fix(quota): veto 5xx errors + tighten patterns to stop false-positive swaps

v0.2.2's 2-poll confirmation was insufficient because Anthropic 500/503
errors are printed into Claude Code's conversation transcript and stay
visible in every tmux capture until the user scrolls. A persistent
server error would confirm on the second poll and still trigger a swap.

Root cause: the pattern "rate limit" (bare substring) matched any 500
payload that happened to mention rate limits in its error text. Real
HTTP 429s from Anthropic are typed as "rate_limit_error" in the error
payload — and that's the signature we should actually key on.

- Remove "rate limit" from quotaPatterns (too generic — matches transcripts).
- Add "rate_limit_error" (Anthropic's typed 429 error) and "5-hour limit".
- Add serverErrorPatterns veto: "api_error", "overloaded_error",
  "internal server error", "api error: 5". When any is present in the
  pane, isQuotaExhausted returns false even if a quota pattern matched.
- 4 new subtests covering the veto paths + sanity that real 429s pass.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

internal/quota/monitor.go

@@ -23,13 +23,26 @@ type SwitchRequest struct {
 }
 
 // quotaPatterns are substrings that indicate quota exhaustion in a pane.
+// Must be specific enough to avoid matching Anthropic server errors (500/503)
+// that happen to include generic words like "rate limit" in their payload.
 var quotaPatterns = []string{
-	"you've hit your limit",
-	"rate limit",
-	"quota exceeded",
-	"usage limit reached",
-	"claude pro usage",
-	"too many requests",
+	"you've hit your limit",   // Claude Code TUI friendly message
+	"rate_limit_error",        // Anthropic typed error (real HTTP 429)
+	"quota exceeded",          // generic, but specific enough
+	"usage limit reached",     // Claude Pro phrasing
+	"claude pro usage",        // Claude Pro dashboard phrasing
+	"too many requests",       // HTTP 429 status text
+	"5-hour limit",            // Claude Code 5h window phrasing
+}
+
+// serverErrorPatterns indicate a transient upstream server error
+// (Anthropic 500/503), NOT a quota hit. When any of these is present in
+// the pane, we treat the "hit" as a false positive and do NOT swap.
+var serverErrorPatterns = []string{
+	"api_error",               // Anthropic typed error (HTTP 500)
+	"overloaded_error",        // Anthropic typed error (HTTP 503)
+	"internal server error",   // HTTP 500 status text
+	"api error: 5",            // Claude TUI rendering of 5xx
 }
 
 // resetTimeRe extracts reset times like "resets 8pm", "resets at 11:30pm",
@@ -210,9 +223,14 @@ func (m *Monitor) isQuotaPaused() bool {
 	return len(m.switchCh) > 0
 }
 
-// isQuotaExhausted returns true if the pane content indicates quota exhaustion.
+// isQuotaExhausted returns true if the pane content indicates quota exhaustion
+// AND does not simultaneously show a transient server error (which would make
+// the apparent quota match a false positive).
 func isQuotaExhausted(paneContent string) bool {
-	return firstMatchingPattern(paneContent) != ""
+	if firstMatchingPattern(paneContent) == "" {
+		return false
+	}
+	return !hasServerError(paneContent)
 }
 
 // firstMatchingPattern returns the first quota pattern found in paneContent,
@@ -227,6 +245,18 @@ func firstMatchingPattern(paneContent string) string {
 	return ""
 }
 
+// hasServerError reports whether the pane content shows an Anthropic 5xx /
+// transient server error. Used to veto a quota match: a 500 is not a quota.
+func hasServerError(paneContent string) bool {
+	lower := strings.ToLower(paneContent)
+	for _, p := range serverErrorPatterns {
+		if strings.Contains(lower, p) {
+			return true
+		}
+	}
+	return false
+}
+
 // snippet returns a 120-char single-line excerpt of pane content for logging.
 func snippet(s string) string {
 	s = strings.ReplaceAll(s, "\n", " ")

internal/quota/monitor_test.go

@@ -28,25 +28,39 @@ func (m *mockTmux) CapturePaneTail(session string, _ int) (string, error) {
 	return m.paneOutput[session], nil
 }
 
-// TestIsQuotaExhausted verifies pattern matching on pane output.
+// TestIsQuotaExhausted verifies pattern matching on pane output, including
+// the server-error veto that prevents 5xx from being mistaken for quota.
 func TestIsQuotaExhausted(t *testing.T) {
 	cases := []struct {
+		name  string
 		input string
 		want  bool
 	}{
-		{"You've hit your limit for Claude Pro.", true},
-		{"rate limit exceeded", true},
-		{"quota exceeded for this period", true},
-		{"Usage limit reached", true},
-		{"Too many requests", true},
-		{"Some normal output ❯", false},
-		{"❯ ", false},
-		{"still running 5s · ", false},
+		{"friendly hit message", "You've hit your limit for Claude Pro.", true},
+		{"typed rate_limit_error", `{"error":{"type":"rate_limit_error"}}`, true},
+		{"quota exceeded", "quota exceeded for this period", true},
+		{"usage limit", "Usage limit reached", true},
+		{"too many requests", "Too many requests", true},
+		{"5-hour limit", "You've reached the 5-hour limit", true},
+
+		{"normal output", "Some normal output ❯", false},
+		{"empty prompt", "❯ ", false},
+		{"status line", "still running 5s · ", false},
+
+		// Server-error veto cases — these MUST NOT trigger a swap.
+		{"api_error 500 veto", `API Error: 500 {"type":"error","error":{"type":"api_error","message":"Internal server error"}} rate limit`, false},
+		{"overloaded_error veto", `{"error":{"type":"overloaded_error"}} rate limit`, false},
+		{"internal server error veto", "Internal Server Error — rate limit mentioned elsewhere", false},
+
+		// Real 429 should still pass even if generic words are around.
+		{"real rate_limit_error wins", `{"error":{"type":"rate_limit_error","message":"Rate limited"}}`, true},
 	}
 	for _, c := range cases {
-		if got := isQuotaExhausted(c.input); got != c.want {
-			t.Errorf("isQuotaExhausted(%q) = %v, want %v", c.input, got, c.want)
-		}
+		t.Run(c.name, func(t *testing.T) {
+			if got := isQuotaExhausted(c.input); got != c.want {
+				t.Errorf("isQuotaExhausted(%q) = %v, want %v", c.input, got, c.want)
+			}
+		})
 	}
 }
 
@@ -76,7 +90,7 @@ func TestPollTriggersSwitchOnTwoBlockedPoolWithReset(t *testing.T) {
 	tc.sessions["ccl-auto-0"] = true
 	tc.sessions["ccl-auto-1"] = true
 	tc.paneOutput["ccl-auto-0"] = "You've hit your limit for Claude Pro. resets in 45 minutes"
-	tc.paneOutput["ccl-auto-1"] = "rate limit exceeded — resets at 8pm"
+	tc.paneOutput["ccl-auto-1"] = `{"error":{"type":"rate_limit_error"}} — resets at 8pm`
 
 	s := state.New("")
 	s.SetActiveAccount("compte1")
@@ -182,7 +196,7 @@ func TestPollNoTriggerWhenBelowThreshold(t *testing.T) {
 	tc := newMockTmux()
 	tc.sessions["ccl-auto-0"] = true
 	tc.sessions["ccl-auto-1"] = true
-	tc.paneOutput["ccl-auto-0"] = "rate limit exceeded"
+	tc.paneOutput["ccl-auto-0"] = "You've hit your limit"
 	tc.paneOutput["ccl-auto-1"] = "❯ " // fine
 
 	s := state.New("")