@psnext/slingcli 2.5.20260617-1 → 2.5.20260617-2

package/node_modules/@earendil-works/pi-agent-core/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@earendil-works/pi-agent-core",
-	"version": "0.79.3",
+	"version": "0.79.6",
 	"description": "General-purpose agent with transport abstraction, state management, and attachment support",
 	"type": "module",
 	"main": "./dist/index.js",
@@ -29,7 +29,7 @@
 		"prepublishOnly": "npm run clean && npm run build"
 	},
 	"dependencies": {
-		"@earendil-works/pi-ai": "^0.79.3",
+		"@earendil-works/pi-ai": "^0.79.6",
 		"ignore": "7.0.5",
 		"typebox": "1.1.38",
 		"yaml": "2.9.0"

package/node_modules/@earendil-works/pi-ai/dist/env-api-keys.js

@@ -26,40 +26,13 @@ if (typeof process !== "undefined" && (process.versions?.node || process.version
         _join = m.join;
     });
 }
-let _procEnvCache = null;
-/**
- * Fallback for https://github.com/oven-sh/bun/issues/27802
- * Bun compiled binaries have an empty `process.env` inside sandbox
- * environments on Linux. We can recover the env from `/proc/self/environ`.
- */
-function getProcEnv(key) {
-    if (!process.versions?.bun)
-        return undefined;
-    if (typeof process === "undefined")
-        return undefined;
-    // If process.env already has entries, the bug is not triggered.
-    if (Object.keys(process.env).length > 0)
-        return undefined;
-    if (_procEnvCache === null) {
-        _procEnvCache = new Map();
-        try {
-            const { readFileSync } = require("node:fs");
-            const data = readFileSync("/proc/self/environ", "utf-8");
-            for (const entry of data.split("\0")) {
-                const idx = entry.indexOf("=");
-                if (idx > 0) {
-                    _procEnvCache.set(entry.slice(0, idx), entry.slice(idx + 1));
-                }
-            }
-        }
-        catch {
-            // /proc/self/environ may not be readable.
-        }
-    }
-    return _procEnvCache.get(key);
-}
+import { getProviderEnvValue } from "./utils/provider-env.js";
 let cachedVertexAdcCredentialsExists = null;
-function hasVertexAdcCredentials() {
+function hasVertexAdcCredentials(env) {
+    const explicitCredentialsPath = env?.GOOGLE_APPLICATION_CREDENTIALS;
+    if (explicitCredentialsPath) {
+        return _existsSync ? _existsSync(explicitCredentialsPath) : false;
+    }
     if (cachedVertexAdcCredentialsExists === null) {
         // If node modules haven't loaded yet (async import race at startup),
         // return false WITHOUT caching so the next call retries once they're ready.
@@ -73,7 +46,7 @@ function hasVertexAdcCredentials() {
             return false;
         }
         // Check GOOGLE_APPLICATION_CREDENTIALS env var first (standard way)
-        const gacPath = process.env.GOOGLE_APPLICATION_CREDENTIALS || getProcEnv("GOOGLE_APPLICATION_CREDENTIALS");
+        const gacPath = getProviderEnvValue("GOOGLE_APPLICATION_CREDENTIALS", env);
         if (gacPath) {
             cachedVertexAdcCredentialsExists = _existsSync(gacPath);
         }
@@ -128,27 +101,24 @@ function getApiKeyEnvVars(provider) {
     const envVar = envMap[provider];
     return envVar ? [envVar] : undefined;
 }
-export function findEnvKeys(provider) {
+export function findEnvKeys(provider, env) {
     const envVars = getApiKeyEnvVars(provider);
     if (!envVars)
         return undefined;
-    const found = envVars.filter((envVar) => !!process.env[envVar] || !!getProcEnv(envVar));
+    const found = envVars.filter((envVar) => !!getProviderEnvValue(envVar, env));
     return found.length > 0 ? found : undefined;
 }
-export function getEnvApiKey(provider) {
-    const envKeys = findEnvKeys(provider);
+export function getEnvApiKey(provider, env) {
+    const envKeys = findEnvKeys(provider, env);
     if (envKeys?.[0]) {
-        return process.env[envKeys[0]] || getProcEnv(envKeys[0]);
+        return getProviderEnvValue(envKeys[0], env);
     }
     // Vertex AI supports either an explicit API key or Application Default Credentials.
     // Auth is configured via `gcloud auth application-default login`.
     if (provider === "google-vertex") {
-        const hasCredentials = hasVertexAdcCredentials();
-        const hasProject = !!(process.env.GOOGLE_CLOUD_PROJECT ||
-            process.env.GCLOUD_PROJECT ||
-            getProcEnv("GOOGLE_CLOUD_PROJECT") ||
-            getProcEnv("GCLOUD_PROJECT"));
-        const hasLocation = !!(process.env.GOOGLE_CLOUD_LOCATION || getProcEnv("GOOGLE_CLOUD_LOCATION"));
+        const hasCredentials = hasVertexAdcCredentials(env);
+        const hasProject = !!(getProviderEnvValue("GOOGLE_CLOUD_PROJECT", env) || getProviderEnvValue("GCLOUD_PROJECT", env));
+        const hasLocation = !!getProviderEnvValue("GOOGLE_CLOUD_LOCATION", env);
         if (hasCredentials && hasProject && hasLocation) {
             return "<authenticated>";
         }
@@ -161,18 +131,12 @@ export function getEnvApiKey(provider) {
         // 4. AWS_CONTAINER_CREDENTIALS_RELATIVE_URI - ECS task roles
         // 5. AWS_CONTAINER_CREDENTIALS_FULL_URI - ECS task roles (full URI)
         // 6. AWS_WEB_IDENTITY_TOKEN_FILE - IRSA (IAM Roles for Service Accounts)
-        if (process.env.AWS_PROFILE ||
-            (process.env.AWS_ACCESS_KEY_ID && process.env.AWS_SECRET_ACCESS_KEY) ||
-            process.env.AWS_BEARER_TOKEN_BEDROCK ||
-            process.env.AWS_CONTAINER_CREDENTIALS_RELATIVE_URI ||
-            process.env.AWS_CONTAINER_CREDENTIALS_FULL_URI ||
-            process.env.AWS_WEB_IDENTITY_TOKEN_FILE ||
-            getProcEnv("AWS_PROFILE") ||
-            (getProcEnv("AWS_ACCESS_KEY_ID") && getProcEnv("AWS_SECRET_ACCESS_KEY")) ||
-            getProcEnv("AWS_BEARER_TOKEN_BEDROCK") ||
-            getProcEnv("AWS_CONTAINER_CREDENTIALS_RELATIVE_URI") ||
-            getProcEnv("AWS_CONTAINER_CREDENTIALS_FULL_URI") ||
-            getProcEnv("AWS_WEB_IDENTITY_TOKEN_FILE")) {
+        if (getProviderEnvValue("AWS_PROFILE", env) ||
+            (getProviderEnvValue("AWS_ACCESS_KEY_ID", env) && getProviderEnvValue("AWS_SECRET_ACCESS_KEY", env)) ||
+            getProviderEnvValue("AWS_BEARER_TOKEN_BEDROCK", env) ||
+            getProviderEnvValue("AWS_CONTAINER_CREDENTIALS_RELATIVE_URI", env) ||
+            getProviderEnvValue("AWS_CONTAINER_CREDENTIALS_FULL_URI", env) ||
+            getProviderEnvValue("AWS_WEB_IDENTITY_TOKEN_FILE", env)) {
             return "<authenticated>";
         }
     }

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

@@ -4227,7 +4227,7 @@ export const MODELS = {
             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, "supportsTemperature": false },
             reasoning: true,
-            thinkingLevelMap: { "xhigh": "xhigh" },
+            thinkingLevelMap: { "xhigh": "xhigh", "minimal": "low" },
             input: ["text", "image"],
             cost: {
                 input: 5,
@@ -4247,7 +4247,7 @@ export const MODELS = {
             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, "supportsTemperature": false },
             reasoning: true,
-            thinkingLevelMap: { "xhigh": "xhigh" },
+            thinkingLevelMap: { "xhigh": "xhigh", "minimal": "low" },
             input: ["text", "image"],
             cost: {
                 input: 5,
@@ -4305,6 +4305,7 @@ export const MODELS = {
             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: { "minimal": "low", "xhigh": "max" },
             input: ["text", "image"],
             cost: {
                 input: 3,
@@ -4801,11 +4802,12 @@ export const MODELS = {
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
             reasoning: true,
+            thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 0.3,
-                output: 2.5,
-                cacheRead: 0.075,
+                input: 1.5,
+                output: 9,
+                cacheRead: 0.15,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -4818,10 +4820,11 @@ export const MODELS = {
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
             reasoning: true,
+            thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 0.1,
-                output: 0.4,
+                input: 0.25,
+                output: 1.5,
                 cacheRead: 0.025,
                 cacheWrite: 0,
             },
@@ -4902,94 +4905,9 @@ export const MODELS = {
         },
     },
     "google-vertex": {
-        "gemini-1.5-flash": {
-            id: "gemini-1.5-flash",
-            name: "Gemini 1.5 Flash (Vertex)",
-            api: "google-vertex",
-            provider: "google-vertex",
-            baseUrl: "https://{location}-aiplatform.googleapis.com",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.075,
-                output: 0.3,
-                cacheRead: 0.01875,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 8192,
-        },
-        "gemini-1.5-flash-8b": {
-            id: "gemini-1.5-flash-8b",
-            name: "Gemini 1.5 Flash-8B (Vertex)",
-            api: "google-vertex",
-            provider: "google-vertex",
-            baseUrl: "https://{location}-aiplatform.googleapis.com",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.0375,
-                output: 0.15,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 8192,
-        },
-        "gemini-1.5-pro": {
-            id: "gemini-1.5-pro",
-            name: "Gemini 1.5 Pro (Vertex)",
-            api: "google-vertex",
-            provider: "google-vertex",
-            baseUrl: "https://{location}-aiplatform.googleapis.com",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 1.25,
-                output: 5,
-                cacheRead: 0.3125,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 8192,
-        },
-        "gemini-2.0-flash": {
-            id: "gemini-2.0-flash",
-            name: "Gemini 2.0 Flash (Vertex)",
-            api: "google-vertex",
-            provider: "google-vertex",
-            baseUrl: "https://{location}-aiplatform.googleapis.com",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0.0375,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 8192,
-        },
-        "gemini-2.0-flash-lite": {
-            id: "gemini-2.0-flash-lite",
-            name: "Gemini 2.0 Flash Lite (Vertex)",
-            api: "google-vertex",
-            provider: "google-vertex",
-            baseUrl: "https://{location}-aiplatform.googleapis.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.075,
-                output: 0.3,
-                cacheRead: 0.01875,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
         "gemini-2.5-flash": {
             id: "gemini-2.5-flash",
-            name: "Gemini 2.5 Flash (Vertex)",
+            name: "Gemini 2.5 Flash",
             api: "google-vertex",
             provider: "google-vertex",
             baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -5006,24 +4924,7 @@ export const MODELS = {
         },
         "gemini-2.5-flash-lite": {
             id: "gemini-2.5-flash-lite",
-            name: "Gemini 2.5 Flash Lite (Vertex)",
-            api: "google-vertex",
-            provider: "google-vertex",
-            baseUrl: "https://{location}-aiplatform.googleapis.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.1,
-                output: 0.4,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
-        "gemini-2.5-flash-lite-preview-09-2025": {
-            id: "gemini-2.5-flash-lite-preview-09-2025",
-            name: "Gemini 2.5 Flash Lite Preview 09-25 (Vertex)",
+            name: "Gemini 2.5 Flash-Lite",
             api: "google-vertex",
             provider: "google-vertex",
             baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -5040,7 +4941,7 @@ export const MODELS = {
         },
         "gemini-2.5-pro": {
             id: "gemini-2.5-pro",
-            name: "Gemini 2.5 Pro (Vertex)",
+            name: "Gemini 2.5 Pro",
             api: "google-vertex",
             provider: "google-vertex",
             baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -5057,7 +4958,7 @@ export const MODELS = {
         },
         "gemini-3-flash-preview": {
             id: "gemini-3-flash-preview",
-            name: "Gemini 3 Flash Preview (Vertex)",
+            name: "Gemini 3 Flash Preview",
             api: "google-vertex",
             provider: "google-vertex",
             baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -5073,27 +4974,27 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "gemini-3-pro-preview": {
-            id: "gemini-3-pro-preview",
-            name: "Gemini 3 Pro Preview (Vertex)",
+        "gemini-3.1-flash-lite": {
+            id: "gemini-3.1-flash-lite",
+            name: "Gemini 3.1 Flash Lite",
             api: "google-vertex",
             provider: "google-vertex",
             baseUrl: "https://{location}-aiplatform.googleapis.com",
             reasoning: true,
-            thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": null, "high": "HIGH" },
+            thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 12,
-                cacheRead: 0.2,
+                input: 0.25,
+                output: 1.5,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 64000,
+            contextWindow: 1048576,
+            maxTokens: 65536,
         },
         "gemini-3.1-pro-preview": {
             id: "gemini-3.1-pro-preview",
-            name: "Gemini 3.1 Pro Preview (Vertex)",
+            name: "Gemini 3.1 Pro Preview",
             api: "google-vertex",
             provider: "google-vertex",
             baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -5111,7 +5012,7 @@ export const MODELS = {
         },
         "gemini-3.1-pro-preview-customtools": {
             id: "gemini-3.1-pro-preview-customtools",
-            name: "Gemini 3.1 Pro Preview Custom Tools (Vertex)",
+            name: "Gemini 3.1 Pro Preview Custom Tools",
             api: "google-vertex",
             provider: "google-vertex",
             baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -5127,6 +5028,60 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
+        "gemini-3.5-flash": {
+            id: "gemini-3.5-flash",
+            name: "Gemini 3.5 Flash",
+            api: "google-vertex",
+            provider: "google-vertex",
+            baseUrl: "https://{location}-aiplatform.googleapis.com",
+            reasoning: true,
+            thinkingLevelMap: { "off": null },
+            input: ["text", "image"],
+            cost: {
+                input: 1.5,
+                output: 9,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
+        "gemini-flash-latest": {
+            id: "gemini-flash-latest",
+            name: "Gemini Flash Latest",
+            api: "google-vertex",
+            provider: "google-vertex",
+            baseUrl: "https://{location}-aiplatform.googleapis.com",
+            reasoning: true,
+            thinkingLevelMap: { "off": null },
+            input: ["text", "image"],
+            cost: {
+                input: 1.5,
+                output: 9,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
+        "gemini-flash-lite-latest": {
+            id: "gemini-flash-lite-latest",
+            name: "Gemini Flash-Lite Latest",
+            api: "google-vertex",
+            provider: "google-vertex",
+            baseUrl: "https://{location}-aiplatform.googleapis.com",
+            reasoning: true,
+            thinkingLevelMap: { "off": null },
+            input: ["text", "image"],
+            cost: {
+                input: 0.25,
+                output: 1.5,
+                cacheRead: 0.025,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
     },
     "groq": {
         "llama-3.1-8b-instant": {
@@ -6457,6 +6412,7 @@ export const MODELS = {
             baseUrl: "https://api.moonshot.ai/v1",
             compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "thinkingFormat": "deepseek" },
             reasoning: true,
+            thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
                 input: 0.95,
@@ -6475,6 +6431,7 @@ export const MODELS = {
             baseUrl: "https://api.moonshot.ai/v1",
             compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "thinkingFormat": "deepseek" },
             reasoning: true,
+            thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
                 input: 1.9,
@@ -6621,6 +6578,7 @@ export const MODELS = {
             baseUrl: "https://api.moonshot.cn/v1",
             compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "thinkingFormat": "deepseek" },
             reasoning: true,
+            thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
                 input: 0.95,
@@ -6639,6 +6597,7 @@ export const MODELS = {
             baseUrl: "https://api.moonshot.cn/v1",
             compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "thinkingFormat": "deepseek" },
             reasoning: true,
+            thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
                 input: 1.9,
@@ -8012,7 +7971,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
-            compat: { "maxTokensField": "max_tokens", "supportsLongCacheRetention": false, "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            compat: { "maxTokensField": "max_tokens", "supportsLongCacheRetention": false, "requiresReasoningContentOnAssistantMessages": true },
             reasoning: true,
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
@@ -8031,7 +7990,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
-            compat: { "maxTokensField": "max_tokens", "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            compat: { "maxTokensField": "max_tokens", "requiresReasoningContentOnAssistantMessages": true },
             reasoning: true,
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
@@ -8050,7 +8009,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
-            compat: { "maxTokensField": "max_tokens", "supportsLongCacheRetention": false, "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            compat: { "maxTokensField": "max_tokens", "supportsLongCacheRetention": false, "requiresReasoningContentOnAssistantMessages": true },
             reasoning: true,
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
@@ -8660,9 +8619,9 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 384000,
         },
-        "glm-5": {
-            id: "glm-5",
-            name: "GLM-5",
+        "glm-5.1": {
+            id: "glm-5.1",
+            name: "GLM-5.1",
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
@@ -8670,17 +8629,17 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1,
-                output: 3.2,
-                cacheRead: 0.2,
+                input: 1.4,
+                output: 4.4,
+                cacheRead: 0.26,
                 cacheWrite: 0,
             },
             contextWindow: 202752,
             maxTokens: 32768,
         },
-        "glm-5.1": {
-            id: "glm-5.1",
-            name: "GLM-5.1",
+        "glm-5.2": {
+            id: "glm-5.2",
+            name: "GLM-5.2",
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
@@ -8693,8 +8652,8 @@ export const MODELS = {
                 cacheRead: 0.26,
                 cacheWrite: 0,
             },
-            contextWindow: 202752,
-            maxTokens: 32768,
+            contextWindow: 1000000,
+            maxTokens: 131072,
         },
         "kimi-k2.6": {
             id: "kimi-k2.6",
@@ -10005,8 +9964,8 @@ export const MODELS = {
                 cacheRead: 0.06,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 80000,
+            contextWindow: 262144,
+            maxTokens: 144000,
         },
         "meta-llama/llama-3.1-70b-instruct": {
             id: "meta-llama/llama-3.1-70b-instruct",
@@ -10210,7 +10169,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 512000,
+            maxTokens: 131072,
         },
         "mistralai/codestral-2508": {
             id: "mistralai/codestral-2508",
@@ -10546,7 +10505,7 @@ export const MODELS = {
             cost: {
                 input: 0.6,
                 output: 2.5,
-                cacheRead: 0,
+                cacheRead: 0.6,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -10925,7 +10884,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1047576,
-            maxTokens: 32768,
+            maxTokens: 4096,
         },
         "openai/gpt-4.1-nano": {
             id: "openai/gpt-4.1-nano",
@@ -10955,7 +10914,7 @@ export const MODELS = {
             cost: {
                 input: 2.5,
                 output: 10,
-                cacheRead: 0,
+                cacheRead: 1.25,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -11091,11 +11050,11 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 2,
-                cacheRead: 0.025,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
-            maxTokens: 128000,
+            maxTokens: 4096,
         },
         "openai/gpt-5-nano": {
             id: "openai/gpt-5-nano",
@@ -11159,11 +11118,11 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.13,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 32000,
+            maxTokens: 16384,
         },
         "openai/gpt-5.1-codex": {
             id: "openai/gpt-5.1-codex",
@@ -11250,7 +11209,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 16384,
+            maxTokens: 32000,
         },
         "openai/gpt-5.2-codex": {
             id: "openai/gpt-5.2-codex",
@@ -12365,7 +12324,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 65536,
         },
         "qwen/qwen3.5-27b": {
             id: "qwen/qwen3.5-27b",
@@ -12432,8 +12391,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 262144,
+            contextWindow: 256000,
+            maxTokens: 32768,
         },
         "qwen/qwen3.5-flash-02-23": {
             id: "qwen/qwen3.5-flash-02-23",
@@ -13045,7 +13004,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 262144,
+            maxTokens: 131072,
         },
         "~anthropic/claude-fable-latest": {
             id: "~anthropic/claude-fable-latest",
@@ -17022,8 +16981,9 @@ export const MODELS = {
             api: "openai-completions",
             provider: "zai",
             baseUrl: "https://api.z.ai/api/coding/paas/v4",
-            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
+            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "supportsReasoningEffort": true, "zaiToolStream": true },
             reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": "high", "medium": "high", "high": "high", "xhigh": "max" },
             input: ["text"],
             cost: {
                 input: 0,
@@ -17132,8 +17092,9 @@ export const MODELS = {
             api: "openai-completions",
             provider: "zai-coding-cn",
             baseUrl: "https://open.bigmodel.cn/api/coding/paas/v4",
-            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
+            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "supportsReasoningEffort": true, "zaiToolStream": true },
             reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": "high", "medium": "high", "high": "high", "xhigh": "max" },
             input: ["text"],
             cost: {
                 input: 0,