feat(analyzer): surface TTFT/TPOT as features and CDF figures

The gateway records three epoch-ms stamps per request (admitted, forwarded to
backend, backend first token). They reached *-raw.jsonl but stopped there:
features.csv had only total latency, and none of the figures covered
time-to-first-token.

Derive ttft_ms, ttft_e2e_ms and tpot_ms in one helper shared by the streaming
path (preparation.py) and the in-memory path (features.py) so the two cannot
drift, and add figures 14 (TTFT, backend vs end-to-end) and 15 (TPOT). The two
TTFT series are plotted together because their offset is the gateway admission
delay, which is then readable straight off the chart.

Rows missing a backend stamp and single-token responses are recorded as 0 and
filtered at plot time; left in, they would stack at the origin and pull every
percentile down. Figure 15 is a single panel: TPOT is near-deterministic
(p50 21.9, p90 23.0), so a p90 zoom renders a flat line and a vertical edge.

Verified by recomputing ttft_ms straight from the original SLS rows for all
2190 requests of a sample: 0 mismatches.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

trace_analyzer/features.py

@@ -1,7 +1,7 @@
 from collections import Counter
 from dataclasses import asdict
 
-from .helpers import percentile, safe_div
+from .helpers import latency_breakdown, percentile, safe_div
 from .models import TraceFeatures
 
 LONG_CONTEXT_THRESHOLD = 32000
@@ -75,6 +75,7 @@ def compute_features(records):
             high_cache=1 if cache_hit_ratio >= HIGH_CACHE_THRESHOLD else 0,
             tool_burst_alert=1 if (max(bursts) if bursts else 0) >= TOOL_BURST_THRESHOLD else 0,
             tool_loop_alert=1 if tool_to_tool_count >= TOOL_LOOP_THRESHOLD else 0,
+            **latency_breakdown(record.meta, output_tokens),
         )
         feature.pattern_labels = base_pattern_labels(feature)
         features.append(feature)