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/tp2_mns8/anchor-0.4921875/result.json

@@ -0,0 +1,74 @@
+{
+  "anchor": 0.4921875,
+  "cell": "tp2_mns8",
+  "early_stop_reason": "slo_pass_rate_unrecoverable",
+  "early_stopped": true,
+  "exact_output_count": 216,
+  "feasible": false,
+  "interval": {
+    "elapsed_s": 51.56724132,
+    "end_mono_ns": 201214250324754,
+    "end_wall_ns": 1783869641376751823,
+    "start_mono_ns": 201162683083434,
+    "start_wall_ns": 1783869589809510519
+  },
+  "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": 8,
+  "observed_count": 269,
+  "pass_rate": 0.6914498141263941,
+  "schema": 1,
+  "selection": {
+    "arrival_order_sha256": "ffbc7b8dd324c8e745654110a2412b03ddade891beb2bfe022ffde6502b0184b",
+    "arrival_s": {
+      "distinct_n": 269,
+      "finite_n": 269,
+      "max": 59.78950000000005,
+      "min": 0.008300000000008368,
+      "missing_n": 0,
+      "n": 269
+    },
+    "count": 269,
+    "long_gt4096": 95,
+    "offered_req_s": 4.483333333333333,
+    "offered_req_s_per_gpu": 2.2416666666666667,
+    "raw_input_tokens": {
+      "distinct_n": 250,
+      "finite_n": 269,
+      "max": 8149.0,
+      "min": 71.0,
+      "missing_n": 0,
+      "n": 269
+    },
+    "raw_length_order_sha256": "bc951350376a487d34d2def78fd32a2286e23bf8a7f481ff578009e12e3f1fb8",
+    "request_id_order_sha256": "cd227aee3be472a35e8c35af60a44a1411c4dc689cbd98746b3fb8a8d329b44c"
+  },
+  "slo_pass_count": 186,
+  "study_sha256": "9474f0d0b53579f1db852ca68abfb0b96ba43ae4e17738118bf8e3209eb09ece",
+  "tp": 2,
+  "tpot_ms": {
+    "distinct_n": 216,
+    "finite_n": 216,
+    "max": 22.936211125952685,
+    "min": 5.354799519524008,
+    "missing_n": 53,
+    "n": 269
+  },
+  "ttft_ms": {
+    "distinct_n": 216,
+    "finite_n": 216,
+    "max": 3692.623541021021,
+    "min": 40.143018995877355,
+    "missing_n": 53,
+    "n": 269
+  }
+}