fix: merge consecutive user messages into single message

Some LLM providers (Minimax, Dashscope) strictly reject consecutive
messages with the same role. build_messages() was emitting two separate
user messages back-to-back: the runtime context and the actual user
content.

Merge them into a single user message, handling both plain text and
multimodal (image) content. Update _save_turn() to strip the runtime
context prefix from the merged message when persisting to session
history.

Fixes #1414
Fixes #1344
This commit is contained in:
Nikolas de Hor
2026-03-03 00:59:58 -03:00
parent 3c79404194
commit ad99d5aaa0
2 changed files with 27 additions and 9 deletions

View File

@@ -464,14 +464,23 @@ class AgentLoop:
entry["content"] = content[:self._TOOL_RESULT_MAX_CHARS] + "\n... (truncated)"
elif role == "user":
if isinstance(content, str) and content.startswith(ContextBuilder._RUNTIME_CONTEXT_TAG):
continue
# Strip the runtime-context prefix, keep only the user text.
parts = content.split("\n\n", 1)
if len(parts) > 1 and parts[1].strip():
entry["content"] = parts[1]
else:
continue
if isinstance(content, list):
entry["content"] = [
{"type": "text", "text": "[image]"} if (
c.get("type") == "image_url"
and c.get("image_url", {}).get("url", "").startswith("data:image/")
) else c for c in content
]
filtered = []
for c in content:
if c.get("type") == "text" and isinstance(c.get("text"), str) and c["text"].startswith(ContextBuilder._RUNTIME_CONTEXT_TAG):
continue # Strip runtime context from multimodal messages
if (c.get("type") == "image_url"
and c.get("image_url", {}).get("url", "").startswith("data:image/")):
filtered.append({"type": "text", "text": "[image]"})
else:
filtered.append(c)
entry["content"] = filtered
entry.setdefault("timestamp", datetime.now().isoformat())
session.messages.append(entry)
session.updated_at = datetime.now()