diff --git a/app/api/chat/route.ts b/app/api/chat/route.ts
index 8f987f34..ef79738a 100644
--- a/app/api/chat/route.ts
+++ b/app/api/chat/route.ts
@@ -13,6 +13,7 @@ import path from "path"
 import { z } from "zod"
 import { checkAccessCode } from "@/lib/access-code"
 import {
+    CACHE_POINT,
     getAIModel,
     SINGLE_SYSTEM_PROVIDERS,
     supportsPromptCaching,
@@ -25,6 +26,7 @@ import {
     replaceHistoricalToolInputs,
     validateFileParts,
 } from "@/lib/chat-helpers"
+import { withDeprecatedParamsFallback } from "@/lib/deprecated-params"
 import {
     checkAndIncrementRequest,
     isQuotaEnabled,
@@ -266,7 +268,6 @@ async function handleChatRequest(req: Request): Promise<Response> {
     const {
         model: baseModel,
         providerOptions,
-        headers,
         modelId,
         provider: resolvedProvider,
     } = getAIModel(clientOverrides)
@@ -289,8 +290,11 @@ async function handleChatRequest(req: Request): Promise<Response> {
         )
     }
 
-    // Retry with a smaller budget if the provider rejects the requested one
-    const model = withOutputTokenLimitFallback(baseModel)
+    // Retry once if the provider rejects the requested budget, or (newer
+    // Claude models) the sampling or thinking settings
+    const model = withOutputTokenLimitFallback(
+        withDeprecatedParamsFallback(baseModel),
+    )
 
     // The user setting can raise the budget only on their own key (desktop users
     // can still raise it themselves); on the server's keys it can only lower it
@@ -444,9 +448,7 @@ ${userInputText}
             if (enhancedMessages[i].role === "assistant") {
                 enhancedMessages[i] = {
                     ...enhancedMessages[i],
-                    providerOptions: {
-                        bedrock: { cachePoint: { type: "default" } },
-                    },
+                    providerOptions: CACHE_POINT,
                 }
                 break // Only cache the last assistant message
             }
@@ -499,21 +501,13 @@ IMPORTANT: The "Current diagram XML" is the SINGLE SOURCE OF TRUTH for what's on
               {
                   role: "system" as const,
                   content: finalSystemMessage,
-                  ...(shouldCache && {
-                      providerOptions: {
-                          bedrock: { cachePoint: { type: "default" } },
-                      },
-                  }),
+                  ...(shouldCache && { providerOptions: CACHE_POINT }),
               },
               // Cache breakpoint 2: Previous and Current diagram XML context
               {
                   role: "system" as const,
                   content: xmlContext,
-                  ...(shouldCache && {
-                      providerOptions: {
-                          bedrock: { cachePoint: { type: "default" } },
-                      },
-                  }),
+                  ...(shouldCache && { providerOptions: CACHE_POINT }),
               },
           ]
 
@@ -566,7 +560,6 @@ IMPORTANT: The "Current diagram XML" is the SINGLE SOURCE OF TRUTH for what's on
         },
         messages: allMessages,
         ...(providerOptions && { providerOptions }), // This now includes all reasoning configs
-        ...(headers && { headers }),
         // Langfuse telemetry config (returns undefined if not configured)
         ...(getTelemetryConfig({ sessionId: validSessionId, userId }) && {
             experimental_telemetry: getTelemetryConfig({
diff --git a/env.example b/env.example
index c8abbc9a..fb5850ce 100644
--- a/env.example
+++ b/env.example
@@ -44,7 +44,6 @@ AI_MODEL=global.anthropic.claude-sonnet-4-5-20250929-v1:0
 # Google Generative AI Configuration
 # GOOGLE_GENERATIVE_AI_API_KEY=...
 # GOOGLE_BASE_URL=https://generativelanguage.googleapis.com/v1beta  # Optional: Custom endpoint
-# GOOGLE_CANDIDATE_COUNT=1                   # Optional: Number of candidates to generate
 # GOOGLE_TOP_K=40                            # Optional: Top K sampling parameter
 # GOOGLE_TOP_P=0.95                          # Optional: Nucleus sampling parameter
 # Note: Gemini 2.5/3 models automatically enable reasoning display (includeThoughts: true)
diff --git a/lib/ai-providers.ts b/lib/ai-providers.ts
index e3ae5823..b3a60d27 100644
--- a/lib/ai-providers.ts
+++ b/lib/ai-providers.ts
@@ -9,6 +9,7 @@ import { createOpenAI, openai } from "@ai-sdk/openai"
 import { aihubmix, createAihubmix } from "@aihubmix/ai-sdk-provider"
 import { fromNodeProviderChain } from "@aws-sdk/credential-providers"
 import { createOpenRouter } from "@openrouter/ai-sdk-provider"
+import { defaultSettingsMiddleware, wrapLanguageModel } from "ai"
 import { createOllama, ollama } from "ollama-ai-provider-v2"
 import {
     adminProvidersToConfig,
@@ -23,7 +24,6 @@ export const AIHUBMIX_APP_CODE = "MSBS9675"
 interface ModelConfig {
     model: any
     providerOptions?: any
-    headers?: Record<string, string>
     modelId: string
     provider: ProviderName
 }
@@ -132,11 +132,6 @@ const BEDROCK_ANTHROPIC_BETA = {
     },
 }
 
-// Direct Anthropic API headers for beta features
-const ANTHROPIC_BETA_HEADERS = {
-    "anthropic-beta": "fine-grained-tool-streaming-2025-05-14",
-}
-
 /**
  * Resolve baseURL based on whether user is providing their own API key.
  * When user provides their own API key, we should NOT fall back to server's
@@ -241,6 +236,26 @@ function parseIntSafe(
     return parsed
 }
 
+/**
+ * GOOGLE_TOP_K and GOOGLE_TOP_P. They are call settings, so they go on the
+ * model through a middleware: as Google provider options they were dropped.
+ */
+function googleSamplingSettings(): { topK?: number; topP?: number } {
+    const settings: { topK?: number; topP?: number } = {}
+    const topK = parseIntSafe(process.env.GOOGLE_TOP_K, "GOOGLE_TOP_K", 1, 100)
+    if (topK) settings.topK = topK
+    if (process.env.GOOGLE_TOP_P) {
+        const topP = Number.parseFloat(process.env.GOOGLE_TOP_P)
+        if (Number.isNaN(topP) || topP < 0 || topP > 1) {
+            throw new Error(
+                `GOOGLE_TOP_P must be a number between 0 and 1, got: ${process.env.GOOGLE_TOP_P}`,
+            )
+        }
+        settings.topP = topP
+    }
+    return settings
+}
+
 /**
  * Build provider-specific options from environment variables
  * Supports various AI SDK providers with their unique configuration options
@@ -335,7 +350,6 @@ function buildProviderOptions(
         }
 
         case "google": {
-            const reasoningEffort = process.env.GOOGLE_REASONING_EFFORT
             const thinkingBudgetVal = parseIntSafe(
                 process.env.GOOGLE_THINKING_BUDGET,
                 "GOOGLE_THINKING_BUDGET",
@@ -374,47 +388,6 @@ function buildProviderOptions(
                 }
 
                 options.google = { thinkingConfig }
-            } else if (reasoningEffort) {
-                options.google = {
-                    reasoningEffort: reasoningEffort as
-                        | "low"
-                        | "medium"
-                        | "high",
-                }
-            }
-
-            // Keep existing Google options
-            const options_obj: Record<string, any> = {}
-            const candidateCount = parseIntSafe(
-                process.env.GOOGLE_CANDIDATE_COUNT,
-                "GOOGLE_CANDIDATE_COUNT",
-                1,
-                8,
-            )
-            if (candidateCount) {
-                options_obj.candidateCount = candidateCount
-            }
-            const topK = parseIntSafe(
-                process.env.GOOGLE_TOP_K,
-                "GOOGLE_TOP_K",
-                1,
-                100,
-            )
-            if (topK) {
-                options_obj.topK = topK
-            }
-            if (process.env.GOOGLE_TOP_P) {
-                const topP = Number.parseFloat(process.env.GOOGLE_TOP_P)
-                if (Number.isNaN(topP) || topP < 0 || topP > 1) {
-                    throw new Error(
-                        `GOOGLE_TOP_P must be a number between 0 and 1, got: ${process.env.GOOGLE_TOP_P}`,
-                    )
-                }
-                options_obj.topP = topP
-            }
-
-            if (Object.keys(options_obj).length > 0) {
-                options.google = { ...options.google, ...options_obj }
             }
             break
         }
@@ -818,7 +791,6 @@ export function getAIModel(overrides?: ClientOverrides): ModelConfig {
 
     let model: any
     let providerOptions: any
-    let headers: Record<string, string> | undefined
 
     // Build provider-specific options from environment variables
     const customProviderOptions = buildProviderOptions(provider, modelId)
@@ -922,14 +894,13 @@ export function getAIModel(overrides?: ClientOverrides): ModelConfig {
             const authToken = !apiKey
                 ? process.env.ANTHROPIC_AUTH_TOKEN
                 : undefined
+            // The provider streams tool input per tool (eager_input_streaming),
+            // which replaced the fine-grained-tool-streaming beta header
             const customProvider = createAnthropic({
                 ...(authToken ? { authToken } : { apiKey }),
                 baseURL,
-                headers: ANTHROPIC_BETA_HEADERS,
             })
             model = customProvider(modelId)
-            // Add beta headers for fine-grained tool streaming
-            headers = ANTHROPIC_BETA_HEADERS
             break
         }
 
@@ -958,6 +929,15 @@ export function getAIModel(overrides?: ClientOverrides): ModelConfig {
             } else {
                 model = google(modelId)
             }
+            const sampling = googleSamplingSettings()
+            if (Object.keys(sampling).length > 0) {
+                model = wrapLanguageModel({
+                    model,
+                    middleware: defaultSettingsMiddleware({
+                        settings: sampling,
+                    }),
+                })
+            }
             break
         }
         case "vertexai": {
@@ -1455,7 +1435,7 @@ export function getAIModel(overrides?: ClientOverrides): ModelConfig {
         providerOptions = customProviderOptions
     }
 
-    return { model, providerOptions, headers, modelId, provider }
+    return { model, providerOptions, modelId, provider }
 }
 
 /**
@@ -1489,11 +1469,20 @@ export function usesServerCredentials(
 }
 
 /**
- * Check if a model supports prompt caching.
- * Currently only Claude models on Bedrock support prompt caching.
+ * Prompt cache breakpoint for Claude, set on a message's providerOptions.
+ * Each provider reads only its own key; OpenRouter also reads the
+ * anthropic one.
+ */
+export const CACHE_POINT = {
+    bedrock: { cachePoint: { type: "default" } },
+    anthropic: { cacheControl: { type: "ephemeral" } },
+}
+
+/**
+ * Check if a model supports prompt caching: Claude models, on Bedrock,
+ * the Anthropic API or OpenRouter (see CACHE_POINT).
  */
 export function supportsPromptCaching(modelId: string): boolean {
-    // Bedrock prompt caching is supported for Claude models
     return (
         modelId.includes("claude") ||
         modelId.includes("anthropic") ||
diff --git a/lib/deprecated-params.ts b/lib/deprecated-params.ts
new file mode 100644
index 00000000..612338b2
--- /dev/null
+++ b/lib/deprecated-params.ts
@@ -0,0 +1,90 @@
+import { wrapLanguageModel } from "ai"
+import { rejectionText } from "@/lib/output-token-limit"
+
+type WrappedModel = ReturnType<typeof wrapLanguageModel>
+
+/**
+ * Claude 4.7 and later answer a non-default temperature, top_p or top_k,
+ * and the extended thinking budget (thinking type "enabled"), with a 400.
+ * TEMPERATURE and the *_THINKING_BUDGET_TOKENS settings send exactly these.
+ */
+const DEPRECATED_PARAM =
+    /`?(?:temperature|top_p|top_k)`? is deprecated for this model|"?thinking\.type\.enabled"? is not supported/i
+
+interface CallParams {
+    temperature?: number
+    topP?: number
+    topK?: number
+    providerOptions?: Record<string, Record<string, unknown> | undefined>
+}
+
+/** Drop a thinking config of type "enabled" stored under key, if any. */
+function withoutEnabledThinking(
+    options: Record<string, unknown> | undefined,
+    key: string,
+): Record<string, unknown> | undefined {
+    const config = options?.[key] as { type?: string } | undefined
+    if (config?.type !== "enabled") return options
+    const { [key]: _, ...rest } = options as Record<string, unknown>
+    return rest
+}
+
+/**
+ * The params without the settings newer Claude models reject, or null when
+ * the error is about something else or there is nothing to drop. The model
+ * then runs with its own default sampling and thinking.
+ */
+export function withoutDeprecatedParams<T extends CallParams>(
+    error: unknown,
+    params: T,
+): T | null {
+    const text = rejectionText(error)
+    if (!text || !DEPRECATED_PARAM.test(text)) return null
+
+    const { temperature, topP, topK, ...rest } = params
+    const options = params.providerOptions
+    const anthropic = withoutEnabledThinking(options?.anthropic, "thinking")
+    const bedrock = withoutEnabledThinking(options?.bedrock, "reasoningConfig")
+    const changed =
+        temperature !== undefined ||
+        topP !== undefined ||
+        topK !== undefined ||
+        anthropic !== options?.anthropic ||
+        bedrock !== options?.bedrock
+    if (!changed) return null
+
+    return {
+        ...rest,
+        ...(options && {
+            providerOptions: {
+                ...options,
+                ...(anthropic && { anthropic }),
+                ...(bedrock && { bedrock }),
+            },
+        }),
+    } as T
+}
+
+/** Retry the stream once without the settings newer Claude models reject. */
+export function withDeprecatedParamsFallback(
+    model: WrappedModel,
+): WrappedModel {
+    return wrapLanguageModel({
+        model,
+        middleware: {
+            specificationVersion: "v3",
+            async wrapStream({ doStream, params, model: inner }) {
+                try {
+                    return await doStream()
+                } catch (error) {
+                    const retry = withoutDeprecatedParams(error, params)
+                    if (!retry) throw error
+                    console.warn(
+                        "[model params] Rejected sampling or thinking settings, retrying with the model defaults",
+                    )
+                    return await inner.doStream(retry)
+                }
+            },
+        },
+    })
+}
diff --git a/lib/output-token-limit.ts b/lib/output-token-limit.ts
index 5aa1c4ed..28119eea 100644
--- a/lib/output-token-limit.ts
+++ b/lib/output-token-limit.ts
@@ -36,7 +36,7 @@ function usableLimit(value: number): number | null {
 }
 
 /** Message and body of an error that may be about the budget, or null. */
-function rejectionText(error: unknown): string | null {
+export function rejectionText(error: unknown): string | null {
     const err = error as {
         message?: unknown
         responseBody?: unknown
diff --git a/package-lock.json b/package-lock.json
index e2106634..33bbe267 100644
--- a/package-lock.json
+++ b/package-lock.json
@@ -9,16 +9,17 @@
             "version": "0.4.16",
             "license": "Apache-2.0",
             "dependencies": {
-                "@ai-sdk/amazon-bedrock": "^4.0.1",
-                "@ai-sdk/anthropic": "^3.0.0",
-                "@ai-sdk/azure": "^3.0.0",
-                "@ai-sdk/deepseek": "^2.0.0",
-                "@ai-sdk/gateway": "^3.0.0",
-                "@ai-sdk/google": "^3.0.0",
-                "@ai-sdk/google-vertex": "^4.0.16",
-                "@ai-sdk/openai": "^3.0.0",
-                "@ai-sdk/react": "^3.0.1",
-                "@aihubmix/ai-sdk-provider": "^2.1.0",
+                "@ai-sdk/amazon-bedrock": "^4.0.191",
+                "@ai-sdk/anthropic": "^3.0.127",
+                "@ai-sdk/azure": "^3.0.133",
+                "@ai-sdk/deepseek": "^2.0.71",
+                "@ai-sdk/gateway": "^3.0.209",
+                "@ai-sdk/google": "^3.0.130",
+                "@ai-sdk/google-vertex": "^4.0.210",
+                "@ai-sdk/openai": "^3.0.124",
+                "@ai-sdk/openai-compatible": "^2.0.81",
+                "@ai-sdk/react": "^3.0.303",
+                "@aihubmix/ai-sdk-provider": "^2.2.1",
                 "@aws-sdk/client-dynamodb": "^3.957.0",
                 "@aws-sdk/credential-providers": "^3.943.0",
                 "@extractus/article-extractor": "^8.0.18",
@@ -28,7 +29,7 @@
                 "@langfuse/tracing": "^4.4.9",
                 "@next/third-parties": "^16.0.6",
                 "@opennextjs/cloudflare": "^1.17.1",
-                "@openrouter/ai-sdk-provider": "^2.0.0",
+                "@openrouter/ai-sdk-provider": "^2.10.0",
                 "@opentelemetry/api": "^1.9.0",
                 "@opentelemetry/exporter-trace-otlp-http": "^0.222.0",
                 "@opentelemetry/sdk-trace-node": "^2.2.0",
@@ -44,7 +45,7 @@
                 "@radix-ui/react-tooltip": "^1.1.8",
                 "@radix-ui/react-use-controllable-state": "^1.2.2",
                 "@xmldom/xmldom": "^0.9.8",
-                "ai": "^6.0.1",
+                "ai": "^6.0.300",
                 "base-64": "^1.0.0",
                 "class-variance-authority": "^0.7.1",
                 "clsx": "^2.1.1",
@@ -56,7 +57,7 @@
                 "nanoid": "^5.0.0",
                 "negotiator": "^1.0.0",
                 "next": "^16.0.7",
-                "ollama-ai-provider-v2": "^3.0.0",
+                "ollama-ai-provider-v2": "^3.6.0",
                 "pako": "^2.1.0",
                 "prism-react-renderer": "^2.4.1",
                 "react": "^19.1.2",
@@ -124,15 +125,15 @@
             "license": "MIT"
         },
         "node_modules/@ai-sdk/amazon-bedrock": {
-            "version": "4.0.113",
-            "resolved": "https://registry.npmjs.org/@ai-sdk/amazon-bedrock/-/amazon-bedrock-4.0.113.tgz",
-            "integrity": "sha512-qoeF2ghkYqHY4u68rasZopYsRuGnRwgqSfe6rhC/jM6W73Z7TU5v9QcfDYKt9dgp19YHY9EqiX3SXVC+uPGkRQ==",
+            "version": "4.0.191",
+            "resolved": "https://registry.npmjs.org/@ai-sdk/amazon-bedrock/-/amazon-bedrock-4.0.191.tgz",
+            "integrity": "sha512-7wgtq8On8oqmofGIGtYl8EOEbawnfiPbIbWpu2ksGNF065J8mbpE6DhkHNv0dpPbvnn4txL4sflUwUPwHw7/SQ==",
             "license": "Apache-2.0",
             "dependencies": {
-                "@ai-sdk/anthropic": "3.0.81",
-                "@ai-sdk/openai": "3.0.68",
-                "@ai-sdk/provider": "3.0.10",
-                "@ai-sdk/provider-utils": "4.0.27",
+                "@ai-sdk/anthropic": "3.0.127",
+                "@ai-sdk/openai": "3.0.124",
+                "@ai-sdk/provider": "3.0.18",
+                "@ai-sdk/provider-utils": "4.0.57",
                 "@smithy/eventstream-codec": "^4.0.1",
                 "@smithy/util-utf8": "^4.0.0",
                 "aws4fetch": "^1.0.20"
@@ -144,75 +145,14 @@
                 "zod": "^3.25.76 || ^4.1.8"
             }
         },
-        "node_modules/@ai-sdk/amazon-bedrock/node_modules/@ai-sdk/anthropic": {
-            "version": "3.0.81",
-            "resolved": "https://registry.npmjs.org/@ai-sdk/anthropic/-/anthropic-3.0.81.tgz",
-            "integrity": "sha512-B1JDd9Ugq9R5AgIaW3674lhGCMMYJcPUxnrZh8fzbGojgg4QvHFRv6eZahGQAUsmGHbcf74G9bdSBDLWQGY2GA==",
-            "license": "Apache-2.0",
-            "dependencies": {
-                "@ai-sdk/provider": "3.0.10",
-                "@ai-sdk/provider-utils": "4.0.27"
-            },
-            "engines": {
-                "node": ">=18"
-            },
-            "peerDependencies": {
-                "zod": "^3.25.76 || ^4.1.8"
-            }
-        },
-        "node_modules/@ai-sdk/amazon-bedrock/node_modules/@ai-sdk/openai": {
-            "version": "3.0.68",
-            "resolved": "https://registry.npmjs.org/@ai-sdk/openai/-/openai-3.0.68.tgz",
-            "integrity": "sha512-FCs/DPr4M95UyZ/ABHJmTmCEYRCka/4J0Bna0nsd78QCdGIS0X/zhn+fVzB7mZJo7464uOWYUjROx9PGNGOb0w==",
-            "license": "Apache-2.0",
-            "dependencies": {
-                "@ai-sdk/provider": "3.0.10",
-                "@ai-sdk/provider-utils": "4.0.27"
-            },
-            "engines": {
-                "node": ">=18"
-            },
-            "peerDependencies": {
-                "zod": "^3.25.76 || ^4.1.8"
-            }
-        },
-        "node_modules/@ai-sdk/amazon-bedrock/node_modules/@ai-sdk/provider": {
-            "version": "3.0.10",
-            "resolved": "https://registry.npmjs.org/@ai-sdk/provider/-/provider-3.0.10.tgz",
-            "integrity": "sha512-Q3BZ27qfpYqnCYGvE3vt+Qi6LGOF9R5Nmzn+9JoM1lCRsD9mYaIhfJLkSunN48nfGXJ6n+XNV0J/XVpqGQl7Dw==",
-            "license": "Apache-2.0",
-            "dependencies": {
-                "json-schema": "^0.4.0"
-            },
-            "engines": {
-                "node": ">=18"
-            }
-        },
-        "node_modules/@ai-sdk/amazon-bedrock/node_modules/@ai-sdk/provider-utils": {
-            "version": "4.0.27",
-            "resolved": "https://registry.npmjs.org/@ai-sdk/provider-utils/-/provider-utils-4.0.27.tgz",
-            "integrity": "sha512-ubkAJ+xODouwtmN1tYlvTPphH1hPOBfZaEQe8U7skGvFAnIRs9PPpsq57bC2+Ky/MB4yzhd6YOsxTAx9sGpazw==",
-            "license": "Apache-2.0",
-            "dependencies": {
-                "@ai-sdk/provider": "3.0.10",
-                "@standard-schema/spec": "^1.1.0",
-                "eventsource-parser": "^3.0.8"
-            },
-            "engines": {
-                "node": ">=18"
-            },
-            "peerDependencies": {
-                "zod": "^3.25.76 || ^4.1.8"
-            }
-        },
         "node_modules/@ai-sdk/anthropic": {
-            "version": "3.0.47",
-            "resolved": "https://registry.npmjs.org/@ai-sdk/anthropic/-/anthropic-3.0.47.tgz",
-            "integrity": "sha512-E6Z3i/xvxGDxRskMMbuX9+xDK4l5LesrP2O7YQ0CcbAkYP25qTo/kYGf/AsJrLkNIY23HeO/kheUWtG1XZllDA==",
+            "version": "3.0.127",
+            "resolved": "https://registry.npmjs.org/@ai-sdk/anthropic/-/anthropic-3.0.127.tgz",
+            "integrity": "sha512-Inff1DmPRVWi6QGr9YL2wiA4maILZuve9I8id/O4keQEoq6fJv6EfvkrSFw/nNvm2jiTcIUfDrpczeHTuhl9mg==",
             "license": "Apache-2.0",
             "dependencies": {
-                "@ai-sdk/provider": "3.0.8",
-                "@ai-sdk/provider-utils": "4.0.15"
+                "@ai-sdk/provider": "3.0.18",
+                "@ai-sdk/provider-utils": "4.0.57"
             },
             "engines": {
                 "node": ">=18"
@@ -222,14 +162,15 @@
             }
         },
         "node_modules/@ai-sdk/azure": {
-            "version": "3.0.34",
-            "resolved": "https://registry.npmjs.org/@ai-sdk/azure/-/azure-3.0.34.tgz",
-            "integrity": "sha512-nnOFtgvZYOa6XIeAm18i56NX77Yu4Bd+Tnbt85LGUEqwJFR54kFTlR1nm3BAJCphHrmQteJd1P3QErtyoXig8A==",
+            "version": "3.0.133",
+            "resolved": "https://registry.npmjs.org/@ai-sdk/azure/-/azure-3.0.133.tgz",
+            "integrity": "sha512-iVCT1q6bRPWjzisu7Xy1bc1yWtegd3WSZzmi4+jkiFTKTxir703F5jH8mWPG0hPnqW/OjdkOrSzcQ063j7T/ng==",
             "license": "Apache-2.0",
             "dependencies": {
-                "@ai-sdk/openai": "3.0.33",
-                "@ai-sdk/provider": "3.0.8",
-                "@ai-sdk/provider-utils": "4.0.15"
+                "@ai-sdk/deepseek": "2.0.71",
+                "@ai-sdk/openai": "3.0.124",
+                "@ai-sdk/provider": "3.0.18",
+                "@ai-sdk/provider-utils": "4.0.57"
             },
             "engines": {
                 "node": ">=18"
@@ -239,13 +180,13 @@
             }
         },
         "node_modules/@ai-sdk/deepseek": {
-            "version": "2.0.20",
-            "resolved": "https://registry.npmjs.org/@ai-sdk/deepseek/-/deepseek-2.0.20.tgz",
-            "integrity": "sha512-MAL04sDTOWUiBjAGWaVgyeE4bYRb9QpKYRlIeCTZFga6I8yQs50XakhWEssrmvVihdpHGkqpDtCHsFqCydsWLA==",
+            "version": "2.0.71",
+            "resolved": "https://registry.npmjs.org/@ai-sdk/deepseek/-/deepseek-2.0.71.tgz",
+            "integrity": "sha512-2uLtZBgONfzEP7tZOg23sBzi33n1/gcW1zLNNw96/PLt9vdqDYIkGQnKRd6F+/0Wwy77jVulU+gzpiudk3f0UQ==",
             "license": "Apache-2.0",
             "dependencies": {
-                "@ai-sdk/provider": "3.0.8",
-                "@ai-sdk/provider-utils": "4.0.15"
+                "@ai-sdk/provider": "3.0.18",
+                "@ai-sdk/provider-utils": "4.0.57"
             },
             "engines": {
                 "node": ">=18"
@@ -255,14 +196,14 @@
             }
         },
         "node_modules/@ai-sdk/gateway": {
-            "version": "3.0.55",
-            "resolved": "https://registry.npmjs.org/@ai-sdk/gateway/-/gateway-3.0.55.tgz",
-            "integrity": "sha512-7xMeTJnCjwRwXKVCiv4Ly4qzWvDuW3+W1WIV0X1EFu6W83d4mEhV9bFArto10MeTw40ewuDjrbrZd21mXKohkw==",
+            "version": "3.0.209",
+            "resolved": "https://registry.npmjs.org/@ai-sdk/gateway/-/gateway-3.0.209.tgz",
+            "integrity": "sha512-CjCBzC35lRZ0LnUYLDfTB92p0Fr1Fu9Wrivc+LI0u3ox/DyZ0wPOHjt8DKBKHD/R4aZ86+JCFFuD9f8MFjAQFg==",
             "license": "Apache-2.0",
             "dependencies": {
-                "@ai-sdk/provider": "3.0.8",
-                "@ai-sdk/provider-utils": "4.0.15",
-                "@vercel/oidc": "3.1.0"
+                "@ai-sdk/provider": "3.0.18",
+                "@ai-sdk/provider-utils": "4.0.57",
+                "@vercel/oidc": "3.2.0"
             },
             "engines": {
                 "node": ">=18"
@@ -272,13 +213,13 @@
             }
         },
         "node_modules/@ai-sdk/google": {
-            "version": "3.0.31",
-            "resolved": "https://registry.npmjs.org/@ai-sdk/google/-/google-3.0.31.tgz",
-            "integrity": "sha512-RVNz8WFSIRbXbYDBE6JvlE2escWPJimBCs22LzKEYH7DNfl/X7cHNa1LFho4PsY6Ib0JmbzB8s2+i0wHs/wNCg==",
+            "version": "3.0.130",
+            "resolved": "https://registry.npmjs.org/@ai-sdk/google/-/google-3.0.130.tgz",
+            "integrity": "sha512-DOhGfFT667LbopxMZU7kIiT4K8F2RNN8ziwmOxAfMbp3xTvAaxQ4ynPKNWBVXcCkGYDmzPb7QiazN1IRX8y3lw==",
             "license": "Apache-2.0",
             "dependencies": {
-                "@ai-sdk/provider": "3.0.8",
-                "@ai-sdk/provider-utils": "4.0.15"
+                "@ai-sdk/provider": "3.0.18",
+                "@ai-sdk/provider-utils": "4.0.57"
             },
             "engines": {
                 "node": ">=18"
@@ -288,15 +229,16 @@
             }
         },
         "node_modules/@ai-sdk/google-vertex": {
-            "version": "4.0.63",
-            "resolved": "https://registry.npmjs.org/@ai-sdk/google-vertex/-/google-vertex-4.0.63.tgz",
-            "integrity": "sha512-/RNi6KSB4162DDYeXHUKQc5jLPmiJMkhTswLwbfPUEPyyFjbxpBWgeAk/vS/u8jxT4IPyYQ8cD/uyvJibmtmww==",
+            "version": "4.0.210",
+            "resolved": "https://registry.npmjs.org/@ai-sdk/google-vertex/-/google-vertex-4.0.210.tgz",
+            "integrity": "sha512-7Jj41iWsTFUcv6pzji5AlW2QaMJt/PEMU/zwqji2H7U52WvZE345kyo+nKRJMFtHgSVqFmzmMUIM9gyeaXKRtw==",
             "license": "Apache-2.0",
             "dependencies": {
-                "@ai-sdk/anthropic": "3.0.47",
-                "@ai-sdk/google": "3.0.31",
-                "@ai-sdk/provider": "3.0.8",
-                "@ai-sdk/provider-utils": "4.0.15",
+                "@ai-sdk/anthropic": "3.0.127",
+                "@ai-sdk/google": "3.0.130",
+                "@ai-sdk/openai-compatible": "2.0.81",
+                "@ai-sdk/provider": "3.0.18",
+                "@ai-sdk/provider-utils": "4.0.57",
                 "google-auth-library": "^10.5.0"
             },
             "engines": {
@@ -307,13 +249,13 @@
             }
         },
         "node_modules/@ai-sdk/openai": {
-            "version": "3.0.33",
-            "resolved": "https://registry.npmjs.org/@ai-sdk/openai/-/openai-3.0.33.tgz",
-            "integrity": "sha512-O/8SVKAiwFHkGAUfBnrLb7L2IjbpP9ySWbmOktOfa0KtzutZkmKNrJ5CtB5dj+lwuENbOuZeRsnsZdOjar7hig==",
+            "version": "3.0.124",
+            "resolved": "https://registry.npmjs.org/@ai-sdk/openai/-/openai-3.0.124.tgz",
+            "integrity": "sha512-7DpRUPXzJ+S6XasEJBojzFCs04J3rNPs0FZFF3PEeix49IggZAwsMrqscUwB/+05+87r01SS/jeopQGOOL4AEQ==",
             "license": "Apache-2.0",
             "dependencies": {
-                "@ai-sdk/provider": "3.0.8",
-                "@ai-sdk/provider-utils": "4.0.15"
+                "@ai-sdk/provider": "3.0.18",
+                "@ai-sdk/provider-utils": "4.0.57"
             },
             "engines": {
                 "node": ">=18"
@@ -323,42 +265,13 @@
             }
         },
         "node_modules/@ai-sdk/openai-compatible": {
-            "version": "2.0.48",
-            "resolved": "https://registry.npmjs.org/@ai-sdk/openai-compatible/-/openai-compatible-2.0.48.tgz",
-            "integrity": "sha512-z9MC6M4Oh/yUY/F/eszOtO8wc2nMz99XmZQKd2gWTtyIfe716xTfrKe3aYZKg20NZDtyjqPPKPSR+wqz7q1T7Q==",
+            "version": "2.0.81",
+            "resolved": "https://registry.npmjs.org/@ai-sdk/openai-compatible/-/openai-compatible-2.0.81.tgz",
+            "integrity": "sha512-L14Jd0lAFKNM42l9TxlpwkNiyMlSvSvGySLc9GN4FB0qOo4/WmYOeLyn/CPhghIr0K4O6vH1y0nChxGljq2ccg==",
             "license": "Apache-2.0",
             "dependencies": {
-                "@ai-sdk/provider": "3.0.10",
-                "@ai-sdk/provider-utils": "4.0.27"
-            },
-            "engines": {
-                "node": ">=18"
-            },
-            "peerDependencies": {
-                "zod": "^3.25.76 || ^4.1.8"
-            }
-        },
-        "node_modules/@ai-sdk/openai-compatible/node_modules/@ai-sdk/provider": {
-            "version": "3.0.10",
-            "resolved": "https://registry.npmjs.org/@ai-sdk/provider/-/provider-3.0.10.tgz",
-            "integrity": "sha512-Q3BZ27qfpYqnCYGvE3vt+Qi6LGOF9R5Nmzn+9JoM1lCRsD9mYaIhfJLkSunN48nfGXJ6n+XNV0J/XVpqGQl7Dw==",
-            "license": "Apache-2.0",
-            "dependencies": {
-                "json-schema": "^0.4.0"
-            },
-            "engines": {
-                "node": ">=18"
-            }
-        },
-        "node_modules/@ai-sdk/openai-compatible/node_modules/@ai-sdk/provider-utils": {
-            "version": "4.0.27",
-            "resolved": "https://registry.npmjs.org/@ai-sdk/provider-utils/-/provider-utils-4.0.27.tgz",
-            "integrity": "sha512-ubkAJ+xODouwtmN1tYlvTPphH1hPOBfZaEQe8U7skGvFAnIRs9PPpsq57bC2+Ky/MB4yzhd6YOsxTAx9sGpazw==",
-            "license": "Apache-2.0",
-            "dependencies": {
-                "@ai-sdk/provider": "3.0.10",
-                "@standard-schema/spec": "^1.1.0",
-                "eventsource-parser": "^3.0.8"
+                "@ai-sdk/provider": "3.0.18",
+                "@ai-sdk/provider-utils": "4.0.57"
             },
             "engines": {
                 "node": ">=18"
@@ -368,9 +281,9 @@
             }
         },
         "node_modules/@ai-sdk/provider": {
-            "version": "3.0.8",
-            "resolved": "https://registry.npmjs.org/@ai-sdk/provider/-/provider-3.0.8.tgz",
-            "integrity": "sha512-oGMAgGoQdBXbZqNG0Ze56CHjDZ1IDYOwGYxYjO5KLSlz5HiNQ9udIXsPZ61VWaHGZ5XW/jyjmr6t2xz2jGVwbQ==",
+            "version": "3.0.18",
+            "resolved": "https://registry.npmjs.org/@ai-sdk/provider/-/provider-3.0.18.tgz",
+            "integrity": "sha512-IpefF5ssZVOZCD4Wu7zxt6PwZoGT2HLVjxpJ10Bjx6EAmRfLYJPjyrfxb0RYDlwvXnDb9nkQ7Do/oJVDuRFzew==",
             "license": "Apache-2.0",
             "dependencies": {
                 "json-schema": "^0.4.0"
@@ -380,30 +293,40 @@
             }
         },
         "node_modules/@ai-sdk/provider-utils": {
-            "version": "4.0.15",
-            "resolved": "https://registry.npmjs.org/@ai-sdk/provider-utils/-/provider-utils-4.0.15.tgz",
-            "integrity": "sha512-8XiKWbemmCbvNN0CLR9u3PQiet4gtEVIrX4zzLxnCj06AwsEDJwJVBbKrEI4t6qE8XRSIvU2irka0dcpziKW6w==",
+            "version": "4.0.57",
+            "resolved": "https://registry.npmjs.org/@ai-sdk/provider-utils/-/provider-utils-4.0.57.tgz",
+            "integrity": "sha512-89a7sPvZqXsP3PigcAQLWntu/duIVEcN/RyChAB+j6p3C7NwW767sVttvL8r0+BetTg63uAXQoYHCZZueQKBSw==",
             "license": "Apache-2.0",
             "dependencies": {
-                "@ai-sdk/provider": "3.0.8",
+                "@ai-sdk/provider": "3.0.18",
                 "@standard-schema/spec": "^1.1.0",
-                "eventsource-parser": "^3.0.6"
+                "eventsource-parser": "^3.0.8",
+                "undici": "^6.28.0"
             },
             "engines": {
-                "node": ">=18"
+                "node": ">=18.17"
             },
             "peerDependencies": {
                 "zod": "^3.25.76 || ^4.1.8"
             }
         },
+        "node_modules/@ai-sdk/provider-utils/node_modules/undici": {
+            "version": "6.29.0",
+            "resolved": "https://registry.npmjs.org/undici/-/undici-6.29.0.tgz",
+            "integrity": "sha512-R+RODBqp6i2pPflGdq+xIOUkl+RNfGgHwoinecKu/JCuf2uO06cOKoDbI2P7Dn6KcswdKwrczbU6IYJ6K8X+wg==",
+            "license": "MIT",
+            "engines": {
+                "node": ">=18.17"
+            }
+        },
         "node_modules/@ai-sdk/react": {
-            "version": "3.0.102",
-            "resolved": "https://registry.npmjs.org/@ai-sdk/react/-/react-3.0.102.tgz",
-            "integrity": "sha512-WPSYJxk/HM3SWhhxE+WrLhIMbaRLpDHWWYzUlrptXowwEoyliYBYZAkzip/gV8hybT2NyrWnsUh5KRO5iBdsQA==",
+            "version": "3.0.303",
+            "resolved": "https://registry.npmjs.org/@ai-sdk/react/-/react-3.0.303.tgz",
+            "integrity": "sha512-PeTBn25x8QxfIIpdUDOpWHfiIZxMRJCw04PhWNHI9hl+gtu+zGwAxWU+sy3PH/f/oEBBAp7eDDUDDjiuqwcw6g==",
             "license": "Apache-2.0",
             "dependencies": {
-                "@ai-sdk/provider-utils": "4.0.15",
-                "ai": "6.0.100",
+                "@ai-sdk/provider-utils": "4.0.57",
+                "ai": "6.0.300",
                 "swr": "^2.2.5",
                 "throttleit": "2.1.0"
             },
@@ -415,9 +338,9 @@
             }
         },
         "node_modules/@aihubmix/ai-sdk-provider": {
-            "version": "2.1.0",
-            "resolved": "https://registry.npmjs.org/@aihubmix/ai-sdk-provider/-/ai-sdk-provider-2.1.0.tgz",
-            "integrity": "sha512-AqK10PV5B4zWFBav5PRUhrWGYTHjC0s6cIbd4v9hBo6D9SqKv5o41B+dkl6IeIPrnZrMGLEE9Mn5R+VaEkhbdg==",
+            "version": "2.2.1",
+            "resolved": "https://registry.npmjs.org/@aihubmix/ai-sdk-provider/-/ai-sdk-provider-2.2.1.tgz",
+            "integrity": "sha512-VUkSYFbrigs5ZF44LRSHEI/q1fZyLkExWvrgBG4w0ysGEE/XXt7fi9NgMG9UH1PQVBgnc/PP03CUhTM1nhmGxQ==",
             "license": "Apache-2.0",
             "dependencies": {
                 "@ai-sdk/anthropic": "^3.0.0",
@@ -5891,9 +5814,9 @@
             }
         },
         "node_modules/@openrouter/ai-sdk-provider": {
-            "version": "2.8.1",
-            "resolved": "https://registry.npmjs.org/@openrouter/ai-sdk-provider/-/ai-sdk-provider-2.8.1.tgz",
-            "integrity": "sha512-Y6j3yivgoEUf/kutD/k5GX/mzZfioRFoSx0gbQ+mIOzMaH/vJv1rCkztiuvlLw5xRYQil7oxHUZvmSfXqOx1NQ==",
+            "version": "2.10.0",
+            "resolved": "https://registry.npmjs.org/@openrouter/ai-sdk-provider/-/ai-sdk-provider-2.10.0.tgz",
+            "integrity": "sha512-FMsAEjLUt5pWuRE2LDC/LCvVrFjLlrEzUITH5+5SZtfq7KZ2wrOHjQVxzz92sju8S9ltpzW87CLW8/b0oBXVCw==",
             "license": "Apache-2.0",
             "engines": {
                 "node": ">=18"
@@ -9327,9 +9250,9 @@
             ]
         },
         "node_modules/@vercel/oidc": {
-            "version": "3.1.0",
-            "resolved": "https://registry.npmjs.org/@vercel/oidc/-/oidc-3.1.0.tgz",
-            "integrity": "sha512-Fw28YZpRnA3cAHHDlkt7xQHiJ0fcL+NRcIqsocZQUSmbzeIKRpwttJjik5ZGanXP+vlA4SbTg+AbA3bP363l+w==",
+            "version": "3.2.0",
+            "resolved": "https://registry.npmjs.org/@vercel/oidc/-/oidc-3.2.0.tgz",
+            "integrity": "sha512-UycprH3T6n3jH0k44NHMa7pnFHGu/N05MjojYr+Mc6I7obkoLIJujSWwin1pCvdy/eOxrI/l3uDLQsmcrOb4ug==",
             "license": "Apache-2.0",
             "engines": {
                 "node": ">= 20"
@@ -9595,15 +9518,15 @@
             }
         },
         "node_modules/ai": {
-            "version": "6.0.100",
-            "resolved": "https://registry.npmjs.org/ai/-/ai-6.0.100.tgz",
-            "integrity": "sha512-BIxhG7M7wvcWCF+IEnZi7WpkRLOM3jR2vJ0mMuohl2UB2i1R/ZUa1cHFel1xI8nWvyUpOoQXKqsM0BAH50EYSQ==",
+            "version": "6.0.300",
+            "resolved": "https://registry.npmjs.org/ai/-/ai-6.0.300.tgz",
+            "integrity": "sha512-ZBT30eQTy6exP+EWJJxm3DMb34m9td8STy+hfnvKdjhyEQoM8vQN5YfFLTRVVTCONHoM+y5K+Tudb6PTFrpikA==",
             "license": "Apache-2.0",
             "dependencies": {
-                "@ai-sdk/gateway": "3.0.55",
-                "@ai-sdk/provider": "3.0.8",
-                "@ai-sdk/provider-utils": "4.0.15",
-                "@opentelemetry/api": "1.9.0"
+                "@ai-sdk/gateway": "3.0.209",
+                "@ai-sdk/provider": "3.0.18",
+                "@ai-sdk/provider-utils": "4.0.57",
+                "@opentelemetry/api": "^1.9.0"
             },
             "engines": {
                 "node": ">=18"
@@ -9612,15 +9535,6 @@
                 "zod": "^3.25.76 || ^4.1.8"
             }
         },
-        "node_modules/ai/node_modules/@opentelemetry/api": {
-            "version": "1.9.0",
-            "resolved": "https://registry.npmjs.org/@opentelemetry/api/-/api-1.9.0.tgz",
-            "integrity": "sha512-3giAOQvZiH5F9bMlMiv8+GSPMeqg0dbaeo58/0SlA9sxSqZhnUtxzX9/2FzyhS9sWQf5S0GJE0AKBrFqjpeYcg==",
-            "license": "Apache-2.0",
-            "engines": {
-                "node": ">=8.0.0"
-            }
-        },
         "node_modules/ajv": {
             "version": "6.14.0",
             "resolved": "https://registry.npmjs.org/ajv/-/ajv-6.14.0.tgz",
@@ -19590,39 +19504,26 @@
             "license": "MIT"
         },
         "node_modules/ollama-ai-provider-v2": {
-            "version": "3.5.0",
-            "resolved": "https://registry.npmjs.org/ollama-ai-provider-v2/-/ollama-ai-provider-v2-3.5.0.tgz",
-            "integrity": "sha512-+s/aYIYa91z2Vk3AkGAz3BaPAQ0flS2eFZD3BN2mD/N6W6YQbcookyu6pc2cbc8SP5VGpNB857WJ0eHDjKXsXw==",
+            "version": "3.6.0",
+            "resolved": "https://registry.npmjs.org/ollama-ai-provider-v2/-/ollama-ai-provider-v2-3.6.0.tgz",
+            "integrity": "sha512-1Om3FVJYhBwkAr5kQ+BX1s/tdVdtVdoFQWrX4PBQHDHPISyGt24CjhtggEjUYpy5ait0YeVfZwEpIYjgD8Ih7Q==",
             "license": "Apache-2.0",
             "dependencies": {
-                "@ai-sdk/provider": "^3.0.8",
-                "@ai-sdk/provider-utils": "^4.0.19"
+                "@ai-sdk/provider": "^3.0.10",
+                "@ai-sdk/provider-utils": "^4.0.27"
             },
             "engines": {
-                "node": ">=18"
+                "node": ">=20"
+            },
+            "funding": {
+                "type": "Buy Me a Coffee",
+                "url": "https://buymeacoffee.com/nordwestt"
             },
             "peerDependencies": {
                 "ai": "^5.0.0 || ^6.0.0",
                 "zod": "^4.0.16"
             }
         },
-        "node_modules/ollama-ai-provider-v2/node_modules/@ai-sdk/provider-utils": {
-            "version": "4.0.23",
-            "resolved": "https://registry.npmjs.org/@ai-sdk/provider-utils/-/provider-utils-4.0.23.tgz",
-            "integrity": "sha512-z8GlDaCmRSDlqkMF2f4/RFgWxdarvIbyuk+m6WXT1LYgsnGiXRJGTD2Z1+SDl3LqtFuRtGX1aghYvQLoHL/9pg==",
-            "license": "Apache-2.0",
-            "dependencies": {
-                "@ai-sdk/provider": "3.0.8",
-                "@standard-schema/spec": "^1.1.0",
-                "eventsource-parser": "^3.0.6"
-            },
-            "engines": {
-                "node": ">=18"
-            },
-            "peerDependencies": {
-                "zod": "^3.25.76 || ^4.1.8"
-            }
-        },
         "node_modules/on-finished": {
             "version": "2.4.1",
             "resolved": "https://registry.npmjs.org/on-finished/-/on-finished-2.4.1.tgz",
diff --git a/package.json b/package.json
index 205055ab..15da0185 100644
--- a/package.json
+++ b/package.json
@@ -31,16 +31,17 @@
         "test:e2e": "playwright test"
     },
     "dependencies": {
-        "@ai-sdk/amazon-bedrock": "^4.0.1",
-        "@ai-sdk/anthropic": "^3.0.0",
-        "@ai-sdk/azure": "^3.0.0",
-        "@ai-sdk/deepseek": "^2.0.0",
-        "@ai-sdk/gateway": "^3.0.0",
-        "@ai-sdk/google": "^3.0.0",
-        "@ai-sdk/google-vertex": "^4.0.16",
-        "@ai-sdk/openai": "^3.0.0",
-        "@ai-sdk/react": "^3.0.1",
-        "@aihubmix/ai-sdk-provider": "^2.1.0",
+        "@ai-sdk/amazon-bedrock": "^4.0.191",
+        "@ai-sdk/anthropic": "^3.0.127",
+        "@ai-sdk/azure": "^3.0.133",
+        "@ai-sdk/deepseek": "^2.0.71",
+        "@ai-sdk/gateway": "^3.0.209",
+        "@ai-sdk/google": "^3.0.130",
+        "@ai-sdk/google-vertex": "^4.0.210",
+        "@ai-sdk/openai": "^3.0.124",
+        "@ai-sdk/openai-compatible": "^2.0.81",
+        "@ai-sdk/react": "^3.0.303",
+        "@aihubmix/ai-sdk-provider": "^2.2.1",
         "@aws-sdk/client-dynamodb": "^3.957.0",
         "@aws-sdk/credential-providers": "^3.943.0",
         "@extractus/article-extractor": "^8.0.18",
@@ -50,7 +51,7 @@
         "@langfuse/tracing": "^4.4.9",
         "@next/third-parties": "^16.0.6",
         "@opennextjs/cloudflare": "^1.17.1",
-        "@openrouter/ai-sdk-provider": "^2.0.0",
+        "@openrouter/ai-sdk-provider": "^2.10.0",
         "@opentelemetry/api": "^1.9.0",
         "@opentelemetry/exporter-trace-otlp-http": "^0.222.0",
         "@opentelemetry/sdk-trace-node": "^2.2.0",
@@ -66,7 +67,7 @@
         "@radix-ui/react-tooltip": "^1.1.8",
         "@radix-ui/react-use-controllable-state": "^1.2.2",
         "@xmldom/xmldom": "^0.9.8",
-        "ai": "^6.0.1",
+        "ai": "^6.0.300",
         "base-64": "^1.0.0",
         "class-variance-authority": "^0.7.1",
         "clsx": "^2.1.1",
@@ -78,7 +79,7 @@
         "nanoid": "^5.0.0",
         "negotiator": "^1.0.0",
         "next": "^16.0.7",
-        "ollama-ai-provider-v2": "^3.0.0",
+        "ollama-ai-provider-v2": "^3.6.0",
         "pako": "^2.1.0",
         "prism-react-renderer": "^2.4.1",
         "react": "^19.1.2",
diff --git a/tests/unit/ai-providers-cache.test.ts b/tests/unit/ai-providers-cache.test.ts
new file mode 100644
index 00000000..c67863da
--- /dev/null
+++ b/tests/unit/ai-providers-cache.test.ts
@@ -0,0 +1,85 @@
+// @vitest-environment node
+import { generateText, type ModelMessage } from "ai"
+import { afterEach, describe, expect, it, vi } from "vitest"
+import { CACHE_POINT, getAIModel } from "@/lib/ai-providers"
+
+const ENV = ["ANTHROPIC_API_KEY", "OPENROUTER_API_KEY"]
+const saved = Object.fromEntries(ENV.map((k) => [k, process.env[k]]))
+
+afterEach(() => {
+    for (const k of ENV) {
+        if (saved[k] === undefined) delete process.env[k]
+        else process.env[k] = saved[k]
+    }
+    vi.unstubAllGlobals()
+})
+
+// The chat route marks its system messages like this
+const messages: ModelMessage[] = [
+    { role: "system", content: "Instructions", providerOptions: CACHE_POINT },
+    { role: "user", content: "hi" },
+]
+
+/** Send the messages through a real provider and return the request body */
+async function requestBody(
+    provider: "anthropic" | "openrouter",
+    reply: unknown,
+) {
+    let body: any
+    vi.stubGlobal(
+        "fetch",
+        vi.fn(async (_url: string, init: RequestInit) => {
+            body = JSON.parse(init.body as string)
+            return new Response(JSON.stringify(reply), {
+                headers: { "content-type": "application/json" },
+            })
+        }),
+    )
+    const { model } = getAIModel({
+        provider,
+        modelId:
+            provider === "anthropic"
+                ? "claude-sonnet-4-5"
+                : "anthropic/claude-sonnet-4.5",
+    })
+    await generateText({ model, messages, maxRetries: 0 }).catch(() => {})
+    return body
+}
+
+describe("prompt cache breakpoints", () => {
+    it("reach the Anthropic API", async () => {
+        process.env.ANTHROPIC_API_KEY = "test-key"
+        const body = await requestBody("anthropic", {
+            id: "msg_1",
+            type: "message",
+            role: "assistant",
+            content: [{ type: "text", text: "ok" }],
+            stop_reason: "end_turn",
+            usage: { input_tokens: 1, output_tokens: 1 },
+        })
+        expect(body.system).toEqual([
+            {
+                type: "text",
+                text: "Instructions",
+                cache_control: { type: "ephemeral" },
+            },
+        ])
+    })
+
+    it("reach OpenRouter", async () => {
+        process.env.OPENROUTER_API_KEY = "test-key"
+        const body = await requestBody("openrouter", {
+            id: "gen-1",
+            choices: [
+                {
+                    index: 0,
+                    message: { role: "assistant", content: "ok" },
+                    finish_reason: "stop",
+                },
+            ],
+        })
+        expect(JSON.stringify(body.messages[0])).toContain(
+            '"cache_control":{"type":"ephemeral"}',
+        )
+    })
+})
diff --git a/tests/unit/ai-providers-google.test.ts b/tests/unit/ai-providers-google.test.ts
new file mode 100644
index 00000000..77b53637
--- /dev/null
+++ b/tests/unit/ai-providers-google.test.ts
@@ -0,0 +1,62 @@
+// @vitest-environment node
+import { generateText } from "ai"
+import { afterEach, describe, expect, it, vi } from "vitest"
+import { getAIModel } from "@/lib/ai-providers"
+
+const ENV = ["GOOGLE_GENERATIVE_AI_API_KEY", "GOOGLE_TOP_K", "GOOGLE_TOP_P"]
+const saved = Object.fromEntries(ENV.map((k) => [k, process.env[k]]))
+
+afterEach(() => {
+    for (const k of ENV) {
+        if (saved[k] === undefined) delete process.env[k]
+        else process.env[k] = saved[k]
+    }
+    vi.unstubAllGlobals()
+})
+
+/** Send one request through the real Google provider and return its body */
+async function googleRequestBody() {
+    let body: any
+    vi.stubGlobal(
+        "fetch",
+        vi.fn(async (_url: string, init: RequestInit) => {
+            body = JSON.parse(init.body as string)
+            return new Response(
+                JSON.stringify({
+                    candidates: [
+                        {
+                            content: { role: "model", parts: [{ text: "ok" }] },
+                            finishReason: "STOP",
+                        },
+                    ],
+                }),
+                { headers: { "content-type": "application/json" } },
+            )
+        }),
+    )
+    const { model } = getAIModel({
+        provider: "google",
+        modelId: "gemini-2.5-flash",
+    })
+    await generateText({ model, prompt: "hi", maxRetries: 0 })
+    return body
+}
+
+describe("Google sampling settings", () => {
+    it("sends GOOGLE_TOP_K and GOOGLE_TOP_P in the generation config", async () => {
+        process.env.GOOGLE_GENERATIVE_AI_API_KEY = "test-key"
+        process.env.GOOGLE_TOP_K = "40"
+        process.env.GOOGLE_TOP_P = "0.9"
+        const body = await googleRequestBody()
+        expect(body.generationConfig).toMatchObject({ topK: 40, topP: 0.9 })
+    })
+
+    it("sends neither when they are not set", async () => {
+        process.env.GOOGLE_GENERATIVE_AI_API_KEY = "test-key"
+        delete process.env.GOOGLE_TOP_K
+        delete process.env.GOOGLE_TOP_P
+        const body = await googleRequestBody()
+        expect(body.generationConfig?.topK).toBeUndefined()
+        expect(body.generationConfig?.topP).toBeUndefined()
+    })
+})
diff --git a/tests/unit/deprecated-params.test.ts b/tests/unit/deprecated-params.test.ts
new file mode 100644
index 00000000..13fff590
--- /dev/null
+++ b/tests/unit/deprecated-params.test.ts
@@ -0,0 +1,112 @@
+// @vitest-environment node
+import { simulateReadableStream, streamText } from "ai"
+import { MockLanguageModelV3 } from "ai/test"
+import { describe, expect, it } from "vitest"
+import {
+    withDeprecatedParamsFallback,
+    withoutDeprecatedParams,
+} from "@/lib/deprecated-params"
+
+// The error texts Claude 4.7 and later return (the Anthropic API and Bedrock)
+const rejection = (message: string) => ({
+    statusCode: 400,
+    message,
+    responseBody: JSON.stringify({ error: { message } }),
+})
+const TEMPERATURE = rejection("`temperature` is deprecated for this model.")
+const THINKING = rejection(
+    '"thinking.type.enabled" is not supported for this model. Use "thinking.type.adaptive" and "output_config.effort" to control thinking behavior.',
+)
+
+describe("withoutDeprecatedParams", () => {
+    const params = {
+        temperature: 0.2,
+        topP: 0.9,
+        maxOutputTokens: 1000,
+        providerOptions: {
+            anthropic: {
+                thinking: { type: "enabled", budgetTokens: 4000 },
+                cacheControl: { type: "ephemeral" },
+            },
+        },
+    }
+
+    it("drops sampling settings and the thinking budget", () => {
+        for (const error of [TEMPERATURE, THINKING]) {
+            expect(withoutDeprecatedParams(error, params)).toEqual({
+                maxOutputTokens: 1000,
+                providerOptions: {
+                    anthropic: { cacheControl: { type: "ephemeral" } },
+                },
+            })
+        }
+    })
+
+    it("drops a Bedrock thinking budget", () => {
+        const bedrock = {
+            providerOptions: {
+                bedrock: {
+                    reasoningConfig: { type: "enabled", budgetTokens: 4000 },
+                },
+            },
+        }
+        expect(withoutDeprecatedParams(THINKING, bedrock)).toEqual({
+            providerOptions: { bedrock: {} },
+        })
+    })
+
+    it("leaves other errors and requests with nothing to drop alone", () => {
+        expect(withoutDeprecatedParams(rejection("bad key"), params)).toBeNull()
+        expect(
+            withoutDeprecatedParams(
+                { ...TEMPERATURE, statusCode: 401 },
+                params,
+            ),
+        ).toBeNull()
+        const nothingToDrop = {
+            providerOptions: {
+                anthropic: { cacheControl: { type: "ephemeral" } },
+            },
+        }
+        expect(withoutDeprecatedParams(TEMPERATURE, nothingToDrop)).toBeNull()
+    })
+})
+
+describe("withDeprecatedParamsFallback", () => {
+    it("retries the stream once without the rejected settings", async () => {
+        const calls: any[] = []
+        const model = new MockLanguageModelV3({
+            // The test stream only has the parts this check needs
+            doStream: (async (options: any) => {
+                calls.push(options)
+                if (options.temperature !== undefined) throw TEMPERATURE
+                return {
+                    stream: simulateReadableStream({
+                        chunks: [
+                            { type: "text-start", id: "t" },
+                            { type: "text-delta", id: "t", delta: "ok" },
+                            { type: "text-end", id: "t" },
+                            {
+                                type: "finish",
+                                finishReason: { unified: "stop", raw: "stop" },
+                                usage: {
+                                    inputTokens: { total: 1 },
+                                    outputTokens: { total: 1 },
+                                },
+                            },
+                        ],
+                    }),
+                }
+            }) as any,
+        })
+        const result = streamText({
+            model: withDeprecatedParamsFallback(model as any),
+            prompt: "hi",
+            temperature: 0.2,
+            maxRetries: 0,
+        })
+        expect(await result.text).toBe("ok")
+        expect(calls).toHaveLength(2)
+        expect(calls[1].temperature).toBeUndefined()
+    })
+})