feat(llm): add iFlytek Spark as a built-in provider (#485)

Spark's official endpoint (https://spark-api-open.xf-yun.com/v1) is
OpenAI-compatible, so it registers like the other OpenAI-protocol
providers (deepseek, kimi, …). Adds the registry entry, the matching
name in the provider-order test, and the provider table in the en/zh/ja
configuration docs. Model ids are the domain values the HTTP endpoint
accepts (4.0Ultra, generalv3.5, max-32k, generalv3, pro-128k, lite).

Signed-off-by: FenjuFu <92919259+FenjuFu@users.noreply.github.com>

Author: FenjuFu

internal/llm/providers.go

@@ -168,6 +168,21 @@ var registry = []Provider{
 			"hy3-preview",
 		},
 	},
+	{
+		Name:        "iflytek",
+		DisplayName: "iFlytek Spark API",
+		Protocol:    ProtocolOpenAIChatCompletions,
+		BaseURL:     "https://spark-api-open.xf-yun.com/v1",
+		EnvVar:      "SPARK_API_KEY",
+		Models: []string{
+			"4.0Ultra",
+			"generalv3.5",
+			"max-32k",
+			"generalv3",
+			"pro-128k",
+			"lite",
+		},
+	},
 	{
 		Name:        "kimi",
 		DisplayName: "Kimi Moonshot API",

internal/llm/providers_test.go

@@ -40,7 +40,7 @@ func TestListProviders_Order(t *testing.T) {
 	if len(providers) < 3 {
 		t.Fatalf("expected at least 3 providers, got %d", len(providers))
 	}
-	expected := []string{"anthropic", "baidu-qianfan", "dashscope", "dashscope-tokenplan", "deepseek", "edenai", "hy-tokenplan", "kimi", "litellm", "mimo", "minimax", "ollama-cloud", "openai", "tencent-tokenhub", "volcengine", "z-ai", "z-ai-coding"}
+	expected := []string{"anthropic", "baidu-qianfan", "dashscope", "dashscope-tokenplan", "deepseek", "edenai", "hy-tokenplan", "iflytek", "kimi", "litellm", "mimo", "minimax", "ollama-cloud", "openai", "tencent-tokenhub", "volcengine", "z-ai", "z-ai-coding"}
 	if len(providers) != len(expected) {
 		t.Fatalf("expected %d providers, got %d", len(expected), len(providers))
 	}

pages/src/content/docs/en/configuration.md

@@ -52,6 +52,7 @@ environment variable.
 | `deepseek` | openai | `https://api.deepseek.com` | `DEEPSEEK_API_KEY` |
 | `tencent-tokenhub` | openai | `https://tokenhub.tencentmaas.com/v1` | `TENCENT_TOKENHUB_API_KEY` |
 | `hy-tokenplan` | openai | `https://api.lkeap.cloud.tencent.com/plan/v3` | `TENCENT_HUNYUAN_TOKENPLAN_KEY` |
+| `iflytek` | openai | `https://spark-api-open.xf-yun.com/v1` | `SPARK_API_KEY` |
 | `kimi` | openai | `https://api.moonshot.cn/v1` | `MOONSHOT_API_KEY` |
 | `z-ai` | openai | `https://open.bigmodel.cn/api/paas/v4` | `Z_AI_API_KEY` |
 | `mimo` | openai | `https://api.xiaomimimo.com/v1` | `MIMO_API_KEY` |

pages/src/content/docs/ja/configuration.md

@@ -50,6 +50,7 @@ ocr config set providers.anthropic.api_key sk-ant-xxxxxxxxxx
 | `deepseek` | openai | `https://api.deepseek.com` | `DEEPSEEK_API_KEY` |
 | `tencent-tokenhub` | openai | `https://tokenhub.tencentmaas.com/v1` | `TENCENT_TOKENHUB_API_KEY` |
 | `hy-tokenplan` | openai | `https://api.lkeap.cloud.tencent.com/plan/v3` | `TENCENT_HUNYUAN_TOKENPLAN_KEY` |
+| `iflytek` | openai | `https://spark-api-open.xf-yun.com/v1` | `SPARK_API_KEY` |
 | `kimi` | openai | `https://api.moonshot.cn/v1` | `MOONSHOT_API_KEY` |
 | `z-ai` | openai | `https://open.bigmodel.cn/api/paas/v4` | `Z_AI_API_KEY` |
 | `mimo` | openai | `https://api.xiaomimimo.com/v1` | `MIMO_API_KEY` |

pages/src/content/docs/zh/configuration.md

@@ -49,6 +49,7 @@ ocr config set providers.anthropic.api_key sk-ant-xxxxxxxxxx
 | `deepseek` | openai | `https://api.deepseek.com` | `DEEPSEEK_API_KEY` |
 | `tencent-tokenhub` | openai | `https://tokenhub.tencentmaas.com/v1` | `TENCENT_TOKENHUB_API_KEY` |
 | `hy-tokenplan` | openai | `https://api.lkeap.cloud.tencent.com/plan/v3` | `TENCENT_HUNYUAN_TOKENPLAN_KEY` |
+| `iflytek` | openai | `https://spark-api-open.xf-yun.com/v1` | `SPARK_API_KEY` |
 | `kimi` | openai | `https://api.moonshot.cn/v1` | `MOONSHOT_API_KEY` |
 | `z-ai` | openai | `https://open.bigmodel.cn/api/paas/v4` | `Z_AI_API_KEY` |
 | `mimo` | openai | `https://api.xiaomimimo.com/v1` | `MIMO_API_KEY` |