fix(providers): enforce role alternation for non-Claude providers
Some LLM providers (OpenAI-compat, Azure, vLLM, Ollama) reject requests with consecutive same-role messages or trailing assistant messages. Add _enforce_role_alternation() to merge consecutive same-role user/assistant messages and strip trailing assistant messages before sending to the API.
This commit is contained in:
@@ -94,9 +94,11 @@ class AzureOpenAIProvider(LLMProvider):
|
||||
) -> dict[str, Any]:
|
||||
"""Prepare the request payload with Azure OpenAI 2024-10-21 compliance."""
|
||||
payload: dict[str, Any] = {
|
||||
"messages": self._sanitize_request_messages(
|
||||
self._sanitize_empty_content(messages),
|
||||
_AZURE_MSG_KEYS,
|
||||
"messages": self._enforce_role_alternation(
|
||||
self._sanitize_request_messages(
|
||||
self._sanitize_empty_content(messages),
|
||||
_AZURE_MSG_KEYS,
|
||||
)
|
||||
),
|
||||
"max_completion_tokens": max(1, max_tokens), # Azure API 2024-10-21 uses max_completion_tokens
|
||||
}
|
||||
|
||||
@@ -196,6 +196,42 @@ class LLMProvider(ABC):
|
||||
err = (content or "").lower()
|
||||
return any(marker in err for marker in cls._TRANSIENT_ERROR_MARKERS)
|
||||
|
||||
@staticmethod
|
||||
def _enforce_role_alternation(messages: list[dict[str, Any]]) -> list[dict[str, Any]]:
|
||||
"""Merge consecutive same-role messages and drop trailing assistant messages.
|
||||
|
||||
Some providers (OpenAI-compat, Azure, vLLM, Ollama, etc.) reject requests
|
||||
where the last message is 'assistant' (prefill not supported) or two
|
||||
consecutive non-system messages share the same role.
|
||||
"""
|
||||
if not messages:
|
||||
return messages
|
||||
|
||||
merged: list[dict[str, Any]] = []
|
||||
for msg in messages:
|
||||
role = msg.get("role")
|
||||
if (
|
||||
merged
|
||||
and role != "system"
|
||||
and role not in ("tool",)
|
||||
and merged[-1].get("role") == role
|
||||
and role in ("user", "assistant")
|
||||
):
|
||||
prev = merged[-1]
|
||||
prev_content = prev.get("content") or ""
|
||||
curr_content = msg.get("content") or ""
|
||||
if isinstance(prev_content, str) and isinstance(curr_content, str):
|
||||
prev["content"] = (prev_content + "\n\n" + curr_content).strip()
|
||||
else:
|
||||
merged[-1] = dict(msg)
|
||||
else:
|
||||
merged.append(dict(msg))
|
||||
|
||||
while merged and merged[-1].get("role") == "assistant":
|
||||
merged.pop()
|
||||
|
||||
return merged
|
||||
|
||||
@staticmethod
|
||||
def _strip_image_content(messages: list[dict[str, Any]]) -> list[dict[str, Any]] | None:
|
||||
"""Replace image_url blocks with text placeholder. Returns None if no images found."""
|
||||
|
||||
@@ -215,7 +215,7 @@ class OpenAICompatProvider(LLMProvider):
|
||||
clean["tool_calls"] = normalized
|
||||
if "tool_call_id" in clean and clean["tool_call_id"]:
|
||||
clean["tool_call_id"] = map_id(clean["tool_call_id"])
|
||||
return sanitized
|
||||
return self._enforce_role_alternation(sanitized)
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Build kwargs
|
||||
|
||||
Reference in New Issue
Block a user