feat: 实现统一模型 ID 机制

实现统一模型 ID 格式 (provider_id/model_name)，支持跨协议模型标识和 Smart Passthrough。

核心变更：
- 新增 pkg/modelid 包：解析、格式化、校验统一模型 ID
- 数据库迁移：models 表使用 UUID 主键 + UNIQUE(provider_id, model_name) 约束
- Repository 层：FindByProviderAndModelName、ListEnabled 方法
- Service 层：联合唯一校验、provider ID 字符集校验
- Conversion 层：ExtractModelName、RewriteRequestModelName/RewriteResponseModelName 方法
- Handler 层：统一模型 ID 路由、Smart Passthrough、Models API 本地聚合
- 新增 error-responses、unified-model-id 规范

测试覆盖：
- 单元测试：modelid、conversion、handler、service、repository
- 集成测试：统一模型 ID 路由、Smart Passthrough 保真性、跨协议转换
- 迁移测试：UUID 主键、UNIQUE 约束、级联删除

OpenSpec：
- 归档 unified-model-id 变更到 archive/2026-04-21-unified-model-id
- 同步 11 个 delta specs 到 main specs
- 新增 error-responses、unified-model-id 规范文件

backend/internal/conversion/stream_test.go

@@ -93,7 +93,7 @@ func TestCanonicalStreamConverter_WithMiddleware(t *testing.T) {
 	chain.Use(&recordingMiddleware{name: "mw1", records: &records})
 	ctx := NewConversionContext(InterfaceTypeChat)
 
-	converter := NewCanonicalStreamConverterWithMiddleware(decoder, encoder, chain, *ctx, "openai", "anthropic")
+	converter := NewCanonicalStreamConverterWithMiddleware(decoder, encoder, chain, *ctx, "openai", "anthropic", "")
 	result := converter.ProcessChunk([]byte("raw"))
 
 	assert.Len(t, result, 1)
@@ -143,7 +143,7 @@ func TestCanonicalStreamConverter_MiddlewareError_Continue(t *testing.T) {
 	chain.Use(&errorMiddleware{})
 	ctx := NewConversionContext(InterfaceTypeChat)
 
-	converter := NewCanonicalStreamConverterWithMiddleware(decoder, encoder, chain, *ctx, "openai", "anthropic")
+	converter := NewCanonicalStreamConverterWithMiddleware(decoder, encoder, chain, *ctx, "openai", "anthropic", "")
 	result := converter.ProcessChunk([]byte("raw"))
 
 	assert.Nil(t, result, "middleware error should cause the event to be skipped (continue)")
@@ -163,7 +163,7 @@ func TestCanonicalStreamConverter_Flush_MiddlewareError_Continue(t *testing.T) {
 	chain.Use(&errorMiddleware{})
 	ctx := NewConversionContext(InterfaceTypeChat)
 
-	converter := NewCanonicalStreamConverterWithMiddleware(decoder, encoder, chain, *ctx, "openai", "anthropic")
+	converter := NewCanonicalStreamConverterWithMiddleware(decoder, encoder, chain, *ctx, "openai", "anthropic", "")
 	result := converter.Flush()
 
 	assert.Len(t, result, 1)