probe done: GitHub Models is retired; brains go through Venice

.github/workflows/probe.yml

@@ -1,44 +0,0 @@
-name: probe
-# One-off: what can Time reach from a GitHub-hosted runner with no secrets?
-on: workflow_dispatch
-permissions:
-  contents: read
-  models: read
-jobs:
-  probe:
-    runs-on: ubuntu-latest
-    timeout-minutes: 5
-    steps:
-      - name: GitHub Models catalog + one call
-        env:
-          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: |
-          python3 - <<'PY'
-          import json, os, urllib.request, urllib.error
-          tok = os.environ["GH_TOKEN"]
-          h = {"Authorization": f"Bearer {tok}", "Accept": "application/vnd.github+json",
-               "X-GitHub-Api-Version": "2022-11-28"}
-          def call(url, body=None):
-              req = urllib.request.Request(url, headers={**h, "Content-Type": "application/json"},
-                                           data=json.dumps(body).encode() if body else None,
-                                           method="POST" if body else "GET")
-              try:
-                  with urllib.request.urlopen(req, timeout=60) as r:
-                      return r.status, r.headers.get("Content-Type"), r.read().decode(errors="replace")
-              except urllib.error.HTTPError as e:
-                  return e.code, e.headers.get("Content-Type"), e.read().decode(errors="replace")
-          st, ct, txt = call("https://models.github.ai/catalog/models")
-          print("catalog:", st, ct, len(txt), "bytes")
-          try:
-              for m in json.loads(txt):
-                  print(" ", m["id"], "|", m.get("rate_limit_tier"))
-          except Exception:
-              print("  raw:", txt[:300])
-          for model in ("openai/gpt-4.1-mini", "xai/grok-3-mini", "deepseek/deepseek-v3-0324", "meta/llama-4-scout-17b-16e-instruct"):
-              st, ct, txt = call("https://models.github.ai/inference/chat/completions",
-                                 {"model": model, "messages": [{"role": "user", "content": "Reply with exactly: ok"}]})
-              try:
-                  print("inference", model, st, json.loads(txt)["choices"][0]["message"]["content"][:40])
-              except Exception:
-                  print("inference", model, st, txt[:200])
-          PY