scripts/llm_translator.py

@@ -23,7 +23,7 @@ think:false, which hybrid models need off. Backend quirks (sampling,
 num_predict cap, think) live in the config, not in the protocol.
 
 Usage:
-    uv run scripts/llm_translator.py ws://localhost:8410/_translate/KEY
+    uv run scripts/llm_translator.py ws://localhost:8210/_translate/KEY
     uv run scripts/llm_translator.py wss://example.com/_translate/KEY --config my.json
 """
 
@@ -277,15 +277,49 @@ def main() -> None:
     )
     p.add_argument(
         "url",
-        help="full translator WebSocket URL including the key, "
-        "e.g. ws://localhost:8410/_translate/KEY",
+        help="full translator WebSocket URL including the access key, "
+        "e.g. ws://localhost:8210/_translate/KEY — printed in the server "
+        "startup log and copyable in the editor's lang tab",
+    )
+    p.add_argument(
+        "--config",
+        help="JSON file overriding any DEFAULT_CONFIG key (see the top of "
+        "this script: api, base_url, model, langs, modes, temperature, "
+        "predict_ratio/cap, think, ...); CLI flags win over the file",
+    )
+    p.add_argument(
+        "--api",
+        choices=["ollama", "openai"],
+        help="LLM endpoint shape: 'ollama' = native /api/chat (needed for "
+        "think:false), 'openai' = /v1/chat/completions (llama.cpp, hosted "
+        "APIs) (default: ollama)",
+    )
+    p.add_argument(
+        "--base-url",
+        help="LLM server root without path, e.g. http://127.0.0.1:11434 "
+        "(default) or https://api.openai.com",
+    )
+    p.add_argument(
+        "--model",
+        help="model string to serve, e.g. qwen3.8:27b (default; the "
+        "structure-proven reference) — announced to the server in Hello",
+    )
+    p.add_argument(
+        "--api-key",
+        help="bearer key for --api openai backends (ollama ignores it)",
+    )
+    p.add_argument(
+        "--langs",
+        help="comma-separated language capabilities announced to the server, "
+        "e.g. de,es,fi,pt,zh (default); jobs come only from the "
+        "intersection with the site's configured target languages",
+    )
+    p.add_argument(
+        "--modes",
+        help="comma-separated job modes to accept: 'markdown,article' "
+        "(default, for a structure-proven model) or 'markdown' for one "
+        "trusted only in scoped mode",
     )
-    p.add_argument("--config", help="JSON config file (overrides the shipped defaults)")
-    p.add_argument("--base-url", help="LLM server root (no path)")
-    p.add_argument("--model", help="model string to serve")
-    p.add_argument("--api-key", help="API key for openai-api backends")
-    p.add_argument("--langs", help="comma-separated announced languages")
-    p.add_argument("--modes", help="comma-separated accepted job modes")
     args = p.parse_args()
     if not args.url.startswith(("ws://", "wss://")):
         p.error("url must start with ws:// or wss://")
@@ -293,7 +327,7 @@ def main() -> None:
     cfg = dict(DEFAULT_CONFIG)
     if args.config:
         cfg.update(json.loads(Path(args.config).read_text()))
-    for key in ("base_url", "model", "api_key"):
+    for key in ("api", "base_url", "model", "api_key"):
         if getattr(args, key):
             cfg[key] = getattr(args, key)
     if args.langs: