fix: anthropic tool-call round-trip, cache zero-hit parity, round-robin load balancing

anthropic.lua v3.0.0:
- Issue 1: tool_result/tool_use round-trip
- Issue 3: thinking default OFF (opt-in via extra_body.thinking)
- Issue 4: tool_choice mapping
- Issue 5: collect_blocks preserves unknown part types
- message_stop no longer emits done=true (was overwriting tool_calls finish_reason)
- cache_read_input_tokens normalized even at 0

gemini.lua:
- transform_response was missing cachedContentTokenCount

openai.lua (Issue 6):
- transform_error handles flat envelopes, nginx HTML, bare text

chat.go mergeUsage:
- Keep PromptTokensDetails even when CachedTokens=0

scheduler.go:
- Remove sort.SliceStable by Pref; round-robin cursor is the only LB mechanism

provider.go ModelAvailable:
- Also check Pref() > prefMin, persistently failing slots exit cands

presets.go:
- 17 built-in source templates

Tests: 6 new test functions, 2 updated for new semantics

internal/config/config.go

@@ -318,6 +318,7 @@ type RuntimeConfig struct {
 	SourceTemplates  []SourceTemplate  `json:"source_templates,omitempty"`
 	DeletedSources   []string          `json:"deleted_sources,omitempty"`
 	DeletedAdapters  []string          `json:"deleted_adapters,omitempty"`
+	PresetTemplates  []string          `json:"preset_templates,omitempty"` // preset names the user has seen (or deleted) — never re-seeded
 	Keys             []GWKey           `json:"keys,omitempty"`
 	Auto             []ModelScope      `json:"auto,omitempty"`
 	AutoImage        []ModelScope      `json:"auto_image,omitempty"`

internal/config/config_test.go

@@ -318,3 +318,55 @@ sources:
 		t.Fatalf("after no-op: %v %v", len(cfg.Sources), err)
 	}
 }
+
+// TestSeedTemplatesOnce verifies preset templates are seeded exactly once:
+// a user's edit survives a restart, and a deliberately deleted preset does
+// not silently come back.
+func TestSeedTemplatesOnce(t *testing.T) {
+	dir := t.TempDir()
+	path := filepath.Join(dir, "runtime.json")
+	presets := []SourceTemplate{
+		{Name: "DeepSeek", BaseURL: "https://api.deepseek.com", Adapter: "deepseek",
+			Models: []Model{{ID: "deepseek-chat", Kind: "chat"}}},
+		{Name: "OpenAI", BaseURL: "https://api.openai.com/v1", Adapter: "openai",
+			Models: []Model{{ID: "gpt-4o", Kind: "chat"}}},
+	}
+
+	// first run: both presets land in the store
+	s1 := NewStore(path)
+	if err := s1.Load(); err != nil {
+		t.Fatal(err)
+	}
+	if err := s1.SeedTemplates(presets); err != nil {
+		t.Fatalf("seed: %v", err)
+	}
+	if got := len(s1.ListTemplates()); got != 2 {
+		t.Fatalf("after seed len = %d, want 2", got)
+	}
+
+	// user edits one preset, deletes the other
+	edited := presets[0]
+	edited.BaseURL = "https://my-proxy.internal/v1"
+	if err := s1.UpsertTemplate(edited); err != nil {
+		t.Fatal(err)
+	}
+	if _, err := s1.RemoveTemplate("OpenAI"); err != nil {
+		t.Fatal(err)
+	}
+
+	// restart: re-seeding must be a no-op for both
+	s2 := NewStore(path)
+	if err := s2.Load(); err != nil {
+		t.Fatal(err)
+	}
+	if err := s2.SeedTemplates(presets); err != nil {
+		t.Fatalf("reseed: %v", err)
+	}
+	tpls := s2.ListTemplates()
+	if len(tpls) != 1 {
+		t.Fatalf("after restart len = %d, want 1 (deleted preset must not return): %+v", len(tpls), tpls)
+	}
+	if tpls[0].Name != "DeepSeek" || tpls[0].BaseURL != "https://my-proxy.internal/v1" {
+		t.Fatalf("user edit lost on restart: %+v", tpls[0])
+	}
+}

internal/config/presets.go

@@ -0,0 +1,212 @@
+package config
+
+// Built-in preset source templates. Seeded into the runtime store on first
+// startup so the WebUI can present "从模板创建" for popular providers — the
+// user only needs to supply a name and API key.
+//
+// Model IDs verified against provider docs 2026-08-28. Providers ship new IDs
+// frequently; treat these as a starting point and edit in the WebUI as needed.
+var PresetTemplates = []SourceTemplate{
+	// ── 国内热门 ────────────────────────────────────────────────────────────
+	{
+		Name:          "DeepSeek",
+		BaseURL:       "https://api.deepseek.com",
+		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"},
+		},
+	},
+	{
+		Name:          "智谱 GLM",
+		BaseURL:       "https://open.bigmodel.cn/api/paas/v4",
+		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"},
+		},
+	},
+	{
+		Name:          "Kimi / Moonshot",
+		BaseURL:       "https://api.moonshot.cn/v1",
+		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"},
+		},
+	},
+	{
+		Name:          "SiliconFlow",
+		BaseURL:       "https://api.siliconflow.cn/v1",
+		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"},
+		},
+	},
+	{
+		Name:          "讯飞星火 (Spark)",
+		BaseURL:       "https://spark-api-open.xf-yun.com/v1",
+		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"},
+		},
+	},
+	{
+		Name:          "阿里云 通义千问",
+		BaseURL:       "https://dashscope.aliyuncs.com/compatible-mode/v1",
+		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"},
+		},
+	},
+	{
+		Name:          "百度 千帆",
+		BaseURL:       "https://qianfan.baidubce.com/v2",
+		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"},
+		},
+	},
+	{
+		Name:          "豆包 (火山方舟)",
+		BaseURL:       "https://ark.cn-beijing.volces.com/api/v3",
+		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"},
+		},
+	},
+	{
+		Name:          "MiniMax",
+		BaseURL:       "https://api.minimax.chat/v1",
+		Adapter:       "openai",
+		MaxConcurrent: 8,
+		Models: []Model{
+			{ID: "MiniMax-M3", Priority: 100, Kind: "chat"},
+			{ID: "MiniMax-M2.5", Priority: 80, Kind: "chat"},
+		},
+	},
+	// ── 国际主流 ────────────────────────────────────────────────────────────
+	{
+		Name:          "OpenAI",
+		BaseURL:       "https://api.openai.com/v1",
+		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"},
+		},
+	},
+	{
+		Name:          "Anthropic Claude",
+		BaseURL:       "https://api.anthropic.com",
+		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"},
+		},
+	},
+	{
+		Name:          "Google Gemini",
+		BaseURL:       "https://generativelanguage.googleapis.com/v1beta",
+		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"},
+		},
+	},
+	{
+		Name:          "Groq",
+		BaseURL:       "https://api.groq.com/openai/v1",
+		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"},
+		},
+	},
+	{
+		Name:          "Mistral",
+		BaseURL:       "https://api.mistral.ai/v1",
+		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"},
+		},
+	},
+	{
+		Name:          "OpenRouter",
+		BaseURL:       "https://openrouter.ai/api/v1",
+		Adapter:       "openai",
+		MaxConcurrent: 8,
+		Headers: map[string]string{
+			"HTTP-Referer": "http://localhost:8080",
+			"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"},
+		},
+	},
+	{
+		Name:          "GitHub Models",
+		BaseURL:       "https://models.inference.ai.azure.com",
+		Adapter:       "github",
+		MaxConcurrent: 8,
+		Models: []Model{
+			{ID: "gpt-5.6-sol", Priority: 100, Kind: "chat"},
+			{ID: "gpt-5.6-luna", Priority: 80, Kind: "chat"},
+		},
+	},
+	// ── 本地模型 ────────────────────────────────────────────────────────────
+	{
+		Name:          "Ollama (localhost)",
+		BaseURL:       "http://127.0.0.1:11434",
+		Adapter:       "ollama",
+		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"},
+		},
+	},
+}

internal/config/store.go

@@ -138,6 +138,38 @@ func (s *Store) DeletedAdapters() map[string]bool {
 	return out
 }
 
+// SeedTemplates adds preset templates that the store has never seen before.
+// A preset is seeded at most once: its name is recorded in PresetTemplates so
+// a user who edits or deletes it never gets it silently restored on restart.
+func (s *Store) SeedTemplates(presets []SourceTemplate) error {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+	seen := make(map[string]bool, len(s.data.PresetTemplates))
+	for _, n := range s.data.PresetTemplates {
+		seen[n] = true
+	}
+	existing := make(map[string]bool, len(s.data.SourceTemplates))
+	for _, t := range s.data.SourceTemplates {
+		existing[t.Name] = true
+	}
+	added := false
+	for _, p := range presets {
+		if p.Name == "" || seen[p.Name] {
+			continue
+		}
+		s.data.PresetTemplates = append(s.data.PresetTemplates, p.Name)
+		added = true
+		if existing[p.Name] {
+			continue // user already has a template by this name: never overwrite
+		}
+		s.data.SourceTemplates = append(s.data.SourceTemplates, p)
+	}
+	if !added {
+		return nil
+	}
+	return s.persistLocked()
+}
+
 // UpsertTemplate adds or replaces a source template and persists.
 func (s *Store) UpsertTemplate(t SourceTemplate) error {
 	s.mu.Lock()