Merge remote-tracking branch 'origin/main' into pr-1618

nanobot/channels/whatsapp.py

@@ -2,6 +2,7 @@
 
 import asyncio
 import json
+import mimetypes
 from collections import OrderedDict
 
 from loguru import logger
@@ -128,10 +129,22 @@ class WhatsAppChannel(BaseChannel):
                 logger.info("Voice message received from {}, but direct download from bridge is not yet supported.", sender_id)
                 content = "[Voice Message: Transcription not available for WhatsApp yet]"
 
+            # Extract media paths (images/documents/videos downloaded by the bridge)
+            media_paths = data.get("media") or []
+
+            # Build content tags matching Telegram's pattern: [image: /path] or [file: /path]
+            if media_paths:
+                for p in media_paths:
+                    mime, _ = mimetypes.guess_type(p)
+                    media_type = "image" if mime and mime.startswith("image/") else "file"
+                    media_tag = f"[{media_type}: {p}]"
+                    content = f"{content}\n{media_tag}" if content else media_tag
+
             await self._handle_message(
                 sender_id=sender_id,
                 chat_id=sender,  # Use full LID for replies
                 content=content,
+                media=media_paths,
                 metadata={
                     "message_id": message_id,
                     "timestamp": data.get("timestamp"),

nanobot/providers/litellm_provider.py

@@ -1,5 +1,6 @@
 """LiteLLM provider implementation for multi-provider support."""
 
+import hashlib
 import os
 import secrets
 import string
@@ -166,16 +167,48 @@ class LiteLLMProvider(LLMProvider):
             return _ANTHROPIC_EXTRA_KEYS
         return frozenset()
 
+    @staticmethod
+    def _normalize_tool_call_id(tool_call_id: Any) -> Any:
+        """Normalize tool_call_id to a provider-safe 9-char alphanumeric form."""
+        if not isinstance(tool_call_id, str):
+            return tool_call_id
+        if len(tool_call_id) == 9 and tool_call_id.isalnum():
+            return tool_call_id
+        return hashlib.sha1(tool_call_id.encode()).hexdigest()[:9]
+
     @staticmethod
     def _sanitize_messages(messages: list[dict[str, Any]], extra_keys: frozenset[str] = frozenset()) -> list[dict[str, Any]]:
         """Strip non-standard keys and ensure assistant messages have a content key."""
         allowed = _ALLOWED_MSG_KEYS | extra_keys
         sanitized = []
+        id_map: dict[str, str] = {}
+
+        def map_id(value: Any) -> Any:
+            if not isinstance(value, str):
+                return value
+            return id_map.setdefault(value, LiteLLMProvider._normalize_tool_call_id(value))
+
         for msg in messages:
             clean = {k: v for k, v in msg.items() if k in allowed}
             # Strict providers require "content" even when assistant only has tool_calls
             if clean.get("role") == "assistant" and "content" not in clean:
                 clean["content"] = None
+
+            # Keep assistant tool_calls[].id and tool tool_call_id in sync after
+            # shortening, otherwise strict providers reject the broken linkage.
+            if isinstance(clean.get("tool_calls"), list):
+                normalized_tool_calls = []
+                for tc in clean["tool_calls"]:
+                    if not isinstance(tc, dict):
+                        normalized_tool_calls.append(tc)
+                        continue
+                    tc_clean = dict(tc)
+                    tc_clean["id"] = map_id(tc_clean.get("id"))
+                    normalized_tool_calls.append(tc_clean)
+                clean["tool_calls"] = normalized_tool_calls
+
+            if "tool_call_id" in clean and clean["tool_call_id"]:
+                clean["tool_call_id"] = map_id(clean["tool_call_id"])
             sanitized.append(clean)
         return sanitized