Add OpProf campaign: protocols, results, patches, run evidence (P0-P6)

Workload-conditioned operator profiling on patched vLLM 0.24.0 +
Qwen3-30B-A3B/H20. H1b PASS (irregular patterns carry +23-45pp R64
raggedness, 8-45% token-efficiency loss vs rectangular controls);
mechanism decomposition kills the padding narrative and finds the
arrival-uniformization artifact (-12.9%); cross-version churn surface
shows TP2/MNS64 -29.4% across vLLM 0.20->0.24 while the argmax held.
Raw Layer-1 JSONL streams (507 MB) stay on disk, git-ignored; footer
sidecars and metrics are tracked.

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

runs/opprof-phase6/phase6/cells/tp4_mns16/confirm-1-anchor-0.033717411016/result.json

@@ -0,0 +1,74 @@
+{
+  "anchor": 0.033717411016,
+  "cell": "tp4_mns16",
+  "early_stop_reason": "",
+  "early_stopped": false,
+  "exact_output_count": 586,
+  "feasible": true,
+  "interval": {
+    "elapsed_s": 61.364052595,
+    "end_mono_ns": 201800328727441,
+    "end_wall_ns": 1783870227455155582,
+    "start_mono_ns": 201738964674846,
+    "start_wall_ns": 1783870166091102450
+  },
+  "invariants": {
+    "arrival_nondecreasing": true,
+    "exact_output_or_failed": true,
+    "outcomes_cover_selected": true,
+    "raw_lengths_present": true,
+    "selected_nonempty": true,
+    "warmup_16": true,
+    "warmup_exact_16": true,
+    "warmup_long": true
+  },
+  "kind": "anchor",
+  "mns": 16,
+  "observed_count": 586,
+  "pass_rate": 1.0,
+  "schema": 1,
+  "selection": {
+    "arrival_order_sha256": "fe44bf6b0efd6e6ab4d19676e34ace608827e419dbb5c19c8595992f0339c9b1",
+    "arrival_s": {
+      "distinct_n": 585,
+      "finite_n": 586,
+      "max": 59.90990000000002,
+      "min": 0.13000000000001818,
+      "missing_n": 0,
+      "n": 586
+    },
+    "count": 586,
+    "long_gt4096": 184,
+    "offered_req_s": 9.766666666666667,
+    "offered_req_s_per_gpu": 2.441666666666667,
+    "raw_input_tokens": {
+      "distinct_n": 534,
+      "finite_n": 586,
+      "max": 8157.0,
+      "min": 69.0,
+      "missing_n": 0,
+      "n": 586
+    },
+    "raw_length_order_sha256": "e2d040068b279e99073f6965d1136eb0ca6e8534c883f331b4cb85c5fc7a4650",
+    "request_id_order_sha256": "472a874ecc0e844b5b36a715bbc309b63e73074d39327cd734869f76721d71db"
+  },
+  "slo_pass_count": 586,
+  "study_sha256": "76e9d642ba9570917cfeeea848ed92f27904e87760eedabd48805b84e82eca26",
+  "tp": 4,
+  "tpot_ms": {
+    "distinct_n": 586,
+    "finite_n": 586,
+    "max": 14.420212055125647,
+    "min": 4.217363204660378,
+    "missing_n": 0,
+    "n": 586
+  },
+  "ttft_ms": {
+    "distinct_n": 586,
+    "finite_n": 586,
+    "max": 819.4046519929543,
+    "min": 36.395939998328686,
+    "missing_n": 0,
+    "n": 586
+  }
+}