chore(deps-dev): bump @tanstack/ai and @tanstack/ai-ollama

[dependabot]

Bumps @tanstack/ai and @tanstack/ai-ollama. These dependencies needed to be updated together.
Updates @tanstack/ai from 0.51.0 to 0.53.0

Release notes

Sourced from @​tanstack/ai's releases.

@​tanstack/ai@​0.53.0

Minor Changes

• #1309 21775ee - Add @tanstack/ai-cloudflare: a Cloudflare adapter for Workers AI chat, summarization, embeddings, image generation, text-to-speech, and transcription over the env.AI binding or the REST API, with AI Gateway routing (gateway option and cloudflareGateway() helper for other providers). @tanstack/ai learns the cloudflare max-tokens key for summarize, lets defineByokProvider declare companion credentials with with, and adds getByokKeys(request, { name: provider }) to @tanstack/ai/byok/server. @tanstack/ai-client's defineByok takes providers: a send for a provider with companions (Cloudflare token plus account id) carries every x-byok-* header and prompts for each missing value.

@​tanstack/ai@​0.52.3

Patch Changes

• #1290 819e77c - Replay OpenAI Responses reasoning items with function_call on the next tool turn. Default include: ['reasoning.encrypted_content'] only on reasoning models.

@​tanstack/ai@​0.52.2

Patch Changes

• #1303 452d6a4 - fix: createChatOptions now preserves the runtime-context requirement on its return type. When tools or middleware declare a required context, the input already enforces context via RuntimeContextOption, but the return type declared it optional — so spreading the result into chat() failed to typecheck (Type 'undefined' is not assignable to type '...'). The return type now applies the same RuntimeContextOption conditional as the parameter, so the documented spread pattern compiles with context-typed tools. Type-level only; runtime is unchanged.

@​tanstack/ai@​0.52.1

Patch Changes

• #1271 cfb8454 - Keep the first text delta when a message speaks after a tool call and the text arrives in more than one chunk.

@​tanstack/ai@​0.52.0

Minor Changes

• #1235 e04ff6a - Keep canonical chat history separate from compacted provider context. Reuse validated compaction checkpoints through an optional persistence metadata store.

• #1235 e04ff6a - Add ctx.emitCustomEvent on chat middleware context. The engine yields CUSTOM chunks while hooks such as onConfig are still running, so a long middleware step can send progress before it finishes. Compaction uses this to emit compaction:started before the strategy returns.

Patch Changes

• #1257 49fc54c - Preserve draft-07 tuple items arrays during structured-output conversion.

  Keep a single widening map for homogeneous arrays so undoNullWidening applies it to every element.

• Updated dependencies [e04ff6a]:

  • @​tanstack/ai-event-client@​0.11.2

Changelog

Sourced from @​tanstack/ai's changelog.

0.53.0

Minor Changes

• #1309 21775ee - Add @tanstack/ai-cloudflare: a Cloudflare adapter for Workers AI chat, summarization, embeddings, image generation, text-to-speech, and transcription over the env.AI binding or the REST API, with AI Gateway routing (gateway option and cloudflareGateway() helper for other providers). @tanstack/ai learns the cloudflare max-tokens key for summarize, lets defineByokProvider declare companion credentials with with, and adds getByokKeys(request, { name: provider }) to @tanstack/ai/byok/server. @tanstack/ai-client's defineByok takes providers: a send for a provider with companions (Cloudflare token plus account id) carries every x-byok-* header and prompts for each missing value.

0.52.3

Patch Changes

• #1290 819e77c - Replay OpenAI Responses reasoning items with function_call on the next tool turn. Default include: ['reasoning.encrypted_content'] only on reasoning models.

0.52.2

Patch Changes

• #1303 452d6a4 - fix: createChatOptions now preserves the runtime-context requirement on its return type. When tools or middleware declare a required context, the input already enforces context via RuntimeContextOption, but the return type declared it optional — so spreading the result into chat() failed to typecheck (Type 'undefined' is not assignable to type '...'). The return type now applies the same RuntimeContextOption conditional as the parameter, so the documented spread pattern compiles with context-typed tools. Type-level only; runtime is unchanged.

0.52.1

Patch Changes

• #1271 cfb8454 - Keep the first text delta when a message speaks after a tool call and the text arrives in more than one chunk.

0.52.0

Minor Changes

• #1235 e04ff6a - Keep canonical chat history separate from compacted provider context. Reuse validated compaction checkpoints through an optional persistence metadata store.

• #1235 e04ff6a - Add ctx.emitCustomEvent on chat middleware context. The engine yields CUSTOM chunks while hooks such as onConfig are still running, so a long middleware step can send progress before it finishes. Compaction uses this to emit compaction:started before the strategy returns.

Patch Changes

• #1257 49fc54c - Preserve draft-07 tuple items arrays during structured-output conversion.

  Keep a single widening map for homogeneous arrays so undoNullWidening applies it to every element.

• Updated dependencies [e04ff6a]:

  • @​tanstack/ai-event-client@​0.11.2

Commits

• 62e4e46 ci: Version Packages (#1314)
• 21775ee feat(ai-cloudflare): add Cloudflare Workers AI and AI Gateway adapter (#1309)
• b87cf29 ci: Version Packages (#1310)
• 5305d32 feat: accept baseURL and defaultHeaders on every provider adapter (#1312)
• 819e77c fix(ai): replay OpenAI reasoning items on tool follow-up (#1290)
• 924d45e ci: Version Packages (#1304)
• 452d6a4 fix(ai): preserve required runtime context in createChatOptions return type (...
• a4ab03e feat(ui): add typed headless createChatUI adapters (#1252)
• 2b03b5c ci: Version Packages (#1281)
• cfb8454 fix(ai): keep the first text delta when the text starts before the tool call ...
• Additional commits viewable in compare view

Updates @tanstack/ai-ollama from 0.10.2 to 0.11.1

Release notes

Sourced from @​tanstack/ai-ollama's releases.

@​tanstack/ai-ollama@​0.11.1

Patch Changes

• Updated dependencies [21775ee]:
  • @​tanstack/ai@​0.53.0

@​tanstack/ai-ollama@​0.11.0

Minor Changes

• #1312 5305d32 - Accept baseURL and defaultHeaders on every adapter's client config so one gateway config (Cloudflare AI Gateway, Vercel AI Gateway, a corporate proxy) can be spread into any adapter. The vendor-specific names (httpOptions, serverURL, host, baseUrl, headers) keep working. Bedrock's Converse adapter now applies defaultHeaders too.

Patch Changes

• Updated dependencies [819e77c]:
  • @​tanstack/ai@​0.52.3

Changelog

Sourced from @​tanstack/ai-ollama's changelog.

0.11.1

Patch Changes

• Updated dependencies [21775ee]:
  • @​tanstack/ai@​0.53.0

0.11.0

Minor Changes

• #1312 5305d32 - Accept baseURL and defaultHeaders on every adapter's client config so one gateway config (Cloudflare AI Gateway, Vercel AI Gateway, a corporate proxy) can be spread into any adapter. The vendor-specific names (httpOptions, serverURL, host, baseUrl, headers) keep working. Bedrock's Converse adapter now applies defaultHeaders too.

Patch Changes

• Updated dependencies [819e77c]:
  • @​tanstack/ai@​0.52.3

0.10.3

Patch Changes

• Updated dependencies [49fc54c, e04ff6a, e04ff6a]:
  • @​tanstack/ai@​0.52.0

Commits

• 62e4e46 ci: Version Packages (#1314)
• b87cf29 ci: Version Packages (#1310)
• 5305d32 feat: accept baseURL and defaultHeaders on every provider adapter (#1312)
• a4ab03e feat(ui): add typed headless createChatUI adapters (#1252)
• c675499 docs: consolidate quick starts and sort guides by build path (#1274)
• b899fe5 ci: Version Packages (#1261)
• See full diff in compare view

[cursor]

Superseded by #147, which applies this bump (and #142) and ships v3.2.1 with the Release label. Closing as redundant.

[dependabot]

OK, I won't notify you again about this release, but will get in touch when a new version is available. You can also ignore all major, minor, or patch releases for a dependency by adding an ignore condition with the desired update_types to your config file.

If you change your mind, just re-open this PR and I'll resolve any conflicts on it.