fix: cap image download size at 50 MB, validate tool call parser fields

vision_tools.py: _download_image() loads the full HTTP response body into
memory via response.content (line 190) with no Content-Length check and no
max file size limit.  An attacker-hosted multi-gigabyte file causes OOM.
Add a 50 MB hard cap: check Content-Length header before download, and
verify actual body size before writing to disk.

hermes_parser.py: tc_data["name"] at line 57 raises KeyError when the LLM
outputs a tool call JSON without a "name" field.  The outer except catches
it silently, causing the entire tool call to be lost with zero diagnostics.
Add "name" field validation before constructing the ChatCompletionMessage.

mistral_parser.py: tc["name"] at line 101 has the same KeyError issue in
the pre-v11 format path.  The fallback decoder (line 112) already checks
"name" correctly, but the primary path does not.  Add validation to match.

Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>

environments/tool_call_parsers/hermes_parser.py

@@ -49,6 +49,8 @@ class HermesToolCallParser(ToolCallParser):
                     continue
 
                 tc_data = json.loads(raw_json)
+                if "name" not in tc_data:
+                    continue
                 tool_calls.append(
                     ChatCompletionMessageToolCall(
                         id=f"call_{uuid.uuid4().hex[:8]}",

environments/tool_call_parsers/mistral_parser.py

@@ -89,6 +89,8 @@ class MistralToolCallParser(ToolCallParser):
                         parsed = [parsed]
 
                     for tc in parsed:
+                        if "name" not in tc:
+                            continue
                         args = tc.get("arguments", {})
                         if isinstance(args, dict):
                             args = json.dumps(args, ensure_ascii=False)