A local-first multi-agent app development platform, built on PenguinHarness
feat(models): add Inkling and Fireworks DeepSeek V4 Flash 0731, delist gateway GLM-5.1 (#220)
Yaowei Zhenge07106a9248b
diff --git a/README.md b/README.mdindex 47ddfe32..929445e8 100644--- a/README.md+++ b/README.md@@ -98,6 +98,7 @@ Four Skill groups ship in the box ([docs](https://penguin.ooo/docs/skills)); age| GPT 5.6 | OpenRouter || Gemini 3.6 Flash | Google Gemini, OpenRouter || Claude 5 | Anthropic, OpenRouter |+| Inkling | OpenRouter, Fireworks AI |Each family's latest generation only — the app's **Models** page lists every built-in preset, and any OpenAI-protocol endpoint works too: pick a preset, or point a custom endpoint at any of the 1000+ online and local models.diff --git a/README.zh.md b/README.zh.mdindex 97d11f1b..bc8262d5 100644--- a/README.zh.md+++ b/README.zh.md@@ -98,6 +98,7 @@ https://github.com/user-attachments/assets/aec49ae9-b743-467b-b247-37bedfeaa36e| GPT 5.6 | OpenRouter || Gemini 3.6 Flash | Google Gemini, OpenRouter || Claude 5 | Anthropic, OpenRouter |+| Inkling | OpenRouter, Fireworks AI |上表每个系列只列最新一代,完整预置清单请在应用的**模型**页查看;只要是 OpenAI 协议的端点都可以接入:选择预置,或用自定义端点连接 1000+ 在线与本地模型。diff --git a/packages/core/src/state/model-catalog.ts b/packages/core/src/state/model-catalog.tsindex 3c05ac95..548778af 100644--- a/packages/core/src/state/model-catalog.ts+++ b/packages/core/src/state/model-catalog.ts@@ -17,10 +17,12 @@** Scope: excludes deepseek-chat / deepseek-reasoner legacy aliases that AgentHub cannot* auto-route (deprecated 2026-07-24), glm-5v-turbo (image input unsupported by AgentHub's GLM- * client), non-chat models (embedding / image generation / TTS), and Bedrock. Direct-vendor- * ids are auto-routed by AgentHub and leave client_type unset; the five gateway groups- * (OpenRouter, Fireworks AI, SiliconFlow, Qwen Token Plan, Qwen Pay-As-You-Go) can't be- * auto-routed, so they set `client_type: "openai"` and inline their preset base URL.+ * client), the OpenRouter z-ai/glm-5.1 and SiliconFlow Pro/zai-org/GLM-5.1 gateway listings+ * (delisted 2026-08-06; the Z.AI direct glm-5.1 remains), non-chat models (embedding / image+ * generation / TTS), and Bedrock. Direct-vendor ids are auto-routed by AgentHub and leave+ * client_type unset; the five gateway groups (OpenRouter, Fireworks AI, SiliconFlow, Qwen+ * Token Plan, Qwen Pay-As-You-Go) can't be auto-routed, so they set `client_type: "openai"`+ * and inline their preset base URL.** This file imports no Node built-ins (type-only imports only), so it can be bundled directly* for the browser.@@ -222,9 +224,9 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [// -- OpenRouter (gateway: OpenAI-compatible protocol, preset base URL). Prices re-read in// one pass on 2026-08-03 from the models API (/api/v1/models): cache_read stores the// published input_cache_read (falling back to the input price for the few rows without- // one — qwen3.6-35b-a3b and the :free rows); cache_write stores input_cache_write only- // when it is a genuine per-token write premium (the Anthropic, GPT and qwen3.8-max rows,- // 1.25x input) —+ // one — qwen3.6-35b-a3b, thinkingmachines/inkling and the :free rows); cache_write stores+ // input_cache_write only when it is a genuine per-token write premium (the Anthropic, GPT+ // and qwen3.8-max rows, 1.25x input) —// Gemini's field is an hourly cache-STORAGE rate, not a per-token price, so those rows// keep the input price — and otherwise also carries the input price. The :free tier and// the openrouter/free Free Models Router store a genuine $0 price (not "unknown"), so@@ -503,6 +505,20 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [clientType: "openai",baseUrl: OPENROUTER_BASE_URL,},+ {+ // Thinking Machines Lab's Inkling (released 2026-07-14): multimodal (image + audio+ // input). Specs and pricing from its OpenRouter page (2026-08-06), which publishes no+ // cached-input price, so cache_read repeats the input price (no discount assumed; see+ // the block comment above).+ modelId: "thinkingmachines/inkling",+ displayName: "Inkling",+ provider: "openrouter",+ contextWindow: 1000000,+ pricing: usd(0.95, 0.95, 4.05),+ supportsVision: true,+ clientType: "openai",+ baseUrl: OPENROUTER_BASE_URL,+ },{modelId: "x-ai/grok-4.5",displayName: "Grok 4.5",@@ -533,19 +549,19 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [clientType: "openai",baseUrl: OPENROUTER_BASE_URL,},+ // -- Fireworks AI (gateway, standard serverless USD pricing: cached input / uncached+ // input / output from each model's page; API ids use the accounts/fireworks/models/<slug>+ // form) --{- modelId: "z-ai/glm-5.1",- displayName: "GLM-5.1",- provider: "openrouter",- contextWindow: 204800,- pricing: usd(0.1794, 0.966, 3.036),+ modelId: "accounts/fireworks/models/deepseek-v4-flash-0731",+ displayName: "DeepSeek V4 Flash 0731",+ provider: "fireworks",+ contextWindow: 1000000,+ pricing: usd(0.028, 0.14, 0.28),supportsVision: false,clientType: "openai",- baseUrl: OPENROUTER_BASE_URL,+ baseUrl: FIREWORKS_BASE_URL,},- // -- Fireworks AI (gateway, standard serverless USD pricing: cached input / uncached- // input / output from each model's page; API ids use the accounts/fireworks/models/<slug>- // form) --{modelId: "accounts/fireworks/models/deepseek-v4-flash",displayName: "DeepSeek V4 Flash",@@ -576,6 +592,18 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [clientType: "openai",baseUrl: FIREWORKS_BASE_URL,},+ {+ // Thinking Machines Lab's Inkling (released 2026-07-14): multimodal (image + audio+ // input); specs and serverless pricing from its Fireworks model page (2026-08-06).+ modelId: "accounts/fireworks/models/inkling",+ displayName: "Inkling",+ provider: "fireworks",+ contextWindow: 1000000,+ pricing: usd(0.17, 1, 4.05),+ supportsVision: true,+ clientType: "openai",+ baseUrl: FIREWORKS_BASE_URL,+ },{modelId: "accounts/fireworks/models/kimi-k3",displayName: "Kimi K3",@@ -649,9 +677,7 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [},// The Pro/ and Qwen/ entries below were unpriced until 2026-08-03 (SiliconFlow's price// list sits behind an authenticated console); prices below are its official CNY list- // prices. GLM-5.1 bills in two input-length tiers ([0, 32k) and [32k, +inf) for hit/input/- // output alike); the catalog stores one number per bucket, so these rows keep the LOWER- // tier — treat its cost as a floor for long-context use.+ // prices.{modelId: "Pro/moonshotai/Kimi-K2.6",displayName: "Kimi K2.6",@@ -662,16 +688,6 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [clientType: "openai",baseUrl: SILICONFLOW_BASE_URL,},- {- modelId: "Pro/zai-org/GLM-5.1",- displayName: "GLM-5.1",- provider: "siliconflow",- contextWindow: 200000,- pricing: cny(1.3, 6, 24),- supportsVision: false,- clientType: "openai",- baseUrl: SILICONFLOW_BASE_URL,- },{// No cache-hit price on the list, so cache_read carries the input price.modelId: "Qwen/Qwen3.6-35B-A3B",diff --git a/packages/core/test/model-catalog.test.ts b/packages/core/test/model-catalog.test.tsindex 4c3e6824..cdbadaee 100644--- a/packages/core/test/model-catalog.test.ts+++ b/packages/core/test/model-catalog.test.ts@@ -41,6 +41,11 @@ describe("model-catalog", () => {expect(providerInfo("siliconflow")!.label).toBe("SiliconFlow");// The catalog no longer includes GLM-5-Turbo.expect(ids).not.toContain("glm-5-turbo");+ // The OpenRouter and SiliconFlow gateway listings of GLM-5.1 were delisted 2026-08-06;+ // the Z.AI direct glm-5.1 remains in the catalog.+ expect(ids).not.toContain("z-ai/glm-5.1");+ expect(ids).not.toContain("Pro/zai-org/GLM-5.1");+ expect(ids).toContain("glm-5.1");});it("every provider is in MODEL_PROVIDERS (custom only groups user-defined models; the catalog never uses it)", () => {@@ -175,10 +180,10 @@ describe("model-catalog", () => {"qwen/qwen3.6-35b-a3b","stepfun/step-3.7-flash","tencent/hy3",+ "thinkingmachines/inkling","x-ai/grok-4.5","xiaomi/mimo-v2.5","z-ai/glm-5.2",- "z-ai/glm-5.1",]);for (const m of or) {expect(m.clientType).toBe("openai");@@ -186,9 +191,11 @@ describe("model-catalog", () => {}const fw = MODEL_CATALOG.filter((m) => m.provider === "fireworks");expect(fw.map((m) => [m.modelId, m.supportsVision])).toEqual([+ ["accounts/fireworks/models/deepseek-v4-flash-0731", false],["accounts/fireworks/models/deepseek-v4-flash", false],["accounts/fireworks/models/deepseek-v4-pro", false],["accounts/fireworks/models/glm-5p2", false],+ ["accounts/fireworks/models/inkling", true],["accounts/fireworks/models/kimi-k3", true],["accounts/fireworks/models/kimi-k2p7-code", true],["accounts/fireworks/models/minimax-m3", true],@@ -206,7 +213,6 @@ describe("model-catalog", () => {"meituan-longcat/LongCat-2.0","moonshotai/Kimi-K2.7-Code","Pro/moonshotai/Kimi-K2.6",- "Pro/zai-org/GLM-5.1","Qwen/Qwen3.6-35B-A3B","zai-org/GLM-5.2",]);@@ -370,14 +376,18 @@ describe("model-catalog", () => {["moonshot", "kimi-k3", "openrouter", "moonshotai/kimi-k3"],["moonshot", "kimi-k2.6", "openrouter", "moonshotai/kimi-k2.6"],["moonshot", "kimi-k2.6", "siliconflow", "Pro/moonshotai/Kimi-K2.6"],- ["zhipu", "glm-5.1", "openrouter", "z-ai/glm-5.1"],- ["zhipu", "glm-5.1", "siliconflow", "Pro/zai-org/GLM-5.1"],] as const) {expect(catalogEntryFor(gatewayProvider, gatewayId)!.displayName,`${gatewayProvider}/${gatewayId}`,).toBe(catalogEntryFor(directProvider, directId)!.displayName);}+ // Inkling has no direct-vendor group (Thinking Machines Lab is gateway-only); its two+ // gateway listings still share one display name, with the vendor prefix stripped.+ expect(catalogEntryFor("openrouter", "thinkingmachines/inkling")!.displayName).toBe("Inkling");+ expect(catalogEntryFor("fireworks", "accounts/fireworks/models/inkling")!.displayName).toBe(+ "Inkling",+ );});it("DeepSeek and Kimi are initialized from official CNY prices (stored in USD; x7 recovers the official price)", () => {diff --git a/packages/skills/skills/agenthub-models/SKILL.md b/packages/skills/skills/agenthub-models/SKILL.mdindex 505e7745..39aec028 100644--- a/packages/skills/skills/agenthub-models/SKILL.md+++ b/packages/skills/skills/agenthub-models/SKILL.md@@ -3,8 +3,8 @@ name: agenthub-modelsdescription: Call model APIs through @prismshadow/agenthub — streaming text generation, image generation, speech synthesis, embeddings and the supported-model registry with one client.short_description: Call model APIs with one AgentHub client.short_description_zh: 用一个 AgentHub 客户端调用模型 API。-version: 10-updated: 2026-08-04T09:33:09Z+version: 11+updated: 2026-08-06T11:51:12Z---# AgentHub Model APIs@@ -60,11 +60,12 @@ Use exact model ids. If an id is not in the table below and the user has not giv| OpenAI embedding | `text-embedding-3-small`, `text-embedding-3-large` | — || Kimi K3 | `kimi-k3` | OpenRouter `moonshotai/kimi-k3` || Kimi K2.6 | `kimi-k2.6` | OpenRouter `moonshotai/kimi-k2.6`; SiliconFlow `Pro/moonshotai/Kimi-K2.6` |-| DeepSeek V4 | `deepseek-v4-pro`, `deepseek-v4-flash` | OpenRouter `deepseek/deepseek-v4-pro`, `deepseek/deepseek-v4-flash`, `deepseek/deepseek-v4-flash-0731`; SiliconFlow `deepseek-ai/DeepSeek-V4-Pro`, `deepseek-ai/DeepSeek-V4-Flash` |+| DeepSeek V4 | `deepseek-v4-pro`, `deepseek-v4-flash` | OpenRouter `deepseek/deepseek-v4-pro`, `deepseek/deepseek-v4-flash`, `deepseek/deepseek-v4-flash-0731`; Fireworks AI `accounts/fireworks/models/deepseek-v4-flash-0731`; SiliconFlow `deepseek-ai/DeepSeek-V4-Pro`, `deepseek-ai/DeepSeek-V4-Flash` || GLM 5.2 | `glm-5.2` | OpenRouter `z-ai/glm-5.2`; SiliconFlow `zai-org/GLM-5.2` |-| GLM 5.1 | `glm-5.1` | OpenRouter `z-ai/glm-5.1`; SiliconFlow `Pro/zai-org/GLM-5.1` |+| GLM 5.1 | `glm-5.1` | — || Qwen 3.8 Max | — | OpenRouter `qwen/qwen3.8-max` || Qwen 3.6 | — | OpenRouter `qwen/qwen3.6-35b-a3b`; SiliconFlow `Qwen/Qwen3.6-35B-A3B` |+| Inkling | — | OpenRouter `thinkingmachines/inkling`; Fireworks AI `accounts/fireworks/models/inkling` |The image endpoint dropped its preview suffix: `gemini-3.1-flash-image-preview` is deprecated, use `gemini-3.1-flash-image`.