codeep 2.15.0 → 2.17.0

package/dist/config/providers.js

@@ -18,11 +18,12 @@ export const PROVIDERS = {
             },
         },
         models: [
-            { id: 'glm-5.2', name: 'GLM-5.2', description: 'Latest GLM model, available to all users' },
+            { id: 'glm-5.2', name: 'GLM-5.2', description: 'Latest flagship for project-scale engineering (1M context)' },
             { id: 'glm-5-turbo', name: 'GLM-5 Turbo', description: 'Fast GLM-5 variant, available to all users' },
         ],
         defaultModel: 'glm-5.2',
         defaultProtocol: 'openai',
+        maxOutputTokens: 131_072,
         envKey: 'ZAI_API_KEY',
         subscribeUrl: 'https://z.ai/subscribe?ic=NXYNXZOV14',
         groupLabel: 'Z.AI — Subscription (GLM Coding Plan)',
@@ -44,11 +45,12 @@ export const PROVIDERS = {
             },
         },
         models: [
-            { id: 'glm-5.2', name: 'GLM-5.2', description: 'Latest GLM model' },
+            { id: 'glm-5.2', name: 'GLM-5.2', description: 'Latest flagship for project-scale engineering (1M context)' },
             { id: 'glm-5-turbo', name: 'GLM-5 Turbo', description: 'Fast GLM-5 variant' },
         ],
         defaultModel: 'glm-5.2',
         defaultProtocol: 'openai',
+        maxOutputTokens: 131_072,
         envKey: 'ZAI_API_KEY',
         subscribeUrl: 'https://api.z.ai',
         groupLabel: 'Z.AI — API (pay-per-use)',
@@ -70,11 +72,12 @@ export const PROVIDERS = {
             },
         },
         models: [
-            { id: 'glm-5.2', name: 'GLM-5.2', description: 'Latest GLM model, available to all users' },
+            { id: 'glm-5.2', name: 'GLM-5.2', description: 'Latest flagship for project-scale engineering (1M context)' },
             { id: 'glm-5-turbo', name: 'GLM-5 Turbo', description: 'Fast GLM-5 variant, available to all users' },
         ],
         defaultModel: 'glm-5.2',
         defaultProtocol: 'openai',
+        maxOutputTokens: 131_072,
         envKey: 'ZAI_CN_API_KEY',
         subscribeUrl: 'https://open.bigmodel.cn/glm-coding',
         groupLabel: 'Z.AI China — Subscription (GLM Coding Plan)',
@@ -96,11 +99,12 @@ export const PROVIDERS = {
             },
         },
         models: [
-            { id: 'glm-5.2', name: 'GLM-5.2', description: 'Latest GLM model' },
+            { id: 'glm-5.2', name: 'GLM-5.2', description: 'Latest flagship for project-scale engineering (1M context)' },
             { id: 'glm-5-turbo', name: 'GLM-5 Turbo', description: 'Fast GLM-5 variant' },
         ],
         defaultModel: 'glm-5.2',
         defaultProtocol: 'openai',
+        maxOutputTokens: 131_072,
         envKey: 'ZAI_CN_API_KEY',
         subscribeUrl: 'https://open.bigmodel.cn',
         groupLabel: 'Z.AI China — API (pay-per-use)',
@@ -205,9 +209,9 @@ export const PROVIDERS = {
     },
     // ── Kimi (Moonshot AI) ────────────────────────────────────────────
     // Subscription (Kimi Code) mirrors the Z.AI GLM-Coding-Plan shape: a
-    // dedicated coding base URL + a separate key, model id ALWAYS
-    // `kimi-for-coding` (a backend alias). OpenAI-compatible is the
-    // battle-tested path so we don't expose the Anthropic surface here.
+    // dedicated coding base URL + a separate key. Model availability depends
+    // on the user's plan, so the picker labels the restricted K3/high-speed ids
+    // instead of pretending every subscription includes them.
     'kimi': {
         name: 'Kimi (Moonshot) — Coding Plan',
         description: 'Kimi Code subscription',
@@ -215,7 +219,10 @@ export const PROVIDERS = {
             openai: { baseUrl: 'https://api.kimi.com/coding/v1', authHeader: 'Bearer', supportsNativeTools: true },
         },
         models: [
-            { id: 'kimi-for-coding', name: 'Kimi Code', description: 'Subscription alias — auto-maps to the latest Kimi coding model (K2.7 Code)' },
+            { id: 'kimi-for-coding', name: 'Kimi Code', description: 'Available on every Kimi Code plan — maps to K2.7 Code' },
+            { id: 'k3', name: 'Kimi K3', description: '1M-context flagship — Moderato plan or higher' },
+            { id: 'k3-256k', name: 'Kimi K3 (256K)', description: 'K3 with a smaller context window — Moderato plan or higher' },
+            { id: 'kimi-for-coding-highspeed', name: 'Kimi Code (High-Speed)', description: 'Low-latency K2.7 Code — Allegretto plan or higher' },
         ],
         defaultModel: 'kimi-for-coding',
         defaultProtocol: 'openai',
@@ -232,18 +239,18 @@ export const PROVIDERS = {
             openai: { baseUrl: 'https://api.moonshot.ai/v1', authHeader: 'Bearer', supportsNativeTools: true },
         },
         models: [
-            { id: 'kimi-k2.7-code', name: 'Kimi K2.7 Code', description: 'Flagship agentic coding model (256K context)' },
+            { id: 'kimi-k3', name: 'Kimi K3', description: 'Latest flagship for software engineering and deep reasoning (1M context)' },
+            { id: 'kimi-k2.7-code', name: 'Kimi K2.7 Code', description: 'Coding-specialized model (256K context)' },
             { id: 'kimi-k2.7-code-highspeed', name: 'Kimi K2.7 Code (High-Speed)', description: 'Throughput-tuned K2.7 Code for latency-sensitive loops' },
-            { id: 'kimi-k2.6', name: 'Kimi K2.6', description: 'Previous-gen multimodal reasoning model' },
-            { id: 'kimi-k2.5', name: 'Kimi K2.5', description: 'Older general-purpose model (cheaper)' },
+            { id: 'kimi-k2.6', name: 'Kimi K2.6', description: 'General-purpose multimodal reasoning model' },
         ],
-        defaultModel: 'kimi-k2.7-code',
+        defaultModel: 'kimi-k3',
         defaultProtocol: 'openai',
-        maxOutputTokens: 32_768,
+        maxOutputTokens: 131_072,
         envKey: 'MOONSHOT_API_KEY',
         subscribeUrl: 'https://platform.kimi.ai/console/api-keys',
         groupLabel: 'Kimi — API (pay-per-use)',
-        hint: 'Pay-per-use via Moonshot API key (platform.kimi.ai).',
+        hint: 'Pay-per-use via Moonshot API key (platform.kimi.ai). Kimi K3 supports 1M context and graded reasoning.',
     },
     'kimi-cn': {
         name: 'Kimi China (Moonshot)',
@@ -252,18 +259,18 @@ export const PROVIDERS = {
             openai: { baseUrl: 'https://api.moonshot.cn/v1', authHeader: 'Bearer', supportsNativeTools: true },
         },
         models: [
-            { id: 'kimi-k2.7-code', name: 'Kimi K2.7 Code', description: 'Flagship agentic coding model (256K context)' },
+            { id: 'kimi-k3', name: 'Kimi K3', description: 'Latest flagship for software engineering and deep reasoning (1M context)' },
+            { id: 'kimi-k2.7-code', name: 'Kimi K2.7 Code', description: 'Coding-specialized model (256K context)' },
             { id: 'kimi-k2.7-code-highspeed', name: 'Kimi K2.7 Code (High-Speed)', description: 'Throughput-tuned K2.7 Code' },
-            { id: 'kimi-k2.6', name: 'Kimi K2.6', description: 'Previous-gen multimodal reasoning model' },
-            { id: 'kimi-k2.5', name: 'Kimi K2.5', description: 'Older general-purpose model' },
+            { id: 'kimi-k2.6', name: 'Kimi K2.6', description: 'General-purpose multimodal reasoning model' },
         ],
-        defaultModel: 'kimi-k2.7-code',
+        defaultModel: 'kimi-k3',
         defaultProtocol: 'openai',
-        maxOutputTokens: 32_768,
+        maxOutputTokens: 131_072,
         envKey: 'MOONSHOT_CN_API_KEY',
         subscribeUrl: 'https://platform.moonshot.cn/console/api-keys',
         groupLabel: 'Kimi China — API (pay-per-use)',
-        hint: 'Pay-per-use via Moonshot China API key (platform.moonshot.cn).',
+        hint: 'Pay-per-use via Moonshot China API key (platform.moonshot.cn). Kimi K3 supports 1M context.',
     },
     // ── Grok (xAI) ────────────────────────────────────────────────────
     // Pay-per-use today (console.x.ai key). The SuperGrok / X Premium+
@@ -279,8 +286,6 @@ export const PROVIDERS = {
             { id: 'grok-4.5', name: 'Grok 4.5', description: 'Flagship reasoning model — highest quality, 500K context' },
             { id: 'grok-build-0.1', name: 'Grok Build 0.1', description: 'Agentic coding model — fast, 256K context' },
             { id: 'grok-4.3', name: 'Grok 4.3', description: 'Previous flagship, 1M context' },
-            { id: 'grok-code-fast-1', name: 'Grok Code Fast 1', description: 'Low-cost speed-first coder (alias of Build 0.1)' },
-            { id: 'grok-4-fast-reasoning', name: 'Grok 4 Fast (reasoning)', description: 'Cheap reasoning model, very large context' },
         ],
         defaultModel: 'grok-build-0.1',
         defaultProtocol: 'openai',
@@ -301,11 +306,11 @@ export const PROVIDERS = {
             openai: { baseUrl: 'https://coding-intl.dashscope.aliyuncs.com/v1', authHeader: 'Bearer', supportsNativeTools: true },
         },
         models: [
-            { id: 'qwen3-coder-plus', name: 'Qwen3-Coder Plus', description: 'Flagship coding model — best quality' },
-            { id: 'qwen3-coder-next', name: 'Qwen3-Coder Next', description: 'Balanced quality/speed/cost' },
-            { id: 'qwen3.7-max', name: 'Qwen3.7-Max', description: 'Flagship general model (code + reasoning)' },
+            { id: 'qwen3.7-plus', name: 'Qwen3.7-Plus', description: 'Recommended current model for coding, reasoning, and vision' },
+            { id: 'qwen3.6-plus', name: 'Qwen3.6-Plus', description: 'Fast multimodal model with a 1M context window' },
+            { id: 'qwen3.5-plus', name: 'Qwen3.5-Plus', description: 'Efficient general-purpose Coding Plan model' },
         ],
-        defaultModel: 'qwen3-coder-plus',
+        defaultModel: 'qwen3.7-plus',
         defaultProtocol: 'openai',
         maxOutputTokens: 65_536,
         noStreamWithTools: true,
@@ -321,12 +326,11 @@ export const PROVIDERS = {
             openai: { baseUrl: 'https://dashscope-intl.aliyuncs.com/compatible-mode/v1', authHeader: 'Bearer', supportsNativeTools: true },
         },
         models: [
-            { id: 'qwen3-coder-plus', name: 'Qwen3-Coder Plus', description: 'Flagship coding model (256K, up to 1M)' },
-            { id: 'qwen3-coder-next', name: 'Qwen3-Coder Next', description: 'Balanced quality/speed/cost' },
-            { id: 'qwen3-coder-flash', name: 'Qwen3-Coder Flash', description: 'Fast/cheap coder' },
-            { id: 'qwen3.7-max', name: 'Qwen3.7-Max', description: 'Flagship general model' },
+            { id: 'qwen3.7-max', name: 'Qwen3.7-Max', description: 'Latest flagship for complex coding and reasoning' },
+            { id: 'qwen3.7-plus', name: 'Qwen3.7-Plus', description: 'Balanced quality, speed, and price (1M context)' },
+            { id: 'qwen3.6-flash', name: 'Qwen3.6-Flash', description: 'Low-latency, low-cost multimodal model' },
         ],
-        defaultModel: 'qwen3-coder-plus',
+        defaultModel: 'qwen3.7-max',
         defaultProtocol: 'openai',
         maxOutputTokens: 65_536,
         noStreamWithTools: true,
@@ -335,6 +339,28 @@ export const PROVIDERS = {
         groupLabel: 'Qwen — API (pay-per-use)',
         hint: 'Pay-per-use via Alibaba Model Studio key (DASHSCOPE_API_KEY).',
     },
+    'qwen-token-plan': {
+        name: 'Qwen (Alibaba) — Token Plan',
+        description: 'Qwen Token Plan subscription (international)',
+        protocols: {
+            openai: { baseUrl: 'https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1', authHeader: 'Bearer', supportsNativeTools: true },
+        },
+        models: [
+            { id: 'qwen3.8-max-preview', name: 'Qwen3.8-Max Preview', description: 'Newest Token Plan flagship for complex agentic work' },
+            { id: 'qwen3.7-max', name: 'Qwen3.7-Max', description: 'Production flagship for complex coding and reasoning' },
+            { id: 'qwen3.7-plus', name: 'Qwen3.7-Plus', description: 'Balanced quality and throughput' },
+            { id: 'qwen3.6-plus', name: 'Qwen3.6-Plus', description: 'Fast multimodal model with a 1M context window' },
+            { id: 'qwen3.6-flash', name: 'Qwen3.6-Flash', description: 'Low-latency, credit-efficient model' },
+        ],
+        defaultModel: 'qwen3.8-max-preview',
+        defaultProtocol: 'openai',
+        maxOutputTokens: 131_072,
+        noStreamWithTools: true,
+        envKey: 'BAILIAN_TOKEN_PLAN_API_KEY',
+        subscribeUrl: 'https://modelstudio.console.alibabacloud.com/',
+        groupLabel: 'Qwen — Subscription (Token Plan)',
+        hint: 'Uses monthly Token Plan credits. Requires a separate sk-sp-… Token Plan key.',
+    },
     'qwen-cn': {
         name: 'Qwen China — Coding Plan',
         description: 'Qwen Coding Plan subscription (China)',
@@ -342,11 +368,11 @@ export const PROVIDERS = {
             openai: { baseUrl: 'https://coding.dashscope.aliyuncs.com/v1', authHeader: 'Bearer', supportsNativeTools: true },
         },
         models: [
-            { id: 'qwen3-coder-plus', name: 'Qwen3-Coder Plus', description: 'Flagship coding model — best quality' },
-            { id: 'qwen3-coder-next', name: 'Qwen3-Coder Next', description: 'Balanced quality/speed/cost' },
-            { id: 'qwen3.7-max', name: 'Qwen3.7-Max', description: 'Flagship general model' },
+            { id: 'qwen3.7-plus', name: 'Qwen3.7-Plus', description: 'Recommended current model for coding, reasoning, and vision' },
+            { id: 'qwen3.6-plus', name: 'Qwen3.6-Plus', description: 'Fast multimodal model with a 1M context window' },
+            { id: 'qwen3.5-plus', name: 'Qwen3.5-Plus', description: 'Efficient general-purpose Coding Plan model' },
         ],
-        defaultModel: 'qwen3-coder-plus',
+        defaultModel: 'qwen3.7-plus',
         defaultProtocol: 'openai',
         maxOutputTokens: 65_536,
         noStreamWithTools: true,
@@ -362,12 +388,11 @@ export const PROVIDERS = {
             openai: { baseUrl: 'https://dashscope.aliyuncs.com/compatible-mode/v1', authHeader: 'Bearer', supportsNativeTools: true },
         },
         models: [
-            { id: 'qwen3-coder-plus', name: 'Qwen3-Coder Plus', description: 'Flagship coding model' },
-            { id: 'qwen3-coder-next', name: 'Qwen3-Coder Next', description: 'Balanced quality/speed/cost' },
-            { id: 'qwen3-coder-flash', name: 'Qwen3-Coder Flash', description: 'Fast/cheap coder' },
-            { id: 'qwen3.7-max', name: 'Qwen3.7-Max', description: 'Flagship general model' },
+            { id: 'qwen3.7-max', name: 'Qwen3.7-Max', description: 'Latest flagship for complex coding and reasoning' },
+            { id: 'qwen3.7-plus', name: 'Qwen3.7-Plus', description: 'Balanced quality, speed, and price (1M context)' },
+            { id: 'qwen3.6-flash', name: 'Qwen3.6-Flash', description: 'Low-latency, low-cost multimodal model' },
         ],
-        defaultModel: 'qwen3-coder-plus',
+        defaultModel: 'qwen3.7-max',
         defaultProtocol: 'openai',
         maxOutputTokens: 65_536,
         noStreamWithTools: true,
@@ -378,21 +403,22 @@ export const PROVIDERS = {
     },
     'modelscope': {
         name: 'ModelScope (free Qwen)',
-        description: 'Free Qwen3-Coder inference via ModelScope',
+        description: 'Live free-model catalog via ModelScope',
         protocols: {
             openai: { baseUrl: 'https://api-inference.modelscope.cn/v1', authHeader: 'Bearer', supportsNativeTools: true },
         },
         models: [
-            { id: 'Qwen/Qwen3-Coder-480B-A35B-Instruct', name: 'Qwen3-Coder 480B', description: 'Open MoE coder — free tier (~2000 req/day)' },
+            { id: 'Qwen/Qwen3-Coder-480B-A35B-Instruct', name: 'Qwen3-Coder 480B', description: 'Fallback model shown until the live catalog loads' },
         ],
         defaultModel: 'Qwen/Qwen3-Coder-480B-A35B-Instruct',
         defaultProtocol: 'openai',
         maxOutputTokens: 65_536,
         noStreamWithTools: true,
+        dynamicModels: true,
         envKey: 'MODELSCOPE_API_KEY',
         subscribeUrl: 'https://modelscope.cn/my/myaccesstoken',
         groupLabel: 'ModelScope — Free (Qwen)',
-        hint: 'Free tier (~2000 req/day) via ModelScope token (modelscope.cn). Needs a bound Aliyun account.',
+        hint: 'Fetches the live free catalog for your ModelScope token; availability and limits vary by account.',
     },
     'openai': {
         name: 'OpenAI',
@@ -408,9 +434,6 @@ export const PROVIDERS = {
             { id: 'gpt-5.6-sol', name: 'GPT-5.6 Sol', description: 'Most capable GPT — best for coding & agentic work' },
             { id: 'gpt-5.6-terra', name: 'GPT-5.6 Terra', description: 'Balanced — GPT-5.5 quality at about half the price' },
             { id: 'gpt-5.6-luna', name: 'GPT-5.6 Luna', description: 'Fast and cheap — high-volume workloads' },
-            { id: 'gpt-5.5', name: 'GPT-5.5', description: 'Previous flagship GPT' },
-            { id: 'gpt-5.4', name: 'GPT-5.4', description: 'Older generation GPT' },
-            { id: 'gpt-5.4-mini', name: 'GPT-5.4 Mini', description: 'Faster and cheaper GPT-5.4' },
         ],
         defaultModel: 'gpt-5.6-sol',
         defaultProtocol: 'openai',
@@ -433,11 +456,11 @@ export const PROVIDERS = {
         },
         models: [
             { id: 'claude-fable-5', name: 'Claude Fable 5', description: 'Most capable — hardest reasoning & long-horizon agentic work' },
-            { id: 'claude-opus-4-8', name: 'Claude Opus 4.8', description: 'Most capable Opus model' },
+            { id: 'claude-opus-5', name: 'Claude Opus 5', description: 'Complex agentic coding & deep reasoning — the Opus workhorse' },
             { id: 'claude-sonnet-5', name: 'Claude Sonnet 5', description: 'Best balance of speed and intelligence' },
             { id: 'claude-haiku-4-5-20251001', name: 'Claude Haiku', description: 'Fastest and most affordable' },
         ],
-        defaultModel: 'claude-opus-4-8',
+        defaultModel: 'claude-opus-5',
         defaultProtocol: 'anthropic',
         envKey: 'ANTHROPIC_API_KEY',
         groupLabel: 'Anthropic',
@@ -455,8 +478,9 @@ export const PROVIDERS = {
         },
         models: [
             { id: 'gemini-3.1-pro-preview', name: 'Gemini 3.1 Pro', description: 'Most capable Gemini model' },
-            { id: 'gemini-3.5-flash', name: 'Gemini 3.5 Flash', description: 'Pro-level intelligence at Flash speed' },
-            { id: 'gemini-3.1-flash-lite', name: 'Gemini 3.1 Flash-Lite', description: 'Low-latency, low-cost workhorse (1M context)' },
+            { id: 'gemini-3.6-flash', name: 'Gemini 3.6 Flash', description: 'Latest production Flash model' },
+            { id: 'gemini-3.5-flash', name: 'Gemini 3.5 Flash', description: 'Stable frontier Flash model for coding and long agentic tasks' },
+            { id: 'gemini-3.5-flash-lite', name: 'Gemini 3.5 Flash-Lite', description: 'Latest low-latency, low-cost workhorse' },
         ],
         defaultModel: 'gemini-3.1-pro-preview',
         defaultProtocol: 'openai',
@@ -482,19 +506,17 @@ export const PROVIDERS = {
         models: [
             { id: 'openrouter/auto', name: 'Auto-route', description: 'OpenRouter picks the best model for the task' },
             { id: 'anthropic/claude-fable-5', name: 'Claude Fable 5', description: 'Anthropic — most capable' },
-            { id: 'anthropic/claude-opus-4', name: 'Claude Opus 4', description: 'Anthropic — Opus tier' },
+            { id: 'anthropic/claude-opus-5', name: 'Claude Opus 5', description: 'Anthropic — flagship Opus tier' },
             { id: 'anthropic/claude-sonnet-5', name: 'Claude Sonnet 5', description: 'Anthropic — balanced' },
             { id: 'openai/gpt-5.6-sol', name: 'GPT-5.6 Sol', description: 'OpenAI — flagship' },
-            { id: 'openai/gpt-5.4-mini', name: 'GPT-5.4 Mini', description: 'OpenAI — fast/cheap' },
-            { id: 'google/gemini-3.1-pro', name: 'Gemini 3.1 Pro', description: 'Google — multimodal' },
-            { id: 'meta-llama/llama-3.1-405b-instruct', name: 'Llama 3.1 405B', description: 'Meta — open weights, largest' },
-            { id: 'meta-llama/llama-3.1-70b-instruct', name: 'Llama 3.1 70B', description: 'Meta — open weights, fast' },
-            { id: 'deepseek/deepseek-v4', name: 'DeepSeek V4', description: 'DeepSeek via OpenRouter' },
-            { id: 'mistralai/mistral-large', name: 'Mistral Large', description: 'Mistral — flagship' },
-            { id: 'qwen/qwen-2.5-coder-32b-instruct', name: 'Qwen 2.5 Coder 32B', description: 'Alibaba — coding-tuned' },
+            { id: 'openai/gpt-5.6-luna', name: 'GPT-5.6 Luna', description: 'OpenAI — fast/efficient' },
+            { id: 'google/gemini-3.6-flash', name: 'Gemini 3.6 Flash', description: 'Google — latest production Flash' },
+            { id: 'deepseek/deepseek-v4-pro', name: 'DeepSeek V4 Pro', description: 'DeepSeek — flagship agentic model' },
+            { id: 'moonshotai/kimi-k3', name: 'Kimi K3', description: 'Moonshot — long-horizon coding' },
+            { id: 'qwen/qwen3.8-max', name: 'Qwen 3.8 Max', description: 'Alibaba — latest flagship' },
             { id: 'x-ai/grok-4.5', name: 'Grok 4.5', description: 'xAI — flagship reasoning' },
         ],
-        defaultModel: 'anthropic/claude-opus-4',
+        defaultModel: 'openrouter/auto',
         defaultProtocol: 'openai',
         envKey: 'OPENROUTER_API_KEY',
         subscribeUrl: 'https://openrouter.ai/keys',
@@ -544,6 +566,65 @@ export const PROVIDERS = {
 export function getProvider(id) {
     return PROVIDERS[id] || null;
 }
+/**
+ * Exact migrations for curated model ids that vendors replaced.
+ *
+ * Keep this deliberately narrower than the provider catalogue. Dynamic
+ * OpenRouter/Ollama/custom ids are user-controlled and must never be rewritten.
+ */
+const RETIRED_MODEL_REPLACEMENTS = {
+    'z.ai': { 'glm-5.1': 'glm-5.2', 'glm-5': 'glm-5.2' },
+    'z.ai-api': { 'glm-5.1': 'glm-5.2', 'glm-5': 'glm-5.2' },
+    'z.ai-cn': { 'glm-5.1': 'glm-5.2', 'glm-5': 'glm-5.2' },
+    'z.ai-cn-api': { 'glm-5.1': 'glm-5.2', 'glm-5': 'glm-5.2' },
+    google: {
+        'gemini-3.1-flash-lite': 'gemini-3.5-flash-lite',
+    },
+    grok: {
+        'grok-code-fast-1': 'grok-build-0.1',
+        'grok-4-fast-reasoning': 'grok-4.3',
+    },
+    openai: {
+        'gpt-5.5': 'gpt-5.6-sol',
+        'gpt-5.4': 'gpt-5.6-terra',
+        'gpt-5.4-mini': 'gpt-5.6-luna',
+    },
+    'kimi-api': {
+        'kimi-k3-code': 'kimi-k3',
+        'kimi-k3-code-highspeed': 'kimi-k3',
+        'kimi-k3-thinking': 'kimi-k3',
+        'kimi-k2.5': 'kimi-k2.6',
+    },
+    'kimi-cn': {
+        'kimi-k3-code': 'kimi-k3',
+        'kimi-k3-code-highspeed': 'kimi-k3',
+        'kimi-k3-thinking': 'kimi-k3',
+        'kimi-k2.5': 'kimi-k2.6',
+    },
+    qwen: {
+        'qwen3-coder-plus': 'qwen3.7-plus',
+        'qwen3-coder-next': 'qwen3.7-plus',
+        'qwen3.7-max': 'qwen3.7-plus',
+    },
+    'qwen-api': {
+        'qwen3-coder-plus': 'qwen3.7-max',
+        'qwen3-coder-next': 'qwen3.7-max',
+        'qwen3-coder-flash': 'qwen3.6-flash',
+    },
+    'qwen-cn': {
+        'qwen3-coder-plus': 'qwen3.7-plus',
+        'qwen3-coder-next': 'qwen3.7-plus',
+        'qwen3.7-max': 'qwen3.7-plus',
+    },
+    'qwen-cn-api': {
+        'qwen3-coder-plus': 'qwen3.7-max',
+        'qwen3-coder-next': 'qwen3.7-max',
+        'qwen3-coder-flash': 'qwen3.6-flash',
+    },
+};
+export function replacementModelFor(providerId, modelId) {
+    return RETIRED_MODEL_REPLACEMENTS[providerId]?.[modelId];
+}
 /**
  * Curated display order for the first-run login flow + `/provider` /
  * `/login` pickers. Headline / popular providers float to the top so
@@ -561,6 +642,7 @@ const DISPLAY_ORDER = [
     'kimi',
     'kimi-api',
     'qwen',
+    'qwen-token-plan',
     'qwen-api',
     'grok',
     'deepseek',
@@ -666,8 +748,8 @@ export function providerNoStreamWithTools(providerId) {
  * internally and 400 on any custom value, so they're here too.
  */
 const SAMPLING_PARAMS_REJECTED = [
-    'claude-fable-5', 'claude-opus-4-8', 'claude-opus-4-7', 'claude-sonnet-5',
-    'kimi-k2.7-code', 'kimi-for-coding',
+    'claude-fable-5', 'claude-opus-5', 'claude-opus-4-8', 'claude-opus-4-7', 'claude-sonnet-5',
+    'kimi-k3', 'kimi-k2.7-code', 'kimi-for-coding', 'k3',
 ];
 export function modelRejectsSamplingParams(model) {
     return SAMPLING_PARAMS_REJECTED.some(id => model === id || model.startsWith(`${id}-`));
@@ -709,10 +791,10 @@ export function modelSupportsReasoningEffort(providerId, model) {
     const id = canonicalModelId(model);
     switch (providerId) {
         case 'anthropic':
-            // Effort is GA on Opus 4.5+, Sonnet 4.6/5, Fable 5 — NOT Haiku or Sonnet 4.5.
+            // Effort is GA on Opus 5, Opus 4.5+, Sonnet 4.6/5, Fable 5 — NOT Haiku or Sonnet 4.5.
             if (idMatches(id, 'claude-haiku-4-5') || idMatches(id, 'claude-sonnet-4-5'))
                 return false;
-            return /^claude-(opus-4-([5-9]|\d\d)|sonnet-(4-6|5)|fable-5)/.test(id);
+            return /^claude-(opus-5|opus-4-([5-9]|\d\d)|sonnet-(4-6|5)|fable-5)/.test(id);
         case 'openai':
             // GPT-5.x are reasoning models — reasoning_effort across the family (incl. mini).
             return id.startsWith('gpt-5');
@@ -725,9 +807,13 @@ export function modelSupportsReasoningEffort(providerId, model) {
         case 'z.ai-api':
         case 'z.ai-cn':
         case 'z.ai-cn-api':
-            // GLM-5.2 added graded High/Max effort. glm-5-turbo is a plain thinking
-            // toggle (no graded levels) so it stays out.
+            // GLM-5.2 exposes graded High/Max effort; Turbo is a plain toggle.
             return idMatches(id, 'glm-5-2');
+        case 'kimi':
+            return idMatches(id, 'k3');
+        case 'kimi-api':
+        case 'kimi-cn':
+            return idMatches(id, 'kimi-k3');
         case 'grok':
             // Grok reasoning models accept reasoning_effort (none/low/medium/high).
             // The coders (grok-code-fast, grok-build — the default) are NON-reasoning
@@ -737,8 +823,7 @@ export function modelSupportsReasoningEffort(providerId, model) {
             if (id.startsWith('grok-build') || id.startsWith('grok-code'))
                 return false;
             return id.startsWith('grok') && !id.includes('non-reasoning');
-        // Kimi (thinking on/off, not graded) and Qwen coders (non-thinking) have
-        // no graded knob → fall through to default false.
+        // GLM Turbo and Qwen coders expose thinking on/off, not a graded knob.
         case 'openrouter':
             // OpenRouter normalizes a unified `reasoning` field and silently ignores
             // it for non-reasoning models, so the control is always safe to expose.
@@ -778,6 +863,11 @@ export function reasoningParamsFor(providerId, model, tier) {
         case 'z.ai-cn-api':
             // Graded thinking depth: high (default) or max. Lower tiers collapse to high.
             return { reasoning_effort: tier === 'max' ? 'max' : 'high' };
+        case 'kimi':
+        case 'kimi-api':
+        case 'kimi-cn':
+            // Kimi K3 accepts low/high/max; collapse our medium tier to high.
+            return { reasoning_effort: tier === 'low' ? 'low' : tier === 'max' ? 'max' : 'high' };
         case 'grok':
             // none/low/medium/high — no "max"; map our Max → high (the ceiling).
             return { reasoning_effort: tier === 'max' ? 'high' : tier };
@@ -814,6 +904,10 @@ export function availableReasoningTiers(providerId, model) {
         case 'z.ai-cn':
         case 'z.ai-cn-api':
             return ['auto', 'high', 'max'];
+        case 'kimi':
+        case 'kimi-api':
+        case 'kimi-cn':
+            return ['auto', 'low', 'high', 'max'];
         case 'grok':
             return ['auto', 'low', 'medium', 'high'];
         case 'openrouter':
@@ -825,8 +919,8 @@ export function availableReasoningTiers(providerId, model) {
 /**
  * Map a (possibly out-of-range) tier to the tier this model actually distinguishes,
  * for display — the chip + the checked menu row. The effort setting is global, so
- * a tier picked on Opus ('low') may not exist on GLM-5.2; we show the level GLM
- * will really run (its 'low' clamps to 'high'). Picks the available tier whose
+ * a tier picked on Opus ('medium') may not exist on Kimi K3; we show the level
+ * Kimi will really run (its 'medium' clamps to 'high'). Picks the tier whose
  * effective param equals the requested one. 'auto' (or unsupported) → 'auto'.
  */
 export function resolveReasoningTier(providerId, model, tier) {

package/dist/renderer/App.d.ts

@@ -20,6 +20,37 @@ export interface ConfirmOptions {
     onConfirm: () => void;
     onCancel?: () => void;
 }
+/**
+ * One hunk in the interactive `/apply --interactive` picker.
+ * `lines` are already-formatted diff lines (e.g. `+ added`, `- removed`).
+ */
+export interface HunkPickerItem {
+    /** File path this hunk belongs to. */
+    path: string;
+    /** 0-based hunk index within the file diff. */
+    hunkIndex: number;
+    /** Human-readable hunk header, e.g. `@@ -12,3 +12,5 @@`. */
+    header: string;
+    /** Pre-formatted diff lines to display. */
+    lines: string[];
+}
+/**
+ * Options for the interactive hunk picker. The picker walks the user
+ * through `items` one at a time; for each they accept (`y`/Enter) or
+ * skip (`n`). `a` accepts all remaining, `q`/Esc quits.
+ *
+ * `onComplete` fires once with the set of accepted `[path, hunkIndex]`
+ * pairs (possibly empty) so the caller can apply them via
+ * `applyHunksToFiles`.
+ */
+export interface HunkPickerOptions {
+    title: string;
+    items: HunkPickerItem[];
+    onComplete: (accepted: Array<{
+        path: string;
+        hunkIndex: number;
+    }>) => void;
+}
 export interface AppOptions {
     onSubmit: (message: string) => Promise<void>;
     onCommand: (command: string, args: string[]) => void;
@@ -29,6 +60,8 @@ export interface AppOptions {
     getStatus: () => StatusInfo;
     hasWriteAccess?: () => boolean;
     hasProjectContext?: () => boolean;
+    /** Project root for `@mention` autocomplete suggestions. Falls back to cwd. */
+    getProjectRoot?: () => string;
 }
 export declare class App {
     private screen;
@@ -56,6 +89,10 @@ export declare class App {
     private agentThinking;
     private agentWaitingForAI;
     private agentLog;
+    /** Process uptime shown in the persistent footer. */
+    private appStartedAt;
+    /** Start of the current agent run; unlike app uptime, resets per task. */
+    private agentStartedAt;
     private pasteInfo;
     private pasteInfoOpen;
     private codeBlockCounter;
@@ -67,9 +104,19 @@ export declare class App {
     private showAutocomplete;
     private autocompleteIndex;
     private autocompleteItems;
+    private showMentionAutocomplete;
+    private mentionIndex;
+    private mentionItems;
+    private mentionAtStart;
+    /** Project root for resolving `suggestMentions`. Cached per update. */
+    private mentionRoot;
     private confirmOpen;
     private confirmOptions;
     private confirmSelection;
+    private hunkPickerOpen;
+    private hunkPickerOptions;
+    private hunkPickerIndex;
+    private hunkPickerAccepted;
     private menuOpen;
     private menuTitle;
     /** Filtered view shown to the user; derived from `menuItemsAll` + `menuFilter`. */
@@ -231,6 +278,11 @@ export declare class App {
      * Show confirmation dialog
      */
     showConfirm(options: ConfirmOptions): void;
+    /**
+     * Show the interactive hunk picker (`/apply --interactive`).
+     * The caller passes pre-built items + an `onComplete` callback.
+     */
+    showHunkPicker(options: HunkPickerOptions): void;
     /**
      * Show permission dialog (inline, below status bar)
      */
@@ -314,6 +366,13 @@ export declare class App {
      * Update autocomplete suggestions
      */
     private updateAutocomplete;
+    /**
+     * Replace the in-progress `@query` (from `mentionAtStart` to the
+     * cursor) with the selected mention's path. Keeps the `@` prefix and
+     * positions the cursor right after the inserted path so the user can
+     * keep typing the rest of the message.
+     */
+    private applyMentionSelection;
     /**
      * Handle inline status keys
      */
@@ -352,6 +411,15 @@ export declare class App {
     private handleInlinePermissionKey;
     private handleInlineSessionPickerKey;
     private handleInlineConfirmKey;
+    /**
+     * Handle keys in the interactive hunk picker.
+     *   y / Enter / →  accept this hunk, advance
+     *   n / ←         skip this hunk, advance
+     *   a             accept this + all remaining, finish
+     *   q / Esc       finish without accepting this hunk
+     *   ↑ / ↓         navigate (preview only — no decision)
+     */
+    private handleHunkPickerKey;
     /**
      * Submit the current input buffer (used by Enter and Escape-in-multiline)
      */
@@ -369,10 +437,23 @@ export declare class App {
      * Render chat screen
      */
     private renderChat;
+    private shouldRenderAgentTimeline;
+    private renderPersistentHeader;
+    private renderAgentTimelineScreen;
+    private renderAgentContextRail;
+    private renderAgentKeyHints;
+    private timelineStatusStyle;
+    private currentActionType;
+    private currentAgentTask;
     /**
      * Render inline confirmation dialog below status bar
      */
     private renderInlineConfirm;
+    /**
+     * Render inline hunk picker (`/apply --interactive`).
+     * Shows the current hunk's diff + the y/n/a/q key legend.
+     */
+    private renderInlineHunkPicker;
     /**
      * Render input line
      */
@@ -394,6 +475,14 @@ export declare class App {
      * Render inline autocomplete below status bar
      */
     private renderInlineAutocomplete;
+    /**
+     * Render inline `@mention` file picker below the status bar.
+     *
+     * Mirrors the layout of `renderInlineAutocomplete` (separator → title →
+     * items → footer) but shows file paths with their parent directory as
+     * the description, and a `@` prefix instead of `/`.
+     */
+    private renderInlineMentionPicker;
     /**
      * Render inline permission dialog
      */