@psnext/slingcli 2.4.20260526-1 → 2.4.20260527-2

package/node_modules/@earendil-works/pi-ai/dist/models.generated.js

@@ -1720,6 +1720,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "anthropic",
             baseUrl: "https://api.anthropic.com",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "max" },
             input: ["text", "image"],
@@ -1738,6 +1739,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "anthropic",
             baseUrl: "https://api.anthropic.com",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
@@ -1824,6 +1826,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "anthropic",
             baseUrl: "https://api.anthropic.com",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -1916,7 +1919,7 @@ export const MODELS = {
             cost: {
                 input: 0.1,
                 output: 0.4,
-                cacheRead: 0.03,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 1047576,
@@ -2001,7 +2004,7 @@ export const MODELS = {
             cost: {
                 input: 0.15,
                 output: 0.6,
-                cacheRead: 0.08,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -2127,7 +2130,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.13,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -2552,7 +2555,7 @@ export const MODELS = {
             cost: {
                 input: 1.1,
                 output: 4.4,
-                cacheRead: 0.28,
+                cacheRead: 0.275,
                 cacheWrite: 0,
             },
             contextWindow: 200000,
@@ -2823,6 +2826,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "cloudflare-ai-gateway",
             baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "max" },
             input: ["text", "image"],
@@ -2841,6 +2845,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "cloudflare-ai-gateway",
             baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
@@ -2893,6 +2898,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "cloudflare-ai-gateway",
             baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -3777,6 +3783,7 @@ export const MODELS = {
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
             headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "max" },
             input: ["text", "image"],
@@ -3796,6 +3803,7 @@ export const MODELS = {
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
             headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
@@ -3834,6 +3842,7 @@ export const MODELS = {
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
             headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -6253,7 +6262,7 @@ export const MODELS = {
             cost: {
                 input: 0.1,
                 output: 0.4,
-                cacheRead: 0.03,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 1047576,
@@ -6338,7 +6347,7 @@ export const MODELS = {
             cost: {
                 input: 0.15,
                 output: 0.6,
-                cacheRead: 0.08,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -6464,7 +6473,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.13,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -6889,7 +6898,7 @@ export const MODELS = {
             cost: {
                 input: 1.1,
                 output: 4.4,
-                cacheRead: 0.28,
+                cacheRead: 0.275,
                 cacheWrite: 0,
             },
             contextWindow: 200000,
@@ -6965,7 +6974,7 @@ export const MODELS = {
                 cacheRead: 0.175,
                 cacheWrite: 0,
             },
-            contextWindow: 272000,
+            contextWindow: 128000,
             maxTokens: 128000,
         },
         "gpt-5.4": {
@@ -7098,6 +7107,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "max" },
             input: ["text", "image"],
@@ -7116,6 +7126,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
@@ -7168,6 +7179,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -7922,6 +7934,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
+        "qwen3.7-max": {
+            id: "qwen3.7-max",
+            name: "Qwen3.7 Max",
+            api: "anthropic-messages",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 2.5,
+                output: 7.5,
+                cacheRead: 0.5,
+                cacheWrite: 3.125,
+            },
+            contextWindow: 1000000,
+            maxTokens: 65536,
+        },
     },
     "openrouter": {
         "ai21/jamba-large-1.7": {
@@ -8268,23 +8297,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 262144,
         },
-        "arcee-ai/trinity-large-thinking:free": {
-            id: "arcee-ai/trinity-large-thinking:free",
-            name: "Arcee AI: Trinity Large Thinking (free)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 80000,
-        },
         "arcee-ai/trinity-mini": {
             id: "arcee-ai/trinity-mini",
             name: "Arcee AI: Trinity Mini",
@@ -10987,8 +10999,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 8192,
+            contextWindow: 262144,
+            maxTokens: 32768,
         },
         "poolside/laguna-xs.2:free": {
             id: "poolside/laguna-xs.2:free",
@@ -11004,8 +11016,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 8192,
+            contextWindow: 262144,
+            maxTokens: 32768,
         },
         "prime-intellect/intellect-3": {
             id: "prime-intellect/intellect-3",
@@ -11087,7 +11099,7 @@ export const MODELS = {
                 input: 0.26,
                 output: 0.78,
                 cacheRead: 0,
-                cacheWrite: 0.325,
+                cacheWrite: 0,
             },
             contextWindow: 1000000,
             maxTokens: 32768,
@@ -11665,7 +11677,7 @@ export const MODELS = {
                 input: 0.065,
                 output: 0.26,
                 cacheRead: 0,
-                cacheWrite: 0.08125,
+                cacheWrite: 0,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
@@ -11682,7 +11694,7 @@ export const MODELS = {
                 input: 0.26,
                 output: 1.56,
                 cacheRead: 0,
-                cacheWrite: 0.325,
+                cacheWrite: 0,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
@@ -11699,7 +11711,7 @@ export const MODELS = {
                 input: 0.3,
                 output: 1.7999999999999998,
                 cacheRead: 0,
-                cacheWrite: 0,
+                cacheWrite: 0.375,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
@@ -11713,13 +11725,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.3,
+                input: 0.29,
                 output: 3.1999999999999997,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 262140,
         },
         "qwen/qwen3.6-35b-a3b": {
             id: "qwen/qwen3.6-35b-a3b",
@@ -11730,7 +11742,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.15,
+                input: 0.14,
                 output: 1,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -11798,10 +11810,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 2.5,
-                output: 7.5,
-                cacheRead: 0,
-                cacheWrite: 3.125,
+                input: 1.25,
+                output: 3.75,
+                cacheRead: 0.25,
+                cacheWrite: 1.5625,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
@@ -12070,9 +12082,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.39999999999999997,
-                output: 2,
-                cacheRead: 0.08,
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.0028,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -12087,13 +12099,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1,
-                output: 3,
-                cacheRead: 0.19999999999999998,
+                input: 0.435,
+                output: 0.87,
+                cacheRead: 0.0036,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 16384,
+            maxTokens: 131072,
         },
         "z-ai/glm-4-32b": {
             id: "z-ai/glm-4-32b",
@@ -12138,13 +12150,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.13,
-                output: 0.85,
-                cacheRead: 0.024999999999999998,
+                input: 0.125,
+                output: 0.84,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 98304,
+            maxTokens: 131070,
         },
         "z-ai/glm-4.5-air:free": {
             id: "z-ai/glm-4.5-air:free",
@@ -13226,6 +13238,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "max" },
             input: ["text", "image"],
@@ -13244,6 +13257,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
@@ -13296,6 +13310,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -15249,9 +15264,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.39999999999999997,
-                output: 2,
-                cacheRead: 0.08,
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.0028,
                 cacheWrite: 0,
             },
             contextWindow: 1050000,
@@ -15266,9 +15281,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 3,
-                cacheRead: 0.19999999999999998,
+                input: 0.435,
+                output: 0.87,
+                cacheRead: 0.0036,
                 cacheWrite: 0,
             },
             contextWindow: 1050000,

package/node_modules/@earendil-works/pi-ai/dist/providers/amazon-bedrock.js

@@ -90,12 +90,13 @@ export const streamBedrock = (model, context, options = {}) => {
         try {
             const client = new BedrockRuntimeClient(config);
             const cacheRetention = resolveCacheRetention(options.cacheRetention);
+            const inferenceMaxTokens = options.maxTokens ?? (isAnthropicClaudeModel(model) ? model.maxTokens : undefined);
             let commandInput = {
                 modelId: model.id,
                 messages: convertMessages(context, model, cacheRetention),
                 system: buildSystemPrompt(context.systemPrompt, model, cacheRetention),
                 inferenceConfig: {
-                    ...(options.maxTokens !== undefined && { maxTokens: options.maxTokens }),
+                    ...(inferenceMaxTokens !== undefined && { maxTokens: inferenceMaxTokens }),
                     ...(options.temperature !== undefined && { temperature: options.temperature }),
                 },
                 toolConfig: convertToolConfig(context.tools, options.toolChoice),

package/node_modules/@earendil-works/pi-ai/dist/providers/anthropic.js

@@ -329,7 +329,7 @@ export const streamAnthropic = (model, context, options) => {
             const requestOptions = {
                 ...(options?.signal ? { signal: options.signal } : {}),
                 ...(options?.timeoutMs !== undefined ? { timeout: options.timeoutMs } : {}),
-                ...(options?.maxRetries !== undefined ? { maxRetries: options.maxRetries } : {}),
+                maxRetries: options?.maxRetries ?? 0,
             };
             const response = await client.messages.create({ ...params, stream: true }, requestOptions).asResponse();
             await options?.onResponse?.({ status: response.status, headers: headersToRecord(response.headers) }, model);
@@ -527,18 +527,6 @@ export const streamAnthropic = (model, context, options) => {
     })();
     return stream;
 };
-/**
- * Check if a model supports adaptive thinking (Opus 4.6+, Sonnet 4.6)
- */
-function supportsAdaptiveThinking(modelId) {
-    // Adaptive-thinking model IDs (with or without date suffix)
-    return (modelId.includes("opus-4-6") ||
-        modelId.includes("opus-4.6") ||
-        modelId.includes("opus-4-7") ||
-        modelId.includes("opus-4.7") ||
-        modelId.includes("sonnet-4-6") ||
-        modelId.includes("sonnet-4.6"));
-}
 /**
  * Map ThinkingLevel to Anthropic effort levels for adaptive thinking.
  * Note: effort "max" is only valid on Opus 4.6, while Opus 4.7 supports "xhigh".
@@ -568,9 +556,9 @@ export const streamSimpleAnthropic = (model, context, options) => {
     if (!options?.reasoning) {
         return streamAnthropic(model, context, { ...base, thinkingEnabled: false });
     }
-    // For Opus 4.6 and Sonnet 4.6: use adaptive thinking with effort level
-    // For older models: use budget-based thinking
-    if (supportsAdaptiveThinking(model.id)) {
+    // For models with adaptive thinking: use an effort level.
+    // For older models: use budget-based thinking.
+    if (model.compat?.forceAdaptiveThinking === true) {
         const effort = mapThinkingLevelToEffort(model, options.reasoning);
         return streamAnthropic(model, context, {
             ...base,
@@ -592,9 +580,8 @@ function isOAuthToken(apiKey) {
     return apiKey.includes("sk-ant-oat");
 }
 function createClient(model, apiKey, interleavedThinking, useFineGrainedToolStreamingBeta, optionsHeaders, dynamicHeaders, sessionId) {
-    // Adaptive thinking models (Opus 4.6, Sonnet 4.6) have interleaved thinking built-in.
-    // The beta header is deprecated on Opus 4.6 and redundant on Sonnet 4.6, so skip it.
-    const needsInterleavedBeta = interleavedThinking && !supportsAdaptiveThinking(model.id);
+    // Adaptive thinking models have interleaved thinking built in, so skip the beta header.
+    const needsInterleavedBeta = interleavedThinking && model.compat?.forceAdaptiveThinking !== true;
     const betaFeatures = [];
     if (useFineGrainedToolStreamingBeta) {
         betaFeatures.push(FINE_GRAINED_TOOL_STREAMING_BETA);
@@ -709,14 +696,13 @@ function buildParams(model, context, isOAuthToken, options) {
         const compat = getAnthropicCompat(model);
         params.tools = convertTools(context.tools, isOAuthToken, compat.supportsEagerToolInputStreaming, compat.supportsCacheControlOnTools ? cacheControl : undefined);
     }
-    // Configure thinking mode: adaptive (Opus 4.6+ and Sonnet 4.6),
-    // budget-based (older models), or explicitly disabled.
+    // Configure thinking mode: adaptive, budget-based, or explicitly disabled.
     if (model.reasoning) {
         if (options?.thinkingEnabled) {
             // Default to "summarized" so Opus 4.7 and Mythos Preview behave like
             // older Claude 4 models (whose API default is also "summarized").
             const display = options.thinkingDisplay ?? "summarized";
-            if (supportsAdaptiveThinking(model.id)) {
+            if (model.compat?.forceAdaptiveThinking === true) {
                 // Adaptive thinking: Claude decides when and how much to think.
                 params.thinking = { type: "adaptive", display };
                 if (options.effort) {

package/node_modules/@earendil-works/pi-ai/dist/providers/azure-openai-responses.js

@@ -83,7 +83,7 @@ export const streamAzureOpenAIResponses = (model, context, options) => {
             const requestOptions = {
                 ...(options?.signal ? { signal: options.signal } : {}),
                 ...(options?.timeoutMs !== undefined ? { timeout: options.timeoutMs } : {}),
-                ...(options?.maxRetries !== undefined ? { maxRetries: options.maxRetries } : {}),
+                maxRetries: options?.maxRetries ?? 0,
             };
             const { data: openaiStream, response } = await client.responses.create(params, requestOptions).withResponse();
             await options?.onResponse?.({ status: response.status, headers: headersToRecord(response.headers) }, model);

package/node_modules/@earendil-works/pi-ai/dist/providers/images/openrouter.js

@@ -25,7 +25,7 @@ export const generateImagesOpenRouter = async (model, context, options) => {
         const requestOptions = {
             ...(options?.signal ? { signal: options.signal } : {}),
             ...(options?.timeoutMs !== undefined ? { timeout: options.timeoutMs } : {}),
-            ...(options?.maxRetries !== undefined ? { maxRetries: options.maxRetries } : {}),
+            maxRetries: options?.maxRetries ?? 0,
         };
         const { data: response, response: rawResponse } = await client.chat.completions
             .create(params, requestOptions)