@oneciel-ai/claude-any 0.1.42 → 0.1.44

package/README.md

@@ -48,7 +48,7 @@ arguments through unchanged.
 
 Credits: One Ciel LLC
 
-Current version: `0.1.42`
+Current version: `0.1.44`
 
 ## Why This Exists
 
@@ -381,6 +381,18 @@ steps under that larger model's supervision.
 
 ## Changelog
 
+### 0.1.44
+
+- **Statusline split**: turning Rate Limit status off now hides only RPM,
+  server-limit, and wait counters. Upstream progress, retry, error, and token
+  diagnostics remain visible.
+
+### 0.1.43
+
+- **429 backoff retry**: upstream `429 Too Many Requests` responses are now
+  handled as retry/backoff events across all retry attempts instead of leaking
+  the raw upstream error after the first backoff.
+
 ### 0.1.42
 
 - **Live stream progress**: the statusline now updates streamed upstream output

package/claude_any.py

@@ -85,7 +85,7 @@ PROVIDER_LABELS = {
     "self-hosted-nim": "Self Hosted NIM",
 }
 APP_NAME = "Claude Any"
-VERSION = "0.1.42"
+VERSION = "0.1.44"
 CREDITS = "Credits: One Ciel LLC"
 
 LOG_LEVELS = {"SILENT": 0, "ERROR": 1, "WARN": 2, "INFO": 3, "DEBUG": 4, "TRACE": 5}
@@ -1249,10 +1249,11 @@ def main():
     except Exception:
         session = {}
     cfg = load_json(CONFIG_PATH, {})
-    providers = cfg.get("providers") if isinstance(cfg.get("providers"), dict) else {}
-    provider = str(cfg.get("current_provider") or "")
-    pcfg = providers.get(provider) if isinstance(providers.get(provider), dict) else {}
-    model = str(pcfg.get("current_model") or "")
+    providers = cfg.get("providers") if isinstance(cfg.get("providers"), dict) else {}
+    provider = str(cfg.get("current_provider") or "")
+    pcfg = providers.get(provider) if isinstance(providers.get(provider), dict) else {}
+    rpm_status = bool(pcfg.get("rate_limit_status", True))
+    model = str(pcfg.get("current_model") or "")
     raw_rpm = pcfg.get("rate_limit_rpm")
     if raw_rpm is None and provider in ("nvidia-hosted", "self-hosted-nim", "ollama", "ollama-cloud"):
         raw_rpm = 40
@@ -1303,29 +1304,33 @@ def main():
     left = f"[{model_name}]"
     if dir_name:
         left += f" {dir_name}"
-    if rpm > 0:
-        shown_limit = display_capacity(rpm)
-        shown_used = min(used, shown_limit)
-        rpm_text = f"RPM used: {shown_used}/{shown_limit}"
-    else:
-        rpm_text = f"RPM used: {used}/min (unlimited)"
-    if server_rpm or server_remaining is not None or server_reset_seconds is not None:
-        parts = []
-        if server_remaining is not None:
-            parts.append(f"remaining {server_remaining}")
-        if server_rpm:
-            parts.append(f"limit {server_rpm}")
-        try:
-            if server_reset_seconds is not None and float(server_reset_seconds) > 0:
-                parts.append(f"reset {float(server_reset_seconds):.0f}s")
-        except Exception:
-            pass
-        if parts:
-            rpm_text += " | server " + ", ".join(parts)
-    if penalty_until > now:
-        rpm_text += f" | wait {max(0.0, penalty_until - now):.0f}s"
-    elif last_wait >= 0.5 and 0.0 <= now - updated_at < 60.0:
-        rpm_text += f" | wait {last_wait:.1f}s"
+    status_parts = []
+    if rpm_status:
+        if rpm > 0:
+            shown_limit = display_capacity(rpm)
+            shown_used = min(used, shown_limit)
+            rpm_text = f"RPM used: {shown_used}/{shown_limit}"
+        else:
+            rpm_text = f"RPM used: {used}/min (unlimited)"
+        if server_rpm or server_remaining is not None or server_reset_seconds is not None:
+            parts = []
+            if server_remaining is not None:
+                parts.append(f"remaining {server_remaining}")
+            if server_rpm:
+                parts.append(f"limit {server_rpm}")
+            try:
+                if server_reset_seconds is not None and float(server_reset_seconds) > 0:
+                    parts.append(f"reset {float(server_reset_seconds):.0f}s")
+            except Exception:
+                pass
+            if parts:
+                rpm_text += " | server " + ", ".join(parts)
+        if penalty_until > now:
+            rpm_text += f" | wait {max(0.0, penalty_until - now):.0f}s"
+        elif last_wait >= 0.5 and 0.0 <= now - updated_at < 60.0:
+            rpm_text += f" | wait {last_wait:.1f}s"
+        status_parts.append(rpm_text)
+    activity_text = ""
     if isinstance(activity, dict):
         try:
             age = now - float(activity.get("updated_at") or 0)
@@ -1334,30 +1339,48 @@ def main():
         if 0 <= age < 180:
             event = str(activity.get("event") or "")
             if event == "retry":
-                rpm_text += f" | retry {activity.get('attempt')}/{activity.get('total')}"
+                activity_text = f"retry {activity.get('attempt')}/{activity.get('total')}"
+                wait = activity.get("wait")
+                try:
+                    if wait is not None and float(wait) > 0:
+                        activity_text += f" wait {float(wait):.0f}s"
+                except Exception:
+                    pass
+                tokens = activity.get("tokens")
+                if tokens:
+                    try:
+                        activity_text += f" last input {int(tokens):,} tok"
+                    except Exception:
+                        activity_text += f" last input {tokens} tok"
             elif event == "request":
                 tokens = activity.get("tokens")
-                rpm_text += f" | upstream {age:.0f}s"
+                activity_text = f"upstream {age:.0f}s"
                 if tokens:
                     try:
-                        rpm_text += f" {int(tokens):,} tok"
+                        activity_text += f" {int(tokens):,} tok"
                     except Exception:
-                        rpm_text += f" {tokens} tok"
+                        activity_text += f" {tokens} tok"
                 output_tokens = activity.get("output_tokens")
                 if output_tokens:
                     try:
-                        rpm_text += f" -> {int(output_tokens):,} tok"
+                        activity_text += f" -> {int(output_tokens):,} tok"
                     except Exception:
-                        rpm_text += f" -> {output_tokens} tok"
+                        activity_text += f" -> {output_tokens} tok"
                 chunks = activity.get("chunks")
                 if chunks:
                     try:
-                        rpm_text += f" ({int(chunks):,} chunks)"
+                        activity_text += f" ({int(chunks):,} chunks)"
                     except Exception:
-                        rpm_text += f" ({chunks} chunks)"
+                        activity_text += f" ({chunks} chunks)"
             elif event in ("success", "error"):
-                rpm_text += f" | {event} {age:.0f}s"
-    print(f"{left} | {color(rpm_text)}")
+                activity_text = f"{event} {age:.0f}s"
+    if activity_text:
+        status_parts.append(activity_text)
+    status_text = " | ".join(status_parts)
+    if status_text:
+        print(f"{left} | {color(status_text)}")
+    else:
+        print(left)
 
 
 if __name__ == "__main__":
@@ -4971,19 +4994,30 @@ def upstream_http_error_message(exc: urllib.error.HTTPError, raw: str | None = N
 UPSTREAM_RETRY_HTTP_CODES: frozenset[int] = frozenset({502, 503, 504})
 
 
-def upstream_retry_message(attempt: int, total: int) -> str:
-    lang = str(load_config().get("language") or "en")
-    if lang == "ko":
-        return f"서버가 응답하지 않아 재시도합니다 ({attempt}/{total})."
+def upstream_retry_message(attempt: int, total: int) -> str:
+    lang = str(load_config().get("language") or "en")
+    if lang == "ko":
+        return f"서버가 응답하지 않아 재시도합니다 ({attempt}/{total})."
     if lang == "ja":
         return f"サーバーが応答しないため再試行します ({attempt}/{total})。"
     if lang == "zh":
         return f"服务器未响应，正在重试 ({attempt}/{total})。"
-    return f"Upstream server did not respond; retrying ({attempt}/{total})."
-
-
-def upstream_retry_wait_seconds(attempt: int) -> float:
-    return min(20.0, 2.0 * max(1, attempt))
+    return f"Upstream server did not respond; retrying ({attempt}/{total})."
+
+
+def upstream_rate_limit_retry_message(attempt: int, total: int) -> str:
+    lang = str(load_config().get("language") or "en")
+    if lang == "ko":
+        return f"Upstream rate limit에 도달해 대기 후 재시도합니다 ({attempt}/{total})."
+    if lang == "ja":
+        return f"Upstream rate limit に達したため、待機して再試行します ({attempt}/{total})。"
+    if lang == "zh":
+        return f"已达到 upstream rate limit，等待后重试 ({attempt}/{total})。"
+    return f"Upstream rate limit reached; waiting before retry ({attempt}/{total})."
+
+
+def upstream_retry_wait_seconds(attempt: int) -> float:
+    return min(20.0, 2.0 * max(1, attempt))
 
 
 def retryable_timeout_exception(exc: BaseException) -> bool:
@@ -5028,10 +5062,15 @@ def post_json_with_rate_retry(
         except urllib.error.HTTPError as exc:
             raw = exc.read().decode("utf-8", errors="ignore")
             learn_router_rate_limit_headers(provider, pcfg, model, exc.headers)
-            if exc.code == 429 and attempt == 0:
-                wait = register_router_rate_limit_backoff(provider, pcfg, model, exc.headers.get("Retry-After"))
-                time.sleep(wait)
-                continue
+            if exc.code == 429 and attempt + 1 < max_attempts:
+                retry_no = attempt + 1
+                wait = register_router_rate_limit_backoff(provider, pcfg, model, exc.headers.get("Retry-After"))
+                write_router_activity("retry", provider, model, attempt=retry_no, total=gateway_retries, code=exc.code, wait=wait, tokens=token_estimate, bytes=byte_estimate)
+                router_log("WARN", f"upstream_rate_limit_retry provider={provider} model={model} attempt={retry_no}/{gateway_retries} wait={wait:.2f}s tokens={token_estimate} bytes={byte_estimate}")
+                if retry_notice:
+                    retry_notice(upstream_rate_limit_retry_message(retry_no, gateway_retries))
+                time.sleep(wait)
+                continue
             if exc.code in UPSTREAM_RETRY_HTTP_CODES and attempt + 1 < max_attempts:
                 retry_no = attempt + 1
                 write_router_activity("retry", provider, model, attempt=retry_no, total=gateway_retries, code=exc.code, tokens=token_estimate, bytes=byte_estimate)
@@ -5092,8 +5131,13 @@ def open_openai_stream_with_rate_retry(
         except urllib.error.HTTPError as exc:
             raw = exc.read().decode("utf-8", errors="ignore")
             learn_router_rate_limit_headers(provider, pcfg, model, exc.headers)
-            if exc.code == 429 and attempt == 0:
+            if exc.code == 429 and attempt + 1 < max_attempts:
+                retry_no = attempt + 1
                 wait = register_router_rate_limit_backoff(provider, pcfg, model, exc.headers.get("Retry-After"))
+                write_router_activity("retry", provider, model, attempt=retry_no, total=gateway_retries, code=exc.code, wait=wait, tokens=token_estimate, bytes=byte_estimate, stream=True)
+                router_log("WARN", f"upstream_stream_rate_limit_retry provider={provider} model={model} attempt={retry_no}/{gateway_retries} wait={wait:.2f}s tokens={token_estimate} bytes={byte_estimate}")
+                if retry_notice:
+                    retry_notice(upstream_rate_limit_retry_message(retry_no, gateway_retries))
                 time.sleep(wait)
                 continue
             if exc.code in UPSTREAM_RETRY_HTTP_CODES and attempt + 1 < max_attempts:

package/docs/README.ja.md

@@ -47,7 +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: `0.1.42`
+現在のバージョン: `0.1.44`
 
 ## 作られた理由
 
@@ -351,6 +351,17 @@ 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
 
+### 0.1.44
+
+- **Statusline split**: Rate Limit status を off にした場合、RPM、server-limit、
+  wait counter だけを非表示にします。Upstream 進捗、retry、error、token 診断は
+  引き続き表示されます。
+
+### 0.1.43
+
+- **429 backoff retry**: upstream `429 Too Many Requests` 応答を初回 backoff 後に
+  raw error として漏らさず、すべての retry attempt で backoff/retry event として処理します。
+
 ### 0.1.42
 
 - **ライブストリーム進捗**: statusline が upstream streaming の出力進捗を

package/docs/README.ko.md

@@ -47,7 +47,7 @@ NVIDIA hosted, self-hosted NIM을 선택하고, Claude Code의 일반 인자는
 
 Credits: One Ciel LLC
 
-현재 버전: `0.1.42`
+현재 버전: `0.1.44`
 
 ## 왜 만들었나
 
@@ -351,6 +351,17 @@ Windows 이벤트 로그 리뷰, 바이러스/랜섬웨어 침입 시도 정리,
 
 ## 변경 이력
 
+### 0.1.44
+
+- **Statusline 분리**: Rate Limit status를 off로 바꾸면 RPM, server-limit,
+  wait 카운터만 숨깁니다. Upstream 진행, retry, error, token 진단은 계속
+  표시됩니다.
+
+### 0.1.43
+
+- **429 backoff retry**: upstream `429 Too Many Requests` 응답을 첫 backoff 이후
+  raw error로 흘리지 않고, 모든 retry attempt에서 backoff/retry 이벤트로 처리합니다.
+
 ### 0.1.42
 
 - **실시간 스트림 진행 표시**: statusline이 upstream streaming 출력 진행을

package/docs/README.zh.md

@@ -47,7 +47,7 @@ NIM，并把普通 Claude Code 参数原样传递。
 
 Credits: One Ciel LLC
 
-当前版本: `0.1.42`
+当前版本: `0.1.44`
 
 ## 为什么存在
 
@@ -337,6 +337,16 @@ Hermes 格式模型或部分较旧的 Qwen tool template。
 
 ## 更新日志
 
+### 0.1.44
+
+- **Statusline split**：关闭 Rate Limit status 后只隐藏 RPM、server-limit 和
+  wait 计数。Upstream 进度、retry、error 和 token 诊断仍会显示。
+
+### 0.1.43
+
+- **429 backoff retry**：upstream `429 Too Many Requests` 响应现在会在所有 retry
+  attempt 中作为 backoff/retry event 处理，不再在首次 backoff 后泄漏 raw error。
+
 ### 0.1.42
 
 - **实时流式进度**：statusline 会持续更新 upstream streaming 输出进度，

package/docs/manual.md

@@ -10,7 +10,7 @@ Code starts, while passing normal Claude Code arguments through unchanged.
 
 Credits: One Ciel LLC
 
-Current version: `0.1.42`
+Current version: `0.1.44`
 
 ## Install
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@oneciel-ai/claude-any",
-  "version": "0.1.42",
+  "version": "0.1.44",
   "description": "Claude Code provider selector for Anthropic, Ollama, Ollama Cloud, vLLM, NVIDIA hosted, and self-hosted NIM.",
   "license": "MIT",
   "author": "One Ciel LLC",