Files
CC-Switch/src-tauri/src/proxy/handler_context.rs
T
YoVinchen e6f18ba801 Feat/usage model extraction (#455)
* feat(proxy): extract model name from API response for accurate usage tracking

- Add model field extraction in TokenUsage parsing for Claude, OpenAI, and Codex
- Prioritize response model over request model in usage logging
- Update model extractors to use parsed usage.model first
- Add tests for model extraction in stream and non-stream responses

* feat(proxy): implement streaming timeout control with validation

- Add first byte timeout (0 or 1-180s) for streaming requests
- Add idle timeout (0 or 60-600s) for streaming data gaps
- Add non-streaming timeout (0 or 60-1800s) for total request
- Implement timeout logic in response processor
- Add 1800s global timeout fallback when disabled
- Add database schema migration for timeout fields
- Add i18n translations for timeout settings

* feat(proxy): add model mapping module for provider-based model substitution

- Add model_mapper.rs with ModelMapping struct to extract model configs from Provider
- Support ANTHROPIC_MODEL, ANTHROPIC_REASONING_MODEL, and default models for haiku/sonnet/opus
- Implement thinking mode detection for reasoning model priority
- Include comprehensive unit tests for all mapping scenarios

* fix(proxy): bypass circuit breaker for single provider scenario

When failover is disabled (single provider), circuit breaker open state
would block all requests causing poor UX. Now bypasses circuit breaker
check in this scenario. Also integrates model mapping into request flow.

* feat(ui): add reasoning model field to Claude provider form

Add ANTHROPIC_REASONING_MODEL configuration field for Claude providers,
allowing users to specify a dedicated model for thinking/reasoning tasks.

* feat(proxy): add openrouter_compat_mode for optional format conversion

Add configurable OpenRouter compatibility mode that enables Anthropic to
OpenAI format conversion. When enabled, rewrites endpoint to /v1/chat/completions
and transforms request/response formats. Defaults to enabled for OpenRouter.

* feat(ui): add OpenRouter compatibility mode toggle

Add UI toggle for OpenRouter providers to enable/disable compatibility
mode which uses OpenAI Chat Completions format with SSE conversion.

* feat(stream-check): use provider-configured model for health checks

Extract model from provider's settings_config (ANTHROPIC_MODEL, GEMINI_MODEL,
or Codex config.toml) instead of always using default test models.

* refactor(ui): remove timeout settings from AutoFailoverConfigPanel

Remove streaming/non-streaming timeout configuration from failover panel
as these settings have been moved to a dedicated location.

* refactor(database): migrate proxy_config to per-app three-row structure

Replace singleton proxy_config table with app_type primary key structure,
allowing independent proxy settings for Claude, Codex, and Gemini.
Add GlobalProxyConfig queries and per-app config management in DAO layer.

* feat(proxy): add GlobalProxyConfig and AppProxyConfig types

Add new type definitions for the refactored proxy configuration:
- GlobalProxyConfig: shared settings (enabled, address, port, logging)
- AppProxyConfig: per-app settings (failover, timeouts, circuit breaker)

* refactor(proxy): update service layer for per-app config structure

Adapt proxy service, handler context, and provider router to use
the new per-app configuration model. Read enabled/timeout settings
from proxy_config table instead of settings table.

* feat(commands): add global and per-app proxy config commands

Add new Tauri commands for the refactored proxy configuration:
- get_global_proxy_config / update_global_proxy_config
- get_proxy_config_for_app / update_proxy_config_for_app
Update startup restore logic to read from proxy_config table.

* feat(api): add frontend API and Query hooks for proxy config

Add TypeScript wrappers and TanStack Query hooks for:
- Global proxy config (address, port, logging)
- Per-app proxy config (failover, timeouts, circuit breaker)
- Proxy takeover status management

* refactor(ui): redesign proxy panel with inline config controls

Replace ProxySettingsDialog with inline controls in ProxyPanel.
Add per-app takeover switches and global address/port settings.
Simplify AutoFailoverConfigPanel by removing timeout settings.

* feat(i18n): add proxy takeover translations and update types

Add i18n strings for proxy takeover status in zh/en/ja.
Update TypeScript types for GlobalProxyConfig and AppProxyConfig.

* refactor(proxy): load circuit breaker config per-app instead of globally

Extract app_type from router key and read circuit breaker settings
from the corresponding proxy_config row for each application.
2025-12-25 10:40:11 +08:00

188 lines
6.1 KiB
Rust
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
//! 请求上下文模块
//!
//! 提供请求生命周期的上下文管理,封装通用初始化逻辑
use crate::app_config::AppType;
use crate::provider::Provider;
use crate::proxy::{
forwarder::RequestForwarder, server::ProxyState, types::AppProxyConfig, ProxyError,
};
use std::time::Instant;
/// 流式超时配置
#[derive(Debug, Clone, Copy)]
pub struct StreamingTimeoutConfig {
/// 首字节超时(秒),0 表示禁用
pub first_byte_timeout: u64,
/// 静默期超时(秒),0 表示禁用
pub idle_timeout: u64,
}
/// 请求上下文
///
/// 贯穿整个请求生命周期,包含:
/// - 计时信息
/// - 应用级代理配置(per-app
/// - 选中的 Provider 列表(用于故障转移)
/// - 请求模型名称
/// - 日志标签
pub struct RequestContext {
/// 请求开始时间
pub start_time: Instant,
/// 应用级代理配置(per-app,包含重试次数和超时配置)
pub app_config: AppProxyConfig,
/// 选中的 Provider(故障转移链的第一个)
pub provider: Provider,
/// 完整的 Provider 列表(用于故障转移)
providers: Vec<Provider>,
/// 请求开始时的“当前供应商”(用于判断是否需要同步 UI/托盘)
///
/// 这里使用本地 settings 的设备级 current provider。
/// 代理模式下如果实际使用的 provider 与此不一致,会触发切换以确保 UI 始终准确。
pub current_provider_id: String,
/// 请求中的模型名称
pub request_model: String,
/// 日志标签(如 "Claude"、"Codex"、"Gemini"
pub tag: &'static str,
/// 应用类型字符串(如 "claude"、"codex"、"gemini"
pub app_type_str: &'static str,
/// 应用类型(预留,目前通过 app_type_str 使用)
#[allow(dead_code)]
pub app_type: AppType,
}
impl RequestContext {
/// 创建请求上下文
///
/// # Arguments
/// * `state` - 代理服务器状态
/// * `body` - 请求体 JSON
/// * `app_type` - 应用类型
/// * `tag` - 日志标签
/// * `app_type_str` - 应用类型字符串
///
/// # Errors
/// 返回 `ProxyError` 如果 Provider 选择失败
pub async fn new(
state: &ProxyState,
body: &serde_json::Value,
app_type: AppType,
tag: &'static str,
app_type_str: &'static str,
) -> Result<Self, ProxyError> {
let start_time = Instant::now();
// 从数据库读取应用级代理配置(per-app)
let app_config = state
.db
.get_proxy_config_for_app(app_type_str)
.await
.map_err(|e| ProxyError::DatabaseError(e.to_string()))?;
let current_provider_id =
crate::settings::get_current_provider(&app_type).unwrap_or_default();
// 从请求体提取模型名称
let request_model = body
.get("model")
.and_then(|m| m.as_str())
.unwrap_or("unknown")
.to_string();
// 使用共享的 ProviderRouter 选择 Provider(熔断器状态跨请求保持)
// 注意:只在这里调用一次,结果传递给 forwarder,避免重复消耗 HalfOpen 名额
let providers = state
.provider_router
.select_providers(app_type_str)
.await
.map_err(|e| ProxyError::DatabaseError(e.to_string()))?;
let provider = providers
.first()
.cloned()
.ok_or(ProxyError::NoAvailableProvider)?;
log::info!(
"[{}] Provider: {}, model: {}, failover chain: {} providers",
tag,
provider.name,
request_model,
providers.len()
);
Ok(Self {
start_time,
app_config,
provider,
providers,
current_provider_id,
request_model,
tag,
app_type_str,
app_type,
})
}
/// 从 URI 提取模型名称(Gemini 专用)
///
/// Gemini API 的模型名称在 URI 中,格式如:
/// `/v1beta/models/gemini-pro:generateContent`
pub fn with_model_from_uri(mut self, uri: &axum::http::Uri) -> Self {
let endpoint = uri
.path_and_query()
.map(|pq| pq.as_str())
.unwrap_or(uri.path());
self.request_model = endpoint
.split('/')
.find(|s| s.starts_with("models/"))
.and_then(|s| s.strip_prefix("models/"))
.map(|s| s.split(':').next().unwrap_or(s))
.unwrap_or("unknown")
.to_string();
log::info!("[{}] 从 URI 提取模型: {}", self.tag, self.request_model);
self
}
/// 创建 RequestForwarder
///
/// 使用共享的 ProviderRouter,确保熔断器状态跨请求保持
pub fn create_forwarder(&self, state: &ProxyState) -> RequestForwarder {
RequestForwarder::new(
state.provider_router.clone(),
self.app_config.non_streaming_timeout as u64,
self.app_config.max_retries as u8,
state.status.clone(),
state.current_providers.clone(),
state.failover_manager.clone(),
state.app_handle.clone(),
self.current_provider_id.clone(),
self.app_config.streaming_first_byte_timeout as u64,
self.app_config.streaming_idle_timeout as u64,
)
}
/// 获取 Provider 列表(用于故障转移)
///
/// 返回在创建上下文时已选择的 providers,避免重复调用 select_providers()
pub fn get_providers(&self) -> Vec<Provider> {
self.providers.clone()
}
/// 计算请求延迟(毫秒)
#[inline]
pub fn latency_ms(&self) -> u64 {
self.start_time.elapsed().as_millis() as u64
}
/// 获取流式超时配置
#[inline]
pub fn streaming_timeout_config(&self) -> StreamingTimeoutConfig {
StreamingTimeoutConfig {
first_byte_timeout: self.app_config.streaming_first_byte_timeout as u64,
idle_timeout: self.app_config.streaming_idle_timeout as u64,
}
}
}