Skip to content

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

删除无用的bot逻辑 (#4769)

DuTao0e754112ada2
diff --git a/.gitignore b/.gitignore
index 7b7480136..599987ebf 100644
--- a/.gitignore
+++ b/.gitignore
@@ -67,6 +67,10 @@ test-reports/
report.html
temp/
+# codex
+diagrams/
+doc-fetch-resources/
+
# Virtual environments
.env
.venv
diff --git a/benchmark/tau2/vikingbot/setup_env.sh b/benchmark/tau2/vikingbot/setup_env.sh
index b3c758be5..423263f6e 100755
--- a/benchmark/tau2/vikingbot/setup_env.sh
+++ b/benchmark/tau2/vikingbot/setup_env.sh
@@ -5,7 +5,7 @@
# 1. creates a fresh .venv at the OpenViking repo root (if missing)
# 2. clones tau2-bench into ./tau2-bench (if missing; external dependency)
# 3. installs openviking + vikingbot (pip install -e .[bot] -> runs the Cargo build;
-# the [bot] extra provides prompt_toolkit/gradio/mcp/... needed by the runner and
+# the [bot] extra provides prompt_toolkit/mcp/... needed by the runner and
# `openviking-server --with-bot`)
# 4. ensures the ragfs_python native binding is built (via maturin) and bundled into
# openviking/lib/ (the editable install can skip it under pip build isolation)
@@ -121,7 +121,7 @@ _setup_install() {
echo "[setup_env] WARNING: 'cargo' not found on PATH; the openviking Rust build may fail." >&2
fi
# Install with the [bot] extra: the vikingbot runner imports vikingbot.cli and
- # `openviking-server --with-bot` needs the bot deps (prompt_toolkit, gradio, mcp, ...).
+ # `openviking-server --with-bot` needs the bot deps (prompt_toolkit, mcp, ...).
echo "[setup_env] Installing openviking + vikingbot with bot extras (pip install -e ${REPO_ROOT}[bot])"
"${PY}" -m pip install -e "${REPO_ROOT}[bot]" || { echo "[setup_env] openviking install failed"; return 1; }
diff --git a/bot/docs/en/concepts/01-architecture.md b/bot/docs/en/concepts/01-architecture.md
index 641dd7578..ac7992a2d 100644
--- a/bot/docs/en/concepts/01-architecture.md
+++ b/bot/docs/en/concepts/01-architecture.md
@@ -97,7 +97,9 @@ The Provider layer gives AgentLoop a unified `chat()` and `chat_stream()` interf
- Provider-specific system message and thinking parameters;
- `prompt_tokens`, `completion_tokens`, and `total_tokens`.
-LiteLLMProvider adapts general model services. OpenViking VLM uses VLMProviderAdapter to implement the same interface. Models are read from the root-level `vlm` configuration by default, while `bot.agents` can override Bot-specific parameters.
+VLMProviderAdapter connects all model services through OpenViking VLM, including its LiteLLM backend. Models are read from the root-level `vlm` configuration by default, while `bot.agents` can override Bot-specific parameters.
+
+The old `bot.providers` field has been removed. Loading an `ov.conf` that contains it emits a warning and ignores its model settings without overriding `vlm` or `bot.agents` or rewriting the file. Saving Bot configuration no longer writes this field. Configure model credentials in `vlm` or `bot.agents` instead. Root-level `vlm.providers` remains supported. The only preserved legacy use is Telegram voice transcription: `bot.providers.groq.api_key` is migrated on load into each Telegram channel's `groq_api_key`, without overriding an explicitly configured value (including an empty string).
## Local Session
diff --git a/bot/docs/en/concepts/03-channels-and-gateway.md b/bot/docs/en/concepts/03-channels-and-gateway.md
index c43a4178c..5ba95d9e4 100644
--- a/bot/docs/en/concepts/03-channels-and-gateway.md
+++ b/bot/docs/en/concepts/03-channels-and-gateway.md
@@ -19,6 +19,8 @@ Channels adapt different chat platforms into unified messages. The Gateway assem
Interactive CLI sessions use ChatChannel, while one-shot commands use SingleTurnChannel. Both use the same unified message model.
+Configure Telegram voice transcription with `groq_api_key` (or `groqApiKey`) on the corresponding `bot.channels[]` entry. `GROQ_API_KEY` remains an environment-variable fallback when no key is configured. This key is independent of the chat model's `vlm` / `bot.agents` configuration.
+
## Channel Responsibilities
BaseChannel and platform-specific implementations jointly handle:
@@ -50,6 +52,8 @@ FastAPI / Uvicorn
The default listen address is `127.0.0.1:18790`. If `gateway.host` is not localhost, `bot.gateway.token` is required or the Gateway refuses to start.
+`vikingbot status` shows the selected model configuration source (inherited root `vlm` or `bot.agents`), credentials in configured order, each credential's provider/model, and whether an API key or custom headers are configured. It does not print secrets or header values or send model requests; an unset API key does not rule out local models or external authentication. This is a configuration summary, not a Gateway health check or an indication of the active credential after runtime failover.
+
## Bot HTTP API
The Bot API is available under `/bot/v1`:
diff --git a/bot/docs/zh/concepts/01-architecture.md b/bot/docs/zh/concepts/01-architecture.md
index b820fc574..12f73aefe 100644
--- a/bot/docs/zh/concepts/01-architecture.md
+++ b/bot/docs/zh/concepts/01-architecture.md
@@ -96,7 +96,9 @@ Provider 层向 AgentLoop 提供统一的 `chat()` 和 `chat_stream()` 接口,
- Provider 特有的 system message 和 thinking 参数;
- `prompt_tokens`、`completion_tokens` 和 `total_tokens`。
-通用模型由 LiteLLMProvider 适配;OpenViking VLM 通过 VLMProviderAdapter 接入相同接口。模型默认读取根级 `vlm` 配置,`bot.agents` 可以覆盖 Bot 专用参数。
+所有模型统一通过 VLMProviderAdapter 接入 OpenViking VLM,包括其 LiteLLM 后端。模型默认读取根级 `vlm` 配置,`bot.agents` 可以覆盖 Bot 专用参数。
+
+旧 `bot.providers` 已移除:加载包含此字段的 `ov.conf` 时会提示并忽略其中的模型配置,不覆盖 `vlm` 或 `bot.agents`,也不改写原文件;再次保存 Bot 配置时不再写入该字段。请将模型凭证配置到 `vlm` 或 `bot.agents`。根级 `vlm.providers` 不受此清理影响。唯一保留的旧用途是 Telegram 语音转写:旧 `bot.providers.groq.api_key` 会在加载时迁入各 Telegram 渠道的 `groq_api_key`,但不会覆盖显式配置的新字段(包括空字符串)。
## 本地 Session
diff --git a/bot/docs/zh/concepts/03-channels-and-gateway.md b/bot/docs/zh/concepts/03-channels-and-gateway.md
index 441501f20..967dbf769 100644
--- a/bot/docs/zh/concepts/03-channels-and-gateway.md
+++ b/bot/docs/zh/concepts/03-channels-and-gateway.md
@@ -19,6 +19,8 @@ Channels 负责把不同聊天平台适配为统一消息,Gateway 则把 Chann
CLI 交互使用 ChatChannel,单条命令使用 SingleTurnChannel,它们也沿用统一消息模型。
+Telegram 语音转写密钥配置在对应的 `bot.channels[]` 条目的 `groq_api_key`(也支持 `groqApiKey`),未配置密钥时仍可使用 `GROQ_API_KEY` 环境变量。该密钥独立于聊天模型的 `vlm` / `bot.agents` 配置。
+
## Channel 的职责
BaseChannel 和具体平台实现共同负责:
@@ -50,6 +52,8 @@ FastAPI / Uvicorn
默认监听 `127.0.0.1:18790`。当 `gateway.host` 不是 localhost 时,必须设置 `bot.gateway.token`,否则 Gateway 拒绝启动。
+`vikingbot status` 展示当前选择的模型配置来源(继承根级 `vlm` 或使用 `bot.agents`)、凭证配置顺序、各凭证的 Provider/模型,以及 API key 和自定义请求头是否配置。它不输出密钥或请求头内容,也不发起模型请求;未配置 API key 不代表本地模型或外部鉴权不可用。这是配置摘要,不是 Gateway 健康检查,也不代表运行中故障切换后的活跃凭证。
+
## Bot HTTP API
Bot API 位于 `/bot/v1`:
diff --git a/bot/tests/test_minimax_provider.py b/bot/tests/test_minimax_provider.py
index c5b177392..43f650a6f 100644
--- a/bot/tests/test_minimax_provider.py
+++ b/bot/tests/test_minimax_provider.py
@@ -2,9 +2,15 @@
# SPDX-License-Identifier: AGPL-3.0
"""Tests for MiniMax provider support (MiniMax-M3, MiniMax-M2.7, MiniMax-M2.7-highspeed)."""
+from copy import deepcopy
+from types import SimpleNamespace
from urllib.parse import urlparse
+import pytest
from vikingbot.providers.registry import ProviderSpec, find_by_model, find_by_name
+from vikingbot.providers.vlm_adapter import VLMProviderAdapter
+
+from openviking.models.vlm.backends.litellm_vlm import LiteLLMVLMProvider
class TestMiniMaxRegistry:
@@ -64,122 +70,39 @@ class TestMiniMaxRegistry:
)
-class TestMiniMaxModelPrefixResolution:
- """Tests for LiteLLM model prefix resolution with MiniMax models."""
-
- def _resolve_model(self, model: str) -> str:
- """Reproduce _resolve_model logic from LiteLLMProvider."""
- from vikingbot.providers.registry import find_by_model
-
- spec = find_by_model(model)
- if spec and spec.litellm_prefix:
- if not any(model.startswith(s) for s in spec.skip_prefixes):
- model = f"{spec.litellm_prefix}/{model}"
- return model
-
- def test_m3_gets_minimax_prefix(self):
- """MiniMax-M3 should be prefixed as minimax/MiniMax-M3."""
- resolved = self._resolve_model("MiniMax-M3")
- assert resolved == "minimax/MiniMax-M3"
-
- def test_m2_7_gets_minimax_prefix(self):
- """MiniMax-M2.7 should be prefixed as minimax/MiniMax-M2.7."""
- resolved = self._resolve_model("MiniMax-M2.7")
- assert resolved == "minimax/MiniMax-M2.7"
-
- def test_m2_7_highspeed_gets_minimax_prefix(self):
- """MiniMax-M2.7-highspeed should be prefixed as minimax/MiniMax-M2.7-highspeed."""
- resolved = self._resolve_model("MiniMax-M2.7-highspeed")
- assert resolved == "minimax/MiniMax-M2.7-highspeed"
-
- def test_already_prefixed_model_not_double_prefixed(self):
- """Model already carrying minimax/ prefix must not be double-prefixed."""
- resolved = self._resolve_model("minimax/MiniMax-M2.7")
- assert resolved == "minimax/MiniMax-M2.7"
-
-
-class TestMiniMaxSystemMessageHandling:
- """Tests for MiniMax system message merging in LiteLLMProvider."""
-
- # ------------------------------------------------------------------ #
- # Helpers
- # ------------------------------------------------------------------ #
-
- def _handle_system_litellm(self, model: str, messages: list[dict]) -> list[dict]:
- """Call the LiteLLMProvider._handle_system_message without a real provider."""
- from vikingbot.providers.litellm_provider import LiteLLMProvider
-
- # Instantiate without a real API key — we only call the static-ish helper.
- provider = LiteLLMProvider.__new__(LiteLLMProvider)
- provider._gateway = None
- return provider._handle_system_message(model, messages)
-
- # ------------------------------------------------------------------ #
- # LiteLLMProvider tests (model name after prefix resolution)
- # ------------------------------------------------------------------ #
-
- def test_litellm_system_message_merged_for_m3(self):
- """System message is merged into the first user message for minimax/MiniMax-M3."""
- messages = [
- {"role": "system", "content": "You are a helpful assistant."},
- {"role": "user", "content": "Hello!"},
- ]
- result = self._handle_system_litellm("minimax/MiniMax-M3", messages)
- assert all(m["role"] != "system" for m in result), "System message not removed"
- user_content = next(m["content"] for m in result if m["role"] == "user")
- assert "You are a helpful assistant." in user_content
- assert "Hello!" in user_content
-
- def test_litellm_system_message_merged_for_m2_7(self):
- """System message is merged into the first user message for minimax/MiniMax-M2.7."""
- messages = [
- {"role": "system", "content": "You are a helpful assistant."},
- {"role": "user", "content": "Hello!"},
- ]
- result = self._handle_system_litellm("minimax/MiniMax-M2.7", messages)
- assert all(m["role"] != "system" for m in result), "System message not removed"
- user_content = next(m["content"] for m in result if m["role"] == "user")
- assert "You are a helpful assistant." in user_content
- assert "Hello!" in user_content
-
- def test_litellm_system_message_merged_for_m2_7_highspeed(self):
- """System message is merged for minimax/MiniMax-M2.7-highspeed."""
- messages = [
- {"role": "system", "content": "Be concise."},
- {"role": "user", "content": "What is 2+2?"},
- ]
- result = self._handle_system_litellm("minimax/MiniMax-M2.7-highspeed", messages)
- assert all(m["role"] != "system" for m in result)
- user_content = next(m["content"] for m in result if m["role"] == "user")
- assert "Be concise." in user_content
-
- def test_litellm_multiple_system_messages_combined(self):
- """Multiple system messages are combined before merging."""
- messages = [
- {"role": "system", "content": "Rule 1."},
- {"role": "system", "content": "Rule 2."},
- {"role": "user", "content": "Go!"},
- ]
- result = self._handle_system_litellm("minimax/MiniMax-M2.7", messages)
- assert all(m["role"] != "system" for m in result)
- user_content = next(m["content"] for m in result if m["role"] == "user")
- assert "Rule 1." in user_content
- assert "Rule 2." in user_content
-
- def test_litellm_no_system_message_passthrough(self):
- """Messages without a system role are returned unchanged."""
- messages = [
- {"role": "user", "content": "Hello!"},
- {"role": "assistant", "content": "Hi there!"},
- ]
- result = self._handle_system_litellm("minimax/MiniMax-M2.7", messages)
- assert result == messages
-
- def test_litellm_non_minimax_model_not_affected(self):
- """System messages for non-MiniMax models must not be touched."""
- messages = [
- {"role": "system", "content": "You are a helpful assistant."},
- {"role": "user", "content": "Hello!"},
- ]
- result = self._handle_system_litellm("anthropic/claude-opus-4-5", messages)
- assert result == messages
+ "model",
+ ["MiniMax-M3", "MiniMax-M2.7", "MiniMax-M2.7-highspeed", "minimax/MiniMax-M2.7"],
+)
+async def test_minimax_chat_uses_core_litellm_backend(monkeypatch, model):
+ """The active adapter forwards MiniMax messages and resolves the provider prefix."""
+ captured = {}
+
+ async def fake_acompletion(**kwargs):
+ captured.update(kwargs)
+ return SimpleNamespace(
+ choices=[
+ SimpleNamespace(
+ message=SimpleNamespace(content="Hello!", tool_calls=None),
+ finish_reason="stop",
+ )
+ ],
+ usage=None,
+ )
+
+ monkeypatch.setattr("openviking.models.vlm.backends.litellm_vlm.acompletion", fake_acompletion)
+ vlm = LiteLLMVLMProvider({"provider": "minimax", "model": model})
+ provider = VLMProviderAdapter(vlm, default_model=model)
+ messages = [
+ {"role": "system", "content": "You are a helpful assistant."},
+ {"role": "user", "content": "Hi!"},
+ ]
+ original = deepcopy(messages)
+
+ response = await provider.chat(messages=messages)
+
+ assert response.content == "Hello!"
+ assert captured["model"] == f"minimax/{model.removeprefix('minimax/')}"
+ assert captured["messages"] == original
+ assert messages == original
diff --git a/bot/tests/test_openapi_auth.py b/bot/tests/test_openapi_auth.py
index 3197f9c57..8d866c3d6 100644
--- a/bot/tests/test_openapi_auth.py
+++ b/bot/tests/test_openapi_auth.py
@@ -633,10 +633,6 @@ class TestOpenAPIAuth:
"agent_id": "web-playground",
"role": "user",
"api_key_type": "user",
- "namespace_policy": {
- "isolate_user_scope_by_agent": False,
- "isolate_agent_scope_by_user": False,
- },
"server_url": "http://ov.local",
"actor_peer_id": "peer-a",
}
diff --git a/bot/tests/test_openviking_api_key_type.py b/bot/tests/test_openviking_api_key_type.py
index d9fb0c7b8..c7d9e0ca8 100644
--- a/bot/tests/test_openviking_api_key_type.py
+++ b/bot/tests/test_openviking_api_key_type.py
@@ -1,6 +1,7 @@
import json
from pathlib import Path
from types import SimpleNamespace
+from unittest.mock import AsyncMock
import pytest
from vikingbot.agent import memory as memory_module
@@ -914,23 +915,21 @@ def test_memory_user_cli_option_warns_at_runtime(capsys):
@pytest.mark.asyncio
-async def test_user_key_mode_skips_admin_namespace_policy_lookup(monkeypatch):
- monkeypatch.setattr(ov_server_module, "load_config", lambda: _make_config("user"))
-
- client = VikingClient()
[email protected]("api_key_type", ["root", "user"])
+async def test_viking_client_initializes_without_admin_account_lookup(monkeypatch, api_key_type):
+ monkeypatch.setattr(ov_server_module, "load_config", lambda: _make_config(api_key_type))
- async def _must_not_call_admin_api():
- raise AssertionError("user key mode must not call admin namespace policy API")
+ lookup = AsyncMock(return_value=[])
+ monkeypatch.setattr(_DummyHTTPClient, "admin_list_accounts", lookup)
+ initialize = AsyncMock()
+ monkeypatch.setattr(_DummyHTTPClient, "initialize", initialize)
- monkeypatch.setattr(client.client, "admin_list_accounts", _must_not_call_admin_api)
+ client = await VikingClient.create(agent_id="workspace")
- await client._load_namespace_policy()
-
- assert client._namespace_policy_loaded is True
- assert client._namespace_policy == {
- "isolate_user_scope_by_agent": False,
- "isolate_agent_scope_by_user": False,
- }
+ initialize.assert_awaited_once()
+ lookup.assert_not_called()
+ expected = "viking://user/alice/memories/" if api_key_type == "root" else "viking://~/memories/"
+ assert client._memory_target_uri("alice") == expected
def test_viking_client_request_connection_uses_active_identity(monkeypatch):
@@ -958,7 +957,7 @@ def test_viking_client_request_connection_uses_active_identity(monkeypatch):
assert client.account_id == "acct"
assert client.admin_user_id == "anonymous"
assert client.agent_id == "web-playground"
- assert client._namespace_policy_loaded is True
+ assert "namespace_policy" not in client._request_connection
assert client.should_sender_fanout() is False
assert client._memory_target_uri(None) == "viking://~/memories/"
assert first.kwargs == {
@@ -1093,10 +1092,6 @@ async def test_request_connection_search_memory_uses_request_client_only(monkeyp
"agent_id": "web-playground",
"role": "user",
"api_key_type": "user",
- "namespace_policy": {
- "isolate_user_scope_by_agent": False,
- "isolate_agent_scope_by_user": False,
- },
},
)
diff --git a/bot/vikingbot/bus/queue.py b/bot/vikingbot/bus/queue.py
index 7d3f17829..a74c89500 100644
--- a/bot/vikingbot/bus/queue.py
+++ b/bot/vikingbot/bus/queue.py
@@ -1,9 +1,6 @@
"""Async message queue for decoupled channel-agent communication."""
import asyncio
-from typing import Awaitable, Callable
-
-from loguru import logger
from vikingbot.bus.events import InboundMessage, OutboundMessage
@@ -19,14 +16,9 @@ class MessageBus:
def __init__(self):
self.inbound: asyncio.Queue[InboundMessage] = asyncio.Queue()
self.outbound: asyncio.Queue[OutboundMessage] = asyncio.Queue()
- self._outbound_subscribers: dict[
- str, list[Callable[[OutboundMessage], Awaitable[None]]]
- ] = {}
- self._running = False
async def publish_inbound(self, msg: InboundMessage) -> None:
"""Publish a message from a channel to the agent."""
- # print(f'publish_inbound={msg}')
await self.inbound.put(msg)
async def consume_inbound(self) -> InboundMessage:
@@ -35,46 +27,12 @@ class MessageBus:
async def publish_outbound(self, msg: OutboundMessage) -> None:
"""Publish a response from the agent to channels."""
- # print(f'publish_outbound={msg}')
await self.outbound.put(msg)
async def consume_outbound(self) -> OutboundMessage:
"""Consume the next outbound message (blocks until available)."""
return await self.outbound.get()
- def subscribe_outbound(
- self, channel_key: str, callback: Callable[[OutboundMessage], Awaitable[None]]
- ) -> None:
- """Subscribe to outbound messages for a specific channel key."""
- if channel_key not in self._outbound_subscribers:
- self._outbound_subscribers[channel_key] = []
- self._outbound_subscribers[channel_key].append(callback)
-
- async def dispatch_outbound(self) -> None:
- """
- Dispatch outbound messages to subscribed channels.
- Run this as a background task.
- """
- self._running = True
- while self._running:
- try:
- msg = await asyncio.wait_for(self.outbound.get(), timeout=1.0)
- channel_key = msg.session_key.channel_key()
- subscribers = self._outbound_subscribers.get(channel_key, [])
- for callback in subscribers:
- try:
- await callback(msg)
- except Exception as e:
- logger.exception(f"Error dispatching to {channel_key}: {e}")
- except asyncio.TimeoutError:
- continue
- except asyncio.CancelledError:
- break
-
- def stop(self) -> None:
- """Stop the dispatcher loop."""
- self._running = False
-
@property
def inbound_size(self) -> int:
"""Number of pending inbound messages."""
diff --git a/bot/vikingbot/channels/botchannel.py b/bot/vikingbot/channels/botchannel.py
deleted file mode 100644
index 61f211402..000000000
--- a/bot/vikingbot/channels/botchannel.py
+++ /dev/null
@@ -1,9 +0,0 @@
-"""Bot Channel configuration.
-
-BotChannel functionality is now integrated into OpenAPIChannel.
-This file keeps the BotChannelConfig for backward compatibility.
-"""
-
-from vikingbot.config.schema import BotChannelConfig
-
-__all__ = ["BotChannelConfig"]
diff --git a/bot/vikingbot/channels/manager.py b/bot/vikingbot/channels/manager.py
index ac83bba2d..5bb1bdc37 100644
--- a/bot/vikingbot/channels/manager.py
+++ b/bot/vikingbot/channels/manager.py
@@ -161,9 +161,6 @@ class ChannelManager:
self.add_channel_from_config(
channel_config,
workspace_path=workspace_path,
- groq_api_key=config.providers.groq.api_key
- if hasattr(config.providers, "groq")
- else None,
)
async def _start_channel(self, name: str, channel: BaseChannel) -> None:
diff --git a/bot/vikingbot/channels/openapi.py b/bot/vikingbot/channels/openapi.py
index eeaffe2bb..91e507a54 100644
--- a/bot/vikingbot/channels/openapi.py
+++ b/bot/vikingbot/channels/openapi.py
@@ -46,10 +46,6 @@ from vikingbot.observability.outcome import evaluate_response_outcome, should_up
from vikingbot.session.manager import SessionManager
DEFAULT_OPENVIKING_AGENT_ID = "web-playground"
-DEFAULT_NAMESPACE_POLICY = {
- "isolate_user_scope_by_agent": False,
- "isolate_agent_scope_by_user": False,
-}
OPENVIKING_AUTH_TIMEOUT_SECONDS = 5.0
OPENVIKING_PROXY_TIMEOUT_SECONDS = 300.0
OPENVIKING_UPSTREAM_NOT_CONFIGURED_DETAIL = (
@@ -859,7 +855,6 @@ class OpenAPIChannel(BaseChannel):
"role": role,
"api_key_type": api_key_type,
"server_url": self._ov_server_url(),
- "namespace_policy": dict(DEFAULT_NAMESPACE_POLICY),
}
if api_key:
connection["api_key"] = api_key
@@ -1761,52 +1756,3 @@ class OpenAPIChannel(BaseChannel):
outcome_payload = evaluation.to_dict()
outcomes[response_id] = outcome_payload
return outcome_payload
-
-
-def get_openapi_router(bus: MessageBus, config: Config) -> APIRouter:
- """
- Create and return the OpenAPI router for mounting in FastAPI.
-
- This factory function creates an OpenAPIChannel and returns its router.
- The router should be mounted in the main FastAPI app.
- """
- # Find OpenAPI config from channels
- openapi_config = None
-
- for ch_config in config.channels:
- # Check for OpenAPI config
- if isinstance(ch_config, dict) and ch_config.get("type") == "openapi":
- openapi_config = OpenAPIChannelConfig(**ch_config)
- break
- elif hasattr(ch_config, "type") and getattr(ch_config, "type", None) == "openapi":
- openapi_config = ch_config
- break
-
- if openapi_config is None:
- # Create default config
- openapi_config = OpenAPIChannelConfig()
-
- # Create channel and get router - pass global config for BotChannel loading
- channel = OpenAPIChannel(
- config=openapi_config,
- bus=bus,
- workspace_path=config.workspace_path,
- global_config=config,
- )
-
- # Register channel's send method as subscriber for outbound messages
- # Subscribe to cli type
- bus.subscribe_outbound(
- f"cli__{openapi_config.channel_id()}",
- channel.send,
- )
-
- # Subscribe to all bot_api channels that were loaded
- for channel_id in channel._bot_configs.keys():
- bus.subscribe_outbound(
- f"bot_api__{channel_id}",
- channel.send,
- )
- logger.info(f"Subscribed to bot_api channel: {channel_id}")
-
- return channel.get_router()
diff --git a/bot/vikingbot/channels/openapi_models.py b/bot/vikingbot/channels/openapi_models.py
index 9b1e77d6e..072760edd 100644
--- a/bot/vikingbot/channels/openapi_models.py
+++ b/bot/vikingbot/channels/openapi_models.py
@@ -153,10 +153,6 @@ class OpenVikingConnection(BaseModel):
actor_peer_id: Optional[str] = Field(default=None, description="Effective actor peer ID")
role: Optional[str] = Field(default=None, description="Effective OpenViking role")
api_key_type: Optional[str] = Field(default=None, description="OpenViking API key type")
- namespace_policy: Optional[Dict[str, bool]] = Field(
- default=None,
- description="Effective account namespace policy",
- )
server_url: Optional[str] = Field(default=None, description="OpenViking server URL")
diff --git a/bot/vikingbot/channels/telegram.py b/bot/vikingbot/channels/telegram.py
index f106464bc..443a72964 100644
--- a/bot/vikingbot/channels/telegram.py
+++ b/bot/vikingbot/channels/telegram.py
@@ -4,16 +4,18 @@ from __future__ import annotations
import asyncio
import re
+from pathlib import Path
+
from loguru import logger
from telegram import BotCommand, Update
-from telegram.ext import Application, CommandHandler, MessageHandler, filters, ContextTypes
+from telegram.ext import Application, CommandHandler, ContextTypes, MessageHandler, filters
from telegram.request import HTTPXRequest
from vikingbot.bus.events import OutboundMessage
from vikingbot.bus.queue import MessageBus
from vikingbot.channels.base import BaseChannel
-from vikingbot.config.schema import TelegramChannelConfig
from vikingbot.channels.utils import extract_image_paths, read_image_file
+from vikingbot.config.schema import TelegramChannelConfig
def _markdown_to_telegram_html(text: str) -> str:
@@ -101,13 +103,13 @@ class TelegramChannel(BaseChannel):
self,
config: TelegramChannelConfig,
bus: MessageBus,
- groq_api_key: str = "",
+ groq_api_key: str | None = None,
workspace_path: Path | None = None,
**kwargs,
):
super().__init__(config, bus, workspace_path=workspace_path, **kwargs)
self.config: TelegramChannelConfig = config
- self.groq_api_key = groq_api_key
+ self.groq_api_key = config.groq_api_key if groq_api_key is None else groq_api_key
self._app: Application | None = None
self._chat_ids: dict[str, int] = {} # Map sender_id to chat_id for replies
self._typing_tasks: dict[str, asyncio.Task] = {} # chat_id -> typing loop task
@@ -319,7 +321,6 @@ class TelegramChannel(BaseChannel):
ext = self._get_extension(media_type, getattr(media_file, "mime_type", None))
# Save to workspace/media/
- from pathlib import Path
from vikingbot.utils.helpers import get_media_path
if self.workspace_path:
diff --git a/bot/vikingbot/cli/commands.py b/bot/vikingbot/cli/commands.py
index 6d38e4f02..8e66c8e0c 100644
--- a/bot/vikingbot/cli/commands.py
+++ b/bot/vikingbot/cli/commands.py
@@ -1251,6 +1251,8 @@ def cron_run(
def status():
"""Show vikingbot status."""
+ from openviking_cli.utils.config.vlm_config import _normalize_provider_name
+
config_path = get_config_path()
config = load_config()
workspace = config.workspace_path
@@ -1265,26 +1267,35 @@ def status():
)
if config_path.exists():
- from vikingbot.providers.registry import PROVIDERS
-
- console.print(f"Model: {config.agents.model}")
-
- # Check API keys from registry
- for spec in PROVIDERS:
- p = getattr(config.providers, spec.name, None)
- if p is None:
- continue
- if spec.is_local:
- # Local deployments show api_base instead of api_key
- if p.api_base:
- console.print(f"{spec.label}: [green]✓ {p.api_base}[/green]")
- else:
- console.print(f"{spec.label}: [dim]not set[/dim]")
- else:
- has_key = bool(p.api_key)
- console.print(
- f"{spec.label}: {'[green]✓[/green]' if has_key else '[dim]not set[/dim]'}"
- )
+ inherited = config.inherits_root_vlm()
+ model_config = config.get_root_vlm_config() if inherited else config.agents
+ console.print(f"Model config: {'vlm (inherited)' if inherited else 'bot.agents'}")
+ if model_config is None:
+ console.print("Model configuration unavailable")
+ return
+
+ parent_provider = _normalize_provider_name(model_config.provider)
+ console.print("Credentials (configured order; not a live health check):")
+ for index, credential in enumerate(model_config.credentials or [model_config], 1):
+ provider = credential.provider or parent_provider or "not set"
+ model = credential.model or model_config.model or "not set"
+ # Root credentials are already normalized by VLMConfig. Bot-owned
+ # credentials match the normalized parent provider for key inheritance;
+ # VLMConfig leaves explicitly set credential provider names unchanged.
+ has_key = bool(credential.api_key)
+ if not inherited and provider == parent_provider:
+ has_key = has_key or bool(model_config.api_key)
+ has_headers = bool(
+ credential.extra_headers
+ or model_config.extra_headers
+ or config.agents.extra_headers
+ )
+ console.print(f" {index}. Provider: {provider} | Model: {model}", markup=False)
+ console.print(
+ f" API key: {'configured' if has_key else 'not set in config'}; "
+ f"Extra headers: {'configured' if has_headers else 'not set in config'}",
+ markup=False,
+ )
@app.command("feedback-stats")
diff --git a/bot/vikingbot/config/loader.py b/bot/vikingbot/config/loader.py
index f61918357..f345e3db7 100644
--- a/bot/vikingbot/config/loader.py
+++ b/bot/vikingbot/config/loader.py
@@ -102,6 +102,23 @@ def load_config() -> Config:
# Extract bot section
bot_data = full_data.get("bot", {})
bot_data = convert_keys(bot_data)
+ if "providers" in bot_data:
+ legacy_providers = bot_data.pop("providers")
+ legacy_groq = (
+ legacy_providers.get("groq") if isinstance(legacy_providers, dict) else None
+ )
+ groq_key = legacy_groq.get("api_key") if isinstance(legacy_groq, dict) else None
+ channels = bot_data.get("channels")
+ if isinstance(groq_key, str) and groq_key and isinstance(channels, list):
+ for channel in channels:
+ if isinstance(channel, dict) and channel.get("type") == "telegram":
+ channel.setdefault("groq_api_key", groq_key)
+ logger.warning(
+ "bot.providers has been removed; its model settings are ignored. "
+ "Configure model credentials in vlm or bot.agents instead. "
+ "Legacy Groq transcription keys are migrated to Telegram channels "
+ "when groq_api_key is absent."
+ )
raw_agents = bot_data.get("agents", {})
bot_model_explicit = bool(
isinstance(raw_agents, dict) and str(raw_agents.get("model") or "").strip()
@@ -775,44 +792,6 @@ def validate_openviking_auth(config: Config) -> None:
return
-def reconcile_vlm_inheritance_after_edit(previous: Config, edited: Config) -> None:
- """Update root-VLM inheritance state after an editor rebuilds Config.
-
- Editors such as the Web Console serialize and reconstruct ``Config``. The
- hidden inheritance marker must survive an unchanged round-trip, but it must
- be cleared when the user explicitly edits the Bot-owned model connection.
-
- When Bot credentials are added to an inherited config, connection fields
- flattened from the root VLM must not become implicit Bot-level fallbacks.
- Preserve only fields whose values were explicitly changed by the editor.
- """
- if not previous.inherits_root_vlm():
- return
-
- connection_fields = ("model", "provider", "api_key", "api_base", "extra_headers")
- credentials_changed = previous.agents.credentials != edited.agents.credentials
- if credentials_changed:
- empty_values = {
- "model": "",
- "provider": "",
- "api_key": "",
- "api_base": "",
- "extra_headers": {},
- }
- for field in connection_fields:
- if getattr(previous.agents, field) == getattr(edited.agents, field):
- setattr(edited.agents, field, empty_values[field])
- edited.set_inherits_root_vlm(False)
- return
-
- ownership_fields = ("model", "provider", "api_key", "api_base")
- if any(
- getattr(previous.agents, field) != getattr(edited.agents, field)
- for field in ownership_fields
- ):
- edited.set_inherits_root_vlm(False)
-
-
def save_config(
config: Config, config_path: Path | None = None, include_defaults: bool = False
) -> None:
diff --git a/bot/vikingbot/config/schema.py b/bot/vikingbot/config/schema.py
index 743bb2ccd..5b2059192 100644
--- a/bot/vikingbot/config/schema.py
+++ b/bot/vikingbot/config/schema.py
@@ -108,6 +108,7 @@ class TelegramChannelConfig(BaseChannelConfig):
type: ChannelType = ChannelType.TELEGRAM
token: str = ""
+ groq_api_key: str = Field(default="", description="Groq API key for voice transcription")
allow_from: list[str] = Field(default_factory=list)
proxy: str | None = None
@@ -541,26 +542,6 @@ class ProviderConfig(BaseModel):
) # Custom headers (e.g. APP-Code for AiHubMix)
-class ProvidersConfig(BaseModel):
- """Configuration for LLM providers."""
-
- anthropic: ProviderConfig = Field(default_factory=ProviderConfig)
- openai: ProviderConfig = Field(default_factory=ProviderConfig)
- openrouter: ProviderConfig = Field(default_factory=ProviderConfig)
- deepseek: ProviderConfig = Field(default_factory=ProviderConfig)
- groq: ProviderConfig = Field(default_factory=ProviderConfig)
- zhipu: ProviderConfig = Field(default_factory=ProviderConfig)
- dashscope: ProviderConfig = Field(default_factory=ProviderConfig) # 阿里云通义千问
- vllm: ProviderConfig = Field(default_factory=ProviderConfig)
- gemini: ProviderConfig = Field(default_factory=ProviderConfig)
- moonshot: ProviderConfig = Field(default_factory=ProviderConfig)
- minimax: ProviderConfig = Field(default_factory=ProviderConfig)
- volcengine: ProviderConfig = Field(
- default_factory=ProviderConfig
- ) # VolcEngine (火山引擎) API gateway
- aihubmix: ProviderConfig = Field(default_factory=ProviderConfig) # AiHubMix API gateway
-
-
class HeartbeatConfig(BaseModel):
"""Heartbeat service configuration."""
@@ -873,9 +854,6 @@ class Config(BaseSettings):
inherits_root_vlm_state: SkipJsonSchema[bool] = Field(default=False, repr=False)
agents: AgentsConfig = Field(default_factory=AgentsConfig)
channels: list[Any] = Field(default_factory=list)
- providers: ProvidersConfig = Field(
- default_factory=ProvidersConfig, deprecated=True
- ) # Deprecated: Use ov.conf vlm config instead
gateway: GatewayConfig = Field(default_factory=GatewayConfig)
tools: ToolsConfig = Field(default_factory=ToolsConfig)
ov_server: OpenVikingConfig = Field(default_factory=OpenVikingConfig)
diff --git a/bot/vikingbot/console/README_GRADIO.md b/bot/vikingbot/console/README_GRADIO.md
deleted file mode 100644
index 60c2b340a..000000000
--- a/bot/vikingbot/console/README_GRADIO.md
+++ /dev/null
@@ -1,41 +0,0 @@
-
-# Vikingbot Console - Gradio 版本
-
-使用 Gradio 实现的纯 Python 控制台界面。
-
-## 运行
-
-```bash
-vikingbot gateway
-```
-
-这会自动在 http://localhost:18791 启动控制台 Web UI!
-
-## 功能
-
-### 1. Dashboard
-- 显示系统状态
-- 版本信息
-- 配置路径和工作区路径
-
-### 2. Config
-- **Skills & Hooks**: 独立标签页
-- **Agents / Providers / Channels / Gateway / Tools / Sandbox / Heartbeat**: 每个在自己的标签页中
- - Agents: 展开 AgentDefaults
- - Providers: 每个 provider 在自己的子标签页中
- - Sandbox: backends 在自己的子标签页中
- - Channels: JSON 编辑器(可配置多个 channel)
- - Enums: 使用下拉框(SandboxBackend, SandboxMode)
-
-### 3. Sessions
-- 刷新按钮:加载会话列表
-- 会话选择:选择会话查看内容
-- 会话内容显示:
- - 用户消息:绿色
- - 助手消息:红色
- - 其他消息:黑色
-
-### 4. Workspace
-- 使用 Gradio 的 FileExplorer 组件
-- 显示工作区文件树
-- 选择文件查看内容
diff --git a/bot/vikingbot/console/__init__.py b/bot/vikingbot/console/__init__.py
deleted file mode 100644
index d6b6ca1fb..000000000
--- a/bot/vikingbot/console/__init__.py
+++ /dev/null
@@ -1,3 +0,0 @@
-"""Vikingbot Console - Web管理界面"""
-
-__version__ = "1.0.0"
diff --git a/bot/vikingbot/console/web_console.py b/bot/vikingbot/console/web_console.py
deleted file mode 100644
index 2b7f78b0e..000000000
--- a/bot/vikingbot/console/web_console.py
+++ /dev/null
@@ -1,571 +0,0 @@
-import json
-import sys
-from pathlib import Path
-from typing import Any, Dict, List, Optional, Tuple
-
-import gradio as gr
-
-from vikingbot.config.loader import (
- get_config_path,
- load_config,
- reconcile_vlm_inheritance_after_edit,
- save_config,
-)
-from vikingbot.config.schema import Config
-from vikingbot.observability.feedback_stats import (
- FEEDBACK_STATS_SORT_FIELDS,
- build_feedback_stats_display,
-)
-
-
-def resolve_schema_ref(
- schema: Dict[str, Any], ref: str, root_schema: Dict[str, Any]
-) -> Dict[str, Any]:
- if ref.startswith("#/$defs/"):
- def_name = ref[len("#/$defs/") :]
- return root_schema["$defs"].get(def_name, {})
- return schema
-
-
-def get_effective_schema(field_info: Dict[str, Any], root_schema: Dict[str, Any]) -> Dict[str, Any]:
- if "$ref" in field_info:
- return get_effective_schema(
- resolve_schema_ref(field_info, field_info["$ref"], root_schema), root_schema
- )
- return field_info
-
-
-def create_dashboard_tab():
- with gr.Tab("Dashboard"):
- from vikingbot import __version__
-
- config = load_config()
- gr.Markdown("# ⚓ Vikingbot Console")
- gr.Markdown(f"""
- | Status | Value |
- |--------|-------|
- | 🟢 Status | Running |
- | 📦 Version | {__version__} |
- | 📁 Config Path | {str(get_config_path())} |
- | 🖥️ Workspace Path | {str(config.workspace_path)} |
- """)
-
-
-def create_feedback_tab():
- with gr.Tab("Feedback"):
- gr.Markdown("## Feedback Observability")
-
- with gr.Row():
- channel_input = gr.Textbox(label="Channel", placeholder="cli__default")
- session_input = gr.Textbox(label="Session", placeholder="cli__default__session-1")
-
- with gr.Row():
- updated_since_input = gr.Textbox(
- label="Updated Since", placeholder="2026-05-01T00:00:00"
- )
- updated_until_input = gr.Textbox(
- label="Updated Until", placeholder="2026-05-31T23:59:59"
- )
-
- with gr.Row():
- sort_by_input = gr.Dropdown(
- choices=list(FEEDBACK_STATS_SORT_FIELDS),
- value="responses_total",
- label="Sort Channels By",
- )
- top_n_input = gr.Number(value=5, precision=0, label="Top Channels")
- session_limit_input = gr.Number(value=10, precision=0, label="Recent Sessions")
-
- with gr.Row():
- refresh_btn = gr.Button("Refresh Feedback Stats", variant="primary")
- status_msg = gr.Markdown("")
-
- summary_md = gr.Markdown("Click refresh to load feedback stats.")
- channels_md = gr.Markdown("")
- sessions_md = gr.Markdown("")
-
- def refresh_feedback_stats(
- channel,
- session_key,
- updated_since,
- updated_until,
- sort_by,
- top_n,
- session_limit,
- ):
- try:
- config = load_config()
- stats_markdown = build_feedback_stats_display(
- config.bot_data_path,
- channel=channel or None,
- session_key=session_key or None,
- updated_since=updated_since or None,
- updated_until=updated_until or None,
- sort_by=sort_by,
- top_n=_normalize_optional_int(top_n),
- include_sessions=True,
- session_limit=_normalize_optional_int(session_limit),
- )
- return (
- stats_markdown["summary_markdown"],
- stats_markdown["channels_markdown"],
- stats_markdown["sessions_markdown"],
- "✓ Feedback stats loaded.",
- )
- except Exception as exc:
- return (
- "Failed to load feedback stats.",
- "",
- "",
- f"✗ Error: {exc}",
- )
-
- refresh_btn.click(
- fn=refresh_feedback_stats,
- inputs=[
- channel_input,
- session_input,
- updated_since_input,
- updated_until_input,
- sort_by_input,
- top_n_input,
- session_limit_input,
- ],
- outputs=[summary_md, channels_md, sessions_md, status_msg],
- )
-
-
-def _normalize_optional_int(value: Any) -> int | None:
- if value in (None, ""):
- return None
- normalized = int(value)
- return normalized if normalized > 0 else None
-
-
-def create_field_group(
- field_name: str,
- field_info: Dict[str, Any],
- current_value: Any,
- parent_path: str = "",
- root_schema: Optional[Dict[str, Any]] = None,
-) -> Tuple[List, Dict[str, Any]]:
- if root_schema is None:
- root_schema = Config.model_json_schema()
-
- field_path = f"{parent_path}.{field_name}" if parent_path else field_name
-
- tab_paths = {"providers", "sandbox.backends"}
-
- effective_field_info = get_effective_schema(field_info, root_schema)
- description = effective_field_info.get("description", "")
- title = effective_field_info.get("title", field_name.replace("_", " ").title())
- components = []
- field_metadata = {}
-
- field_type = effective_field_info.get("type", "string")
- enum_values = effective_field_info.get("enum")
-
- if enum_values:
- dropdown = gr.Dropdown(
- choices=enum_values,
- value=current_value,
- label=title,
- elem_id=f"field_{field_path.replace('.', '_')}",
- )
- components.append(dropdown)
- field_metadata[field_path] = {"type": "enum"}
- elif field_type == "object" and "properties" in effective_field_info:
- properties = list(effective_field_info["properties"].items())
- if field_path in tab_paths and len(properties) > 1:
- with gr.Tab(title):
- if description:
- gr.Markdown(f"*{description}*")
- with gr.Tabs():
- for nested_field_name, nested_field_info in properties:
- with gr.Tab(
- nested_field_info.get(
- "title", nested_field_name.replace("_", " ").title()
- )
- ):
- nested_value = (
- current_value.get(nested_field_name, None)
- if current_value
- else None
- )
- nested_components, nested_metadata = create_field_group(
- nested_field_name,
- nested_field_info,
- nested_value,
- field_path,
- root_schema,
- )
- components.extend(nested_components)
- field_metadata.update(nested_metadata)
- else:
- with gr.Group():
- gr.Markdown(f"### {title}")
- if description:
- gr.Markdown(f"*{description}*")
- for nested_field_name, nested_field_info in properties:
- nested_value = (
- current_value.get(nested_field_name, None) if current_value else None
- )
- nested_components, nested_metadata = create_field_group(
- nested_field_name, nested_field_info, nested_value, field_path, root_schema
- )
- components.extend(nested_components)
- field_metadata.update(nested_metadata)
- elif field_type == "array":
- items_info = effective_field_info.get("items", {})
- effective_items_info = get_effective_schema(items_info, root_schema)
- items_type = effective_items_info.get("type", "string")
- use_textbox = False
- if items_type == "string" and not (
- "properties" in effective_items_info or items_type == "object"
- ):
- current_list = current_value or []
- if all(isinstance(item, str) for item in current_list):
- use_textbox = True
-
- if use_textbox:
- current_list = current_value or []
- value = "\n".join(current_list) if current_list else ""
- textbox = gr.Textbox(
- value=value,
- label=f"{title} (one per line)",
- lines=3,
- elem_id=f"field_{field_path.replace('.', '_')}",
- )
- components.append(textbox)
- field_metadata[field_path] = {"type": "array", "items_type": "string"}
- else:
- value = json.dumps(current_value, indent=2) if current_value else ""
- code = gr.Code(
- value=value,
- label=title,
- language="json",
- elem_id=f"field_{field_path.replace('.', '_')}",
- )
- components.append(code)
- field_metadata[field_path] = {"type": "array", "items_type": "json"}
- elif field_type == "integer":
- number = gr.Number(
- value=current_value, label=title, elem_id=f"field_{field_path.replace('.', '_')}"
- )
- components.append(number)
- field_metadata[field_path] = {"type": "integer"}
- elif field_type == "number":
- number = gr.Number(
- value=current_value, label=title, elem_id=f"field_{field_path.replace('.', '_')}"
- )
- components.append(number)
- field_metadata[field_path] = {"type": "number"}
- elif field_type == "boolean":
- checkbox = gr.Checkbox(
- value=current_value or False,
- label=title,
- elem_id=f"field_{field_path.replace('.', '_')}",
- )
- components.append(checkbox)
- field_metadata[field_path] = {"type": "boolean"}
- else:
- textbox = gr.Textbox(
- value=current_value or "", label=title, elem_id=f"field_{field_path.replace('.', '_')}"
- )
- components.append(textbox)
- field_metadata[field_path] = {"type": "string"}
-
- return components, field_metadata
-
-
-def collect_values_from_components(
- components, schema, parent_path: str = "", root_schema: Optional[Dict[str, Any]] = None
-) -> Tuple[Dict[str, Any], int]:
- if root_schema is None:
- root_schema = Config.model_json_schema()
-
- result = {}
- comp_idx = 0
-
- for field_name, field_info in schema.get("properties", {}).items():
- field_path = f"{parent_path}.{field_name}" if parent_path else field_name
- effective_field_info = get_effective_schema(field_info, root_schema)
- field_type = effective_field_info.get("type", "string")
-
- if field_type == "object" and "properties" in effective_field_info:
- nested_result, num_consumed = collect_values_from_components(
- components[comp_idx:], effective_field_info, field_path, root_schema
- )
- result[field_name] = nested_result
- comp_idx += num_consumed
- else:
- component = components[comp_idx]
- comp_idx += 1
-
- if hasattr(component, "value"):
- value = component.value
-
- if field_type == "array":
- items_info = effective_field_info.get("items", {})
- effective_items_info = get_effective_schema(items_info, root_schema)
- items_type = effective_items_info.get("type", "string")
- if items_type == "string" and isinstance(value, str):
- value = [line.strip() for line in value.split("\n") if line.strip()]
- elif isinstance(value, str):
- try:
- value = json.loads(value)
- except Exception:
- value = []
-
- result[field_name] = value
-
- return result, comp_idx
-
-
-def create_config_tabs():
- config = load_config()
- config_dict = config.model_dump()
- schema = Config.model_json_schema()
-
- all_components = []
- component_metadata = {}
-
- top_level_fields = list(schema["properties"].keys())
-
- with gr.Tabs():
- for field_name in top_level_fields:
- if field_name in schema["properties"]:
- with gr.Tab(
- schema["properties"][field_name].get(
- "title", field_name.replace("_", " ").title()
- )
- ):
- gr.Markdown(
- f"## {schema['properties'][field_name].get('title', field_name.replace('_', ' ').title())}"
- )
- field_info = schema["properties"][field_name]
- current_value = config_dict.get(field_name, None)
- components, metadata = create_field_group(
- field_name, field_info, current_value, root_schema=schema
- )
- all_components.extend(components)
- component_metadata.update(metadata)
-
- save_btn = gr.Button("Save Config", variant="primary")
- status_msg = gr.Markdown("")
-
- def save_config_fn(*args):
- try:
- previous_config = load_config()
- config_dict = previous_config.model_dump()
-
- remaining_args = list(args)
- comp_idx = 0
-
- for field_name in top_level_fields:
- if field_name in schema["properties"]:
- field_info = schema["properties"][field_name]
- field_result, num_consumed = collect_values_from_components(
- remaining_args[comp_idx:], field_info, root_schema=schema
- )
- config_dict[field_name] = field_result
- comp_idx += num_consumed
-
- config = Config(**config_dict)
- reconcile_vlm_inheritance_after_edit(previous_config, config)
- save_config(config)
- return "✓ Config saved successfully! Please restart the gateway service for changes to take effect."
- except Exception as e:
- return f"✗ Error: {str(e)}"
-
- save_btn.click(fn=save_config_fn, inputs=all_components, outputs=status_msg)
-
-
-def create_sessions_tab():
- with gr.Tab("Sessions"):
- gr.Markdown("## Sessions")
-
- with gr.Row():
- with gr.Column(scale=1):
- session_list = gr.Dropdown(
- choices=[],
- label="Select Session",
- info="Click Refresh to load sessions",
- allow_custom_value=True,
- )
- refresh_btn = gr.Button("Refresh Sessions")
-
- with gr.Column(scale=2):
- session_content = gr.HTML(value="", label="Session Content")
- status_msg = gr.Markdown("")
-
- def refresh_sessions():
- config = load_config()
- sessions_dir = config.bot_data_path / "sessions"
- if not sessions_dir.exists():
- return gr.Dropdown(choices=[], value=None), ""
- session_files = list(sessions_dir.glob("*.jsonl")) + list(sessions_dir.glob("*.json"))
- session_names = [f.stem for f in session_files]
- return gr.Dropdown(choices=session_names, value=None), ""
-
- def load_session(session_name):
- if not session_name:
- return "", "Please select a session"
- config = load_config()
- sessions_dir = config.bot_data_path / "sessions"
- session_file_jsonl = sessions_dir / f"{session_name}.jsonl"
- session_file_json = sessions_dir / f"{session_name}.json"
-
- lines = []
- if session_file_jsonl.exists():
- with open(session_file_jsonl, "r") as f:
- for line in f:
- line = line.strip()
- if not line:
- continue
- try:
- data = json.loads(line)
- role = data.get("role", "")
- content = data.get("content", "")
- if role == "user":
- lines.append(
- f'<div style="color: green;"><b>User:</b> {content}</div>'
- )
- elif role == "assistant":
- lines.append(
- f'<div style="color: red;"><b>Assistant:</b> {content}</div>'
- )
- else:
- lines.append(
- f'<div style="color: black;"><b>{role}:</b> {content}</div>'
- )
- except Exception:
- lines.append(f'<div style="color: black;">{line}</div>')
- elif session_file_json.exists():
- with open(session_file_json, "r") as f:
- return f.read(), ""
- else:
- return "Session not found", ""
- return "<br>".join(lines), ""
-
- refresh_btn.click(fn=refresh_sessions, outputs=[session_list, status_msg])
-
- session_list.change(
- fn=load_session, inputs=session_list, outputs=[session_content, status_msg]
- )
-
-
-def create_workspace_tab():
- with gr.Tab("Workspace"):
- gr.Markdown("## Workspace")
- config = load_config()
- workspace_path = config.workspace_path
- # Create workspace directory if it doesn't exist
- workspace_path.mkdir(parents=True, exist_ok=True)
- workspace_root = workspace_path.resolve()
- workspace_path_str = str(workspace_path)
-
- with gr.Row():
- with gr.Column(scale=1):
- file_explorer = gr.FileExplorer(
- root_dir=workspace_path_str,
- label="Workspace File Explorer",
- file_count="single",
- )
-
- with gr.Column(scale=2):
- file_content = gr.Code(
- value="", label="File Content", language="python", interactive=False
- )
- status_msg = gr.Markdown("")
-
- def load_file_content(selected_file):
- if not selected_file:
- return "", "Please select a file to view"
-
- try:
- candidate = Path(selected_file).resolve()
- except OSError:
- return "", "File not found"
-
- if not candidate.is_relative_to(workspace_root):
- return "", "Access denied"
-
- if candidate.is_file():
- try:
- with open(candidate, "r") as f:
- return f.read(), f"Loaded {candidate.name}"
- except Exception:
- return "Cannot read file (binary or encoding error)", ""
- elif candidate.is_dir():
- return "", f"{candidate.name} is a directory"
- return "", "File not found"
-
- file_explorer.change(
- fn=load_file_content, inputs=file_explorer, outputs=[file_content, status_msg]
- )
-
-
-with gr.Blocks(title="Vikingbot Console") as demo:
- with gr.Tabs():
- create_dashboard_tab()
- create_feedback_tab()
- with gr.Tab("Config"):
- create_config_tabs()
- create_sessions_tab()
- create_workspace_tab()
-
-
-def create_console_app(bus=None, config=None):
- """Create and return the FastAPI app with Gradio mounted."""
- from fastapi import FastAPI
-
- # Create FastAPI app for health endpoint
- app = FastAPI()
-
- # Add /health endpoint
- @app.get("/health")
- async def health_endpoint():
- from vikingbot import __version__
-
- return {"status": "healthy", "version": __version__}
-
- # Mount OpenAPI router if bus and config are provided
- if bus is not None and config is not None:
- try:
- from vikingbot.channels.openapi import get_openapi_router
-
- openapi_router = get_openapi_router(bus, config)
- app.include_router(
- openapi_router,
- prefix="/api/v1/openapi",
- tags=["openapi"],
- )
- except Exception as e:
- import logging
-
- logging.getLogger(__name__).warning(f"Failed to mount OpenAPI router: {e}")
-
- # Mount Gradio app
- demo.queue()
- app = gr.mount_gradio_app(app, demo, path="/")
-
- return app
-
-
-def run_console_server(port: int = 18791):
- """Run the console server in the current thread."""
- import uvicorn
-
- app = create_console_app()
- uvicorn.run(app, host="0.0.0.0", port=port, log_level="warning")
-
-
-if __name__ == "__main__":
- port = 18791
- if len(sys.argv) > 1:
- try:
- port = int(sys.argv[1])
- except ValueError:
- pass
- run_console_server(port)
diff --git a/bot/vikingbot/openviking_mount/ov_server.py b/bot/vikingbot/openviking_mount/ov_server.py
index 028053e30..dbe733c3a 100644
--- a/bot/vikingbot/openviking_mount/ov_server.py
+++ b/bot/vikingbot/openviking_mount/ov_server.py
@@ -71,11 +71,6 @@ class VikingClient:
self.admin_user_client = None
self._user_clients = {}
- self._namespace_policy = {
- "isolate_user_scope_by_agent": False,
- "isolate_agent_scope_by_user": False,
- }
- self._namespace_policy_loaded = False
connection_actor_peer_id = (
self._request_connection.get("actor_peer_id") if self._request_connection else None
)
@@ -160,16 +155,6 @@ class VikingClient:
value = connection.get(key)
if isinstance(value, str) and value.strip():
normalized[key] = value.strip()
- policy = connection.get("namespace_policy")
- if isinstance(policy, Mapping):
- normalized["namespace_policy"] = {
- "isolate_user_scope_by_agent": bool(
- policy.get("isolate_user_scope_by_agent", False)
- ),
- "isolate_agent_scope_by_user": bool(
- policy.get("isolate_agent_scope_by_user", False)
- ),
- }
if not normalized.get("api_key"):
if (
normalized.get("api_key_type") == "root"
@@ -192,11 +177,6 @@ class VikingClient:
self.account_id = connection.get("account_id")
self.admin_user_id = connection.get("user_id")
- policy = connection.get("namespace_policy")
- if isinstance(policy, dict):
- self._namespace_policy = policy
- self._namespace_policy_loaded = True
-
remote_client_kwargs = {
"url": self.openviking_config.server_url,
"profile_enabled": False,
@@ -214,7 +194,6 @@ class VikingClient:
async def _initialize(self):
"""Initialize the client (must be called after construction)"""
await self.client.initialize()
- await self._load_namespace_policy()
@classmethod
async def create(
@@ -350,47 +329,10 @@ class VikingClient:
if self.actor_peer_id:
client_kwargs["actor_peer_id"] = self.actor_peer_id
- async def _load_namespace_policy(self) -> None:
- if self._namespace_policy_loaded:
- return
-
- policy = {
- "isolate_user_scope_by_agent": False,
- "isolate_agent_scope_by_user": False,
- }
- if self._has_request_connection() or self._is_dev_mode() or self._is_user_key_mode():
- self._namespace_policy = policy
- self._namespace_policy_loaded = True
- return
-
- if self._is_root_key_mode() and self.account_id:
- try:
- accounts = await self.client.admin_list_accounts()
- for account in accounts or []:
- if account.get("account_id") == self.account_id:
- policy = {
- "isolate_user_scope_by_agent": bool(
- account.get("isolate_user_scope_by_agent", False)
- ),
- "isolate_agent_scope_by_user": bool(
- account.get("isolate_agent_scope_by_user", False)
- ),
- }
- break
- except Exception as e:
- logger.warning(
- f"Failed to load account namespace policy for {self.account_id}: {e}"
- )
-
- self._namespace_policy = policy
- self._namespace_policy_loaded = True
-
def _user_space_fragment(self, user_id: Optional[str]) -> str:
effective_user_id = self._effective_user_id(user_id)
if not effective_user_id:
return ""
- if self._namespace_policy["isolate_user_scope_by_agent"] and self.agent_id:
- return f"{effective_user_id}/agent/{self.agent_id}"
return effective_user_id
def _memory_target_uri(self, user_id: Optional[str]) -> str:
diff --git a/bot/vikingbot/providers/litellm_provider.py b/bot/vikingbot/providers/litellm_provider.py
deleted file mode 100644
index 70f07f411..000000000
--- a/bot/vikingbot/providers/litellm_provider.py
+++ /dev/null
@@ -1,572 +0,0 @@
-"""LiteLLM provider implementation for multi-provider support."""
-
-import os
-from typing import Any, AsyncIterator
-
-import litellm
-from litellm import acompletion
-from loguru import logger
-
-from openviking.utils.multimodal import redact_image_data_urls
-from vikingbot.integrations.langfuse import LangfuseClient
-from vikingbot.providers.base import (
- LLMProvider,
- LLMResponse,
- LLMStreamEvent,
- ToolCallRequest,
- build_stream_response,
- merge_stream_tool_call_delta,
- parse_tool_arguments,
- stream_delta_value,
-)
-from vikingbot.providers.registry import find_by_model, find_gateway
-from vikingbot.utils.helpers import cal_str_tokens
-from vikingbot.utils.tracing import get_current_response_id
-
-_OPENAI_REASONING_MODEL_PREFIXES = ("gpt-5", "openai/gpt-5", "o1", "o3", "o4")
-
-
-def _is_openai_reasoning_model(model: str) -> bool:
- return model.lower().startswith(_OPENAI_REASONING_MODEL_PREFIXES)
-
-
-class LiteLLMProvider(LLMProvider):
- """
- LLM provider using LiteLLM for multi-provider support.
-
- Supports OpenRouter, Anthropic, OpenAI, Gemini, MiniMax, and many other providers through
- a unified interface. Provider-specific logic is driven by the registry
- (see providers/registry.py) — no if-elif chains needed here.
- """
-
- def __init__(
- self,
- api_key: str | None = None,
- api_base: str | None = None,
- default_model: str = "anthropic/claude-opus-4-5",
- extra_headers: dict[str, str] | None = None,
- provider_name: str | None = None,
- timeout: float | None = None,
- thinking: bool = True,
- langfuse_client: LangfuseClient | None = None,
- ):
- super().__init__(api_key, api_base)
- self.default_model = default_model
- self.extra_headers = extra_headers or {}
- self.timeout = timeout
- self.thinking = thinking
- self.langfuse = langfuse_client or LangfuseClient.get_instance()
-
- # Detect gateway / local deployment.
- # provider_name (from config key) is the primary signal;
- # api_key / api_base are fallback for auto-detection.
- self._gateway = find_gateway(provider_name, api_key, api_base)
-
- # Configure environment variables
- if api_key:
- self._setup_env(api_key, api_base, default_model)
-
- if api_base:
- litellm.api_base = api_base
-
- # Disable LiteLLM logging noise
- litellm.suppress_debug_info = True
- # Drop unsupported parameters for providers (e.g., gpt-5 rejects some params)
- litellm.drop_params = True
-
- def _setup_env(self, api_key: str, api_base: str | None, model: str) -> None:
- """Set environment variables based on detected provider."""
- spec = self._gateway or find_by_model(model)
- if not spec:
- return
-
- # Gateway/local overrides existing env; standard provider doesn't
- if self._gateway:
- os.environ[spec.env_key] = api_key
- else:
- os.environ.setdefault(spec.env_key, api_key)
-
- # Resolve env_extras placeholders:
- # {api_key} → user's API key
- # {api_base} → user's api_base, falling back to spec.default_api_base
- effective_base = api_base or spec.default_api_base
- for env_name, env_val in spec.env_extras:
- resolved = env_val.replace("{api_key}", api_key)
- resolved = resolved.replace("{api_base}", effective_base)
- os.environ.setdefault(env_name, resolved)
-
- def _resolve_model(self, model: str) -> str:
- """Resolve model name by applying provider/gateway prefixes."""
- if self._gateway:
- # Gateway mode: apply gateway prefix, skip provider-specific prefixes
- prefix = self._gateway.litellm_prefix
- if self._gateway.strip_model_prefix:
- model = model.split("/")[-1]
- if prefix and not model.startswith(f"{prefix}/"):
- model = f"{prefix}/{model}"
- return model
-
- # Standard mode: auto-prefix for known providers
- spec = find_by_model(model)
- if spec and spec.litellm_prefix:
- if not any(model.startswith(s) for s in spec.skip_prefixes):
- model = f"{spec.litellm_prefix}/{model}"
-
- return model
-
- def _apply_model_overrides(self, model: str, kwargs: dict[str, Any]) -> None:
- """Apply model-specific parameter overrides from the registry."""
- model_lower = model.lower()
- spec = find_by_model(model)
- if spec:
- for pattern, overrides in spec.model_overrides:
- if pattern in model_lower:
- kwargs.update(overrides)
- return
-
- def _apply_thinking_overrides(self, model: str, kwargs: dict[str, Any]) -> None:
- """Attach explicit thinking params only for providers that support them."""
- if not self.thinking:
- return
-
- spec = self._gateway or find_by_model(model)
- thinking_param = spec.thinking_param if spec else ""
- model_lower = model.lower()
-
- if thinking_param == "volcengine_thinking" or model_lower.startswith("volcengine/"):
- kwargs["thinking"] = {"type": "enabled"}
- return
-
- if thinking_param == "dashscope_enable_thinking" or model_lower.startswith("dashscope/"):
- extra_body = dict(kwargs.get("extra_body") or {})
- extra_body["enable_thinking"] = True
- kwargs["extra_body"] = extra_body
- return
-
- if (
- (thinking_param == "openai_reasoning_effort" or not spec)
- and _is_openai_reasoning_model(model)
- and "reasoning_effort" not in kwargs
- ):
- kwargs["reasoning_effort"] = "low"
-
- def _handle_system_message(
- self, model: str, messages: list[dict[str, Any]]
- ) -> list[dict[str, Any]]:
- """
- Handle system message for providers that don't support it (e.g. MiniMax).
- Merges system message into the first user message or converts to user role.
- """
- # Check for MiniMax
- if model.startswith("minimax/") or "/minimax/" in model:
- # Create a copy to avoid modifying the original list
- new_messages = []
-
- # Helper to merge content
- def merge_content(base_content, new_content):
- if isinstance(base_content, str) and isinstance(new_content, str):
- return f"{new_content}\n\n{base_content}"
- if isinstance(base_content, list):
- base_content = list(base_content)
- base_content.insert(0, {"type": "text", "text": f"{new_content}\n\n"})
- return base_content
- return f"{new_content}\n\n{str(base_content)}"
-
- # First pass: identify system messages
- system_contents = []
- cleaned_messages = []
-
- for msg in messages:
- if msg.get("role") == "system":
- system_contents.append(msg.get("content", ""))
- else:
- cleaned_messages.append(msg)
-
- # If no system messages, return as is
- if not system_contents:
- return messages
-
- # Combine all system prompts
- full_system_prompt = "\n\n".join([str(c) for c in system_contents])
-
- # Merge into the first user message if available
- merged = False
- for msg in cleaned_messages:
- if not merged and msg.get("role") == "user":
- msg = msg.copy()
- msg["content"] = merge_content(msg.get("content", ""), full_system_prompt)
- new_messages.append(msg)
- merged = True
- else:
- new_messages.append(msg)
-
- # If no user message found, create one at the beginning
- if not merged:
- new_messages.insert(0, {"role": "user", "content": full_system_prompt})
-
- return new_messages
-
- return messages
-
- async def chat(
- self,
- messages: list[dict[str, Any]],
- tools: list[dict[str, Any]] | None = None,
- model: str | None = None,
- max_tokens: int | None = None,
- temperature: float = 0.7,
- session_id: str | None = None,
- ) -> LLMResponse:
- """
- Send a chat completion request via LiteLLM.
-
- Args:
- messages: List of message dicts with 'role' and 'content'.
- tools: Optional list of tool definitions in OpenAI format.
- model: Model identifier (e.g., 'anthropic/claude-sonnet-4-5').
- max_tokens: Maximum tokens in response. None uses the model provider default.
- temperature: Sampling temperature.
- session_id: Optional session ID for tracing.
-
- Returns:
- LLMResponse with content and/or tool calls.
- """
- model = self._resolve_model(model or self.default_model)
-
- # Handle system message for MiniMax and others that don't support it
- messages = self._handle_system_message(model, messages)
-
- kwargs: dict[str, Any] = {
- "model": model,
- "messages": messages,
- "temperature": temperature,
- }
- if max_tokens is not None:
- kwargs["max_tokens"] = max_tokens
-
- # Apply model-specific overrides (e.g. kimi-k2.5 temperature)
- self._apply_model_overrides(model, kwargs)
- self._apply_thinking_overrides(model, kwargs)
-
- # Pass api_key directly — more reliable than env vars alone
- if self.api_key:
- kwargs["api_key"] = self.api_key
-
- # Pass api_base for custom endpoints
- if self.api_base:
- kwargs["api_base"] = self.api_base
-
- if self.timeout is not None:
- kwargs["timeout"] = self.timeout
-
- # Pass extra headers (e.g. APP-Code for AiHubMix)
- if self.extra_headers:
- kwargs["extra_headers"] = self.extra_headers
-
- if tools:
- kwargs["tools"] = tools
- kwargs["tool_choice"] = "auto"
-
- # Langfuse integration
- # Note: session_id is set via propagate_attributes in loop.py, not here
- langfuse_observation = None
- try:
- if self.langfuse.enabled and self.langfuse._client:
- metadata = {"has_tools": tools is not None}
- response_id = get_current_response_id()
- if response_id:
- metadata["response_id"] = response_id
- client = self.langfuse._client
- # Use start_observation with generation type
- if hasattr(client, "start_observation"):
- langfuse_observation = client.start_observation(
- name="llm-chat",
- as_type="generation",
- model=model,
- input=redact_image_data_urls(messages),
- metadata=metadata,
- )
- if response_id:
- self.langfuse.register_generation(
- response_id, langfuse_observation, metadata=metadata
- )
-
- response = await acompletion(**kwargs)
- llm_response = self._parse_response(response)
-
- # Update and end Langfuse observation
- if langfuse_observation:
- output_text = llm_response.content or ""
- if llm_response.tool_calls:
- output_text = (
- output_text
- or f"[Tool calls: {[tc.name for tc in llm_response.tool_calls]}]"
- )
-
- # Update observation with output and usage
- update_kwargs: dict[str, Any] = {
- "output": output_text,
- "metadata": {
- "finish_reason": llm_response.finish_reason,
- **(
- {"response_id": get_current_response_id()}
- if get_current_response_id()
- else {}
- ),
- },
- }
-
- if llm_response.usage:
- # Add usage data using usage_details format
- usage_details: dict[str, Any] = {
- "input": llm_response.usage.get("prompt_tokens", 0),
- "output": llm_response.usage.get("completion_tokens", 0),
- }
-
- # Add cache read tokens if available
- cache_read_tokens = llm_response.usage.get(
- "cache_read_input_tokens"
- ) or llm_response.usage.get("prompt_tokens_details", {}).get("cached_tokens")
- if cache_read_tokens:
- usage_details["cache_read_input_tokens"] = cache_read_tokens
-
- update_kwargs["usage_details"] = usage_details
-
- response_id = get_current_response_id()
- if response_id:
- update_kwargs["metadata"] = self.langfuse.update_generation_metadata(
- response_id,
- update_kwargs.get("metadata", {}),
- )
-
- # Update the observation
- if hasattr(langfuse_observation, "update"):
- try:
- langfuse_observation.update(**update_kwargs)
- except Exception as e:
- logger.debug(f"[LANGFUSE] Failed to update observation: {e}")
-
- # End the observation
- if hasattr(langfuse_observation, "end"):
- try:
- langfuse_observation.end()
- except Exception as e:
- logger.debug(f"[LANGFUSE] Failed to end observation: {e}")
-
- try:
- self.langfuse.flush()
- except Exception as e:
- logger.debug(f"[LANGFUSE] Failed to flush: {e}")
-
- return llm_response
- except Exception as e:
- # End Langfuse observation with error
- if langfuse_observation:
- try:
- if hasattr(langfuse_observation, "update"):
- langfuse_observation.update(
- output=f"Error: {str(e)}",
- metadata={
- "error": str(e),
- **(
- {"response_id": get_current_response_id()}
- if get_current_response_id()
- else {}
- ),
- },
- )
- if hasattr(langfuse_observation, "end"):
- langfuse_observation.end()
- try:
- self.langfuse.flush()
- except Exception:
- pass
- except Exception:
- pass
- # Return error as content for graceful handling
- return LLMResponse(
- content=f"Error calling LLM in LiteLLM: {str(e)}",
- finish_reason="error",
- )
-
- async def chat_stream(
- self,
- messages: list[dict[str, Any]],
- tools: list[dict[str, Any]] | None = None,
- model: str | None = None,
- max_tokens: int | None = None,
- temperature: float = 0.7,
- session_id: str | None = None,
- ) -> AsyncIterator[LLMStreamEvent]:
- """Send a streaming chat completion request via LiteLLM."""
- model = self._resolve_model(model or self.default_model)
- messages = self._handle_system_message(model, messages)
-
- kwargs: dict[str, Any] = {
- "model": model,
- "messages": messages,
- "temperature": temperature,
- "stream": True,
- }
- if max_tokens is not None:
- kwargs["max_tokens"] = max_tokens
- self._apply_model_overrides(model, kwargs)
- self._apply_thinking_overrides(model, kwargs)
-
- if self.api_key:
- kwargs["api_key"] = self.api_key
- if self.api_base:
- kwargs["api_base"] = self.api_base
- if self.timeout is not None:
- kwargs["timeout"] = self.timeout
- if self.extra_headers:
- kwargs["extra_headers"] = self.extra_headers
- if tools:
- kwargs["tools"] = tools
- kwargs["tool_choice"] = "auto"
-
- content_parts: list[str] = []
- reasoning_parts: list[str] = []
- tool_calls: dict[int, dict[str, Any]] = {}
- finish_reason = "stop"
- usage: dict[str, int] = {}
-
- try:
- response = await acompletion(**kwargs)
- async for chunk in response:
- if getattr(chunk, "usage", None):
- usage = self._parse_usage(chunk.usage)
-
- choices = getattr(chunk, "choices", None) or []
- if not choices:
- continue
- choice = choices[0]
- if getattr(choice, "finish_reason", None):
- finish_reason = choice.finish_reason or finish_reason
-
- delta = getattr(choice, "delta", None)
- if delta is None:
- continue
-
- reasoning_delta = stream_delta_value(delta, "reasoning_content")
- if reasoning_delta:
- reasoning_parts.append(reasoning_delta)
- yield LLMStreamEvent(type="reasoning_delta", content=reasoning_delta)
-
- content_delta = stream_delta_value(delta, "content")
- if content_delta:
- content_parts.append(content_delta)
- yield LLMStreamEvent(type="content_delta", content=content_delta)
-
- for fallback_index, delta_tool_call in enumerate(
- getattr(delta, "tool_calls", None) or []
- ):
- merge_stream_tool_call_delta(
- tool_calls,
- delta_tool_call,
- fallback_index=fallback_index,
- )
-
- response_obj = build_stream_response(
- content="".join(content_parts),
- reasoning_content="".join(reasoning_parts),
- raw_tool_calls=tool_calls,
- finish_reason=finish_reason,
- usage=usage,
- token_counter=self._stream_tool_tokens,
- )
- yield LLMStreamEvent(type="response", response=response_obj)
- except Exception as e:
- yield LLMStreamEvent(
- type="response",
- response=LLMResponse(
- content=f"Error calling LLM in LiteLLM stream: {str(e)}",
- finish_reason="error",
- ),
- )
-
- @staticmethod
- def _parse_usage(raw_usage: Any) -> dict[str, int]:
- if not raw_usage:
- return {}
- usage = {
- "prompt_tokens": int(getattr(raw_usage, "prompt_tokens", 0) or 0),
- "completion_tokens": int(getattr(raw_usage, "completion_tokens", 0) or 0),
- "total_tokens": int(getattr(raw_usage, "total_tokens", 0) or 0),
- }
- details = getattr(raw_usage, "prompt_tokens_details", None)
- cached = getattr(details, "cached_tokens", 0) if details else 0
- if not cached:
- cached = getattr(raw_usage, "cache_read_input_tokens", 0) or 0
- if cached:
- usage["cache_read_input_tokens"] = int(cached)
- return usage
-
- @staticmethod
- def _stream_tool_tokens(name: str, raw_arguments: str) -> int:
- tokens = cal_str_tokens(name, text_type="en")
- if raw_arguments:
- tokens += cal_str_tokens(raw_arguments, text_type="mixed")
- return tokens
-
- def _parse_response(self, response: Any) -> LLMResponse:
- """Parse LiteLLM response into our standard format."""
- choice = response.choices[0]
- message = choice.message
-
- tool_calls = []
- if hasattr(message, "tool_calls") and message.tool_calls:
- for tc in message.tool_calls:
- # Parse arguments from JSON string if needed
- args = tc.function.arguments
- tokens = cal_str_tokens(tc.function.name, text_type="en")
- if isinstance(args, str):
- tokens += cal_str_tokens(args, text_type="mixed")
- args = parse_tool_arguments(args)
-
- tool_calls.append(
- ToolCallRequest(id=tc.id, name=tc.function.name, arguments=args, tokens=tokens)
- )
-
- usage = {}
- if hasattr(response, "usage") and response.usage:
- usage = {
- "prompt_tokens": response.usage.prompt_tokens,
- "completion_tokens": response.usage.completion_tokens,
- "total_tokens": response.usage.total_tokens,
- }
-
- # Extract cached tokens from various provider formats
- # OpenAI style: prompt_tokens_details.cached_tokens
- if hasattr(response.usage, "prompt_tokens_details"):
- details = response.usage.prompt_tokens_details
- if details and hasattr(details, "cached_tokens"):
- cached = details.cached_tokens
- if cached:
- usage["cache_read_input_tokens"] = cached
- # Anthropic style: cache_read_input_tokens
- elif hasattr(response.usage, "cache_read_input_tokens"):
- cached = response.usage.cache_read_input_tokens
- if cached:
- usage["cache_read_input_tokens"] = cached
-
- reasoning_content = getattr(message, "reasoning_content", None)
-
- return LLMResponse(
- content=message.content,
- tool_calls=tool_calls,
- finish_reason=choice.finish_reason or "stop",
- usage=usage,
- reasoning_content=reasoning_content,
- )
-
- def get_default_model(self) -> str:
- """Get the default model."""
- return self.default_model
-
- def supports_tool_result_media(self, model: str | None = None) -> bool:
- """Enable only the native tool-result media path verified for Anthropic."""
- if self._gateway is not None:
- return False
- spec = find_by_model(model or self.default_model)
- return spec is not None and spec.name == "anthropic"
diff --git a/bot/vikingbot/providers/registry.py b/bot/vikingbot/providers/registry.py
index 5e035e13b..a91cd8cd9 100644
--- a/bot/vikingbot/providers/registry.py
+++ b/bot/vikingbot/providers/registry.py
@@ -1,10 +1,6 @@
"""
-Provider Registry — single source of truth for LLM provider metadata.
-
-Adding a new provider:
- 1. Add a ProviderSpec to PROVIDERS below.
- 2. Add a field to ProvidersConfig in config/schema.py.
- Done. Env vars, prefixing, config matching, status display all derive from here.
+Bot provider metadata used for history formatting and configuration helpers.
+Model backend registration and request routing are owned by OpenViking VLM.
Order matters — it controls match priority and fallback. Gateways first.
Every entry writes out all fields so you can copy-paste as a template.
@@ -26,10 +22,10 @@ class ProviderSpec:
"""
# identity
- name: str # config field name, e.g. "dashscope"
+ name: str # provider identifier, e.g. "dashscope"
keywords: tuple[str, ...] # model-name keywords for matching (lowercase)
env_key: str # LiteLLM env var, e.g. "DASHSCOPE_API_KEY"
- display_name: str = "" # shown in `vikingbot status`
+ display_name: str = "" # human-readable provider label
# model prefixing
litellm_prefix: str = "" # "dashscope" → model becomes "dashscope/{model}"
@@ -52,7 +48,9 @@ class ProviderSpec:
model_overrides: tuple[tuple[str, dict[str, Any]], ...] = ()
# Provider-specific way to request reasoning/thinking, if supported by the protocol.
- thinking_param: str = "" # volcengine_thinking | dashscope_enable_thinking | openai_reasoning_effort
+ thinking_param: str = (
+ "" # volcengine_thinking | dashscope_enable_thinking | openai_reasoning_effort
+ )
@property
def label(self) -> str:
diff --git a/bot/vikingbot/providers/vlm_adapter.py b/bot/vikingbot/providers/vlm_adapter.py
index 7600a2d57..527a3f768 100644
--- a/bot/vikingbot/providers/vlm_adapter.py
+++ b/bot/vikingbot/providers/vlm_adapter.py
@@ -748,7 +748,7 @@ class VLMProviderAdapter(LLMProvider):
return provider in {"anthropic", "openai-codex"}
# ------------------------------------------------------------------
- # Langfuse helpers (same pattern as LiteLLMProvider.chat())
+ # Langfuse helpers
# ------------------------------------------------------------------
def _end_langfuse_observation(self, obs, llm_response: LLMResponse) -> None:
diff --git a/bot/vikingbot/tests/unit/test_bot_model_timeout.py b/bot/vikingbot/tests/unit/test_bot_model_timeout.py
index 535d002de..2604c83b0 100644
--- a/bot/vikingbot/tests/unit/test_bot_model_timeout.py
+++ b/bot/vikingbot/tests/unit/test_bot_model_timeout.py
@@ -4,9 +4,10 @@ from unittest import mock
import pytest
from pydantic import ValidationError
+from openviking.models.vlm.backends.litellm_vlm import LiteLLMVLMProvider
from vikingbot.config.loader import _merge_vlm_model_config
from vikingbot.config.schema import AgentsConfig
-from vikingbot.providers.litellm_provider import LiteLLMProvider
+from vikingbot.providers.vlm_adapter import VLMProviderAdapter
def _chat_response(content: str = "ok"):
@@ -58,21 +59,25 @@ def test_bot_agents_timeout_overrides_vlm_timeout():
@pytest.mark.asyncio
-async def test_litellm_provider_passes_timeout_to_chat_request(monkeypatch):
+async def test_vlm_adapter_passes_litellm_timeout_to_chat_request(monkeypatch):
captured = {}
async def fake_acompletion(**kwargs):
captured.update(kwargs)
return _chat_response()
- monkeypatch.setattr("vikingbot.providers.litellm_provider.acompletion", fake_acompletion)
+ monkeypatch.setattr("openviking.models.vlm.backends.litellm_vlm.acompletion", fake_acompletion)
- provider = LiteLLMProvider(
- api_key="sk-test",
- api_base="https://example.invalid",
- default_model="openai/gpt-4o-mini",
- timeout=75.0,
+ vlm = LiteLLMVLMProvider(
+ {
+ "provider": "litellm",
+ "api_key": "sk-test",
+ "api_base": "https://example.invalid",
+ "model": "openai/gpt-4o-mini",
+ "timeout": 75.0,
+ }
)
+ provider = VLMProviderAdapter(vlm, default_model="openai/gpt-4o-mini")
response = await provider.chat(messages=[{"role": "user", "content": "hi"}])
assert response.content == "ok"
diff --git a/bot/vikingbot/tests/unit/test_bot_provider_thinking.py b/bot/vikingbot/tests/unit/test_bot_provider_thinking.py
index d05a4c36f..e6dec10e8 100644
--- a/bot/vikingbot/tests/unit/test_bot_provider_thinking.py
+++ b/bot/vikingbot/tests/unit/test_bot_provider_thinking.py
@@ -8,7 +8,6 @@ from openviking.models.vlm.backends.litellm_vlm import (
LiteLLMVLMProvider as OpenVikingLiteLLMVLMProvider,
)
from vikingbot.config.schema import AgentsConfig
-from vikingbot.providers.litellm_provider import LiteLLMProvider
from vikingbot.providers.vlm_adapter import VLMProviderAdapter
@@ -67,21 +66,6 @@ def test_vlm_adapter_exposes_only_native_tool_result_media_backends():
assert mixed_failover.supports_tool_result_media() is False
-def test_litellm_provider_exposes_anthropic_tool_result_media_only():
- langfuse = SimpleNamespace()
- anthropic = LiteLLMProvider(
- default_model="claude-sonnet-4-5",
- langfuse_client=langfuse,
- )
- openai = LiteLLMProvider(
- default_model="gpt-4o",
- langfuse_client=langfuse,
- )
-
- assert anthropic.supports_tool_result_media() is True
- assert openai.supports_tool_result_media() is False
-
-
def test_vlm_adapter_uses_litellm_resolved_provider_for_tool_result_media():
vlm = OpenVikingLiteLLMVLMProvider(
{
@@ -162,61 +146,19 @@ def test_make_provider_passes_default_thinking_to_vlm_adapter(monkeypatch):
@pytest.mark.asyncio
-async def test_litellm_bot_provider_enables_volcengine_thinking(monkeypatch):
- captured = {}
-
- async def fake_acompletion(**kwargs):
- captured.update(kwargs)
- return SimpleNamespace(
- choices=[
- SimpleNamespace(
- message=SimpleNamespace(content="ok", tool_calls=None),
- finish_reason="stop",
- )
- ],
- usage=None,
- )
-
- monkeypatch.setattr("vikingbot.providers.litellm_provider.acompletion", fake_acompletion)
-
- provider = LiteLLMProvider(
- api_key="ak-test",
- default_model="volcengine/ep-test",
- )
- await provider.chat(messages=[{"role": "user", "content": "hi"}])
-
- assert captured["thinking"] == {"type": "enabled"}
-
-
-async def test_litellm_bot_provider_enables_dashscope_thinking(monkeypatch):
- captured = {}
-
- async def fake_acompletion(**kwargs):
- captured.update(kwargs)
- return SimpleNamespace(
- choices=[
- SimpleNamespace(
- message=SimpleNamespace(content="ok", tool_calls=None),
- finish_reason="stop",
- )
- ],
- usage=None,
- )
-
- monkeypatch.setattr("vikingbot.providers.litellm_provider.acompletion", fake_acompletion)
-
- provider = LiteLLMProvider(
- api_key="sk-test",
- default_model="qwen-plus",
- )
- await provider.chat(messages=[{"role": "user", "content": "hi"}])
-
- assert captured["extra_body"] == {"enable_thinking": True}
-
-
-async def test_vlm_adapter_preserves_dashscope_thinking(monkeypatch):
[email protected]("thinking", [True, False])
+ ("backend", "model", "resolved_model"),
+ [
+ ("dashscope", "qwen-plus", "dashscope/qwen-plus"),
+ ("openai", "gpt-4o", "gpt-4o"),
+ ("gemini", "gemini/gemini-2.5-pro", "gemini/gemini-2.5-pro"),
+ ("zhipu", "glm-4", "zhipu/glm-4"),
+ ],
+)
+async def test_vlm_adapter_routes_litellm_thinking_parameters(
+ monkeypatch, thinking, backend, model, resolved_model
+):
from openviking.models.vlm.backends.litellm_vlm import LiteLLMVLMProvider
captured = {}
@@ -240,48 +182,24 @@ async def test_vlm_adapter_preserves_dashscope_thinking(monkeypatch):
vlm = LiteLLMVLMProvider(
{
- "provider": "dashscope",
- "model": "qwen-plus",
+ "provider": backend,
+ "model": model,
"api_key": "sk-test",
- "thinking": True,
+ "thinking": thinking,
}
)
- provider = VLMProviderAdapter(vlm, default_model="qwen-plus")
+ provider = VLMProviderAdapter(vlm, default_model=model)
response = await provider.chat(messages=[{"role": "user", "content": "hi"}])
assert response.content == "ok"
- assert captured["model"] == "dashscope/qwen-plus"
- assert captured["extra_body"] == {"enable_thinking": True}
-
-
-async def test_litellm_bot_provider_does_not_send_thinking_to_generic_openai(monkeypatch):
- captured = {}
-
- async def fake_acompletion(**kwargs):
- captured.update(kwargs)
- return SimpleNamespace(
- choices=[
- SimpleNamespace(
- message=SimpleNamespace(content="ok", tool_calls=None),
- finish_reason="stop",
- )
- ],
- usage=None,
- )
-
- monkeypatch.setattr("vikingbot.providers.litellm_provider.acompletion", fake_acompletion)
-
- provider = LiteLLMProvider(
- api_key="sk-test",
- default_model="gpt-4o",
- )
- await provider.chat(messages=[{"role": "user", "content": "hi"}])
-
+ assert captured["model"] == resolved_model
+ if backend == "dashscope":
+ assert captured["extra_body"] == {"enable_thinking": thinking}
+ else:
+ assert "extra_body" not in captured
assert "thinking" not in captured
- assert "extra_body" not in captured
- assert "max_tokens" not in captured
+ assert "reasoning_effort" not in captured
@pytest.mark.asyncio
@@ -289,7 +207,9 @@ async def test_litellm_bot_provider_does_not_send_thinking_to_generic_openai(mon
("configured_max_tokens", "expected_max_tokens"),
[(None, None), (8192, 8192)],
)
[email protected]("thinking", [True, False])
async def test_vlm_adapter_volcengine_stream_respects_optional_max_tokens(
+ thinking,
configured_max_tokens,
expected_max_tokens,
):
@@ -321,7 +241,7 @@ async def test_vlm_adapter_volcengine_stream_respects_optional_max_tokens(
model="ep-test",
temperature=0.0,
max_tokens=configured_max_tokens,
- thinking=False,
+ thinking=thinking,
extra_headers=None,
get_async_client=lambda: SimpleNamespace(
chat=SimpleNamespace(completions=FakeCompletions())
@@ -341,120 +261,8 @@ async def test_vlm_adapter_volcengine_stream_respects_optional_max_tokens(
]
assert events[-1].response.content == "ok"
+ assert captured["thinking"] == {"type": "enabled" if thinking else "disabled"}
if expected_max_tokens is None:
assert "max_tokens" not in captured
else:
assert captured["max_tokens"] == expected_max_tokens
-
-
-async def test_litellm_bot_provider_enables_openai_reasoning_model(monkeypatch):
- captured = {}
-
- async def fake_acompletion(**kwargs):
- captured.update(kwargs)
- return SimpleNamespace(
- choices=[
- SimpleNamespace(
- message=SimpleNamespace(content="ok", tool_calls=None),
- finish_reason="stop",
- )
- ],
- usage=None,
- )
-
- monkeypatch.setattr("vikingbot.providers.litellm_provider.acompletion", fake_acompletion)
-
- provider = LiteLLMProvider(
- api_key="sk-test",
- default_model="gpt-5",
- )
- await provider.chat(messages=[{"role": "user", "content": "hi"}])
-
- assert captured["reasoning_effort"] == "low"
-
-
-async def test_litellm_bot_provider_respects_thinking_disabled(monkeypatch):
- captured = {}
-
- async def fake_acompletion(**kwargs):
- captured.update(kwargs)
- return SimpleNamespace(
- choices=[
- SimpleNamespace(
- message=SimpleNamespace(content="ok", tool_calls=None),
- finish_reason="stop",
- )
- ],
- usage=None,
- )
-
- monkeypatch.setattr("vikingbot.providers.litellm_provider.acompletion", fake_acompletion)
-
- provider = LiteLLMProvider(
- api_key="ak-test",
- default_model="volcengine/ep-test",
- thinking=False,
- )
- await provider.chat(messages=[{"role": "user", "content": "hi"}])
-
- assert "thinking" not in captured
-
-
-async def test_litellm_bot_provider_does_not_send_dashscope_param_to_gemini(monkeypatch):
- captured = {}
-
- async def fake_acompletion(**kwargs):
- captured.update(kwargs)
- return SimpleNamespace(
- choices=[
- SimpleNamespace(
- message=SimpleNamespace(content="ok", tool_calls=None),
- finish_reason="stop",
- )
- ],
- usage=None,
- )
-
- monkeypatch.setattr("vikingbot.providers.litellm_provider.acompletion", fake_acompletion)
-
- provider = LiteLLMProvider(
- api_key="sk-test",
- default_model="gemini/gemini-2.5-pro",
- )
- await provider.chat(messages=[{"role": "user", "content": "hi"}])
-
- assert "thinking" not in captured
- assert "extra_body" not in captured
- assert "reasoning_effort" not in captured
-
-
-async def test_litellm_bot_provider_does_not_send_dashscope_param_to_zhipu(monkeypatch):
- captured = {}
-
- async def fake_acompletion(**kwargs):
- captured.update(kwargs)
- return SimpleNamespace(
- choices=[
- SimpleNamespace(
- message=SimpleNamespace(content="ok", tool_calls=None),
- finish_reason="stop",
- )
- ],
- usage=None,
- )
-
- monkeypatch.setattr("vikingbot.providers.litellm_provider.acompletion", fake_acompletion)
-
- provider = LiteLLMProvider(
- api_key="sk-test",
- default_model="glm-4",
- )
- await provider.chat(messages=[{"role": "user", "content": "hi"}])
-
- assert "thinking" not in captured
- assert "extra_body" not in captured
- assert "reasoning_effort" not in captured
diff --git a/bot/vikingbot/tests/unit/test_bot_vlm_credentials.py b/bot/vikingbot/tests/unit/test_bot_vlm_credentials.py
index aeb1177a2..d06e115c9 100644
--- a/bot/vikingbot/tests/unit/test_bot_vlm_credentials.py
+++ b/bot/vikingbot/tests/unit/test_bot_vlm_credentials.py
@@ -3,11 +3,11 @@ from types import SimpleNamespace
from unittest.mock import AsyncMock
import pytest
+from typer.testing import CliRunner
from openviking.models.vlm import MultiCredentialVLM
from openviking.models.vlm.backends.litellm_vlm import LiteLLMVLMProvider
from vikingbot.config import loader
-from vikingbot.config.schema import Config
from vikingbot.providers.vlm_adapter import VLMProviderAdapter
@@ -15,9 +15,230 @@ def _write_config(tmp_path, monkeypatch, data):
config_path = tmp_path / "ov.conf"
config_path.write_text(json.dumps(data))
monkeypatch.setattr(loader, "CONFIG_PATH", config_path)
+ monkeypatch.setenv("OPENVIKING_CONFIG_FILE", str(config_path))
return loader.load_config()
[email protected]("bot_override", [False, True])
[email protected]("legacy_providers", [{"openai": {"api_key": "obsolete-secret"}}, {}, None])
+def test_legacy_providers_do_not_change_model_selection_or_persist(
+ tmp_path, monkeypatch, bot_override, legacy_providers
+):
+ data = {
+ "vlm": {"provider": "openai", "model": "root-model", "api_key": "root-secret"},
+ "bot": {"providers": legacy_providers},
+ }
+ if bot_override:
+ data["bot"]["agents"] = {
+ "provider": "openai",
+ "model": "bot-model",
+ "api_key": "bot-secret",
+ }
+ warnings = []
+ monkeypatch.setattr(loader.logger, "warning", warnings.append)
+
+ config = _write_config(tmp_path, monkeypatch, data)
+ from vikingbot.cli.commands import _make_provider
+
+ provider = _make_provider(config)
+ assert provider._vlm.model == ("bot-model" if bot_override else "root-model")
+ assert provider._vlm.api_key == ("bot-secret" if bot_override else "root-secret")
+ assert any("bot.providers" in message and "ignored" in message for message in warnings)
+ assert "obsolete-secret" not in " ".join(warnings)
+ path = tmp_path / "ov.conf"
+ assert json.loads(path.read_text()) == data # Loading never rewrites the user's file.
+
+ loader.save_config(config, path, include_defaults=True)
+ saved = json.loads(path.read_text())
+ assert "providers" not in saved["bot"]
+ assert saved["vlm"] == data["vlm"]
+ assert loader.load_config().inherits_root_vlm() is (not bot_override)
+
+
[email protected]("explicit_key", [None, "channel-secret", ""])
+def test_legacy_groq_key_migrates_to_telegram_without_overriding_channel_config(
+ tmp_path, monkeypatch, explicit_key
+):
+ pytest.importorskip("telegram")
+ from vikingbot.bus.queue import MessageBus
+ from vikingbot.channels.manager import ChannelManager
+
+ channel = {"type": "telegram", "enabled": True, "token": "123:test-token"}
+ if explicit_key is not None:
+ channel["groqApiKey"] = explicit_key
+ data = {
+ "bot": {
+ "providers": {"groq": {"apiKey": "legacy-groq-secret"}},
+ "channels": [channel],
+ }
+ }
+ config = _write_config(tmp_path, monkeypatch, data)
+ manager = ChannelManager(MessageBus())
+
+ manager.load_channels_from_config(config)
+
+ expected_key = "legacy-groq-secret" if explicit_key is None else explicit_key
+ assert manager.channels["telegram__123"].groq_api_key == expected_key
+ assert json.loads((tmp_path / "ov.conf").read_text()) == data
+ loader.save_config(config, tmp_path / "ov.conf")
+ saved = json.loads((tmp_path / "ov.conf").read_text())
+ assert "providers" not in saved["bot"]
+ assert saved["bot"]["channels"][0]["groqApiKey"] == expected_key
+ reloaded = loader.load_config()
+ manager = ChannelManager(MessageBus())
+ manager.load_channels_from_config(reloaded)
+ assert manager.channels["telegram__123"].groq_api_key == expected_key
+
+
[email protected]("bot_override", [False, True])
[email protected]("credential_chain", [False, True])
+def test_status_shows_selected_model_config_without_exposing_secrets(
+ tmp_path, monkeypatch, bot_override, credential_chain
+):
+ from vikingbot.cli import commands
+
+ selected = {
+ "provider": "openai",
+ "model": "selected-model",
+ "api_key": "selected-secret",
+ "extra_headers": {"Authorization": "header-secret"},
+ }
+ if credential_chain:
+ selected["credentials"] = [
+ {"id": "primary", "model": "first-model", "api_key": "first-secret"},
+ {"id": "backup"},
+ ]
+ data = {"vlm": selected}
+ if bot_override:
+ data = {
+ "vlm": {"provider": "openai", "model": "unused-root", "api_key": "root-secret"},
+ "bot": {"agents": selected},
+ }
+ _write_config(tmp_path, monkeypatch, data)
+
+ def fail_create(*args, **kwargs):
+ raise AssertionError("status must not initialize model backends")
+
+ monkeypatch.setattr("openviking.models.vlm.base.VLMFactory.create", fail_create)
+ result = CliRunner().invoke(commands.app, ["status"])
+
+ assert result.exit_code == 0, result.output
+ source = "bot.agents" if bot_override else "vlm (inherited)"
+ assert f"Model config: {source}" in result.output
+ assert "Model: selected-model" in result.output
+ assert "Provider: openai" in result.output
+ assert "API key: configured" in result.output
+ assert "Extra headers: configured" in result.output
+ assert "not set in config" not in result.output
+ assert "not a live health check" in result.output
+ if credential_chain:
+ assert result.output.index("Model: first-model") < result.output.index(
+ "Model: selected-model"
+ )
+ assert result.output.count("API key: configured") == 2
+ for hidden in (
+ "selected-secret",
+ "first-secret",
+ "header-secret",
+ "root-secret",
+ "unused-root",
+ ):
+ assert hidden not in result.output
+
+
+def test_status_handles_bot_credentials_without_parent_model(tmp_path, monkeypatch):
+ from vikingbot.cli import commands
+
+ _write_config(
+ tmp_path,
+ monkeypatch,
+ {
+ "bot": {
+ "agents": {
+ "credentials": [
+ {"provider": "litellm", "model": "ollama/qwen3"},
+ ]
+ }
+ }
+ },
+ )
+
+ result = CliRunner().invoke(commands.app, ["status"])
+
+ assert result.exit_code == 0, result.output
+ assert "Model config: bot.agents" in result.output
+ assert "Model: ollama/qwen3" in result.output
+ assert "Provider: litellm" in result.output
+ assert "API key: not set in config" in result.output
+
+
[email protected]("parent_provider", ["openai", "OpenAI", " OpenAI \t"])
[email protected]("credential_provider", [None, "openai"])
+def test_status_inherits_parent_key_only_for_the_normalized_parent_provider(
+ tmp_path, monkeypatch, parent_provider, credential_provider
+):
+ from vikingbot.cli import commands
+
+ _write_config(
+ tmp_path,
+ monkeypatch,
+ {
+ "bot": {
+ "agents": {
+ "provider": parent_provider,
+ "model": "gpt-4o",
+ "api_key": "openai-secret",
+ "credentials": [
+ {"id": "primary", "provider": credential_provider},
+ {
+ "id": "native",
+ "provider": "litellm",
+ "model": "vertex_ai/gemini-2.5-pro",
+ },
+ ],
+ }
+ }
+ },
+ )
+
+ def fail_create(*args, **kwargs):
+ raise AssertionError("status must not initialize model backends")
+
+ monkeypatch.setattr("openviking.models.vlm.base.VLMFactory.create", fail_create)
+ result = CliRunner().invoke(commands.app, ["status"])
+
+ assert result.exit_code == 0, result.output
+ assert "1. Provider: openai | Model: gpt-4o" in result.output
+ assert "2. Provider: litellm | Model: vertex_ai/gemini-2.5-pro" in result.output
+ assert result.output.count("API key: configured") == 1
+ assert "API key: not set in config" in result.output
+ assert "openai-secret" not in result.output
+
+
+def test_status_keeps_root_vlm_providers_support(tmp_path, monkeypatch):
+ from vikingbot.cli import commands
+
+ _write_config(
+ tmp_path,
+ monkeypatch,
+ {
+ "vlm": {
+ "model": "root-model",
+ "default_provider": "openai",
+ "providers": {"openai": {"api_key": "root-secret"}},
+ }
+ },
+ )
+
+ result = CliRunner().invoke(commands.app, ["status"])
+
+ assert result.exit_code == 0, result.output
+ assert "Model config: vlm (inherited)" in result.output
+ assert "Provider: openai" in result.output
+ assert "API key: configured" in result.output
+ assert "root-secret" not in result.output
+
+
def test_bot_inherits_root_vlm_credentials_when_agents_model_is_omitted(tmp_path, monkeypatch):
config = _write_config(
tmp_path,
@@ -393,173 +614,6 @@ def test_saving_inherited_config_does_not_turn_root_model_into_bot_override(tmp_
assert reloaded.agents.inherits_root_vlm() is True
-def test_console_roundtrip_preserves_root_vlm_inheritance(tmp_path, monkeypatch):
- config = _write_config(
- tmp_path,
- monkeypatch,
- {
- "vlm": {
- "model": "root-primary",
- "credentials": [
- {
- "id": "root-primary",
- "provider": "openai",
- "model": "root-primary",
- "api_key": "root-primary-key",
- },
- {
- "id": "root-backup",
- "provider": "openai",
- "model": "root-backup",
- "api_key": "root-backup-key",
- },
- ],
- }
- },
- )
-
- config_dict = config.model_dump()
- rebuilt = Config(**config_dict)
- loader.reconcile_vlm_inheritance_after_edit(config, rebuilt)
-
- assert config.inherits_root_vlm() is True
- assert rebuilt.inherits_root_vlm() is True
- assert rebuilt.agents.inherits_root_vlm() is True
- assert "inherits_root_vlm_state" not in Config.model_json_schema()["properties"]
-
- loader.save_config(rebuilt, tmp_path / "ov.conf")
-
- saved = json.loads((tmp_path / "ov.conf").read_text())
- assert "inheritsRootVlmState" not in saved.get("bot", {})
- assert "model" not in saved.get("bot", {}).get("agents", {})
-
- reloaded = loader.load_config()
- assert reloaded.inherits_root_vlm() is True
- assert reloaded.agents.inherits_root_vlm() is True
- assert [credential.id for credential in reloaded.get_root_vlm_config().credentials] == [
- "root-primary",
- "root-backup",
- ]
-
-
-def test_console_edit_can_switch_from_root_vlm_to_bot_model(tmp_path, monkeypatch):
- previous = _write_config(
- tmp_path,
- monkeypatch,
- {
- "vlm": {
- "provider": "openai",
- "model": "root-model",
- "api_key": "root-key",
- }
- },
- )
-
- config_dict = previous.model_dump()
- config_dict["agents"]["model"] = "bot-model"
- config_dict["agents"]["api_key"] = "bot-key"
- edited = Config(**config_dict)
-
- loader.reconcile_vlm_inheritance_after_edit(previous, edited)
- loader.save_config(edited, tmp_path / "ov.conf")
-
- saved = json.loads((tmp_path / "ov.conf").read_text())
- assert saved["bot"]["agents"]["model"] == "bot-model"
-
- reloaded = loader.load_config()
- assert reloaded.inherits_root_vlm() is False
- assert reloaded.agents.model == "bot-model"
- assert reloaded.agents.api_key == "bot-key"
-
-
-def test_console_credentials_edit_does_not_persist_inherited_model(tmp_path, monkeypatch):
- previous = _write_config(
- tmp_path,
- monkeypatch,
- {
- "vlm": {
- "provider": "openai",
- "model": "root-model",
- "api_key": "root-key",
- "api_base": "https://root-gateway.example/v1",
- "extra_headers": {"X-Root-Tenant": "root"},
- }
- },
- )
-
- config_dict = previous.model_dump()
- config_dict["agents"]["credentials"] = [
- {
- "id": "bot-primary",
- "provider": "openai",
- "model": "bot-model",
- "api_key": "bot-key",
- }
- ]
- edited = Config(**config_dict)
-
- loader.reconcile_vlm_inheritance_after_edit(previous, edited)
- loader.save_config(edited, tmp_path / "ov.conf")
-
- assert edited.inherits_root_vlm() is False
- saved = json.loads((tmp_path / "ov.conf").read_text())
- assert "model" not in saved["bot"]["agents"]
- assert saved["bot"]["agents"]["provider"] == ""
- assert saved["bot"]["agents"]["apiKey"] == ""
- assert saved["bot"]["agents"]["apiBase"] == ""
- assert saved["bot"]["agents"]["extraHeaders"] == {}
-
- reloaded = loader.load_config()
- assert reloaded.inherits_root_vlm() is False
- assert reloaded.agents.model == ""
- assert reloaded.agents.credentials[0].model == "bot-model"
-
- from vikingbot.cli.commands import _make_provider
-
- provider = _make_provider(reloaded)
- assert provider._vlm.model == "bot-model"
- assert provider._vlm.api_key == "bot-key"
- assert provider._vlm.api_base is None
- assert provider._vlm.extra_headers is None
-
-
-def test_console_bot_credentials_do_not_inherit_root_api_key(tmp_path, monkeypatch):
- previous = _write_config(
- tmp_path,
- monkeypatch,
- {
- "vlm": {
- "provider": "openai",
- "model": "root-model",
- "api_key": "root-key",
- "api_base": "https://root-gateway.example/v1",
- }
- },
- )
-
- config_dict = previous.model_dump()
- config_dict["agents"]["credentials"] = [
- {
- "id": "bot-primary",
- "provider": "openai",
- "model": "bot-model",
- }
- ]
- edited = Config(**config_dict)
-
- loader.reconcile_vlm_inheritance_after_edit(previous, edited)
- loader.save_config(edited, tmp_path / "ov.conf")
-
- reloaded = loader.load_config()
- assert reloaded.agents.api_key == ""
- assert reloaded.agents.api_base == ""
-
- from vikingbot.cli.commands import _make_provider
-
- with pytest.raises(ValueError, match="requires 'api_key' to be set"):
- _make_provider(reloaded)
-
-
def test_saving_credentials_only_config_keeps_model_omitted(tmp_path, monkeypatch):
config = _write_config(
tmp_path,
diff --git a/bot/vikingbot/tests/unit/test_openviking_peer_identity.py b/bot/vikingbot/tests/unit/test_openviking_peer_identity.py
index 7e0c652fd..458e79683 100644
--- a/bot/vikingbot/tests/unit/test_openviking_peer_identity.py
+++ b/bot/vikingbot/tests/unit/test_openviking_peer_identity.py
@@ -29,10 +29,6 @@ def _client(api_key_type: str = "user") -> VikingClient:
client.admin_user_id = "bot-user"
client.agent_id = "agent-1"
client._request_connection = None
- client._namespace_policy = {
- "isolate_user_scope_by_agent": False,
- "isolate_agent_scope_by_user": False,
- }
return client
diff --git a/openviking/server/routers/bot.py b/openviking/server/routers/bot.py
index 5b0d73120..bf34c4e50 100644
--- a/openviking/server/routers/bot.py
+++ b/openviking/server/routers/bot.py
@@ -26,10 +26,6 @@ logger = get_logger(__name__)
BOT_API_URL: Optional[str] = None # e.g., "http://localhost:18791"
BOT_API_KEY: str = ""
DEFAULT_BOT_AGENT_ID = "web-playground"
-DEFAULT_NAMESPACE_POLICY = {
- "isolate_user_scope_by_agent": False,
- "isolate_agent_scope_by_user": False,
-}
def _create_bot_proxy_client() -> httpx.AsyncClient:
@@ -88,7 +84,6 @@ def _build_openviking_connection(
"role": getattr(ctx.role, "value", str(ctx.role)),
"api_key_type": "root" if effective_auth_mode == "trusted" else "user",
"server_url": server_url,
- "namespace_policy": dict(DEFAULT_NAMESPACE_POLICY),
}
if api_key:
connection["api_key"] = api_key
diff --git a/pyproject.toml b/pyproject.toml
index 6c20a8de9..afda052fd 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -157,7 +157,6 @@ bot = [
"beautifulsoup4>=4.12.0",
"ddgs>=9.0.0",
"tavily-python>=0.5.0",
- "gradio>=6.6.0",
"py-machineid>=1.0.0",
"mcp>=1,<2",
# All optional features included by default
diff --git a/tests/server/test_bot_proxy_auth.py b/tests/server/test_bot_proxy_auth.py
index d53262f59..153a995e3 100644
--- a/tests/server/test_bot_proxy_auth.py
+++ b/tests/server/test_bot_proxy_auth.py
@@ -146,10 +146,6 @@ async def test_chat_proxy_attaches_authenticated_openviking_connection(monkeypat
"role": "user",
"api_key_type": "root",
"server_url": "http://127.0.0.1:1944",
- "namespace_policy": {
- "isolate_user_scope_by_agent": False,
- "isolate_agent_scope_by_user": False,
- },
}
assert forwarded["headers"]["X-Gateway-Token"] == "gateway-secret"
assert forwarded["timeout"] == 300.0
@@ -213,10 +209,6 @@ async def test_chat_proxy_forwards_trusted_request_without_root_api_key(monkeypa
"role": "user",
"api_key_type": "root",
"server_url": "http://127.0.0.1:1955",
- "namespace_policy": {
- "isolate_user_scope_by_agent": False,
- "isolate_agent_scope_by_user": False,
- },
}
assert "X-Gateway-Token" not in forwarded["headers"]
assert forwarded["timeout"] == 300.0
diff --git a/uv.lock b/uv.lock
index 911db2aaf..900837782 100644
--- a/uv.lock
+++ b/uv.lock
@@ -31,15 +31,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/26/b5/2748e86137ee757b749d2fb7f5504e039f780c9346be798870ae01ee1559/agent_sandbox-0.0.26-py2.py3-none-any.whl", hash = "sha256:6421fc4eb6144f10ddfdd2668c6644e132056eaeb6ab89d76a0b2e4bcf327a0a", size = 216489, upload-time = "2026-03-02T08:47:23.351Z" },
]
-[[package]]
-name = "aiofiles"
-version = "24.1.0"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/0b/03/a88171e277e8caa88a4c77808c20ebb04ba74cc4681bf1e9416c862de237/aiofiles-24.1.0.tar.gz", hash = "sha256:22a075c9e5a3810f0c2e48f3008c94d68c65d763b9b03857924c99e57355166c", size = 30247, upload-time = "2024-06-24T11:02:03.584Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/a5/45/30bb92d442636f570cb5651bc661f52b610e2eec3f891a5dc3a4c3667db0/aiofiles-24.1.0-py3-none-any.whl", hash = "sha256:b4ec55f4195e3eb5d7abd1bf7e061763e864dd4954231fb8539a0ef8bb8260e5", size = 15896, upload-time = "2024-06-24T11:02:01.529Z" },
-]
-
[[package]]
name = "aiohappyeyeballs"
version = "2.6.1"
@@ -310,62 +301,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/3a/2a/7cc015f5b9f5db42b7d48157e23356022889fc354a2813c15934b7cb5c0e/attrs-25.4.0-py3-none-any.whl", hash = "sha256:adcf7e2a1fb3b36ac48d97835bb6d8ade15b8dcce26aba8bf1d14847b57a3373", size = 67615, upload-time = "2025-10-06T13:54:43.17Z" },
]
-[[package]]
-name = "audioop-lts"
-version = "0.2.2"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/38/53/946db57842a50b2da2e0c1e34bd37f36f5aadba1a929a3971c5d7841dbca/audioop_lts-0.2.2.tar.gz", hash = "sha256:64d0c62d88e67b98a1a5e71987b7aa7b5bcffc7dcee65b635823dbdd0a8dbbd0", size = 30686, upload-time = "2025-08-05T16:43:17.409Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/de/d4/94d277ca941de5a507b07f0b592f199c22454eeaec8f008a286b3fbbacd6/audioop_lts-0.2.2-cp313-abi3-macosx_10_13_universal2.whl", hash = "sha256:fd3d4602dc64914d462924a08c1a9816435a2155d74f325853c1f1ac3b2d9800", size = 46523, upload-time = "2025-08-05T16:42:20.836Z" },
- { url = "https://files.pythonhosted.org/packages/f8/5a/656d1c2da4b555920ce4177167bfeb8623d98765594af59702c8873f60ec/audioop_lts-0.2.2-cp313-abi3-macosx_10_13_x86_64.whl", hash = "sha256:550c114a8df0aafe9a05442a1162dfc8fec37e9af1d625ae6060fed6e756f303", size = 27455, upload-time = "2025-08-05T16:42:22.283Z" },
- { url = "https://files.pythonhosted.org/packages/1b/83/ea581e364ce7b0d41456fb79d6ee0ad482beda61faf0cab20cbd4c63a541/audioop_lts-0.2.2-cp313-abi3-macosx_11_0_arm64.whl", hash = "sha256:9a13dc409f2564de15dd68be65b462ba0dde01b19663720c68c1140c782d1d75", size = 26997, upload-time = "2025-08-05T16:42:23.849Z" },
- { url = "https://files.pythonhosted.org/packages/b8/3b/e8964210b5e216e5041593b7d33e97ee65967f17c282e8510d19c666dab4/audioop_lts-0.2.2-cp313-abi3-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:51c916108c56aa6e426ce611946f901badac950ee2ddaf302b7ed35d9958970d", size = 85844, upload-time = "2025-08-05T16:42:25.208Z" },
- { url = "https://files.pythonhosted.org/packages/c7/2e/0a1c52faf10d51def20531a59ce4c706cb7952323b11709e10de324d6493/audioop_lts-0.2.2-cp313-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:47eba38322370347b1c47024defbd36374a211e8dd5b0dcbce7b34fdb6f8847b", size = 85056, upload-time = "2025-08-05T16:42:26.559Z" },
- { url = "https://files.pythonhosted.org/packages/75/e8/cd95eef479656cb75ab05dfece8c1f8c395d17a7c651d88f8e6e291a63ab/audioop_lts-0.2.2-cp313-abi3-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:ba7c3a7e5f23e215cb271516197030c32aef2e754252c4c70a50aaff7031a2c8", size = 93892, upload-time = "2025-08-05T16:42:27.902Z" },
- { url = "https://files.pythonhosted.org/packages/5c/1e/a0c42570b74f83efa5cca34905b3eef03f7ab09fe5637015df538a7f3345/audioop_lts-0.2.2-cp313-abi3-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:def246fe9e180626731b26e89816e79aae2276f825420a07b4a647abaa84becc", size = 96660, upload-time = "2025-08-05T16:42:28.9Z" },
- { url = "https://files.pythonhosted.org/packages/50/d5/8a0ae607ca07dbb34027bac8db805498ee7bfecc05fd2c148cc1ed7646e7/audioop_lts-0.2.2-cp313-abi3-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:e160bf9df356d841bb6c180eeeea1834085464626dc1b68fa4e1d59070affdc3", size = 79143, upload-time = "2025-08-05T16:42:29.929Z" },
- { url = "https://files.pythonhosted.org/packages/12/17/0d28c46179e7910bfb0bb62760ccb33edb5de973052cb2230b662c14ca2e/audioop_lts-0.2.2-cp313-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:4b4cd51a57b698b2d06cb9993b7ac8dfe89a3b2878e96bc7948e9f19ff51dba6", size = 84313, upload-time = "2025-08-05T16:42:30.949Z" },
- { url = "https://files.pythonhosted.org/packages/84/ba/bd5d3806641564f2024e97ca98ea8f8811d4e01d9b9f9831474bc9e14f9e/audioop_lts-0.2.2-cp313-abi3-musllinux_1_2_ppc64le.whl", hash = "sha256:4a53aa7c16a60a6857e6b0b165261436396ef7293f8b5c9c828a3a203147ed4a", size = 93044, upload-time = "2025-08-05T16:42:31.959Z" },
- { url = "https://files.pythonhosted.org/packages/f9/5e/435ce8d5642f1f7679540d1e73c1c42d933331c0976eb397d1717d7f01a3/audioop_lts-0.2.2-cp313-abi3-musllinux_1_2_riscv64.whl", hash = "sha256:3fc38008969796f0f689f1453722a0f463da1b8a6fbee11987830bfbb664f623", size = 78766, upload-time = "2025-08-05T16:42:33.302Z" },
- { url = "https://files.pythonhosted.org/packages/ae/3b/b909e76b606cbfd53875693ec8c156e93e15a1366a012f0b7e4fb52d3c34/audioop_lts-0.2.2-cp313-abi3-musllinux_1_2_s390x.whl", hash = "sha256:15ab25dd3e620790f40e9ead897f91e79c0d3ce65fe193c8ed6c26cffdd24be7", size = 87640, upload-time = "2025-08-05T16:42:34.854Z" },
- { url = "https://files.pythonhosted.org/packages/30/e7/8f1603b4572d79b775f2140d7952f200f5e6c62904585d08a01f0a70393a/audioop_lts-0.2.2-cp313-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:03f061a1915538fd96272bac9551841859dbb2e3bf73ebe4a23ef043766f5449", size = 86052, upload-time = "2025-08-05T16:42:35.839Z" },
- { url = "https://files.pythonhosted.org/packages/b5/96/c37846df657ccdda62ba1ae2b6534fa90e2e1b1742ca8dcf8ebd38c53801/audioop_lts-0.2.2-cp313-abi3-win32.whl", hash = "sha256:3bcddaaf6cc5935a300a8387c99f7a7fbbe212a11568ec6cf6e4bc458c048636", size = 26185, upload-time = "2025-08-05T16:42:37.04Z" },
- { url = "https://files.pythonhosted.org/packages/34/a5/9d78fdb5b844a83da8a71226c7bdae7cc638861085fff7a1d707cb4823fa/audioop_lts-0.2.2-cp313-abi3-win_amd64.whl", hash = "sha256:a2c2a947fae7d1062ef08c4e369e0ba2086049a5e598fda41122535557012e9e", size = 30503, upload-time = "2025-08-05T16:42:38.427Z" },
- { url = "https://files.pythonhosted.org/packages/34/25/20d8fde083123e90c61b51afb547bb0ea7e77bab50d98c0ab243d02a0e43/audioop_lts-0.2.2-cp313-abi3-win_arm64.whl", hash = "sha256:5f93a5db13927a37d2d09637ccca4b2b6b48c19cd9eda7b17a2e9f77edee6a6f", size = 24173, upload-time = "2025-08-05T16:42:39.704Z" },
- { url = "https://files.pythonhosted.org/packages/58/a7/0a764f77b5c4ac58dc13c01a580f5d32ae8c74c92020b961556a43e26d02/audioop_lts-0.2.2-cp313-cp313t-macosx_10_13_universal2.whl", hash = "sha256:73f80bf4cd5d2ca7814da30a120de1f9408ee0619cc75da87d0641273d202a09", size = 47096, upload-time = "2025-08-05T16:42:40.684Z" },
- { url = "https://files.pythonhosted.org/packages/aa/ed/ebebedde1a18848b085ad0fa54b66ceb95f1f94a3fc04f1cd1b5ccb0ed42/audioop_lts-0.2.2-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:106753a83a25ee4d6f473f2be6b0966fc1c9af7e0017192f5531a3e7463dce58", size = 27748, upload-time = "2025-08-05T16:42:41.992Z" },
- { url = "https://files.pythonhosted.org/packages/cb/6e/11ca8c21af79f15dbb1c7f8017952ee8c810c438ce4e2b25638dfef2b02c/audioop_lts-0.2.2-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:fbdd522624141e40948ab3e8cdae6e04c748d78710e9f0f8d4dae2750831de19", size = 27329, upload-time = "2025-08-05T16:42:42.987Z" },
- { url = "https://files.pythonhosted.org/packages/84/52/0022f93d56d85eec5da6b9da6a958a1ef09e80c39f2cc0a590c6af81dcbb/audioop_lts-0.2.2-cp313-cp313t-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:143fad0311e8209ece30a8dbddab3b65ab419cbe8c0dde6e8828da25999be911", size = 92407, upload-time = "2025-08-05T16:42:44.336Z" },
- { url = "https://files.pythonhosted.org/packages/87/1d/48a889855e67be8718adbc7a01f3c01d5743c325453a5e81cf3717664aad/audioop_lts-0.2.2-cp313-cp313t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:dfbbc74ec68a0fd08cfec1f4b5e8cca3d3cd7de5501b01c4b5d209995033cde9", size = 91811, upload-time = "2025-08-05T16:42:45.325Z" },
- { url = "https://files.pythonhosted.org/packages/98/a6/94b7213190e8077547ffae75e13ed05edc488653c85aa5c41472c297d295/audioop_lts-0.2.2-cp313-cp313t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:cfcac6aa6f42397471e4943e0feb2244549db5c5d01efcd02725b96af417f3fe", size = 100470, upload-time = "2025-08-05T16:42:46.468Z" },
- { url = "https://files.pythonhosted.org/packages/e9/e9/78450d7cb921ede0cfc33426d3a8023a3bda755883c95c868ee36db8d48d/audioop_lts-0.2.2-cp313-cp313t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:752d76472d9804ac60f0078c79cdae8b956f293177acd2316cd1e15149aee132", size = 103878, upload-time = "2025-08-05T16:42:47.576Z" },
- { url = "https://files.pythonhosted.org/packages/4f/e2/cd5439aad4f3e34ae1ee852025dc6aa8f67a82b97641e390bf7bd9891d3e/audioop_lts-0.2.2-cp313-cp313t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:83c381767e2cc10e93e40281a04852facc4cd9334550e0f392f72d1c0a9c5753", size = 84867, upload-time = "2025-08-05T16:42:49.003Z" },
- { url = "https://files.pythonhosted.org/packages/68/4b/9d853e9076c43ebba0d411e8d2aa19061083349ac695a7d082540bad64d0/audioop_lts-0.2.2-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:c0022283e9556e0f3643b7c3c03f05063ca72b3063291834cca43234f20c60bb", size = 90001, upload-time = "2025-08-05T16:42:50.038Z" },
- { url = "https://files.pythonhosted.org/packages/58/26/4bae7f9d2f116ed5593989d0e521d679b0d583973d203384679323d8fa85/audioop_lts-0.2.2-cp313-cp313t-musllinux_1_2_ppc64le.whl", hash = "sha256:a2d4f1513d63c795e82948e1305f31a6d530626e5f9f2605408b300ae6095093", size = 99046, upload-time = "2025-08-05T16:42:51.111Z" },
- { url = "https://files.pythonhosted.org/packages/b2/67/a9f4fb3e250dda9e9046f8866e9fa7d52664f8985e445c6b4ad6dfb55641/audioop_lts-0.2.2-cp313-cp313t-musllinux_1_2_riscv64.whl", hash = "sha256:c9c8e68d8b4a56fda8c025e538e639f8c5953f5073886b596c93ec9b620055e7", size = 84788, upload-time = "2025-08-05T16:42:52.198Z" },
- { url = "https://files.pythonhosted.org/packages/70/f7/3de86562db0121956148bcb0fe5b506615e3bcf6e63c4357a612b910765a/audioop_lts-0.2.2-cp313-cp313t-musllinux_1_2_s390x.whl", hash = "sha256:96f19de485a2925314f5020e85911fb447ff5fbef56e8c7c6927851b95533a1c", size = 94472, upload-time = "2025-08-05T16:42:53.59Z" },
- { url = "https://files.pythonhosted.org/packages/f1/32/fd772bf9078ae1001207d2df1eef3da05bea611a87dd0e8217989b2848fa/audioop_lts-0.2.2-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:e541c3ef484852ef36545f66209444c48b28661e864ccadb29daddb6a4b8e5f5", size = 92279, upload-time = "2025-08-05T16:42:54.632Z" },
- { url = "https://files.pythonhosted.org/packages/4f/41/affea7181592ab0ab560044632571a38edaf9130b84928177823fbf3176a/audioop_lts-0.2.2-cp313-cp313t-win32.whl", hash = "sha256:d5e73fa573e273e4f2e5ff96f9043858a5e9311e94ffefd88a3186a910c70917", size = 26568, upload-time = "2025-08-05T16:42:55.627Z" },
- { url = "https://files.pythonhosted.org/packages/28/2b/0372842877016641db8fc54d5c88596b542eec2f8f6c20a36fb6612bf9ee/audioop_lts-0.2.2-cp313-cp313t-win_amd64.whl", hash = "sha256:9191d68659eda01e448188f60364c7763a7ca6653ed3f87ebb165822153a8547", size = 30942, upload-time = "2025-08-05T16:42:56.674Z" },
- { url = "https://files.pythonhosted.org/packages/ee/ca/baf2b9cc7e96c179bb4a54f30fcd83e6ecb340031bde68f486403f943768/audioop_lts-0.2.2-cp313-cp313t-win_arm64.whl", hash = "sha256:c174e322bb5783c099aaf87faeb240c8d210686b04bd61dfd05a8e5a83d88969", size = 24603, upload-time = "2025-08-05T16:42:57.571Z" },
- { url = "https://files.pythonhosted.org/packages/5c/73/413b5a2804091e2c7d5def1d618e4837f1cb82464e230f827226278556b7/audioop_lts-0.2.2-cp314-cp314t-macosx_10_13_universal2.whl", hash = "sha256:f9ee9b52f5f857fbaf9d605a360884f034c92c1c23021fb90b2e39b8e64bede6", size = 47104, upload-time = "2025-08-05T16:42:58.518Z" },
- { url = "https://files.pythonhosted.org/packages/ae/8c/daa3308dc6593944410c2c68306a5e217f5c05b70a12e70228e7dd42dc5c/audioop_lts-0.2.2-cp314-cp314t-macosx_10_13_x86_64.whl", hash = "sha256:49ee1a41738a23e98d98b937a0638357a2477bc99e61b0f768a8f654f45d9b7a", size = 27754, upload-time = "2025-08-05T16:43:00.132Z" },
- { url = "https://files.pythonhosted.org/packages/4e/86/c2e0f627168fcf61781a8f72cab06b228fe1da4b9fa4ab39cfb791b5836b/audioop_lts-0.2.2-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:5b00be98ccd0fc123dcfad31d50030d25fcf31488cde9e61692029cd7394733b", size = 27332, upload-time = "2025-08-05T16:43:01.666Z" },
- { url = "https://files.pythonhosted.org/packages/c7/bd/35dce665255434f54e5307de39e31912a6f902d4572da7c37582809de14f/audioop_lts-0.2.2-cp314-cp314t-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:a6d2e0f9f7a69403e388894d4ca5ada5c47230716a03f2847cfc7bd1ecb589d6", size = 92396, upload-time = "2025-08-05T16:43:02.991Z" },
- { url = "https://files.pythonhosted.org/packages/2d/d2/deeb9f51def1437b3afa35aeb729d577c04bcd89394cb56f9239a9f50b6f/audioop_lts-0.2.2-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:f9b0b8a03ef474f56d1a842af1a2e01398b8f7654009823c6d9e0ecff4d5cfbf", size = 91811, upload-time = "2025-08-05T16:43:04.096Z" },
- { url = "https://files.pythonhosted.org/packages/76/3b/09f8b35b227cee28cc8231e296a82759ed80c1a08e349811d69773c48426/audioop_lts-0.2.2-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:2b267b70747d82125f1a021506565bdc5609a2b24bcb4773c16d79d2bb260bbd", size = 100483, upload-time = "2025-08-05T16:43:05.085Z" },
- { url = "https://files.pythonhosted.org/packages/0b/15/05b48a935cf3b130c248bfdbdea71ce6437f5394ee8533e0edd7cfd93d5e/audioop_lts-0.2.2-cp314-cp314t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:0337d658f9b81f4cd0fdb1f47635070cc084871a3d4646d9de74fdf4e7c3d24a", size = 103885, upload-time = "2025-08-05T16:43:06.197Z" },
- { url = "https://files.pythonhosted.org/packages/83/80/186b7fce6d35b68d3d739f228dc31d60b3412105854edb975aa155a58339/audioop_lts-0.2.2-cp314-cp314t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:167d3b62586faef8b6b2275c3218796b12621a60e43f7e9d5845d627b9c9b80e", size = 84899, upload-time = "2025-08-05T16:43:07.291Z" },
- { url = "https://files.pythonhosted.org/packages/49/89/c78cc5ac6cb5828f17514fb12966e299c850bc885e80f8ad94e38d450886/audioop_lts-0.2.2-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:0d9385e96f9f6da847f4d571ce3cb15b5091140edf3db97276872647ce37efd7", size = 89998, upload-time = "2025-08-05T16:43:08.335Z" },
- { url = "https://files.pythonhosted.org/packages/4c/4b/6401888d0c010e586c2ca50fce4c903d70a6bb55928b16cfbdfd957a13da/audioop_lts-0.2.2-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:48159d96962674eccdca9a3df280e864e8ac75e40a577cc97c5c42667ffabfc5", size = 99046, upload-time = "2025-08-05T16:43:09.367Z" },
- { url = "https://files.pythonhosted.org/packages/de/f8/c874ca9bb447dae0e2ef2e231f6c4c2b0c39e31ae684d2420b0f9e97ee68/audioop_lts-0.2.2-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:8fefe5868cd082db1186f2837d64cfbfa78b548ea0d0543e9b28935ccce81ce9", size = 84843, upload-time = "2025-08-05T16:43:10.749Z" },
- { url = "https://files.pythonhosted.org/packages/3e/c0/0323e66f3daebc13fd46b36b30c3be47e3fc4257eae44f1e77eb828c703f/audioop_lts-0.2.2-cp314-cp314t-musllinux_1_2_s390x.whl", hash = "sha256:58cf54380c3884fb49fdd37dfb7a772632b6701d28edd3e2904743c5e1773602", size = 94490, upload-time = "2025-08-05T16:43:12.131Z" },
- { url = "https://files.pythonhosted.org/packages/98/6b/acc7734ac02d95ab791c10c3f17ffa3584ccb9ac5c18fd771c638ed6d1f5/audioop_lts-0.2.2-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:088327f00488cdeed296edd9215ca159f3a5a5034741465789cad403fcf4bec0", size = 92297, upload-time = "2025-08-05T16:43:13.139Z" },
- { url = "https://files.pythonhosted.org/packages/13/c3/c3dc3f564ce6877ecd2a05f8d751b9b27a8c320c2533a98b0c86349778d0/audioop_lts-0.2.2-cp314-cp314t-win32.whl", hash = "sha256:068aa17a38b4e0e7de771c62c60bbca2455924b67a8814f3b0dee92b5820c0b3", size = 27331, upload-time = "2025-08-05T16:43:14.19Z" },
- { url = "https://files.pythonhosted.org/packages/72/bb/b4608537e9ffcb86449091939d52d24a055216a36a8bf66b936af8c3e7ac/audioop_lts-0.2.2-cp314-cp314t-win_amd64.whl", hash = "sha256:a5bf613e96f49712073de86f20dbdd4014ca18efd4d34ed18c75bd808337851b", size = 31697, upload-time = "2025-08-05T16:43:15.193Z" },
- { url = "https://files.pythonhosted.org/packages/f6/22/91616fe707a5c5510de2cac9b046a30defe7007ba8a0c04f9c08f27df312/audioop_lts-0.2.2-cp314-cp314t-win_arm64.whl", hash = "sha256:b492c3b040153e68b9fdaff5913305aaaba5bb433d8a7f73d5cf6a64ed3cc1dd", size = 25206, upload-time = "2025-08-05T16:43:16.444Z" },
-]
-
[[package]]
name = "automat"
version = "25.4.16"
@@ -452,64 +387,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/9a/60/17a2d3b94658bb999c6aee7bba6c76b271905debf0c8c8e6ac63ca8491bc/botocore-1.42.63-py3-none-any.whl", hash = "sha256:83f39d04f2b316bdfc59a3cac2d12238bde7126ac99d9a57d910dbd86d58c528", size = 14639889, upload-time = "2026-03-06T22:47:39.347Z" },
]
-[[package]]
-name = "brotli"
-version = "1.2.0"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/f7/16/c92ca344d646e71a43b8bb353f0a6490d7f6e06210f8554c8f874e454285/brotli-1.2.0.tar.gz", hash = "sha256:e310f77e41941c13340a95976fe66a8a95b01e783d430eeaf7a2f87e0a57dd0a", size = 7388632, upload-time = "2025-11-05T18:39:42.86Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/64/10/a090475284fc4a71aed40a96f32e44a7fe5bda39687353dd977720b211b6/brotli-1.2.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:3b90b767916ac44e93a8e28ce6adf8d551e43affb512f2377c732d486ac6514e", size = 863089, upload-time = "2025-11-05T18:38:01.181Z" },
- { url = "https://files.pythonhosted.org/packages/03/41/17416630e46c07ac21e378c3464815dd2e120b441e641bc516ac32cc51d2/brotli-1.2.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:6be67c19e0b0c56365c6a76e393b932fb0e78b3b56b711d180dd7013cb1fd984", size = 445442, upload-time = "2025-11-05T18:38:02.434Z" },
- { url = "https://files.pythonhosted.org/packages/24/31/90cc06584deb5d4fcafc0985e37741fc6b9717926a78674bbb3ce018957e/brotli-1.2.0-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:0bbd5b5ccd157ae7913750476d48099aaf507a79841c0d04a9db4415b14842de", size = 1532658, upload-time = "2025-11-05T18:38:03.588Z" },
- { url = "https://files.pythonhosted.org/packages/62/17/33bf0c83bcbc96756dfd712201d87342732fad70bb3472c27e833a44a4f9/brotli-1.2.0-cp310-cp310-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:3f3c908bcc404c90c77d5a073e55271a0a498f4e0756e48127c35d91cf155947", size = 1631241, upload-time = "2025-11-05T18:38:04.582Z" },
- { url = "https://files.pythonhosted.org/packages/48/10/f47854a1917b62efe29bc98ac18e5d4f71df03f629184575b862ef2e743b/brotli-1.2.0-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:1b557b29782a643420e08d75aea889462a4a8796e9a6cf5621ab05a3f7da8ef2", size = 1424307, upload-time = "2025-11-05T18:38:05.587Z" },
- { url = "https://files.pythonhosted.org/packages/e4/b7/f88eb461719259c17483484ea8456925ee057897f8e64487d76e24e5e38d/brotli-1.2.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:81da1b229b1889f25adadc929aeb9dbc4e922bd18561b65b08dd9343cfccca84", size = 1488208, upload-time = "2025-11-05T18:38:06.613Z" },
- { url = "https://files.pythonhosted.org/packages/26/59/41bbcb983a0c48b0b8004203e74706c6b6e99a04f3c7ca6f4f41f364db50/brotli-1.2.0-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:ff09cd8c5eec3b9d02d2408db41be150d8891c5566addce57513bf546e3d6c6d", size = 1597574, upload-time = "2025-11-05T18:38:07.838Z" },
- { url = "https://files.pythonhosted.org/packages/8e/e6/8c89c3bdabbe802febb4c5c6ca224a395e97913b5df0dff11b54f23c1788/brotli-1.2.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:a1778532b978d2536e79c05dac2d8cd857f6c55cd0c95ace5b03740824e0e2f1", size = 1492109, upload-time = "2025-11-05T18:38:08.816Z" },
- { url = "https://files.pythonhosted.org/packages/ed/9a/4b19d4310b2dbd545c0c33f176b0528fa68c3cd0754e34b2f2bcf56548ae/brotli-1.2.0-cp310-cp310-win32.whl", hash = "sha256:b232029d100d393ae3c603c8ffd7e3fe6f798c5e28ddca5feabb8e8fdb732997", size = 334461, upload-time = "2025-11-05T18:38:10.729Z" },
- { url = "https://files.pythonhosted.org/packages/ac/39/70981d9f47705e3c2b95c0847dfa3e7a37aa3b7c6030aedc4873081ed005/brotli-1.2.0-cp310-cp310-win_amd64.whl", hash = "sha256:ef87b8ab2704da227e83a246356a2b179ef826f550f794b2c52cddb4efbd0196", size = 369035, upload-time = "2025-11-05T18:38:11.827Z" },
- { url = "https://files.pythonhosted.org/packages/7a/ef/f285668811a9e1ddb47a18cb0b437d5fc2760d537a2fe8a57875ad6f8448/brotli-1.2.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:15b33fe93cedc4caaff8a0bd1eb7e3dab1c61bb22a0bf5bdfdfd97cd7da79744", size = 863110, upload-time = "2025-11-05T18:38:12.978Z" },
- { url = "https://files.pythonhosted.org/packages/50/62/a3b77593587010c789a9d6eaa527c79e0848b7b860402cc64bc0bc28a86c/brotli-1.2.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:898be2be399c221d2671d29eed26b6b2713a02c2119168ed914e7d00ceadb56f", size = 445438, upload-time = "2025-11-05T18:38:14.208Z" },
- { url = "https://files.pythonhosted.org/packages/cd/e1/7fadd47f40ce5549dc44493877db40292277db373da5053aff181656e16e/brotli-1.2.0-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:350c8348f0e76fff0a0fd6c26755d2653863279d086d3aa2c290a6a7251135dd", size = 1534420, upload-time = "2025-11-05T18:38:15.111Z" },
- { url = "https://files.pythonhosted.org/packages/12/8b/1ed2f64054a5a008a4ccd2f271dbba7a5fb1a3067a99f5ceadedd4c1d5a7/brotli-1.2.0-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:2e1ad3fda65ae0d93fec742a128d72e145c9c7a99ee2fcd667785d99eb25a7fe", size = 1632619, upload-time = "2025-11-05T18:38:16.094Z" },
- { url = "https://files.pythonhosted.org/packages/89/5a/7071a621eb2d052d64efd5da2ef55ecdac7c3b0c6e4f9d519e9c66d987ef/brotli-1.2.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:40d918bce2b427a0c4ba189df7a006ac0c7277c180aee4617d99e9ccaaf59e6a", size = 1426014, upload-time = "2025-11-05T18:38:17.177Z" },
- { url = "https://files.pythonhosted.org/packages/26/6d/0971a8ea435af5156acaaccec1a505f981c9c80227633851f2810abd252a/brotli-1.2.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:2a7f1d03727130fc875448b65b127a9ec5d06d19d0148e7554384229706f9d1b", size = 1489661, upload-time = "2025-11-05T18:38:18.41Z" },
- { url = "https://files.pythonhosted.org/packages/f3/75/c1baca8b4ec6c96a03ef8230fab2a785e35297632f402ebb1e78a1e39116/brotli-1.2.0-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:9c79f57faa25d97900bfb119480806d783fba83cd09ee0b33c17623935b05fa3", size = 1599150, upload-time = "2025-11-05T18:38:19.792Z" },
- { url = "https://files.pythonhosted.org/packages/0d/1a/23fcfee1c324fd48a63d7ebf4bac3a4115bdb1b00e600f80f727d850b1ae/brotli-1.2.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:844a8ceb8483fefafc412f85c14f2aae2fb69567bf2a0de53cdb88b73e7c43ae", size = 1493505, upload-time = "2025-11-05T18:38:20.913Z" },
- { url = "https://files.pythonhosted.org/packages/36/e5/12904bbd36afeef53d45a84881a4810ae8810ad7e328a971ebbfd760a0b3/brotli-1.2.0-cp311-cp311-win32.whl", hash = "sha256:aa47441fa3026543513139cb8926a92a8e305ee9c71a6209ef7a97d91640ea03", size = 334451, upload-time = "2025-11-05T18:38:21.94Z" },
- { url = "https://files.pythonhosted.org/packages/02/8b/ecb5761b989629a4758c394b9301607a5880de61ee2ee5fe104b87149ebc/brotli-1.2.0-cp311-cp311-win_amd64.whl", hash = "sha256:022426c9e99fd65d9475dce5c195526f04bb8be8907607e27e747893f6ee3e24", size = 369035, upload-time = "2025-11-05T18:38:22.941Z" },
- { url = "https://files.pythonhosted.org/packages/11/ee/b0a11ab2315c69bb9b45a2aaed022499c9c24a205c3a49c3513b541a7967/brotli-1.2.0-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:35d382625778834a7f3061b15423919aa03e4f5da34ac8e02c074e4b75ab4f84", size = 861543, upload-time = "2025-11-05T18:38:24.183Z" },
- { url = "https://files.pythonhosted.org/packages/e1/2f/29c1459513cd35828e25531ebfcbf3e92a5e49f560b1777a9af7203eb46e/brotli-1.2.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:7a61c06b334bd99bc5ae84f1eeb36bfe01400264b3c352f968c6e30a10f9d08b", size = 444288, upload-time = "2025-11-05T18:38:25.139Z" },
- { url = "https://files.pythonhosted.org/packages/3d/6f/feba03130d5fceadfa3a1bb102cb14650798c848b1df2a808356f939bb16/brotli-1.2.0-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:acec55bb7c90f1dfc476126f9711a8e81c9af7fb617409a9ee2953115343f08d", size = 1528071, upload-time = "2025-11-05T18:38:26.081Z" },
- { url = "https://files.pythonhosted.org/packages/2b/38/f3abb554eee089bd15471057ba85f47e53a44a462cfce265d9bf7088eb09/brotli-1.2.0-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:260d3692396e1895c5034f204f0db022c056f9e2ac841593a4cf9426e2a3faca", size = 1626913, upload-time = "2025-11-05T18:38:27.284Z" },
- { url = "https://files.pythonhosted.org/packages/03/a7/03aa61fbc3c5cbf99b44d158665f9b0dd3d8059be16c460208d9e385c837/brotli-1.2.0-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:072e7624b1fc4d601036ab3f4f27942ef772887e876beff0301d261210bca97f", size = 1419762, upload-time = "2025-11-05T18:38:28.295Z" },
- { url = "https://files.pythonhosted.org/packages/21/1b/0374a89ee27d152a5069c356c96b93afd1b94eae83f1e004b57eb6ce2f10/brotli-1.2.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:adedc4a67e15327dfdd04884873c6d5a01d3e3b6f61406f99b1ed4865a2f6d28", size = 1484494, upload-time = "2025-11-05T18:38:29.29Z" },
- { url = "https://files.pythonhosted.org/packages/cf/57/69d4fe84a67aef4f524dcd075c6eee868d7850e85bf01d778a857d8dbe0a/brotli-1.2.0-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:7a47ce5c2288702e09dc22a44d0ee6152f2c7eda97b3c8482d826a1f3cfc7da7", size = 1593302, upload-time = "2025-11-05T18:38:30.639Z" },
- { url = "https://files.pythonhosted.org/packages/d5/3b/39e13ce78a8e9a621c5df3aeb5fd181fcc8caba8c48a194cd629771f6828/brotli-1.2.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:af43b8711a8264bb4e7d6d9a6d004c3a2019c04c01127a868709ec29962b6036", size = 1487913, upload-time = "2025-11-05T18:38:31.618Z" },
- { url = "https://files.pythonhosted.org/packages/62/28/4d00cb9bd76a6357a66fcd54b4b6d70288385584063f4b07884c1e7286ac/brotli-1.2.0-cp312-cp312-win32.whl", hash = "sha256:e99befa0b48f3cd293dafeacdd0d191804d105d279e0b387a32054c1180f3161", size = 334362, upload-time = "2025-11-05T18:38:32.939Z" },
- { url = "https://files.pythonhosted.org/packages/1c/4e/bc1dcac9498859d5e353c9b153627a3752868a9d5f05ce8dedd81a2354ab/brotli-1.2.0-cp312-cp312-win_amd64.whl", hash = "sha256:b35c13ce241abdd44cb8ca70683f20c0c079728a36a996297adb5334adfc1c44", size = 369115, upload-time = "2025-11-05T18:38:33.765Z" },
- { url = "https://files.pythonhosted.org/packages/6c/d4/4ad5432ac98c73096159d9ce7ffeb82d151c2ac84adcc6168e476bb54674/brotli-1.2.0-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:9e5825ba2c9998375530504578fd4d5d1059d09621a02065d1b6bfc41a8e05ab", size = 861523, upload-time = "2025-11-05T18:38:34.67Z" },
- { url = "https://files.pythonhosted.org/packages/91/9f/9cc5bd03ee68a85dc4bc89114f7067c056a3c14b3d95f171918c088bf88d/brotli-1.2.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:0cf8c3b8ba93d496b2fae778039e2f5ecc7cff99df84df337ca31d8f2252896c", size = 444289, upload-time = "2025-11-05T18:38:35.6Z" },
- { url = "https://files.pythonhosted.org/packages/2e/b6/fe84227c56a865d16a6614e2c4722864b380cb14b13f3e6bef441e73a85a/brotli-1.2.0-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c8565e3cdc1808b1a34714b553b262c5de5fbda202285782173ec137fd13709f", size = 1528076, upload-time = "2025-11-05T18:38:36.639Z" },
- { url = "https://files.pythonhosted.org/packages/55/de/de4ae0aaca06c790371cf6e7ee93a024f6b4bb0568727da8c3de112e726c/brotli-1.2.0-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:26e8d3ecb0ee458a9804f47f21b74845cc823fd1bb19f02272be70774f56e2a6", size = 1626880, upload-time = "2025-11-05T18:38:37.623Z" },
- { url = "https://files.pythonhosted.org/packages/5f/16/a1b22cbea436642e071adcaf8d4b350a2ad02f5e0ad0da879a1be16188a0/brotli-1.2.0-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:67a91c5187e1eec76a61625c77a6c8c785650f5b576ca732bd33ef58b0dff49c", size = 1419737, upload-time = "2025-11-05T18:38:38.729Z" },
- { url = "https://files.pythonhosted.org/packages/46/63/c968a97cbb3bdbf7f974ef5a6ab467a2879b82afbc5ffb65b8acbb744f95/brotli-1.2.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:4ecdb3b6dc36e6d6e14d3a1bdc6c1057c8cbf80db04031d566eb6080ce283a48", size = 1484440, upload-time = "2025-11-05T18:38:39.916Z" },
- { url = "https://files.pythonhosted.org/packages/06/9d/102c67ea5c9fc171f423e8399e585dabea29b5bc79b05572891e70013cdd/brotli-1.2.0-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:3e1b35d56856f3ed326b140d3c6d9db91740f22e14b06e840fe4bb1923439a18", size = 1593313, upload-time = "2025-11-05T18:38:41.24Z" },
- { url = "https://files.pythonhosted.org/packages/9e/4a/9526d14fa6b87bc827ba1755a8440e214ff90de03095cacd78a64abe2b7d/brotli-1.2.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:54a50a9dad16b32136b2241ddea9e4df159b41247b2ce6aac0b3276a66a8f1e5", size = 1487945, upload-time = "2025-11-05T18:38:42.277Z" },
- { url = "https://files.pythonhosted.org/packages/5b/e8/3fe1ffed70cbef83c5236166acaed7bb9c766509b157854c80e2f766b38c/brotli-1.2.0-cp313-cp313-win32.whl", hash = "sha256:1b1d6a4efedd53671c793be6dd760fcf2107da3a52331ad9ea429edf0902f27a", size = 334368, upload-time = "2025-11-05T18:38:43.345Z" },
- { url = "https://files.pythonhosted.org/packages/ff/91/e739587be970a113b37b821eae8097aac5a48e5f0eca438c22e4c7dd8648/brotli-1.2.0-cp313-cp313-win_amd64.whl", hash = "sha256:b63daa43d82f0cdabf98dee215b375b4058cce72871fd07934f179885aad16e8", size = 369116, upload-time = "2025-11-05T18:38:44.609Z" },
- { url = "https://files.pythonhosted.org/packages/17/e1/298c2ddf786bb7347a1cd71d63a347a79e5712a7c0cba9e3c3458ebd976f/brotli-1.2.0-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:6c12dad5cd04530323e723787ff762bac749a7b256a5bece32b2243dd5c27b21", size = 863080, upload-time = "2025-11-05T18:38:45.503Z" },
- { url = "https://files.pythonhosted.org/packages/84/0c/aac98e286ba66868b2b3b50338ffbd85a35c7122e9531a73a37a29763d38/brotli-1.2.0-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:3219bd9e69868e57183316ee19c84e03e8f8b5a1d1f2667e1aa8c2f91cb061ac", size = 445453, upload-time = "2025-11-05T18:38:46.433Z" },
- { url = "https://files.pythonhosted.org/packages/ec/f1/0ca1f3f99ae300372635ab3fe2f7a79fa335fee3d874fa7f9e68575e0e62/brotli-1.2.0-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:963a08f3bebd8b75ac57661045402da15991468a621f014be54e50f53a58d19e", size = 1528168, upload-time = "2025-11-05T18:38:47.371Z" },
- { url = "https://files.pythonhosted.org/packages/d6/a6/2ebfc8f766d46df8d3e65b880a2e220732395e6d7dc312c1e1244b0f074a/brotli-1.2.0-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:9322b9f8656782414b37e6af884146869d46ab85158201d82bab9abbcb971dc7", size = 1627098, upload-time = "2025-11-05T18:38:48.385Z" },
- { url = "https://files.pythonhosted.org/packages/f3/2f/0976d5b097ff8a22163b10617f76b2557f15f0f39d6a0fe1f02b1a53e92b/brotli-1.2.0-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:cf9cba6f5b78a2071ec6fb1e7bd39acf35071d90a81231d67e92d637776a6a63", size = 1419861, upload-time = "2025-11-05T18:38:49.372Z" },
- { url = "https://files.pythonhosted.org/packages/9c/97/d76df7176a2ce7616ff94c1fb72d307c9a30d2189fe877f3dd99af00ea5a/brotli-1.2.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:7547369c4392b47d30a3467fe8c3330b4f2e0f7730e45e3103d7d636678a808b", size = 1484594, upload-time = "2025-11-05T18:38:50.655Z" },
- { url = "https://files.pythonhosted.org/packages/d3/93/14cf0b1216f43df5609f5b272050b0abd219e0b54ea80b47cef9867b45e7/brotli-1.2.0-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:fc1530af5c3c275b8524f2e24841cbe2599d74462455e9bae5109e9ff42e9361", size = 1593455, upload-time = "2025-11-05T18:38:51.624Z" },
- { url = "https://files.pythonhosted.org/packages/b3/73/3183c9e41ca755713bdf2cc1d0810df742c09484e2e1ddd693bee53877c1/brotli-1.2.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:d2d085ded05278d1c7f65560aae97b3160aeb2ea2c0b3e26204856beccb60888", size = 1488164, upload-time = "2025-11-05T18:38:53.079Z" },
- { url = "https://files.pythonhosted.org/packages/64/6a/0c78d8f3a582859236482fd9fa86a65a60328a00983006bcf6d83b7b2253/brotli-1.2.0-cp314-cp314-win32.whl", hash = "sha256:832c115a020e463c2f67664560449a7bea26b0c1fdd690352addad6d0a08714d", size = 339280, upload-time = "2025-11-05T18:38:54.02Z" },
- { url = "https://files.pythonhosted.org/packages/f5/10/56978295c14794b2c12007b07f3e41ba26acda9257457d7085b0bb3bb90c/brotli-1.2.0-cp314-cp314-win_amd64.whl", hash = "sha256:e7c0af964e0b4e3412a0ebf341ea26ec767fa0b4cf81abb5e897c9338b5ad6a3", size = 375639, upload-time = "2025-11-05T18:38:55.67Z" },
-]
-
[[package]]
name = "build"
version = "1.4.0"
@@ -1325,15 +1202,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/4e/eb/c96d64137e29ae17d83ad2552470bafe3a7a915e85434d9942077d7fd011/feedparser-6.0.12-py3-none-any.whl", hash = "sha256:6bbff10f5a52662c00a2e3f86a38928c37c48f77b3c511aedcd51de933549324", size = 81480, upload-time = "2025-09-10T13:33:58.022Z" },
]
-[[package]]
-name = "ffmpy"
-version = "1.0.0"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/7d/d2/1c4c582d71bcc65c76fa69fab85de6257d50fdf6fd4a2317c53917e9a581/ffmpy-1.0.0.tar.gz", hash = "sha256:b12932e95435c8820f1cd041024402765f821971e4bae753b327fc02a6e12f8b", size = 5101, upload-time = "2025-11-11T06:24:23.856Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/55/56/dd3669eccebb6d8ac81e624542ebd53fe6f08e1b8f2f8d50aeb7e3b83f99/ffmpy-1.0.0-py3-none-any.whl", hash = "sha256:5640e5f0fd03fb6236d0e119b16ccf6522db1c826fdf35dcb87087b60fd7504f", size = 5614, upload-time = "2025-11-11T06:24:22.818Z" },
-]
-
[[package]]
name = "filelock"
version = "3.25.0"
@@ -1562,64 +1430,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/69/28/23eea8acd65972bbfe295ce3666b28ac510dfcb115fac089d3edb0feb00a/googleapis_common_protos-1.73.0-py3-none-any.whl", hash = "sha256:dfdaaa2e860f242046be561e6d6cb5c5f1541ae02cfbcb034371aadb2942b4e8", size = 297578, upload-time = "2026-03-06T21:52:33.933Z" },
]
-[[package]]
-name = "gradio"
-version = "6.9.0"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
- { name = "aiofiles" },
- { name = "anyio" },
- { name = "audioop-lts", marker = "python_full_version >= '3.13'" },
- { name = "brotli" },
- { name = "fastapi" },
- { name = "ffmpy" },
- { name = "gradio-client" },
- { name = "groovy" },
- { name = "httpx" },
- { name = "huggingface-hub" },
- { name = "jinja2" },
- { name = "markupsafe" },
- { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" },
- { name = "numpy", version = "2.4.3", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.11'" },
- { name = "orjson" },
- { name = "packaging" },
- { name = "pandas", version = "2.3.3", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" },
- { name = "pandas", version = "3.0.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.11'" },
- { name = "pillow" },
- { name = "pydantic" },
- { name = "pydub" },
- { name = "python-multipart" },
- { name = "pytz" },
- { name = "pyyaml" },
- { name = "safehttpx" },
- { name = "semantic-version" },
- { name = "starlette" },
- { name = "tomlkit" },
- { name = "typer" },
- { name = "typing-extensions" },
- { name = "uvicorn" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/bd/83/29bdbf94b212512e3c775482d390f5b699a72d71a2c431dea367a6e45a37/gradio-6.9.0.tar.gz", hash = "sha256:593e60e33233f3586452ebfa9f741817c5ae849a98cc70945f3ccb8dc895eb22", size = 57904480, upload-time = "2026-03-06T17:44:26.025Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/b3/8b/dc357ab966544e4dc898a2fee326d755c5f54da82af71a1a802e3476e78e/gradio-6.9.0-py3-none-any.whl", hash = "sha256:c173dd330c9247002a42222c85d76c0ecee65437eff808084e360862e7bbd24f", size = 42940853, upload-time = "2026-03-06T17:44:22.009Z" },
-]
-
-[[package]]
-name = "gradio-client"
-version = "2.3.0"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
- { name = "fsspec" },
- { name = "httpx" },
- { name = "huggingface-hub" },
- { name = "packaging" },
- { name = "typing-extensions" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/97/d2/de2037f5eff13a5145cdf6982fd34c9735f0806e8a2ee5d4bfe9a7d25a54/gradio_client-2.3.0.tar.gz", hash = "sha256:1c700dc60e65bae4386ba7cf3732b9f9d5bcf5fb8eb451df3944fe092d7d9a29", size = 57552, upload-time = "2026-03-06T17:44:38.247Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/99/6a/41752781399811afbf8ac858f63c20eff354ed35169daa39604aefced4e8/gradio_client-2.3.0-py3-none-any.whl", hash = "sha256:9ec51a927888fc188e123a0ac5ad341d9265b325539a399554d1fc2604942e74", size = 58531, upload-time = "2026-03-06T17:44:36.961Z" },
-]
-
[[package]]
name = "greenlet"
version = "3.3.2"
@@ -1687,15 +1497,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/40/79/29f1373b2ce1eec37c03aefbc17194c2470d8b61ede288e5043231825999/grep_ast-0.9.0-py3-none-any.whl", hash = "sha256:a3973dca99f1abc026a01bbbc70e00a63860c8ff94a56182ff18b089836826d7", size = 13918, upload-time = "2025-05-08T01:08:27.481Z" },
]
-[[package]]
-name = "groovy"
-version = "0.1.2"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/52/36/bbdede67400277bef33d3ec0e6a31750da972c469f75966b4930c753218f/groovy-0.1.2.tar.gz", hash = "sha256:25c1dc09b3f9d7e292458aa762c6beb96ea037071bf5e917fc81fb78d2231083", size = 17325, upload-time = "2025-02-28T20:24:56.068Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/28/27/3d6dcadc8a3214d8522c1e7f6a19554e33659be44546d44a2f7572ac7d2a/groovy-0.1.2-py3-none-any.whl", hash = "sha256:7f7975bab18c729a257a8b1ae9dcd70b7cafb1720481beae47719af57c35fa64", size = 14090, upload-time = "2025-02-28T20:24:55.152Z" },
-]
-
[[package]]
name = "grpcio"
version = "1.80.0"
@@ -3685,7 +3486,6 @@ bot = [
{ name = "ddgs" },
{ name = "dingtalk-stream" },
{ name = "fusepy" },
- { name = "gradio" },
{ name = "html2text" },
{ name = "httpx", extra = ["socks"] },
{ name = "langfuse" },
@@ -3797,7 +3597,6 @@ requires-dist = [
{ name = "fusepy", marker = "extra == 'bot'", specifier = ">=3.0.1" },
{ name = "google-genai", marker = "extra == 'gemini'", specifier = ">=1.0.0" },
{ name = "google-genai", marker = "extra == 'gemini-async'", specifier = ">=1.0.0" },
- { name = "gradio", marker = "extra == 'bot'", specifier = ">=6.6.0" },
{ name = "grep-ast", specifier = ">=0.9.0" },
{ name = "html2text", marker = "extra == 'bot'", specifier = ">=2020.1.16" },
{ name = "httpx", specifier = ">=0.25.0" },
@@ -4846,15 +4645,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/66/0e/9ee7bc0b48ec45d93b302fa2d787830dca4dc454d31a237faa5815995988/PyDispatcher-2.0.7-py3-none-any.whl", hash = "sha256:96543bea04115ffde08f851e1d45cacbfd1ee866ac42127d9b476dc5aefa7de0", size = 12040, upload-time = "2023-02-17T20:11:11.991Z" },
]
-[[package]]
-name = "pydub"
-version = "0.25.1"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/fe/9a/e6bca0eed82db26562c73b5076539a4a08d3cffd19c3cc5913a3e61145fd/pydub-0.25.1.tar.gz", hash = "sha256:980a33ce9949cab2a569606b65674d748ecbca4f0796887fd6f46173a7b0d30f", size = 38326, upload-time = "2021-03-10T02:09:54.659Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/a6/53/d78dc063216e62fc55f6b2eebb447f6a4b0a59f55c8406376f76bf959b08/pydub-0.25.1-py2.py3-none-any.whl", hash = "sha256:65617e33033874b59d87db603aa1ed450633288aefead953b30bded59cb599a6", size = 32327, upload-time = "2021-03-10T02:09:53.503Z" },
-]
-
[[package]]
name = "pygments"
version = "2.19.2"
@@ -5691,18 +5481,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/fc/51/727abb13f44c1fcf6d145979e1535a35794db0f6e450a0cb46aa24732fe2/s3transfer-0.16.0-py3-none-any.whl", hash = "sha256:18e25d66fed509e3868dc1572b3f427ff947dd2c56f844a5bf09481ad3f3b2fe", size = 86830, upload-time = "2025-12-01T02:30:57.729Z" },
]
-[[package]]
-name = "safehttpx"
-version = "0.1.7"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
- { name = "httpx" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/89/d1/4282284d9cf1ee873607a46442da977fc3c985059315ab23610be31d5885/safehttpx-0.1.7.tar.gz", hash = "sha256:db201c0978c41eddb8bb480f3eee59dd67304fdd91646035e9d9a720049a9d23", size = 10385, upload-time = "2025-10-24T18:30:09.783Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/2e/a3/0f0b7d78e2f1eb9e8e1afbff1d2bff8d60144aee17aca51c065b516743dd/safehttpx-0.1.7-py3-none-any.whl", hash = "sha256:c4f4a162db6993464d7ca3d7cc4af0ffc6515a606dfd220b9f82c6945d869cde", size = 8959, upload-time = "2025-10-24T18:30:08.733Z" },
-]
-
[[package]]
name = "scrapy"
version = "2.16.0"
@@ -5732,15 +5510,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/1d/c9/7cc7631ca85c08b7e1162e1e08ecb0c139f8f640cc403257ac500a8e50fe/scrapy-2.16.0-py3-none-any.whl", hash = "sha256:fcb83db5500743503b1fea4d55c81aac056b15481d0aad46b6f929d324d9bcf5", size = 344254, upload-time = "2026-05-19T12:29:17.206Z" },
]
-[[package]]
-name = "semantic-version"
-version = "2.10.0"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/7d/31/f2289ce78b9b473d582568c234e104d2a342fd658cc288a7553d83bb8595/semantic_version-2.10.0.tar.gz", hash = "sha256:bdabb6d336998cbb378d4b9db3a4b56a1e3235701dc05ea2690d9a997ed5041c", size = 52289, upload-time = "2022-05-26T13:35:23.454Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/6a/23/8146aad7d88f4fcb3a6218f41a60f6c2d4e3a72de72da1825dc7c8f7877c/semantic_version-2.10.0-py2.py3-none-any.whl", hash = "sha256:de78a3b8e0feda74cabc54aab2da702113e33ac9d9eb9d2389bcf1f58b7d9177", size = 15552, upload-time = "2022-05-26T13:35:21.206Z" },
-]
-
[[package]]
name = "service-identity"
version = "26.1.0"
@@ -6335,15 +6104,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/23/d1/136eb2cb77520a31e1f64cbae9d33ec6df0d78bdf4160398e86eec8a8754/tomli-2.4.0-py3-none-any.whl", hash = "sha256:1f776e7d669ebceb01dee46484485f43a4048746235e683bcdffacdf1fb4785a", size = 14477, upload-time = "2026-01-11T11:22:37.446Z" },
]
-[[package]]
-name = "tomlkit"
-version = "0.13.3"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/cc/18/0bbf3884e9eaa38819ebe46a7bd25dcd56b67434402b66a58c4b8e552575/tomlkit-0.13.3.tar.gz", hash = "sha256:430cf247ee57df2b94ee3fbe588e71d362a941ebb545dec29b53961d61add2a1", size = 185207, upload-time = "2025-06-05T07:13:44.947Z" }
-wheels = [
- { url = "https://files.pythonhosted.org/packages/bd/75/8539d011f6be8e29f339c42e633aae3cb73bffa95dd0f9adec09b9c58e85/tomlkit-0.13.3-py3-none-any.whl", hash = "sha256:c89c649d79ee40629a9fda55f8ace8c6a1b42deb912b2a8fd8d942ddadb606b0", size = 38901, upload-time = "2025-06-05T07:13:43.546Z" },
-]
-
[[package]]
name = "tqdm"
version = "4.67.3"