docs: scrub PII/IPs from gpu-bakeoff

- Rename host alias matt-strix -> strix-halo (removes third-party name)
- Move host URLs to env-var lookup (OLLAMA_*_URL), drop hardcoded IPs
  from harness source. Defaults: steel141 keeps localhost; pve197 and
  strix-halo require their env var to be set before use.
- Update doc: remove the Tailscale IP and LAN-IP references, describe
  access paths without specific addresses.
- Rename runs/matt-strix -> runs/strix-halo and patch the host field
  in each JSON.

Harness still functional for the original author (set the env vars)
and safe to share without leaking routable addresses.

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

scripts/gpu-bakeoff/harness.py

@@ -5,7 +5,7 @@ three hosts:
 
   - steel141  : RTX 3090 Ti (24 GB GDDR6X, compute 8.6, ~1008 GB/s)
   - pve197    : Tesla V100-PCIE-32GB (32 GB HBM2, compute 7.0, ~900 GB/s)
-  - matt-strix: AMD Strix Halo iGPU (shared LPDDR5X, ~256 GB/s)
+  - strix-halo: AMD Strix Halo iGPU (shared LPDDR5X, ~256 GB/s)
 
 Per (host, model, prompt_length), runs 1 warmup + N measurement runs,
 records Ollama's canonical timing fields, and writes one JSON trace to
@@ -15,6 +15,13 @@ All three Ollama servers are polled via HTTP; no SSH required. All
 timings come from Ollama's own /api/generate response fields so wall-
 clock jitter between the harness and the server is excluded.
 
+Host URLs are resolved from environment variables so routable addresses
+don't live in source. Set these before running against non-local hosts:
+
+    OLLAMA_STEEL141_URL=http://127.0.0.1:11434
+    OLLAMA_PVE197_URL=http://<lan-ip>:11434
+    OLLAMA_STRIX_URL=http://<tailscale-ip>:11434
+
 Invocation:
     python3 harness.py --host steel141 --model gemma4:26b --prompt short
     python3 harness.py all   # runs the full planned matrix
@@ -24,6 +31,7 @@ from __future__ import annotations
 
 import argparse
 import json
+import os
 import sys
 import time
 import urllib.request
@@ -31,16 +39,30 @@ from pathlib import Path
 
 
 HOSTS = {
-    "steel141":   {"url": "http://127.0.0.1:11434",       "gpu": "RTX 3090 Ti",           "vram_gb": 24},
-    "pve197":     {"url": "http://192.168.0.179:11434",   "gpu": "Tesla V100-PCIE-32GB",  "vram_gb": 32},
-    "matt-strix": {"url": "http://100.117.155.64:11434",  "gpu": "AMD Strix Halo iGPU",   "vram_gb": None},
+    "steel141":   {"url_env": "OLLAMA_STEEL141_URL", "default_url": "http://127.0.0.1:11434",
+                   "gpu": "RTX 3090 Ti",          "vram_gb": 24},
+    "pve197":     {"url_env": "OLLAMA_PVE197_URL",   "default_url": None,
+                   "gpu": "Tesla V100-PCIE-32GB", "vram_gb": 32},
+    "strix-halo": {"url_env": "OLLAMA_STRIX_URL",    "default_url": None,
+                   "gpu": "AMD Strix Halo iGPU",  "vram_gb": None},
 }
 
-# Per-host model tag mapping. matt-strix uses gemma4:31b, the others
+
+def _host_url(host: str) -> str:
+    cfg = HOSTS[host]
+    url = os.environ.get(cfg["url_env"]) or cfg["default_url"]
+    if not url:
+        raise RuntimeError(
+            f"host {host!r} has no URL — set ${cfg['url_env']} in env"
+        )
+    return url
+
+
+# Per-host model tag mapping. strix-halo uses gemma4:31b, the others
 # use gemma4:31b-it-q4_K_M — identical weights, different tags.
 MODEL_ALIASES = {
-    "gemma4:26b":  {"steel141": "gemma4:26b",            "pve197": "gemma4:26b",            "matt-strix": "gemma4:26b"},
-    "gemma4:31b":  {"steel141": "gemma4:31b-it-q4_K_M",  "pve197": "gemma4:31b-it-q4_K_M",  "matt-strix": "gemma4:31b"},
+    "gemma4:26b":  {"steel141": "gemma4:26b",            "pve197": "gemma4:26b",            "strix-halo": "gemma4:26b"},
+    "gemma4:31b":  {"steel141": "gemma4:31b-it-q4_K_M",  "pve197": "gemma4:31b-it-q4_K_M",  "strix-halo": "gemma4:31b"},
     # V100-only edge case — only 32 GB host has headroom for the Q8 MoE.
     "gemma4:26b-q8":  {"pve197": "gemma4:26b-a4b-it-q8_0"},
 }
@@ -151,7 +173,7 @@ def run_matrix(
         return {"host": host, "model_alias": model_alias, "skipped": "model not available on host"}
 
     prompt = PROMPTS[prompt_key]
-    url = host_cfg["url"]
+    url = _host_url(host)
 
     trace = {
         "host": host,