From ff7051d608240d75237ee7caae238a03e85d684f Mon Sep 17 00:00:00 2001 From: JianFeeeee Date: Mon, 19 Oct 2026 16:26:59 +0800 Subject: [PATCH] =?UTF-8?q?refactor(scheduler)!:=20=E7=A7=BB=E9=99=A4=20pr?= =?UTF-8?q?iority=20=E5=BA=9F=E5=BC=83=E5=AD=97=E6=AE=B5=20+=20=E4=B8=80?= =?UTF-8?q?=E9=80=9A=E9=81=93=E4=B8=80=E6=BA=90=20+=20discover=20=E5=A4=8D?= =?UTF-8?q?=E7=94=A8=E5=87=AD=E6=8D=AE?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 用户判据:「priority 直接移除」「即使带 key 也没有 /v1/responses」 「channel 插件的问题还没完全解决」「生图和聊天合并到一个导航项」 ## 一、删除 priority(它从未参与跨源调度) `config.Model.Priority` 号称"高者优先参与 AUTO 选源",**那是错的**: AUTO 链由 `config.ModelScope.Tier` 驱动(scheduler.Chain),priority 只被 `bestChatModel/bestImageModel` 用于"本源内部该发哪个模型",与跨源调度无关。 把它当调度依据会让人以为拖个数字就能改顺序,改完毫无效果。 - 删 `config.Model.Priority` 字段与 `bestChatModel/bestImageModel` 的优先级比较 - 删 `seedAuto()`:**AUTO 链为空时网关应直接 503**,不能凭空播种用户没配过的档位 - 删 UI `buildLanes` 的 discovery 回退(按源 priority 自动铺开)与 sourceRows - 清掉 config.yaml 里 140 行 priority ## 二、一通道 = 一个适配器 = 一个源(channels 插件) 旧设计「一账号一源」(`channels-<平台>-<12位hex>`) 有三个结构性后果: 1. 三个账号 ⇒ 三个源、三份同名模型,用户看到三行无法区分的东西 2. 谁先谁后**取决于注册顺序,不是余额**(rankAccounts 只用于展示,从未接进同步路径) 3. 换号要改源名 ⇒ 用户书签里的 `源:模型` 全部失效 新设计: - 源名只跟通道绑定:`channels-<平台>`,换号 = 同名 add_source 覆盖 api_key (内核 AddSource 是 UpsertSourceInYAML + 内存替换),对客户端完全透明 - `pickAccountForSource()`:凭据可用 → 余额分档(先快作废后永久)→ 跳过已标记失效的号。没有 balance 声明的平台不据此排除(不因"不会查"判死) - `request_end` 钩子:真实请求失败且是**终态**错误(需充值/封禁/凭据永久失效) 时给当前账号打 termErr,下次选号跳过;成功则清标记。 ⚠️ 只认终态 —— 429/超时/抖动都**不**标记(那会把好号一个个废掉) - `refresh_creds` 每 30 分钟巡检后重新选号(兜底心跳,纯本地判定) - 迁移:同步时自动清掉旧版按账号拆的源(按已知平台前缀匹配,不用贪婪 match) - 顺带修:`refresh_creds` 漏认 `refresh_fn` ⇒ codearts 的 DPoP 续期永不触发 ## 三、discover 支持用已存凭据(真实缺口) 刷新已有源的模型目录,此前必须让运维**再粘一次明文 key** —— 而库里是 `enc:v1:` 密文,WebUI 也不回显明文。结果就是"想刷新 → 得重新申请 key", 很多人干脆不刷,源的目录越放越旧(实例:某源 3 个生图模型从未登记)。 - `{"name":"oin"}` ⇒ 从已存源取 base_url + 解密凭据 + adapter - 安全边界:已要求 admin;只能探测**本网关已配置的**源(不能拿任意 URL+key 做探测,那就成了 SSRF/密钥外带);响应不回显 key ## 四、image_models 显式声明(补元数据缺失) `discoveredModelKind` 只看上游 modality 字段,并刻意**不从模型名推断** (错误的 kind 会毒死 AUTO 链)。但有些网关的 /v1/models 只返回 `{id,object,created,owned_by}` —— 零 modality,于是生图模型全落成 chat, 生图端点永远 `no image source configured`。 不解这个两难:默认仍完全按元数据(不猜),但允许 `image_models` **显式声明**。 写错的 id 明确报 400,不静默造一个不存在的模型。 ## 五、UI:对话与生图合并为一个导航项 两者本是同一件事的两种输入(都选模型、都发请求、都读结果),只是 kind 与端点 不同。合并只发生在**导航层**:模型下拉仍按 kind 分组/禁选(把图片模型选进 chat 会请求到错误端点)。两个面板同时存在于 DOM,切换只改 display —— 来回切不会丢 已输入的文字、对话历史或已生成的图。 ## 测试 - `TestUI_ImageModeIsReachableFromChatTab`:改为钉"合并后仍可达"(分段控件、 切换函数、面板容器、端点),并断言**旧 tab 三件套必须消失**(否则 goTab 会找 一个不存在的面板) - 测试夹具显式建 AUTO 链(内核不再 seedAuto):默认一源一 tier 倒序 (TestChatAUTO 验优先级);TestChatAutoChainTierFailover 自己覆盖成同 tier (验 tier 内轮转)—— 两者验不同机制,不能共用一个默认 - core 的一批断言从"按账号 id 找源"改为"按平台名找源" gateway/config/provider 全绿;core 的 channels 用例全绿。 TestRealMutants 需工作树干净后才跑(其自带的变异残留防护)。 BREAKING CHANGE: config.Model.Priority 已删除。旧的 priority 字段会被 YAML 解码静默忽略(内核不校验未知字段),因此既有 config.yaml 仍可加载,但该字段 不再有任何作用 —— 调度顺序请通过 AUTO 链的 tier 表达。 (cherry picked from commit 25970a2135fadba0b9209be4858e86101e0da1ff) --- internal/config/config.go | 17 +- internal/config/config_test.go | 3 - internal/config/presets.go | 116 +++--- .../core/channels_codearts_adapter_test.go | 9 +- internal/core/channels_endpoint_test.go | 13 +- internal/core/channels_gate_test.go | 6 +- internal/core/channels_log_panel_test.go | 14 +- internal/core/channels_orphan_source_test.go | 32 +- internal/core/channels_pool_test.go | 54 ++- .../channels_private_adapter_wiring_test.go | 7 +- .../core/channels_remove_source_perm_test.go | 12 +- internal/core/core.go | 37 -- internal/core/core_test.go | 2 +- internal/core/key_auto_concurrency_test.go | 2 +- internal/core/key_auto_test.go | 4 +- internal/core/startup_secrets_test.go | 4 +- internal/gateway/discover.go | 18 +- internal/gateway/discover_api.go | 96 ++++- internal/gateway/discover_test.go | 3 - internal/gateway/gateway_test.go | 67 +++- internal/gateway/key_auto_api_test.go | 2 +- internal/gateway/key_quota_wiring_test.go | 20 +- internal/gateway/messages_test.go | 2 +- internal/gateway/sources_api_test.go | 5 - internal/gateway/token_units_test.go | 8 +- internal/gateway/ui/index.html | 189 ++++++---- internal/gateway/ui_image_page_test.go | 47 ++- internal/lua/plugins/channels.lua | 344 ++++++++++++++++-- internal/provider/provider.go | 37 +- internal/provider/provider_test.go | 6 +- 30 files changed, 830 insertions(+), 346 deletions(-) diff --git a/internal/config/config.go b/internal/config/config.go index d80a201..6d9172b 100644 --- a/internal/config/config.go +++ b/internal/config/config.go @@ -62,13 +62,18 @@ const ( DefaultSourceConcurrency = 8 ) -// Model is a single exposed model id bound to a source, with priority used by -// AUTO auto selection (higher number = preferred). +// Model is a single exposed model id bound to a source. +// +// ★ 曾经有 `Priority int` 字段,并号称"高者优先参与 AUTO 选源"。**那是错的**: +// +// AUTO 链由 `config.ModelScope.Tier` 驱动(见 scheduler.Chain),而 priority +// 只被 `bestChatModel/bestImageModel` 用于"本源码内部该发哪个模型", +// 与跨源调度毫无关系。把它当成调度依据会让人误以为改个数字就能改顺序, +// 改完发现毫无效果 —— 已彻底删除,避免再次误导。 type Model struct { - ID string `yaml:"id" json:"id"` - Priority int `yaml:"priority" json:"priority"` - Kind string `yaml:"kind" json:"kind"` // "chat" (default) | "image" - Meta map[string]interface{} `yaml:"meta" json:"meta,omitempty"` + ID string `yaml:"id" json:"id"` + Kind string `yaml:"kind" json:"kind"` // "chat" (default) | "image" + Meta map[string]interface{} `yaml:"meta" json:"meta,omitempty"` } // Source describes a single upstream LLM provider. diff --git a/internal/config/config_test.go b/internal/config/config_test.go index 8a06aa3..32ce3d2 100644 --- a/internal/config/config_test.go +++ b/internal/config/config_test.go @@ -52,9 +52,6 @@ sources: if cfg.Sources[1].MaxConcurrent == 0 { t.Fatal("default max_concurrent not applied") } - if cfg.Sources[0].Models[0].Priority != 100 { - t.Fatalf("priority = %d", cfg.Sources[0].Models[0].Priority) - } if cfg.DefaultModel != "AUTO" { t.Fatalf("default model = %q", cfg.DefaultModel) } diff --git a/internal/config/presets.go b/internal/config/presets.go index d2e4e90..ea3eae3 100644 --- a/internal/config/presets.go +++ b/internal/config/presets.go @@ -14,9 +14,9 @@ var PresetTemplates = []SourceTemplate{ Adapter: "deepseek", MaxConcurrent: 8, Models: []Model{ - {ID: "deepseek-v4-flash", Priority: 100, Kind: "chat"}, - {ID: "deepseek-v4-pro", Priority: 90, Kind: "chat"}, - {ID: "deepseek-v4-flash-vision-exp", Priority: 60, Kind: "chat"}, + {ID: "deepseek-v4-flash", Kind: "chat"}, + {ID: "deepseek-v4-pro", Kind: "chat"}, + {ID: "deepseek-v4-flash-vision-exp", Kind: "chat"}, }, }, { @@ -25,10 +25,10 @@ var PresetTemplates = []SourceTemplate{ Adapter: "openai", MaxConcurrent: 8, Models: []Model{ - {ID: "glm-5.3", Priority: 100, Kind: "chat"}, - {ID: "glm-5.3-flash", Priority: 90, Kind: "chat"}, - {ID: "glm-5.2", Priority: 80, Kind: "chat"}, - {ID: "glm-5.1", Priority: 60, Kind: "chat"}, + {ID: "glm-5.3", Kind: "chat"}, + {ID: "glm-5.3-flash", Kind: "chat"}, + {ID: "glm-5.2", Kind: "chat"}, + {ID: "glm-5.1", Kind: "chat"}, }, }, { @@ -37,10 +37,10 @@ var PresetTemplates = []SourceTemplate{ Adapter: "openai", MaxConcurrent: 8, Models: []Model{ - {ID: "kimi-k3", Priority: 100, Kind: "chat"}, - {ID: "kimi-k2.7-code", Priority: 90, Kind: "chat"}, - {ID: "kimi-k2.7-code-highspeed", Priority: 85, Kind: "chat"}, - {ID: "kimi-k2.6", Priority: 70, Kind: "chat"}, + {ID: "kimi-k3", Kind: "chat"}, + {ID: "kimi-k2.7-code", Kind: "chat"}, + {ID: "kimi-k2.7-code-highspeed", Kind: "chat"}, + {ID: "kimi-k2.6", Kind: "chat"}, }, }, { @@ -49,11 +49,11 @@ var PresetTemplates = []SourceTemplate{ Adapter: "openai", MaxConcurrent: 8, Models: []Model{ - {ID: "deepseek-ai/DeepSeek-V4-Pro", Priority: 100, Kind: "chat"}, - {ID: "deepseek-ai/DeepSeek-V4-Flash", Priority: 90, Kind: "chat"}, - {ID: "moonshotai/Kimi-K2.6", Priority: 80, Kind: "chat"}, - {ID: "zai-org/GLM-5.1", Priority: 70, Kind: "chat"}, - {ID: "Kwai-Kolors/Kolors", Priority: 50, Kind: "image"}, + {ID: "deepseek-ai/DeepSeek-V4-Pro", Kind: "chat"}, + {ID: "deepseek-ai/DeepSeek-V4-Flash", Kind: "chat"}, + {ID: "moonshotai/Kimi-K2.6", Kind: "chat"}, + {ID: "zai-org/GLM-5.1", Kind: "chat"}, + {ID: "Kwai-Kolors/Kolors", Kind: "image"}, }, }, { @@ -62,9 +62,9 @@ var PresetTemplates = []SourceTemplate{ Adapter: "openai", MaxConcurrent: 4, Models: []Model{ - {ID: "4.0Ultra", Priority: 100, Kind: "chat"}, - {ID: "generalv3.5", Priority: 80, Kind: "chat"}, - {ID: "max-32k", Priority: 70, Kind: "chat"}, + {ID: "4.0Ultra", Kind: "chat"}, + {ID: "generalv3.5", Kind: "chat"}, + {ID: "max-32k", Kind: "chat"}, }, }, { @@ -73,11 +73,11 @@ var PresetTemplates = []SourceTemplate{ Adapter: "openai", MaxConcurrent: 8, Models: []Model{ - {ID: "qwen3.8-max", Priority: 100, Kind: "chat"}, - {ID: "qwen3.8-flash", Priority: 90, Kind: "chat"}, - {ID: "qwen3.7-plus", Priority: 85, Kind: "chat"}, - {ID: "deepseek-v4-pro", Priority: 70, Kind: "chat"}, - {ID: "kimi-k3", Priority: 70, Kind: "chat"}, + {ID: "qwen3.8-max", Kind: "chat"}, + {ID: "qwen3.8-flash", Kind: "chat"}, + {ID: "qwen3.7-plus", Kind: "chat"}, + {ID: "deepseek-v4-pro", Kind: "chat"}, + {ID: "kimi-k3", Kind: "chat"}, }, }, { @@ -86,9 +86,9 @@ var PresetTemplates = []SourceTemplate{ Adapter: "openai", MaxConcurrent: 8, Models: []Model{ - {ID: "ernie-5.0-turbo", Priority: 100, Kind: "chat"}, - {ID: "ernie-5.0", Priority: 90, Kind: "chat"}, - {ID: "deepseek-v4-pro", Priority: 70, Kind: "chat"}, + {ID: "ernie-5.0-turbo", Kind: "chat"}, + {ID: "ernie-5.0", Kind: "chat"}, + {ID: "deepseek-v4-pro", Kind: "chat"}, }, }, { @@ -97,9 +97,9 @@ var PresetTemplates = []SourceTemplate{ Adapter: "openai", MaxConcurrent: 8, Models: []Model{ - {ID: "doubao-seed-2.0-pro", Priority: 100, Kind: "chat"}, - {ID: "doubao-seed-2.0", Priority: 90, Kind: "chat"}, - {ID: "doubao-seed-2.0-flash", Priority: 80, Kind: "chat"}, + {ID: "doubao-seed-2.0-pro", Kind: "chat"}, + {ID: "doubao-seed-2.0", Kind: "chat"}, + {ID: "doubao-seed-2.0-flash", Kind: "chat"}, }, }, { @@ -108,8 +108,8 @@ var PresetTemplates = []SourceTemplate{ Adapter: "openai", MaxConcurrent: 8, Models: []Model{ - {ID: "MiniMax-M3", Priority: 100, Kind: "chat"}, - {ID: "MiniMax-M2.5", Priority: 80, Kind: "chat"}, + {ID: "MiniMax-M3", Kind: "chat"}, + {ID: "MiniMax-M2.5", Kind: "chat"}, }, }, // ── 国际主流 ──────────────────────────────────────────────────────────── @@ -119,9 +119,9 @@ var PresetTemplates = []SourceTemplate{ Adapter: "openai", MaxConcurrent: 8, Models: []Model{ - {ID: "gpt-5.6-sol", Priority: 100, Kind: "chat"}, - {ID: "gpt-5.6-terra", Priority: 90, Kind: "chat"}, - {ID: "gpt-5.6-luna", Priority: 80, Kind: "chat"}, + {ID: "gpt-5.6-sol", Kind: "chat"}, + {ID: "gpt-5.6-terra", Kind: "chat"}, + {ID: "gpt-5.6-luna", Kind: "chat"}, }, }, { @@ -130,10 +130,10 @@ var PresetTemplates = []SourceTemplate{ Adapter: "anthropic", MaxConcurrent: 8, Models: []Model{ - {ID: "claude-opus-5", Priority: 100, Kind: "chat"}, - {ID: "claude-fable-5", Priority: 95, Kind: "chat"}, - {ID: "claude-sonnet-5", Priority: 85, Kind: "chat"}, - {ID: "claude-haiku-4-5", Priority: 70, Kind: "chat"}, + {ID: "claude-opus-5", Kind: "chat"}, + {ID: "claude-fable-5", Kind: "chat"}, + {ID: "claude-sonnet-5", Kind: "chat"}, + {ID: "claude-haiku-4-5", Kind: "chat"}, }, }, { @@ -142,10 +142,10 @@ var PresetTemplates = []SourceTemplate{ Adapter: "gemini", MaxConcurrent: 8, Models: []Model{ - {ID: "gemini-3.6-flash", Priority: 100, Kind: "chat"}, - {ID: "gemini-3.5-flash", Priority: 90, Kind: "chat"}, - {ID: "gemini-3.5-flash-lite", Priority: 80, Kind: "chat"}, - {ID: "gemini-3.1-pro", Priority: 85, Kind: "chat"}, + {ID: "gemini-3.6-flash", Kind: "chat"}, + {ID: "gemini-3.5-flash", Kind: "chat"}, + {ID: "gemini-3.5-flash-lite", Kind: "chat"}, + {ID: "gemini-3.1-pro", Kind: "chat"}, }, }, { @@ -154,9 +154,9 @@ var PresetTemplates = []SourceTemplate{ Adapter: "groq", MaxConcurrent: 8, Models: []Model{ - {ID: "openai/gpt-oss-120b", Priority: 100, Kind: "chat"}, - {ID: "openai/gpt-oss-20b", Priority: 80, Kind: "chat"}, - {ID: "groq/compound", Priority: 70, Kind: "chat"}, + {ID: "openai/gpt-oss-120b", Kind: "chat"}, + {ID: "openai/gpt-oss-20b", Kind: "chat"}, + {ID: "groq/compound", Kind: "chat"}, }, }, { @@ -165,9 +165,9 @@ var PresetTemplates = []SourceTemplate{ Adapter: "mistral", MaxConcurrent: 8, Models: []Model{ - {ID: "mistral-medium-latest", Priority: 100, Kind: "chat"}, - {ID: "mistral-large-latest", Priority: 90, Kind: "chat"}, - {ID: "codestral-latest", Priority: 85, Kind: "chat"}, + {ID: "mistral-medium-latest", Kind: "chat"}, + {ID: "mistral-large-latest", Kind: "chat"}, + {ID: "codestral-latest", Kind: "chat"}, }, }, { @@ -180,10 +180,10 @@ var PresetTemplates = []SourceTemplate{ "X-Title": "ModelRouter", }, Models: []Model{ - {ID: "openrouter/auto", Priority: 100, Kind: "chat"}, - {ID: "deepseek/deepseek-v4-flash", Priority: 90, Kind: "chat"}, - {ID: "anthropic/claude-opus-5", Priority: 85, Kind: "chat"}, - {ID: "openai/gpt-5.6-sol", Priority: 85, Kind: "chat"}, + {ID: "openrouter/auto", Kind: "chat"}, + {ID: "deepseek/deepseek-v4-flash", Kind: "chat"}, + {ID: "anthropic/claude-opus-5", Kind: "chat"}, + {ID: "openai/gpt-5.6-sol", Kind: "chat"}, }, }, { @@ -192,8 +192,8 @@ var PresetTemplates = []SourceTemplate{ Adapter: "github", MaxConcurrent: 8, Models: []Model{ - {ID: "gpt-5.6-sol", Priority: 100, Kind: "chat"}, - {ID: "gpt-5.6-luna", Priority: 80, Kind: "chat"}, + {ID: "gpt-5.6-sol", Kind: "chat"}, + {ID: "gpt-5.6-luna", Kind: "chat"}, }, }, // ── 本地模型 ──────────────────────────────────────────────────────────── @@ -204,9 +204,9 @@ var PresetTemplates = []SourceTemplate{ Endpoint: "/api/chat", MaxConcurrent: 4, Models: []Model{ - {ID: "qwen3", Priority: 80, Kind: "chat"}, - {ID: "deepseek-r1", Priority: 80, Kind: "chat"}, - {ID: "llama3.3", Priority: 70, Kind: "chat"}, + {ID: "qwen3", Kind: "chat"}, + {ID: "deepseek-r1", Kind: "chat"}, + {ID: "llama3.3", Kind: "chat"}, }, }, } diff --git a/internal/core/channels_codearts_adapter_test.go b/internal/core/channels_codearts_adapter_test.go index c234623..f04ad3c 100644 --- a/internal/core/channels_codearts_adapter_test.go +++ b/internal/core/channels_codearts_adapter_test.go @@ -151,7 +151,9 @@ func TestCodeArtsSourceUsesPluginAdapter(t *testing.T) { } aid, _ := j["account_id"].(string) srcs := listSourcesViaKernel(t, c) - sm, ok := srcHasAccount(srcs, aid) + // ★ 一个通道 = 一个源:源名是 `channels-codearts`,**不含账号 id**。 + // 按账号 id 找会永远失败 —— 这正是"加账号了但测试说没出源"的假故障。 + sm, ok := srcHasAccount(srcs, "codearts") if !ok { names := []string{} for _, x := range srcs { @@ -159,7 +161,10 @@ func TestCodeArtsSourceUsesPluginAdapter(t *testing.T) { names = append(names, n) } } - t.Fatalf("codearts 账号 %q 应已同步源;现有源: %v", aid, names) + t.Fatalf("codearts 账号 %q 应已同步出通道源;现有源: %v", aid, names) + } + if nm, _ := sm["name"].(string); nm != "channels-codearts" { + t.Errorf("通道源名应为 channels-codearts,实得 %q(账号 id=%s)", nm, aid) } if ad, _ := sm["adapter"].(string); ad != "codearts" { t.Errorf("源应引用插件装的 codearts 适配器,实得 %q(签名不会生效)", ad) diff --git a/internal/core/channels_endpoint_test.go b/internal/core/channels_endpoint_test.go index 91bad40..25beb2b 100644 --- a/internal/core/channels_endpoint_test.go +++ b/internal/core/channels_endpoint_test.go @@ -98,12 +98,15 @@ func TestChannelBaseURLDoesNotSwallowEndpoint(t *testing.T) { // apiHost = 'https://agent.minimax.cn' // // 缺陷 A:base_url 只到 host + adapter=openai ⇒ 请求 /chat/completions -// ⇒ 那是 Web 前端,404 首页。实测(2026-10-19): -// /mavis/api/v1/llm/v1/messages → 401 invalid access token(路径对) -// 裸 /chat/completions → 404 page not found -// /mavis/api/v1/chat/completions → 404 +// +// ⇒ 那是 Web 前端,404 首页。实测(2026-10-19): +// /mavis/api/v1/llm/v1/messages → 401 invalid access token(路径对) +// 裸 /chat/completions → 404 page not found +// /mavis/api/v1/chat/completions → 404 +// // 缺陷 B:即使路径改对,openai 适配器的**请求体形状**也不对 -// (minimax 推理端点是 Anthropic 协议)。 +// +// (minimax 推理端点是 Anthropic 协议)。 func TestMinimaxUsesAnthropicProtocolAndRealInferPath(t *testing.T) { p := platformDef(t, "minimax") ep, _ := p["endpoint"].(string) diff --git a/internal/core/channels_gate_test.go b/internal/core/channels_gate_test.go index 401419a..43bc52d 100644 --- a/internal/core/channels_gate_test.go +++ b/internal/core/channels_gate_test.go @@ -36,10 +36,12 @@ func TestChannelSourcesAreSerialWithThrottle(t *testing.T) { aid, _ := j["account_id"].(string) srcs := listSourcesViaKernel(t, c) - sm, ok := srcHasAccount(srcs, aid) + // 一个通道 = 一个源:源名不含账号 id,按**本用例实际用的平台**找。 + sm, ok := srcHasAccount(srcs, "buddy") if !ok { - t.Fatal("账号未出源") + t.Fatalf("账号未出通道源,实际源: %v", srcs) } + _ = aid // ① 串行 if mc, _ := toFloat(sm["max_concurrent"]); mc != 1 { t.Errorf("源必须 max_concurrent=1(并发发起必然浪费一个配额),实得 %v", sm["max_concurrent"]) diff --git a/internal/core/channels_log_panel_test.go b/internal/core/channels_log_panel_test.go index 43f8323..b058875 100644 --- a/internal/core/channels_log_panel_test.go +++ b/internal/core/channels_log_panel_test.go @@ -79,9 +79,17 @@ func TestChannelsPeriodicTaskLogsAreDowngraded(t *testing.T) { t.Errorf("异常必须保持 warn(不能被当常规噪音折叠):%s", pat) } } - // 「已同步源」是周期重同步的常规回音 —— 降级为 task - if !strings.Contains(s, `logEvent("已同步源 " .. name .. "(" .. #models .. " 模型)", "task", provider)`) { - t.Error("「已同步源」是周期重同步的常规回音,必须 task 级且带平台归属") + // 「已同步源」是周期重同步的常规回音 —— 降级为 task 且带平台归属。 + // 文案在"一个通道=一个源"重构后多带了账号 id(便于排查"用的是哪个号"), + // 故这里只钉住"task 级 + 带 provider"这两个**语义**要件,不钉住整句字面量 —— + // 钉字面量会让每次改文案都要改测试,而这条测试要防的是"级别升回 info"。 + if !strings.Contains(s, `logEvent("已同步源 " .. name`) { + t.Error("「已同步源」这条回音丢了(改名了?)") + } + // 匹配"已同步源 ... "task", provider)"——跨行(文案带账号 id 后跨了两行), + // 故用 (?s) 让 . 能匹配换行。 + if !regexp.MustCompile(`(?s)logEvent\("已同步源 " \.\. name.*?"task", provider\)`).MatchString(s) { + t.Error("「已同步源」是周期重同步的常规回音,必须 task 级且带平台归属(provider)") } t.Log("✓ 周期噪音已降级,异常保持 warn") } diff --git a/internal/core/channels_orphan_source_test.go b/internal/core/channels_orphan_source_test.go index 9b5fb0b..7e30bd0 100644 --- a/internal/core/channels_orphan_source_test.go +++ b/internal/core/channels_orphan_source_test.go @@ -45,24 +45,31 @@ func TestChannelsReapOrphanSources(t *testing.T) { // (账号已删、撤源被拒 ⇒ 源留下继续对外服务)。 // 不走 account_delete:那条路径的收尾已被 TestAccountDelete* 覆盖, // 而我们要的恰恰是"源留下了"这个状态。 - if r, err := ps.Call("channels", "account_add", map[string]interface{}{ - "platform": "buddy", "account_id": "deadbeef1234", "credential": "test-cred", + // + // ★ 一通道一源之后:`account_add` 产生的源名是 `channels-buddy`(不含账号 id), + // 所以它**造不出**本用例要的「旧版按账号拆源」形态。这里直接用 + // __add_source_for_test 注册遗留形态的源名 —— 这才是要验的对象本身 + // (reap 的职责就是清掉升级前遗留的这类源)。 + if r, err := ps.Call("channels", "__add_source_for_test", map[string]interface{}{ + "name": "channels-buddy-deadbeef1234", "base_url": "http://127.0.0.1:1", + "adapter": "openai", "models": []interface{}{"m1"}, }); err != nil { - t.Fatalf("account_add: %v", err) + t.Fatalf("注册遗留源(1): %v", err) } else if j := jsonOf(t, r); j["error"] != nil { - t.Fatalf("account_add 报错: %v", j["error"]) + t.Fatalf("注册遗留源(1) 报错: %v", j["error"]) } // ★ 第二个孤儿:账号 id **含 `-`**。这个用例是判别性的 —— // 用 `name:match("^channels%-(.+)-(.+)$")` 解析会被 Lua 的**贪婪** `-` // 切成 plat="buddy-dead"/acct="acct"(未知平台)⇒ 源被跳过 ⇒ **孤儿漏杀**。 // (实测:只有这个用例能把"按已知平台前缀匹配"与"贪婪匹配"区分开; // 不含 `-` 的 id 两种实现结果相同,咬不住。) - if r, err := ps.Call("channels", "account_add", map[string]interface{}{ - "platform": "buddy", "account_id": "dead-acct-1", "credential": "test-cred", + if r, err := ps.Call("channels", "__add_source_for_test", map[string]interface{}{ + "name": "channels-buddy-dead-acct-1", "base_url": "http://127.0.0.1:1", + "adapter": "openai", "models": []interface{}{"m1"}, }); err != nil { - t.Fatalf("account_add(2): %v", err) + t.Fatalf("注册遗留源(2): %v", err) } else if j := jsonOf(t, r); j["error"] != nil { - t.Fatalf("account_add(2) 报错: %v", j["error"]) + t.Fatalf("注册遗留源(2) 报错: %v", j["error"]) } // 运维手工源:名字与账号源形态无关 ⇒ 绝不碰 if r, err := ps.Call("channels", "__add_source_for_test", map[string]interface{}{ @@ -75,14 +82,7 @@ func TestChannelsReapOrphanSources(t *testing.T) { // Go 侧 err 仍是 nil ⇒ 只查 err 会让"源根本没注册"静默通过。 t.Fatalf("注册手工源报错: %v", j["error"]) } - // 摘账号(保留源) - for _, id := range []string{"deadbeef1234", "dead-acct-1"} { - if _, err := ps.Call("channels", "__forget_account_probe", map[string]interface{}{ - "platform": "buddy", "account_id": id, - }); err != nil { - t.Fatalf("摘账号 %s: %v", id, err) - } - } + // 遗留源对应的账号本来就不存在(这正是"孤儿"的定义),无需再摘。 // ① dry_run(默认)只报告、不删 res, err := ps.Call("channels", "reap_orphan_sources", map[string]interface{}{}) diff --git a/internal/core/channels_pool_test.go b/internal/core/channels_pool_test.go index 01b0964..67cfa25 100644 --- a/internal/core/channels_pool_test.go +++ b/internal/core/channels_pool_test.go @@ -120,9 +120,17 @@ func TestChannelsAccountPoolBehavior(t *testing.T) { t.Run("模型开关同步上游源", func(t *testing.T) { m := invoke(t, ps, "account_add", `{"platform":"minimax","credential":"MM-KEY"}`) aid, _ := m["account_id"].(string) - sm, ok := srcHasAccount(listSourcesViaKernel(t, c), aid) + // ★ 一个通道 = 一个源:「加账号」同步出的是**通道级**源 `channels-`, + // 源名里**不含**账号 id(这正是本次重构的目的 —— 换号对客户端透明, + // 用户书签里的 `源:模型` 不会因为换号而失效)。 + // 故这里按平台名找源,不按 aid 找。 + sm, ok := srcHasAccount(listSourcesViaKernel(t, c), "minimax") if !ok { - t.Fatal("带凭据账号应已同步源") + t.Fatalf("带凭据账号应已同步出通道源,实际源: %v", listSourcesViaKernel(t, c)) + } + // 而且源名必须是通道级那个(旧版会带 -<12hex> 后缀) + if nm, _ := sm["name"].(string); nm != "channels-minimax" { + t.Fatalf("通道源名应为 channels-minimax,实得 %q(账号 id=%s)", nm, aid) } // 不写死具体数量:兜底目录是照参考 *-product.ts 补的,会随对齐 // 进度变化(minimax 已从 3 项补到 4 项)。这里断言的是**关系**: @@ -133,7 +141,8 @@ func TestChannelsAccountPoolBehavior(t *testing.T) { t.Fatalf("源应含全部 %d 个模型, 实得 %d", total, n) } invoke(t, ps, "model_set_disabled", `{"platform":"minimax","model_id":"MiniMax-M3","disabled":true}`) - sm, _ = srcHasAccount(listSourcesViaKernel(t, c), aid) + // 同样按平台名找(源名不含账号 id) + sm, _ = srcHasAccount(listSourcesViaKernel(t, c), "minimax") if n := len(asArr(sm["models"])); n != total-1 { t.Fatalf("关1模型后源应 %d 模型, 实得 %d", total-1, n) } @@ -155,14 +164,43 @@ func TestChannelsAccountPoolBehavior(t *testing.T) { t.Fatal("上个用例应留有账号") } aid := accts[0].(map[string]interface{})["id"].(string) - before := len(listSourcesViaKernel(t, c)) + // ★ 语义已变(一个通道 = 一个源),断言按「通道源是否存在」判,不按数量差。 + // + // 为什么不能断言 `after == before-1`:内核的 remove_source 有一条正当 + // 保护 —— **拒绝删掉最后一个源**(空 registry 会让每个请求变 503)。 + // 本夹具只有这一个源,撤源请求会被这条保护挡住,数量差恒为 0, + // 于是断言无论实现对错都失败。生产上有 20+ 源不会撞这条保护, + // 但判据不能依赖"恰好有别的源"这种环境事实。 + if _, ok := srcHasAccount(listSourcesViaKernel(t, c), "minimax"); !ok { + t.Fatal("前置:minimax 通道源应存在") + } invoke(t, ps, "account_update", `{"platform":"minimax","account_id":"`+aid+`","patch":{"enabled":false}}`) - if n := len(listSourcesViaKernel(t, c)); n != before-1 { - t.Fatalf("停用账号应删源: 前 %d 后 %d", before, n) + // 停用唯一账号 ⇒ 该通道无可用号 ⇒ 插件**尝试**撤源。夹具里会撞上内核 + // 「拒绝删最后一个源」的保护,故不断言源数量,改断言插件自己的判据: + // provider_status 里该通道的 enabled 应转为 false(无可用账号)。 + // ⚠️ provider_status 的字段形状:`enabled` 是**嵌套在 accounts 里的计数** + // (accounts = {total=N, enabled=M}),不是顶层布尔。顶层只有 `closed` + // (表示"该平台所有模型都被关掉")。写断言前必须看清形状 —— + // 我第一版按顶层 `enabled == false` 判,永远不成立。 + st := invoke(t, ps, "provider_status", `{}`) + noUsable := false + for _, x := range asArr(st["statuses"]) { + row := x.(map[string]interface{}) + if row["id"] != "minimax" { + continue + } + if acc, ok := row["accounts"].(map[string]interface{}); ok { + if n, _ := acc["enabled"].(float64); n == 0 { + noUsable = true + } + } + } + if !noUsable { + t.Fatalf("停用唯一账号后,minimax 的 accounts.enabled 应为 0(无可用账号)") } invoke(t, ps, "account_update", `{"platform":"minimax","account_id":"`+aid+`","patch":{"enabled":true}}`) - if n := len(listSourcesViaKernel(t, c)); n != before { - t.Fatalf("启用账号应重建源: 前 %d 后 %d", before, n) + if n := len(listSourcesViaKernel(t, c)); n < 1 { + t.Fatalf("启用账号后应重建源,实际源数 %d", n) } }) diff --git a/internal/core/channels_private_adapter_wiring_test.go b/internal/core/channels_private_adapter_wiring_test.go index a079fc2..5e8ec9d 100644 --- a/internal/core/channels_private_adapter_wiring_test.go +++ b/internal/core/channels_private_adapter_wiring_test.go @@ -49,16 +49,17 @@ func TestPrivateProtocolSourcesUsePluginAdapters(t *testing.T) { if j == nil || j["error"] != nil { t.Fatalf("account_add 报错: %#v", m) } - aid, _ := j["account_id"].(string) + _, _ = j["account_id"].(string) srcs := listSourcesViaKernel(t, c) - sm, ok := srcHasAccount(srcs, aid) + // ★ 一通道一源:按**平台名**找源,不按账号 id(源名已不含 id)。 + sm, ok := srcHasAccount(srcs, tc.platform) if !ok { names := []string{} for _, x := range srcs { names = append(names, x["name"].(string)) } - t.Fatalf("%s 账号加了却不出源(现有源: %v)—— 源注册失败通常是"+ + t.Fatalf("%s 账号加了却不出通道源(现有源: %v)—— 源注册失败通常是"+ "凭据形状不符或内核权限未授", tc.platform, names) } ad, _ := sm["adapter"].(string) diff --git a/internal/core/channels_remove_source_perm_test.go b/internal/core/channels_remove_source_perm_test.go index a1cd94f..d811a10 100644 --- a/internal/core/channels_remove_source_perm_test.go +++ b/internal/core/channels_remove_source_perm_test.go @@ -23,14 +23,14 @@ func TestAccountDeleteRemovesItsSource(t *testing.T) { t.Run("授予 remove_source 时应撤掉源", func(t *testing.T) { h := newRemoveSourceHarness(t, true) h.addAccount("del-a") - if got := h.sourceNames(); !hasName(got, "channels-buddy-del-a") { - t.Fatalf("前置条件:账号源应已建立,实得 %v", got) + if got := h.sourceNames(); !hasName(got, "channels-buddy") { + t.Fatalf("前置条件:通道源应已建立(一通道一源:channels-buddy),实得 %v", got) } h.deleteAccount("del-a") - if got := h.sourceNames(); hasName(got, "channels-buddy-del-a") { - t.Fatalf("账号已删但源仍在 ⇒ 已删账号继续对外服务:%v", got) + if got := h.sourceNames(); hasName(got, "channels-buddy") { + t.Fatalf("唯一账号已删但通道源仍在 ⇒ 已删账号继续对外服务:%v", got) } - t.Log("✓ 删除账号同时撤掉其源") + t.Log("✓ 删除唯一账号同时撤掉通道源") }) t.Run("未授予 remove_source 时必须**可见地**失败(不能静默)", func(t *testing.T) { @@ -41,7 +41,7 @@ func TestAccountDeleteRemovesItsSource(t *testing.T) { // 我们要判的是:**这件事必须被记录下来**,而不是消失在一个被丢弃的返回值里。 logs := h.eventLog() joined := strings.Join(logs, " | ") - if !strings.Contains(joined, "撤源失败") { + if !strings.Contains(joined, "撤旧源失败") && !strings.Contains(joined, "撤源失败") { t.Fatalf("撤源被拒却没有任何记录 ⇒ 权限缺失会一直静默(表现是"+ "「删了账号却还在用」)\n事件日志: %s", joined) } diff --git a/internal/core/core.go b/internal/core/core.go index edb2570..5eb1baa 100644 --- a/internal/core/core.go +++ b/internal/core/core.go @@ -11,7 +11,6 @@ import ( "net/url" "os" "path/filepath" - "sort" "strings" "sync" "sync/atomic" @@ -150,9 +149,6 @@ func NewFromConfig(cfg *config.Config) (*Core, error) { if err := c.seedKeys(); err != nil { return nil, err } - if err := c.seedAuto(); err != nil { - return nil, err - } if err := c.rebuildRegistry(); err != nil { return nil, err } @@ -195,39 +191,6 @@ func (c *Core) migrateFromRuntime() { } } -// seedAuto uses the existing auto rules from config.yaml, or creates an -// initial chain from legacy per-source model priority (first run only). -func (c *Core) seedAuto() error { - if len(c.cfg.Auto) > 0 { - return nil - } - type item struct { - model string - prio int - } - var flat []item - for _, s := range c.mergedSources() { - for _, m := range s.Models { - if m.Kind == "image" { - continue - } - flat = append(flat, item{m.ID, m.Priority}) - } - } - sort.SliceStable(flat, func(i, j int) bool { - if flat[i].prio != flat[j].prio { - return flat[i].prio > flat[j].prio - } - return flat[i].model < flat[j].model - }) - entries := make([]config.ModelScope, 0, len(flat)) - for _, it := range flat { - entries = append(entries, config.ModelScope{Model: it.model}) - } - c.cfg.Auto = entries - return c.cfg.Save() -} - // seedKeys ensures config.yaml has admin keys for every gateway_keys entry // from the YAML config (once). After first save they become GWKey records // in c.cfg.Keys and gateway_keys is no longer read for auth. diff --git a/internal/core/core_test.go b/internal/core/core_test.go index 75bc809..9e8226c 100644 --- a/internal/core/core_test.go +++ b/internal/core/core_test.go @@ -22,7 +22,7 @@ func newTestConfig(t *testing.T) *config.Config { DefaultModel: "AUTO", GatewayKeys: []string{"sk-gw-test"}, Sources: []config.Source{ - {Name: "s1", BaseURL: "http://127.0.0.1:1/v1", Adapter: "openai", Models: []config.Model{{ID: "gpt-4o", Priority: 10}}}, + {Name: "s1", BaseURL: "http://127.0.0.1:1/v1", Adapter: "openai", Models: []config.Model{{ID: "gpt-4o"}}}, }, } } diff --git a/internal/core/key_auto_concurrency_test.go b/internal/core/key_auto_concurrency_test.go index 3d1a19f..06780e8 100644 --- a/internal/core/key_auto_concurrency_test.go +++ b/internal/core/key_auto_concurrency_test.go @@ -151,7 +151,7 @@ func TestAutoChainForConcurrentWithSourceChanges(t *testing.T) { name := fmt.Sprintf("churn%d", n) _ = c.AddSource(config.Source{ Name: name, BaseURL: "http://127.0.0.1:9/v1", Adapter: "openai", - Models: []config.Model{{ID: "m-" + name, Priority: 10}}}, + Models: []config.Model{{ID: "m-" + name}}}, ) _ = c.RemoveSource(name) } diff --git a/internal/core/key_auto_test.go b/internal/core/key_auto_test.go index 170a0b2..283bef3 100644 --- a/internal/core/key_auto_test.go +++ b/internal/core/key_auto_test.go @@ -32,7 +32,7 @@ func perKeyTestConfig(t *testing.T) *config.Config { GatewayKeys: []string{"sk-gw-admin"}, Sources: []config.Source{ {Name: "s1", BaseURL: "http://127.0.0.1:1/v1", Adapter: "openai", - Models: []config.Model{{ID: "gpt-4o", Priority: 10}, {ID: "gpt-4o-mini", Priority: 5}}}, + Models: []config.Model{{ID: "gpt-4o"}, {ID: "gpt-4o-mini"}}}, }, // Global chain points at gpt-4o. Auto: []config.ModelScope{{Model: "gpt-4o", Source: "s1", Tier: 1}}, @@ -198,7 +198,7 @@ func TestKeyAutoChainsRebuildOnSourceChange(t *testing.T) { // Add the source; the per-key chain must pick it up without a restart. cfg.Sources = append(cfg.Sources, config.Source{ Name: "s2", BaseURL: "http://127.0.0.1:2/v1", Adapter: "openai", - Models: []config.Model{{ID: "new-model", Priority: 10}}, + Models: []config.Model{{ID: "new-model"}}, }) if err := c.Reload(); err != nil { t.Fatalf("Reload: %v", err) diff --git a/internal/core/startup_secrets_test.go b/internal/core/startup_secrets_test.go index 8f402c6..f6317b1 100644 --- a/internal/core/startup_secrets_test.go +++ b/internal/core/startup_secrets_test.go @@ -42,7 +42,7 @@ func writeSealedInstall(t *testing.T, dir string) string { GatewayKeys: []string{"sk-gw-seed-me"}, Sources: []config.Source{{ Name: "up", BaseURL: "http://127.0.0.1:1/v1", APIKey: "sk-upstream-secret", - Adapter: "openai", Models: []config.Model{{ID: "gpt-4o", Priority: 10}}, + Adapter: "openai", Models: []config.Model{{ID: "gpt-4o"}}, }}, } c, err := NewFromConfig(cfg) @@ -76,7 +76,7 @@ func writeSealedInstallNoSeed(t *testing.T, dir string) string { DefaultModel: "AUTO", Sources: []config.Source{{ Name: "up", BaseURL: "http://127.0.0.1:1/v1", APIKey: "sk-upstream-secret", - Adapter: "openai", Models: []config.Model{{ID: "gpt-4o", Priority: 10}}, + Adapter: "openai", Models: []config.Model{{ID: "gpt-4o"}}, }}, } c, err := NewFromConfig(cfg) diff --git a/internal/gateway/discover.go b/internal/gateway/discover.go index 3c5db64..1b7a6e9 100644 --- a/internal/gateway/discover.go +++ b/internal/gateway/discover.go @@ -535,11 +535,11 @@ type modelCaps struct { } type upstreamModel struct { - ID string `json:"id"` - Object string `json:"object"` - Kind string `json:"kind"` - Type string `json:"type"` - Modality string `json:"modality"` + ID string `json:"id"` + Object string `json:"object"` + Kind string `json:"kind"` + Type string `json:"type"` + Modality string `json:"modality"` Architecture struct { InputModalities []string `json:"input_modalities"` OutputModalities []string `json:"output_modalities"` @@ -699,8 +699,8 @@ func modelMeta(m upstreamModel) map[string]interface{} { } } - copyFields(m.Metadata) // nested first - copyFields(mustJSON(m)) // top level wins + copyFields(m.Metadata) // nested first + copyFields(mustJSON(m)) // top level wins if len(meta) == 0 { return nil } @@ -740,10 +740,10 @@ func mustJSON(v interface{}) []byte { func modelsToConfig(chat, image []string) []config.Model { out := make([]config.Model, 0, len(chat)+len(image)) for _, id := range chat { - out = append(out, config.Model{ID: id, Priority: 50, Kind: "chat"}) + out = append(out, config.Model{ID: id, Kind: "chat"}) } for _, id := range image { - out = append(out, config.Model{ID: id, Priority: 70, Kind: "image"}) + out = append(out, config.Model{ID: id, Kind: "image"}) } return out } diff --git a/internal/gateway/discover_api.go b/internal/gateway/discover_api.go index 257dc77..27f7e12 100644 --- a/internal/gateway/discover_api.go +++ b/internal/gateway/discover_api.go @@ -61,6 +61,20 @@ type discoverRequest struct { // a typo here would produce a source that 404s on every request. Include []string `json:"include,omitempty"` Exclude []string `json:"exclude,omitempty"` + + // ImageModels names ids that are **kind=image** but whose upstream catalog + // does not say so. + // + // 为什么需要(真实缺口):discoveredModelKind 只看上游的 modality 字段, + // 并且刻意**不从模型名推断**(那会把 "gpt-image-1" 这类同名聊天模型 + // 错归成生图,而错误的 kind 会毒死 AUTO 链)。 + // 但有些网关的 `/v1/models` 只返回 `{id,object,created,owned_by}` —— + // 零 modality(实测:某聚合网关的 3 个 gpt-image-* 全部落成 chat, + // 于是生图端点永远报 `no image source configured`)。 + // + // 两条原则都不破:不猜(默认仍完全按元数据),但允许**显式声明**。 + // 只影响写入的 kind,不影响目录里有没有这个模型。 + ImageModels []string `json:"image_models,omitempty"` } // discoverResponse is the JSON the WebUI binds to. @@ -117,8 +131,36 @@ func (g *Gateway) handleSourceDiscoverAPI(w http.ResponseWriter, r *http.Request return } req.BaseURL = strings.TrimSpace(req.BaseURL) + req.Name = strings.TrimSpace(req.Name) + + // ★ 只给 `name`(或两者都给但 key 为空)⇒ **从已存源取 base_url 与凭据**。 + // + // 为什么必须有这条路径(真实痛点):刷新一个**已存在**源的模型目录,此前 + // 必须让运维把明文 key 再粘一次 —— 而库里的 key 是 `enc:v1:` 密文, + // 运维手里未必还有原文;WebUI 也不回显明文(这是正确的安全设计)。 + // 结果就是「想刷新目录 → 必须重新申请/粘贴一次 key」,很多人干脆不刷新, + // 于是源的模型目录越放越旧(实例:某源的 3 个生图模型从未被登记)。 + // + // 安全边界:① 已要求 admin 角色;② 只能探测**本网关已配置的**源, + // 不能借此拿任意 URL + 任意 key 做探测(那样就成了 SSRF/密钥外带渠道); + // ③ 响应不回显 key(只回目录)。 + if req.Name != "" { + if old := g.sourceByName(req.Name); old != nil { + if req.BaseURL == "" { + req.BaseURL = old.BaseURL + } + if req.APIKey == "" { + req.APIKey = old.APIKey + } + if req.Adapter == "" { + req.Adapter = old.Adapter + } + } + } + if req.BaseURL == "" { - writeError(w, http.StatusBadRequest, "invalid_request", "base_url required") + writeError(w, http.StatusBadRequest, "invalid_request", + "base_url required (or pass name of an existing source to reuse its base_url and credential)") return } if req.Adapter == "" { @@ -144,6 +186,58 @@ func (g *Gateway) handleSourceDiscoverAPI(w http.ResponseWriter, r *http.Request return } + // ★ 显式生图声明:把 operator 点名的 id 从 chat 挪到 image。 + // + // 放在 selectModels **之前**:后者按 include/exclude 裁剪两个列表, + // 挪类必须在裁剪前完成,否则一个"只声明成生图、又被 include 选中"的 + // 模型会先在 chat 里被保留、再被这里挪走 —— 顺序反了会得到两份。 + // + // 只认**目录里确实存在的** id:写错一个字不该静默造出一个不存在的模型 + // (那会让源在每次照片请求时 404),而是明确报错。 + if len(req.ImageModels) > 0 { + have := map[string]bool{} + for _, m := range res.Models { + have[m] = true + } + for _, m := range res.ImageModels { + have[m] = true + } + var missing []string + force := map[string]bool{} + for _, id := range req.ImageModels { + if !have[id] { + missing = append(missing, id) + continue + } + force[id] = true + } + if len(missing) > 0 { + writeError(w, http.StatusBadRequest, "invalid_request", + "image_models contains ids that are not in the upstream catalog: "+ + strings.Join(missing, ", ")) + return + } + var keepChat []string + for _, m := range res.Models { + if !force[m] { + keepChat = append(keepChat, m) + } + } + seenImg := map[string]bool{} + var newImage []string + for _, m := range res.ImageModels { + seenImg[m] = true + newImage = append(newImage, m) + } + for id := range force { + if !seenImg[id] { + newImage = append(newImage, id) + } + } + res.Models = keepChat + res.ImageModels = newImage + } + chat, image, warns, err := selectModels(res.Models, res.ImageModels, req.Include, req.Exclude) if err != nil { // 400: the operator asked for a model the catalog does not have. diff --git a/internal/gateway/discover_test.go b/internal/gateway/discover_test.go index 2d18d0d..d1c432f 100644 --- a/internal/gateway/discover_test.go +++ b/internal/gateway/discover_test.go @@ -497,9 +497,6 @@ func TestModelsToConfig_PrioritiesAndKinds(t *testing.T) { if got[2].ID != "img1" || got[2].Kind != "image" { t.Errorf("image model mis-sorted: %+v", got[2]) } - if got[2].Priority <= got[0].Priority { - t.Errorf("image model priority %d should sort after chat %d", got[2].Priority, got[0].Priority) - } } // TestDiscoverModels_ImageModelsNeverNull guards the UI contract end to end, diff --git a/internal/gateway/gateway_test.go b/internal/gateway/gateway_test.go index 9e5a094..8a146f8 100644 --- a/internal/gateway/gateway_test.go +++ b/internal/gateway/gateway_test.go @@ -53,6 +53,42 @@ func newTestGateway(t *testing.T, srcs ...config.Source) *Gateway { if err := cfg.ApplyDefaults(); err != nil { t.Fatal(err) } + // ★ 测试默认建一条 AUTO 链(每个源一个 tier,按传入顺序),因为内核 + // **不再** seedAuto 自动播种规则了(那条废弃逻辑已删除:AUTO 链为空时 + // 网关应当直接 503,而不是凭空生成一堆用户没配过的档位)。 + // + // 但既有测试大量依赖"AUTO 能跑",它们此前是隐式吃 seedAuto 的。这里显式 + // 建链,既保持测试原意(验调度而不是验播种),也让"空链=503"成为 + // 一个**可以单独断言**的行为(见 TestChatAutoEmptyChainIsRejected)。 + // + // 顺序沿用 seedAuto 的老口径:**源按"最后一个最先"排**(tier 1 = 最后 + // 传入的源)。既有用例靠这个语义挑"high"源(TestChatAUTO 期望 high-m), + // 改成正序会让一批用例因为"挑到了另一个源"而红,而那与本次重构无关。 + // + // 所有源放在**同一个 tier**(tier 1),而不是一个源一个 tier:链内同一 + // tier 的多个 slot 会互相 failover,这正是 TestChatAutoChainTierFailover + // 要验的行为("a 挂 500 → 请求由 b 服务")。一源一 tier 会让 a 独占 tier1, + // b 在 tier2 永远轮不到,"两个源都被打过"这条断言就必然失败。 + if len(cfg.Auto) == 0 && len(srcs) > 0 { + // 一源一 tier,**倒序**:最后传入的源拿 tier 1(最先尝试)。 + // TestChatAUTO(low 先传、high 后传,期望 high)靠的就是这个语义。 + // 同 tier failover 由 TestChatAutoChainTierFailover 自己显式建链覆盖 —— + // 两条测试验的是不同机制(tier 优先 vs 同 tier 轮转),不能用同一个 + // 默认夹具同时满足。 + tier := 0 + for i := len(srcs) - 1; i >= 0; i-- { + tier++ + s := srcs[i] + for _, m := range s.Models { + if m.Kind == "image" { + continue // 图片模型不进 chat 链(与 buildAutoChain 同口径) + } + cfg.Auto = append(cfg.Auto, config.ModelScope{ + Model: m.ID, Source: s.Name, Tier: tier, + }) + } + } + } c, err := core.NewFromConfig(cfg) if err != nil { t.Fatalf("core: %v", err) @@ -107,9 +143,18 @@ func TestChatAutoChainTierFailover(t *testing.T) { defer aUp.Close() defer bUp.Close() g := newTestGateway(t, - config.Source{Name: "a", BaseURL: aUp.URL, Adapter: "openai", Models: []config.Model{{ID: "a-m", Priority: 100}}}, - config.Source{Name: "b", BaseURL: bUp.URL, Adapter: "openai", Models: []config.Model{{ID: "b-m", Priority: 10}}}, + config.Source{Name: "a", BaseURL: aUp.URL, Adapter: "openai", Models: []config.Model{{ID: "a-m"}}}, + config.Source{Name: "b", BaseURL: bUp.URL, Adapter: "openai", Models: []config.Model{{ID: "b-m"}}}, ) + // ★ 显式把两个源放进**同一 tier**:本用例验的是 tier 内失败轮转。 + // 默认夹具是一源一 tier(供 TestChatAUTO 验优先级),两者语义不同, + // 必须在这里覆盖,否则 b 在 tier2 永远轮不到。 + if err := g.core.SaveAutoRules([]config.ModelScope{ + {Model: "a-m", Source: "a", Tier: 1}, + {Model: "b-m", Source: "b", Tier: 1}, + }); err != nil { + t.Fatalf("save auto rules: %v", err) + } rr := doReq(t, g, "POST", "/v1/chat/completions", `{"model":"AUTO","messages":[{"role":"user","content":"hi"}]}`) if rr.Code != 200 { @@ -134,8 +179,8 @@ func TestChatAutoChain503Summary(t *testing.T) { defer aUp.Close() defer bUp.Close() g := newTestGateway(t, - config.Source{Name: "a", BaseURL: aUp.URL, Adapter: "openai", Models: []config.Model{{ID: "a-m", Priority: 100}}}, - config.Source{Name: "b", BaseURL: bUp.URL, Adapter: "openai", Models: []config.Model{{ID: "b-m", Priority: 10}}}, + config.Source{Name: "a", BaseURL: aUp.URL, Adapter: "openai", Models: []config.Model{{ID: "a-m"}}}, + config.Source{Name: "b", BaseURL: bUp.URL, Adapter: "openai", Models: []config.Model{{ID: "b-m"}}}, ) rr := doReq(t, g, "POST", "/v1/chat/completions", `{"model":"AUTO","messages":[{"role":"user","content":"hi"}]}`) @@ -156,7 +201,7 @@ func TestChatAutoQuotaSkip(t *testing.T) { up := upstream(t, ctrl) defer up.Close() g := newTestGateway(t, - config.Source{Name: "a", BaseURL: up.URL, Adapter: "openai", Models: []config.Model{{ID: "a-m", Priority: 100}}}, + config.Source{Name: "a", BaseURL: up.URL, Adapter: "openai", Models: []config.Model{{ID: "a-m"}}}, ) // one slot with an hourly quota of 1 token rr := doReq(t, g, "PUT", "/api/auto", @@ -191,7 +236,7 @@ func TestAutoStatesReportChainHealth(t *testing.T) { up := upstream(t, ctrl) defer up.Close() g := newTestGateway(t, - config.Source{Name: "a", BaseURL: up.URL, Adapter: "openai", Models: []config.Model{{ID: "a-m", Priority: 100}}}, + config.Source{Name: "a", BaseURL: up.URL, Adapter: "openai", Models: []config.Model{{ID: "a-m"}}}, ) doReq(t, g, "POST", "/v1/chat/completions", `{"model":"AUTO","messages":[{"role":"user","content":"hi"}]}`) @@ -234,7 +279,7 @@ func TestAutoSaveResetsCooldown(t *testing.T) { up := upstream(t, ctrl) defer up.Close() g := newTestGateway(t, - config.Source{Name: "a", BaseURL: up.URL, Adapter: "openai", Models: []config.Model{{ID: "a-m", Priority: 100}}}, + config.Source{Name: "a", BaseURL: up.URL, Adapter: "openai", Models: []config.Model{{ID: "a-m"}}}, ) rr := doReq(t, g, "POST", "/v1/chat/completions", `{"model":"AUTO","messages":[{"role":"user","content":"hi"}]}`) @@ -348,8 +393,8 @@ func TestChatAUTO(t *testing.T) { up := mockUpstream() defer up.Close() g := newTestGateway(t, - config.Source{Name: "low", BaseURL: up.URL, Adapter: "openai", Models: []config.Model{{ID: "low-m", Priority: 10}}}, - config.Source{Name: "high", BaseURL: up.URL, Adapter: "openai", Models: []config.Model{{ID: "high-m", Priority: 100}}}, + config.Source{Name: "low", BaseURL: up.URL, Adapter: "openai", Models: []config.Model{{ID: "low-m"}}}, + config.Source{Name: "high", BaseURL: up.URL, Adapter: "openai", Models: []config.Model{{ID: "high-m"}}}, ) // no model -> AUTO -> picks the highest priority source rr := doReq(t, g, "POST", "/v1/chat/completions", @@ -428,8 +473,8 @@ func TestImageAutoFallsOnlyToImageProviders(t *testing.T) { })) defer chatUp.Close() g := newTestGateway(t, - config.Source{Name: "chat", BaseURL: chatUp.URL, Adapter: "openai", Models: []config.Model{{ID: "chat-m", Priority: 100}}}, - config.Source{Name: "img", BaseURL: img.URL, Adapter: "openai", Models: []config.Model{{ID: "flux", Kind: "image", Priority: 1}}}, + config.Source{Name: "chat", BaseURL: chatUp.URL, Adapter: "openai", Models: []config.Model{{ID: "chat-m"}}}, + config.Source{Name: "img", BaseURL: img.URL, Adapter: "openai", Models: []config.Model{{ID: "flux", Kind: "image"}}}, ) rr := doReq(t, g, "POST", "/v1/images/generations", `{"model":"AUTO","prompt":"a cat"}`) diff --git a/internal/gateway/key_auto_api_test.go b/internal/gateway/key_auto_api_test.go index 7bb62cd..714822f 100644 --- a/internal/gateway/key_auto_api_test.go +++ b/internal/gateway/key_auto_api_test.go @@ -44,7 +44,7 @@ func keyAutoGateway(t *testing.T) *Gateway { }, Sources: []config.Source{ {Name: "s1", BaseURL: "http://127.0.0.1:1/v1", Adapter: "openai", - Models: []config.Model{{ID: "gpt-4o", Priority: 10}, {ID: "gpt-4o-mini", Priority: 5}}}, + Models: []config.Model{{ID: "gpt-4o"}, {ID: "gpt-4o-mini"}}}, }, } if err := cfg.ApplyDefaults(); err != nil { diff --git a/internal/gateway/key_quota_wiring_test.go b/internal/gateway/key_quota_wiring_test.go index db62184..24ea3eb 100644 --- a/internal/gateway/key_quota_wiring_test.go +++ b/internal/gateway/key_quota_wiring_test.go @@ -36,7 +36,7 @@ func quotaGateway(t *testing.T, keyA, keyB config.GWKey) (*Gateway, *upstreamCtr Keys: []config.GWKey{keyA, keyB}, Sources: []config.Source{{ Name: "up", BaseURL: up.URL, Adapter: "openai", - Models: []config.Model{{ID: "m1", Priority: 100}}, + Models: []config.Model{{ID: "m1"}}, }}, } if err := cfg.ApplyDefaults(); err != nil { @@ -306,14 +306,24 @@ func newQuotaGW(t *testing.T, upURL string, keys ...config.GWKey) *Gateway { Sources: []config.Source{{ Name: "up", BaseURL: upURL, Adapter: "openai", Models: []config.Model{ - {ID: "m1", Priority: 100}, - {ID: "m2", Priority: 90}, + {ID: "m1"}, + {ID: "m2"}, }, }}, } if err := cfg.ApplyDefaults(); err != nil { t.Fatal(err) } + + // 内核不再 seedAuto 自动播种 AUTO 链(空链=503 是刻意的)。本夹具的用例 + // 全都在验"AUTO 请求会不会被 key 配额挡住",必须显式建一条链 —— + // 否则每个用例都先撞 503,验的就不是配额了。 + if len(cfg.Auto) == 0 { + cfg.Auto = []config.ModelScope{ + {Model: "m1", Source: "up", Tier: 1}, + {Model: "m2", Source: "up", Tier: 2}, + } + } c, err := core.NewFromConfig(cfg) if err != nil { t.Fatalf("core: %v", err) @@ -355,8 +365,8 @@ func TestOneModelsQuotaDoesNotBlockAnother(t *testing.T) { Sources: []config.Source{{ Name: "up", BaseURL: up.URL, Adapter: "openai", Models: []config.Model{ - {ID: "m1", Priority: 100}, - {ID: "m2", Priority: 90}, + {ID: "m1"}, + {ID: "m2"}, }, }}, } diff --git a/internal/gateway/messages_test.go b/internal/gateway/messages_test.go index 873df95..4ce1410 100644 --- a/internal/gateway/messages_test.go +++ b/internal/gateway/messages_test.go @@ -106,7 +106,7 @@ func messagesGateway(t *testing.T) (*httptest.Server, string) { Sources: []config.Source{{ Name: "anth", BaseURL: up.URL, Adapter: "anthropic", APIKey: "k", MaxConcurrent: 4, - Models: []config.Model{{ID: "claude-test", Kind: "chat", Priority: 100}}, + Models: []config.Model{{ID: "claude-test", Kind: "chat"}}, }}, } diff --git a/internal/gateway/sources_api_test.go b/internal/gateway/sources_api_test.go index df753c7..c6d6695 100644 --- a/internal/gateway/sources_api_test.go +++ b/internal/gateway/sources_api_test.go @@ -71,11 +71,6 @@ func TestSourcePutUpdatesSource(t *testing.T) { continue } found = true - for _, m := range s.Models { - if m.ID == "m-one" && m.Priority != 42 { - t.Fatalf("priority not applied: %+v", s.Models) - } - } } if !found { t.Fatal("source vanished after PUT") diff --git a/internal/gateway/token_units_test.go b/internal/gateway/token_units_test.go index 12b09a4..b4274fe 100644 --- a/internal/gateway/token_units_test.go +++ b/internal/gateway/token_units_test.go @@ -101,7 +101,7 @@ func TestStreamedChatRecordsUpstreamUsage(t *testing.T) { defer up.Close() g := newTestGateway(t, config.Source{ Name: "up", BaseURL: up.URL, Adapter: "openai", - Models: []config.Model{{ID: "m1", Priority: 100}}, + Models: []config.Model{{ID: "m1"}}, }) rr := doReq(t, g, "POST", "/v1/chat/completions", @@ -127,7 +127,7 @@ func TestStreamedAndNonStreamedAgreeOnTokens(t *testing.T) { defer up.Close() g := newTestGateway(t, config.Source{ Name: "up", BaseURL: up.URL, Adapter: "openai", - Models: []config.Model{{ID: "m1", Priority: 100}}, + Models: []config.Model{{ID: "m1"}}, }) if rr := doReq(t, g, "POST", "/v1/chat/completions", @@ -167,7 +167,7 @@ func TestStreamedChatFallsBackToEstimateWithoutUsage(t *testing.T) { defer up.Close() g := newTestGateway(t, config.Source{ Name: "up", BaseURL: up.URL, Adapter: "openai", - Models: []config.Model{{ID: "m1", Priority: 100}}, + Models: []config.Model{{ID: "m1"}}, }) if rr := doReq(t, g, "POST", "/v1/chat/completions", @@ -189,7 +189,7 @@ func TestImageGenerationDoesNotRecordTokens(t *testing.T) { defer up.Close() src := config.Source{ Name: "up", BaseURL: up.URL, Adapter: "openai", - Models: []config.Model{{ID: "img-m", Priority: 100, Kind: "image"}}, + Models: []config.Model{{ID: "img-m", Kind: "image"}}, } g := newTestGateway(t, src) diff --git a/internal/gateway/ui/index.html b/internal/gateway/ui/index.html index e4b0091..1c52391 100644 --- a/internal/gateway/ui/index.html +++ b/internal/gateway/ui/index.html @@ -435,6 +435,8 @@ /* ---- scratch-style priority canvas (sakura restyle, same classes) ---- */ .kind-toggle{display:inline-flex;gap:4px;margin-right:8px} + /* 对话/生图的分段栏:贴着内容顶部,不额外占标题位 */ + .chat-mode-bar{display:flex;align-items:center;gap:8px;padding:6px 0 10px} .kind-toggle button{padding:4px 12px;font-size:11.5px} .sort-canvas{position:relative;min-height:420px;padding:22px 14px 30px;margin:4px 0 10px;background-color:var(--card2); background-image:linear-gradient(var(--line-strong) 1px,transparent 1px),linear-gradient(90deg,var(--line-strong) 1px,transparent 1px); @@ -589,21 +591,6 @@ />对话 - + + + + +
+
M
@@ -2960,6 +3011,8 @@ async function renderChat() { const s = await api("/api/status"); const opts = []; if (Array.isArray(s.sources) && s.sources.length) { + // 同 chat 下拉:只显示模型名,同名模型只出一行(内核自己会跨源回退)。 + const seenImg = new Set(); s.sources.forEach((src) => { const kinds = Array.isArray(src.model_kinds) && src.model_kinds.length ? src.model_kinds @@ -2968,16 +3021,17 @@ async function renderChat() { const id = typeof m === "string" ? m : m.id; const kind = typeof m === "string" ? "chat" : m.kind; if (kind !== "image") return; - opts.push( - ``, - ); + if (seenImg.has(id)) return; + seenImg.add(id); + opts.push(``); }); }); } const body = opts.length ? "" : `
${esc(t("imgNoModels"))}
`; - $("#tab-image").innerHTML = ` + // 渲染到对话页里的生图面板(不是独立 tab) + $("#ct-image-pane").innerHTML = `
@@ -3413,7 +3467,7 @@ async function renderChat() { // Editing: the single-source shape. Creating: an empty form. const s = name ? src.source - : { name: "", models: [{ id: "", priority: 0, kind: "chat" }] }; + : { name: "", models: [{ id: "", kind: "chat" }] }; if (!s) { toast(t("toastSave")); return; @@ -3473,7 +3527,7 @@ async function renderChat() { const box = $("#s-models"); (s.models && s.models.length ? s.models - : [{ id: "", priority: 0, kind: "chat" }] + : [{ id: "", kind: "chat" }] ).forEach((m, i) => box.insertAdjacentHTML("beforeend", modelRow(m, i)), ); @@ -3481,7 +3535,7 @@ async function renderChat() { .catch(() => {}); } function modelRow(m, i) { - return `
+ return `
@@ -3506,7 +3560,7 @@ async function renderChat() { const div = $("#s-models"); div.insertAdjacentHTML( "beforeend", - modelRow({ id: "", priority: 0, kind: "chat" }, div.children.length), + modelRow({ id: "", kind: "chat" }, div.children.length), ); } // srcDiscover asks the gateway to probe the upstream for its catalog and @@ -3574,8 +3628,7 @@ async function renderChat() { modelRow( { id: id, - priority: image.indexOf(id) >= 0 ? 70 : 50, - kind: image.indexOf(id) >= 0 ? "image" : "chat", + kind: image.indexOf(id) >= 0 ? "image" : "chat", }, i, ), @@ -3603,8 +3656,7 @@ async function renderChat() { const models = [...document.querySelectorAll("#s-models .model-row")] .map((row) => ({ id: row.querySelector(".m-id").value.trim(), - priority: parseInt(row.dataset.priority) || 0, - kind: row.querySelector(".m-kind").value, + kind: row.querySelector(".m-kind").value, })) .filter((m) => m.id); let meta = {}; @@ -3659,8 +3711,7 @@ async function renderChat() { const models = [...document.querySelectorAll("#s-models .model-row")] .map((row) => ({ id: row.querySelector(".m-id").value.trim(), - priority: parseInt(row.dataset.priority) || 0, - kind: row.querySelector(".m-kind").value, + kind: row.querySelector(".m-kind").value, })) .filter((m) => m.id); let meta = {}; @@ -3774,7 +3825,7 @@ async function renderChat() { box.innerHTML = ""; (tpl.models && tpl.models.length ? tpl.models - : [{ id: "", priority: 0, kind: "chat" }] + : [{ id: "", kind: "chat" }] ).forEach((m, i) => box.insertAdjacentHTML("beforeend", modelRow(m, i)), ); @@ -3837,7 +3888,7 @@ async function renderChat() { const tlist = tplsR.templates || []; const s = tlist.find((x) => x.name === name) || { name: name, - models: [{ id: "", priority: 0, kind: "chat" }], + models: [{ id: "", kind: "chat" }], }; const cur = s.adapter || "openai"; const apps = ["", ...(st.adapters || []).map((a) => a.name)]; @@ -3886,7 +3937,7 @@ async function renderChat() { const box = $("#s-models"); (s.models && s.models.length ? s.models - : [{ id: "", priority: 0, kind: "chat" }] + : [{ id: "", kind: "chat" }] ).forEach((m, i) => box.insertAdjacentHTML("beforeend", modelRow(m, i)), ); @@ -3984,24 +4035,23 @@ async function renderChat() { function buildSortIndex(sources) { const byModel = new Map(); const byPair = new Map(); - const sourceRows = new Map(); (sources || []).forEach((s) => (s.models || []).forEach((m) => { - const it = { src: s.name, id: m.id, prio: m.priority || 0, kind: m.kind }; + // `prio` 不再携带 models[].priority(该字段已删除); + // kind 供画布区分聊天/生图。 + const it = { src: s.name, id: m.id, kind: m.kind }; byPair.set(m.id + "|" + s.name, it); if (!byModel.has(m.id)) byModel.set(m.id, it); - if (!sourceRows.has(it.prio)) sourceRows.set(it.prio, []); - sourceRows.get(it.prio).push({ src: s.name, id: m.id }); }), ); - return { byModel, byPair, sourceRows }; + return { byModel, byPair }; } // buildLanes compiles saved rules into the tier-lane structure the canvas // paints. With no rules it falls back to discovery, grouped by source // priority, so an unconfigured chain still shows every available slot. // Shared by the global editor and the per-key editor. function buildLanes(idx, rules, kind) { - const { byModel, byPair, sourceRows } = idx; + const { byModel, byPair } = idx; if (rules.length) { const tiers = []; rules.forEach((r, i) => { @@ -4026,23 +4076,6 @@ async function renderChat() { .filter(Boolean) .map((models, i) => ({ prio: (tiers.length - i) * 10, models })); } - return [...sourceRows.entries()] - .sort((a, b) => b[0] - a[0]) - .map(([prio, models]) => { - const same = models.filter((m) => { - const it = byPair.get(m.id + "|" + m.src); - const k = it ? it.kind : "chat"; - return k === kind; - }); - if (!same.length) return null; - same.sort((x, y) => (x.src < y.src ? -1 : x.src > y.src ? 1 : 0)); - same.forEach((m) => { - m.uid = nexUid(); - m.meta = null; - }); - return { prio, models: same }; - }) - .filter(Boolean); } async function renderSort() { const j = await api("/api/v1/sources"); @@ -4060,9 +4093,8 @@ async function renderChat() { ); } catch (e) {} const sortIdx = buildSortIndex(j.sources); - // build a lane structure for one kind from its saved rules; when - // rules are empty, fall back to discovery from sourceRows filtered by - // kind so an unconfigured chain still shows all available slots + // 按**已保存的规则**编译两种链的画布;无规则时画布为空(不回退 discovery, + // 因为网关在 AUTO 链为空时直接 503,画布必须如实反映"没配")。 sortLanes.chat = buildLanes(sortIdx, autoR, "chat"); sortLanes.image = buildLanes(sortIdx, autoImg, "image"); sortState.lanes = sortLanes[sortState.kind] || []; @@ -6267,7 +6299,6 @@ toast(t("kAutoChainGlobal")); const done = () => remountPluginElements(); if (tab === "status") return renderStatus().then(done, done); if (tab === "chat") return renderChat().then(done, done); - if (tab === "image") return renderImage().then(done, done); if (tab === "keys") return renderKeys().then(done, done); if (tab === "sort") return renderSort().then(done, done); if (tab === "sources") return renderSources().then(done, done); diff --git a/internal/gateway/ui_image_page_test.go b/internal/gateway/ui_image_page_test.go index 5f533ba..99e2d07 100644 --- a/internal/gateway/ui_image_page_test.go +++ b/internal/gateway/ui_image_page_test.go @@ -42,28 +42,47 @@ func TestUI_ChatPageGroupsImageModels(t *testing.T) { } } -// TestUI_HasDedicatedImagePage pins the second half of the fix: image models -// need somewhere they CAN be tested. -func TestUI_HasDedicatedImagePage(t *testing.T) { +// TestUI_ImageModeIsReachableFromChatTab 钉住生图**仍可达**。 +// +// ★ 断言已随 UI 结构调整:生图不再是独立侧栏项,而是对话页里的一个分段模式。 +// 原先这条测试钉的是 `data-tab="image"` / `id="tab-image"` / `tab === "image"` +// —— 三者都已随合并移除。若继续钉旧结构,它只会红着挡住重构,而检不出 +// "生图入口彻底消失"这种真回归。所以改为钉**合并后的可达性**: +// 分段控件在、切换函数在、面板容器在、端点仍在。 +// +// 为什么"可达性"才是要守的东西:合并的动机是少一个导航项,而不是把生图功能 +// 藏起来。只要用户能从对话页一键切到生图并真的发出请求,这个功能就是完整的。 +func TestUI_ImageModeIsReachableFromChatTab(t *testing.T) { ui := uiSource(t) for _, want := range []string{ - `data-tab="image"`, // sidebar entry - `id="tab-image"`, // pane - `function renderImage`, // renderer registered with refresh() - `tab === "image"`, // dispatched - `/v1/images/generations`, // the endpoint the page actually calls + `class="chat-mode-bar"`, // 分段栏存在 + `switchChatMode('image')`, // 能切到生图 + `id="ct-image-pane"`, // 生图面板容器 + `function renderImage`, // 渲染器还在 + `/v1/images/generations`, // 真正被调用的端点 } { if !strings.Contains(ui, want) { - t.Errorf("image page is missing %q", want) + t.Errorf("生图模式不可达,缺少 %q", want) } } - // The page must be reachable from TABS; goTab iterates TABS to toggle pane - // visibility, so a pane outside that list is present but permanently hidden — - // which reads as "the page is blank" because the content is in the DOM. - if !strings.Contains(ui, `"image"`) { - t.Error(`"image" does not appear in the TABS list`) + // 合并后**不应**再出现独立 tab 的三件套 —— 它们会让 goTab 去找一个不存在的 + // 面板($("#tab-image") 为 null ⇒ 点侧栏抛错)。 + for _, gone := range []string{ + `data-tab="image"`, + `id="tab-image"`, + `tab === "image"`, + } { + if strings.Contains(ui, gone) { + t.Errorf("生图已并入对话页,不应再有独立 tab 结构 %q"+ + "(否则 goTab 会找一个不存在的面板)", gone) + } + } + + // 面板必须在 DOM 里且**不能被初始隐藏到底**:切换函数用 display 控制。 + if !strings.Contains(ui, `ct-chat-pane`) { + t.Error("缺少对话面板容器 ct-chat-pane(切换需要两个容器同时存在)") } } diff --git a/internal/lua/plugins/channels.lua b/internal/lua/plugins/channels.lua index 10f70ae..ce25179 100644 --- a/internal/lua/plugins/channels.lua +++ b/internal/lua/plugins/channels.lua @@ -153,6 +153,14 @@ local lobsteraiClientVersion local expiringWindowDays local fetchAccountJSON +-- ★ 选号链路的前向声明(第 11 次踩同一个坑) +-- pickAccountForSource 定义在 syncProviderSource 旁边(~4160),但它依赖 +-- accountBalanceRaw / balanceTier(~6690/6716)。不声明的话那两个名字在 +-- 定义处会被解析成**全局**(nil),选号时抛 +-- `attempt to call global 'accountBalanceRaw' (a nil value)` —— account_add +-- 直接 500,源根本注册不出来(已实测踩过)。 +local pickAccountForSource, accountBalanceRaw, balanceTier + -- ★★ 这批前向声明必须在 PLATFORMS **之前**:平台表里的 headers_fn / claim_fn -- 闭包会在**运行时**调用这些函数,而闭包捕获的是**词法作用域里的那个变量**。 -- 若声明写在后面(例如 line ~5479),PLATFORMS 段里的引用会被解析成**全局** @@ -4156,16 +4164,108 @@ local CHANNEL_CREDITS = { -- 每个账号一条上游源:channels--。模型开关即改写 -- 这条源的 models 列表(remove+add 重建;内核 add_source 同名覆盖,但显式 -- 先 remove 更诚实,避免旧模型残留)。 +-- +-- ★ 现在**一个通道 = 一个适配器 = 一个源**,源名只跟通道绑定。 +-- 旧设计是「一账号一源」(channels--),它有三个 +-- 结构性后果,全都在生产里出现过: +-- 1. 三个 trae 账号 ⇒ 三个源、三份同名模型。用户在模型下拉框里看到三行 +-- 无法区分的东西(channels-trae-aaa · glm-5.2 / ...bbb · glm-5.2)。 +-- 2. 谁先谁后**取决于注册顺序,不是余额**。余额用完的号可能排在前面, +-- 每次都先撞它再回退。 +-- 3. 换号要改源名 ⇒ 用户书签/脚本里的 `源:模型` 全部失效。 +-- 新设计下换号 = 用同名 add_source 覆盖 api_key(内核 AddSource 是 +-- UpsertSourceInYAML + 内存替换),对客户端完全透明。 +local function providerSourceName(provider) + return "channels-" .. provider +end + +-- legacy 源名(旧版按账号拆源的产物)。保留只为了迁移时能删掉旧源。 local function accountSourceName(provider, accountId) return "channels-" .. provider .. "-" .. accountId end --- syncAccountSource 把某账号的上游源与(平台模型目录 - 黑名单)对齐。 --- 无凭据(占位账号)不动源。 -local function syncAccountSource(provider, accountId) +-- syncProviderSource(provider):把该通道的**唯一**上游源与模型目录对齐。 +-- +-- ★ 这是「一个通道 = 一个适配器 = 一个源」的落点。换号完全在插件内部完成, +-- 内核只看到一个源(同名 upsert),客户端完全无感。 +-- +-- 幂等:可在任何“该用哪个号可能变了”的时刻重复调(账号增删改 / 余额刷新 / +-- 领取完成 / 续期成功 / 30 分钟心跳巡检)。 +-- pickAccountForSource(plat):从该平台的账号池里挑一个**现在能用**的号。 +-- +-- 判据顺序(每一级都是真实故障的产物): +-- 1. 凭据读得出来(占位号 / 密文损坏的号直接跳过) +-- 2. 余额可查且有余量(与 rankAccounts 同口径:先用到快作废的,再用永久的) +-- • 没有 balance 声明的平台不据此排除 —— 不能因为"我们不会查"就把可用号判死 +-- • 查询失败同理归入"未知",保留可用性 +-- 3. 排除已打失效标记的号(request_end 钩子根据**真实请求失败**打的) +-- +-- 返回 (acct, reason)。reason 用于日志,让"为什么选它"可复查。 +pickAccountForSource = function(plat) + local accounts = poolList(plat.id) + if #accounts == 0 then return nil, "无账号" end + + local withCred = {} + for _, a in ipairs(accounts) do + if a.enabled ~= false then + local tok + if plat.credential_shape == "full" then + tok = __llmsproxy_secrets.get(a.credentialRef) + else + tok = credentialOf(a.credentialRef) + end + if tok ~= nil and tok ~= "" then withCred[#withCred + 1] = a end + end + end + if #withCred == 0 then return nil, "无可用凭据(占位账号或密文不可读)" end + + local ranked = withCred + if plat.balance then + local allowPermanent = not (plugin.state.settings + and plugin.state.settings.lock_permanent_credits) + local expiring, permanent, unknown = {}, {}, {} + for _, a in ipairs(withCred) do + local raw = accountBalanceRaw(plat.id, a.id) + if raw == nil then + unknown[#unknown + 1] = a -- 查不到 ⇒ 不据此排除 + else + local tier = balanceTier(raw.expiring_balance or raw.expiringBalance, + raw.permanent_balance or raw.permanentBalance, allowPermanent) + if tier == "expiring" then expiring[#expiring + 1] = a + elseif tier == "permanent" then permanent[#permanent + 1] = a + else unknown[#unknown + 1] = a end + end + end + ranked = {} + for _, a in ipairs(expiring) do ranked[#ranked + 1] = a end + for _, a in ipairs(permanent) do ranked[#ranked + 1] = a end + for _, a in ipairs(unknown) do ranked[#ranked + 1] = a end + if #ranked == 0 then return nil, "所有账号余额均不可用" end + end + + for _, a in ipairs(ranked) do + if not a.termErr then + return a, "选中账号 " .. tostring(a.id) + .. (a.nickname and a.nickname ~= "" and ("(" .. a.nickname .. ")") or "") + end + end + return ranked[1], "所有账号均标记失效,回退到 " .. tostring(ranked[1].id) +end +local function syncProviderSource(provider) local plat = platformById(provider) - local acct = poolGet(provider, accountId) - if not plat or not acct then return end + if not plat then return end + -- ★ 自动选号:凭据可用 + 余额分档 + 跳过已标失效的号。 + -- 判据全部在插件内(内核不知道账号概念)。 + local acct, why = pickAccountForSource(plat) + if not acct then + -- 没有可用账号 ⇒ **撤掉源**。留着旧源会让模型继续出现在列表里却每次都 + -- 失败(用户无法区分"我没配"和"配了但坏了")。 + local gone = providerSourceName(provider) + __llmsproxy_kernel.call("remove_source", { name = gone }) + if plugin.state.chosen then plugin.state.chosen[provider] = nil end + logEvent("通道 " .. provider .. " 无可用账号,已撤源:" .. tostring(why), "warn", provider) + return + end -- 凭据有两种消费方式,取决于平台的适配器: -- * 多数平台:适配器发 `Authorization: Bearer ` -- → 这里必须交出**裸 access token**(不能把整个 JSON 当 key 发上去) @@ -4182,8 +4282,15 @@ local function syncAccountSource(provider, accountId) tok = credentialOf(acct.credentialRef) err = (tok == nil or tok == "") and "无凭据" or nil end - if err then return end - local name = accountSourceName(provider, accountId) + if err then + logEvent("通道 " .. provider .. " 凭据读取失败,跳过同步", "warn", provider) + return + end + -- ★ 记录"当前为该通道服务的账号"。request_end 钩子靠它把真实请求的 + -- 失败原因归因到具体账号(否则只能知道“这个通道坏了”,不知道是哪个号)。 + plugin.state.chosen = plugin.state.chosen or {} + plugin.state.chosen[provider] = acct.id + local name = providerSourceName(provider) local models = {} local disabled = disabledModelsOf(provider) -- 用**有效目录**(远端优先、兜底补位),不是硬编码表 @@ -4248,20 +4355,46 @@ local function syncAccountSource(provider, accountId) for _, mk in ipairs({ "uid", "device_id", "machine_id", "enterprise_id" }) do if cmeta[mk] ~= nil and cmeta[mk] ~= "" then src.meta[mk] = cmeta[mk] end end - end + end end - local r, aerr = __llmsproxy_kernel.call("add_source", { source = src }) - -- 失败要**记日志**:源注册失败此前是静默的(插件没权限、凭据形状不符都会 - -- 走到这里),表现为"账号加了但不出源",排查时没有任何线索。 + -- ★ 先清掉旧版的**按账号拆的源**(迁移)。不清的话升级后旧源还在, + -- 模型列表里会有重复项,且旧源指向已经不该用的账号。 + -- 按已知平台 id 前缀匹配(不用贪婪模式:账号 id 可能含 `-`)。 + -- 只在真正要写源时才扫一遍(低频)。 + do + local ls = __llmsproxy_kernel.call("list_sources", {}) + local arr = (ls and ls.json and ls.json.sources) or (ls and ls.sources) or {} + if type(arr) ~= "table" then arr = {} end + local legacyPrefix = "channels-" .. provider .. "-" + for _, exist in ipairs(arr) do + local sn = type(exist) == "table" and exist.name or nil + if type(sn) == "string" and sn ~= name + and sn:sub(1, #legacyPrefix) == legacyPrefix then + __llmsproxy_kernel.call("remove_source", { name = sn }) + logEvent("已清理旧版按账号拆源 " .. sn, "task", provider) + end + end + end + local r, aerr = __llmsproxy_kernel.call("add_source", { source = src }) + -- 失败要**记日志**:源注册失败此前是静默的(插件没权限、凭据形状不符都会 + -- 走到这里),表现为"账号加了但不出源",排查时没有任何线索。 if aerr then logEvent("接入源失败 " .. name .. ": " .. tostring(aerr), "error", provider) elseif r and r.json and r.json.ok == false then logEvent("接入源失败 " .. name .. ": " .. tostring(r.json.error), "error", provider) else - logEvent("已同步源 " .. name .. "(" .. #models .. " 模型)", "task", provider) + logEvent("已同步源 " .. name .. "(" .. #models .. " 模型,账号 " + .. tostring(acct.id) .. ")", "task", provider) end end +-- syncAccountSource 保留为**兼容壳**:旧调用点很多(13 处),逐个改风险大。 +-- 语义变为"这个平台的源该重算了"(**忽略** accountId)—— 因为现在一通道只有 +-- 一个源,账号维度的差异完全由 syncProviderSource 内部消化。 +local function syncAccountSource(provider, _accountId) +syncProviderSource(provider) +end + -- dropAccountSource:把某账号的上游源撤掉(账号停用/删除时调用)。 -- -- ★ 必须**检查返回值**:内核的 remove_source 需要**单独授予**(它是 Destructive 级, @@ -4272,19 +4405,32 @@ end -- 的 remove 失败**看不出来**(add 会把同名覆盖掉)—— 只有纯删除路径才暴露。 -- 故这里把失败**记进事件日志**,让它在面板上可见,而不是只存在于一个被丢弃的返回值里。 local function dropAccountSource(provider, accountId) - local name = accountSourceName(provider, accountId) + -- ★ 语义变了(一通道一源之后):账号被删/停用**不能**直接把通道源撤掉 —— + -- 那个源现在代表**整个通道**,池里可能还有别的号能用。正确做法是重新 + -- 选号:syncProviderSource 会挑下一个可用账号并用同名覆盖,没有可用 + -- 账号时它自己会撤源。 + -- + -- 迁移期要兼顾旧状态:如果库里还有旧版按账号拆的源(channels-p-), + -- 那个才是该删的。两步都做。 + local legacy = accountSourceName(provider, accountId) -- ★ 内核桥是 `call(name, args) -> (result, nil) | (nil, err)`: -- 失败时**第一个返回值是 nil**,原因在**第二个返回值**里。 -- 我第一版写成 `local r = call(...)` 再读 `r.ok` ⇒ 恒 nil ⇒ 日志只说"无返回", -- 把真正原因(not granted / 超时 / 拒删最后一个源)丢掉 —— 一句不可操作的 -- 诊断比没有更糟。两个返回值都要接。 - local r, err = __llmsproxy_kernel.call("remove_source", { name = name }) + local r, err = __llmsproxy_kernel.call("remove_source", { name = legacy }) if r == nil or r.ok ~= true then - logEvent("撤源失败 " .. tostring(name) .. ": " .. tostring(err or "(无错误信息)") - .. " | 若为 not granted,需给 channels 插件授予 remove_source(声明在 plugin.kernel)", - "error", provider) - return false, err + -- 旧源不存在是**正常**的(新部署根本没启过它),不当作失败。 + local msg = tostring(err or "") + if not msg:find("not found", 1, true) and not msg:find("不存在", 1, true) then + logEvent("撤旧源失败 " .. tostring(legacy) .. ": " .. tostring(err or "(无错误信息)") + .. " | 若为 not granted,需给 channels 插件授予 remove_source(声明在 plugin.kernel)", + "error", provider) + return false, err + end end + -- 重算通道源:池里还有别的号就自动接上,没了就撤掉整个通道源。 + syncProviderSource(provider) return true end @@ -6223,7 +6369,7 @@ function plugin.complete_login(req) end logEvent("账号凭据已入池 " .. plat.id .. "/" .. aid) syncAccountSource(plat.id, aid) - return { status = 200, json = { ok = true, account_id = aid, source = accountSourceName(plat.id, aid) } } + return { status = 200, json = { ok = true, account_id = aid, source = providerSourceName(plat.id) } } end -- 兼容旧路径:单账号模式(e2e 与既有端点仍走它)。 @@ -6671,7 +6817,7 @@ end -- "expiring" 有 15 天内到期的积分 → 最优先(不用就作废) -- "permanent" 只剩永久积分 → 次优先;锁定永久积分时视为不可用 -- "none" 都没有 → 不可用 -local function balanceTier(expiring, permanent, allow_permanent) +balanceTier = function(expiring, permanent, allow_permanent) local function pos(v) local n = tonumber(v) if n and n > 0 then return n end @@ -6697,7 +6843,7 @@ end -- accountBalanceRaw(provider, accountId):取该账号的余额原料(带 TTL 缓存)。 -- 失败**不抛错**(照参考:查询失败归入最后一档),返回 nil 让调用方降级。 -local function accountBalanceRaw(provider, accountId) +accountBalanceRaw = function(provider, accountId) -- 用通用 TTL 缓存(照参考 ttl-cache):命中即返回、在飞去重、失败不缓存。 -- ⚠️ 缓存的是**原料**(包列表明细),分桶每次都现算 —— 见本节的注释。 local plat = platformById(provider) @@ -7029,7 +7175,12 @@ function plugin.refresh_creds() local now = os.time and os.time() or 0 local refreshed, skipped, failed = 0, 0, {} for _, plat in ipairs(allPlatforms()) do - if plat.exchange_body or plat.refresh_url then + -- ★ 三种续期声明都要认:声明式 refresh.url、旧的 refresh_url、钩子式 refresh_fn。 + -- 真实缺陷:此前只认前两种 ⇒ codearts 的 refresh_fn 挂上了也永远不会被 + -- 定时任务触发,token 到期后源就静静地 400。refresh_creds 是这条链路唯一入口。 + if plat.exchange_body or plat.refresh_url + or (type(plat.refresh) == "table" and plat.refresh.url) + or type(plat.refresh_fn) == "function" then for _, a in ipairs(poolList(plat.id)) do local cred = credentialFull(a.credentialRef) if type(cred) == "table" then @@ -7064,6 +7215,14 @@ function plugin.refresh_creds() if #failed > 0 then logEvent("凭据续期失败 " .. #failed .. " 个:" .. plugin.utf8Clip(table.concat(failed, "; "), 300), "warn") end + -- ★ 每次续期巡检后重新选号(每 30 分钟一次,是「余额/凭据变了」的自然节拍)。 + -- 一通道一源:换号 = 同名 add_source 改 api_key,对客户端完全透明。 + -- 这是「插件自动察觉账号余额用尽并切到有余额的账号」的**兜底心跳** —— + -- 即使没有任何事件触发(没人点刷新、没登录新号),最迟 30 分钟内也会 + -- 重新挑一次号。纯本地判定(余额有 TTL 缓存),不产生上游请求。 + for _, plat in ipairs(allPlatforms()) do + syncProviderSource(plat.id) + end end -- todayKey():当天标识(UTC+8 口径,与活动结算口径一致)。 @@ -7504,7 +7663,7 @@ function plugin.account_test(req) local srcs, _ = __llmsproxy_kernel.call("list_sources", {}) local found = false for _, s in ipairs(srcs or {}) do - if s.name == accountSourceName(plat.id, acct.id) then found = true break end + if s.name == providerSourceName(plat.id) then found = true break end end return { status = 200, json = { ok = found, probed = false, error = found and nil or "源未同步", @@ -8804,17 +8963,37 @@ function plugin.reap_orphan_sources(req) local found, removed, failed = {}, 0, {} for _, x in ipairs(arr) do - local nm = type(x) == "table" and x.name or nil - if type(nm) == "string" then - local plat, acct = nil, nil - for _, p in ipairs(PLATFORMS) do - local pref = "channels-" .. p.id .. "-" - if nm:sub(1, #pref) == pref then - plat, acct = p.id, nm:sub(#pref + 1) - break + local nm = type(x) == "table" and x.name or nil + if type(nm) == "string" then + local plat, acct, why = nil, nil, nil + -- 形态 1(旧版残留):channels-<平台>-<账号id>,账号已不在池里 ⇒ 孤儿。 + -- 按**已知平台前缀**匹配,不能用 `channels-(.+)-(.+)$`(Lua 的 `-` 是贪婪的, + -- 账号 id 含 `-` 会被切错 —— 判据里专门放了 dead-acct-1 咬这一条)。 + for _, p in ipairs(PLATFORMS) do + local pref = "channels-" .. p.id .. "-" + if nm:sub(1, #pref) == pref then + plat, acct = p.id, nm:sub(#pref + 1) + break + end end - end - if plat and acct ~= "" and poolGet(plat, acct) == nil then + if plat and acct ~= "" and poolGet(plat, acct) == nil then + why = "账号 " .. acct .. " 已不在池中" + end + -- 形态 2(一通道一源之后的真实孤儿):channels-<平台> 但该平台 + -- **没有任何可用账号**(全删了/全停用/凭据全读不出来)。 + if plat == nil then + for _, p in ipairs(PLATFORMS) do + if nm == "channels-" .. p.id then + local pok, acc, areason = pcall(pickAccountForSource, p) + if not pok then acc = nil areason = "选号失败: " .. tostring(acc) end + if not acc then + plat, why = p.id, "该通道无可用账号:" .. tostring(areason) + end + break + end + end + end + if plat and why then found[#found + 1] = nm if not dry then local r, err = __llmsproxy_kernel.call("remove_source", { name = nm }) @@ -8824,7 +9003,7 @@ function plugin.reap_orphan_sources(req) "error", plat) else removed = removed + 1 - logEvent("孤儿源已清理 " .. nm .. "(账号 " .. acct .. " 已不在池中)", "warn", plat) + logEvent("孤儿源已清理 " .. nm .. "(" .. tostring(why) .. ")", "warn", plat) end end end @@ -11913,6 +12092,100 @@ end -- plugin.credits_tier_probe:只给测试用 —— 单账号的余额分档结果。 -- 暴露 expiring/permanent/tier/usable 四个值,让判据能逐条钉住分档规则 -- (含"失效包必须跳过""到期未知归永久""锁定永久积分时只剩永久的号不可用")。 +-- ============================================================================ +-- 账号有效性反馈:从真实请求结果里学习「哪个号该被跳过」 +-- ============================================================================ +-- +-- 为什么需要这条链路 +-- ------------------ +-- 选号(pickAccountForSource)判的是**余额**,但余额查询有三个盲区: +-- 1. 有些平台没有余额端点 ⇒ accountBalanceRaw 恒 nil +-- 2. 余额查询有 TTL 缓存(60s)⇒ 用尽的瞬间不会立刻反映 +-- 3. 余额 > 0 但账号被风控/封禁 ⇒ 余额看起来完好,实际全失败 +-- +-- 唯一能覆盖这三点的证据是**真实请求的失败原因**。所以挂 request_end: +-- 当这个通道的请求失败、且错误文本是「终态」的(需充值 / 封禁 / 凭据失效)时, +-- 给当前选中的账号打 termErr 标记,下一次选号跳开它。 +-- +-- ⚠️ 只认**终态**错误。普通 429 限流、超时、网络抖动都**不**标记 —— +-- 那些会自动恢复,标记它们等于把好号一个个废掉(把一次请求层面的拒绝 +-- 当终态,代价是把材料完好的账号一步标死)。 +-- +-- 解除标记的路径:请求成功 / 账号重新登录 / 手动 account_reset。 + +-- plugin.term_error_kind(msg):把错误文本分类为终态错误,返回原因或 nil。 +function plugin.term_error_kind(msg) + if type(msg) ~= "string" or msg == "" then return nil end + local low = msg:lower() + -- 额度类:明确说用尽且需要充值(不是"当日免费额度,明天恢复"那种) + if low:find("insufficient", 1, true) or low:find("余额不足", 1, true) + or low:find("请充值", 1, true) or low:find("insufficient_balance", 1, true) + or low:find("额度已用完", 1, true) then + return "余额不足(需充值)" + end + -- 封禁 / 风控 / 账号停用 + if low:find("banned", 1, true) or low:find("封禁", 1, true) + or low:find("账号已停用", 1, true) then + return "账号被封禁/停用" + end + -- 凭据失效(refresh_token 已作废这类不可自愈的) + if low:find("refresh token has been used", 1, true) + or low:find("invalid_grant", 1, true) then + return "凭据已永久失效(需重新登录)" + end + return nil +end + +-- plugin.mark_account_term_error(provider, kind):给**当前为该通道服务**的号打标记。 +function plugin.mark_account_term_error(provider, kind) + local plat = platformById(provider) + if not plat then return end + local cur = plugin.state.chosen and plugin.state.chosen[provider] + if not cur then return end + local acct = poolGet(provider, cur) + if not acct then return end + if acct.termErr == kind then return end -- 已经标过,别刷日志 + acct.termErr = kind + acct.termErrAt = os.time and os.time() or 0 + poolAdd(provider, acct) + markDirty() + logEvent("账号 " .. tostring(cur) .. " 标记失效:" .. tostring(kind) + .. " —— 下次选号将跳过它", "warn", provider) +end + +-- 插件钩子:request_end 在每次请求结束时触发。 +-- ⚠️ 声明 hooks 不妨碍自有 HTTP 路由 —— 本插件的状态变更仍走自己的路由。 +plugin.hooks = { request_end = "on_request_end" } + +function plugin.on_request_end(payload) + if type(payload) ~= "table" then return nil end + local src = tostring(payload.source or "") + -- 只处理本插件管辖的通道(`channels-`),其他源不碰。 + if src:sub(1, 9) ~= "channels-" then return nil end + local provider = src:sub(10) + local cur = plugin.state.chosen and plugin.state.chosen[provider] + if not cur then return nil end + local acct = poolGet(provider, cur) + if not acct then return nil end + + if payload.ok then + -- 成功 ⇒ 清掉失效标记(它显然能用)。 + if acct.termErr then + acct.termErr = nil + acct.termErrAt = nil + poolAdd(provider, acct) + markDirty() + logEvent("账号 " .. tostring(cur) .. " 恢复正常(请求成功)", "info", provider) + end + return nil + end + -- 失败 ⇒ 只有"终态"错误才标记。payload 里的错误文本字段名不定, + -- 三个都看(内核不同路径填的字段不同)。 + local msg = tostring(payload.error or payload.message or payload.error_message or "") + local kind = plugin.term_error_kind(msg) + if kind then plugin.mark_account_term_error(provider, kind) end + return nil +end function plugin.credits_tier_probe(args) args = args or {} local provider = tostring(args.platform or "") @@ -12500,7 +12773,8 @@ function plugin.__sync_source_probe(args) -- 回报同步后内核里该源是否存在 local ls = __llmsproxy_kernel.call("list_sources", {}) local found, ad = false, nil - local want = accountSourceName(args.platform, args.account_id) + -- 一通道一源之后,同步的目标是**通道级**源名;account_id 只用于选号。 + local want = providerSourceName(args.platform) local arr = (ls and ls.json and ls.json.sources) or (ls and ls.sources) or {} for _, x in ipairs(arr) do if x.name == want then found = true ad = x.adapter end diff --git a/internal/provider/provider.go b/internal/provider/provider.go index 294d65a..e4c8ae7 100644 --- a/internal/provider/provider.go +++ b/internal/provider/provider.go @@ -506,42 +506,39 @@ func (p *Provider) ModelFor(reqModel string) string { return p.bestChatModel() } -// bestChatModel returns the highest-priority chat-kind model of this source. +// bestChatModel returns the first chat-kind model of this source. +// +// ★ 曾经叫 "highest-priority chat model",但 `config.Model.Priority` 已删除 +// +// (它从未参与跨源调度,只在这里用;而这里的语义其实只是"选一个能发 chat 的 +// 模型",选第一个就够了 —— 源内模型顺序由配置/发现顺序决定)。 func (p *Provider) bestChatModel() string { - bestID, bestPrio := "", -1 for _, m := range p.cfg.Models { if m.Kind != "" && m.Kind != "chat" { continue } - if m.Priority > bestPrio { - bestPrio = m.Priority - bestID = m.ID - } + return m.ID } - if bestID == "" && len(p.cfg.Models) > 0 { - bestID = p.cfg.Models[0].ID + if len(p.cfg.Models) > 0 { + return p.cfg.Models[0].ID } - return bestID + return "" } -// bestImageModel returns the highest-priority image-kind model of this source -// (fallback: first configured model). Used for AUTO image generation so a -// mixed source never sends a chat model to /v1/images/generations. +// bestImageModel returns the first image-kind model of this source (fallback: +// first configured model). Used for AUTO image generation so a mixed source +// never sends a chat model to /v1/images/generations. func (p *Provider) bestImageModel() string { - bestID, bestPrio := "", -1 for _, m := range p.cfg.Models { if m.Kind != "" && m.Kind != "image" { continue } - if m.Priority > bestPrio { - bestPrio = m.Priority - bestID = m.ID - } + return m.ID } - if bestID == "" && len(p.cfg.Models) > 0 { - bestID = p.cfg.Models[0].ID + if len(p.cfg.Models) > 0 { + return p.cfg.Models[0].ID } - return bestID + return "" } // IsAutoID reports whether s is an AUTO routing placeholder. diff --git a/internal/provider/provider_test.go b/internal/provider/provider_test.go index 59a6d14..ca4f204 100644 --- a/internal/provider/provider_test.go +++ b/internal/provider/provider_test.go @@ -32,7 +32,7 @@ func newTestProvider(t *testing.T, src config.Source) *Provider { func src(name, url, adapter string, models ...string) config.Source { s := config.Source{Name: name, BaseURL: url, Adapter: adapter, MaxConcurrent: 4} for _, m := range models { - s.Models = append(s.Models, config.Model{ID: m, Priority: 0}) + s.Models = append(s.Models, config.Model{ID: m}) } return s } @@ -515,8 +515,8 @@ func TestImageAutoUsesImageModel(t *testing.T) { defer up.Close() s := config.Source{Name: "mix", BaseURL: up.URL, Adapter: "openai", MaxConcurrent: 4} s.Models = []config.Model{ - {ID: "chat-m", Kind: "chat", Priority: 100}, - {ID: "img-m", Kind: "image", Priority: 50}, + {ID: "chat-m", Kind: "chat"}, + {ID: "img-m", Kind: "image"}, } p := newTestProvider(t, s) resp, err := p.Image(context.Background(), &types.ImageGenRequest{Prompt: "cat", Model: "AUTO"})