发布 0.2.0:模型池自愈、探测修正、任务异步触发与删除加固

2026-07-10 20:25:37 +08:00
parent dbba1f4905
commit 7706f59549
19 changed files with 978 additions and 107 deletions
@@ -76,3 +76,34 @@ func ServiceStatus(err error) (int, bool) {
 	}
 	return 0, false
 }
+
+// IsOnDemandUnsupported 识别「模型在该区域仅为微调基座、不支持按需调用」的 400:
+// OCI 消息形如 "Not allowed to call finetune base model …, use Endpoint: false"。
+// ListModels 无字段可事先区分,只能在调用报错时识别并换渠道。
+func IsOnDemandUnsupported(err error) bool {
+	var svcErr common.ServiceError
+	if !errors.As(err, &svcErr) {
+		return false
+	}
+	return svcErr.GetHTTPStatusCode() == 400 &&
+		strings.Contains(strings.ToLower(svcErr.GetMessage()), "finetune base model")
+}
+
+// IsEntityNotFound 识别「实体不存在」404(消息 "Entity with key … not found"):
+// GenAI 对区域内无按需供给的模型 OCID 返回此类 404,属模型级错误;
+// 鉴权失败的 404 是 NotAuthorizedOrNotFound(消息为 Authorization failed…),不在此列。
+func IsEntityNotFound(err error) bool {
+	var svcErr common.ServiceError
+	if !errors.As(err, &svcErr) {
+		return false
+	}
+	msg := strings.ToLower(svcErr.GetMessage())
+	return svcErr.GetHTTPStatusCode() == 404 &&
+		strings.Contains(msg, "entity with key") && strings.Contains(msg, "not found")
+}
+
+// IsModelUnavailable 归并「模型×区域不可按需调用」两类报错:微调基座 400 与实体不存在 404;
+// 命中即应把该 (渠道, 模型) 从池中剔除并换候选/换渠道,而非定论租户配额问题。
+func IsModelUnavailable(err error) bool {
+	return IsOnDemandUnsupported(err) || IsEntityNotFound(err)
+}
@@ -109,3 +109,52 @@ func TestErrorHint(t *testing.T) {
 		})
 	}
 }
+
+func TestIsOnDemandUnsupported(t *testing.T) {
+	ft := fakeServiceError{status: 400, code: "InvalidParameter",
+		message: "Not allowed to call finetune base model ocid1.generativeaimodel.oc1.eu-frankfurt-1.tpel5q, use Endpoint: false"}
+	tests := []struct {
+		name string
+		err  error
+		want bool
+	}{
+		{"微调基座 400 命中(含包装链)", fmt.Errorf("genai chat: %w", ft), true},
+		{"同消息但非 400 不命中", fakeServiceError{status: 500, code: "InternalError", message: ft.message}, false},
+		{"普通 400 不命中", fakeServiceError{status: 400, code: "InvalidParameter", message: "bad request"}, false},
+		{"非服务端错误不命中", errors.New("finetune base model"), false},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := IsOnDemandUnsupported(tt.err); got != tt.want {
+				t.Errorf("IsOnDemandUnsupported() = %v, want %v", got, tt.want)
+			}
+		})
+	}
+}
+
+func TestIsModelUnavailable(t *testing.T) {
+	entity404 := fakeServiceError{status: 404, code: "NotFound",
+		message: "Entity with key ocid1.generativeaimodel.oc1.eu-frankfurt-1.2flsfq not found"}
+	auth404 := fakeServiceError{status: 404, code: "NotAuthorizedOrNotFound",
+		message: "Authorization failed or requested resource not found."}
+	ft400 := fakeServiceError{status: 400, code: "InvalidParameter",
+		message: "Not allowed to call finetune base model ocid1.generativeaimodel.oc1..x, use Endpoint: false"}
+	tests := []struct {
+		name string
+		err  error
+		want bool
+	}{
+		{"实体不存在 404 命中(含包装链)", fmt.Errorf("genai chat: %w", entity404), true},
+		{"鉴权类 404 不命中(仍属租户级)", auth404, false},
+		{"微调基座 400 命中", ft400, true},
+		{"其他 404 消息不命中", fakeServiceError{status: 404, code: "NotFound", message: "route not found"}, false},
+		{"非服务端错误不命中", errors.New("entity with key x not found"), false},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := IsModelUnavailable(tt.err); got != tt.want {
+				t.Errorf("IsModelUnavailable() = %v, want %v", got, tt.want)
+			}
+		})
+	}
+}
@@ -17,11 +17,10 @@ import (

 // GenAiModel 是区域可用基础模型的摘要(管理面 ListModels)。
 type GenAiModel struct {
-	Ocid     string   `json:"ocid"`
-	Name     string   `json:"name"`
-	Vendor   string   `json:"vendor"`
-	ChatOnly bool     `json:"-"`
-	Caps     []string `json:"capabilities"`
+	Ocid   string   `json:"ocid"`
+	Name   string   `json:"name"`
+	Vendor string   `json:"vendor"`
+	Caps   []string `json:"capabilities"`
 	// Capability 是网关侧归一能力:CHAT / EMBEDDING(兼具时算 CHAT)
 	Capability string `json:"capability"`
 	// Deprecated 是 OCI 宣布的弃用时间(TimeDeprecated),nil 表示未宣布;
@@ -71,18 +70,39 @@ func (c *RealClient) ListGenAiModels(ctx context.Context, cred Credentials, regi
 	if err != nil {
 		return nil, fmt.Errorf("list genai models: %w", err)
 	}
-	seen := map[string]bool{}
-	now := time.Now()
+	return dedupGenAiModels(resp.Items, time.Now()), nil
+}
+
+// dedupGenAiModels 压平并按名称去重;同名多条目时优先保留不含 FINE_TUNE 能力的条目
+// (微调基座条目在部分区域不支持按需调用,缓存其 OCID 会导致调用 400)。
+func dedupGenAiModels(items []generativeai.ModelSummary, now time.Time) []GenAiModel {
+	seen := map[string]int{}
 	var out []GenAiModel
-	for _, m := range resp.Items {
+	for _, m := range items {
 		gm, ok := toGenAiModel(m, now)
-		if !ok || seen[gm.Name] {
+		if !ok {
 			continue
 		}
-		seen[gm.Name] = true
+		if i, dup := seen[gm.Name]; dup {
+			if hasFineTune(out[i].Caps) && !hasFineTune(gm.Caps) {
+				out[i] = gm
+			}
+			continue
+		}
+		seen[gm.Name] = len(out)
 		out = append(out, gm)
 	}
-	return out, nil
+	return out
+}
+
+// hasFineTune 判断能力列表是否含 FINE_TUNE(微调基座条目)。
+func hasFineTune(caps []string) bool {
+	for _, c := range caps {
+		if c == string(generativeai.ModelCapabilityFineTune) {
+			return true
+		}
+	}
+	return false
 }

 // toGenAiModel 压平模型摘要;无归一能力、无名称或按需推理已退役
@@ -38,3 +38,33 @@ func TestToGenAiModelRetiredFilter(t *testing.T) {
 		t.Error("正常模型应入池")
 	}
 }
+
+func TestDedupGenAiModelsFineTunePreference(t *testing.T) {
+	now := time.Date(2026, 7, 10, 0, 0, 0, 0, time.UTC)
+	chat := []generativeai.ModelCapabilityEnum{generativeai.ModelCapabilityChat}
+	chatFT := []generativeai.ModelCapabilityEnum{generativeai.ModelCapabilityChat, generativeai.ModelCapabilityFineTune}
+	mk := func(id, name string, caps []generativeai.ModelCapabilityEnum) generativeai.ModelSummary {
+		return generativeai.ModelSummary{
+			Id: common.String(id), DisplayName: common.String(name), Vendor: common.String("meta"),
+			Capabilities: caps, LifecycleState: generativeai.ModelLifecycleStateActive,
+		}
+	}
+	const name = "meta.llama-3-70b-instruct"
+	tests := []struct {
+		name  string
+		items []generativeai.ModelSummary
+		want  string // 期望保留的 OCID
+	}{
+		{"基座在前、纯对话在后:保留纯对话条目", []generativeai.ModelSummary{mk("o-ft", name, chatFT), mk("o-od", name, chat)}, "o-od"},
+		{"纯对话在前、基座在后:保留纯对话条目", []generativeai.ModelSummary{mk("o-od", name, chat), mk("o-ft", name, chatFT)}, "o-od"},
+		{"仅基座条目:保留不误删", []generativeai.ModelSummary{mk("o-ft", name, chatFT)}, "o-ft"},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := dedupGenAiModels(tt.items, now)
+			if len(got) != 1 || got[0].Ocid != tt.want {
+				t.Errorf("dedupGenAiModels() = %+v, want 仅保留 %s", got, tt.want)
+			}
+		})
+	}
+}