chore: auto-commit from dashboard

src/router.py

@@ -9,6 +9,8 @@ from datetime import datetime, timezone
 from pathlib import Path
 from typing import Callable
 
+import requests
+
 from src.config import Config
 from src.fast_commands import dispatch as fast_dispatch, set_channel_context
 from src.last_response_store import set_last as _set_last_response
@@ -87,6 +89,63 @@ def _get_config() -> Config:
     return _config
 
 
+# Claude CLI rate-limit errors look like:
+#   "Claude CLI error (exit 1): You've hit your session limit · resets 10:50am (UTC)"
+# (also seen for the total subscription limit, not just per-session — same phrasing).
+_RATE_LIMIT_RE = re.compile(r"hit your .*limit", re.IGNORECASE)
+
+_LOCAL_FALLBACK_SYSTEM_PROMPT = (
+    "Ești Echo, asistentul personal al lui Marius, dar rulezi temporar pe un "
+    "model local mic pentru că Claude a atins limita de rate. Nu ai acces la "
+    "unelte, memorie sau istoricul conversației — răspunde scurt și direct, "
+    "doar la mesajul curent, în limba în care a fost scris."
+)
+
+_LOCAL_FALLBACK_PREFIX = (
+    "⚠️ Claude e la limită — răspund temporar pe un model local, mai simplu "
+    "(fără istoric, fără unelte):\n\n"
+)
+
+
+def _is_rate_limit_error(err: Exception) -> bool:
+    return bool(_RATE_LIMIT_RE.search(str(err)))
+
+
+def _local_fallback_reply(text: str) -> str | None:
+    """Best-effort reply from the local llama.cpp fallback (LXC 104, Qwen3.5-2B).
+
+    Returns None if the fallback itself is unreachable/fails, so the caller
+    can fall back further to surfacing the original Claude error.
+    """
+    cfg = _get_config().get("local_fallback", {}) or {}
+    if not cfg.get("enabled", False):
+        return None
+    url = cfg.get("url")
+    if not url:
+        return None
+    try:
+        resp = requests.post(
+            url,
+            json={
+                "messages": [
+                    {"role": "system", "content": _LOCAL_FALLBACK_SYSTEM_PROMPT},
+                    {"role": "user", "content": text},
+                ],
+                "temperature": 0.3,
+                "max_tokens": 500,
+            },
+            timeout=45,
+        )
+        resp.raise_for_status()
+        content = resp.json()["choices"][0]["message"]["content"].strip()
+        if not content:
+            return None
+        return _LOCAL_FALLBACK_PREFIX + content
+    except Exception as e:  # noqa: BLE001
+        log.error("Local fallback LLM failed: %s", e)
+        return None
+
+
 def route_message(
     channel_id: str,
     user_id: str,
@@ -218,6 +277,12 @@ def route_message(
         return response, False
     except Exception as e:
         log.error("Claude error for channel %s: %s", channel_id, e)
+        if _is_rate_limit_error(e):
+            log.warning("Rate limit detected for channel %s — trying local fallback", channel_id)
+            fallback = _local_fallback_reply(text)
+            if fallback is not None:
+                _set_last_response(channel_id, fallback)
+                return fallback, False
         return f"Error: {e}", False