@oneciel-ai/claude-any 0.1.32 → 0.1.34

package/README.md

@@ -1,6 +1,10 @@
-# Claude Any
-
-![Claude Any: full Claude Code experience with free or low-cost LLMs](claude-any-adv.png)
+# Claude Any
+
+<p align="center">
+  <img src="logo.png" alt="Claude Any logo" width="360">
+</p>
+
+![Claude Any: full Claude Code experience with free or low-cost LLMs](claude-any-adv.png)
 
 | English | [한국어](docs/README.ko.md) | [日本語](docs/README.ja.md) | [中文](docs/README.zh.md) |
 | --- | --- | --- | --- |
@@ -44,7 +48,7 @@ arguments through unchanged.
 
 Credits: One Ciel LLC
 
-Current version: `0.1.32`
+Current version: `0.1.34`
 
 ## Why This Exists
 
@@ -117,14 +121,57 @@ Run one non-interactive Claude Code prompt:
 claude-any --ca-provider nvidia-hosted --ca-model z-ai/glm-4.7 --ca-no-update-check -p "Reply with OK only." --output-format text
 ```
 
-Use the saved provider/model and only skip the menu:
-
-```sh
-CLAUDE_ANY_SKIP_MENU=1 claude-any -p "Summarize this repository." --output-format text
-```
-
-More examples are in [Headless Examples](#headless-examples) and
-[the full manual](docs/manual.md#headless-usage).
+Use the saved provider/model and only skip the menu:
+
+```sh
+CLAUDE_ANY_SKIP_MENU=1 claude-any -p "Summarize this repository." --output-format text
+```
+
+Configure every launch option with flags:
+
+```sh
+claude-any --ca-provider nvidia-hosted --ca-base-url https://integrate.api.nvidia.com/v1 --ca-model z-ai/glm-4.7 --ca-advisor-model deepseek-ai/deepseek-v4-pro --ca-api-key-env NVIDIA_API_KEY --ca-max-output-tokens 4096 --ca-context-window 65536 --ca-request-timeout-ms 300000 --ca-rate-limit-rpm 40 --ca-rate-limit-status on --ca-no-update-check -p "Reply with OK only." --output-format text
+```
+
+Or put the same values in environment variables:
+
+```sh
+export CLAUDE_ANY_SKIP_MENU=1
+export CLAUDE_ANY_PROVIDER=nvidia-hosted
+export CLAUDE_ANY_BASE_URL=https://integrate.api.nvidia.com/v1
+export CLAUDE_ANY_MODEL=z-ai/glm-4.7
+export CLAUDE_ANY_ADVISOR_MODEL=deepseek-ai/deepseek-v4-pro
+export CLAUDE_ANY_API_KEY_ENV=NVIDIA_API_KEY
+export CLAUDE_ANY_MAX_OUTPUT_TOKENS=4096
+export CLAUDE_ANY_CONTEXT_WINDOW=65536
+export CLAUDE_ANY_REQUEST_TIMEOUT_MS=300000
+export CLAUDE_ANY_RATE_LIMIT_RPM=40
+export CLAUDE_ANY_RATE_LIMIT_STATUS=on
+claude-any -p "Reply with OK only." --output-format text
+```
+
+For `.env` driven runs, save the same `CLAUDE_ANY_*` values in a file and pass
+it explicitly:
+
+```sh
+claude-any --ca-env-file .env.claude-any -p "Reply with OK only." --output-format text
+```
+
+Override order is deterministic: saved user choices from the menu are the
+baseline, OS environment variables override them, `--ca-env-file` values
+override the OS environment, CLI `--ca-*` parameters override the env file, and
+`--ca-menu` lets the final interactive menu choice override everything.
+
+Headless coverage checklist: provider, base URL, model, Advisor model, API key
+or API-key environment variable, max output, context window, request timeout,
+RPM limit, RPM status display, streaming, web search, web fetch, Claude skills,
+update check, language, Ollama context/options, and normal Claude Code
+passthrough arguments are all configurable without opening the menu. API keys
+can be passed directly with `--ca-api-key`, but `--ca-api-key-env` is safer for
+scripts because the secret does not appear in shell history.
+
+More examples are in [Headless Examples](#headless-examples) and
+[the full manual](docs/manual.md#headless-usage).
 
 **Upgrade:**
 
@@ -334,6 +381,21 @@ steps under that larger model's supervision.
 
 ## Changelog
 
+### 0.1.34
+
+- **Complete headless configuration path**: add `--ca-env-file`,
+  environment-variable mapping, Advisor model, rate-limit, streaming, language,
+  and web-fetch headless controls.
+- **Documented override order**: saved menu choices < OS environment <
+  `.env` file < CLI parameters < final interactive menu choice via `--ca-menu`.
+
+### 0.1.33
+
+- **Logo branding in every README**: add the Claude Any logo at the top of the
+  English, Korean, Japanese, and Chinese README files.
+- **npm image assets included**: package `logo.png`, `logo-small.png`, and
+  `claude-any-adv.png` so the npm README renders the same branding as GitHub.
+
 ### 0.1.32
 
 - **NVIDIA preset menu fix**: LLM presets no longer try to apply the unsupported

package/claude_any.py

@@ -31,9 +31,9 @@ try:
 except Exception:
     pass
 
-HOME = Path.home()
-CONFIG_DIR = HOME / ".config" / "claude-any"
-CONFIG_PATH = CONFIG_DIR / "config.json"
+HOME = Path.home()
+CONFIG_DIR = Path(os.environ.get("CLAUDE_ANY_CONFIG_DIR") or (HOME / ".config" / "claude-any"))
+CONFIG_PATH = CONFIG_DIR / "config.json"
 LOG_PATH = CONFIG_DIR / "router.log"
 LOG_LEVEL_PATH = CONFIG_DIR / "log-level"
 REQUEST_DUMP_PATH = CONFIG_DIR / "requests.jsonl"
@@ -84,7 +84,7 @@ PROVIDER_LABELS = {
     "self-hosted-nim": "Self Hosted NIM",
 }
 APP_NAME = "Claude Any"
-VERSION = "0.1.32"
+VERSION = "0.1.34"
 CREDITS = "Credits: One Ciel LLC"
 
 LOG_LEVELS = {"SILENT": 0, "ERROR": 1, "WARN": 2, "INFO": 3, "DEBUG": 4, "TRACE": 5}
@@ -955,11 +955,28 @@ def read_env_file(path: Path) -> dict[str, str]:
     return env
 
 
-def meaningful_key_value(value: Any) -> bool:
-    if value is None:
-        return False
-    text = str(value).strip()
-    return bool(text and text not in ("dummy", "not-used", "ollama"))
+def meaningful_key_value(value: Any) -> bool:
+    if value is None:
+        return False
+    text = str(value).strip()
+    return bool(text and text not in ("dummy", "not-used", "ollama"))
+
+
+def env_bool(value: str | None, default: bool | None = None) -> bool | None:
+    if value is None:
+        return default
+    text = value.strip().lower()
+    if text in ("1", "true", "yes", "on", "y"):
+        return True
+    if text in ("0", "false", "no", "off", "n"):
+        return False
+    return default
+
+
+def load_dotenv_into_environ(path: Path, *, override: bool = True) -> None:
+    for key, value in read_env_file(path).items():
+        if override or key not in os.environ:
+            os.environ[key] = value
 
 
 def executable_candidates(name: str) -> list[str]:
@@ -7900,9 +7917,11 @@ def has_noninteractive_claude_args(passthrough: list[str]) -> bool:
     return any(arg == "-p" or arg == "--print" or arg.startswith("--print=") for arg in passthrough)
 
 
-def run_prelaunch_menu(passthrough: list[str], skip_menu: bool = False) -> int:
-    if skip_menu or has_noninteractive_claude_args(passthrough) or os.environ.get("CLAUDE_ANY_SKIP_MENU") == "1":
-        return 0
+def run_prelaunch_menu(passthrough: list[str], skip_menu: bool = False, force_menu: bool = False) -> int:
+    if not force_menu and (
+        skip_menu or has_noninteractive_claude_args(passthrough) or os.environ.get("CLAUDE_ANY_SKIP_MENU") == "1"
+    ):
+        return 0
     if not (sys.stdin.isatty() and sys.stdout.isatty()):
         return 0
     if os.environ.get("CLAUDE_ANY_USE_LEGACY_MENU") == "1":
@@ -8037,14 +8056,15 @@ def run_claude_update_check(claude: str, enabled: bool = True) -> None:
         print(f"Claude Code update check exited with {p.returncode}; continuing.", flush=True)
 
 
-def launch_claude(
-    passthrough: list[str],
-    skip_menu: bool = False,
-    web_search_override: bool | None = None,
-    disable_skills_override: bool | None = None,
-    update_check: bool = True,
-) -> int:
-    rc = run_prelaunch_menu(passthrough, skip_menu=skip_menu)
+def launch_claude(
+    passthrough: list[str],
+    skip_menu: bool = False,
+    force_menu: bool = False,
+    web_search_override: bool | None = None,
+    disable_skills_override: bool | None = None,
+    update_check: bool = True,
+) -> int:
+    rc = run_prelaunch_menu(passthrough, skip_menu=skip_menu, force_menu=force_menu)
     if rc == 10:
         return 0
     if rc != 0:
@@ -8121,8 +8141,8 @@ def launch_claude(
     return subprocess.call(cmd, env=env)
 
 
-def cli_usage() -> str:
-    return """Usage:
+def cli_usage() -> str:
+    return """Usage:
   claude-any                         Launch Claude Code through claude-any router
 
 Control plane, runs before Claude Code and does not require LLM connectivity:
@@ -8148,21 +8168,31 @@ Control plane, runs before Claude Code and does not require LLM connectivity:
   claude-any stop                    Stop router/proxy
 
 Headless setup flags, namespaced to avoid Claude CLI collisions:
-  claude-any --ca-provider PROVIDER  Set provider, then launch
-  claude-any --ca-base-url URL       Set current provider base URL, then launch
-  claude-any --ca-model MODEL_ID     Set provider model, then launch
-  claude-any --ca-api-key KEY        Set current provider API key, then launch
-  claude-any --ca-api-key-env ENVVAR Set current provider API key from env, then launch
-  claude-any --ca-set-api-key PROVIDER KEY
-  claude-any --ca-set-api-key-env PROVIDER ENVVAR
+  claude-any --ca-provider PROVIDER  Set provider, then launch
+  claude-any --ca-env-file PATH      Load CLAUDE_ANY_* values from a .env file
+  claude-any --ca-menu               Apply setup values, then open the menu
+  claude-any --ca-language en|ko|ja|zh
+  claude-any --ca-base-url URL       Set current provider base URL, then launch
+  claude-any --ca-model MODEL_ID     Set provider model, then launch
+  claude-any --ca-advisor-model MODEL_ID
+  claude-any --ca-api-key KEY        Set current provider API key, then launch
+  claude-any --ca-api-key-env ENVVAR Set current provider API key from env, then launch
+  claude-any --ca-set-api-key PROVIDER KEY
+  claude-any --ca-set-api-key-env PROVIDER ENVVAR
   claude-any --ca-ollama-num-ctx VALUE
   claude-any --ca-ollama-ctx-range MIN MAX
   claude-any --ca-ollama-option KEY=VALUE
   claude-any --ca-max-output-tokens VALUE
-  claude-any --ca-context-window VALUE
-  claude-any --ca-request-timeout-ms VALUE
-  claude-any --ca-web-search         Force DuckDuckGo MCP for this launch
-  claude-any --ca-no-web-search      Disable DuckDuckGo MCP for this launch
+  claude-any --ca-context-window VALUE
+  claude-any --ca-request-timeout-ms VALUE
+  claude-any --ca-rate-limit-rpm VALUE
+  claude-any --ca-rate-limit-status on|off
+  claude-any --ca-stream on|off
+  claude-any --ca-stream-word-chunking on|off
+  claude-any --ca-web-search         Force DuckDuckGo MCP for this launch
+  claude-any --ca-no-web-search      Disable DuckDuckGo MCP for this launch
+  claude-any --ca-web-fetch          Enable fetch MCP
+  claude-any --ca-no-web-fetch       Disable fetch MCP
   claude-any --ca-disable-skills     Disable Claude Code skills for this launch
   claude-any --ca-enable-skills      Keep Claude Code skills enabled for this launch
   claude-any --ca-no-update-check    Skip Claude Code update check for this launch
@@ -8171,15 +8201,112 @@ Headless setup flags, namespaced to avoid Claude CLI collisions:
 
 Provider names: anthropic, ollama, ollama-cloud, vllm, nvidia-hosted, self-hosted-nim
 Any other arguments are passed through to claude. Use -- before Claude flags that
-collide with claude-any setup flags."""
-
-
-def run_cli(argv: list[str]) -> int:
-    if argv and argv[0] in ("help", "--help", "-h"):
-        print(cli_usage())
-        return 0
-    if argv:
-        head, rest = argv[0], argv[1:]
+collide with claude-any setup flags."""
+
+
+def pop_headless_env_file_args(argv: list[str]) -> list[str]:
+    cleaned: list[str] = []
+    i = 0
+    while i < len(argv):
+        arg = argv[i]
+        if arg == "--ca-env-file" or arg.startswith("--ca-env-file="):
+            value = arg.split("=", 1)[1] if "=" in arg else None
+            if value is None:
+                if i + 1 >= len(argv):
+                    raise SystemExit("Missing path for --ca-env-file")
+                value = argv[i + 1]
+                i += 2
+            else:
+                i += 1
+            path = Path(value).expanduser()
+            if not path.exists():
+                raise SystemExit(f"--ca-env-file not found: {path}")
+            load_dotenv_into_environ(path, override=True)
+        else:
+            cleaned.append(arg)
+            i += 1
+    return cleaned
+
+
+def apply_headless_env_config() -> tuple[bool, bool | None, bool | None, bool | None, bool]:
+    skip_menu = os.environ.get("CLAUDE_ANY_SKIP_MENU") == "1"
+    force_menu = bool(env_bool(os.environ.get("CLAUDE_ANY_FORCE_MENU"), False))
+    web_search_override = env_bool(os.environ.get("CLAUDE_ANY_WEB_SEARCH"))
+    disable_skills_override = env_bool(os.environ.get("CLAUDE_ANY_DISABLE_SKILLS"))
+    update_check_override = env_bool(os.environ.get("CLAUDE_ANY_UPDATE_CHECK"))
+    language = os.environ.get("CLAUDE_ANY_LANGUAGE", "").strip()
+    if language:
+        cmd_language(argparse.Namespace(value=language))
+        skip_menu = True
+    web_fetch = env_bool(os.environ.get("CLAUDE_ANY_WEB_FETCH"))
+    if web_fetch is not None:
+        cmd_web_fetch(argparse.Namespace(value="on" if web_fetch else "off"))
+        skip_menu = True
+    provider = os.environ.get("CLAUDE_ANY_PROVIDER", "").strip()
+    if provider:
+        cmd_provider(argparse.Namespace(name=provider))
+        skip_menu = True
+    api_key_env = os.environ.get("CLAUDE_ANY_API_KEY_ENV", "").strip()
+    api_key = os.environ.get("CLAUDE_ANY_API_KEY", "").strip()
+    current_provider, _ = get_current_provider(load_config())
+    if api_key_env:
+        value = os.environ.get(api_key_env, "")
+        if not value:
+            raise SystemExit(f"Environment variable {api_key_env} is empty or not set")
+        cmd_set_api_key(argparse.Namespace(provider=current_provider, key=value))
+        skip_menu = True
+    elif api_key:
+        cmd_set_api_key(argparse.Namespace(provider=current_provider, key=api_key))
+        skip_menu = True
+    base_url = os.environ.get("CLAUDE_ANY_BASE_URL", "").strip()
+    if base_url:
+        current_provider, _ = get_current_provider(load_config())
+        cmd_base_url(argparse.Namespace(provider=current_provider, url=base_url))
+        skip_menu = True
+    model = os.environ.get("CLAUDE_ANY_MODEL", "").strip()
+    if model:
+        cmd_model(argparse.Namespace(value=[model]))
+        skip_menu = True
+    advisor_model = os.environ.get("CLAUDE_ANY_ADVISOR_MODEL", "").strip()
+    if advisor_model:
+        set_advisor_model_config(advisor_model)
+        skip_menu = True
+    provider_option_keys = {
+        "CLAUDE_ANY_MAX_OUTPUT_TOKENS": "max_output_tokens",
+        "CLAUDE_ANY_CONTEXT_WINDOW": "context_window",
+        "CLAUDE_ANY_REQUEST_TIMEOUT_MS": "request_timeout_ms",
+        "CLAUDE_ANY_RATE_LIMIT_RPM": "rate_limit_rpm",
+        "CLAUDE_ANY_RATE_LIMIT_STATUS": "rate_limit_status",
+        "CLAUDE_ANY_STREAM": "stream_enabled",
+        "CLAUDE_ANY_STREAM_WORD_CHUNKING": "stream_word_chunking",
+    }
+    provider_values = [
+        f"{option_key}={os.environ[env_key].strip()}"
+        for env_key, option_key in provider_option_keys.items()
+        if os.environ.get(env_key, "").strip()
+    ]
+    if provider_values:
+        cmd_provider_options(argparse.Namespace(values=provider_values))
+        skip_menu = True
+    ollama_values: list[str] = []
+    if os.environ.get("CLAUDE_ANY_OLLAMA_NUM_CTX", "").strip():
+        ollama_values.append(f"num_ctx={os.environ['CLAUDE_ANY_OLLAMA_NUM_CTX'].strip()}")
+    for item in os.environ.get("CLAUDE_ANY_OLLAMA_OPTIONS", "").replace(",", " ").split():
+        if item.strip():
+            ollama_values.append(item.strip())
+    if ollama_values:
+        cmd_ollama_options(argparse.Namespace(values=ollama_values))
+        skip_menu = True
+    return skip_menu, web_search_override, disable_skills_override, update_check_override, force_menu
+
+
+def run_cli(argv: list[str]) -> int:
+    if argv and argv[0] in ("help", "--help", "-h"):
+        print(cli_usage())
+        return 0
+    argv = pop_headless_env_file_args(argv)
+    if argv:
+        head, rest = argv[0], argv[1:]
         if head in ("version", "--version", "-v"):
             print(f"claude-any {VERSION}")
             return 0
@@ -8263,16 +8390,30 @@ def run_cli(argv: list[str]) -> int:
                 subprocess.run([ncp, "kill"], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
             return 0
 
-    passthrough: list[str] = []
-    skip_menu = False
-    web_search_override: bool | None = None
-    disable_skills_override: bool | None = None
-    update_check = True
-    i = 0
-    while i < len(argv):
-        arg = argv[i]
-        if arg == "--ca-provider" or arg.startswith("--ca-provider="):
-            provider_value = arg.split("=", 1)[1] if "=" in arg else None
+    passthrough: list[str] = []
+    skip_menu, web_search_override, disable_skills_override, update_check_override, force_menu = apply_headless_env_config()
+    update_check = True
+    if update_check_override is not None:
+        update_check = update_check_override
+    i = 0
+    while i < len(argv):
+        arg = argv[i]
+        if arg in ("--ca-menu", "--ca-interactive"):
+            force_menu = True
+            i += 1
+        elif arg == "--ca-language" or arg.startswith("--ca-language="):
+            value = arg.split("=", 1)[1] if "=" in arg else None
+            if value is None:
+                if i + 1 >= len(argv):
+                    raise SystemExit("Missing language for --ca-language")
+                value = argv[i + 1]
+                i += 2
+            else:
+                i += 1
+            cmd_language(argparse.Namespace(value=value))
+            skip_menu = True
+        elif arg == "--ca-provider" or arg.startswith("--ca-provider="):
+            provider_value = arg.split("=", 1)[1] if "=" in arg else None
             if provider_value:
                 cmd_provider(argparse.Namespace(name=provider_value))
                 skip_menu = True
@@ -8301,20 +8442,32 @@ def run_cli(argv: list[str]) -> int:
             provider, _ = get_current_provider(load_config())
             cmd_base_url(argparse.Namespace(provider=provider, url=value))
             skip_menu = True
-        elif arg == "--ca-model" or arg.startswith("--ca-model="):
-            value = arg.split("=", 1)[1] if "=" in arg else None
-            if value is None:
-                if i + 1 >= len(argv):
-                    raise SystemExit("Missing model id for --ca-model")
+        elif arg == "--ca-model" or arg.startswith("--ca-model="):
+            value = arg.split("=", 1)[1] if "=" in arg else None
+            if value is None:
+                if i + 1 >= len(argv):
+                    raise SystemExit("Missing model id for --ca-model")
                 value = argv[i + 1]
                 i += 2
             else:
                 i += 1
-            cmd_model(argparse.Namespace(value=[value]))
-            skip_menu = True
-        elif arg == "--ca-models":
-            cmd_models(argparse.Namespace(provider=None))
-            return 0
+            cmd_model(argparse.Namespace(value=[value]))
+            skip_menu = True
+        elif arg == "--ca-advisor-model" or arg.startswith("--ca-advisor-model="):
+            value = arg.split("=", 1)[1] if "=" in arg else None
+            if value is None:
+                if i + 1 >= len(argv):
+                    raise SystemExit("Missing model id for --ca-advisor-model")
+                value = argv[i + 1]
+                i += 2
+            else:
+                i += 1
+            for line in set_advisor_model_config(value):
+                print(line)
+            skip_menu = True
+        elif arg == "--ca-models":
+            cmd_models(argparse.Namespace(provider=None))
+            return 0
         elif arg == "--ca-api-key" or arg.startswith("--ca-api-key="):
             value = arg.split("=", 1)[1] if "=" in arg else None
             if value is None:
@@ -8419,25 +8572,77 @@ def run_cli(argv: list[str]) -> int:
                 i += 1
             cmd_provider_options(argparse.Namespace(values=[f"context_window={value}"]))
             skip_menu = True
-        elif arg == "--ca-request-timeout-ms" or arg.startswith("--ca-request-timeout-ms="):
-            value = arg.split("=", 1)[1] if "=" in arg else None
-            if value is None:
-                if i + 1 >= len(argv):
-                    raise SystemExit("Missing value for --ca-request-timeout-ms")
+        elif arg == "--ca-request-timeout-ms" or arg.startswith("--ca-request-timeout-ms="):
+            value = arg.split("=", 1)[1] if "=" in arg else None
+            if value is None:
+                if i + 1 >= len(argv):
+                    raise SystemExit("Missing value for --ca-request-timeout-ms")
                 value = argv[i + 1]
                 i += 2
             else:
                 i += 1
-            cmd_provider_options(argparse.Namespace(values=[f"request_timeout_ms={value}"]))
-            skip_menu = True
-        elif arg == "--ca-web-search":
-            web_search_override = True
-            skip_menu = True
-            i += 1
-        elif arg == "--ca-no-web-search":
-            web_search_override = False
-            skip_menu = True
-            i += 1
+            cmd_provider_options(argparse.Namespace(values=[f"request_timeout_ms={value}"]))
+            skip_menu = True
+        elif arg == "--ca-rate-limit-rpm" or arg.startswith("--ca-rate-limit-rpm="):
+            value = arg.split("=", 1)[1] if "=" in arg else None
+            if value is None:
+                if i + 1 >= len(argv):
+                    raise SystemExit("Missing value for --ca-rate-limit-rpm")
+                value = argv[i + 1]
+                i += 2
+            else:
+                i += 1
+            cmd_provider_options(argparse.Namespace(values=[f"rate_limit_rpm={value}"]))
+            skip_menu = True
+        elif arg == "--ca-rate-limit-status" or arg.startswith("--ca-rate-limit-status="):
+            value = arg.split("=", 1)[1] if "=" in arg else None
+            if value is None:
+                if i + 1 >= len(argv):
+                    raise SystemExit("Missing on/off for --ca-rate-limit-status")
+                value = argv[i + 1]
+                i += 2
+            else:
+                i += 1
+            cmd_provider_options(argparse.Namespace(values=[f"rate_limit_status={value}"]))
+            skip_menu = True
+        elif arg == "--ca-stream" or arg.startswith("--ca-stream="):
+            value = arg.split("=", 1)[1] if "=" in arg else None
+            if value is None:
+                if i + 1 >= len(argv):
+                    raise SystemExit("Missing on/off for --ca-stream")
+                value = argv[i + 1]
+                i += 2
+            else:
+                i += 1
+            cmd_provider_options(argparse.Namespace(values=[f"stream_enabled={value}"]))
+            skip_menu = True
+        elif arg == "--ca-stream-word-chunking" or arg.startswith("--ca-stream-word-chunking="):
+            value = arg.split("=", 1)[1] if "=" in arg else None
+            if value is None:
+                if i + 1 >= len(argv):
+                    raise SystemExit("Missing on/off for --ca-stream-word-chunking")
+                value = argv[i + 1]
+                i += 2
+            else:
+                i += 1
+            cmd_provider_options(argparse.Namespace(values=[f"stream_word_chunking={value}"]))
+            skip_menu = True
+        elif arg == "--ca-web-search":
+            web_search_override = True
+            skip_menu = True
+            i += 1
+        elif arg == "--ca-no-web-search":
+            web_search_override = False
+            skip_menu = True
+            i += 1
+        elif arg == "--ca-web-fetch":
+            cmd_web_fetch(argparse.Namespace(value="on"))
+            skip_menu = True
+            i += 1
+        elif arg == "--ca-no-web-fetch":
+            cmd_web_fetch(argparse.Namespace(value="off"))
+            skip_menu = True
+            i += 1
         elif arg == "--ca-disable-skills":
             disable_skills_override = True
             skip_menu = True
@@ -8462,9 +8667,10 @@ def run_cli(argv: list[str]) -> int:
         else:
             passthrough.append(arg)
             i += 1
-    return launch_claude(
-        passthrough,
-        skip_menu=skip_menu,
+    return launch_claude(
+        passthrough,
+        skip_menu=skip_menu,
+        force_menu=force_menu,
         web_search_override=web_search_override,
         disable_skills_override=disable_skills_override,
         update_check=update_check,

package/docs/README.ja.md

@@ -1,6 +1,10 @@
-# Claude Any
-
-![Claude Any: 無料または低コスト LLM で Claude Code 体験](../claude-any-adv.png)
+# Claude Any
+
+<p align="center">
+  <img src="../logo.png" alt="Claude Any ロゴ" width="360">
+</p>
+
+![Claude Any: 無料または低コスト LLM で Claude Code 体験](../claude-any-adv.png)
 
 | [English](../README.md) | [한국어](README.ko.md) | 日本語 | [中文](README.zh.md) |
 | --- | --- | --- | --- |
@@ -43,7 +47,7 @@ vLLM、NVIDIA hosted、self-hosted NIM を選択し、通常の Claude Code 引
 
 Credits: One Ciel LLC
 
-現在のバージョン: `0.1.32`
+現在のバージョン: `0.1.34`
 
 ## 作られた理由
 
@@ -112,13 +116,53 @@ claude-any --ca-provider ollama --ca-base-url http://127.0.0.1:11434 --ca-model
 claude-any --ca-provider nvidia-hosted --ca-model z-ai/glm-4.7 --ca-no-update-check -p "Reply with OK only." --output-format text
 ```
 
-保存済み provider/model を使い、メニューだけをスキップ:
-
-```sh
-CLAUDE_ANY_SKIP_MENU=1 claude-any -p "Summarize this repository." --output-format text
-```
-
-その他の例は [manual](manual.md#headless-usage) を参照してください。
+保存済み provider/model を使い、メニューだけをスキップ:
+
+```sh
+CLAUDE_ANY_SKIP_MENU=1 claude-any -p "Summarize this repository." --output-format text
+```
+
+すべての起動オプションをフラグで渡す例:
+
+```sh
+claude-any --ca-provider nvidia-hosted --ca-base-url https://integrate.api.nvidia.com/v1 --ca-model z-ai/glm-4.7 --ca-advisor-model deepseek-ai/deepseek-v4-pro --ca-api-key-env NVIDIA_API_KEY --ca-max-output-tokens 4096 --ca-context-window 65536 --ca-request-timeout-ms 300000 --ca-rate-limit-rpm 40 --ca-rate-limit-status on --ca-no-update-check -p "Reply with OK only." --output-format text
+```
+
+同じ値を環境変数で指定:
+
+```sh
+export CLAUDE_ANY_SKIP_MENU=1
+export CLAUDE_ANY_PROVIDER=nvidia-hosted
+export CLAUDE_ANY_BASE_URL=https://integrate.api.nvidia.com/v1
+export CLAUDE_ANY_MODEL=z-ai/glm-4.7
+export CLAUDE_ANY_ADVISOR_MODEL=deepseek-ai/deepseek-v4-pro
+export CLAUDE_ANY_API_KEY_ENV=NVIDIA_API_KEY
+export CLAUDE_ANY_MAX_OUTPUT_TOKENS=4096
+export CLAUDE_ANY_CONTEXT_WINDOW=65536
+export CLAUDE_ANY_REQUEST_TIMEOUT_MS=300000
+export CLAUDE_ANY_RATE_LIMIT_RPM=40
+export CLAUDE_ANY_RATE_LIMIT_STATUS=on
+claude-any -p "Reply with OK only." --output-format text
+```
+
+`.env` 方式では、同じ `CLAUDE_ANY_*` 値をファイルに保存して明示的に読み込みます:
+
+```sh
+claude-any --ca-env-file .env.claude-any -p "Reply with OK only." --output-format text
+```
+
+上書き順序は固定です: メニューで保存された最後のユーザー選択が基準になり、
+OS 環境変数、`--ca-env-file` の `.env` 値、CLI `--ca-*` パラメータ、
+`--ca-menu` で再度開いた UI での最終選択の順に上書きされます。
+
+ヘッドレス対応範囲: provider、base URL、model、Advisor model、API key または
+API-key 環境変数、max output、context window、request timeout、RPM limit、
+RPM status 表示、streaming、web search、web fetch、Claude skills、update check、
+language、Ollama context/options、通常の Claude Code passthrough 引数をすべて
+メニューなしで設定できます。API key は `--ca-api-key` で直接渡せますが、
+スクリプトでは shell history に秘密値を残さない `--ca-api-key-env` を推奨します。
+
+その他の例は [manual](manual.md#headless-usage) を参照してください。
 
 **アップグレード:**
 
@@ -307,6 +351,20 @@ Windows/Linux 管理、クリーンアップスクリプト、定期的なセキ
 
 ## 変更履歴
 
+### 0.1.34
+
+- **完全な headless 設定経路**: `--ca-env-file`、環境変数マッピング、Advisor
+  model、rate-limit、streaming、language、web-fetch の headless 制御を追加。
+- **上書き順序を文書化**: 保存済みメニュー選択 < OS 環境変数 < `.env` ファイル <
+  CLI パラメータ < `--ca-menu` で直接選んだ最終 UI 選択。
+
+### 0.1.33
+
+- **すべての README の先頭にロゴを追加**: 英語、韓国語、日本語、中国語 README
+  の先頭に Claude Any ロゴを配置しました。
+- **npm に画像アセットを同梱**: npm README でも GitHub と同じブランディングが
+  表示されるよう、`logo.png`、`logo-small.png`、`claude-any-adv.png` をパッケージに含めました。
+
 ### 0.1.32
 
 - **NVIDIA preset メニュー修正**: NVIDIA hosted で未対応の `native` option を

package/docs/README.ko.md

@@ -1,6 +1,10 @@
-# Claude Any
-
-![Claude Any: 무료 또는 저비용 LLM으로 Claude Code 경험](../claude-any-adv.png)
+# Claude Any
+
+<p align="center">
+  <img src="../logo.png" alt="Claude Any 로고" width="360">
+</p>
+
+![Claude Any: 무료 또는 저비용 LLM으로 Claude Code 경험](../claude-any-adv.png)
 
 | [English](../README.md) | 한국어 | [日本語](README.ja.md) | [中文](README.zh.md) |
 | --- | --- | --- | --- |
@@ -43,7 +47,7 @@ NVIDIA hosted, self-hosted NIM을 선택하고, Claude Code의 일반 인자는
 
 Credits: One Ciel LLC
 
-현재 버전: `0.1.32`
+현재 버전: `0.1.34`
 
 ## 왜 만들었나
 
@@ -112,14 +116,54 @@ claude-any --ca-provider ollama --ca-base-url http://127.0.0.1:11434 --ca-model
 claude-any --ca-provider nvidia-hosted --ca-model z-ai/glm-4.7 --ca-no-update-check -p "Reply with OK only." --output-format text
 ```
 
-저장된 provider/model을 그대로 쓰고 메뉴만 건너뛰기:
-
-```sh
-CLAUDE_ANY_SKIP_MENU=1 claude-any -p "Summarize this repository." --output-format text
-```
-
-더 많은 예시는 [헤드리스 예제](#헤드리스-에이전트-채팅)와
-[전체 manual](manual.md#headless-usage)을 참고하세요.
+저장된 provider/model을 그대로 쓰고 메뉴만 건너뛰기:
+
+```sh
+CLAUDE_ANY_SKIP_MENU=1 claude-any -p "Summarize this repository." --output-format text
+```
+
+모든 실행 옵션을 플래그로 전달:
+
+```sh
+claude-any --ca-provider nvidia-hosted --ca-base-url https://integrate.api.nvidia.com/v1 --ca-model z-ai/glm-4.7 --ca-advisor-model deepseek-ai/deepseek-v4-pro --ca-api-key-env NVIDIA_API_KEY --ca-max-output-tokens 4096 --ca-context-window 65536 --ca-request-timeout-ms 300000 --ca-rate-limit-rpm 40 --ca-rate-limit-status on --ca-no-update-check -p "Reply with OK only." --output-format text
+```
+
+같은 값을 환경변수로 설정:
+
+```sh
+export CLAUDE_ANY_SKIP_MENU=1
+export CLAUDE_ANY_PROVIDER=nvidia-hosted
+export CLAUDE_ANY_BASE_URL=https://integrate.api.nvidia.com/v1
+export CLAUDE_ANY_MODEL=z-ai/glm-4.7
+export CLAUDE_ANY_ADVISOR_MODEL=deepseek-ai/deepseek-v4-pro
+export CLAUDE_ANY_API_KEY_ENV=NVIDIA_API_KEY
+export CLAUDE_ANY_MAX_OUTPUT_TOKENS=4096
+export CLAUDE_ANY_CONTEXT_WINDOW=65536
+export CLAUDE_ANY_REQUEST_TIMEOUT_MS=300000
+export CLAUDE_ANY_RATE_LIMIT_RPM=40
+export CLAUDE_ANY_RATE_LIMIT_STATUS=on
+claude-any -p "Reply with OK only." --output-format text
+```
+
+`.env` 방식은 같은 `CLAUDE_ANY_*` 값을 파일에 저장한 뒤 명시적으로 불러옵니다:
+
+```sh
+claude-any --ca-env-file .env.claude-any -p "Reply with OK only." --output-format text
+```
+
+오버라이드 순서는 고정되어 있습니다: 메뉴에서 저장된 최종 사용자 선택값이
+기본값이고, OS 환경변수, `--ca-env-file`의 `.env` 값, CLI `--ca-*` 파라미터,
+`--ca-menu`로 다시 연 인터페이스에서 사용자가 직접 고른 값 순서로 덮어씁니다.
+
+헤드리스 지원 범위: provider, base URL, model, Advisor model, API key 또는
+API-key 환경변수, max output, context window, request timeout, RPM limit,
+RPM status 표시, streaming, web search, web fetch, Claude skills, update check,
+language, Ollama context/options, 일반 Claude Code passthrough 인자를 모두 메뉴
+없이 설정할 수 있습니다. API key는 `--ca-api-key`로 직접 전달할 수 있지만,
+스크립트에서는 shell history에 비밀값이 남지 않는 `--ca-api-key-env`를 권장합니다.
+
+더 많은 예시는 [헤드리스 예제](#헤드리스-에이전트-채팅)와
+[전체 manual](manual.md#headless-usage)을 참고하세요.
 
 **업그레이드:**
 
@@ -307,6 +351,20 @@ Windows 이벤트 로그 리뷰, 바이러스/랜섬웨어 침입 시도 정리,
 
 ## 변경 이력
 
+### 0.1.34
+
+- **완전한 headless 설정 경로**: `--ca-env-file`, 환경변수 매핑, Advisor model,
+  rate-limit, streaming, language, web-fetch headless 제어를 추가했습니다.
+- **오버라이드 순서 문서화**: 저장된 메뉴 선택값 < OS 환경변수 < `.env` 파일 <
+  CLI 파라미터 < `--ca-menu`로 직접 고른 최종 인터페이스 선택값.
+
+### 0.1.33
+
+- **모든 README 상단 로고 브랜딩**: 영어, 한국어, 일본어, 중국어 README 최상단에
+  Claude Any 로고를 추가했습니다.
+- **npm 이미지 자산 포함**: npm README에서도 GitHub와 같은 브랜딩이 보이도록
+  `logo.png`, `logo-small.png`, `claude-any-adv.png`를 패키지에 포함했습니다.
+
 ### 0.1.32
 
 - **NVIDIA preset 메뉴 수정**: NVIDIA hosted에서 지원하지 않는 `native` 옵션을

package/docs/README.zh.md

@@ -1,6 +1,10 @@
-# Claude Any
-
-![Claude Any: 使用免费或低成本 LLM 获得 Claude Code 体验](../claude-any-adv.png)
+# Claude Any
+
+<p align="center">
+  <img src="../logo.png" alt="Claude Any 标志" width="360">
+</p>
+
+![Claude Any: 使用免费或低成本 LLM 获得 Claude Code 体验](../claude-any-adv.png)
 
 | [English](../README.md) | [한국어](README.ko.md) | [日本語](README.ja.md) | 中文 |
 | --- | --- | --- | --- |
@@ -43,7 +47,7 @@ NIM，并把普通 Claude Code 参数原样传递。
 
 Credits: One Ciel LLC
 
-当前版本: `0.1.32`
+当前版本: `0.1.34`
 
 ## 为什么存在
 
@@ -109,13 +113,53 @@ claude-any --ca-provider ollama --ca-base-url http://127.0.0.1:11434 --ca-model
 claude-any --ca-provider nvidia-hosted --ca-model z-ai/glm-4.7 --ca-no-update-check -p "Reply with OK only." --output-format text
 ```
 
-使用已保存的 provider/model，只跳过菜单:
-
-```sh
-CLAUDE_ANY_SKIP_MENU=1 claude-any -p "Summarize this repository." --output-format text
-```
-
-更多示例见 [manual](manual.md#headless-usage)。
+使用已保存的 provider/model，只跳过菜单:
+
+```sh
+CLAUDE_ANY_SKIP_MENU=1 claude-any -p "Summarize this repository." --output-format text
+```
+
+用 flags 传入全部启动选项:
+
+```sh
+claude-any --ca-provider nvidia-hosted --ca-base-url https://integrate.api.nvidia.com/v1 --ca-model z-ai/glm-4.7 --ca-advisor-model deepseek-ai/deepseek-v4-pro --ca-api-key-env NVIDIA_API_KEY --ca-max-output-tokens 4096 --ca-context-window 65536 --ca-request-timeout-ms 300000 --ca-rate-limit-rpm 40 --ca-rate-limit-status on --ca-no-update-check -p "Reply with OK only." --output-format text
+```
+
+也可以用环境变量传入同样的值:
+
+```sh
+export CLAUDE_ANY_SKIP_MENU=1
+export CLAUDE_ANY_PROVIDER=nvidia-hosted
+export CLAUDE_ANY_BASE_URL=https://integrate.api.nvidia.com/v1
+export CLAUDE_ANY_MODEL=z-ai/glm-4.7
+export CLAUDE_ANY_ADVISOR_MODEL=deepseek-ai/deepseek-v4-pro
+export CLAUDE_ANY_API_KEY_ENV=NVIDIA_API_KEY
+export CLAUDE_ANY_MAX_OUTPUT_TOKENS=4096
+export CLAUDE_ANY_CONTEXT_WINDOW=65536
+export CLAUDE_ANY_REQUEST_TIMEOUT_MS=300000
+export CLAUDE_ANY_RATE_LIMIT_RPM=40
+export CLAUDE_ANY_RATE_LIMIT_STATUS=on
+claude-any -p "Reply with OK only." --output-format text
+```
+
+`.env` 方式是把同样的 `CLAUDE_ANY_*` 值保存到文件，并显式加载:
+
+```sh
+claude-any --ca-env-file .env.claude-any -p "Reply with OK only." --output-format text
+```
+
+覆盖顺序是固定的: 菜单保存的最后一次用户选择是基线，随后依次由 OS 环境变量、
+`--ca-env-file` 的 `.env` 值、CLI `--ca-*` 参数覆盖；如果使用 `--ca-menu`
+重新打开界面，用户在界面中的最终选择会覆盖前面所有值。
+
+Headless 覆盖范围: provider、base URL、model、Advisor model、API key 或
+API-key 环境变量、max output、context window、request timeout、RPM limit、
+RPM status 显示、streaming、web search、web fetch、Claude skills、update check、
+language、Ollama context/options，以及普通 Claude Code passthrough 参数，都可以
+不打开菜单直接配置。API key 可以用 `--ca-api-key` 直接传入，但脚本中更推荐
+`--ca-api-key-env`，避免密钥进入 shell history。
+
+更多示例见 [manual](manual.md#headless-usage)。
 
 **升级:**
 
@@ -293,6 +337,20 @@ Hermes 格式模型或部分较旧的 Qwen tool template。
 
 ## 更新日志
 
+### 0.1.34
+
+- **完整 headless 配置路径**：新增 `--ca-env-file`、环境变量映射、Advisor
+  model、rate-limit、streaming、language、web-fetch headless 控制。
+- **记录覆盖顺序**：已保存菜单选择 < OS 环境变量 < `.env` 文件 < CLI 参数 <
+  通过 `--ca-menu` 直接选择的最终界面值。
+
+### 0.1.33
+
+- **所有 README 顶部加入 Logo 品牌展示**：在英文、韩文、日文和中文 README
+  顶部添加 Claude Any Logo。
+- **npm 包包含图片资源**：将 `logo.png`、`logo-small.png` 和
+  `claude-any-adv.png` 打进包内，让 npm README 与 GitHub 显示一致的品牌图片。
+
 ### 0.1.32
 
 - **NVIDIA preset 菜单修复**：在 NVIDIA hosted 上应用 LLM preset 时不再触碰

package/docs/manual.md

@@ -1,12 +1,16 @@
-# Claude Any Manual
-
-Claude Any is a pre-launch configuration layer for Claude Code. It lets you
-choose a provider, model, base URL, API key, and provider options before Claude
-Code starts, while passing normal Claude Code arguments through unchanged.
+# Claude Any Manual
+
+<p align="center">
+  <img src="../logo-small.png" alt="Claude Any logo" width="220">
+</p>
+
+Claude Any is a pre-launch configuration layer for Claude Code. It lets you
+choose a provider, model, base URL, API key, and provider options before Claude
+Code starts, while passing normal Claude Code arguments through unchanged.
 
 Credits: One Ciel LLC
 
-Current version: `0.1.32`
+Current version: `0.1.34`
 
 ## Install
 
@@ -243,11 +247,22 @@ Any's saved configuration first, skips the menu, starts the required
 router services, then immediately executes Claude Code with the remaining
 arguments.
 
-Basic pattern:
-
-```sh
-claude-any --ca-provider PROVIDER --ca-model MODEL [claude-code args...]
-```
+Basic pattern:
+
+```sh
+claude-any --ca-provider PROVIDER --ca-model MODEL [claude-code args...]
+```
+
+Configuration precedence is deterministic:
+
+1. Saved user choices from the interactive menu.
+2. OS environment variables such as `CLAUDE_ANY_PROVIDER`.
+3. Values loaded from `--ca-env-file .env.claude-any`.
+4. CLI `--ca-*` parameters.
+5. If `--ca-menu` is present, the final choice made in the interactive menu.
+
+That lets automation provide defaults while still allowing a human operator to
+make the final choice when needed.
 
 Direct Claude Code launch examples:
 
@@ -300,11 +315,11 @@ claude-any \
   --ca-context-window 65536 \
   --ca-max-output-tokens 4096
 
-# NVIDIA hosted API Catalog through the local Claude Any router
-export NVIDIA_API_KEY="..."
-claude-any \
-  --ca-provider nvidia-hosted \
-  --ca-api-key-env NVIDIA_API_KEY \
+# NVIDIA hosted API Catalog through the local Claude Any router
+export NVIDIA_API_KEY="..."
+claude-any \
+  --ca-provider nvidia-hosted \
+  --ca-api-key-env NVIDIA_API_KEY \
   --ca-model moonshotai/kimi-k2.6 \
   --ca-request-timeout-ms 300000
 
@@ -312,9 +327,92 @@ claude-any \
 claude-any \
   --ca-provider self-hosted-nim \
   --ca-base-url http://127.0.0.1:8000 \
-  --ca-model model \
-  --ca-api-key not-used
-```
+  --ca-model model \
+  --ca-api-key not-used
+```
+
+Full headless configuration with flags:
+
+```sh
+claude-any \
+  --ca-language en \
+  --ca-provider nvidia-hosted \
+  --ca-base-url https://integrate.api.nvidia.com/v1 \
+  --ca-model z-ai/glm-4.7 \
+  --ca-advisor-model deepseek-ai/deepseek-v4-pro \
+  --ca-api-key-env NVIDIA_API_KEY \
+  --ca-max-output-tokens 4096 \
+  --ca-context-window 65536 \
+  --ca-request-timeout-ms 300000 \
+  --ca-rate-limit-rpm 40 \
+  --ca-rate-limit-status on \
+  --ca-stream on \
+  --ca-stream-word-chunking off \
+  --ca-web-search \
+  --ca-web-fetch \
+  --ca-enable-skills \
+  --ca-no-update-check \
+  -p "Reply with OK only." \
+  --output-format text
+```
+
+Full headless configuration with environment variables:
+
+```sh
+export CLAUDE_ANY_SKIP_MENU=1
+export CLAUDE_ANY_LANGUAGE=en
+export CLAUDE_ANY_PROVIDER=nvidia-hosted
+export CLAUDE_ANY_BASE_URL=https://integrate.api.nvidia.com/v1
+export CLAUDE_ANY_MODEL=z-ai/glm-4.7
+export CLAUDE_ANY_ADVISOR_MODEL=deepseek-ai/deepseek-v4-pro
+export CLAUDE_ANY_API_KEY_ENV=NVIDIA_API_KEY
+export CLAUDE_ANY_MAX_OUTPUT_TOKENS=4096
+export CLAUDE_ANY_CONTEXT_WINDOW=65536
+export CLAUDE_ANY_REQUEST_TIMEOUT_MS=300000
+export CLAUDE_ANY_RATE_LIMIT_RPM=40
+export CLAUDE_ANY_RATE_LIMIT_STATUS=on
+export CLAUDE_ANY_STREAM=on
+export CLAUDE_ANY_STREAM_WORD_CHUNKING=off
+export CLAUDE_ANY_WEB_SEARCH=on
+export CLAUDE_ANY_WEB_FETCH=on
+export CLAUDE_ANY_DISABLE_SKILLS=off
+export CLAUDE_ANY_UPDATE_CHECK=off
+claude-any -p "Reply with OK only." --output-format text
+```
+
+The same values can be stored in a dotenv-style file and loaded explicitly:
+
+```dotenv
+CLAUDE_ANY_SKIP_MENU=1
+CLAUDE_ANY_LANGUAGE=en
+CLAUDE_ANY_PROVIDER=nvidia-hosted
+CLAUDE_ANY_BASE_URL=https://integrate.api.nvidia.com/v1
+CLAUDE_ANY_MODEL=z-ai/glm-4.7
+CLAUDE_ANY_ADVISOR_MODEL=deepseek-ai/deepseek-v4-pro
+CLAUDE_ANY_API_KEY_ENV=NVIDIA_API_KEY
+CLAUDE_ANY_MAX_OUTPUT_TOKENS=4096
+CLAUDE_ANY_CONTEXT_WINDOW=65536
+CLAUDE_ANY_REQUEST_TIMEOUT_MS=300000
+CLAUDE_ANY_RATE_LIMIT_RPM=40
+CLAUDE_ANY_RATE_LIMIT_STATUS=on
+CLAUDE_ANY_STREAM=on
+CLAUDE_ANY_STREAM_WORD_CHUNKING=off
+CLAUDE_ANY_WEB_SEARCH=on
+CLAUDE_ANY_WEB_FETCH=on
+CLAUDE_ANY_DISABLE_SKILLS=off
+CLAUDE_ANY_UPDATE_CHECK=off
+```
+
+```sh
+claude-any --ca-env-file .env.claude-any -p "Reply with OK only." --output-format text
+```
+
+To let `.env` or CLI values prefill the menu while the user makes the final
+choice, add `--ca-menu`:
+
+```sh
+claude-any --ca-env-file .env.claude-any --ca-model z-ai/glm-4.7 --ca-menu
+```
 
 Passing Claude Code arguments:
 
@@ -348,31 +446,42 @@ claude-any stop
 
 Common Claude Any setup flags:
 
-| Flag | Purpose |
-| --- | --- |
-| `--ca-provider PROVIDER` | Set provider and skip the menu for this launch. |
-| `--ca-model MODEL` | Set the current provider model. |
-| `--ca-base-url URL` | Set the current provider base URL. |
-| `--ca-api-key KEY` | Store the current provider API key directly. Prefer env vars for scripts. |
-| `--ca-api-key-env ENVVAR` | Store the current provider API key from an environment variable. |
+| Flag | Purpose |
+| --- | --- |
+| `--ca-env-file PATH` | Load `CLAUDE_ANY_*` values from a dotenv-style file. |
+| `--ca-menu` | Apply env/flag values, then open the interactive menu for the final user choice. |
+| `--ca-language en|ko|ja|zh` | Set display language. |
+| `--ca-provider PROVIDER` | Set provider and skip the menu for this launch. |
+| `--ca-model MODEL` | Set the current provider model. |
+| `--ca-advisor-model MODEL` | Set the Advisor model; use `off` to disable it. |
+| `--ca-base-url URL` | Set the current provider base URL. |
+| `--ca-api-key KEY` | Store the current provider API key directly. Prefer env vars for scripts. |
+| `--ca-api-key-env ENVVAR` | Store the current provider API key from an environment variable. |
 | `--ca-set-api-key PROVIDER KEY` | Store a key for a specific provider. |
 | `--ca-set-api-key-env PROVIDER ENVVAR` | Store a provider key from an environment variable. |
-| `--ca-max-output-tokens VALUE` | Set provider output-token cap. |
-| `--ca-context-window VALUE` | Set provider/router context-window cap where supported. |
-| `--ca-request-timeout-ms VALUE` | Set upstream request timeout in milliseconds. |
-| `--ca-ollama-num-ctx VALUE` | Set Ollama `num_ctx`. |
-| `--ca-ollama-ctx-range MIN MAX` | Set Ollama auto context range. |
-| `--ca-ollama-option KEY=VALUE` | Set an Ollama option such as `temperature=0.3`. |
-| `--ca-web-search` / `--ca-no-web-search` | Force-enable or disable web-search MCP for this launch. |
-| `--ca-disable-skills` / `--ca-enable-skills` | Control Claude Code skills for this launch. |
-| `--ca-no-update-check` | Skip the Claude Code update check. |
-| `--ca-status` | Print status and exit. |
+| `--ca-max-output-tokens VALUE` | Set provider output-token cap. |
+| `--ca-context-window VALUE` | Set provider/router context-window cap where supported. |
+| `--ca-request-timeout-ms VALUE` | Set upstream request timeout in milliseconds. |
+| `--ca-rate-limit-rpm VALUE` | Set provider RPM limit; `0` disables throttling but keeps usage display. |
+| `--ca-rate-limit-status on|off` | Show or hide RPM/rate-limit status in the Claude Code statusline. |
+| `--ca-stream on|off` | Enable or disable streaming through the router. |
+| `--ca-stream-word-chunking on|off` | Split streamed text into smaller word-like chunks when enabled. |
+| `--ca-ollama-num-ctx VALUE` | Set Ollama `num_ctx`. |
+| `--ca-ollama-ctx-range MIN MAX` | Set Ollama auto context range. |
+| `--ca-ollama-option KEY=VALUE` | Set an Ollama option such as `temperature=0.3`. |
+| `--ca-web-search` / `--ca-no-web-search` | Force-enable or disable web-search MCP for this launch. |
+| `--ca-web-fetch` / `--ca-no-web-fetch` | Enable or disable fetch MCP for web page content. |
+| `--ca-disable-skills` / `--ca-enable-skills` | Control Claude Code skills for this launch. |
+| `--ca-no-update-check` | Skip the Claude Code update check. |
+| `--ca-status` | Print status and exit. |
 | `--ca-stop` | Stop managed router services and exit. |
 
 Notes for automation:
 
-- `--ca-api-key-env` avoids putting secrets directly in shell history.
-- `claude-any stop` is safe to run before scripted tests to remove stale
+- `--ca-api-key-env` avoids putting secrets directly in shell history.
+- `--ca-api-key` and `--ca-set-api-key` are available for direct key passing,
+  but prefer the environment-variable forms in shared scripts and terminals.
+- `claude-any stop` is safe to run before scripted tests to remove stale
   router/proxy processes.
 - Use `claude-any test 60 auto` for a quick readiness check and reserve
   `claude-any test 180 full` for deeper provider validation.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@oneciel-ai/claude-any",
-  "version": "0.1.32",
+  "version": "0.1.34",
   "description": "Claude Code provider selector for Anthropic, Ollama, Ollama Cloud, vLLM, NVIDIA hosted, and self-hosted NIM.",
   "license": "MIT",
   "author": "One Ciel LLC",
@@ -24,9 +24,12 @@
     "claude-any-tool-guard.py",
     "npm-bin/",
     "install.sh",
-    "install.ps1",
-    "README.md",
-    "LICENSE",
+    "install.ps1",
+    "README.md",
+    "logo.png",
+    "logo-small.png",
+    "claude-any-adv.png",
+    "LICENSE",
     "NOTICE",
     "docs/"
   ],