Files
CC-Switch/src-tauri/src/provider.rs
T
Dex Miller 5376ea042b Feat/usage improvements (#508)
* i18n: update cache terminology across all languages

- Change 'Cache Read' to 'Cache Hit' in all languages
- Change 'Cache Write' to 'Cache Creation' in all languages
- Update zh: 缓存读取 → 缓存命中, 缓存写入 → 缓存创建
- Update en: Cache Read → Cache Hit, Cache Write → Cache Creation
- Update ja: キャッシュ読取 → キャッシュヒット, キャッシュ書込 → キャッシュ作成

Affected keys: cacheReadTokens, cacheCreationTokens, cacheReadCost,
cacheWriteCost, cacheRead, cacheWrite

* feat(usage): add cache metrics to trend chart

- Add cache creation tokens visualization (orange line)
- Add cache hit tokens visualization (purple line)
- Add gradient definitions for new cache metrics
- Include cache data in hourly aggregation
- Display cache metrics alongside input/output tokens

This provides better visibility into cache usage patterns over time.

* fix(usage): fix timezone handling in datetime picker

- Add timestampToLocalDatetime() to convert Unix timestamp to local datetime
- Add localDatetimeToTimestamp() with validation for incomplete input
- Fix issue where typing hours/minutes would jump to previous day
- Validate datetime format completeness before conversion
- Use local timezone instead of UTC for datetime-local input

This resolves the issue where users couldn't fine-tune time selection
and the input would jump unexpectedly when editing hours or minutes.

* feat(usage): add auto-refresh for usage statistics

- Add 30-second auto-refresh interval for all usage queries
- Disable background refresh to save resources
- Apply to: summary, trends, provider stats, model stats, request logs
- Queries automatically update when tab is active
- Pause refresh when user switches to another tab

This keeps usage data fresh without manual refresh.

* fix(proxy): improve usage logging and cache token parsing

- Log requests even when usage parsing fails (with default values)
- Add detailed debug logging for usage metrics
- Support cache_read_input_tokens field in Codex responses
- Fallback to input_tokens_details.cached_tokens if needed
- Add test case for cached_tokens in input_tokens_details
- Ensure all requests are tracked in database for analytics

This fixes missing request logs when API responses lack usage data
and improves cache token detection across different response formats.

* style(rust): use inline format args in format! macros

- Replace format!("...", var) with format!("...{var}")
- Update universal provider ID formatting
- Update error message formatting
- Update config.toml generation in Codex provider

Fixes clippy::uninlined_format_args warnings.

* feat(proxy): enhance provider router logging

- Add debug logs for failover queue provider count
- Log circuit breaker state for each provider check
- Add logs for missing current provider scenarios
- Log when no current provider is configured
- Use inline format args for better readability

This improves debugging of provider selection and failover behavior.

* feat(database): update model pricing data

- Update Claude models to full version format (e.g. claude-opus-4-5-20251101)
- Add GPT-5.2 series model pricing (10 models)
- Add GPT-5.1 series model pricing (10 models)
- Add GPT-5 series model pricing (12 models)
- Add Gemini 3 series model pricing (2 models)
- Update Gemini 2.5 series model ID format (use dot separator)
- Unify display names by removing thinking level suffixes

* fix(usage): correct Gemini output token calculation

Fix Gemini API output token parsing to use totalTokenCount - promptTokenCount
instead of candidatesTokenCount alone. This ensures thoughtsTokenCount is
included in output statistics.

- Update from_gemini_response to calculate output from total - input
- Update from_gemini_stream_chunks with same logic for consistency
- Fix from_codex_stream_events to use adjusted token calculation
- Add test case for responses with thoughtsTokenCount
- Update existing tests to match new calculation logic

* fix(usage): correct cache token billing and add Codex format auto-detection

- Avoid double-billing cache tokens by subtracting from input before calculation
- Add smart Codex parser that auto-detects OpenAI vs Codex API format
- Extract model name from Codex responses for accurate tracking

* fix(proxy): improve takeover detection with live config check

- Add live config takeover detection for hot-switch decision
- Rebuild takeover when backup is missing or placeholder remains
- Make detect_takeover_in_live_config_for_app public
- Fix is_takeover_active to use actual takeover status

* refactor(usage): simplify model pricing lookup by removing suffix fallback

Replace complex suffix-stripping fallback with direct prefix/suffix cleanup.
Model IDs are now cleaned by removing vendor prefix (before /) and colon
suffix (after :), then matched exactly against pricing table.

* feat(database): add Chinese AI model pricing data

Add pricing for domestic AI models (CNY/1M tokens):
- Doubao-Seed-Code (ByteDance)
- DeepSeek V3/V3.1/V3.2
- Kimi K2/K2-Thinking/K2-Turbo (Moonshot)
- MiniMax M2/M2.1/M2.1-Lightning
- GLM-4.6/4.7 (Zhipu)
- Mimo V2 Flash (Xiaomi)

Also fix test case to use correct model ID and remove invalid currency column.

* refactor(proxy): improve header forwarding with blacklist approach

Change from whitelist to blacklist mode for request header forwarding.
Only skip headers that will be overridden (auth, host, content-length).
This preserves client's original headers and improves compatibility.

* fix(proxy): bypass timeout and retry configs when failover is disabled

When auto_failover_enabled is false, timeout and retry configurations
should not affect normal request flow. This change ensures:

- create_forwarder: passes 0 for all timeout/retry params when failover
  is disabled, effectively bypassing these checks
- streaming_timeout_config: returns 0 for both first_byte_timeout and
  idle_timeout when failover is disabled

This prevents unnecessary timeout errors and retry attempts when users
have explicitly disabled the failover feature.

* fix(proxy): handle zero value input in failover config fields

* refactor(proxy): remove retry logic and add enabled check for failover

* refactor(proxy): distinguish circuit-open from no-provider errors

* Align usage stats to sliding windows

* feat(proxy): add body and header filtering for upstream requests

* feat(proxy): enable transparent passthrough for headers

- Passthrough anthropic-beta header as-is from client
- Passthrough anthropic-version header from client
- Passthrough client IP headers (x-forwarded-for, x-real-ip) by default
- Filter private params (underscore-prefixed fields) from request body
- No database changes required

* feat(proxy): extract session ID from client requests for logging

- Add SessionIdExtractor to parse session ID from Claude/Codex requests
- Support extraction from metadata.user_id, headers, previous_response_id
- Pass session_id through RequestContext to usage logger
- Enable request correlation by session in proxy_request_logs
2025-12-31 22:57:00 +08:00

458 lines
15 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.
use indexmap::IndexMap;
use serde::{Deserialize, Serialize};
use serde_json::Value;
use std::collections::HashMap;
// SSOT 模式:不再写供应商副本文件
/// 供应商结构体
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct Provider {
pub id: String,
pub name: String,
#[serde(rename = "settingsConfig")]
pub settings_config: Value,
#[serde(skip_serializing_if = "Option::is_none")]
#[serde(rename = "websiteUrl")]
pub website_url: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub category: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
#[serde(rename = "createdAt")]
pub created_at: Option<i64>,
#[serde(skip_serializing_if = "Option::is_none")]
#[serde(rename = "sortIndex")]
pub sort_index: Option<usize>,
/// 备注信息
#[serde(skip_serializing_if = "Option::is_none")]
pub notes: Option<String>,
/// 供应商元数据(不写入 live 配置,仅存于 ~/.cc-switch/config.json
#[serde(skip_serializing_if = "Option::is_none")]
pub meta: Option<ProviderMeta>,
/// 图标名称(如 "openai", "anthropic"
#[serde(skip_serializing_if = "Option::is_none")]
pub icon: Option<String>,
/// 图标颜色(Hex 格式,如 "#00A67E"
#[serde(skip_serializing_if = "Option::is_none")]
#[serde(rename = "iconColor")]
pub icon_color: Option<String>,
/// 是否加入故障转移队列
#[serde(default)]
#[serde(rename = "inFailoverQueue")]
pub in_failover_queue: bool,
}
impl Provider {
/// 从现有ID创建供应商
pub fn with_id(
id: String,
name: String,
settings_config: Value,
website_url: Option<String>,
) -> Self {
Self {
id,
name,
settings_config,
website_url,
category: None,
created_at: None,
sort_index: None,
notes: None,
meta: None,
icon: None,
icon_color: None,
in_failover_queue: false,
}
}
}
/// 供应商管理器
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct ProviderManager {
pub providers: IndexMap<String, Provider>,
pub current: String,
}
/// 用量查询脚本配置
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct UsageScript {
pub enabled: bool,
pub language: String,
pub code: String,
#[serde(skip_serializing_if = "Option::is_none")]
pub timeout: Option<u64>,
/// 用量查询专用的 API Key(通用模板使用)
#[serde(skip_serializing_if = "Option::is_none")]
#[serde(rename = "apiKey")]
pub api_key: Option<String>,
/// 用量查询专用的 Base URL(通用和 NewAPI 模板使用)
#[serde(skip_serializing_if = "Option::is_none")]
#[serde(rename = "baseUrl")]
pub base_url: Option<String>,
/// 访问令牌(用于需要登录的接口,NewAPI 模板使用)
#[serde(skip_serializing_if = "Option::is_none")]
#[serde(rename = "accessToken")]
pub access_token: Option<String>,
/// 用户ID(用于需要用户标识的接口,NewAPI 模板使用)
#[serde(skip_serializing_if = "Option::is_none")]
#[serde(rename = "userId")]
pub user_id: Option<String>,
/// 自动查询间隔(单位:分钟,0 表示禁用自动查询)
#[serde(skip_serializing_if = "Option::is_none")]
#[serde(rename = "autoQueryInterval")]
pub auto_query_interval: Option<u64>,
}
/// 用量数据
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct UsageData {
#[serde(skip_serializing_if = "Option::is_none")]
#[serde(rename = "planName")]
pub plan_name: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub extra: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
#[serde(rename = "isValid")]
pub is_valid: Option<bool>,
#[serde(skip_serializing_if = "Option::is_none")]
#[serde(rename = "invalidMessage")]
pub invalid_message: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub total: Option<f64>,
#[serde(skip_serializing_if = "Option::is_none")]
pub used: Option<f64>,
#[serde(skip_serializing_if = "Option::is_none")]
pub remaining: Option<f64>,
#[serde(skip_serializing_if = "Option::is_none")]
pub unit: Option<String>,
}
/// 用量查询结果(支持多套餐)
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct UsageResult {
pub success: bool,
#[serde(skip_serializing_if = "Option::is_none")]
pub data: Option<Vec<UsageData>>, // 支持返回多个套餐
#[serde(skip_serializing_if = "Option::is_none")]
pub error: Option<String>,
}
/// 供应商元数据
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct ProviderMeta {
/// 自定义端点列表(按 URL 去重存储)
#[serde(default, skip_serializing_if = "HashMap::is_empty")]
pub custom_endpoints: HashMap<String, crate::settings::CustomEndpoint>,
/// 用量查询脚本配置
#[serde(skip_serializing_if = "Option::is_none")]
pub usage_script: Option<UsageScript>,
/// 合作伙伴标记(前端使用 isPartner,保持字段名一致)
#[serde(rename = "isPartner", skip_serializing_if = "Option::is_none")]
pub is_partner: Option<bool>,
/// 合作伙伴促销 key,用于识别 PackyCode 等特殊供应商
#[serde(
rename = "partnerPromotionKey",
skip_serializing_if = "Option::is_none"
)]
pub partner_promotion_key: Option<String>,
/// 成本倍数(用于计算实际成本)
#[serde(rename = "costMultiplier", skip_serializing_if = "Option::is_none")]
pub cost_multiplier: Option<String>,
/// 每日消费限额(USD
#[serde(rename = "limitDailyUsd", skip_serializing_if = "Option::is_none")]
pub limit_daily_usd: Option<String>,
/// 每月消费限额(USD
#[serde(rename = "limitMonthlyUsd", skip_serializing_if = "Option::is_none")]
pub limit_monthly_usd: Option<String>,
}
impl ProviderManager {
/// 获取所有供应商
pub fn get_all_providers(&self) -> &IndexMap<String, Provider> {
&self.providers
}
}
// ============================================================================
// 统一供应商(Universal Provider- 跨应用共享配置
// ============================================================================
/// 统一供应商的应用启用状态
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct UniversalProviderApps {
#[serde(default)]
pub claude: bool,
#[serde(default)]
pub codex: bool,
#[serde(default)]
pub gemini: bool,
}
/// Claude 模型配置
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct ClaudeModelConfig {
/// 主模型
#[serde(skip_serializing_if = "Option::is_none")]
pub model: Option<String>,
/// Haiku 默认模型
#[serde(skip_serializing_if = "Option::is_none")]
#[serde(rename = "haikuModel")]
pub haiku_model: Option<String>,
/// Sonnet 默认模型
#[serde(skip_serializing_if = "Option::is_none")]
#[serde(rename = "sonnetModel")]
pub sonnet_model: Option<String>,
/// Opus 默认模型
#[serde(skip_serializing_if = "Option::is_none")]
#[serde(rename = "opusModel")]
pub opus_model: Option<String>,
}
/// Codex 模型配置
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct CodexModelConfig {
/// 模型名称
#[serde(skip_serializing_if = "Option::is_none")]
pub model: Option<String>,
/// 推理强度
#[serde(skip_serializing_if = "Option::is_none")]
#[serde(rename = "reasoningEffort")]
pub reasoning_effort: Option<String>,
}
/// Gemini 模型配置
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct GeminiModelConfig {
/// 模型名称
#[serde(skip_serializing_if = "Option::is_none")]
pub model: Option<String>,
}
/// 各应用的模型配置
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct UniversalProviderModels {
#[serde(skip_serializing_if = "Option::is_none")]
pub claude: Option<ClaudeModelConfig>,
#[serde(skip_serializing_if = "Option::is_none")]
pub codex: Option<CodexModelConfig>,
#[serde(skip_serializing_if = "Option::is_none")]
pub gemini: Option<GeminiModelConfig>,
}
/// 统一供应商(跨应用共享配置)
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct UniversalProvider {
/// 唯一标识
pub id: String,
/// 供应商名称
pub name: String,
/// 供应商类型(如 "newapi", "custom"
#[serde(rename = "providerType")]
pub provider_type: String,
/// 应用启用状态
pub apps: UniversalProviderApps,
/// API 基础地址
#[serde(rename = "baseUrl")]
pub base_url: String,
/// API 密钥
#[serde(rename = "apiKey")]
pub api_key: String,
/// 各应用的模型配置
#[serde(default)]
pub models: UniversalProviderModels,
/// 网站链接
#[serde(skip_serializing_if = "Option::is_none")]
#[serde(rename = "websiteUrl")]
pub website_url: Option<String>,
/// 备注信息
#[serde(skip_serializing_if = "Option::is_none")]
pub notes: Option<String>,
/// 图标名称
#[serde(skip_serializing_if = "Option::is_none")]
pub icon: Option<String>,
/// 图标颜色
#[serde(skip_serializing_if = "Option::is_none")]
#[serde(rename = "iconColor")]
pub icon_color: Option<String>,
/// 元数据
#[serde(skip_serializing_if = "Option::is_none")]
pub meta: Option<ProviderMeta>,
/// 创建时间戳
#[serde(skip_serializing_if = "Option::is_none")]
#[serde(rename = "createdAt")]
pub created_at: Option<i64>,
/// 排序索引
#[serde(skip_serializing_if = "Option::is_none")]
#[serde(rename = "sortIndex")]
pub sort_index: Option<usize>,
}
impl UniversalProvider {
/// 创建新的统一供应商
pub fn new(
id: String,
name: String,
provider_type: String,
base_url: String,
api_key: String,
) -> Self {
Self {
id,
name,
provider_type,
apps: UniversalProviderApps::default(),
base_url,
api_key,
models: UniversalProviderModels::default(),
website_url: None,
notes: None,
icon: None,
icon_color: None,
meta: None,
created_at: Some(chrono::Utc::now().timestamp_millis()),
sort_index: None,
}
}
/// 生成 Claude 供应商配置
pub fn to_claude_provider(&self) -> Option<Provider> {
if !self.apps.claude {
return None;
}
let models = self.models.claude.as_ref();
let model = models
.and_then(|m| m.model.clone())
.unwrap_or_else(|| "claude-sonnet-4-20250514".to_string());
let haiku = models
.and_then(|m| m.haiku_model.clone())
.unwrap_or_else(|| model.clone());
let sonnet = models
.and_then(|m| m.sonnet_model.clone())
.unwrap_or_else(|| model.clone());
let opus = models
.and_then(|m| m.opus_model.clone())
.unwrap_or_else(|| model.clone());
let settings_config = serde_json::json!({
"env": {
"ANTHROPIC_BASE_URL": self.base_url,
"ANTHROPIC_AUTH_TOKEN": self.api_key,
"ANTHROPIC_MODEL": model,
"ANTHROPIC_DEFAULT_HAIKU_MODEL": haiku,
"ANTHROPIC_DEFAULT_SONNET_MODEL": sonnet,
"ANTHROPIC_DEFAULT_OPUS_MODEL": opus,
}
});
Some(Provider {
id: format!("universal-claude-{}", self.id),
name: self.name.clone(),
settings_config,
website_url: self.website_url.clone(),
category: Some("aggregator".to_string()),
created_at: self.created_at,
sort_index: self.sort_index,
notes: self.notes.clone(),
meta: self.meta.clone(),
icon: self.icon.clone(),
icon_color: self.icon_color.clone(),
in_failover_queue: false,
})
}
/// 生成 Codex 供应商配置
pub fn to_codex_provider(&self) -> Option<Provider> {
if !self.apps.codex {
return None;
}
let models = self.models.codex.as_ref();
let model = models
.and_then(|m| m.model.clone())
.unwrap_or_else(|| "gpt-4o".to_string());
let reasoning_effort = models
.and_then(|m| m.reasoning_effort.clone())
.unwrap_or_else(|| "high".to_string());
// 确保 base_url 以 /v1 结尾(Codex 使用 OpenAI 兼容 API
let codex_base_url = if self.base_url.ends_with("/v1") {
self.base_url.clone()
} else {
format!("{}/v1", self.base_url.trim_end_matches('/'))
};
// 生成 Codex 的 config.toml 内容
let config_toml = format!(
r#"model_provider = "newapi"
model = "{model}"
model_reasoning_effort = "{reasoning_effort}"
disable_response_storage = true
[model_providers.newapi]
name = "NewAPI"
base_url = "{codex_base_url}"
wire_api = "responses"
requires_openai_auth = true"#
);
let settings_config = serde_json::json!({
"auth": {
"OPENAI_API_KEY": self.api_key
},
"config": config_toml
});
Some(Provider {
id: format!("universal-codex-{}", self.id),
name: self.name.clone(),
settings_config,
website_url: self.website_url.clone(),
category: Some("aggregator".to_string()),
created_at: self.created_at,
sort_index: self.sort_index,
notes: self.notes.clone(),
meta: self.meta.clone(),
icon: self.icon.clone(),
icon_color: self.icon_color.clone(),
in_failover_queue: false,
})
}
/// 生成 Gemini 供应商配置
pub fn to_gemini_provider(&self) -> Option<Provider> {
if !self.apps.gemini {
return None;
}
let models = self.models.gemini.as_ref();
let model = models
.and_then(|m| m.model.clone())
.unwrap_or_else(|| "gemini-2.5-pro".to_string());
let settings_config = serde_json::json!({
"env": {
"GOOGLE_GEMINI_BASE_URL": self.base_url,
"GEMINI_API_KEY": self.api_key,
"GEMINI_MODEL": model,
}
});
Some(Provider {
id: format!("universal-gemini-{}", self.id),
name: self.name.clone(),
settings_config,
website_url: self.website_url.clone(),
category: Some("aggregator".to_string()),
created_at: self.created_at,
sort_index: self.sort_index,
notes: self.notes.clone(),
meta: self.meta.clone(),
icon: self.icon.clone(),
icon_color: self.icon_color.clone(),
in_failover_queue: false,
})
}
}