
 	       f.evidence, f.worker, f.asset_ids, COALESCE(f.status, 'pending'), f.created_at,
 	       COALESCE(t.description, '') AS task_description, f.evidence_version, f.report_evidence_version,
+	       f.poe_level, COALESCE(f.verification_status, 'unverified'), COALESCE(f.verification_note, ''),
  (SELECT count(*) FROM finding_traffic_bindings b WHERE b.finding_id=f.id)`
 
 // scanFindings materializes rows selected via findingSelectCols.
@@ -118,7 +122,7 @@ func scanFindings(rows interface {
 		f := &DBFinding{}
 		var aidsJSON string
 		if err := rows.Scan(&f.ID, &f.TaskID, &f.NodeID, &f.VulnClass, &f.Name, &f.Severity,
-			&f.Summary, &f.Evidence, &f.Worker, &aidsJSON, &f.Status, &f.CreatedAt, &f.TaskDescription, &f.EvidenceVersion, &f.ReportEvidenceVersion, &f.TrafficCount); err != nil {
+			&f.Summary, &f.Evidence, &f.Worker, &aidsJSON, &f.Status, &f.CreatedAt, &f.TaskDescription, &f.EvidenceVersion, &f.ReportEvidenceVersion, &f.PoELevel, &f.VerificationStatus, &f.VerificationNote, &f.TrafficCount); err != nil {
 			return nil, err
 		}
 		_ = json.Unmarshal([]byte(aidsJSON), &f.AssetIDs)
@@ -519,7 +523,7 @@ func (d *DB) ListFindingsForExport(f FindingFilter, ids []int64) ([]*DBFinding,
 		var aidsJSON string
 		if err := rows.Scan(&f.ID, &f.TaskID, &f.NodeID, &f.VulnClass, &f.Name, &f.Severity,
 			&f.Summary, &f.Evidence, &f.Worker, &aidsJSON, &f.Status, &f.CreatedAt,
-			&f.TaskDescription, &f.EvidenceVersion, &f.ReportEvidenceVersion, &f.TrafficCount, &f.Report); err != nil {
+			&f.TaskDescription, &f.EvidenceVersion, &f.ReportEvidenceVersion, &f.PoELevel, &f.VerificationStatus, &f.VerificationNote, &f.TrafficCount, &f.Report); err != nil {
 			return nil, err
 		}
 		_ = json.Unmarshal([]byte(aidsJSON), &f.AssetIDs)
@@ -649,7 +653,7 @@ func (d *DB) GetFinding(id int64) (*DBFinding, error) {
 		WHERE f.id = $1`, id).Scan(
 		&f.ID, &f.TaskID, &f.NodeID, &f.VulnClass, &f.Name, &f.Severity,
 		&f.Summary, &f.Evidence, &f.Worker, &aidsJSON, &f.Status, &f.CreatedAt,
-		&f.TaskDescription, &f.EvidenceVersion, &f.ReportEvidenceVersion, &f.TrafficCount, &f.Report)
+		&f.TaskDescription, &f.EvidenceVersion, &f.ReportEvidenceVersion, &f.PoELevel, &f.VerificationStatus, &f.VerificationNote, &f.TrafficCount, &f.Report)
 	if err == sql.ErrNoRows {
 		return nil, nil
 	}

db/schema.sql

@@ -1177,6 +1177,12 @@ CREATE TRIGGER trg_conversation_retest_delete BEFORE DELETE ON conversations
 
 ALTER TABLE findings ADD COLUMN IF NOT EXISTS evidence_version BIGINT NOT NULL DEFAULT 0;
 ALTER TABLE findings ADD COLUMN IF NOT EXISTS report_evidence_version BIGINT NOT NULL DEFAULT 0;
+-- Machine-checked proof state (S1). Separate from status (human disposition). Existing rows stay
+-- unverified / POE 0: history is never auto-verified. Values validated server-side, no CHECK.
+-- verification_status: verified / unverified / blocked / not_assessed / false_positive.
+ALTER TABLE findings ADD COLUMN IF NOT EXISTS poe_level SMALLINT NOT NULL DEFAULT 0;
+ALTER TABLE findings ADD COLUMN IF NOT EXISTS verification_status TEXT NOT NULL DEFAULT 'unverified';
+ALTER TABLE findings ADD COLUMN IF NOT EXISTS verification_note TEXT NOT NULL DEFAULT '';
 
 CREATE TABLE IF NOT EXISTS traffic_evidence_snapshots (
     id TEXT PRIMARY KEY,

server/dto.go

@@ -312,6 +312,9 @@ type FindingDTO struct {
 	ReportEvidenceVersion int64                      `json:"report_evidence_version"`
 	ReportStale           bool                       `json:"report_stale"`
 	TrafficBindings       []db.FindingTrafficBinding `json:"traffic_bindings,omitempty"`
+	PoELevel              int                        `json:"poe_level"`
+	VerificationStatus    string                     `json:"verification_status"`
+	VerificationNote      string                     `json:"verification_note"`
 
 	ID        string `json:"id"`
 	FindingID string `json:"finding_id,omitempty"` // standalone findings-table id — the handle for status updates
@@ -452,6 +455,7 @@ func findingFromDB(f *db.DBFinding, assets map[int64]*db.Asset) FindingDTO {
 		FindingID:    i64s(f.ID),
 		TrafficCount: f.TrafficCount, EvidenceVersion: f.EvidenceVersion, ReportEvidenceVersion: f.ReportEvidenceVersion,
 		ReportStale: f.Report != "" && f.EvidenceVersion != f.ReportEvidenceVersion, TrafficBindings: f.TrafficBindings,
+		PoELevel: f.PoELevel, VerificationStatus: f.VerificationStatus, VerificationNote: f.VerificationNote,
 		VulnClass: f.VulnClass,
 		Name:      f.Name,
 		Severity:  f.Severity,

server/finding_verification.go

@@ -0,0 +1,170 @@
+package server
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"fmt"
+	"io"
+	"log"
+	"strings"
+	"unicode/utf8"
+
+	"github.com/Autumn-27/artex/db"
+	"github.com/Autumn-27/artex/evidence"
+)
+
+// S1 receipt check. A finding is verified only when a proof/verification
+// traffic body is bound, the agent declared POE L3 or higher, and every quote
+// appears verbatim (after whitespace normalization) in one of those response
+// bodies. Anything else is unverified, blocked or not_assessed, with a note.
+
+const (
+	verificationMinPOE       = 3
+	verificationReadCap      = 4 << 20 // bytes read per bound body; a quote beyond this cannot be confirmed
+	verificationNoteQuoteLen = 60
+)
+
+// boundBody is one bound response body, read through the evidence store and
+// normalized for the substring check.
+type boundBody struct {
+	text      string // whitespace-normalized text (only when !nonText)
+	truncated bool   // body was longer than verificationReadCap
+	nonText   bool   // binary or non-UTF-8 content: never claimed as a match
+}
+
+// normalizeEvidenceText trims and collapses every run of whitespace to one space.
+// Case is kept.
+func normalizeEvidenceText(s string) string {
+	return strings.Join(strings.Fields(s), " ")
+}
+
+// readBoundResponse reads the response side of a bound snapshot through the
+// evidence store (same bytes the UI shows), capped at verificationReadCap.
+func readBoundResponse(store *evidence.Store, snap db.TrafficEvidenceSnapshot) (boundBody, error) {
+	f, _, err := store.OpenBody(snap, "response")
+	if err != nil {
+		return boundBody{}, err
+	}
+	defer f.Close()
+	raw, err := io.ReadAll(io.LimitReader(f, verificationReadCap+1))
+	if err != nil {
+		return boundBody{}, err
+	}
+	var bb boundBody
+	if len(raw) > verificationReadCap {
+		bb.truncated = true
+		raw = raw[:verificationReadCap]
+		// The cap may cut a multi-byte rune: drop at most UTFMax-1 trailing bytes.
+		for i := 0; i < utf8.UTFMax-1 && !utf8.Valid(raw) && len(raw) > 0; i++ {
+			raw = raw[:len(raw)-1]
+		}
+	}
+	if bytes.IndexByte(raw, 0) >= 0 || !utf8.Valid(raw) {
+		bb.nonText = true
+		return bb, nil
+	}
+	bb.text = normalizeEvidenceText(string(raw))
+	return bb, nil
+}
+
+// assessFindingVerification computes the verification state of a finding from
+// its bound traffic and the quotes the agent supplied. poe is the declared POE
+// level (0 when absent). It never returns "verified" unless every rule passes.
+func (s *Server) assessFindingVerification(ctx context.Context, findingID int64, poe int, quotes []string) (status, note string) {
+	tr, err := s.m.pg.GetFindingTraffic(ctx, findingID)
+	if err != nil {
+		return db.VerificationNotAssessed, "binding read error: " + err.Error()
+	}
+	var proofs []db.FindingTrafficBinding
+	for _, b := range tr.Bindings {
+		if b.Role == "proof" || b.Role == "verification" {
+			proofs = append(proofs, b)
+		}
+	}
+	if len(proofs) == 0 {
+		return db.VerificationUnverified, "no proof traffic bound"
+	}
+	if poe < verificationMinPOE {
+		return db.VerificationUnverified, fmt.Sprintf("POE L%d below L3", poe)
+	}
+	if len(quotes) == 0 {
+		return db.VerificationUnverified, "no evidence quotes provided"
+	}
+	store := s.evidenceStore()
+	bodies := make([]boundBody, 0, len(proofs))
+	for _, b := range proofs {
+		bb, err := readBoundResponse(store, b.Snapshot)
+		if err != nil {
+			// Fail closed: an unreadable body is never an "unverified" verdict.
+			return db.VerificationNotAssessed, "evidence body unreadable: " + err.Error()
+		}
+		bodies = append(bodies, bb)
+	}
+	for _, q := range quotes {
+		nq := normalizeEvidenceText(q)
+		if nq != "" && quoteInBodies(nq, bodies) {
+			continue
+		}
+		for _, bb := range bodies {
+			if bb.nonText {
+				return db.VerificationNotAssessed, "non-text evidence"
+			}
+		}
+		for _, bb := range bodies {
+			if bb.truncated {
+				return db.VerificationNotAssessed, "quote not found within read cap of bound evidence"
+			}
+		}
+		return db.VerificationUnverified, "quote not found in bound evidence: " + shortQuote(q)
+	}
+	return db.VerificationVerified, ""
+}
+
+func quoteInBodies(nq string, bodies []boundBody) bool {
+	for _, bb := range bodies {
+		if !bb.nonText && strings.Contains(bb.text, nq) {
+			return true
+		}
+	}
+	return false
+}
+
+// shortQuote returns the first verificationNoteQuoteLen runes of the trimmed
+// quote, for use in a note.
+func shortQuote(q string) string {
+	r := []rune(strings.TrimSpace(q))
+	if len(r) > verificationNoteQuoteLen {
+		r = r[:verificationNoteQuoteLen]
+	}
+	return string(r)
+}
+
+// seedFindingVerificationSchema adds the S1 optional properties to the
+// update_finding_report schema of existing databases. Idempotent: a property is
+// added only when the stored schema lacks it, and user edits are preserved.
+func (s *Server) seedFindingVerificationSchema() {
+	raw, err := json.Marshal(s.toolUpdateFindingReport().InputSchema())
+	if err != nil {
+		log.Printf("[verification] tool schema: %v", err)
+		return
+	}
+	var obj map[string]json.RawMessage
+	if err := json.Unmarshal(raw, &obj); err != nil {
+		return
+	}
+	var properties map[string]json.RawMessage
+	if err := json.Unmarshal(obj["properties"], &properties); err != nil {
+		return
+	}
+	for _, name := range []string{"poe_level", "evidence_quotes"} {
+		if len(properties[name]) == 0 {
+			continue
+		}
+		_, err := s.m.pg.Exec(`UPDATE tools SET schema=jsonb_set(schema,ARRAY['properties',$2::text],$3::jsonb,true),updated_at=now()
+WHERE key=$1 AND system AND NOT(COALESCE(schema->'properties','{}'::jsonb) ? $2)`, "update_finding_report", name, string(properties[name]))
+		if err != nil {
+			log.Printf("[verification] upgrade update_finding_report.%s: %v", name, err)
+		}
+	}
+}

server/finding_verification_test.go

@@ -0,0 +1,165 @@
+package server
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"net/http/httptest"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+
+	"github.com/Autumn-27/artex/db"
+	actool "github.com/Autumn-27/norma/tool"
+)
+
+const verificationBody = "HTTP/1.1 200 OK\nuser   admin:\tx7\nend of dump"
+
+func TestNormalizeEvidenceText(t *testing.T) {
+	cases := map[string]string{
+		"  a\t\tb\r\n c  ": "a b c",
+		"Admin  User":      "Admin User", // case is kept
+		"":                 "",
+	}
+	for in, want := range cases {
+		if got := normalizeEvidenceText(in); got != want {
+			t.Fatalf("normalize(%q) = %q, want %q", in, got, want)
+		}
+	}
+}
+
+func TestShortQuoteCapsAtSixtyRunes(t *testing.T) {
+	long := strings.Repeat("é", 100)
+	if got := []rune(shortQuote(long)); len(got) != verificationNoteQuoteLen {
+		t.Fatalf("shortQuote kept %d runes, want %d", len(got), verificationNoteQuoteLen)
+	}
+}
+
+// verificationFixture returns a server with one finding whose traffic "a" is
+// bound with the given role and whose response body is verificationBody.
+func verificationFixture(t *testing.T, role string) (*Server, *db.RecordedFinding, func(string, string, string) *httptest.ResponseRecorder) {
+	t.Helper()
+	s, f, req := trafficEvidenceServer(t)
+	seedServerEvidenceFlow(t, s, "a", []byte(verificationBody))
+	if role != "" {
+		base := fmt.Sprintf("/api/exploration/findings/%d/traffic", f.FindingID)
+		w := req("POST", base, fmt.Sprintf(`{"traffic_refs":[{"traffic_id":"a","role":%q}]}`, role))
+		if w.Code != 200 {
+			t.Fatalf("bind: %d %s", w.Code, w.Body)
+		}
+	}
+	return s, f, req
+}
+
+// updateReport calls update_finding_report with the node id, as the agent does.
+func updateReport(t *testing.T, s *Server, nodeID int64, extra string) (string, bool) {
+	t.Helper()
+	in := fmt.Sprintf(`{"finding_id":%d,"report":"# report","evidence_version":null%s}`, nodeID, extra)
+	res, err := s.toolUpdateFindingReport().Call(context.Background(), json.RawMessage(in), &actool.ToolContext{})
+	if err != nil {
+		t.Fatal(err)
+	}
+	return res.Flatten(), res.IsError
+}
+
+func storedVerification(t *testing.T, s *Server, findingID int64) (status string, poe int, note, report string) {
+	t.Helper()
+	if err := s.m.pg.QueryRow(`SELECT verification_status, poe_level, verification_note, report FROM findings WHERE id=$1`, findingID).
+		Scan(&status, &poe, &note, &report); err != nil {
+		t.Fatal(err)
+	}
+	return
+}
+
+func TestVerificationNoBindingPOE4Unverified(t *testing.T) {
+	s, f, _ := verificationFixture(t, "")
+	msg, isErr := updateReport(t, s, f.NodeID, `,"poe_level":4,"evidence_quotes":["x7"]`)
+	if isErr || !strings.Contains(msg, "verification: unverified - no proof traffic bound") {
+		t.Fatalf("unexpected result: err=%v %q", isErr, msg)
+	}
+	status, poe, note, report := storedVerification(t, s, f.FindingID)
+	if status != db.VerificationUnverified || poe != 4 || note != "no proof traffic bound" || report == "" {
+		t.Fatalf("stored: status=%s poe=%d note=%q report=%q", status, poe, note, report)
+	}
+}
+
+func TestVerificationProofPOE3MissingQuoteUnverified(t *testing.T) {
+	s, f, _ := verificationFixture(t, "proof")
+	msg, isErr := updateReport(t, s, f.NodeID, `,"poe_level":3,"evidence_quotes":["secret=999"]`)
+	if isErr || !strings.Contains(msg, "warning:") {
+		t.Fatalf("unexpected result: err=%v %q", isErr, msg)
+	}
+	status, _, note, report := storedVerification(t, s, f.FindingID)
+	if status != db.VerificationUnverified || !strings.HasPrefix(note, "quote not found in bound evidence: secret=999") || report == "" {
+		t.Fatalf("stored: status=%s note=%q report=%q", status, note, report)
+	}
+}
+
+func TestVerificationProofPOE3ExactQuoteVerified(t *testing.T) {
+	s, f, _ := verificationFixture(t, "verification")
+	// The quote differs from the body only in whitespace runs: it must still match.
+	msg, isErr := updateReport(t, s, f.NodeID, `,"poe_level":3,"evidence_quotes":["user admin:  x7"]`)
+	if isErr || !strings.Contains(msg, "verification: verified (POE L3)") {
+		t.Fatalf("unexpected result: err=%v %q", isErr, msg)
+	}
+	status, poe, note, _ := storedVerification(t, s, f.FindingID)
+	if status != db.VerificationVerified || poe != 3 || note != "" {
+		t.Fatalf("stored: status=%s poe=%d note=%q", status, poe, note)
+	}
+}
+
+func TestVerificationOldStyleCallUnverifiedWithoutError(t *testing.T) {
+	s, f, _ := verificationFixture(t, "proof")
+	msg, isErr := updateReport(t, s, f.NodeID, "")
+	if isErr || !strings.Contains(msg, "verification: unverified") {
+		t.Fatalf("unexpected result: err=%v %q", isErr, msg)
+	}
+	status, poe, _, report := storedVerification(t, s, f.FindingID)
+	if status != db.VerificationUnverified || poe != 0 || report == "" {
+		t.Fatalf("stored: status=%s poe=%d report=%q", status, poe, report)
+	}
+}
+
+func TestVerificationUnreadableStoreNotAssessedReportSaved(t *testing.T) {
+	s, f, _ := verificationFixture(t, "proof")
+	// Remove the blobs behind the bound snapshot: the evidence store cannot open the body.
+	if err := os.RemoveAll(filepath.Join(s.m.dir, "evidence")); err != nil {
+		t.Fatal(err)
+	}
+	msg, isErr := updateReport(t, s, f.NodeID, `,"poe_level":3,"evidence_quotes":["x7"]`)
+	if isErr || !strings.Contains(msg, "verification: not_assessed") {
+		t.Fatalf("unexpected result: err=%v %q", isErr, msg)
+	}
+	status, _, note, report := storedVerification(t, s, f.FindingID)
+	if status != db.VerificationNotAssessed || !strings.HasPrefix(note, "evidence body unreadable") || report == "" {
+		t.Fatalf("stored: status=%s note=%q report=%q", status, note, report)
+	}
+}
+
+func TestVerificationRejectsOutOfRangePOE(t *testing.T) {
+	s, f, _ := verificationFixture(t, "proof")
+	msg, isErr := updateReport(t, s, f.NodeID, `,"poe_level":9`)
+	if !isErr || !strings.Contains(msg, "invalid poe_level 9") {
+		t.Fatalf("unexpected result: err=%v %q", isErr, msg)
+	}
+	if _, _, _, report := storedVerification(t, s, f.FindingID); report != "" {
+		t.Fatal("report must not be written when the input is rejected")
+	}
+}
+
+func TestVerificationColumnsExistWithHonestDefaults(t *testing.T) {
+	s, f, _ := trafficEvidenceServer(t)
+	var n int
+	if err := s.m.pg.QueryRow(`SELECT count(*) FROM information_schema.columns
+		WHERE table_name='findings' AND column_name IN ('poe_level','verification_status','verification_note')`).Scan(&n); err != nil {
+		t.Fatal(err)
+	}
+	if n != 3 {
+		t.Fatalf("expected 3 verification columns, found %d", n)
+	}
+	status, poe, note, _ := storedVerification(t, s, f.FindingID)
+	if status != db.VerificationUnverified || poe != 0 || note != "" {
+		t.Fatalf("new row: status=%s poe=%d note=%q", status, poe, note)
+	}
+}

server/orchestration.go

@@ -2,7 +2,9 @@ package server
 
 import (
 	"context"
+	"database/sql"
 	"encoding/json"
+	"errors"
 	"fmt"
 	"log"
 	"strconv"
@@ -430,26 +432,57 @@ func (s *Server) toolUpdateFindingReport() actool.CoreTool {
 			"finding_id":       map[string]any{"type": "integer", "description": "target vulnerability id (the id returned by report_finding)"},
 			"report":           strParam("full report text, Markdown format"),
 			"evidence_version": map[string]any{"type": "integer", "description": "evidence version returned by get_finding_traffic; prevents the report from overwriting newer evidence changes"},
+			"poe_level":        map[string]any{"type": "integer", "description": "proof-of-exploitation level 0-4: 1 error/timing/response variation, 2 structural manipulation, 3 actual data extracted, 4 critical impact. L3 is the minimum for verified. Omit or 0 when not proven."},
+			"evidence_quotes":  map[string]any{"type": "array", "items": map[string]any{"type": "string"}, "description": "exact lines copied from a bound proof/verification response body (get_finding_traffic). Never from memory; the server checks each one verbatim after whitespace normalization."},
 		}, "finding_id", "report"),
 		func(ctx context.Context, in json.RawMessage) (actool.Result, error) {
 			var a struct {
 				EvidenceVersion *int64          `json:"evidence_version"`
 				FindingID       json.RawMessage `json:"finding_id"`
 				Report          string          `json:"report"`
+				PoELevel        *int            `json:"poe_level"`
+				EvidenceQuotes  []string        `json:"evidence_quotes"`
 			}
 			_ = json.Unmarshal(in, &a)
 			nodeID := parseProfileID(a.FindingID) // reuses the "number or numeric string" parser
 			if nodeID <= 0 {
 				return actool.Errorf("invalid finding_id"), nil
 			}
+			poe := 0
+			if a.PoELevel != nil {
+				poe = *a.PoELevel
+			}
+			if poe < 0 || poe > 4 {
+				return actool.Errorf(fmt.Sprintf("invalid poe_level %d (want 0-4)", poe)), nil
+			}
+			notFound := actool.Errorf(fmt.Sprintf("no vulnerability record found for finding_id=%d (register it with report_finding first)", nodeID))
+			findingID, err := s.m.pg.FindingIDByNodeID(nodeID)
+			if errors.Is(err, sql.ErrNoRows) {
+				return notFound, nil
+			}
+			if err != nil {
+				return actool.Errorf(err.Error()), nil
+			}
 			n, err := s.m.pg.SetFindingReportVersionByNodeID(ctx, nodeID, a.Report, a.EvidenceVersion)
 			if err != nil {
 				return actool.Errorf(err.Error()), nil
 			}
 			if n == 0 {
-				return actool.Errorf(fmt.Sprintf("no vulnerability record found for finding_id=%d (register it with report_finding first)", nodeID)), nil
+				return notFound, nil
 			}
-			return actool.Text(fmt.Sprintf("finding %d report updated (%d chars)", nodeID, len(a.Report))), nil
+			// The report is saved above; verification only decides the status. A
+			// downgrade is recorded and reported, never used to drop the report.
+			status, note := s.assessFindingVerification(ctx, findingID, poe, a.EvidenceQuotes)
+			if err := s.m.pg.SetFindingVerification(findingID, status, poe, note); err != nil {
+				return actool.Errorf("report saved, but verification not recorded: " + err.Error()), nil
+			}
+			msg := fmt.Sprintf("finding %d report updated (%d chars)\nverification: %s", nodeID, len(a.Report), status)
+			if status == db.VerificationVerified {
+				msg += fmt.Sprintf(" (POE L%d)", poe)
+			} else {
+				msg += " - " + note + "\nwarning: the report is saved but the finding is not verified. To reach verified, declare poe_level 3 or 4 and pass exact quotes copied from a bound proof/verification response body."
+			}
+			return actool.Text(msg), nil
 		})
 }
 
@@ -513,6 +546,7 @@ func (s *Server) seedOrchestrationTools() {
 	s.upgradeReporterTriggerMessage() // backfill migration for old DBs: makes the reporter send evidence_version back (one-time)
 	s.seedFindingTrafficTools()       // adds optional evidence params and read-only evidence tools, preserving user config
 	s.seedFindingWorkflowTools()
+	s.seedFindingVerificationSchema() // S1: poe_level / evidence_quotes on update_finding_report, added once per DB
 	// Note: pentest's default tool bindings need no migration — BuiltinToolSeeds already seeds
 	// list_assets/insert_assets/report_finding/list_findings/list_companies together with
 	// pentest at fresh initialization (no old DBs exist in this project, so no migration).