Add barrier-confirmed yielding, measured residency, persistence and closed-loop tuning

Nine changes, in rough order of how much they affect real behaviour:

1. VRAM yield is now a barrier. Posting keep_alive:0 only asks Ollama to unload;
   measured here, the HTTP call returns in 63ms while the driver takes a further
   77ms to release 14.9GB. Returning inside that window is how ComfyUI ends up
   allocating into VRAM that is still occupied. instant_free_ollama_vram() polls
   NVML until the allocation is actually gone and reports request/confirm split.

2. ComfyUI VRAM is no longer purged 1.5s after every prompt, which forced a full
   checkpoint reload on each workflow iteration. It is held for 30s of genuinely
   empty queue, with an immediate purge when Ollama actually asks for the memory.

3. Cache-hit classification uses achieved bandwidth (size / load duration) rather
   than a fixed `load_duration < 2500ms`. That constant called a 12.9GB model read
   at 2.9GB/s a cold load, and a 0.5GB model read from NVMe a cache hit.

4. Page-cache residency is measured, not assumed. mincore(2) reported 128GB
   resident on a box with 46GB of page cache: the kernel only permits page-cache
   introspection on files you own, and the Ollama blobs are owned by uid ollama,
   for which mincore answers "all resident" instead of failing. Uses cachestat(2)
   where permitted and a randomised read-rate probe elsewhere, labelling which was
   used. Fixed-offset probing was self-fulfilling, so windows are random and cold
   ones are returned with FADV_DONTNEED.

5. Warming is budgeted and ranked by recency/frequency instead of reading every
   file top-to-bottom, which on 64GB of RAM just evicts whatever was warmed first.

6. Telemetry and events persist to SQLite (~0.38 MB/hour) instead of living in a
   50-entry in-memory deque, so /api/analytics/profiles can finally answer whether
   an overclock profile actually delivers more tok/s.

7. Thermal governor walks the overclock back on sustained heat or hardware
   throttling, with hysteresis, fed from the existing sampler.

8. Autotune sweeps a clock offset, benchmarks decode at each step, watches for Xid
   errors and degenerate output, and restores the profile in a finally block.

9. Stock clocks/power/fans are restored on shutdown and via systemd ExecStopPost.
   Nothing previously undid a locked clock or a manually pinned fan.

Also: one shared 1Hz telemetry sampler fanned out to SSE subscribers rather than
every client re-running the whole snapshot; wall-clock timestamps in place of the
event loop's monotonic clock; cached nvidia-smi shell-outs; quieter httpx logging.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

overclock_profiles.json

@@ -2,8 +2,8 @@
   "ollama": {
     "label": "Ollama \u2014 LLM decode (memory-bandwidth bound)",
     "power_limit_w": 370,
-    "core_offset_mhz": 150,
-    "mem_offset_mhz": 825,
+    "core_offset_mhz": 35,
+    "mem_offset_mhz": 200,
     "lock_core_min": 0,
     "lock_core_max": 0,
     "lock_mem_mhz": 0,
@@ -14,12 +14,12 @@
     "label": "ComfyUI \u2014 diffusion (core-compute bound)",
     "power_limit_w": 370,
     "core_offset_mhz": 100,
-    "mem_offset_mhz": 500,
+    "mem_offset_mhz": 150,
     "lock_core_min": 2900,
     "lock_core_max": 3105,
     "lock_mem_mhz": 0,
     "fan_mode": "manual",
-    "fan_speed_pct": 75
+    "fan_speed_pct": 100
   },
   "balanced": {
     "label": "Balanced \u2014 stock boost, power unlocked",