Timeline de Lanzamientos

## What's changed - Opus 4.6 now defaults to medium effort for Max and Team subscribers. Medium effort works well for most tasks — it's the sweet spot between speed and thoroughness. You can change this anytime with `/model` - Re-introduced the "ultrathink" keyword to enable high effort for the nex

## What's Changed * Fixed issue where GLM-OCR would not work due to incorrect prompt rendering * Fixed tool calling parsing and rendering for Qwen 3.5 models ## New Contributors * @Victor-Quqi made their first contribution in https://github.com/ollama/ollama/pull/14584 **Full Changelog**: h

Gemini 3.1 Flash-Lite is our fastest and most cost-efficient Gemini 3 series model yet.

### Patch Changes - fix: correctly add \_\_svelte_meta after else-if chains ([#17830](https://github.com/sveltejs/svelte/pull/17830)) - perf: cache element interactivity and source line splitting in compiler ([#17839](https://github.com/sveltejs/svelte/pull/17839)) - chore: avoid rescheduli

### 2.7.2 / 2026.03.03 - feat: v8 14.6, fix require(esm), libuv compat (#32347) - fix(ci): fix ordering of platforms in ecosystem_compat_slack (#32393) - fix(cli): load multiple env files in the correct order (#32354) - fix(compile): store self extracting dir in hidden dir beside executable

Node.js v25.8.0

Changes since langchain-core==1.2.16 release(core): 1.2.17 (#35527) fix(core): extract usage metadata from serialized tracer message outputs (#35526) chore: bump the langchain-deps group across 3 directories with 7 updates (#35513) chore: bump the langchain-deps group across 3 directories with 14 u

Changes since langchain-huggingface==1.2.0 fix(huggingface): switch integration test provider to together (#35525) fix(huggingface): resolve huggingface-hub 1.x compat (#35524) fix(huggingface): bump transformers and sentence-transformers lower bounds (#35522) chore: bump langgraph-checkpoint from

## New models - [Qwen3.5](https://ollama.com/library/qwen3.5): the small Qwen 3.5 model series is now available in 0.8B, 2B, 4B and 9B parameter sizes. ## What's Changed * Fixed crash in Qwen 3.5 models when split over GPU & CPU * Fixed issue where Qwen 3.5 models would repeat themselves due t

## What's changed - Added `/simplify` and `/batch` bundled slash commands - Fixed local slash command output like /cost appearing as user-sent messages instead of system messages in the UI - Project configs & auto memory now shared across git worktrees of the same repository - Added `ENABLE_CLAUDEA

### Patch Changes - Bumped `@remix-run/*` dependencies: - [`fetch-router@0.17.0`](https://github.com/remix-run/remix/releases/tag/fetch-router@0.17.0) - [`fs@0.4.2`](https://github.com/remix-run/remix/releases/tag/fs@0.4.2) - [`mime@0.4.0`](https://github.com/remix-run/remix/releases/tag/mime

### Patch Changes - Bumped `@remix-run/*` dependencies: - [`fetch-router@0.17.0`](https://github.com/remix-run/remix/releases/tag/fetch-router@0.17.0)

### Minor Changes - Add Memcache session storage with `createMemcacheSessionStorage(server, options)`. This adds a Node.js Memcache backend with support for `useUnknownIds`, `keyPrefix`, and `ttlSeconds`, along with integration tests that run against Memcached in CI.

### Patch Changes - Bumped `@remix-run/*` dependencies: - [`mime@0.4.0`](https://github.com/remix-run/remix/releases/tag/mime@0.4.0)

### Minor Changes - BREAKING CHANGE: Remove `RoutePatternOptions` type and rework `ignoreCase` `RoutePattern.ignoreCase` field has been removed and `ignoreCase` now only applies to `pathname` (no longer applies to `search`) Case sensitivity is now determined only when matching. - `RoutePat

### Minor Changes - Include all MIME types from mime-db, including experimental (`x-`) and vendor-specific (`vnd.`) types.

### Patch Changes - perf: optimize parser hot paths for faster compilation ([#17811](https://github.com/sveltejs/svelte/pull/17811)) - fix: `SvelteMap` incorrectly handles keys with `undefined` values ([#17826](https://github.com/sveltejs/svelte/pull/17826)) - fix: SvelteURL `search` setter

## New models - [Qwen 3.5](https://ollama.com/library/qwen3.5): a family of open-source multimodal models that delivers exceptional utility and performance. - [LFM 2](https://ollama.com/library/lfm2): LFM2 is a family of hybrid models designed for on-device deployment. LFM2-24B-A2B is the largest

## What's Changed * Fixed issue where tool calls in the Qwen 3 and Qwen 3.5 model families would not be parsed correctly if emitted during thinking **Full Changelog**: https://github.com/ollama/ollama/compare/v0.17.2...v0.17.3

## What's changed - Fixed prompt suggestion cache regression that reduced cache hit rates

## What's Changed * Fixed issue where Ollama's app on Windows would crash when a new update has been downloaded **Full Changelog**: https://github.com/ollama/ollama/compare/v0.17.1...v0.17.2

## What's changed - Fixed concurrent writes corrupting config file on Windows

# Generated by Speakeasy CLI ## 2026-02-26 08:33:13 ### Changes Based on: - OpenAPI Doc 1.0.0 - Speakeasy CLI 1.729.0 (2.841.0) https://github.com/speakeasy-api/speakeasy ### Generated - [python v2.0.0b1] . ### Releases - [PyPI v2.0.0b1] https://pypi.org/project/mistralai/2.0.0b1 - . Publishing C

## [1.43.0](https://github.com/googleapis/js-genai/compare/v1.42.0...v1.43.0) (2026-02-26) ### Features * Add gemini-3.1-pro-preview to list of models in Interactions ([14775fe](https://github.com/googleapis/js-genai/commit/14775fefb814c21d8f34b776935b72d7f20896bd)) * Add Image Grounding support

## What's changed - Claude automatically saves useful context to auto-memory. Manage with /memory - Added `/copy` command to show an interactive picker when code blocks are present, allowing selection of individual code blocks or the full response. - Improved "always allow" prefix suggestions for c

## [1.65.0](https://github.com/googleapis/python-genai/compare/v1.64.0...v1.65.0) (2026-02-26) ### Features * Add gemini-3.1-pro-preview to list of models in Interactions ([fe86870](https://github.com/googleapis/python-genai/commit/fe86870752ca8cc66d140d3942e9b07f19ca092c)) * Add Image Grounding

## What's changed - Expand Remote Control to more users

### Minor Changes - [#15589](https://github.com/withastro/astro/pull/15589) [`b7dd447`](https://github.com/withastro/astro/commit/b7dd447e319a7b435c01ccd69347e5261bd9dc14) Thanks [@qzio](https://github.com/qzio)! - Adds a new `security.actionBodySizeLimit` option to configure the maximum size of

### 2.7.1 / 2026.02.25 This is a maintenance release to fix wrong output of `deno --version` in v2.7.0.

Changes since langchain-core==1.2.15 release(core): 1.2.16 (#35439) fix(core): treat empty tool chunk ids as missing in merge (#35414)

### Patch Changes - fix: escape `innerText` and `textContent` bindings of `contenteditable` ([`0df5abcae223058ceb95491470372065fb87951d`](https://github.com/sveltejs/svelte/commit/0df5abcae223058ceb95491470372065fb87951d)) - fix: sanitize `transformError` values prior to embedding in HTML comm

### Patch Changes - fix: set server context after async transformError ([#17799](https://github.com/sveltejs/svelte/pull/17799)) - fix: hydrate if blocks correctly ([#17784](https://github.com/sveltejs/svelte/pull/17784)) - fix: handle default parameters scope leaks ([#17788](https://github

# Generated by Speakeasy CLI [@mistralai/mistralai 1.14.1](https://www.npmjs.com/package/@mistralai/mistralai/v/1.14.1) ## Typescript SDK Changes: * `mistral.beta.agents.updateVersion()`: `response` **Changed** **Breaking** :warning: * `mistral.beta.agents.getVersion()`: `response` **Changed** **B

### 2.7.0 / 2026.02.25 Read more: http://deno.com/blog/v2.7 - feat(audit): add `--ignore` flag to filter advisories by CVE ID (#32221) - feat(check): add `--check-js` flag (#32235) - feat(cli): add `--save-exact`/`--exact` flag to `deno add` and `install` (#31977) - feat(cli): add `deno

## What's changed - VS Code: Fixed another cause of "command 'claude-vscode.editor.openLast' not found" crashes

## 0.84.0 (2026-02-25) Full Changelog: [v0.83.0...v0.84.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.83.0...v0.84.0) ### Features * **api:** change array_format to brackets ([925d2ad](https://github.com/anthropics/anthropic-sdk-python/commit/925d2ad6b76ad7c15de07b9b2768738775f

## What's changed - Fixed BashTool failing on Windows with EINVAL error

## What's changed - Fixed a UI flicker where user input would briefly disappear after submission before the message rendered - Fixed bulk agent kill (ctrl+f) to send a single aggregate notification instead of one per agent, and to properly clear the command queue - Fixed graceful shutdown sometimes

## 2.24.0 (2026-02-24) Full Changelog: [v2.23.0...v2.24.0](https://github.com/openai/openai-python/compare/v2.23.0...v2.24.0) ### Features * **api:** add phase ([391deb9](https://github.com/openai/openai-python/commit/391deb99f6a92e51bffb25efd8dfe367d144bb9d)) ### Bug Fixes * **api:** fix phas

## 6.25.0 (2026-02-24) Full Changelog: [v6.24.0...v6.25.0](https://github.com/openai/openai-node/compare/v6.24.0...v6.25.0) ### Features * **api:** add phase ([e32b853](https://github.com/openai/openai-node/commit/e32b853c3c57f2d0e4c05b09177b94677aed0e5a)) ### Bug Fixes * **api:** fix phase en

### Patch Changes - [#15561](https://github.com/withastro/astro/pull/15561) [`413b0f7`](https://github.com/withastro/astro/commit/413b0f746a28503c936b3875ffaee6b7f04c67b9) Thanks [@renovate](https://github.com/apps/renovate)! - Updates `fast-xml-parser` to v5.3.6

### Patch Changes - [#15581](https://github.com/withastro/astro/pull/15581) [`2851f10`](https://github.com/withastro/astro/commit/2851f1094c03d696682efb4f3b321ef27e29e88c) Thanks [@renovate](https://github.com/apps/renovate)! - Updates `svelte` to v5.51.5

## What's Changed * Nemotron architecture support in Ollama's engine * MLX engine now has improved memory usage * Ollama's app will now allow models that support tools to use web search capabilities * Improved LFM2 and LFM2.5 models in Ollama's engine * `ollama create` will no longer default to

Changes since langchain-anthropic==1.3.3 release(anthropic): 1.3.4 (#35418) fix(anthropic): filter out common OpenAI Responses block types (#35417) fix(anthropic): update integration tests (#35396) revert: add ChatAnthropicBedrockWrapper (#35371) fix(anthropic): replace retired model IDs in tests a

## What's changed - VS Code: Fixed extension crash on Windows ("command 'claude-vscode.editor.openLast' not found")

For stable releases, please refer to [CHANGELOG.md](https://github.com/vuejs/core/blob/main/CHANGELOG.md) for details. For pre-releases, please refer to [CHANGELOG.md](https://github.com/vuejs/core/blob/minor/CHANGELOG.md) of the `minor` branch.

## 6.24.0 (2026-02-24) Full Changelog: [v6.23.0...v6.24.0](https://github.com/openai/openai-node/compare/v6.23.0...v6.24.0) ### Features * **api:** add gpt-realtime-1.5 and gpt-audio-1.5 models to realtime ([75875bf](https://github.com/openai/openai-node/commit/75875bfb850c0780878553c566fe8821048

## 2.23.0 (2026-02-24) Full Changelog: [v2.22.0...v2.23.0](https://github.com/openai/openai-python/compare/v2.22.0...v2.23.0) ### Features * **api:** add gpt-realtime-1.5 and gpt-audio-1.5 model options to realtime calls ([3300b61](https://github.com/openai/openai-python/commit/3300b61e1d5a34c9d2

## What's changed - Added `claude remote-control` subcommand for external builds, enabling local environment serving for all users. - Updated plugin marketplace default git timeout from 30s to 120s and added `CLAUDE_CODE_PLUGIN_GIT_TIMEOUT_MS` to configure. - Added support for custom npm registries

Node.js v24.14.0

Node.js v25.7.0

## 2.22.0 (2026-02-23) Full Changelog: [v2.21.0...v2.22.0](https://github.com/openai/openai-python/compare/v2.21.0...v2.22.0) ### Features * **api:** websockets for responses api ([c01f6fb](https://github.com/openai/openai-python/commit/c01f6fb0d55b7454f73c4904ea7a1954553085dc)) ### Chores * *

## 6.23.0 (2026-02-23) Full Changelog: [v6.22.0...v6.23.0](https://github.com/openai/openai-node/compare/v6.22.0...v6.23.0) ### Features * **api:** websockets for responses api ([c6b96b8](https://github.com/openai/openai-node/commit/c6b96b8b8d5f8132e0a4c5f7399a04185302adcc)) ### Bug Fixes * **

Changes since langchain-core==1.2.14 fix(core): improve error message for non-JSON-serializable tool schemas (#34376) fix(core): improve typing/docs for on_chat_model_start to clarify required positional args (#35324) perf(core): defer specific `langsmith` imports to reduce import time (#35298) rev

### Fixed - Allow trailing dash in functional utility names for backwards compatibility ([#19696](https://github.com/tailwindlabs/tailwindcss/pull/19696)) - Properly detect classes containing `.` characters within curly braces in MDX files ([#19711](https://github.com/tailwindlabs/tailwindcss/pu

### Patch Changes - fix: render `:catch` of `#await` block with correct key ([#17769](https://github.com/sveltejs/svelte/pull/17769)) - chore: pin aria-query@5.3.1 ([#17772](https://github.com/sveltejs/svelte/pull/17772)) - fix: make string coercion consistent to `toString` ([#17774](https:

### Patch Changes - fix: update expressions on server deriveds ([#17767](https://github.com/sveltejs/svelte/pull/17767)) - fix: further obfuscate `node:crypto` import from overzealous static analysis ([#17763](https://github.com/sveltejs/svelte/pull/17763))

### Patch Changes - fix: handle shadowed function names correctly ([#17753](https://github.com/sveltejs/svelte/pull/17753))

## OpenClaw OpenClaw can now be installed and configured automatically via Ollama, making it the easiest way to get up and running with OpenClaw with open models like Kimi-K2.5, GLM-5, and Minimax-M2.5. ### Get started `ollama launch openclaw` <img width="2368" height="1830" alt="oc1" sr

## What's changed - Added support for `startupTimeout` configuration for LSP servers - Added `WorktreeCreate` and `WorktreeRemove` hook events, enabling custom VCS setup and teardown when agent worktree isolation creates or removes worktrees. - Fixed a bug where resumed sessions could be invisible

# Generated by Speakeasy CLI [mistralai 1.12.4](https://pypi.org/project/mistralai/1.12.4) ## Python SDK Changes: * `mistral.beta.conversations.start()`: * `request.inputs.[array].[]` **Changed** **Breaking** :warning: * `response` **Changed** **Breaking** :warning: * `mistral.beta.conversati

## What's changed - Fixed Ctrl+C and ESC being silently ignored when background agents are running and the main thread is idle. Pressing twice within 3 seconds now kills all background agents. - Fixed prompt suggestion cache regression that reduced cache hit rates. - Fixed `plugin enable` and `plug

## What's Changed * New `ollama launch cline` added for the Cline CLI * `ollama launch <integration>` will now always show the model picker * Added Gemma 3, Llama and Qwen 3 architectures to MLX runner ## New Contributors * @hellosaumil made their first contribution in https://github.com/oll

## 0.26.4 (2026-02-19) Full Changelog: [bedrock-sdk-v0.26.3...bedrock-sdk-v0.26.4](https://github.com/anthropics/anthropic-sdk-typescript/compare/bedrock-sdk-v0.26.3...bedrock-sdk-v0.26.4) ### Bug Fixes * **bedrock:** eliminate race condition in AWS credential resolution ([#901](https://github.co

## 0.14.4 (2026-02-19) Full Changelog: [vertex-sdk-v0.14.3...vertex-sdk-v0.14.4](https://github.com/anthropics/anthropic-sdk-typescript/compare/vertex-sdk-v0.14.3...vertex-sdk-v0.14.4)

## 0.78.0 (2026-02-19) Full Changelog: [sdk-v0.77.0...sdk-v0.78.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.77.0...sdk-v0.78.0) ### Features * **api:** Add top-level cache control (automatic caching) ([1e2f83d](https://github.com/anthropics/anthropic-sdk-typescript/co

## 0.83.0 (2026-02-19) Full Changelog: [v0.82.0...v0.83.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.82.0...v0.83.0) ### Features * **api:** Add top-level cache control (automatic caching) ([a940123](https://github.com/anthropics/anthropic-sdk-python/commit/a940123da34ac33f0b6

3.1 Pro is designed for tasks where a simple answer isn’t enough.

Changes since langchain-core==1.2.13 release(core): 1.2.14 (#35328) chore(core): remove `langserve` from sys info util, add `deepagents` (#35325) fix(core): fix merge_lists incorrectly merging parallel tool calls (#35281) fix(core): accept int temperature in _get_ls_params for LangSmith tracing (#3

## [1.42.0](https://github.com/googleapis/js-genai/compare/v1.41.0...v1.42.0) (2026-02-18) ### Features * Support multimodal embedding for Gemini Embedding 2.0 and support MaaS models in Models.embed_content() (Vertex AI API) ([944ae97](https://github.com/googleapis/js-genai/commit/944ae97f33168a

## [1.64.0](https://github.com/googleapis/python-genai/compare/v1.63.0...v1.64.0) (2026-02-18) ### Features * Add UnifiedMetric support to Vertex Tuning evaluation config ([9a9908a](https://github.com/googleapis/python-genai/commit/9a9908a9605756a94404359187cad09b21c094e0)) * Support multimodal e

Changes since langchain-text-splitters==1.1.0 release(text-splitters): 1.1.1 (#35318) fix(text-splitters): prevent JSFrameworkTextSplitter from mutating self._separators on each split_text() call (#35316) chore: bump transformers from 5.1.0 to 5.2.0 in /libs/text-splitters in the other-deps group a

### Minor Changes - feat: allow comments in tags ([#17671](https://github.com/sveltejs/svelte/pull/17671)) - feat: allow error boundaries to work on the server ([#17672](https://github.com/sveltejs/svelte/pull/17672)) ### Patch Changes - fix: use TrustedHTML to test for customizable <selec

## What's changed - Fixed FileWriteTool line counting to preserve intentional trailing blank lines instead of stripping them with `trimEnd()`. - Fixed Windows terminal rendering bugs caused by `os.EOL` (`\r\n`) in display code — line counts now show correct values instead of always showing 1 on Win

### Minor Changes - feat: support TrustedHTML in `{@html}` expressions ([#17701](https://github.com/sveltejs/svelte/pull/17701)) ### Patch Changes - fix: repair dynamic component truthy/falsy hydration mismatches ([#17737](https://github.com/sveltejs/svelte/pull/17737)) - fix: re-run non-r

## What's Changed * Deprecate `BaseImageResponse.prompt` after `up_sampled_prompt` proto removal by @shawnthapa in https://github.com/xai-org/xai-sdk-python/pull/96 * Add 2K image resolution support by @shawnthapa in https://github.com/xai-org/xai-sdk-python/pull/97 * Reduce default PollTimer poll i

## 0.77.0 (2026-02-18) Full Changelog: [sdk-v0.76.0...sdk-v0.77.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.76.0...sdk-v0.77.0) ### Features * **api:** fix shared UserLocation and error code types ([c84038f](https://github.com/anthropics/anthropic-sdk-typescript/commi

### Patch Changes - [#15564](https://github.com/withastro/astro/pull/15564) [`522f880`](https://github.com/withastro/astro/commit/522f880b07a4ea7d69a19b5507fb53a5ed6c87f8) Thanks [@matthewp](https://github.com/matthewp)! - Add a default body size limit for server actions to prevent oversized requ

### Patch Changes - [#15564](https://github.com/withastro/astro/pull/15564) [`522f880`](https://github.com/withastro/astro/commit/522f880b07a4ea7d69a19b5507fb53a5ed6c87f8) Thanks [@matthewp](https://github.com/matthewp)! - Add a default body size limit for server actions to prevent oversized requ

## 0.82.0 (2026-02-18) Full Changelog: [v0.81.0...v0.82.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.81.0...v0.82.0) ### Features * **api:** fix shared UserLocation and error code types ([da3b931](https://github.com/anthropics/anthropic-sdk-python/commit/da3b931a2be768d77c228a

### Patch Changes - fix: check to make sure `svelte:element` tags are valid during SSR ([`73098bb26c6f06e7fd1b0746d817d2c5ee90755f`](https://github.com/sveltejs/svelte/commit/73098bb26c6f06e7fd1b0746d817d2c5ee90755f)) - fix: misc option escaping and backwards compatibility ([#17741](https://gi

For release notes, check out the [release announcement](https://devblogs.microsoft.com/typescript/announcing-typescript-6-0-beta/). * [fixed issues query for Typescript 6.0.0 (Beta)](https://github.com/Microsoft/TypeScript/issues?utf8=%E2%9C%93&q=milestone%3A%22TypeScript+6.0.0%22+is%3Aclosed+).

### Patch Changes - chore: proactively defer effects in pending boundary ([#17734](https://github.com/sveltejs/svelte/pull/17734)) - fix: detect and error on non-idempotent each block keys in dev mode ([#17732](https://github.com/sveltejs/svelte/pull/17732))

Changes since langchain-tests==1.1.4 chore: bump the other-deps group across 3 directories with 2 updates (#35255) style: bump ruff version to 0.15 (#35042) chore(deps): bump langsmith from 0.4.56 to 0.6.3 in /libs/standard-tests (#35157) release(standard-tests): release 1.1.5 (#35139) chore(deps):

Learn more about new agentic capabilities coming to Chrome, powered by Gemini 3.

### Added - Add mauve, olive, mist, and taupe color palettes to the default theme ([#19627](https://github.com/tailwindlabs/tailwindcss/pull/19627)) - Add `@tailwindcss/webpack` package to run Tailwind CSS as a webpack plugin ([#19610](https://github.com/tailwindlabs/tailwindcss/pull/19610)) -

## 0.81.0 (2026-02-18) Full Changelog: [v0.80.0...v0.81.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.80.0...v0.81.0) ### Features * **api:** Make new tool versions available as top level tool types ([0a385c2](https://github.com/anthropics/anthropic-sdk-python/commit/0a385c29d2

## 0.76.0 (2026-02-18) Full Changelog: [sdk-v0.75.0...sdk-v0.76.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.75.0...sdk-v0.76.0) ### Features * **api:** Make new tool versions available as top level tool types ([25fe41c](https://github.com/anthropics/anthropic-sdk-type

## 0.75.0 (2026-02-17) Full Changelog: [sdk-v0.74.0...sdk-v0.75.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.74.0...sdk-v0.75.0) ### Features * **api:** Releasing claude-sonnet-4-6 ([d75e1c0](https://github.com/anthropics/anthropic-sdk-typescript/commit/d75e1c07bf8c108

## 0.80.0 (2026-02-17) Full Changelog: [v0.79.0...v0.80.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.79.0...v0.80.0) ### Features * **api:** Releasing claude-sonnet-4-6 ([d518d6e](https://github.com/anthropics/anthropic-sdk-python/commit/d518d6ecede3d0638f0b14950dc2be8efa0b4ff

## What's changed - Added support for Claude Sonnet 4.6 - Added support for reading `enabledPlugins` and `extraKnownMarketplaces` from `--add-dir` directories - Added `spinnerTipsOverride` setting to customize spinner tips — configure `tips` with an array of custom tip strings, and optionally set `

Changes since langchain-openai==1.1.9 release(openai): 1.1.10 (#35292) feat(openai): support automatic server-side compaction (#35212) fix(openai): add `model` property (#35284) fix(nomic,openai,perplexity): update pillow version to >= 12.1.1, <13.0.0 (#35254) docs(openai): more nits (#35277) docs(

### 2.6.10 / 2026.02.17 - feat(ext/tls): add `SSLKEYLOGFILE` support for TLS key logging (#31867) - feat(publish): support more license file types (#32133) - feat: add `deno install --compile` (#32046) - fix(compile): remove data.is_empty() check (#32125) - fix(deploy): bypass minimumDependen

# Generated by Speakeasy CLI [mistralai 1.12.3](https://pypi.org/project/mistralai/1.12.3) ## Python SDK Changes: * `mistral.fine-tuning.jobs.create()`: * `request` **Changed** **Breaking** :warning: * `response` **Changed** **Breaking** :warning: * `mistral.models.update()`: `response` **Ch

### Patch Changes - fix: prevent event delegation logic conflicting between svelte instances ([#17728](https://github.com/sveltejs/svelte/pull/17728)) - fix: treat CSS attribute selectors as case-insensitive for HTML enumerated attributes ([#17712](https://github.com/sveltejs/svelte/pull/17712

### Patch Changes - Updated dependencies \[[`6f19ecc`](https://github.com/withastro/astro/commit/6f19ecc35adfb2ddaabbba2269630f95c13f5a57), [`f94d3c5`](https://github.com/withastro/astro/commit/f94d3c5313e5a7576cf2cb316a85d68d335a188f)]: - @astrojs/markdown-remark@7.0.0-beta.9

### Misc Changes - Ensure we only run main test mode with custom deploy script: #90665 ### Credits Huge thanks to @ijjk for helping!

## What's changed - Fixed auth refresh errors

## New Model additions ### VoxtralRealtime <img width="1920" height="1080" alt="image" src="https://github.com/user-attachments/assets/80e37670-6d70-402b-8c8e-ccfb8c32df2d" /> VoxtralRealtime is a streaming speech-to-text model from [Mistral AI](https://mistral.ai), designed for real-time a

### Patch Changes - [#14589](https://github.com/withastro/astro/pull/14589) [`7038f07`](https://github.com/withastro/astro/commit/7038f0700898a17cb87b5a2e408480c1226a47f4) Thanks [@43081j](https://github.com/43081j)! - Improves CLI styling

### Patch Changes - [#15495](https://github.com/withastro/astro/pull/15495) [`5b99e90`](https://github.com/withastro/astro/commit/5b99e9077a92602f1e46e9b6eb9094bcd00c640e) Thanks [@leekeh](https://github.com/leekeh)! - Refactors to use `middlewareMode` adapter feature (set to `classic`) - [#15

### Major Changes - [#15726](https://github.com/withastro/astro/pull/15726) [`6f19ecc`](https://github.com/withastro/astro/commit/6f19ecc35adfb2ddaabbba2269630f95c13f5a57) Thanks [@ocavue](https://github.com/ocavue)! - Updates dependency `shiki` to v4 Check [Shiki's upgrade guide](https://sh

### Patch Changes - [#15696](https://github.com/withastro/astro/pull/15696) [`a9fd221`](https://github.com/withastro/astro/commit/a9fd221bda99db4660c241c494b6d3225eb4e51d) Thanks [@Princesseuh](https://github.com/Princesseuh)! - Fixes duplicate logging showing up in some cases when prerendering p

### Patch Changes - [#15496](https://github.com/withastro/astro/pull/15496) [`eb7cdda`](https://github.com/withastro/astro/commit/eb7cdda6837a8b28e279f668d0fe2a06f02f6990) Thanks [@matthewp](https://github.com/matthewp)! - Fix syntax highlighting for lowercase component tags that start with "styl

### Minor Changes - [#15646](https://github.com/withastro/astro/pull/15646) [`0dd9d00`](https://github.com/withastro/astro/commit/0dd9d00cf8be38c53217426f6b0e155a6f7c2a22) Thanks [@delucis](https://github.com/delucis)! - Removes redundant `fetchpriority` attributes from the output of Astro’s `<Im

### Patch Changes - Updated dependencies \[[`6f19ecc`](https://github.com/withastro/astro/commit/6f19ecc35adfb2ddaabbba2269630f95c13f5a57), [`f94d3c5`](https://github.com/withastro/astro/commit/f94d3c5313e5a7576cf2cb316a85d68d335a188f)]: - @astrojs/markdown-remark@7.0.0-beta.9

### Patch Changes - fix: take async into consideration for dev delegated handlers ([#17710](https://github.com/sveltejs/svelte/pull/17710)) - fix: emit state_referenced_locally warning for non-destructured props ([#17708](https://github.com/sveltejs/svelte/pull/17708))

Changes since langchain-openrouter==0.0.1 chore(openrouter): bump core ver, silence warning (#35231)

Changes since langchain-anthropic==1.3.2 release(anthropic): 1.3.3 (#35146) fix(anthropic): support effort="max" and remove beta headers (#35141) feat(core): add ContextOverflowError, raise in anthropic and openai (#35099) feat(model-profiles): add text_inputs and text_outputs (#35084) fix(anthropi

Changes since langchain-openai==1.1.8 release(openai): 1.1.9 (#35145) fix(openai): sanitize urls when counting tokens in images (#35143) feat(core): add ContextOverflowError, raise in anthropic and openai (#35099) feat(model-profiles): add text_inputs and text_outputs (#35084)

Changes since langchain-openai==1.1.7 release(openai): 1.1.8 (#35097) fix(openai): detect codex models for responses api preference (#35058) chore: add make type target (#35015) revert: "chore: add typing target in Makefile" (#35013) chore: add typing target in Makefile (#35012) chore: enrich pypro

Changes since langchain-core==1.2.12 release(core): 1.2.13 (#35230) docs(core): expanded `get_lc_namespace` docstring (#35229) feat(openrouter): add `langchain-openrouter` provider package (#35211) style: bump ruff version to 0.15 (#35042)

### Patch Changes - fix: don't crash on undefined `document.contentType` ([#17707](https://github.com/sveltejs/svelte/pull/17707)) - fix: use symbols for encapsulated event delegation ([#17703](https://github.com/sveltejs/svelte/pull/17703))

## What's Changed * `ollama launch claude` now supports searching the web when using `:cloud` models * Fixed rendering issue when running `ollama` in PowerShell * New setting in Ollama's app makes it easier to disable cloud models for sensitive and private tasks where data cannot leave your compu

## 6.22.0 (2026-02-14) Full Changelog: [v6.21.0...v6.22.0](https://github.com/openai/openai-node/compare/v6.21.0...v6.22.0) ### Features * **api:** container network_policy and skills ([65c1482](https://github.com/openai/openai-node/commit/65c1482a41f16d39ff6ba26849a72b417b27403e)) ### Bug Fixe

## 2.21.0 (2026-02-13) Full Changelog: [v2.20.0...v2.21.0](https://github.com/openai/openai-python/compare/v2.20.0...v2.21.0) ### Features * **api:** container network_policy and skills ([d19de2e](https://github.com/openai/openai-python/commit/d19de2ee5c74413f9dc52684b650df1898dee82b)) ### Bug

## What's changed - Fixed /resume showing interrupt messages as session titles - Fixed Opus 4.6 launch announcement showing for Bedrock/Vertex/Foundry users - Improved error message for many-image dimension limit errors with /compact suggestion

### Minor Changes - feat: Use `TrustedTypes` for HTML handling where supported ([#16271](https://github.com/sveltejs/svelte/pull/16271)) ### Patch Changes - fix: sanitize template-literal-special-characters in SSR attribute values ([#17692](https://github.com/sveltejs/svelte/pull/17692)) -

We’ve upgraded Cloudflare One to support post-quantum encryption by implementing the latest IETF drafts for hybrid ML-KEM into our Cloudflare IPsec product. This extends post-quantum encryption across all major Cloudflare One on-ramps and off-ramps.

Discover GitHub Agentic Workflows, now in technical preview. Build automations using coding agents in GitHub Actions to handle triage, documentation, code quality, and more. The post Automate repository tasks with GitHub Agentic Workflows   appeared first on The GitHub Blog.

GPT-5.2 is the latest model family in the GPT-5 series. The comprehensive safety mitigation approach for these models is largely the same as that described in the GPT-5 System Card and GPT-5.1 System Card. Like OpenAI’s other models, the GPT-5.2 models were trained on diverse datasets, including inf

OpenAI is a non-profit artificial intelligence research company. Our goal is to advance digital intelligence in the way that is most likely to benefit humanity as a whole, unconstrained by a need to generate financial return. Since our research is free from financial obligations, we can better focus

## What's changed - Fixed AWS auth refresh hanging indefinitely by adding a 3-minute timeout - Added `claude auth login`, `claude auth status`, and `claude auth logout` CLI subcommands - Added Windows ARM64 (win32-arm64) native binary support - Improved `/rename` to auto-generate session name from

Breaking down complex tasks across specialized agents is one of the most effective approaches to building capable AI systems. In this post, we'll show you how to build multi-agent systems with Deep Agents.

How to train a new language model from scratch using Transformers and Tokenizers

Rust has been named Stack Overflow's Most Loved (now called Most Admired) language every year since our 1.0 release in 2015. That means people who use Rust want to keep using Rust1--and not just for performance-heavy stuff or embedded development, but for shell scripts, web apps, and all kinds of th

## What's Changed * Installing Ollama via the `curl` install script on macOS will now only prompt for your password if its required * Installing Ollama via the `iem` install script in Windows will now show progress * Image generation models will now respect the `OLLAMA_LOAD_TIMEOUT` variable *

### Patch Changes - fix: take into account `nodeName` case sensitivity on XHTML pages ([#17689](https://github.com/sveltejs/svelte/pull/17689)) - fix: render `multiple` and `selected` attributes as empty strings for XHTML compliance ([#17689](https://github.com/sveltejs/svelte/pull/17689)) -

Changes since langchain-core==1.2.11 release(core): 1.2.12 (#35192) fix(core): fix setting `ChatGeneration.text` (#35191)

Interactive image segmentation has become a defining mobile experience across the world’s most popular apps. In plain terms, you tap (or draw a rough hint) on an image, and the...

Google AI announcements from January

GPT‑5.3-Codex is the most capable agentic coding model to date, combining the frontier coding performance of GPT‑5.2-Codex with the reasoning and professional knowledge capabilities of GPT‑5.2.

Vue 3.6 is now entering beta phase as we have completed the intended feature set for Vapor Mode as outlined in the [roadmap](https://github.com/vuejs/core/issues/13687)! Vapor Mode now has feature parity with all stable features in Virtual DOM mode. Suspense is not supported in Vapor-only mode, but

Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/v8.0.0-beta.10/packages/vite/CHANGELOG.md) for details.

## New models * [GLM-5](https://ollama.com/library/glm-5): A strong reasoning and agentic model from Z.ai with 744B total parameters (40B active), built for complex systems engineering and long-horizon tasks. * [MiniMax-M2.5](https://ollama.com/library/minimax-m2.5): a new state-of-the-art large l

## [1.41.0](https://github.com/googleapis/js-genai/compare/v1.40.0...v1.41.0) (2026-02-10) ### Features * Add HTTP retry support to the SDK ([37d4f2e](https://github.com/googleapis/js-genai/commit/37d4f2e806793d71074eb0b763336b5c7132224b)) * Add INCOMPLETE status to Interaction. ([519f837](https:

The Rust team has published a new point release of Rust, 1.93.1. Rust is a programming language that is empowering everyone to build reliable and efficient software. If you have a previous version of Rust installed via rustup, getting Rust 1.93.1 is as easy as: rustup update stable If you don't hav

## [1.63.0](https://github.com/googleapis/python-genai/compare/v1.62.0...v1.63.0) (2026-02-11) ### Features * Add INCOMPLETE status to Interaction. ([1a84605](https://github.com/googleapis/python-genai/commit/1a84605bcac5445c8e13658b8bd7ff1860f10f1b)) * Support encryption_spec in tuning job creat

### Patch Changes - fix: resolve `effect_update_depth_exceeded` when using `bind:value` on `<select>` with derived state in legacy mode ([#17645](https://github.com/sveltejs/svelte/pull/17645)) - fix: don't swallow `DOMException` when `media.play()` fails in `bind:paused` ([#17656](https://git

### Patch Changes - [`c13b536`](https://github.com/withastro/astro/commit/c13b536197a70d8d4fd0037c5bd3aaa2be0598b9) Thanks [@matthewp](https://github.com/matthewp)! - Improves error page loading to read from disk first before falling back to configured host

### Patch Changes - [`c13b536`](https://github.com/withastro/astro/commit/c13b536197a70d8d4fd0037c5bd3aaa2be0598b9) Thanks [@matthewp](https://github.com/matthewp)! - Improves Host header handling for SSR deployments behind proxies

# Generated by Speakeasy CLI ## 2026-02-11 15:49:15 ### Changes Based on: - OpenAPI Doc 1.0.0 - Speakeasy CLI 1.685.0 (2.794.1) https://github.com/speakeasy-api/speakeasy ### Generated - [python v1.12.2] . ### Releases - [PyPI v1.12.2] https://pypi.org/project/mistralai/1.12.2 - . Publishing Comp

# Generated by Speakeasy CLI ## 2026-02-11 09:17:57 ### Changes Based on: - OpenAPI Doc 1.0.0 - Speakeasy CLI 1.685.0 (2.794.1) https://github.com/speakeasy-api/speakeasy ### Generated - [python v1.12.1] . ### Releases - [PyPI v1.12.1] https://pypi.org/project/mistralai/1.12.1 - . Publishing Comp

## What's changed - Improved terminal rendering performance - Fixed fatal errors being swallowed instead of displayed - Fixed process hanging after session close - Fixed character loss at terminal screen boundary - Fixed blank lines in verbose transcript view

Changes since langchain-core==1.2.10 release(core): 1.2.11 (#35144) fix(openai): sanitize urls when counting tokens in images (#35143) chore(core): clean up docstring mismatch and redundant logic in langchain-core (#35064) fix(core): replace bare except with Exception in tracer (#35138)

## 2.20.0 (2026-02-10) Full Changelog: [v2.19.0...v2.20.0](https://github.com/openai/openai-python/compare/v2.19.0...v2.20.0) ### Features * **api:** support for images in batch api ([28edb6e](https://github.com/openai/openai-python/commit/28edb6e1b7eb30dbb7be49979cee7882e8889264))

## 6.21.0 (2026-02-10) Full Changelog: [v6.20.0...v6.21.0](https://github.com/openai/openai-node/compare/v6.20.0...v6.21.0) ### Features * **api:** support for images in batch api ([017ba1c](https://github.com/openai/openai-node/commit/017ba1cb5a08428ca59197764cff460c70950e84))

## 2.19.0 (2026-02-10) Full Changelog: [v2.18.0...v2.19.0](https://github.com/openai/openai-python/compare/v2.18.0...v2.19.0) ### Features * **api:** skills and hosted shell ([27fdf68](https://github.com/openai/openai-python/commit/27fdf6820655b5994e3c1eddb3c8d9344a8be744)) ### Chores * **inte

## 6.20.0 (2026-02-10) Full Changelog: [v6.19.0...v6.20.0](https://github.com/openai/openai-node/compare/v6.19.0...v6.20.0) ### Features * **api:** skills and hosted shell ([e4bdd62](https://github.com/openai/openai-node/commit/e4bdd6205a0225d662ddeb07367f26094eaadbdd))

### 2.6.9 / 2026.02.10 - feat(doc): support markdown files (#32024) - feat(upgrade): ability to verify zip archive against checksum (#31804) - feat(upgrade): add context to error messages for better troubleshooting (#32018) - feat: Send reject-ack message through cron socket (#32035) - fix

Changes since langchain==1.2.9 release(langchain): 1.2.10 (#35137) chore(deps): bump the langchain-deps group across 3 directories with 40 updates (#35129) chore(deps): bump the langchain-deps group across 3 directories with 11 updates (#35121) fix(langchain): fix token counting on partial message

### Patch Changes - fix: render boolean attribute values as empty strings for XHTML compliance ([#17648](https://github.com/sveltejs/svelte/pull/17648)) - fix: prevent async render tag hydration mismatches ([#17652](https://github.com/sveltejs/svelte/pull/17652))

## What's changed - Fixed VS Code terminal scroll-to-top regression introduced in 2.1.37 - Fixed Tab key queueing slash commands instead of autocompleting - Fixed bash permission matching for commands using environment variable wrappers - Fixed text between tool uses disappearing when not using str

The Go Blog Testing Time (and other asynchronicities) In Go 1.24, we introduced the testing/synctest package as an experimental package. This package can significantly simplify writing tests for concurrent, asynchronous code. In Go 1.25, the testing/synctest package has graduated from experiment to

## 2.18.0 (2026-02-09) Full Changelog: [v2.17.0...v2.18.0](https://github.com/openai/openai-python/compare/v2.17.0...v2.18.0) ### Features * **api:** add context_management to responses ([137e992](https://github.com/openai/openai-python/commit/137e992b80956401d1867274fa7a0969edfdba54)) * **api:**

## 6.19.0 (2026-02-09) Full Changelog: [v6.18.0...v6.19.0](https://github.com/openai/openai-node/compare/v6.18.0...v6.19.0) ### Features * **api:** responses context_management ([40e7671](https://github.com/openai/openai-node/commit/40e7671675159966fe219b3aebfb24b9b03f2c95))

Deno 1.0

For stable releases, please refer to [CHANGELOG.md](https://github.com/vuejs/core/blob/main/CHANGELOG.md) for details. For pre-releases, please refer to [CHANGELOG.md](https://github.com/vuejs/core/blob/minor/CHANGELOG.md) of the `minor` branch.

Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/create-vite@8.3.0/packages/create-vite/CHANGELOG.md) for details.

Node.js v24.13.1

Node.js v25.6.1

## What's changed - Fixed an issue where /fast was not immediately available after enabling /extra-usage

## 0.79.0 (2026-02-07) Full Changelog: [v0.78.0...v0.79.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.78.0...v0.79.0) ### Features * **api:** enabling fast-mode in claude-opus-4-6 ([5953ba7](https://github.com/anthropics/anthropic-sdk-python/commit/5953ba7b425ba113595de570bc8c6

## What's changed - Fast mode is now available for Opus 4.6. Learn more at https://code.claude.com/docs/en/fast-mode

## 0.74.0 (2026-02-07) Full Changelog: [sdk-v0.73.0...sdk-v0.74.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.73.0...sdk-v0.74.0) ### Features * **api:** enabling fast-mode in claude-opus-4-6 ([e337981](https://github.com/anthropics/anthropic-sdk-typescript/commit/e3379

> 4.2.0 is the next minor release. ## 👀 Highlights We're excited to announce Nuxt 4.2, bringing new capabilities for better TypeScript DX, enhanced error handling, and improved control over data fetching! 🎉 ### 🎯 Abort Control for Data Fetching You can now use `AbortController` signal

## What's Changed * Fixed context limits when running `ollama launch droid` * `ollama launch` will now download missing models instead of erroring * Fixed bug where `ollama launch claude` would cause context compaction when providing images **Full Changelog**: https://github.com/ollama/ollama/

### Minor Changes - feat: allow use of createContext when instantiating components programmatically ([#17575](https://github.com/sveltejs/svelte/pull/17575)) ### Patch Changes - fix: ensure infinite effect loops are cleared after flushing ([#17601](https://github.com/sveltejs/svelte/pull/1760

## What's changed - Fixed a crash when agent teams setting changed between renders - Fixed a bug where commands excluded from sandboxing (via `sandbox.excludedCommands` or `dangerouslyDisableSandbox`) could bypass the Bash ask permission rule when `autoAllowBashIfSandboxed` was enabled

Changes since langchain==1.2.8 fix(langchain): normalize raw schemas in middleware response_format override (#35019) feat: support state updates from `wrap_model_call` with command(s) (#35033) test(langchain): types in `test_tool_call_limit` and `test_model_retry` (#34629) fix(langchain): bump min

## What's changed - Fixed agent teammate sessions in tmux to send and receive messages - Fixed warnings about agent teams not being available on your current plan - Added `TeammateIdle` and `TaskCompleted` hook events for multi-agent workflows - Added support for restricting which sub-agents can be

## 0.2.3 (2026-02-05) Full Changelog: [foundry-sdk-v0.2.2...foundry-sdk-v0.2.3](https://github.com/anthropics/anthropic-sdk-typescript/compare/foundry-sdk-v0.2.2...foundry-sdk-v0.2.3) ### Bug Fixes * **client:** avoid memory leak with abort signals ([53e47df](https://github.com/anthropics/anthrop

## 0.26.3 (2026-02-05) Full Changelog: [bedrock-sdk-v0.26.2...bedrock-sdk-v0.26.3](https://github.com/anthropics/anthropic-sdk-typescript/compare/bedrock-sdk-v0.26.2...bedrock-sdk-v0.26.3) ### Bug Fixes * **client:** avoid memory leak with abort signals ([53e47df](https://github.com/anthropics/an

## 0.14.3 (2026-02-05) Full Changelog: [vertex-sdk-v0.14.2...vertex-sdk-v0.14.3](https://github.com/anthropics/anthropic-sdk-typescript/compare/vertex-sdk-v0.14.2...vertex-sdk-v0.14.3) ### Bug Fixes * **client:** avoid memory leak with abort signals ([53e47df](https://github.com/anthropics/anthro

## 0.78.0 (2026-02-05) Full Changelog: [v0.77.1...v0.78.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.77.1...v0.78.0) ### Features * **api:** Release Claude Opus 4.6, adaptive thinking, and other features ([3ef1529](https://github.com/anthropics/anthropic-sdk-python/commit/3ef1

## 0.73.0 (2026-02-05) Full Changelog: [sdk-v0.72.1...sdk-v0.73.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.72.1...sdk-v0.73.0) ### Features * **api:** Release Claude Opus 4.6, adaptive thinking, and other features ([f741f92](https://github.com/anthropics/anthropic-sd

## What's changed - Claude Opus 4.6 is now available! - Added research preview agent teams feature for multi-agent collaboration (token-intensive feature, requires setting CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1) - Claude now automatically records and recalls memories as it works - Added "Summarize

## 6.18.0 (2026-02-05) Full Changelog: [v6.17.0...v6.18.0](https://github.com/openai/openai-node/compare/v6.17.0...v6.18.0) ### Features * **api:** image generation actions for responses; ResponseFunctionCallArgumentsDoneEvent.name ([d373c32](https://github.com/openai/openai-node/commit/d373c3210

## 2.17.0 (2026-02-05) Full Changelog: [v2.16.0...v2.17.0](https://github.com/openai/openai-python/compare/v2.16.0...v2.17.0) ### Features * **api:** add shell_call_output status field ([1bbaf88](https://github.com/openai/openai-python/commit/1bbaf8865000b338c24c9fdd5e985183feaca10f)) * **api:**

## New Model additions ### EXAONE-MoE <img width="2278" height="1142" alt="image" src="https://github.com/user-attachments/assets/0c3d5341-0483-49c3-8467-f9784ec94b37" /> K-EXAONE is a large-scale multilingual language model developed by LG AI Research. Built using a Mixture-of-Experts arch

The number of DDoS attacks more than doubled in 2025. The network layer is under particular threat as hyper-volumetric attacks grew 700%.

## [1.40.0](https://github.com/googleapis/js-genai/compare/v1.39.0...v1.40.0) (2026-02-04) ### Features

## [1.62.0](https://github.com/googleapis/python-genai/compare/v1.61.0...v1.62.0) (2026-02-04) ### Features ### Bug Fixes * Add error handling for live and live music APIs ([1148276](https://github.com/googleapis/python-genai/commit/114827682339fcc3c81543c008d9716b1a6b8401)), closes [#6

### Patch Changes - chore: remove SvelteKit data attributes from elements.d.ts ([#17613](https://github.com/sveltejs/svelte/pull/17613)) - fix: avoid erroneous async derived expressions for blocks ([#17604](https://github.com/sveltejs/svelte/pull/17604)) - fix: avoid Cloudflare warnings abo

# Generated by Speakeasy CLI ## 2026-02-04 14:44:36 ### Changes Based on: - OpenAPI Doc 1.0.0 - Speakeasy CLI 1.690.1 (2.797.1) https://github.com/speakeasy-api/speakeasy ### Generated - [typescript v1.14.0] . ### Releases - [NPM v1.14.0] https://www.npmjs.com/package/@mistralai/mistralai/v/1.14.0

## 0.77.1 (2026-02-03) Full Changelog: [v0.77.0...v0.77.1](https://github.com/anthropics/anthropic-sdk-python/compare/v0.77.0...v0.77.1) ### Bug Fixes * **structured outputs:** send structured output beta header when format is omitted ([#1158](https://github.com/anthropics/anthropic-sdk-python/is

## New models - [Qwen3-Coder-Next](https://ollama.com/library/qwen3-coder-next): a coding-focused language model from Alibaba's Qwen team, optimized for agentic coding workflows and local development. - [GLM-OCR](https://ollama.com/library/glm-ocr): GLM-OCR is a multimodal OCR model for complex do

What is the unsaid joy of local LLMs? The magic of downloading weights, running some experiments overnight, maybe your room gets a bit toasty, and voila, you create a small...

### 2.6.8 / 2026.02.02 - feat(npm): support `jsr:` scheme in package.json (#31938) - feat: Windows on ARM builds (#31917) - fix(ext/node): enable defensive option on `DatabaseSync` (#32004) - fix(ext/node): error formatting compatibility (#31970) - fix(ext/node): implement `sqlite`' `SQLTagSt

Node.js v25.6.0

## What's Changed * `ollama launch openclaw` will now enter the standard OpenClaw onboarding flow if this has not yet been completed. **Full Changelog**: https://github.com/ollama/ollama/compare/v0.15.3...v0.15.4

## What's Changed * Renamed `ollama launch clawdbot` to `ollama launch openclaw` to reflect the project's new name * Improved tool calling for Ministral models * docs: add clawdbot by @ParthSareen in https://github.com/ollama/ollama/pull/13925 * cmd/config: Use envconfig.Host() for base API in l

## [1.39.0](https://github.com/googleapis/js-genai/compare/v1.38.0...v1.39.0) (2026-01-30) ### Features * Add `include_input` query parameter to Get Interaction endpoint. ([84bc7f4](https://github.com/googleapis/js-genai/commit/84bc7f4d386da05a5e893cfe810b078451400a30)) * Add registerFiles for yo

We're excited to announce Astro as a new way to build static websites and deliver lightning-fast performance without sacrificing a modern developer experience.

## [1.61.0](https://github.com/googleapis/python-genai/compare/v1.60.0...v1.61.0) (2026-01-30) ### Features * Add `include_input` query parameter to Get Interaction endpoint. ([a0240d9](https://github.com/googleapis/python-genai/commit/a0240d9cf4c817d1737cb2cf818d405addabeed8)) * Add registerFile

### Patch Changes - fix: merge consecutive large text nodes ([#17587](https://github.com/sveltejs/svelte/pull/17587)) - fix: only create async functions in SSR output when necessary ([#17593](https://github.com/sveltejs/svelte/pull/17593)) - fix: properly separate multiline html blocks from

## 0.72.1 (2026-01-30) Full Changelog: [sdk-v0.72.0...sdk-v0.72.1](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.72.0...sdk-v0.72.1) ### Bug Fixes * **client:** remove OutputFormat exports from index.ts ([bf2cf08](https://github.com/anthropics/anthropic-sdk-typescript/comm

## 0.77.0 (2026-01-29) Full Changelog: [v0.76.0...v0.77.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.76.0...v0.77.0) ### Features * **api:** add support for Structured Outputs in the Messages API ([ad56677](https://github.com/anthropics/anthropic-sdk-python/commit/ad5667774ad2

## 0.2.2 (2026-01-29) Full Changelog: [foundry-sdk-v0.2.1...foundry-sdk-v0.2.2](https://github.com/anthropics/anthropic-sdk-typescript/compare/foundry-sdk-v0.2.1...foundry-sdk-v0.2.2) ### Chores * **internal:** version bump ([24ecc83](https://github.com/anthropics/anthropic-sdk-typescript/commit/

## 0.26.2 (2026-01-29) Full Changelog: [bedrock-sdk-v0.26.1...bedrock-sdk-v0.26.2](https://github.com/anthropics/anthropic-sdk-typescript/compare/bedrock-sdk-v0.26.1...bedrock-sdk-v0.26.2) ### Chores * **internal:** version bump ([24ecc83](https://github.com/anthropics/anthropic-sdk-typescript/co

## 0.14.2 (2026-01-29) Full Changelog: [vertex-sdk-v0.14.1...vertex-sdk-v0.14.2](https://github.com/anthropics/anthropic-sdk-typescript/compare/vertex-sdk-v0.14.1...vertex-sdk-v0.14.2) ### Chores * **internal:** version bump ([24ecc83](https://github.com/anthropics/anthropic-sdk-typescript/commit

## 0.72.0 (2026-01-29) Full Changelog: [sdk-v0.71.2...sdk-v0.72.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.71.2...sdk-v0.72.0) ### Features * **api:** add support for Structured Outputs in the Messages API ([eeb7fab](https://github.com/anthropics/anthropic-sdk-typesc

### 2.6.7 / 2026.01.29 - feat(ext/node): implement mock API for node:test module (#31954) - feat(node): implement `FileHandle.readv()` method (#31943) - feat(npm): use JSR for `@jsr` scope (#31925) - feat: External Socket-Based Cron Implementation (#31952) - feat: V8 14.5 (#31873) - feat: ad

## What's Changed * Update changelog by @Omar-V2 in https://github.com/xai-org/xai-sdk-python/pull/90 * Add Imagine image/video API support by @shawnthapa in https://github.com/xai-org/xai-sdk-python/pull/91 * Bump version from 1.6.0 to 1.6.1 by @shawnthapa in https://github.com/xai-org/xai-sdk-pyth

### Minor Changes - feat: allow passing `ShadowRootInit` object to custom element `shadow` option ([#17088](https://github.com/sveltejs/svelte/pull/17088)) ### Patch Changes - fix: throw for unset `createContext` get on the server ([#17580](https://github.com/sveltejs/svelte/pull/17580)) -

Introducing GPT-4.1 in the API—a new family of models with across-the-board improvements, including major gains in coding, instruction following, and long-context understanding. We’re also releasing our first nano model. Available to developers worldwide starting today.

## 6.17.0 (2026-01-28) Full Changelog: [v6.16.0...v6.17.0](https://github.com/openai/openai-node/compare/v6.16.0...v6.17.0) ### Features * **api:** add shell_call_output status field ([edf9590](https://github.com/openai/openai-node/commit/edf95904294cce6cdcac521ee75dc8e0a033df4c)) * **api:** api

# Generated by Speakeasy CLI [mistralai 1.11.1](https://pypi.org/project/mistralai/1.11.1) ## Python SDK Changes: * `mistral.beta.agents.list_versions()`: **Added** * `mistral.beta.agents.get_version()`: **Added** * `mistral.ocr.process()`: `request.document_annotation_prompt` **Added** Generated

### Pre-release Changes - Added `package.json` `exports`: - `remix/data-schema` to re-export APIs from `@remix-run/data-schema` - `remix/data-schema/checks` to re-export APIs from `@remix-run/data-schema/checks` - `remix/data-schema/coerce` to re-export APIs from `@remix-run/data-schema/coer

### Patch Changes - Bumped `@remix-run/*` dependencies: - [`@remix-run/fetch-router@0.16.0`](https://github.com/remix-run/remix/releases/tag/fetch-router@0.16.0)

### Patch Changes - Bumped `@remix-run/*` dependencies: - [`fetch-router@0.17.0`](https://github.com/remix-run/remix/releases/tag/fetch-router@0.17.0)

### Patch Changes - Bumped `@remix-run/*` dependencies: - [`@remix-run/fetch-router@0.16.0`](https://github.com/remix-run/remix/releases/tag/fetch-router@0.16.0)

### Minor Changes - Bump multipart-parser dependency to 0.14.2

### Minor Changes - BREAKING CHANGE: Remove `Router.size` property `Matcher`s no longer keep track of size, so `Router` cannot wrap `Matcher.size` anymore. ### Patch Changes - Bumped `@remix-run/*` dependencies: - [`@remix-run/route-pattern@0.18.0`](https://github.com/remix-run/remix/release

### Minor Changes - BREAKING CHANGE: Remove `createHrefBuilder`, `type HrefBuilder`, `type HrefBuilderArg` `createHrefBuilder` was the original design and implementation of href generation, but with the new `RoutePattern.href` method it is now obsolete. Use `HrefArgs` instead of `HrefBuilde

### Minor Changes - BREAKING CHANGE: Removed `onError` option from `createContainer`. Errors thrown in event listeners now dispatch an `ErrorEvent` on the target element with `bubbles: true`, allowing them to propagate up the DOM tree. Also removed the `raise` method from the `Interaction` interfac

## 2.16.0 (2026-01-27) Full Changelog: [v2.15.0...v2.16.0](https://github.com/openai/openai-python/compare/v2.15.0...v2.16.0) ### Features * **api:** api update ([b97f9f2](https://github.com/openai/openai-python/commit/b97f9f26b9c46ca4519130e60a8bf12ad8d52bf3)) * **api:** api updates ([9debcc0](h

### 2.5.7 / 2026.01.27 - fix: deno cross compile for intel mac target (#31714) - fix: fetch fd leak (#31375) - fix(bundle): avoid name clash in hack (#31409) - fix(bundle): do not error on failing to clean up esbuild dir (#31408) - fix(bundle): fix import.meta.main transform with jsr entrypoi

## What's Changed * Add user-location support for web-search tool by @mark-xai in https://github.com/xai-org/xai-sdk-python/pull/80 * Add `tool_call_id` field by @mark-xai in https://github.com/xai-org/xai-sdk-python/pull/81 * Add `developer` role by @mark-xai in https://github.com/xai-org/xai-sdk-p

<img width="1916" height="976" alt="Ollama screenshot 2026-01-26 at 17 53 40@2x (1)" src="https://github.com/user-attachments/assets/7937e607-e16e-46f5-a280-5cf9ce088a68" /> ## What's Changed * New `ollama launch clawdbot` command for launching Clawdbot using Ollama models **Full Changelo

## React Server Components - Add more DoS mitigations to Server Actions, and harden Server Components ([#35632](https://github.com/facebook/react/pull/35632) by @gnoff, @lubieowoce, @sebmarkbage, @unstubbable)

## React Server Components - Add more DoS mitigations to Server Actions, and harden Server Components ([#35632](https://github.com/facebook/react/pull/35632) by @gnoff, @lubieowoce, @sebmarkbage, @unstubbable)

## React Server Components - Add more DoS mitigations to Server Actions, and harden Server Components ([#35632](https://github.com/facebook/react/pull/35632) by @gnoff, @lubieowoce, @sebmarkbage, @unstubbable)

## Transformers v5 release notes <img width="1800" height="1013" alt="image" src="https://github.com/user-attachments/assets/7b5187d7-6945-4108-a546-6d1d7bfb55e3" /> - Highlights - Significant API changes: dynamic weight loading, tokenization - Backwards Incompatible Changes - Bugfixes and

## Transformers v5 release notes <img width="1800" height="1013" alt="image" src="https://github.com/user-attachments/assets/7b5187d7-6945-4108-a546-6d1d7bfb55e3" /> - Highlights - Significant API changes: dynamic weight loading, tokenization - Backwards Incompatible Changes - Bugfixes and

Node.js v25.5.0

## What's Changed * GLM-4.7-Flash performance and correctness improvements, fixing repetitive answers and tool calling quality * Fixed performance issues on macOS and arm64 Linux * Fixed issue where `ollama launch` would not detect `claude` and would incorrectly update `opencode` configurations

### 2.6.6 / 2026.01.22 - feat(cli/tsc): show progress bar for TSGO downloads (#31893) - feat(inspector): accept bare host and bare port for --inspect flag (#31881) - feat(inspector/unstable): add /ws/events endpoint in inspector server, notify watcher restart event in it (#31901) - feat(tas

# Generated by Speakeasy CLI [@mistralai/mistralai 1.13.0](https://www.npmjs.com/package/@mistralai/mistralai/v/1.13.0) ## Typescript SDK Changes: * `mistral.beta.agents.listVersions()`: **Added** * `mistral.beta.agents.getVersion()`: **Added** * `mistral.ocr.process()`: * `request.documentAnnot

The Rust team is happy to announce a new version of Rust, 1.93.0. Rust is a programming language empowering everyone to build reliable and efficient software. If you have a previous version of Rust installed via rustup, you can get 1.93.0 with: $ rustup update stable If you don't have it already, y

<img width="4502" height="2222" alt="An image of Ollama building rapidly on the computer. Build with Ollama!" src="https://github.com/user-attachments/assets/0810fb5c-6727-400a-b711-4ffc349d0bb5" /> ## `ollama launch` A new `ollama launch` command to use Ollama's models with Claude Code, Codex

## [1.60.0](https://github.com/googleapis/python-genai/compare/v1.59.0...v1.60.0) (2026-01-21) ### Features * Add ModelArmorConfig support for prompt and response sanitization via the Model Armor service ([8d1091a](https://github.com/googleapis/python-genai/commit/8d1091a7e8d8eef774984ff2202

We are excited to announce the release of PyTorch® 2.10 (release notes)! This release features a number of improvements for performance and numerical debugging. Performance has been a focus for...

## [1.38.0](https://github.com/googleapis/js-genai/compare/v1.37.0...v1.38.0) (2026-01-20) ### Features * Add ModelArmorConfig support for prompt and response sanitization via the Model Armor service ([be65c24](https://github.com/googleapis/js-genai/commit/be65c2431d070bd19642623c97effccf4161f9a2

# Generated by Speakeasy CLI ## 2026-01-20 16:24:49 ### Changes Based on: - OpenAPI Doc 1.0.0 - Speakeasy CLI 1.690.1 (2.797.1) https://github.com/speakeasy-api/speakeasy ### Generated - [typescript v1.7.0] packages/mistralai-azure ### Releases - [NPM v1.7.0] https://www.npmjs.com/package/@mistral

# Generated by Speakeasy CLI ## 2026-02-04 14:49:15 ### Changes Based on: - OpenAPI Doc 1.0.0 - Speakeasy CLI 1.685.0 (2.794.1) https://github.com/speakeasy-api/speakeasy ### Generated - [python v1.12.0] . ### Releases - [PyPI v1.12.0] https://pypi.org/project/mistralai/1.12.0 - . Publishing Comp

For stable releases, please refer to [CHANGELOG.md](https://github.com/vuejs/core/blob/main/CHANGELOG.md) for details. For pre-releases, please refer to [CHANGELOG.md](https://github.com/vuejs/core/blob/minor/CHANGELOG.md) of the `minor` branch.

Node.js v25.4.0

## What's Changed Another fix for qwen vl models that prevented correctly loading the associated model type - this works together with https://github.com/huggingface/transformers/pull/41808 of the previous patch release. * Fixed incorrect model_type for qwen2vl and qwen2.5vl when config is saved

## [1.37.0](https://github.com/googleapis/js-genai/compare/v1.36.0...v1.37.0) (2026-01-15) ### Features * Support 4:5 and 5:4 aspect ratio in Interactions ([5294da2](https://github.com/googleapis/js-genai/commit/5294da273cbc9a206cd58544b42d1de70500a7a9))

## [1.59.0](https://github.com/googleapis/python-genai/compare/v1.58.0...v1.59.0) (2026-01-15) ### Features * Set the environment variable GOOGLE_API_PREVENT_AGENT_TOKEN_SHARING_FOR_GCP_SERVICES to 'false' within BaseApiClient to disable bound token sharing. ([79ac880](https://github.com/googleap

# Generated by Speakeasy CLI [mistralai 1.10.1](https://pypi.org/project/mistralai/1.10.1) ## SDK Changes Detected: * `mistral.beta.conversations.restart()`: * `request.inputs.[array].[]` **Changed** **Breaking** :warning: * `response.outputs.[].[message_output_entry].content.[array].[]` **Ch

### 2.6.5 / 2026.01.15 - feat(ext/canvas): support gif, webp for `createImageBitmap` (#31402) - feat(ext/web): add performance.clearResourceTimings() and setResourceTimingBufferSize() (#31603) - feat(node/fs): implement FileHandle.readableWebStream() (#31745) - fix(audit): respect --level f

## [1.58.0](https://github.com/googleapis/python-genai/compare/v1.57.0...v1.58.0) (2026-01-14) ### Features * Add FileSearchCallContent to Interactions ([a882dea](https://github.com/googleapis/python-genai/commit/a882deab12a03d9390e2dd83243afc767e78c789)) * Add ImageConfig to GenerationConfig for

## [1.36.0](https://github.com/googleapis/js-genai/compare/v1.35.0...v1.36.0) (2026-01-14) ### Features * Add FileSearchCallContent to Interactions ([ccf11a4](https://github.com/googleapis/js-genai/commit/ccf11a463f3364683b7c39ffec9670f77bcc16dc)) * Add ImageConfig to GenerationConfig for image g

## 0.76.0 (2026-01-13) Full Changelog: [v0.75.0...v0.76.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.75.0...v0.76.0) ### Features * allow raw JSON schema to be passed to messages.stream() ([955c61d](https://github.com/anthropics/anthropic-sdk-python/commit/955c61dd5aae4c8a2c7b

## What's Changed Should not have said last patch :wink: These should be the last remaining fixes that got lost in between patches and the transition to v5. * QwenVL: add skipped keys in setattr as well by @zucchini-nlp in https://github.com/huggingface/transformers/pull/41808 * Fix lr_schedul

## What's Changed Last patch release for v4: We have a few small fixes for remote generation methods (e.g. group beam search), vLLM, and an offline tokenizer fix (if it's already been cached). * Grouped beam search from config params by @zucchini-nlp in https://github.com/huggingface/transformer

Node.js v24.13.0

Node.js v25.3.0

## 6.16.0 (2026-01-09) Full Changelog: [v6.15.0...v6.16.0](https://github.com/openai/openai-node/compare/v6.15.0...v6.16.0) ### Features * **api:** add new Response completed_at prop ([ca40534](https://github.com/openai/openai-node/commit/ca40534778311def52bc7dbbab043d925cdaf847)) * **ci:** add b

## 2.15.0 (2026-01-09) Full Changelog: [v2.14.0...v2.15.0](https://github.com/openai/openai-python/compare/v2.14.0...v2.15.0) ### Features * **api:** add new Response completed_at prop ([f077752](https://github.com/openai/openai-python/commit/f077752f4a8364a74f784f8fb1cbe31277e1762b)) ### Chore

## [1.35.0](https://github.com/googleapis/js-genai/compare/v1.34.0...v1.35.0) (2026-01-07) ### Features * [Python] add RegisterFiles so gcs files can be used with genai. ([1bf555c](https://github.com/googleapis/js-genai/commit/1bf555c38e5001f147e29db16c1141653ec252d4)) * Add PersonGeneration to I

## [1.57.0](https://github.com/googleapis/python-genai/compare/v1.56.0...v1.57.0) (2026-01-07) ### Features * [Python] add RegisterFiles so gcs files can be used with genai. ([68fa075](https://github.com/googleapis/python-genai/commit/68fa0754290bcbd84c1c34806eedfdad28890921)) * Add gemini-3-pro-

We’re upgrading the GPT-5 series with warmer, more capable models and new ways to customize ChatGPT’s tone and style. GPT-5.1 starts rolling out today to paid users.

### 2.6.4 / 2026.01.05 - fix(compile): make compile work with `--unstable-npm-lazy-caching` (#31704) - fix(ext/node): enable keepAlive connection reuse for HTTP Agent (#31709) - fix(ext/node): handle errors in sqlite session filter callback (#31756) - fix(ext/node): support TypedArray and Data

### 2.6.3 / 2025.12.20 - fix(check): improve node types handling - Revert "fix(ext/node): stub out Module.register and Module.registerHooks" (#31684)

### 2.6.2 / 2025.12.19 - feat(unstable): add sandbox subcommand (#31568) - fix(audit): fix deserde for transitive npm audit actions (#31671) - fix(check): handle workspace members having different jsx import sources and importing each other (#31654) - fix(check): regression with tsgo and no

## 6.15.0 (2025-12-19) Full Changelog: [v6.14.0...v6.15.0](https://github.com/openai/openai-node/compare/v6.14.0...v6.15.0) ### Bug Fixes * rebuild ([5627b41](https://github.com/openai/openai-node/commit/5627b4181775981e48991ea246e091afdfdc3caf))

## 2.14.0 (2025-12-19) Full Changelog: [v2.13.0...v2.14.0](https://github.com/openai/openai-python/compare/v2.13.0...v2.14.0) ### Features * **api:** slugs for new audio models; make all `model` params accept strings ([e517792](https://github.com/openai/openai-python/commit/e517792b58d1768cfb3432

For stable releases, please refer to [CHANGELOG.md](https://github.com/vuejs/core/blob/main/CHANGELOG.md) for details. For pre-releases, please refer to [CHANGELOG.md](https://github.com/vuejs/core/blob/minor/CHANGELOG.md) of the `minor` branch.

# Generated by Speakeasy CLI [@mistralai/mistralai 1.11.0](https://www.npmjs.com/package/@mistralai/mistralai/v/1.11.0) ## SDK Changes Detected: * `mistral.beta.libraries.create()`: `response.owner_id` **Changed** **Breaking** :warning: * `mistral.beta.libraries.documents.get()`: `response` **Chan

## [1.34.0](https://github.com/googleapis/js-genai/compare/v1.33.0...v1.34.0) (2025-12-16) ### Features * Add minimal and medium thinking levels. ([19f8969](https://github.com/googleapis/js-genai/commit/19f8969f0cd9f423b10384d91a4ea8396a791d01)) * Add support for Struct in ToolResult Content. ([7

## [1.56.0](https://github.com/googleapis/python-genai/compare/v1.55.0...v1.56.0) (2025-12-16) ### Features * Add minimal and medium thinking levels. ([96d644c](https://github.com/googleapis/python-genai/commit/96d644cd52a300063040c6d7bf70e2939b735e6f)) * Add support for Struct in ToolResult Cont

## 6.14.0 (2025-12-16) Full Changelog: [v6.13.0...v6.14.0](https://github.com/openai/openai-node/compare/v6.13.0...v6.14.0) ### Features * **api:** gpt-image-1.5 ([6c1ac1d](https://github.com/openai/openai-node/commit/6c1ac1d8a2947c59f38aabaf07795a244c45a688))

## 2.13.0 (2025-12-16) Full Changelog: [v2.12.0...v2.13.0](https://github.com/openai/openai-python/compare/v2.12.0...v2.13.0) ### Features * **api:** gpt-image-1.5 ([1c88f03](https://github.com/openai/openai-python/commit/1c88f03bb48aa67426744e5b74f6197f30f61c73)) ### Chores * **ci:** add CI j

### 2.6.1 / 2025.12.15 - feat(unstable): deploy config allow app to be optional (#31567) - fix(add): include type-only imports when building graph (#31552) - fix(cli): add streams as transferable types (#31586) - fix(compile): intel mac compile fix (#31575) - fix(compile): sentinal conflict w

## 6.13.0 (2025-12-15) Full Changelog: [v6.12.0...v6.13.0](https://github.com/openai/openai-node/compare/v6.12.0...v6.13.0) ### Features * **api:** api update ([bc759dc](https://github.com/openai/openai-node/commit/bc759dc39518412b58b2ebf7e57758776971ce15)) * **api:** fix grader input list, add d

## 2.12.0 (2025-12-15) Full Changelog: [v2.11.0...v2.12.0](https://github.com/openai/openai-python/compare/v2.11.0...v2.12.0) ### Features * **api:** api update ([a95c4d0](https://github.com/openai/openai-python/commit/a95c4d0952ff5eb767206574e687cb029a49a4ab)) * **api:** fix grader input list, a

## React Server Components - Add extra loop protection to React Server Functions (@sebmarkbage [#35351](https://github.com/facebook/react/pull/35351))

## React Server Components - Add extra loop protection to React Server Functions (@sebmarkbage [#35351](https://github.com/facebook/react/pull/35351))

## React Server Components - Add extra loop protection to React Server Functions (@sebmarkbage [#35351](https://github.com/facebook/react/pull/35351))

## React Server Components - Patch Promise cycles and toString on Server Functions (@sebmarkbage, @unstubbable [#35289](https://github.com/facebook/react/pull/35289), [#35345](https://github.com/facebook/react/pull/35345))

## React Server Components - Move `react-server-dom-webpack/*.unbundled` to private `react-server-dom-unbundled` (@eps1lon [#35290](https://github.com/facebook/react/pull/35290)) - Patch Promise cycles and toString on Server Functions (@sebmarkbage, @unstubbable [#35289](https://github.com/faceb

## React Server Components - Move `react-server-dom-webpack/*.unbundled` to private `react-server-dom-unbundled` (@eps1lon https://github.com/facebook/react/pull/35290) - Patch Promise cycles and toString on Server Functions (@sebmarkbage, @unstubbable [#35289](https://github.com/facebook/react/

### Fixed - Ensure validation of `source(…)` happens relative to the file it is in ([#19274](https://github.com/tailwindlabs/tailwindcss/pull/19274)) - Include filename and line numbers in CSS parse errors ([#19282](https://github.com/tailwindlabs/tailwindcss/pull/19282)) - Skip comments in Rub

## [1.33.0](https://github.com/googleapis/js-genai/compare/v1.32.0...v1.33.0) (2025-12-11) ### Features * Add IMAGE_RECITATION and IMAGE_OTHER enum values to FinishReason ([ab87f51](https://github.com/googleapis/js-genai/commit/ab87f51b8b2f0109d3ea89a18987c49101adfd70)) * Add voice activity detec

## [1.55.0](https://github.com/googleapis/python-genai/compare/v1.54.0...v1.55.0) (2025-12-11) ### Features * Add the Interactions API ([836a3](https://github.com/googleapis/python-genai/commit/836a33c93f26f56349758ca22e59b8e46962dad4)) * Add enableEnhancedCivicAnswers feature in GenerateContentC

The Rust team is happy to announce a new version of Rust, 1.92.0. Rust is a programming language empowering everyone to build reliable and efficient software. If you have a previous version of Rust installed via rustup, you can get 1.92.0 with: $ rustup update stable If you don't have it already, y

2020 has been a long year. As it comes to an end we wanted to share a special Holiday Update on our research into zero-bundle-size React Server Components.

### Fixed - Don’t break `sibling-*()` functions when used inside `calc(…)` ([#19335](https://github.com/tailwindlabs/tailwindcss/pull/19335))

Node.js v24.12.0

## What's Changed * Add `end_index`, rename document search tools, and add `verbose_streaming` include option by @shawnthapa in https://github.com/xai-org/xai-sdk-python/pull/71 * Add inline citations support to Chunk and Response classes by @Omar-V2 in https://github.com/xai-org/xai-sdk-python/pull

## React Server Components - Bring React Server Component fixes to Server Actions (@sebmarkbage [#35277](https://github.com/facebook/react/pull/35277))

## What's Changed * Update changelog following the v.1.4.0 release by @Omar-V2 in https://github.com/xai-org/xai-sdk-python/pull/63 * Update the metadata sent on requests to also include the language by @Omar-V2 in https://github.com/xai-org/xai-sdk-python/pull/62 * Update proto definitions to inclu

## 0.75.0 (2025-11-24) Full Changelog: [v0.74.1...v0.75.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.74.1...v0.75.0) ### Features * **api:** adds support for Claude Opus 4.5, Effort, Advance Tool Use Features, Autocompaction, and Computer Use v5 ([5c3e633](https://github.com/a

## 0.74.1 (2025-11-19) Full Changelog: [v0.74.0...v0.74.1](https://github.com/anthropics/anthropic-sdk-python/compare/v0.74.0...v0.74.1) ### Bug Fixes * **structured outputs:** use correct beta header ([e90d347](https://github.com/anthropics/anthropic-sdk-python/commit/e90d347dfd80adc5ae2a412ebfe

## 0.74.0 (2025-11-18) Full Changelog: [v0.73.0...v0.74.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.73.0...v0.74.0) ### Features * add Foundry SDK ([3ae9e45](https://github.com/anthropics/anthropic-sdk-python/commit/3ae9e45451d3ff85b25ba5f5f9f8786ea35e3cc9)) ### Bug Fixes

Node.js v25.2.1

## 0.73.0 (2025-11-14) Full Changelog: [v0.72.1...v0.73.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.72.1...v0.73.0) ### Features * **api:** add support for structured outputs beta ([688da81](https://github.com/anthropics/anthropic-sdk-python/commit/688da8126df8a304c5f01f0dc63

## 0.72.1 (2025-11-11) Full Changelog: [v0.72.0...v0.72.1](https://github.com/anthropics/anthropic-sdk-python/compare/v0.72.0...v0.72.1) ### Bug Fixes * **client:** close streams without requiring full consumption ([109b771](https://github.com/anthropics/anthropic-sdk-python/commit/109b77175c844c

Node.js v25.2.0

Node.js v24.11.1

## What's Changed * Add xai-sdk-version to the request metadata by @mark-xai in https://github.com/xai-org/xai-sdk-python/pull/41 * Remove double await in async interceptor by @Omar-V2 in https://github.com/xai-org/xai-sdk-python/pull/42 * Add context manager support and proper channel cleanup to cl

### Fixed - Substitute `@variant` inside legacy JS APIs ([#19263](https://github.com/tailwindlabs/tailwindcss/pull/19263)) - Prevent occasional crash on Windows when loaded into a worker thread ([#19242](https://github.com/tailwindlabs/tailwindcss/pull/19242))

Learn what's new in CSS Colors Module Level 4, including color spaces, color functions, fancy gradients, and support for wide-gamut displays.

Granite 4.0 Nano: Just how small can you go?

Node.js v24.11.0

Node.js v25.1.0

Swift Transformers Reaches 1.0 – and Looks to the Future

LeRobot v0.4.0: Supercharging OSS Robot Learning

### Fixed - Discard candidates with an empty data type ([#19172](https://github.com/tailwindlabs/tailwindcss/pull/19172)) - Fix canonicalization of arbitrary variants with attribute selectors ([#19176](https://github.com/tailwindlabs/tailwindcss/pull/19176)) - Fix invalid colors due to nested `

### Fixed - Fix Safari devtools rendering issue due to `color-mix` fallback ([#19069](https://github.com/tailwindlabs/tailwindcss/pull/19069)) - Suppress Lightning CSS warnings about `:deep`, `:slotted`, and `:global` ([#19094](https://github.com/tailwindlabs/tailwindcss/pull/19094)) - Fix reso

## What's Changed * Support multiple outputs in chunk and response of chat service by @mark-xai in https://github.com/xai-org/xai-sdk-python/pull/39 * Bump version from v1.3.0 -> v.1.3.1 by @Omar-V2 in https://github.com/xai-org/xai-sdk-python/pull/40 ## New Contributors * @mark-xai made their firs

We are introducing AutoPatchBench, a benchmark for the automated repair of vulnerabilities identified through fuzzing. By providing a standardized benchmark, AutoPatchBench enables researchers and practitioners to objectively evaluate and compare the effectiveness of various AI program repair system

## What's Changed * Update changelog by @Omar-V2 in https://github.com/xai-org/xai-sdk-python/pull/31 * Add proto support for server side tools by @Omar-V2 in https://github.com/xai-org/xai-sdk-python/pull/32 * Bump version from v1.2.0 -> v1.3.0a0 by @Omar-V2 in https://github.com/xai-org/xai-sdk-py

Node.js v25.0.0

Node.js v24.10.0

# Generated by Speakeasy CLI ## 2025-10-02 15:52:34 ### Changes Based on: - OpenAPI Doc 1.0.0 - Speakeasy CLI 1.606.10 (2.687.13) https://github.com/speakeasy-api/speakeasy ### Generated - [python v1.9.11] . ### Releases - [PyPI v1.9.11] https://pypi.org/project/mistralai/1.9.11 - . Publishing Co

Note: this tag was recreated to point at the correct commit. The npm package contained the correct content. For release notes, check out the [release announcement](https://devblogs.microsoft.com/typescript/announcing-typescript-5-9-beta/). * [fixed issues query for Typescript 5.9.0 (Beta)](htt

Note: this tag was recreated to point at the correct commit. The npm package contained the correct content. For release notes, check out the [release announcement](https://devblogs.microsoft.com/typescript/announcing-typescript-5-8/). * [fixed issues query for Typescript 5.8.0 (Beta)](https://

Note: this tag was recreated to point at the correct commit. The npm package contained the correct content. For release notes, check out the [release announcement](https://devblogs.microsoft.com/typescript/announcing-typescript-5-9/) * [fixed issues query for Typescript 5.9.0 (Beta)](https://g

### Fixed - Handle `'` syntax in ClojureScript when extracting classes ([#18888](https://github.com/tailwindlabs/tailwindcss/pull/18888)) - Handle `@variant` inside `@custom-variant` ([#18885](https://github.com/tailwindlabs/tailwindcss/pull/18885)) - Merge suggestions when using `@utility` ([#

### Fixed - Improve support for raw `supports-[…]` queries in arbitrary values ([#13605](https://github.com/tailwindlabs/tailwindcss/pull/13605)) - Fix `require.cache` error when loaded through a TypeScript file in Node 22.18+ ([#18665](https://github.com/tailwindlabs/tailwindcss/pull/18665)) -

## What's Changed * Update changelog by @Omar-V2 in https://github.com/xai-org/xai-sdk-python/pull/26 * Add SDK support for the Collections API by @Omar-V2 in https://github.com/xai-org/xai-sdk-python/pull/28 * Add support for the stateful chat API by @Omar-V2 in https://github.com/xai-org/xai-sdk-p

Gradio 3.0 is Out!