v3 M3: z.ai (GLM) provider — Anthropic-compatible poll from a pasted API key

ZaiProvider replaces the zai stub. It reaches z.ai's Anthropic-compatible
endpoint (default https://api.z.ai/api/anthropic) exactly like Claude Code with
ANTHROPIC_BASE_URL pointed at z.ai: a /v1/messages POST with a Bearer key. The
key + base URL come from the config the control panel's z.ai field writes
(providers.zai.base_url/.api_key) — no OAuth, no local files.

Two z.ai-specific cares: (1) static API key, no self-refresh; (2) the GLM Coding
Plan meters by prompts, so a 60s poll would drain quota — the provider
self-throttles to one network call per poll_interval_s (default 15 min) and
serves a cached status in between. Rate-limit parsing assumes z.ai proxies
Anthropic's unified headers (5h->s/sr, 7d->w/wr); if a real response lacks them
it still reports connected and logs the limit-ish headers it did return, so the
mapping can be finalized against a live key.

tools/probe_zai.py dumps a real z.ai response's headers (key via env, never
printed) to pin the exact header names. Graceful without a key: selecting z.ai
shows the blue theme + "no key", never crashes the loop. Registry: all three
providers now real; unknown ids fall back to StubProvider. +7 z.ai tests (mocked
transport: header mapping, auth, throttle, fallback); 120 passed, 2 Linux-only.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

tools/probe_zai.py

@@ -0,0 +1,54 @@
+#!/usr/bin/env python3
+"""One-off diagnostic: see exactly what z.ai's Anthropic-compatible endpoint
+returns, so the ZaiProvider's rate-limit header mapping can be finalized against
+a real response (the header names aren't documented).
+
+Usage (key via env so it never lands in shell history):
+    ZAI_API_KEY=... python tools/probe_zai.py [base_url] [model]
+
+Defaults: base = https://api.z.ai/api/anthropic , model = glm-4.6
+
+Prints the HTTP status and the FULL response header set (highlighting any header
+mentioning limit/rate/quota/usage/reset), plus a short body preview. Sends a
+1-token "hi" — on a prompt-metered plan that is one prompt, so run it sparingly.
+The API key is read from the environment and never printed.
+"""
+import json
+import os
+import sys
+
+import httpx
+
+BASE = (sys.argv[1] if len(sys.argv) > 1 else "https://api.z.ai/api/anthropic").rstrip("/")
+MODEL = sys.argv[2] if len(sys.argv) > 2 else "glm-4.6"
+KEY = os.environ.get("ZAI_API_KEY") or os.environ.get("ANTHROPIC_AUTH_TOKEN")
+
+if not KEY:
+    sys.exit("Set ZAI_API_KEY in the environment first (it is not printed).")
+
+url = f"{BASE}/v1/messages"
+headers = {
+    "Authorization": f"Bearer {KEY}",
+    "anthropic-version": "2023-06-01",
+    "Content-Type": "application/json",
+}
+body = {"model": MODEL, "max_tokens": 1, "messages": [{"role": "user", "content": "hi"}]}
+
+print(f"POST {url}  (model={MODEL})")
+try:
+    resp = httpx.post(url, headers=headers, json=body, timeout=30.0)
+except httpx.HTTPError as e:
+    sys.exit(f"request failed: {e}")
+
+print(f"HTTP {resp.status_code}\n")
+INTEREST = ("limit", "rate", "quota", "usage", "reset", "remaining")
+print("--- response headers ---")
+for k in sorted(resp.headers.keys()):
+    mark = "  <<<" if any(w in k.lower() for w in INTEREST) else ""
+    print(f"  {k}: {resp.headers[k]}{mark}")
+
+print("\n--- body preview ---")
+try:
+    print(json.dumps(resp.json(), ensure_ascii=False)[:600])
+except ValueError:
+    print(resp.text[:600])