@cloudflare/tanstack-ai@0.1.9

Patch Changes

• #518 4358cc1 Thanks @zackarychapple! - Widen @tanstack/ai peer dependency and optional adapter ranges to accept newer 0.x releases (up to but not including 1.0.0). Previously the caret ranges on pre-1.0 versions resolved to a single minor (e.g. ^0.8.0 only allowed >=0.8.0 <0.9.0), causing unmet-peer warnings when consumers installed @tanstack/ai@0.14.0 and matching adapter versions.

workers-ai-provider@3.1.13

Patch Changes

• #510 dfd2cb4 Thanks @Specy! - Map inputTokens.cacheRead and inputTokens.noCache from Workers AI's usage.prompt_tokens_details.cached_tokens instead of always reporting them as undefined. This makes prompt-cache hits visible to consumers that compute pricing or telemetry from LanguageModelV3Usage (generateText/streamText result.usage).

  cached_tokens is treated as cacheRead; cacheWrite remains undefined because the OpenAI-style usage shape Workers AI returns does not distinguish cache reads from writes.

  Closes #509.

workers-ai-provider@3.1.12

Patch Changes

• #504 e9b2a9a Thanks @threepointone! - Forward reasoning_effort and chat_template_kwargs onto binding.run(model, inputs)'s inputs object instead of silently dropping them into the options arg / REST query string. This fixes reasoning models (GLM-4.7-flash, Kimi K2.5/K2.6, GPT-OSS, QwQ) burning the entire output token budget on chain-of-thought with no visible content.

  Both settings-level and per-call usage are supported:

  // Settings-level
  const model = workersai("@cf/zai-org/glm-4.7-flash", {
  	reasoning_effort: "low",
  	chat_template_kwargs: { enable_thinking: false },
  });
  
  // Per-call (overrides settings)
  await generateText({
  	model,
  	prompt,
  	providerOptions: {
  		"workers-ai": { reasoning_effort: "low" },
  	},
  });

  reasoning_effort: null is preserved as-is (explicit "disable reasoning" signal). The two fields are also typed directly on WorkersAIChatSettings.

  Closes #501.

@cloudflare/tanstack-ai@0.1.8

Patch Changes

• #505 f43f6f0 Thanks @threepointone! - Add passthrough for reasoning_effort and chat_template_kwargs in createWorkersAiChat. Pass them per-call through modelOptions:

  const adapter = createWorkersAiChat("@cf/zai-org/glm-4.7-flash", {
  	binding: env.AI,
  });
  
  chat({
  	adapter,
  	messages,
  	modelOptions: {
  		reasoning_effort: "low",
  		chat_template_kwargs: { enable_thinking: false },
  	},
  });

  Previously these fields were silently dropped, which could cause reasoning models (GLM-4.7-flash, Kimi K2.5/K2.6, GPT-OSS) to burn the entire output token budget on chain-of-thought with no visible content. They now reach binding.run(model, inputs) at the inputs level as required by Workers AI.

  A new WorkersAiTextModelOptions type is exported from @cloudflare/tanstack-ai and @cloudflare/tanstack-ai/adapters/workers-ai.

  Closes #503.

workers-ai-provider@3.1.11

Patch Changes

• #494 ed6112a Thanks @threepointone! - Emit tool-input-end and tool-call events eagerly when streaming multiple tool calls, instead of deferring all of them to stream close. Previously, all tool calls appeared "in progress" simultaneously because tool-input-end was only emitted in flush(). Now each tool call is closed as soon as the next one starts or a null finalization chunk is received, matching the behavior of other AI SDK providers.

workers-ai-provider@3.1.10

Patch Changes

• #480 1c6bdad Thanks @threepointone! - Add optional fetch parameter to credentials mode for request interception and testing. Available when using accountId + apiKey (not with bindings). Matches the pattern used by @ai-sdk/openai and @ai-sdk/anthropic.

workers-ai-provider@3.1.9

Patch Changes

• #474 dc95a5f Thanks @threepointone! - update dependencies

• #461 9131bb4 Thanks @threepointone! - Replace tsup with tsdown as the build tool

ai-gateway-provider@3.1.3

Patch Changes

• #474 dc95a5f Thanks @threepointone! - update dependencies

• #461 9131bb4 Thanks @threepointone! - Replace tsup with tsdown as the build tool

@cloudflare/tanstack-ai@0.1.7

Patch Changes

• #474 dc95a5f Thanks @threepointone! - update dependencies

• #461 9131bb4 Thanks @threepointone! - Replace tsup with tsdown as the build tool

workers-ai-provider@3.1.8

Patch Changes

• #455 e02cdd2 Thanks @ferdousbhai! - fix(workers-ai-provider): close reasoning block before tool calls and text