probe: show raw responses

.github/workflows/probe.yml

@@ -14,18 +14,31 @@ jobs:
           GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         run: |
           python3 - <<'PY'
-          import json, os, urllib.request
+          import json, os, urllib.request, urllib.error
           tok = os.environ["GH_TOKEN"]
-          h = {"Authorization": f"Bearer {tok}", "Accept": "application/json"}
-          req = urllib.request.Request("https://models.github.ai/catalog/models", headers=h)
-          cat = json.loads(urllib.request.urlopen(req, timeout=30).read())
-          print(f"{len(cat)} models")
-          for m in cat:
-              print(m["id"], "|", m.get("rate_limit_tier"), "|", m.get("publisher"))
-          body = {"model": "openai/gpt-4.1-mini", "messages": [{"role": "user", "content": "Reply with exactly: ok"}]}
-          req = urllib.request.Request("https://models.github.ai/inference/chat/completions",
-                                       data=json.dumps(body).encode(), method="POST",
-                                       headers={**h, "Content-Type": "application/json"})
-          out = json.loads(urllib.request.urlopen(req, timeout=60).read())
-          print("inference:", out["choices"][0]["message"]["content"])
+          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