feat: add per-source TTFB and tokens/s metrics to status page

- Req: add FirstByteMs field (ms to first byte, tracked for streaming)
- Stat: add FirstByteSum for aggregation
- SourceAverages(): new method computing per-source avg TTFB and tokens/s
  from the in-memory ring (300s window)
- SourceStatus: add AvgFirstByteMs and AvgTokPerS fields
- pumpStream: record FirstByteMs after first SSE chunk sent to client
- singleChat/singleChatAuto: set FirstByteMs = LatMs (non-streaming)
- handleStatusAPI: populate the new SourceStatus fields from SourceAverages()
- WebUI source table: two new columns showing TTFB (s) and Tokens/s

internal/provider/registry.go

@@ -217,6 +217,12 @@ type SourceStatus struct {
 	// probe was rate-limited by the upstream).
 	RecentOK  int64 `json:"recent_ok,omitempty"`
 	RecentErr int64 `json:"recent_err,omitempty"`
+	// AvgFirstByteMs is the mean time-to-first-byte (ms) for recently
+	// successful requests served by this source (0 when unmeasured).
+	AvgFirstByteMs int64 `json:"avg_first_byte_ms,omitempty"`
+	// AvgTokPerS is the aggregate completion throughput (tokens/s) for
+	// recently successful requests served by this source (0 when no data).
+	AvgTokPerS int64 `json:"avg_tok_per_s,omitempty"`
 }
 
 // ProbeAll runs a live reachability check for every provider (in parallel).