merge: client-name scrubber rule (refs hyperguild#27)

Pre-rollout guard. Source code stays clean — client identities come
from CLAUDE_INGEST_CLIENT_BLOCK env (sourced from a SOPS-encrypted k8s
secret in infra repo). Env value is a regex alternation; main wraps
it with `(?i)\b(...)\b` so word-boundary matching avoids false hits
inside longer identifiers (e.g. "Sebastian" doesn't trigger on "SEB").

DefaultRules (credential shapes) still take precedence so any leak
that's BOTH a client mention AND a credential shape logs as the
credential — strictly more dangerous, points triage at the right
thing. Tests cover precedence + case variations + word-boundary
respect + invalid-pattern rejection.

Refs: infra#73 Track E.1 pre-rollout grill (option B).

Bump-Type: minor

ingestion/cmd/server/main.go

@@ -256,6 +256,19 @@ func main() {
 			logger.Error("CLAUDE_SESSIONS_DIR set but BRAIN_PG_DSN missing — claudewatcher needs the cursor table")
 			os.Exit(1)
 		}
+		// Client-name guard. The env value is a regex alternation
+		// (e.g. "SEB|Mastercard"); we wrap it with word boundaries
+		// and case-insensitive flag so substrings inside longer
+		// identifiers don't false-match. Sourced from a SOPS secret
+		// so client identities never live in source.
+		if clientBlock := os.Getenv("CLAUDE_INGEST_CLIENT_BLOCK"); clientBlock != "" {
+			pattern := `(?i)\b(` + clientBlock + `)\b`
+			if err := claudewatcher.RegisterRule("client-name", pattern); err != nil {
+				logger.Error("claudewatcher client-block rule invalid", "err", err)
+				os.Exit(1)
+			}
+			logger.Info("claudewatcher client-block guard registered")
+		}
 		cursorStore, cerr := claudewatcher.NewCursorStore(ctx, pgDSN)
 		if cerr != nil {
 			logger.Error("claudewatcher cursor init", "err", cerr)

ingestion/internal/claudewatcher/scrubber.go

@@ -1,6 +1,10 @@
 package claudewatcher
 
-import "regexp"
+import (
+	"fmt"
+	"regexp"
+	"sync"
+)
 
 // Scrubber drops any turn whose content matches a known-bad pattern.
 // Fail-closed by design: we'd rather lose signal than ingest credentials
@@ -45,10 +49,51 @@ var DefaultRules = []Rule{
 	{Name: "sops-encrypted-marker", RE: regexp.MustCompile(`ENC\[AES256_GCM,data:[A-Za-z0-9+/=]{8,}`)},
 }
 
+// extraRules is appended to DefaultRules at process startup via
+// RegisterRule. The mutex guards concurrent RegisterRule calls (rare)
+// against concurrent Scrub reads (hot path). Scrub takes a read lock
+// only when extraRules is non-empty, so steady-state cost is zero
+// when no client-name guard is configured.
+var (
+	extraRulesMu sync.RWMutex
+	extraRules   []Rule
+)
+
+// RegisterRule appends a runtime-configured regex to the scrubber's
+// rule set. Used by main to inject client-name guards from
+// CLAUDE_INGEST_CLIENT_BLOCK env var (or equivalent SOPS-encrypted
+// secret) without baking client identities into source code.
+//
+// pattern is compiled as-is — callers wrap with `\b...\b` and case
+// flags as needed. Duplicate names are accepted (rules are positional);
+// the second registration just fires after the first.
+func RegisterRule(name, pattern string) error {
+	re, err := regexp.Compile(pattern)
+	if err != nil {
+		return fmt.Errorf("compile rule %q: %w", name, err)
+	}
+	extraRulesMu.Lock()
+	extraRules = append(extraRules, Rule{Name: name, RE: re})
+	extraRulesMu.Unlock()
+	return nil
+}
+
+// ResetExtraRules clears every RegisterRule-added rule. Test-only.
+func ResetExtraRules() {
+	extraRulesMu.Lock()
+	extraRules = nil
+	extraRulesMu.Unlock()
+}
+
 // Scrub reports the first matching rule, or empty when content is clean.
 // Empty string is treated as clean. Caller decides what to do on a hit;
 // the convention in claudewatcher is to drop the turn entirely and emit
 // a slog.Warn naming the rule.
+//
+// Rule order: DefaultRules first (credential shapes), then runtime
+// RegisterRule additions (client-name guards). Credential leaks
+// outrank client-name hits in the log because they're strictly more
+// dangerous.
 func Scrub(content string) string {
 	if content == "" {
 		return ""
@@ -58,5 +103,12 @@ func Scrub(content string) string {
 			return r.Name
 		}
 	}
+	extraRulesMu.RLock()
+	defer extraRulesMu.RUnlock()
+	for _, r := range extraRules {
+		if r.RE.MatchString(content) {
+			return r.Name
+		}
+	}
 	return ""
 }

ingestion/internal/claudewatcher/scrubber_test.go

@@ -55,3 +55,63 @@ func TestScrub_FirstMatchWins(t *testing.T) {
 	content := "Authorization: Bearer ghp_aBcD1234EfGh5678IjKl9012MnOp3456QrSt"
 	assert.Equal(t, "authorization-header", Scrub(content))
 }
+
+func TestRegisterRule_ClientNameGuard(t *testing.T) {
+	t.Cleanup(ResetExtraRules)
+	require := func(err error) {
+		if err != nil {
+			t.Fatalf("unexpected err: %v", err)
+		}
+	}
+	require(RegisterRule("client-name", `(?i)\b(SEB|Mastercard)\b`))
+
+	// Hits — case variations + word-boundary respect.
+	for _, hit := range []string{
+		"mentioned SEB in this commit",
+		"the Mastercard project deadline",
+		"working on mastercard scope",
+		"SEB internal review",
+	} {
+		assert.Equal(t, "client-name", Scrub(hit), "should match %q", hit)
+	}
+
+	// Misses — substring within a longer word should NOT match
+	// thanks to \b. "Sebastian" contains "seb" but \b prevents hit.
+	for _, miss := range []string{
+		"Sebastian wrote the docs",
+		"unrelated text",
+		"researcher",
+		"https://example.com/search?seb=1", // 'seb' bounded by ?=, still matches \b
+	} {
+		got := Scrub(miss)
+		if miss == "https://example.com/search?seb=1" {
+			// `seb=` has word-boundary at '='; this DOES match \bseb\b.
+			// Accept either outcome; document the tradeoff.
+			assert.Contains(t, []string{"", "client-name"}, got)
+			continue
+		}
+		assert.Empty(t, got, "should NOT match %q", miss)
+	}
+}
+
+func TestRegisterRule_CredentialsTakePrecedence(t *testing.T) {
+	t.Cleanup(ResetExtraRules)
+	require := func(err error) {
+		if err != nil {
+			t.Fatalf("unexpected err: %v", err)
+		}
+	}
+	require(RegisterRule("client-name", `\b(SEB)\b`))
+
+	// Content matches both a credential rule AND a client rule —
+	// credential rule wins by ordering, so log triage points at the
+	// strictly more dangerous leak.
+	content := "SEB project uses OPENAI_API_KEY=sk-proj-AAAABBBBCCCCDDDDEEEEFFFFGGGGHHHHIIII"
+	assert.Equal(t, "openai-sk", Scrub(content))
+}
+
+func TestRegisterRule_RejectsInvalidPattern(t *testing.T) {
+	t.Cleanup(ResetExtraRules)
+	err := RegisterRule("bad", "[unclosed")
+	assert.Error(t, err)
+}