fix(#544): harden Bezalel Gemma4 VPS wiring proof

scripts/README_bezalel_gemma4_vps.md

@@ -0,0 +1,51 @@
+# Bezalel Gemma 4 VPS Wiring
+
+Issue: timmy-home #544
+
+This helper is the repo-side operator bundle for wiring a live Gemma 4 endpoint into Bezalel's VPS config without hardcoding one dead pod forever.
+
+What `scripts/bezalel_gemma4_vps.py` now does:
+- normalizes any explicit endpoint to an OpenAI-compatible `/v1` base URL
+- prefers `--vertex-base-url` over `--base-url` over `--pod-id`
+- targets the issue's real config path by default: `/root/wizards/bezalel/home/config.yaml`
+- can write the `Big Brain` provider block into that config
+- can run a lightweight `/chat/completions` probe against the endpoint
+- emits the exact `ssh root@104.131.15.18 ... curl ...` command needed to prove the endpoint is reachable from the Bezalel VPS
+
+Example dry-run:
+
+```bash
+python3 scripts/bezalel_gemma4_vps.py \
+  --base-url https://<pod-id>-11434.proxy.runpod.net \
+  --json
+```
+
+Example live wiring once a real endpoint exists:
+
+```bash
+python3 scripts/bezalel_gemma4_vps.py \
+  --base-url https://<pod-id>-11434.proxy.runpod.net \
+  --config-path /root/wizards/bezalel/home/config.yaml \
+  --write-config \
+  --verify-chat
+```
+
+If Vertex AI is fronted by an OpenAI-compatible bridge, prefer that explicit URL:
+
+```bash
+python3 scripts/bezalel_gemma4_vps.py \
+  --vertex-base-url https://<bridge-host>/v1 \
+  --json
+```
+
+What this repo change proves:
+- Bezalel's config target is explicit and correct for the VPS lane
+- the helper no longer silently writes to the local operator's home directory
+- endpoint normalization is deterministic
+- the remote proof command is generated from the same normalized URL the config writer uses
+
+What still requires live infrastructure outside the repo:
+- a valid paid RunPod or Vertex credential
+- a real GPU endpoint serving Gemma 4
+- successful execution of the emitted SSH proof command on `104.131.15.18`
+- successful Bezalel Hermes chat against that live endpoint

scripts/bezalel_gemma4_vps.py

@@ -8,12 +8,14 @@ Safe by default:
 - can call the RunPod GraphQL API if a key is provided and --apply-runpod is used
 - can update a Hermes config file in-place when --write-config is used
 - can verify an OpenAI-compatible endpoint with a lightweight chat probe
+- emits the exact Bezalel VPS curl proof command for remote verification
 """
 
 from __future__ import annotations
 
 import argparse
 import json
+import shlex
 from pathlib import Path
 from typing import Any
 from urllib import request
@@ -27,7 +29,9 @@ DEFAULT_IMAGE = "ollama/ollama:latest"
 DEFAULT_MODEL = "gemma4:latest"
 DEFAULT_PROVIDER_NAME = "Big Brain"
 DEFAULT_TOKEN_FILE = Path.home() / ".config" / "runpod" / "access_key"
-DEFAULT_CONFIG_PATH = Path.home() / "wizards" / "bezalel" / "home" / "config.yaml"
+DEFAULT_CONFIG_PATH = Path("/root/wizards/bezalel/home/config.yaml")
+DEFAULT_BEZALEL_VPS_HOST = "104.131.15.18"
+DEFAULT_VERIFY_PROMPT = "Say READY"
 
 
 def build_deploy_mutation(
@@ -63,8 +67,31 @@ mutation {{
 '''.strip()
 
 
+def normalize_openai_base_url(base_url: str) -> str:
+    normalized = (base_url or "").strip().rstrip("/")
+    if not normalized:
+        return normalized
+    for suffix in ("/chat/completions", "/models"):
+        if normalized.endswith(suffix):
+            normalized = normalized[: -len(suffix)]
+            break
+    if not normalized.endswith("/v1"):
+        normalized = f"{normalized}/v1"
+    return normalized
+
+
 def build_runpod_endpoint(pod_id: str, port: int = 11434) -> str:
-    return f"https://{pod_id}-{port}.proxy.runpod.net/v1"
+    return normalize_openai_base_url(f"https://{pod_id}-{port}.proxy.runpod.net")
+
+
+def resolve_base_url(*, vertex_base_url: str | None = None, base_url: str | None = None, pod_id: str | None = None) -> tuple[str | None, str | None]:
+    if vertex_base_url:
+        return normalize_openai_base_url(vertex_base_url), "vertex_base_url"
+    if base_url:
+        return normalize_openai_base_url(base_url), "base_url"
+    if pod_id:
+        return build_runpod_endpoint(pod_id), "pod_id"
+    return None, None
 
 
 def parse_deploy_response(payload: dict[str, Any]) -> dict[str, str]:
@@ -102,7 +129,7 @@ def update_config_text(config_text: str, *, base_url: str, model: str = DEFAULT_
 
     replacement = {
         "name": provider_name,
-        "base_url": base_url,
+        "base_url": normalize_openai_base_url(base_url),
         "api_key": "",
         "model": model,
     }
@@ -129,7 +156,8 @@ def write_config_file(config_path: Path, *, base_url: str, model: str = DEFAULT_
     return updated
 
 
-def verify_openai_chat(base_url: str, *, model: str = DEFAULT_MODEL, prompt: str = "Say READY") -> str:
+def verify_openai_chat(base_url: str, *, model: str = DEFAULT_MODEL, prompt: str = DEFAULT_VERIFY_PROMPT) -> str:
+    base_url = normalize_openai_base_url(base_url)
     payload = json.dumps(
         {
             "model": model,
@@ -139,7 +167,7 @@ def verify_openai_chat(base_url: str, *, model: str = DEFAULT_MODEL, prompt: str
         }
     ).encode()
     req = request.Request(
-        f"{base_url.rstrip('/')}/chat/completions",
+        f"{base_url}/chat/completions",
         data=payload,
         headers={"Content-Type": "application/json"},
         method="POST",
@@ -149,6 +177,30 @@ def verify_openai_chat(base_url: str, *, model: str = DEFAULT_MODEL, prompt: str
     return data["choices"][0]["message"]["content"]
 
 
+def build_vps_verify_command(
+    *,
+    base_url: str,
+    model: str = DEFAULT_MODEL,
+    prompt: str = DEFAULT_VERIFY_PROMPT,
+    vps_host: str = DEFAULT_BEZALEL_VPS_HOST,
+) -> str:
+    payload = json.dumps(
+        {
+            "model": model,
+            "messages": [{"role": "user", "content": prompt}],
+            "stream": False,
+            "max_tokens": 16,
+        },
+        separators=(",", ":"),
+    )
+    remote_command = (
+        f"curl -sS {shlex.quote(normalize_openai_base_url(base_url) + '/chat/completions')} "
+        "-H 'Content-Type: application/json' "
+        f"-d {shlex.quote(payload)}"
+    )
+    return f"ssh root@{vps_host} {shlex.quote(remote_command)}"
+
+
 def parse_args() -> argparse.Namespace:
     parser = argparse.ArgumentParser(description="Provision a RunPod Gemma 4 endpoint and wire a Hermes config for Bezalel.")
     parser.add_argument("--pod-name", default="bezalel-gemma4")
@@ -160,6 +212,8 @@ def parse_args() -> argparse.Namespace:
     parser.add_argument("--config-path", type=Path, default=DEFAULT_CONFIG_PATH)
     parser.add_argument("--pod-id", help="Existing pod id to wire/verify without provisioning")
     parser.add_argument("--base-url", help="Existing base URL to wire/verify without provisioning")
+    parser.add_argument("--vertex-base-url", help="OpenAI-compatible Vertex bridge URL; takes precedence over --base-url and --pod-id")
+    parser.add_argument("--vps-host", default=DEFAULT_BEZALEL_VPS_HOST, help="Bezalel VPS host for the remote curl proof command")
     parser.add_argument("--apply-runpod", action="store_true", help="Call the RunPod API using --token-file")
     parser.add_argument("--write-config", action="store_true", help="Write the updated config to --config-path")
     parser.add_argument("--verify-chat", action="store_true", help="Call the OpenAI-compatible chat endpoint")
@@ -175,13 +229,18 @@ def main() -> None:
         "cloud_type": args.cloud_type,
         "model": args.model,
         "provider_name": args.provider_name,
+        "config_path": str(args.config_path),
+        "vps_host": args.vps_host,
         "actions": [],
     }
 
-    base_url = args.base_url
-    if not base_url and args.pod_id:
-        base_url = build_runpod_endpoint(args.pod_id)
-        summary["actions"].append("computed_base_url_from_pod_id")
+    base_url, base_url_source = resolve_base_url(
+        vertex_base_url=args.vertex_base_url,
+        base_url=args.base_url,
+        pod_id=args.pod_id,
+    )
+    if base_url_source:
+        summary["actions"].append(f"resolved_base_url_from_{base_url_source}")
 
     if args.apply_runpod:
         if not args.token_file.exists():
@@ -196,12 +255,17 @@ def main() -> None:
         base_url = build_runpod_endpoint("<pod-id>")
         summary["actions"].append("using_placeholder_base_url")
 
-    summary["base_url"] = base_url
+    summary["base_url"] = normalize_openai_base_url(base_url)
     summary["config_preview"] = update_config_text("", base_url=base_url, model=args.model, provider_name=args.provider_name)
+    summary["vps_verify_command"] = build_vps_verify_command(
+        base_url=base_url,
+        model=args.model,
+        prompt=DEFAULT_VERIFY_PROMPT,
+        vps_host=args.vps_host,
+    )
 
     if args.write_config:
         write_config_file(args.config_path, base_url=base_url, model=args.model, provider_name=args.provider_name)
-        summary["config_path"] = str(args.config_path)
         summary["actions"].append("wrote_config")
 
     if args.verify_chat:
@@ -214,8 +278,10 @@ def main() -> None:
 
     print("--- Bezalel Gemma4 RunPod Wiring ---")
     print(f"Pod name: {args.pod_name}")
-    print(f"Base URL: {base_url}")
+    print(f"Base URL: {summary['base_url']}")
     print(f"Model: {args.model}")
+    print(f"Config target: {args.config_path}")
+    print(f"Bezalel VPS proof: {summary['vps_verify_command']}")
     if args.write_config:
         print(f"Config written: {args.config_path}")
     if "verify_response" in summary:

tests/test_bezalel_gemma4_vps.py

@@ -1,14 +1,20 @@
 from __future__ import annotations
 
 import json
+from pathlib import Path
 from unittest.mock import patch
 
 import yaml
 
 from scripts.bezalel_gemma4_vps import (
+    DEFAULT_CONFIG_PATH,
+    DEFAULT_BEZALEL_VPS_HOST,
     build_deploy_mutation,
     build_runpod_endpoint,
+    build_vps_verify_command,
+    normalize_openai_base_url,
     parse_deploy_response,
+    resolve_base_url,
     update_config_text,
     verify_openai_chat,
 )
@@ -28,6 +34,10 @@ class _FakeResponse:
         return False
 
 
+def test_default_config_path_targets_bezalel_vps_root_config() -> None:
+    assert DEFAULT_CONFIG_PATH == Path("/root/wizards/bezalel/home/config.yaml")
+
+
 def test_build_deploy_mutation_uses_ollama_image_and_openai_port() -> None:
     query = build_deploy_mutation(name="bezalel-gemma4", gpu_type="NVIDIA L40S", model_tag="gemma4:latest")
 
@@ -37,6 +47,30 @@ def test_build_deploy_mutation_uses_ollama_image_and_openai_port() -> None:
     assert 'volumeMountPath: "/root/.ollama"' in query
 
 
+def test_normalize_openai_base_url_adds_v1_suffix() -> None:
+    assert normalize_openai_base_url("https://pod-11434.proxy.runpod.net") == "https://pod-11434.proxy.runpod.net/v1"
+
+
+def test_normalize_openai_base_url_trims_chat_completions_suffix() -> None:
+    assert normalize_openai_base_url("https://pod-11434.proxy.runpod.net/v1/chat/completions") == "https://pod-11434.proxy.runpod.net/v1"
+
+
+def test_resolve_base_url_prefers_vertex_over_base_and_pod_id() -> None:
+    base_url, source = resolve_base_url(
+        vertex_base_url="https://vertex.example.com/openai",
+        base_url="https://plain.example.com",
+        pod_id="abc123",
+    )
+    assert source == "vertex_base_url"
+    assert base_url == "https://vertex.example.com/openai/v1"
+
+
+def test_resolve_base_url_falls_back_to_base_url_before_pod_id() -> None:
+    base_url, source = resolve_base_url(base_url="https://plain.example.com", pod_id="abc123")
+    assert source == "base_url"
+    assert base_url == "https://plain.example.com/v1"
+
+
 def test_build_runpod_endpoint_appends_v1_suffix() -> None:
     assert build_runpod_endpoint("abc123") == "https://abc123-11434.proxy.runpod.net/v1"
 
@@ -60,7 +94,7 @@ def test_parse_deploy_response_extracts_pod_id_and_endpoint() -> None:
     }
 
 
-def test_update_config_text_upserts_big_brain_provider() -> None:
+def test_update_config_text_upserts_big_brain_provider_and_normalizes_base_url() -> None:
     original = """
 model:
   default: kimi-k2.5
@@ -72,7 +106,7 @@ custom_providers:
     model: gemma3:27b
 """
 
-    updated = update_config_text(original, base_url="https://new-pod-11434.proxy.runpod.net/v1", model="gemma4:latest")
+    updated = update_config_text(original, base_url="https://new-pod-11434.proxy.runpod.net", model="gemma4:latest")
     parsed = yaml.safe_load(updated)
 
     assert parsed["model"] == {"default": "kimi-k2.5", "provider": "kimi-coding"}
@@ -86,7 +120,14 @@ custom_providers:
     ]
 
 
-def test_verify_openai_chat_calls_chat_completions() -> None:
+def test_build_vps_verify_command_targets_bezalel_host_and_chat_completions() -> None:
+    command = build_vps_verify_command(base_url="https://pod-11434.proxy.runpod.net", model="gemma4:latest")
+    assert command.startswith(f"ssh root@{DEFAULT_BEZALEL_VPS_HOST} ")
+    assert "/v1/chat/completions" in command
+    assert "gemma4:latest" in command
+
+
+def test_verify_openai_chat_calls_chat_completions_with_normalized_base_url() -> None:
     response_payload = {
         "choices": [
             {
@@ -101,7 +142,7 @@ def test_verify_openai_chat_calls_chat_completions() -> None:
         "scripts.bezalel_gemma4_vps.request.urlopen",
         return_value=_FakeResponse(response_payload),
     ) as mocked:
-        result = verify_openai_chat("https://pod-11434.proxy.runpod.net/v1", model="gemma4:latest", prompt="say READY")
+        result = verify_openai_chat("https://pod-11434.proxy.runpod.net", model="gemma4:latest", prompt="say READY")
 
     assert result == "READY"
     req = mocked.call_args.args[0]
@@ -109,3 +150,10 @@ def test_verify_openai_chat_calls_chat_completions() -> None:
     payload = json.loads(req.data.decode())
     assert payload["model"] == "gemma4:latest"
     assert payload["messages"][0]["content"] == "say READY"
+
+
+def test_readme_documents_root_config_path_and_vps_proof_command() -> None:
+    readme = Path("scripts/README_bezalel_gemma4_vps.md").read_text()
+    assert "/root/wizards/bezalel/home/config.yaml" in readme
+    assert "ssh root@104.131.15.18" in readme
+    assert "--vertex-base-url" in readme