Skip to content

Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

fix(vlm): add max_tokens parameter to VLM completion calls to prevent vLLM rejection (#689)

Matt Van Horn985c60af2a7b
diff --git a/openviking/models/vlm/backends/litellm_vlm.py b/openviking/models/vlm/backends/litellm_vlm.py
index c64e16530..eb3bffa9a 100644
--- a/openviking/models/vlm/backends/litellm_vlm.py
+++ b/openviking/models/vlm/backends/litellm_vlm.py
@@ -199,6 +199,8 @@ class LiteLLMVLMProvider(VLMBase):
"messages": messages,
"temperature": self.temperature,
}
+ if self.max_tokens is not None:
+ kwargs["max_tokens"] = self.max_tokens
if self.api_key:
kwargs["api_key"] = self.api_key
diff --git a/openviking/models/vlm/backends/openai_vlm.py b/openviking/models/vlm/backends/openai_vlm.py
index 68649364e..862342b2e 100644
--- a/openviking/models/vlm/backends/openai_vlm.py
+++ b/openviking/models/vlm/backends/openai_vlm.py
@@ -62,6 +62,8 @@ class OpenAIVLM(VLMBase):
"messages": [{"role": "user", "content": prompt}],
"temperature": self.temperature,
}
+ if self.max_tokens is not None:
+ kwargs["max_tokens"] = self.max_tokens
response = client.chat.completions.create(**kwargs)
self._update_token_usage_from_response(response)
@@ -77,6 +79,8 @@ class OpenAIVLM(VLMBase):
"messages": [{"role": "user", "content": prompt}],
"temperature": self.temperature,
}
+ if self.max_tokens is not None:
+ kwargs["max_tokens"] = self.max_tokens
last_error = None
for attempt in range(max_retries + 1):
@@ -165,6 +169,8 @@ class OpenAIVLM(VLMBase):
"messages": [{"role": "user", "content": content}],
"temperature": self.temperature,
}
+ if self.max_tokens is not None:
+ kwargs["max_tokens"] = self.max_tokens
response = client.chat.completions.create(**kwargs)
self._update_token_usage_from_response(response)
@@ -189,6 +195,8 @@ class OpenAIVLM(VLMBase):
"messages": [{"role": "user", "content": content}],
"temperature": self.temperature,
}
+ if self.max_tokens is not None:
+ kwargs["max_tokens"] = self.max_tokens
response = await client.chat.completions.create(**kwargs)
self._update_token_usage_from_response(response)
diff --git a/openviking/models/vlm/backends/volcengine_vlm.py b/openviking/models/vlm/backends/volcengine_vlm.py
index 7880818a4..eedbff83f 100644
--- a/openviking/models/vlm/backends/volcengine_vlm.py
+++ b/openviking/models/vlm/backends/volcengine_vlm.py
@@ -68,6 +68,8 @@ class VolcEngineVLM(OpenAIVLM):
"temperature": self.temperature,
"thinking": {"type": "disabled" if not thinking else "enabled"},
}
+ if self.max_tokens is not None:
+ kwargs["max_tokens"] = self.max_tokens
response = client.chat.completions.create(**kwargs)
self._update_token_usage_from_response(response)
@@ -84,6 +86,8 @@ class VolcEngineVLM(OpenAIVLM):
"temperature": self.temperature,
"thinking": {"type": "disabled" if not thinking else "enabled"},
}
+ if self.max_tokens is not None:
+ kwargs["max_tokens"] = self.max_tokens
last_error = None
for attempt in range(max_retries + 1):
@@ -235,6 +239,8 @@ class VolcEngineVLM(OpenAIVLM):
"temperature": self.temperature,
"thinking": {"type": "disabled" if not thinking else "enabled"},
}
+ if self.max_tokens is not None:
+ kwargs["max_tokens"] = self.max_tokens
response = client.chat.completions.create(**kwargs)
self._update_token_usage_from_response(response)
@@ -260,6 +266,8 @@ class VolcEngineVLM(OpenAIVLM):
"temperature": self.temperature,
"thinking": {"type": "disabled" if not thinking else "enabled"},
}
+ if self.max_tokens is not None:
+ kwargs["max_tokens"] = self.max_tokens
response = await client.chat.completions.create(**kwargs)
self._update_token_usage_from_response(response)
diff --git a/openviking/models/vlm/base.py b/openviking/models/vlm/base.py
index 5d8676719..d8641bf84 100644
--- a/openviking/models/vlm/base.py
+++ b/openviking/models/vlm/base.py
@@ -25,6 +25,7 @@ class VLMBase(ABC):
self.api_base = config.get("api_base")
self.temperature = config.get("temperature", 0.0)
self.max_retries = config.get("max_retries", 2)
+ self.max_tokens = config.get("max_tokens")
# Token usage tracking
self._token_tracker = TokenUsageTracker()
diff --git a/openviking_cli/utils/config/vlm_config.py b/openviking_cli/utils/config/vlm_config.py
index eea7682bf..6c42d6436 100644
--- a/openviking_cli/utils/config/vlm_config.py
+++ b/openviking_cli/utils/config/vlm_config.py
@@ -26,6 +26,10 @@ class VLMConfig(BaseModel):
default_provider: Optional[str] = Field(default=None, description="Default provider name")
+ max_tokens: Optional[int] = Field(
+ default=None, description="Maximum tokens for VLM completion output (None = provider default)"
+ )
+
thinking: bool = Field(default=False, description="Enable thinking mode for VolcEngine models")
max_concurrent: int = Field(
@@ -134,6 +138,7 @@ class VLMConfig(BaseModel):
"max_retries": self.max_retries,
"provider": name,
"thinking": self.thinking,
+ "max_tokens": self.max_tokens,
}
if config: