profile(kvc): add D KV pool timeseries poller + analyzer for v6 root-cause

v5 dropped errors but pushed session-cap fallback to 46-51%. Before adding
v6 mitigations we need to attribute that capacity loss to one of:
  (a) active sessions — real footprint
  (b) idle-evictable sessions — LRU not aggressive enough
  (c) prefill backup blocks / in-flight / fragmentation — release timing

Without this it's all guessing. Plumb a 1Hz poller into replay that hits
each P/D worker's /server_info, captures session_cache + memory_usage, and
writes a per-worker time-series JSONL to <run_dir>/d-pool-timeseries.jsonl.
Off by default (--pool-poll-interval-s 0); v5+profile sweep enables it at
1.0s. Per-tick HTTP cost is ~8 parallel /server_info calls — negligible
relative to the 50min run.

Analyzer (scripts/analysis/analyze_pool_timeseries.py) decomposes each D's
capacity into active_held / idle_evictable / other (= cap-held-avail, the
backup-blocks bucket) / free, and reports session residency churn across
workers as a starvation/thrashing signal.

Mock-tested poller end-to-end (cancellation clean, file flushed, sessions
captured); analyzer validated against synthetic timeseries.

Next: run scripts/sweep_tp1_v5_optD_profile.sh on hardware (~90min), then
analyze results to pick a v6 direction.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/agentic_pd_hybrid/benchmark.py

@@ -43,6 +43,8 @@ class BenchmarkConfig:
     kvcache_prefill_priority_eviction: bool = False
     kvcache_prefill_direct_priority: int = -100
     kvcache_prefill_normal_priority: int = 100
+    pool_poll_interval_s: float = 0.0
+    pool_poll_include_sessions: bool = True
     sample_profile: str = "default"
     min_initial_input_tokens: int | None = None
     max_initial_input_tokens: int | None = None
@@ -190,6 +192,8 @@ def run_live_benchmark(config: BenchmarkConfig) -> BenchmarkArtifacts:
             ),
             kvcache_prefill_direct_priority=config.kvcache_prefill_direct_priority,
             kvcache_prefill_normal_priority=config.kvcache_prefill_normal_priority,
+            pool_poll_interval_s=config.pool_poll_interval_s,
+            pool_poll_include_sessions=config.pool_poll_include_sessions,
         )
         if config.request_timeout_s is not None:
             replay_config = replace(
@@ -246,6 +250,8 @@ def run_live_benchmark(config: BenchmarkConfig) -> BenchmarkArtifacts:
                 "kvcache_prefill_normal_priority": (
                     config.kvcache_prefill_normal_priority
                 ),
+                "pool_poll_interval_s": config.pool_poll_interval_s,
+                "pool_poll_include_sessions": config.pool_poll_include_sessions,
                 "sample_profile": config.sample_profile,
                 "min_initial_input_tokens": config.min_initial_input_tokens,
                 "max_initial_input_tokens": config.max_initial_input_tokens,