feat(models): refresh qianwenai lineup, add flash-0731 and gpt-5.6-luna, default to flash (#160)

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>

packages/core/src/state/model-catalog.ts

@@ -219,32 +219,27 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [
     pricing: cny(0.025, 3, 6),
     supportsVision: false,
   },
-  // -- OpenRouter (gateway: OpenAI-compatible protocol, preset base URL). Entries added
-  // 2026-07-20 list no cache pricing on their OpenRouter pages, so cache_read carries the
-  // standard input price; the :free tier and the openrouter/free Free Models Router store a
-  // genuine $0 price (not "unknown"), so costs correctly compute to 0. GPT models are
-  // uniformly vision-capable (OpenAI product-line policy) even where the gateway page omits
-  // the modality.
-  // Two cache_read conventions coexist in this block: rows whose upstream publishes a
-  // cache-hit price store that real price (the google/gemini-3.6-flash and
-  // google/gemini-3.5-flash-lite entries below), while the 2026-07-20 rows still repeat the
-  // input price. Several of those older rows do have a published cache price upstream and
-  // should be re-read in one pass; until then treat their cache_read as an upper bound. --
+  // -- 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 and GPT 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
+  // costs correctly compute to 0. GPT models are uniformly vision-capable (OpenAI
+  // product-line policy) even where the gateway page omits the modality. --
   {
     modelId: "anthropic/claude-fable-5",
     displayName: "Claude Fable 5",
     provider: "openrouter",
     contextWindow: 1000000,
-    pricing: usd(10, 10, 50),
+    pricing: usd(1, 12.5, 50),
     supportsVision: true,
     clientType: "openai",
     baseUrl: OPENROUTER_BASE_URL,
   },
   {
-    // Upstream publishes full cache pricing for this row (2026-07-24, per the OpenRouter
-    // models API: $0.50/mtok cache hit, $6.25 cache write = 1.25 x input, $5 input, $25
-    // output), so cache_read stores the real discounted price — same convention as the
-    // Gemini rows below — instead of repeating the input price.
     modelId: "anthropic/claude-opus-5",
     displayName: "Claude Opus 5",
     provider: "openrouter",
@@ -259,7 +254,7 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [
     displayName: "Claude Opus 4.8",
     provider: "openrouter",
     contextWindow: 1000000,
-    pricing: usd(5, 5, 25),
+    pricing: usd(0.5, 6.25, 25),
     supportsVision: true,
     clientType: "openai",
     baseUrl: OPENROUTER_BASE_URL,
@@ -269,7 +264,7 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [
     displayName: "Claude Opus 4.7",
     provider: "openrouter",
     contextWindow: 1000000,
-    pricing: usd(5, 5, 25),
+    pricing: usd(0.5, 6.25, 25),
     supportsVision: true,
     clientType: "openai",
     baseUrl: OPENROUTER_BASE_URL,
@@ -279,17 +274,27 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [
     displayName: "Claude Sonnet 5",
     provider: "openrouter",
     contextWindow: 1000000,
-    pricing: usd(2, 2, 10),
+    pricing: usd(0.2, 2.5, 10),
     supportsVision: true,
     clientType: "openai",
     baseUrl: OPENROUTER_BASE_URL,
   },
+  {
+    modelId: "deepseek/deepseek-v4-flash-0731",
+    displayName: "DeepSeek V4 Flash 0731",
+    provider: "openrouter",
+    contextWindow: 1000000,
+    pricing: usd(0.018, 0.09, 0.18),
+    supportsVision: false,
+    clientType: "openai",
+    baseUrl: OPENROUTER_BASE_URL,
+  },
   {
     modelId: "deepseek/deepseek-v4-flash",
     displayName: "DeepSeek V4 Flash",
     provider: "openrouter",
     contextWindow: 1000000,
-    pricing: usd(0.09, 0.09, 0.18),
+    pricing: usd(0.028, 0.14, 0.28),
     supportsVision: false,
     clientType: "openai",
     baseUrl: OPENROUTER_BASE_URL,
@@ -299,19 +304,16 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [
     displayName: "DeepSeek V4 Pro",
     provider: "openrouter",
     contextWindow: 1000000,
-    pricing: usd(0.435, 0.435, 0.87),
+    pricing: usd(0.003625, 0.435, 0.87),
     supportsVision: false,
     clientType: "openai",
     baseUrl: OPENROUTER_BASE_URL,
   },
   {
-    // Unlike the older OpenRouter entries above, upstream **does** publish a cache-hit price
-    // for the Gemini rows (2026-07-22: $0.15/mtok here, agreed by the OpenRouter models API
-    // and AgentHub's own supported-model registry), so cache_read stores the real discounted
-    // price rather than repeating the input price: cache_read is billed as its own bucket in
-    // the cost center, and an input-priced cache_read overstates cache-heavy spend 10x.
-    // cache_write repeats the input price (no separate per-token cache-write fee), matching
-    // the direct-vendor Gemini rows below.
+    // cache_read is billed as its own bucket in the cost center, and an input-priced
+    // cache_read would overstate cache-heavy Gemini spend 10x; cache_write repeats the input
+    // price (see the block comment — Gemini publishes storage-per-hour, not per-token write),
+    // matching the direct-vendor Gemini rows below.
     modelId: "google/gemini-3.6-flash",
     displayName: "Gemini 3.6 Flash",
     provider: "openrouter",
@@ -326,7 +328,7 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [
     displayName: "Gemini 3.5 Flash",
     provider: "openrouter",
     contextWindow: 1048576,
-    pricing: usd(1.5, 1.5, 9),
+    pricing: usd(0.15, 1.5, 9),
     supportsVision: true,
     clientType: "openai",
     baseUrl: OPENROUTER_BASE_URL,
@@ -372,7 +374,7 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [
     displayName: "Kimi K3",
     provider: "openrouter",
     contextWindow: 1000000,
-    pricing: usd(3, 3, 15),
+    pricing: usd(0.3, 3, 15),
     supportsVision: true,
     clientType: "openai",
     baseUrl: OPENROUTER_BASE_URL,
@@ -382,7 +384,7 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [
     displayName: "Kimi K2.6",
     provider: "openrouter",
     contextWindow: 262144,
-    pricing: usd(0.144, 0.684, 3.42),
+    pricing: usd(0.2, 0.6, 3.41),
     supportsVision: true,
     clientType: "openai",
     baseUrl: OPENROUTER_BASE_URL,
@@ -397,12 +399,25 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [
     clientType: "openai",
     baseUrl: OPENROUTER_BASE_URL,
   },
+  {
+    // The page shows the $0.10/$0.60 rate under a "50% off" banner; the models API bills the
+    // same numbers (with real hit/write prices), so this row stores them — re-read when the
+    // promotion ends.
+    modelId: "openai/gpt-5.6-luna",
+    displayName: "GPT-5.6 Luna",
+    provider: "openrouter",
+    contextWindow: 1000000,
+    pricing: usd(0.01, 0.125, 0.6),
+    supportsVision: true,
+    clientType: "openai",
+    baseUrl: OPENROUTER_BASE_URL,
+  },
   {
     modelId: "openai/gpt-5.6-sol",
     displayName: "GPT-5.6 Sol",
     provider: "openrouter",
     contextWindow: 1000000,
-    pricing: usd(5, 5, 30),
+    pricing: usd(0.5, 6.25, 30),
     supportsVision: true,
     clientType: "openai",
     baseUrl: OPENROUTER_BASE_URL,
@@ -412,7 +427,7 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [
     displayName: "GPT-5.6 Terra",
     provider: "openrouter",
     contextWindow: 1000000,
-    pricing: usd(2.5, 2.5, 15),
+    pricing: usd(0.1, 1.25, 6),
     supportsVision: true,
     clientType: "openai",
     baseUrl: OPENROUTER_BASE_URL,
@@ -422,7 +437,7 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [
     displayName: "GPT-5.5",
     provider: "openrouter",
     contextWindow: 1000000,
-    pricing: usd(5, 5, 30),
+    pricing: usd(0.5, 5, 30),
     supportsVision: true,
     clientType: "openai",
     baseUrl: OPENROUTER_BASE_URL,
@@ -444,19 +459,6 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [
     clientType: "openai",
     baseUrl: OPENROUTER_BASE_URL,
   },
-  {
-    // Poolside's free tier of Laguna M.1, its flagship coding-agent model (agentic coding
-    // workflows with tool calling and reasoning), text-only; context and $0 pricing per the
-    // OpenRouter models API (2026-07-24).
-    modelId: "poolside/laguna-m.1:free",
-    displayName: "Laguna M.1 (free)",
-    provider: "openrouter",
-    contextWindow: 262144,
-    pricing: usd(0, 0, 0),
-    supportsVision: false,
-    clientType: "openai",
-    baseUrl: OPENROUTER_BASE_URL,
-  },
   {
     // Neither the OpenRouter page nor AgentHub's registry publishes a cache price for this
     // model, so cache_read repeats the input price (no discount assumed).
@@ -485,7 +487,7 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [
     displayName: "Hy3",
     provider: "openrouter",
     contextWindow: 262144,
-    pricing: usd(0.035, 0.14, 0.58),
+    pricing: usd(0.033, 0.132, 0.528),
     supportsVision: false,
     clientType: "openai",
     baseUrl: OPENROUTER_BASE_URL,
@@ -495,7 +497,7 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [
     displayName: "Grok 4.5",
     provider: "openrouter",
     contextWindow: 500000,
-    pricing: usd(2, 2, 6),
+    pricing: usd(0.3, 2, 6),
     supportsVision: true,
     clientType: "openai",
     baseUrl: OPENROUTER_BASE_URL,
@@ -515,7 +517,7 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [
     displayName: "GLM-5.2",
     provider: "openrouter",
     contextWindow: 1000000,
-    pricing: usd(0.93, 0.93, 3),
+    pricing: usd(0.221, 1.19, 3.74),
     supportsVision: false,
     clientType: "openai",
     baseUrl: OPENROUTER_BASE_URL,
@@ -634,16 +636,17 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [
     clientType: "openai",
     baseUrl: SILICONFLOW_BASE_URL,
   },
-  // The three Pro/ and Qwen/ entries below carry no pricing: AgentHub's registry publishes
-  // none for them, and SiliconFlow's price list sits behind an authenticated API (the public
-  // /v1/models endpoint returns 401 and the console page is client-rendered). Rather than
-  // invent a rate, the entries ship unpriced — the same state as qwen3.8-max-preview, so their
-  // cost reads as 0 until a published price can be filled in.
+  // 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.
   {
     modelId: "Pro/moonshotai/Kimi-K2.6",
     displayName: "Kimi K2.6",
     provider: "siliconflow",
     contextWindow: 262144,
+    pricing: cny(1.1, 6.5, 27),
     supportsVision: true,
     clientType: "openai",
     baseUrl: SILICONFLOW_BASE_URL,
@@ -653,15 +656,18 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [
     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",
     displayName: "Qwen 3.6 35B A3B",
     provider: "siliconflow",
     contextWindow: 262144,
+    pricing: cny(1.8, 1.8, 10.8),
     supportsVision: true,
     clientType: "openai",
     baseUrl: SILICONFLOW_BASE_URL,
@@ -679,9 +685,18 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [
   // -- Qwen Token Plan (subscription gateway; vision flags per the plan's supported-model
   // table). Pricing and context windows from each model's page at
   // www.qianwenai.com/models/<id> (official CNY list prices; limited-time promotions such as
-  // the 20%/50% off discounts are not stored). qwen3.8-max-preview is preview-only with a
-  // quota-multiplier promotion and publishes no per-token list price nor a context window, so
-  // it carries no pricing and uses its family's 1M window. --
+  // the 20%/50% off discounts are not stored). Lineup updated 2026-08-03: qwen3.8-max and
+  // deepseek-v4-flash-0731 join; qwen3.8-max-preview and qwen3.7-max leave the plan. --
+  {
+    modelId: "deepseek-v4-flash-0731",
+    displayName: "DeepSeek V4 Flash 0731",
+    provider: "qwen-token-plan",
+    contextWindow: 1000000,
+    pricing: cny(0.2, 1, 2),
+    supportsVision: false,
+    clientType: "openai",
+    baseUrl: QWEN_TOKEN_PLAN_BASE_URL,
+  },
   {
     modelId: "deepseek-v4-pro",
     displayName: "DeepSeek V4 Pro",
@@ -703,24 +718,15 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [
     baseUrl: QWEN_TOKEN_PLAN_BASE_URL,
   },
   {
-    modelId: "qwen3.8-max-preview",
-    displayName: "Qwen 3.8 Max Preview",
+    modelId: "qwen3.8-max",
+    displayName: "Qwen 3.8 Max",
     provider: "qwen-token-plan",
     contextWindow: 1000000,
+    pricing: cny(1.5, 12, 36),
     supportsVision: true,
     clientType: "openai",
     baseUrl: QWEN_TOKEN_PLAN_BASE_URL,
   },
-  {
-    modelId: "qwen3.7-max",
-    displayName: "Qwen 3.7 Max",
-    provider: "qwen-token-plan",
-    contextWindow: 1000000,
-    pricing: cny(2.4, 12, 36),
-    supportsVision: false,
-    clientType: "openai",
-    baseUrl: QWEN_TOKEN_PLAN_BASE_URL,
-  },
   {
     modelId: "qwen3.7-plus",
     displayName: "Qwen 3.7 Plus",
@@ -733,7 +739,18 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [
   },
   // -- Qwen Pay-As-You-Go (DashScope's OpenAI-compatible pay-per-token marketplace; official
   // CNY list prices and specs from each model's page at www.qianwenai.com/models/<id> —
-  // resold third-party models keep their vendor-prefixed upstream ids) --
+  // resold third-party models keep their upstream ids exactly as the page lists them: kimi/
+  // and ZHIPU/ carry vendor prefixes, DeepSeek is listed bare) --
+  {
+    modelId: "deepseek-v4-flash-0731",
+    displayName: "DeepSeek V4 Flash 0731",
+    provider: "qwen-pay-as-you-go",
+    contextWindow: 1000000,
+    pricing: cny(0.2, 1, 2),
+    supportsVision: false,
+    clientType: "openai",
+    baseUrl: QWEN_PAYG_BASE_URL,
+  },
   {
     modelId: "kimi/kimi-k3",
     displayName: "Kimi K3",
@@ -745,12 +762,12 @@ export const MODEL_CATALOG: ModelCatalogEntry[] = [
     baseUrl: QWEN_PAYG_BASE_URL,
   },
   {
-    modelId: "qwen3.7-max",
-    displayName: "Qwen 3.7 Max",
+    modelId: "qwen3.8-max",
+    displayName: "Qwen 3.8 Max",
     provider: "qwen-pay-as-you-go",
     contextWindow: 1000000,
-    pricing: cny(2.4, 12, 36),
-    supportsVision: false,
+    pricing: cny(1.5, 12, 36),
+    supportsVision: true,
     clientType: "openai",
     baseUrl: QWEN_PAYG_BASE_URL,
   },
@@ -1044,16 +1061,13 @@ export function presetModelEntries(): ModelEntry[] {
 /**
  * The model's own homepage/detail page for the frontend's model-card link. Gateway groups
  * have a stable per-model URL pattern (works for user-added ids in those groups too);
- * direct-vendor models link to the vendor's model list/docs page; the Token Plan preview
- * model has no dedicated page and links to the plan's model overview; custom and
- * user-defined groups have no page to vouch for.
+ * direct-vendor models link to the vendor's model list/docs page; custom and user-defined
+ * groups have no page to vouch for.
  */
 export function modelHomepageUrl(provider: string, modelId: string): string | undefined {
   if (provider === "openrouter") return `https://openrouter.ai/${modelId}`;
   if (provider === "qwen-token-plan") {
-    return modelId === "qwen3.8-max-preview"
-      ? providerInfo(provider)?.modelsUrl
-      : `https://www.qianwenai.com/models/${modelId}`;
+    return `https://www.qianwenai.com/models/${modelId}`;
   }
   if (provider === "fireworks") {
     // API id "accounts/<owner>/models/<slug>" -> page "app.fireworks.ai/models/<owner>/<slug>";

packages/core/src/state/project-config.ts

@@ -133,7 +133,7 @@ export interface ProjectConfig {
  */
 export function defaultProjectConfig(): ProjectConfig {
   return {
-    default_model: { provider: "deepseek", model_id: "deepseek-v4-pro" },
+    default_model: { provider: "deepseek", model_id: "deepseek-v4-flash" },
     models: presetModelEntries(),
   };
 }

packages/core/test/agent.test.ts

@@ -169,9 +169,9 @@ describe("Agent.createSession model reference ((provider, model_id) pair)", () =
       // (same source that Trace writes).
       const meta = session.metaMessage.payload as { provider: string; model_id: string };
       expect(meta.provider).toBe("deepseek");
-      expect(meta.model_id).toBe("deepseek-v4-pro");
+      expect(meta.model_id).toBe("deepseek-v4-flash");
       expect(session.provider).toBe("deepseek");
-      expect(session.modelId).toBe("deepseek-v4-pro");
+      expect(session.modelId).toBe("deepseek-v4-flash");
     } finally {
       session.dispose();
     }
@@ -229,7 +229,7 @@ describe("Agent.createSession model reference ((provider, model_id) pair)", () =
     const session = await agent.createSession({ workspaceDir: ws });
     try {
       expect(session.provider).toBe("deepseek");
-      expect(session.modelId).toBe("deepseek-v4-pro");
+      expect(session.modelId).toBe("deepseek-v4-flash");
     } finally {
       session.dispose();
     }

packages/core/test/model-catalog.test.ts

@@ -68,22 +68,12 @@ describe("model-catalog", () => {
     }
   });
 
-  it("price buckets are positive (preview models without a list price omit pricing); context_window is a positive integer", () => {
-    // Models with no obtainable published price. qwen3.8-max-preview: the plan runs a
-    // quota-multiplier promotion instead of a per-token list price. The three SiliconFlow
-    // entries: AgentHub's registry publishes no pricing for them and SiliconFlow's price list
-    // is only reachable with an authenticated token, so no number can be sourced. All of them
-    // carry no pricing and their costs read as 0, same as unpriced user models.
-    const UNPRICED = new Set([
-      "qwen-token-plan\0qwen3.8-max-preview",
-      "siliconflow\0Pro/moonshotai/Kimi-K2.6",
-      "siliconflow\0Pro/zai-org/GLM-5.1",
-      "siliconflow\0Qwen/Qwen3.6-35B-A3B",
-    ]);
+  it("every entry is priced (free-tier rows store a genuine $0); context_window is a positive integer", () => {
+    // As of 2026-08-03 no catalog entry ships unpriced: the last holdouts (the three
+    // SiliconFlow Pro//Qwen/ rows) got their official CNY list prices. Unpriced remains a
+    // legal state for user-added models only.
     for (const m of MODEL_CATALOG) {
-      if (UNPRICED.has(`${m.provider}\0${m.modelId}`)) {
-        expect(m.pricing, m.modelId).toBeUndefined();
-      } else if (m.modelId.endsWith(":free") || m.modelId === "openrouter/free") {
+      if (m.modelId.endsWith(":free") || m.modelId === "openrouter/free") {
         // Free-tier gateway model (:free variants and the openrouter/free router): a genuine
         // $0 price (not "unknown"), so costs compute to 0.
         expect(m.pricing, m.modelId).toBeDefined();
@@ -111,8 +101,8 @@ describe("model-catalog", () => {
     // It matches on (group, upstream id) pairs, so an identically named upstream id never
     // matches across the wrong group. There is no bare-id lookup at all: a gateway reselling a
     // vendor model keeps the vendor's upstream id, so a bare id names no single catalog entry
-    // and the catalog never offers to pick one (`glm-5.2`, `qwen3.7-max`, `qwen3.7-plus` and
-    // `deepseek-v4-pro` each appear under two groups).
+    // and the catalog never offers to pick one (`glm-5.2`, `deepseek-v4-pro`, `qwen3.8-max`,
+    // `qwen3.7-plus` and `deepseek-v4-flash-0731` each appear under two groups).
     expect(catalogEntryFor("anthropic", "claude-sonnet-4-6")?.displayName).toBe(
       "Claude Sonnet 4.6",
     );
@@ -121,6 +111,14 @@ describe("model-catalog", () => {
     expect(catalogEntryFor("openrouter", "xiaomi/mimo-v2.5")?.displayName).toBe("MiMo-V2.5");
     expect(catalogEntryFor("custom", "my-own")).toBeUndefined();
     // Each group's entry for a resold id is reached only through that group.
+    expect(catalogEntryFor("qwen-token-plan", "qwen3.8-max")?.provider).toBe("qwen-token-plan");
+    expect(catalogEntryFor("qwen-pay-as-you-go", "qwen3.8-max")?.provider).toBe(
+      "qwen-pay-as-you-go",
+    );
+    // The bare resold id never leaks into the vendor's own group (deepseek's flash revision is
+    // sold there as deepseek-v4-flash, without the date suffix).
+    expect(catalogEntryFor("deepseek", "deepseek-v4-flash-0731")).toBeUndefined();
+    expect(catalogEntryFor("deepseek", "deepseek-v4-flash")?.provider).toBe("deepseek");
     expect(catalogEntryFor("zhipu", "glm-5.2")?.contextWindow).toBe(1000000);
     expect(catalogEntryFor("qwen-token-plan", "glm-5.2")?.contextWindow).toBe(1048576);
     expect(catalogEntryFor("deepseek", "deepseek-v4-pro")?.provider).toBe("deepseek");
@@ -157,6 +155,7 @@ describe("model-catalog", () => {
       "anthropic/claude-opus-4.8",
       "anthropic/claude-opus-4.7",
       "anthropic/claude-sonnet-5",
+      "deepseek/deepseek-v4-flash-0731",
       "deepseek/deepseek-v4-flash",
       "deepseek/deepseek-v4-pro",
       "google/gemini-3.6-flash",
@@ -167,11 +166,11 @@ describe("model-catalog", () => {
       "moonshotai/kimi-k3",
       "moonshotai/kimi-k2.6",
       "nvidia/nemotron-3-ultra-550b-a55b:free",
+      "openai/gpt-5.6-luna",
       "openai/gpt-5.6-sol",
       "openai/gpt-5.6-terra",
       "openai/gpt-5.5",
       "openrouter/free",
-      "poolside/laguna-m.1:free",
       "qwen/qwen3.6-35b-a3b",
       "stepfun/step-3.7-flash",
       "tencent/hy3",
@@ -216,28 +215,29 @@ describe("model-catalog", () => {
     }
     const qtp = MODEL_CATALOG.filter((m) => m.provider === "qwen-token-plan");
     expect(qtp.map((m) => m.modelId)).toEqual([
+      "deepseek-v4-flash-0731",
       "deepseek-v4-pro",
       "glm-5.2",
-      "qwen3.8-max-preview",
-      "qwen3.7-max",
+      "qwen3.8-max",
       "qwen3.7-plus",
     ]);
     for (const m of qtp) {
       expect(m.clientType).toBe("openai");
       expect(m.baseUrl).toBe("https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1");
     }
-    // Vision flags per the plan's supported-model table: 3.8-max-preview and 3.7-plus see images.
+    // Vision flags per the plan's supported-model table: 3.8-max and 3.7-plus see images.
     expect(qtp.map((m) => [m.modelId, m.supportsVision])).toEqual([
+      ["deepseek-v4-flash-0731", false],
       ["deepseek-v4-pro", false],
       ["glm-5.2", false],
-      ["qwen3.8-max-preview", true],
-      ["qwen3.7-max", false],
+      ["qwen3.8-max", true],
       ["qwen3.7-plus", true],
     ]);
     const qpayg = MODEL_CATALOG.filter((m) => m.provider === "qwen-pay-as-you-go");
     expect(qpayg.map((m) => [m.modelId, m.supportsVision])).toEqual([
+      ["deepseek-v4-flash-0731", false],
       ["kimi/kimi-k3", true],
-      ["qwen3.7-max", false],
+      ["qwen3.8-max", true],
       ["qwen3.7-plus", true],
       ["ZHIPU/GLM-5.2", false],
     ]);
@@ -280,11 +280,16 @@ describe("model-catalog", () => {
       }
     }
     const gateway = [...or, ...fw, ...sf, ...qtp, ...qpayg];
-    // Pricing (USD): MiMo v2.5 and Hy3.
+    // Pricing (USD, per the 2026-08-03 models-API re-read): MiMo v2.5 and Hy3 publish a real
+    // cache-hit price and no per-token write premium, so cache_write carries the input price.
     const mimo = MODEL_CATALOG.find((m) => m.modelId === "xiaomi/mimo-v2.5")!.pricing!;
     expect([mimo.cache_read, mimo.cache_write, mimo.output]).toEqual([0.0028, 0.14, 0.28]);
     const hy3 = MODEL_CATALOG.find((m) => m.modelId === "tencent/hy3")!.pricing!;
-    expect([hy3.cache_read, hy3.cache_write, hy3.output]).toEqual([0.035, 0.14, 0.58]);
+    expect([hy3.cache_read, hy3.cache_write, hy3.output]).toEqual([0.033, 0.132, 0.528]);
+    // Anthropic/GPT rows publish a genuine 1.25x per-token cache-write premium; it is stored
+    // as-is (cache_write > input would be wrong to collapse back to input).
+    const sonnet5 = catalogEntryFor("openrouter", "anthropic/claude-sonnet-5")!.pricing!;
+    expect([sonnet5.cache_read, sonnet5.cache_write, sonnet5.output]).toEqual([0.2, 2.5, 10]);
     // Gemini 3.6 Flash and 3.5 Flash Lite: upstream publishes a cache-hit price, so cache_read
     // stores the real discounted price (not the input price) — cache_read is its own billing
     // bucket in the cost center. cache_write repeats input (no per-token cache-write fee).
@@ -453,9 +458,9 @@ describe("resolveModelEnv (PRN-021: env fallback resolved by AgentHub routing ru
     expect(modelHomepageUrl("qwen-pay-as-you-go", "ZHIPU/GLM-5.2")).toBe(
       "https://www.qianwenai.com/models/ZHIPU%2FGLM-5.2",
     );
-    // The preview model has no dedicated page: falls back to the plan's model overview.
-    expect(modelHomepageUrl("qwen-token-plan", "qwen3.8-max-preview")).toBe(
-      providerInfo("qwen-token-plan")!.modelsUrl,
+    // Token Plan models link to their qianwenai model page (bare ids, no encoding needed).
+    expect(modelHomepageUrl("qwen-token-plan", "qwen3.8-max")).toBe(
+      "https://www.qianwenai.com/models/qwen3.8-max",
     );
     // Direct vendors link to the vendor's model docs page.
     expect(modelHomepageUrl("deepseek", "deepseek-v4-pro")).toBe(

packages/core/test/state.test.ts

@@ -1143,9 +1143,9 @@ describe("project-config round trip", () => {
     expect(entry?.vision).toBeUndefined();
   });
 
-  it("default config presets the full model catalog (default = deepseek deepseek-v4-pro)", () => {
+  it("default config presets the full model catalog (default = deepseek deepseek-v4-flash)", () => {
     const cfg = defaultProjectConfig();
-    expect(cfg.default_model).toEqual({ provider: "deepseek", model_id: "deepseek-v4-pro" });
+    expect(cfg.default_model).toEqual({ provider: "deepseek", model_id: "deepseek-v4-flash" });
     // The catalog is presented in full: provider and model_id are separate columns, model_id
     // being the plain upstream id (vision is only persisted as false for models that don't
     // support images).
@@ -1157,8 +1157,8 @@ describe("project-config round trip", () => {
         (c) => c.provider === entry.provider && c.modelId === entry.model_id,
       )!;
       expect(entry.vision).toBe(cat.supportsVision ? undefined : false);
-      // A catalog entry without a list price (the Token Plan preview model) presets no
-      // pricing; every other catalog entry stores USD pricing.
+      // A catalog entry without a list price would preset no pricing (none currently);
+      // every priced catalog entry stores USD pricing.
       if (cat.pricing === undefined) expect(entry.pricing).toBeUndefined();
       else expect(entry.pricing?.unit).toBe("usd_per_mtok");
       // A model that auto-routes leaves client_type unset; a gateway model (OpenRouter)