Vista cronológica de todos los releases por año
## 2.43.0 (2026-06-17) Full Changelog: [v2.42.0...v2.43.0](https://github.com/openai/openai-python/compare/v2.42.0...v2.43.0) ### Features * **api:** update OpenAPI spec or Stainless config ([2254235](https://github.com/openai/openai-python/commit/22542358490ef8f31f0d373e17f7b791b3d983ca))
## 6.44.0 (2026-06-17) Full Changelog: [v6.43.0...v6.44.0](https://github.com/openai/openai-node/compare/v6.43.0...v6.44.0) ### Features * **api:** update OpenAPI spec or Stainless config ([d05bdbc](https://github.com/openai/openai-node/commit/d05bdbc70b24c2970cf6b583d54529601e5442d8))
## What's Changed * models: add Cohere2MoE model by @jmorganca in https://github.com/ollama/ollama/pull/16670 * llama: update llama.cpp to b9672 by @pdevine in https://github.com/ollama/ollama/pull/16775 **Full Changelog**: https://github.com/ollama/ollama/compare/v0.30.9...v0.30.10-rc0
### Patch Changes - [#17109](https://github.com/withastro/astro/pull/17109) [`27c80ea`](https://github.com/withastro/astro/commit/27c80ea92248993e5fce94b2c26d87d611ab6785) Thanks [@ematipico](https://github.com/ematipico)! - Harden the limits on the number of decoding on the URL.
# Generated by Speakeasy CLI ## 2026-06-17 12:47:32 ### Changes Based on: - OpenAPI Doc - Speakeasy CLI 1.763.6 (2.884.13) https://github.com/speakeasy-api/speakeasy ### Generated - [python v2.4.12] . ### Releases - [PyPI v2.4.12] https://pypi.org/project/mistralai/2.4.12 - . Publishing Complete
## 2.42.0 (2026-06-16) Full Changelog: [v2.41.1...v2.42.0](https://github.com/openai/openai-python/compare/v2.41.1...v2.42.0) ### Features * **api:** admin spend_alerts ([6134198](https://github.com/openai/openai-python/commit/6134198a488996c4ff6fca4551afd55fb3294fdc)) * **api:** manual updates (
## 6.43.0 (2026-06-16) Full Changelog: [v6.42.0...v6.43.0](https://github.com/openai/openai-node/compare/v6.42.0...v6.43.0) ### Bug Fixes * fix TS to use `main` ([dc5078b](https://github.com/openai/openai-node/commit/dc5078bcb03c9192c36e5d34a7fc597592220c6a)) * restore pnpm repo configuration on
## What's changed - Fixed mid-stream connection drops: partial responses are now preserved instead of showing a raw error, and the spinner no longer gets stuck at "running tool" - Fixed mouse-wheel scrolling in WSL2 under Windows Terminal and VS Code (regression in 2.1.172) - Fixed a sandbox `denyR
# Generated by Speakeasy CLI ## 2026-06-16 13:00:09 ### Changes Based on: - OpenAPI Doc - Speakeasy CLI 1.763.6 (2.884.13) https://github.com/speakeasy-api/speakeasy ### Generated - [python v2.4.11] . ### Releases - [PyPI v2.4.11] https://pypi.org/project/mistralai/2.4.11 - . Publishing Complete
# Generated by Speakeasy CLI ## 2026-06-15 12:58:44 ### Changes Based on: - OpenAPI Doc - Speakeasy CLI 1.763.6 (2.884.13) https://github.com/speakeasy-api/speakeasy ### Generated - [typescript v2.2.6] . ### Releases - [NPM v2.2.6] https://www.npmjs.com/package/@mistralai/mistralai/v/2.2.6 - . P
# Generated by Speakeasy CLI ## 2026-06-15 12:49:25 ### Changes Based on: - OpenAPI Doc - Speakeasy CLI 1.763.6 (2.884.13) https://github.com/speakeasy-api/speakeasy ### Generated - [python v2.4.10] . ### Releases - [PyPI v2.4.10] https://pypi.org/project/mistralai/2.4.10 - . Publishing Complete
## [2.9.0-rc0](https://github.com/googleapis/python-genai/compare/v2.8.0...v2.9.0-rc0) (2026-06-16) ### Major updates * The interactions implementation has been completely replaced. The public api surface should be unchanged. ([d830f16](https://github.com/googleapis/python-genai/commit/d830f165d2
## What's changed - Added `Tool(param:value)` syntax for permission rules to match a tool's input parameters (with `*` wildcard), e.g. `Agent(model:opus)` to block Opus subagents - Skills in nested `.claude/skills` directories now load when working on files there; on a name clash, the nested skill
## What's Changed * Support for Cohere2Moe architecture * Fixed LFM2 parser/render for cases where thinking was not emitted * Fixed issue where `ollama launch claude` and other coding agent or assistant use cases would only output one token * Ollama will now return an error if a single message i
## 0.109.2 (2026-06-15) Full Changelog: [v0.109.1...v0.109.2](https://github.com/anthropics/anthropic-sdk-python/compare/v0.109.1...v0.109.2) ### Chores * **api:** remove retired models from API and SDKs ([d4bcfcc](https://github.com/anthropics/anthropic-sdk-python/commit/d4bcfcc257bd0c97d5e75060
## 0.104.2 (2026-06-15) Full Changelog: [sdk-v0.104.1...sdk-v0.104.2](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.104.1...sdk-v0.104.2) ### Chores * **api:** remove retired models from API and SDKs ([a942876](https://github.com/anthropics/anthropic-sdk-typescript/commit/
### Patch Changes - [#17035](https://github.com/withastro/astro/pull/17035) [`197e50e`](https://github.com/withastro/astro/commit/197e50e2e37168a9b9e8a014c13d1308b2220ca1) Thanks [@astrobot-houston](https://github.com/astrobot-houston)! - Fixes `getRelativeLocaleUrl`, `getAbsoluteLocaleUrl`, and
Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/plugin-legacy@8.1.0-beta.0/packages/plugin-legacy/CHANGELOG.md) for details.
## What's changed - Session titles are now generated in the language of your conversation (set the `language` setting to pin a specific language) - Added `footerLinksRegexes` setting for regex-matched link badges in the footer row, configurable via user or managed settings - Improved Bedrock creden
### Added - Add `--silent` option to suppress output in `@tailwindcss/cli` ([#20100](https://github.com/tailwindlabs/tailwindcss/pull/20100)) ### Fixed - Remove deprecation warnings by using `Module#registerHooks` instead of `Module#register` on Node 26+ ([#20028](https://github.com/tailwin
## What's Changed * Fixed `ollama launch` selecting the wrong provider in some cases * Improved prompt caching by decoupling it from context shift for better KV cache reuse * More stable MLX inference with hardened linear and embedding layers * MLX runner now creates snapshots during prompt proc
## What's changed - Added `enforceAvailableModels` managed setting — when enabled, the `availableModels` allowlist also constrains the Default model (a Default that would resolve to a disallowed model now falls back to the first allowed model), and user or project settings can no longer widen a man
## What's Changed * feat: add service_tier support for priority processing by @double-di in https://github.com/xai-org/xai-sdk-python/pull/163 * chore: bump version to 1.17.0 by @double-di in https://github.com/xai-org/xai-sdk-python/pull/165 **Full Changelog**: https://github.com/xai-org/xai-sdk-
## What's changed - Added `wheelScrollAccelerationEnabled` setting to disable mouse-wheel scroll acceleration in fullscreen mode - Fixed the `/model` picker hiding the model family that Default resolves to — Opus now appears as its own row on Max/Team Premium/Enterprise plans, Sonnet on Pro/Team pl
### 2.8.3 / 2026.06.11 - feat(cli): suggest DENO_TLS_CA_STORE on untrusted TLS certificate (#34756) - feat(cli): support --env-file in dependency and registry subcommands (#34843) - feat(compile): support watch mode (#34860) - feat(config): support globs in links (#34849) - feat(ext/crypto):
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.
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.
## What's changed - Fixed Fable 5 model names with a `[1m]` suffix not being normalized — Fable 5 includes 1M context by default, so the suffix is now stripped automatically - Fixed a spurious "sandbox dependencies missing" startup warning on Windows when sandbox was enabled in settings
## What's changed - Sub-agents can now spawn their own sub-agents (up to 5 levels deep) - Amazon Bedrock now reads the AWS region from `~/.aws` config files when `AWS_REGION` isn't set, matching AWS SDK precedence; `/status` shows where the region came from - Added a search bar when browsing a mark
## What's Changed * Add Imagine file storage & file-ID inputs to image/video generation by @Omar-V2 in https://github.com/xai-org/xai-sdk-python/pull/160 * Add public file URLs and list filtering to the files client by @Omar-V2 in https://github.com/xai-org/xai-sdk-python/pull/161 * Add new grok ima
### Patch Changes - [#17018](https://github.com/withastro/astro/pull/17018) [`1310277`](https://github.com/withastro/astro/commit/1310277db33cd93aa99e87492650c633af0fe257) Thanks [@matthewp](https://github.com/matthewp)! - Hardens `remotePatterns` regex generation to match canonical wildcard sema
### Patch Changes - [#16765](https://github.com/withastro/astro/pull/16765) [`b10e86e`](https://github.com/withastro/astro/commit/b10e86e6dbaf04678127c86366befc0b78a164f6) Thanks [@fkatsuhiro](https://github.com/fkatsuhiro)! - Fixes an issue where renaming an image file while the dev server is ru
## 2.41.1 (2026-06-05) Full Changelog: [v2.41.0...v2.41.1](https://github.com/openai/openai-python/compare/v2.41.0...v2.41.1) ### Build System * Remove scheduled release workflow trigger ([#3366](https://github.com/openai/openai-python/issues/3366)) ([2a91011](https://github.com/openai/openai-pyt
Empty release to ensure `next@latest` points at a stable release. Next.js only allows publishing with Trusted Publishing enabled. In order to fix NPM dist-tags, we have to release a new version. Updating dist-tags is not possible with Trusted Publishing.
Release with no changes in an attempt to fix `next@latest` pointing at a prerelease version.
## 0.104.1 (2026-06-09) Full Changelog: [sdk-v0.104.0...sdk-v0.104.1](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.104.0...sdk-v0.104.1) ### Bug Fixes * **api:** add `frontier_llm` refusal category ([465e686](https://github.com/anthropics/anthropic-sdk-typescript/commit/4
## 0.109.1 (2026-06-09) Full Changelog: [v0.109.0...v0.109.1](https://github.com/anthropics/anthropic-sdk-python/compare/v0.109.0...v0.109.1) ### Bug Fixes * **api:** add `frontier_llm` refusal category ([d3a806b](https://github.com/anthropics/anthropic-sdk-python/commit/d3a806b454d8aaf5806db11c6
## 0.104.0 (2026-06-09) Full Changelog: [sdk-v0.103.0...sdk-v0.104.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.103.0...sdk-v0.104.0) ### Features * **api:** add support for Managed Agents deployments and environment variable credentials ([d01e38b](https://github.com/a
## 0.109.0 (2026-06-09) Full Changelog: [v0.108.0...v0.109.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.108.0...v0.109.0) ### Features * **api:** add support for Managed Agents deployments and environment variable credentials ([47633bf](https://github.com/anthropics/anthropic-
## What's changed - Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use. Fable’s capabilities exceed those of any model we’ve ever made generally available. Update to version 2.1.170 for access. https://www.anthropic.com/news/claude-fable-5-mythos-5 - Fixed session
## 0.108.0 (2026-06-09) Full Changelog: [v0.107.1...v0.108.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.107.1...v0.108.0) ### Features * **api:** add support for claude-mythos-5 and claude-fable-5, with support for server-side fallbacks on refusal ([6b76649](https://github.com
## 0.4.2 (2026-06-09) Full Changelog: [aws-sdk-v0.4.1...aws-sdk-v0.4.2](https://github.com/anthropics/anthropic-sdk-typescript/compare/aws-sdk-v0.4.1...aws-sdk-v0.4.2) ### Bug Fixes * **client:** 3p middleware ordering ([#53](https://github.com/anthropics/anthropic-sdk-typescript/issues/53)) ([2a
## 0.30.2 (2026-06-09) Full Changelog: [bedrock-sdk-v0.30.1...bedrock-sdk-v0.30.2](https://github.com/anthropics/anthropic-sdk-typescript/compare/bedrock-sdk-v0.30.1...bedrock-sdk-v0.30.2) ### Bug Fixes * **client:** 3p middleware ordering ([#53](https://github.com/anthropics/anthropic-sdk-typesc
## 0.17.1 (2026-06-09) Full Changelog: [vertex-sdk-v0.17.0...vertex-sdk-v0.17.1](https://github.com/anthropics/anthropic-sdk-typescript/compare/vertex-sdk-v0.17.0...vertex-sdk-v0.17.1) ### Bug Fixes * **client:** 3p middleware ordering ([#53](https://github.com/anthropics/anthropic-sdk-typescript
## 0.103.0 (2026-06-09) Full Changelog: [sdk-v0.102.0...sdk-v0.103.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.102.0...sdk-v0.103.0) ### Features * **api:** add support for claude-mythos-5 and claude-fable-5, with support for server-side fallbacks on refusal ([cc337f7
### Patch Changes - [#17027](https://github.com/withastro/astro/pull/17027) [`241250b`](https://github.com/withastro/astro/commit/241250bf126f39c86a8aedd38df106e533301752) Thanks [@ocavue](https://github.com/ocavue)! - Triggers beta prereleases for packages that are still on alpha
### Patch Changes - [#16985](https://github.com/withastro/astro/pull/16985) [`4ecff32`](https://github.com/withastro/astro/commit/4ecff3268acb6ee3db719c4b38bbaead703ff4de) Thanks [@maximslo](https://github.com/maximslo)! - Fixes the `experimental.logger` destination not being used for the "Server
### Patch Changes - [#16964](https://github.com/withastro/astro/pull/16964) [`b048826`](https://github.com/withastro/astro/commit/b048826b7a0406c751073c1bd95686d9ffae8edc) Thanks [@Princesseuh](https://github.com/Princesseuh)! - Deprecates the `@astrojs/db` integration. We no longer have the band
### Minor Changes - [#16571](https://github.com/withastro/astro/pull/16571) [`d4b0cd1`](https://github.com/withastro/astro/commit/d4b0cd111ca0958e5da8772e34dd4fdc3e3a89dc) Thanks [@MA2153](https://github.com/MA2153)! - Sets immutable cache headers for static assets Static assets under `_astr
### Patch Changes - [#16985](https://github.com/withastro/astro/pull/16985) [`4ecff32`](https://github.com/withastro/astro/commit/4ecff3268acb6ee3db719c4b38bbaead703ff4de) Thanks [@maximslo](https://github.com/maximslo)! - Fixes the `experimental.logger` destination not being used for the "Server
## What's changed - Added `--safe-mode` flag (and `CLAUDE_CODE_SAFE_MODE`) to start Claude Code with all customizations (CLAUDE.md, plugins, skills, hooks, MCP servers) disabled for troubleshooting - Added `/cd` command to move a session to a new working directory without breaking the prompt cache
### Minor Changes - [#16969](https://github.com/withastro/astro/pull/16969) [`4a31f90`](https://github.com/withastro/astro/commit/4a31f90c765bcd1c4af8b85160b74a0da338cfe7) Thanks [@Princesseuh](https://github.com/Princesseuh)! - Adds support for Prism syntax highlighting to the Sätteri Markdown a
### Patch Changes - [#16990](https://github.com/withastro/astro/pull/16990) [`ebeb830`](https://github.com/withastro/astro/commit/ebeb83075ba7825a822fdcf4228b475cae38c9c5) Thanks [@ocavue](https://github.com/ocavue)! - Fixes a build crash when using `experimental.advancedRouting` with a custom `f
Ollama Launch now supports Hermes Desktop, a native desktop interface for the Hermes agent. Run it alongside your Hermes agent to get a visual interface for managing conversations, integrations, and messaging apps. ``` ollama launch hermes-desktop ``` <img width="2556" height="1716" alt="image
### Patch Changes - fix: ignore errors that occur in destroyed effects ([#18384](https://github.com/sveltejs/svelte/pull/18384)) - fix: type BigInts in `$state.snapshot(...)` return values ([#18388](https://github.com/sveltejs/svelte/pull/18388))
## 0.107.1 (2026-06-07) Full Changelog: [v0.107.0...v0.107.1](https://github.com/anthropics/anthropic-sdk-python/compare/v0.107.0...v0.107.1) ### Bug Fixes * **foundry:** send x-api-key header for API-key auth ([#62](https://github.com/anthropics/anthropic-sdk-python/issues/62)) ([1338141](https:
## What's changed - Bug fixes and reliability improvements
## 0.4.1 (2026-06-06) Full Changelog: [aws-sdk-v0.4.0...aws-sdk-v0.4.1](https://github.com/anthropics/anthropic-sdk-typescript/compare/aws-sdk-v0.4.0...aws-sdk-v0.4.1) ### Bug Fixes * **client:** run middleware before request signing ([#45](https://github.com/anthropics/anthropic-sdk-typescript/i
## 0.107.0 (2026-06-06) Full Changelog: [v0.106.0...v0.107.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.106.0...v0.107.0) ### Features * **api:** small updates to Managed Agents types ([72923f9](https://github.com/anthropics/anthropic-sdk-python/commit/72923f986f808597f86482a7
## 0.30.1 (2026-06-06) Full Changelog: [bedrock-sdk-v0.30.0...bedrock-sdk-v0.30.1](https://github.com/anthropics/anthropic-sdk-typescript/compare/bedrock-sdk-v0.30.0...bedrock-sdk-v0.30.1) ### Bug Fixes * **client:** run middleware before request signing ([#45](https://github.com/anthropics/anthr
## 0.102.0 (2026-06-06) Full Changelog: [sdk-v0.101.0...sdk-v0.102.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.101.0...sdk-v0.102.0) ### Features * **api:** small updates to Managed Agents types ([8ba4f92](https://github.com/anthropics/anthropic-sdk-typescript/commit/
## What's changed - Bug fixes and reliability improvements
## What's changed - Added `fallbackModel` setting to configure up to three fallback models tried in order when the primary model is overloaded or unavailable; `--fallback-model` now also applies to interactive sessions - Added glob pattern support in deny rule tool-name position (`"*"` denies all t
## 0.106.0 (2026-06-05) Full Changelog: [v0.105.2...v0.106.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.105.2...v0.106.0) ### Features * **api:** mark Claude Opus 4.1 as deprecated ([85068cc](https://github.com/anthropics/anthropic-sdk-python/commit/85068cc4cb42feecb80a378942c
# New models - [Gemma 4 QAT weights](https://ollama.com/library/gemma4): the Gemma 4 family is now optimized with Quantization-Aware Training (QAT) to dramatically reduce memory requirements and maximize on-device performance. Look for the tags ending in `-qat`: - `gemma4:e2b-it-qat` - `gemma
## 0.4.0 (2026-06-05) Full Changelog: [aws-sdk-v0.3.1...aws-sdk-v0.4.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/aws-sdk-v0.3.1...aws-sdk-v0.4.0) ### Features * **api:** mark Claude Opus 4.1 as deprecated ([4ee46f2](https://github.com/anthropics/anthropic-sdk-typescript/comm
## 0.30.0 (2026-06-05) Full Changelog: [bedrock-sdk-v0.29.2...bedrock-sdk-v0.30.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/bedrock-sdk-v0.29.2...bedrock-sdk-v0.30.0) ### Features * **api:** mark Claude Opus 4.1 as deprecated ([4ee46f2](https://github.com/anthropics/anthropi
## 0.17.0 (2026-06-05) Full Changelog: [vertex-sdk-v0.16.1...vertex-sdk-v0.17.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/vertex-sdk-v0.16.1...vertex-sdk-v0.17.0) ### Features * **api:** mark Claude Opus 4.1 as deprecated ([4ee46f2](https://github.com/anthropics/anthropic-sd
## 0.101.0 (2026-06-05) Full Changelog: [sdk-v0.100.1...sdk-v0.101.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.100.1...sdk-v0.101.0) ### Features * **client:** add support for middleware ([9b01120](https://github.com/anthropics/anthropic-sdk-typescript/commit/9b011207
### Patch Changes - Bumped `@remix-run/*` dependencies: - [`fetch-router@0.20.0`](https://github.com/remix-run/remix/releases/tag/fetch-router@0.20.0)
### Patch Changes - Bumped `@remix-run/*` dependencies: - [`fetch-router@0.20.0`](https://github.com/remix-run/remix/releases/tag/fetch-router@0.20.0)
### Patch Changes - Fixed `createHref()` so optional route params set to `null` are omitted instead of serialized as `"null"`, and empty pathname variables throw instead of generating hrefs that cannot match their pattern. - Fixed route matching so malformed percent-encoded pathnames return no mat
## What's changed - Bug fixes and reliability improvements
## What's changed - Added `requiredMinimumVersion` and `requiredMaximumVersion` managed settings — Claude Code refuses to start if its version is outside the allowed range and directs the user to an approved version - Added `/plugin list` command to list installed plugins, with `--enabled`/`--disab
### Patch Changes - fix: properly track effect end node for async sibling component ([#18371](https://github.com/sveltejs/svelte/pull/18371)) - fix: prevent false-positive reactivity loss warning ([#18373](https://github.com/sveltejs/svelte/pull/18373)) - chore: bump esrap dependency ([#183
## What's Changed * Fixed the `gemma4:12b` floating point exception crash on x86, CUDA, Linux, and Windows systems. * `ollama launch hermes-desktop` now launches Hermes Desktop and can skip rebuilding when a packaged desktop app is already installed. * `ollama launch hermes` now supports native
## 2.41.0 (2026-06-03) Full Changelog: [v2.40.0...v2.41.0](https://github.com/openai/openai-python/compare/v2.40.0...v2.41.0) ### Features * **api:** responses.moderation and chat_completions.moderation ([87e46c2](https://github.com/openai/openai-python/commit/87e46c25ac9ca8cff407b52ad9fb33e326c0
## [2.8.0](https://github.com/googleapis/python-genai/compare/v2.7.0...v2.8.0) (2026-06-03) ### Features * Add Agent Platform MCP support to async generate_content ([e3be9af](https://github.com/googleapis/python-genai/commit/e3be9af3c21c9f8f625aecd890a5ee1f9993fb3d)) * Add transcription language
## 6.42.0 (2026-06-03) Full Changelog: [v6.41.0...v6.42.0](https://github.com/openai/openai-node/compare/v6.41.0...v6.42.0) ### Features * **api:** responses.moderation and chat_completions.moderation ([6d8f592](https://github.com/openai/openai-node/commit/6d8f592d6aec5487684723b75137629a12225d29
## What's changed - `claude agents --json` now includes `waitingFor` showing what a waiting session is blocked on (e.g. permission prompt) - `--tools`: explicitly listing Grep/Glob now provides the dedicated search tools on native builds with embedded search (previously these names were silently ig
# New models - [Nemotron-3-Ultra](https://ollama.com/library/nemotron-3-ultra): NVIDIA Nemotron 3 Ultra is built for high-throughput reasoning and long-running agent workflows. ## What's Changed * Fixed multimodal models not using GPU on the llama.cpp backend can now use Metal GPU offload on
### Patch Changes - [#16926](https://github.com/withastro/astro/pull/16926) [`1b39ae8`](https://github.com/withastro/astro/commit/1b39ae8485406937501d8a734afe2a464d671064) Thanks [@narendraio](https://github.com/narendraio)! - Prevents `App.match()` from throwing on request paths that contain an
### Patch Changes - [#16955](https://github.com/withastro/astro/pull/16955) [`9a93d68`](https://github.com/withastro/astro/commit/9a93d68429aa15e76f07268863badfbda7b59d23) Thanks [@Princesseuh](https://github.com/Princesseuh)! - Updates Sätteri processor to v0.8.0. See [its changelog](https://git
## New models - [Gemma 4 12B](https://ollama.com/library/gemma4:12b): high-performance multimodal intelligence that runs directly on laptops, combining efficiency with advanced reasoning. ## What's Changed * Added support for `gemma4:12b`. **Full Changelog**: https://github.com/ollama/olla
### 2.8.2 / 2026.06.03 - feat(compile): improve --bundle dependency resolution and add --minify (#34536) - feat(compile): scope --bundle npm embed to packages actually reached (#34532) - feat(ext/crypto): add ChaCha20-Poly1305, SHAKE, cSHAKE, TurboSHAKE, SHA-3 HMAC (#34417) - feat(ext/cr
# Generated by Speakeasy CLI ## 2026-06-03 11:09:54 ### Changes Based on: - OpenAPI Doc - Speakeasy CLI 1.763.6 (2.884.13) https://github.com/speakeasy-api/speakeasy ### Generated - [python v2.4.9] . ### Releases - [PyPI v2.4.9] https://pypi.org/project/mistralai/2.4.9 - . Publishing Completed
## What's Changed * `ollama launch` now supports Qwen Code and can guide users through installing the Cline CLI when it is missing. * `ollama launch codex` now uses an isolated launch configuration, avoiding conflicts with a user's existing Codex settings. * Added llama.cpp backend compatibilit
## What's changed - `OTEL_RESOURCE_ATTRIBUTES` values are now included as labels on metric datapoints, so you can slice usage metrics by custom dimensions like team or repo - `claude agents` rows now show `done/total` before the detail when work is fanned out; peek shows the longest-running item -
## What's Changed * feat(launch): show and auto-install Cline CLI by @hoyyeva in https://github.com/ollama/ollama/pull/16402 * log template details to aid troubleshooting by @dhiltgen in https://github.com/ollama/ollama/pull/16403 * cmd/launch: add Qwen code integration by @hoyyeva in https://git
### Patch Changes - [#16922](https://github.com/withastro/astro/pull/16922) [`7dce185`](https://github.com/withastro/astro/commit/7dce1852a4f185fb44f885030f48c1883e9b17ff) Thanks [@astrobot-houston](https://github.com/astrobot-houston)! - Fixes prerendered pages returning 404 when using `build.fo
### Patch Changes - [#16693](https://github.com/withastro/astro/pull/16693) [`9e6edc2`](https://github.com/withastro/astro/commit/9e6edc2da5ccf06243588a7f519dea5fbcc126cd) Thanks [@ArmandPhilippot](https://github.com/ArmandPhilippot)! - Fixes a link in the documentation specifying where to open a
### Patch Changes - [#16900](https://github.com/withastro/astro/pull/16900) [`17a0fbd`](https://github.com/withastro/astro/commit/17a0fbd34d11db765e79caf269bfd5f43ef51da8) Thanks [@ocavue](https://github.com/ocavue)! - Bumps `devalue` dependency to v5.8.1
### Patch Changes - [#16900](https://github.com/withastro/astro/pull/16900) [`17a0fbd`](https://github.com/withastro/astro/commit/17a0fbd34d11db765e79caf269bfd5f43ef51da8) Thanks [@ocavue](https://github.com/ocavue)! - Bumps `devalue` dependency to v5.8.1 - [#16016](https://github.com/withastr
### Patch Changes - [#16900](https://github.com/withastro/astro/pull/16900) [`17a0fbd`](https://github.com/withastro/astro/commit/17a0fbd34d11db765e79caf269bfd5f43ef51da8) Thanks [@ocavue](https://github.com/ocavue)! - Bumps `devalue` dependency to v5.8.1
### Patch Changes - [#16914](https://github.com/withastro/astro/pull/16914) [`4bdd240`](https://github.com/withastro/astro/commit/4bdd240a6174b12ee9344d9b97456079aa5975ce) Thanks [@matthewp](https://github.com/matthewp)! - Fixes `astro/fetch` and `astro/hono` being discovered at runtime during de
## What's changed - Added a prompt before writing to shell startup files (`.zshenv`, `.zlogin`, `.bash_login`) and `~/.config/git/`, which could otherwise lead to unintended command execution - `acceptEdits` mode now prompts before writing build-tool config files that grant code execution (`.npmrc`
### Patch Changes - fix: error at compile time on duplicate snippet/declaration tag definitions ([#18351](https://github.com/sveltejs/svelte/pull/18351)) - fix: parse declaration tag contents more robustly ([#18353](https://github.com/sveltejs/svelte/pull/18353)) - fix: correctly transform
## 2.40.0 (2026-06-01) Full Changelog: [v2.39.0...v2.40.0](https://github.com/openai/openai-python/compare/v2.39.0...v2.40.0) ### Features * **api:** Add Amazon Bedrock Responses support ### Bug Fixes * **api:** allow setting bedrock api keys on the client directly ([4d5bfde](https://github.com
## 6.41.0 (2026-06-01) Full Changelog: [v6.40.0...v6.41.0](https://github.com/openai/openai-node/compare/v6.40.0...v6.41.0) ### Features * **api:** Add Amazon Bedrock Responses support ([#1899](https://github.com/openai/openai-node/issues/1899)) ([535b045](https://github.com/openai/openai-node/co
> [!NOTE] > This release is backporting bug fixes. It does **not** include all pending features/changes on canary. ### Core Changes - [15.5.x] Don't drop `FormData` entries (#94244) ### Other - [15.5.x] Fix CI (#94281) ### Credits Huge thanks to @eps1lon for helping!
> [!NOTE] > This release is backporting bug fixes. It does **not** include all pending features/changes on canary. ### Core Changes - Backport documentation fixes for v16.2 (#93804) - [backport] Patch `playwright-core` to resolve `_finishedPromise` on `requestFailed` (#93920) - [backport] F
## 2.39.0 (2026-06-01) Full Changelog: [v2.38.0...v2.39.0](https://github.com/openai/openai-python/compare/v2.38.0...v2.39.0) ### Features * **api:** workload identity in audit logs, additional_tools item in responses, fix ActionSearch.query to be optional. ([ab60d7a](https://github.com/openai/op
## 6.40.0 (2026-06-01) Full Changelog: [v6.39.1...v6.40.0](https://github.com/openai/openai-node/compare/v6.39.1...v6.40.0) ### Features * **api:** workload identity in audit logs, additional_tools item in responses, fix ActionSearch.query to be optional. ([aee09f3](https://github.com/openai/open
## React Server Components - Fixed missing `FormData` entries in Server Actions which regressed in 19.2.6 ([#36566](https://github.com/facebook/react/pull/36566) by @unstubbable)
## React Server Components - Fixed missing `FormData` entries in Server Actions which regressed in 19.1.7 ([#36567](https://github.com/facebook/react/pull/36567) by @unstubbable)
## React Server Components - Fixed missing `FormData` entries in Server Actions which regressed in 19.0.6 ([#36568](https://github.com/facebook/react/pull/36568) by @unstubbable)
See the changelog for the release notes: https://github.com/remix-run/remix/blob/v2/CHANGELOG.md#v2175
Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/v6.4.3/packages/vite/CHANGELOG.md) for details.
Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/v7.3.5/packages/vite/CHANGELOG.md) for details.
Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/v8.0.16/packages/vite/CHANGELOG.md) for details.
Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/v8.0.15/packages/vite/CHANGELOG.md) for details.
Node.js v26.3.0
## What's changed - Internal infrastructure improvements (no user-facing changes)
## What's changed - Auto mode is now available on Bedrock, Vertex, and Foundry for Opus 4.7 and Opus 4.8. Opt in by setting `CLAUDE_CODE_ENABLE_AUTO_MODE=1`
## What's Changed * Add grok-build-0.1 to ChatModel by @shawnthapa in https://github.com/xai-org/xai-sdk-python/pull/155 * Add context compaction support by @shawnthapa in https://github.com/xai-org/xai-sdk-python/pull/156 * Bump version from 1.14.0 to 1.15.0 by @shawnthapa in https://github.com/xai
### Minor Changes - feat: allow declarations in the template ([#18282](https://github.com/sveltejs/svelte/pull/18282)) ### Patch Changes - perf: use `createElement` instead of `createElementNS` for HTML elements ([#18262](https://github.com/sveltejs/svelte/pull/18262)) - perf: store `curre
## What's changed - Plugins in `.claude/skills` directories are now automatically loaded, no marketplace required - Added `claude plugin init <name>` to scaffold a new plugin in `.claude/skills` - Added autocomplete for `/plugin` arguments: subcommands, installed plugin names, and plugins from know
### Patch Changes - Prevent `staticFiles()` from serving files outside its configured root through symlinks. - Bumped `@remix-run/*` dependencies: - [`fetch-router@0.19.2`](https://github.com/remix-run/remix/releases/tag/fetch-router@0.19.2) - [`fs@0.4.5`](https://github.com/remix-run/remix/re
### Patch Changes - Bumped `@remix-run/*` dependencies: - [`headers@0.21.1`](https://github.com/remix-run/remix/releases/tag/headers@0.21.1)
### Patch Changes - Bumped `@remix-run/*` dependencies: - [`headers@0.21.1`](https://github.com/remix-run/remix/releases/tag/headers@0.21.1)
### Minor Changes - Matchers now normalize percent-encoded pathname during matching Pathname matching now uses the URL parser's normalized pathname, splits it into segments, and canonicalizes each segment as percent-encoded text before matching. This allows equivalent path text like `a` and `%61
## What's changed - Fixed an issue when using Opus 4.8 where thinking blocks were modified, leading to API errors.
## 0.105.2 (2026-05-29) Full Changelog: [v0.105.1...v0.105.2](https://github.com/anthropics/anthropic-sdk-python/compare/v0.105.1...v0.105.2)
## 0.3.1 (2026-06-09) Full Changelog: [foundry-sdk-v0.3.0...foundry-sdk-v0.3.1](https://github.com/anthropics/anthropic-sdk-typescript/compare/foundry-sdk-v0.3.0...foundry-sdk-v0.3.1) ### Bug Fixes * **client:** 3p middleware ordering ([#53](https://github.com/anthropics/anthropic-sdk-typescript/
## 0.2.4 (2026-05-29) Full Changelog: [foundry-sdk-v0.2.3...foundry-sdk-v0.2.4](https://github.com/anthropics/anthropic-sdk-typescript/compare/foundry-sdk-v0.2.3...foundry-sdk-v0.2.4) ### Chores * **client:** update lockfiles to have proper dependencies on standardwebhooks ([5e9b523](https://gith
## 0.100.1 (2026-05-29) Full Changelog: [sdk-v0.100.0...sdk-v0.100.1](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.100.0...sdk-v0.100.1) ### Bug Fixes * **streaming:** carry encrypted_content on beta compaction blocks ([#1025](https://github.com/anthropics/anthropic-sdk-t
## 0.105.1 (2026-05-29) Full Changelog: [v0.105.0...v0.105.1](https://github.com/anthropics/anthropic-sdk-python/compare/v0.105.0...v0.105.1) ### Chores * **internal:** use Trusted Publishing for PyPI releases ([1d04fc5](https://github.com/anthropics/anthropic-sdk-python/commit/1d04fc52d2dd1f88e2
## What's changed - Opus 4.8 is here! Now defaults to high effort · /effort xhigh for your hardest tasks - Introducing dynamic workflows: ask Claude to create a workflow and it orchestrates work across tens to hundreds of agents in the background, so you can take on larger, more complex tasks. Run
## 6.39.1 (2026-05-27) Full Changelog: [v6.39.0...v6.39.1](https://github.com/openai/openai-node/compare/v6.39.0...v6.39.1) ### Bug Fixes * Improve undici dispatcher mismatch guidance ([#1898](https://github.com/openai/openai-node/issues/1898)) ([b6e5fd6](https://github.com/openai/openai-node/com
## 0.105.0 (2026-05-28) Full Changelog: [v0.104.1...v0.105.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.104.1...v0.105.0) ### Features * **api:** Add support for claude-opus-4-8, mid-conversation system blocks, and usage.output_tokens_details ([f18b014](https://github.com/anth
## 0.100.0 (2026-05-28) Full Changelog: [sdk-v0.99.0...sdk-v0.100.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.99.0...sdk-v0.100.0) ### Features * **api:** Add support for claude-opus-4-8, mid-conversation system blocks, and usage.output_tokens_details ([bb0bf27](https
### Patch Changes - [#16889](https://github.com/withastro/astro/pull/16889) [`b94bcfd`](https://github.com/withastro/astro/commit/b94bcfd8da64a3f2862a20572e7a9847aebdbc70) Thanks [@Princesseuh](https://github.com/Princesseuh)! - Fixes a `plugins is not iterable` crash when using a pre-6.0 `@astro
## [2.7.0](https://github.com/googleapis/python-genai/compare/v2.6.0...v2.7.0) (2026-05-27) ### Features * Additional computer_use field support for vertex. ([b4828fa](https://github.com/googleapis/python-genai/commit/b4828fa5b085d2dbb47a0adc9c10e4b35d60ad64)) * **interaction-api:** Allow "text/c
### Patch Changes - [#16883](https://github.com/withastro/astro/pull/16883) [`eeb064c`](https://github.com/withastro/astro/commit/eeb064ca9452fd9d0ad9b7557059a646a90a3e57) Thanks [@Princesseuh](https://github.com/Princesseuh)! - Fixes missing provenance information on the publish
### Patch Changes - Updated dependencies [[`f732f3c`](https://github.com/withastro/astro/commit/f732f3cc716342a63e5b03815243ba10964b89dc)]: - @astrojs/internal-helpers@0.10.0 - @astrojs/underscore-redirects@1.0.3
### Patch Changes - Updated dependencies [[`f732f3c`](https://github.com/withastro/astro/commit/f732f3cc716342a63e5b03815243ba10964b89dc)]: - @astrojs/internal-helpers@0.10.0
### Patch Changes - Updated dependencies [[`f732f3c`](https://github.com/withastro/astro/commit/f732f3cc716342a63e5b03815243ba10964b89dc)]: - @astrojs/internal-helpers@0.10.0
### Patch Changes - Updated dependencies [[`f732f3c`](https://github.com/withastro/astro/commit/f732f3cc716342a63e5b03815243ba10964b89dc)]: - @astrojs/internal-helpers@0.10.0
### Minor Changes - [#16468](https://github.com/withastro/astro/pull/16468) [`4cff3a1`](https://github.com/withastro/astro/commit/4cff3a107c3750ab5f0878a6b41836705282b771) Thanks [@matthewp](https://github.com/matthewp)! - Adds a new `preserveBuildServerDir` adapter feature Adapters can now
# Generated by Speakeasy CLI ## 2026-05-27 16:56:58 ### Changes Based on: - OpenAPI Doc - Speakeasy CLI 1.763.6 (2.884.13) https://github.com/speakeasy-api/speakeasy ### Generated - [python v2.4.8] . ### Releases - [PyPI v2.4.8] https://pypi.org/project/mistralai/2.4.8 - . Publishing Completed
## What's changed - Added `skipLfs` option to `github`/`git` plugin marketplace sources to skip Git LFS downloads during clone and update - Claude Code now shows a one-time notice when your npm global install can't auto-update; `/doctor` lists the fixes - Status line commands now receive `COLUMNS`
The Rust team is happy to announce a new version of Rust, 1.96.0. 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 1.96.0 with: $ rustup update stable If you don't have it already, yo
### Patch Changes - fix: unlink errored and otherwise finished batch ([#18264](https://github.com/sveltejs/svelte/pull/18264)) - perf: walk composedPath() directly in delegated event propagation ([#18268](https://github.com/sveltejs/svelte/pull/18268)) - fix: transfer effects when merging b
# Generated by Speakeasy CLI ## 2026-05-22 14:12:57 ### Changes Based on: - OpenAPI Doc - Speakeasy CLI 1.763.6 (2.884.13) https://github.com/speakeasy-api/speakeasy ### Generated - [python v2.4.7] . ### Releases - [PyPI v2.4.7] https://pypi.org/project/mistralai/2.4.7 - . Publishing Completed
# Generated by Speakeasy CLI ## 2026-05-22 14:36:33 ### Changes Based on: - OpenAPI Doc - Speakeasy CLI 1.763.6 (2.884.13) https://github.com/speakeasy-api/speakeasy ### Generated - [typescript v2.2.5] . ### Releases - [NPM v2.2.5] https://www.npmjs.com/package/@mistralai/mistralai/v/2.2.5 - . P
### 2.8.1 / 2026.05.27 - Revert "fix(ext/node): polyfill module.enableCompileCache and companions" (#34190) (#34348) - feat(bundle): support `browser` field map in package.json (#34407) - fix(bundle): read package.json sideEffects field (#34406) - fix(cli): clearer error when importing .nod
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.
## What's Changed * Add enable_image_search to web_search and SERVER_SIDE_TOOL_IMAGE_SEARCH enum by @ushiromiya-lion in https://github.com/xai-org/xai-sdk-python/pull/152 * Bump version to 1.14.0 by @ushiromiya-lion in https://github.com/xai-org/xai-sdk-python/pull/153 ## New Contributors * @ushiro
## What's changed - `/code-review --fix` now applies review findings to your working tree after the review, surfacing reuse, simplification, and efficiency suggestions; `/simplify` now invokes `/code-review --fix` - Skills and slash commands can now set `disallowed-tools` in frontmatter to remove t
## 0.99.0 (2026-05-27) Full Changelog: [sdk-v0.98.1...sdk-v0.99.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.98.1...sdk-v0.99.0) ### Features * support custom file size caps ([#1029](https://github.com/anthropics/anthropic-sdk-typescript/issues/1029)) ([814cd4c](https:
## 0.98.1 (2026-05-26) Full Changelog: [sdk-v0.98.0...sdk-v0.98.1](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.98.0...sdk-v0.98.1) ### Bug Fixes * **client:** preserve directory prefix in skills.versions.create uploads ([#1024](https://github.com/anthropics/anthropic-sdk
### Patch Changes - [#16827](https://github.com/withastro/astro/pull/16827) [`90ee151`](https://github.com/withastro/astro/commit/90ee151f1a77b1e3d55d0f8db768e65c3f8c8948) Thanks [@matthewp](https://github.com/matthewp)! - Fixes a crash in the language server and `astro check` when using TypeScri
### Patch Changes - [#16496](https://github.com/withastro/astro/pull/16496) [`4d79750`](https://github.com/withastro/astro/commit/4d79750c3535d35bbec521e8d93546bf73e2ea6a) Thanks [@fkatsuhiro](https://github.com/fkatsuhiro)! - Fixed an issue where type errors occurred during testing library type
### Patch Changes - [#16607](https://github.com/withastro/astro/pull/16607) [`98297af`](https://github.com/withastro/astro/commit/98297afb4fad0b61a69ff84b842cf65e5d71f5a4) Thanks [@alexanderflodin](https://github.com/alexanderflodin)! - Fixes incorrect `assets.directory` in the generated `wrangle
### Patch Changes - [#16837](https://github.com/withastro/astro/pull/16837) [`783c4a6`](https://github.com/withastro/astro/commit/783c4a6e7789999aac0259e4777c90178adb9a02) Thanks [@jdevalk](https://github.com/jdevalk)! - Improves `<lastmod>` accuracy in the sitemap index. Each `<sitemap>` entry i
### Patch Changes - [#16830](https://github.com/withastro/astro/pull/16830) [`f2bf3cb`](https://github.com/withastro/astro/commit/f2bf3cb257788ff657ffbe9044fe6225e6662cb7) Thanks [@matthewp](https://github.com/matthewp)! - Fixes 404s for dynamically imported JS chunks when using an adapter with `
### Patch Changes - [#16813](https://github.com/withastro/astro/pull/16813) [`8f7d8c4`](https://github.com/withastro/astro/commit/8f7d8c46ffc79b23200a98fcf6b72c53e19d71db) Thanks [@matthewp](https://github.com/matthewp)! - Populates styles in the SSR manifest for prerendered routes. Previously, p
## What's changed - Internal infrastructure improvements (no user-facing changes)
## What's changed - `/usage` now shows a per-category breakdown of what's driving your limits usage — skills, subagents, plugins, and per-MCP-server cost - `/diff` detail view can now be scrolled with the keyboard (arrows, `j`/`k`, `PgUp`/`PgDn`, `Space`, `Home`/`End`) - Markdown output now renders
## 0.104.1 (2026-05-21) Full Changelog: [v0.104.0...v0.104.1](https://github.com/anthropics/anthropic-sdk-python/compare/v0.104.0...v0.104.1) ### Bug Fixes * **streaming:** carry encrypted_content through beta compaction accumulator ([#1821](https://github.com/anthropics/anthropic-sdk-python/issu
### 2.8.0 / 2026.05.22 Read more: http://deno.com/blog/v2.8 - feat: accept `deno audit fix` as alias for `deno audit --fix` (#34273) - feat: add --watch flag to deno check (#34224) - feat: add `deno bump-version` subcommand (#30562) - feat: add `deno why` subcommand (#32908) - feat: suppor
## What's changed - Fixed the Bash tool returning exit code 127 on every command for some users (a regression introduced in 2.1.147)
## [2.6.0](https://github.com/googleapis/python-genai/compare/v2.5.0...v2.6.0) (2026-05-21) ### Features * Add `enable_prompt_injection_detection` for Computer Use feature for the Gemini API. ([b1f632d](https://github.com/googleapis/python-genai/commit/b1f632d5d617a8e24fd4cb87556a4eb180b6d29b)) *
## 6.39.0 (2026-05-21) Full Changelog: [v6.38.0...v6.39.0](https://github.com/openai/openai-node/compare/v6.38.0...v6.39.0) ### Features * **api:** api update ([33ea11f](https://github.com/openai/openai-node/commit/33ea11fc5e7656990005cfb932584e0e646957d4)) * **api:** manual updates ([c210b09](ht
## 2.38.0 (2026-05-21) Full Changelog: [v2.37.0...v2.38.0](https://github.com/openai/openai-python/compare/v2.37.0...v2.38.0) ### Features * **api:** api update ([33d1d01](https://github.com/openai/openai-python/commit/33d1d013250053886a73d178136e6bd1b09df059)) * **api:** manual updates ([a21700a
## What's changed - Pinned background sessions (`Ctrl+T` in `claude agents`) now stay alive when idle, are restarted in place to apply Claude Code updates, and are shed under memory pressure only after non-pinned sessions - Renamed `/simplify` to `/code-review`. It now reports correctness bugs at a
## 0.104.0 (2026-05-21) Full Changelog: [v0.103.1...v0.104.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.103.1...v0.104.0) ### Features * **api:** Add support for thinking-token-count beta for estimated tokens in thinking block deltas when streaming ([80d0fdf](https://github.co
## 0.98.0 (2026-05-21) Full Changelog: [sdk-v0.97.1...sdk-v0.98.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.97.1...sdk-v0.98.0) ### Features * **api:** Add support for thinking-token-count beta for estimated tokens in thinking block deltas when streaming ([0528d47](ht
### Patch Changes - [#16769](https://github.com/withastro/astro/pull/16769) [`428cb1b`](https://github.com/withastro/astro/commit/428cb1bb80f9c5672ed68bfc219fa700b7a569fa) Thanks [@astrobot-houston](https://github.com/astrobot-houston)! - Forwards user-provided `optimizeDeps` settings (exclude, i
### Patch Changes - [#16821](https://github.com/withastro/astro/pull/16821) [`9c76b12`](https://github.com/withastro/astro/commit/9c76b12052c445416df6b034d7b6df66957a0503) Thanks [@astrobot-houston](https://github.com/astrobot-houston)! - Fixes request body handling in the Node adapter when `req.
Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/v8.0.14/packages/vite/CHANGELOG.md) for details.
## What's changed - Renamed `/simplify` to `/code-review` with an optional effort level (e.g. `/code-review high`) - Auto mode no longer suppresses `AskUserQuestion` when the user or a skill explicitly relies on it - Fixed Windows PowerShell tool failing with "command line is invalid" when `pwsh` i
### Patch Changes - Bumped `@remix-run/*` dependencies: - [`fetch-router@0.19.1`](https://github.com/remix-run/remix/releases/tag/fetch-router@0.19.1) - [`fs@0.4.4`](https://github.com/remix-run/remix/releases/tag/fs@0.4.4) - [`html-template@0.3.1`](https://github.com/remix-run/remix/releases
### Patch Changes - Fix browser tests so bare package imports resolve with browser and ESM conditions, matching the asset server and avoiding CommonJS entries for packages like `clsx` (see #11478). - Update the optional `playwright` peer dependency range to match the workspace Playwright catalog
## [2.5.0](https://github.com/googleapis/python-genai/compare/v2.4.0...v2.5.0) (2026-05-20) ### Features * Add Gemini 3.5 Flash model to options ([706fd02](https://github.com/googleapis/python-genai/commit/706fd021fb0e0119e0867be2267592e7709cd274))
### Patch Changes - [#16774](https://github.com/withastro/astro/pull/16774) [`8f77583`](https://github.com/withastro/astro/commit/8f7758313df4af52e83e039bb64c41006de93c4e) Thanks [@astrobot-houston](https://github.com/astrobot-houston)! - Fixes markdown images with empty alt text (`
### Patch Changes - [#16801](https://github.com/withastro/astro/pull/16801) [`d619277`](https://github.com/withastro/astro/commit/d6192772a424b12bdf5f5991c3c882c3ae5cd707) Thanks [@ematipico](https://github.com/ematipico)! - Reverts a change to the esbuild dep-scan plugin that caused `astro check
### Patch Changes - fix: don't unset batch when calling `{#await ...}` promise ([#18243](https://github.com/sveltejs/svelte/pull/18243)) - fix: promise-ify `{#await await ...}` expressions on the server and correctly hydrate them on the client ([#18243](https://github.com/sveltejs/svelte/pull/
### Patch Changes - Bumped `@remix-run/*` dependencies: - [`fetch-router@0.19.0`](https://github.com/remix-run/remix/releases/tag/fetch-router@0.19.0) - [`response@0.3.4`](https://github.com/remix-run/remix/releases/tag/response@0.3.4)
### Patch Changes - Bumped `@remix-run/*` dependencies: - [`headers@0.20.0`](https://github.com/remix-run/remix/releases/tag/headers@0.20.0)
### Minor Changes - BREAKING CHANGE: Remove the `compareFn` parameter from `match` and `matchAll` methods Matches always sort by specificity (most specific first). If you need a different order, sort the result of `matchAll` yourself. ```ts import * as Specificity from 'remix/route-pattern/
Node.js v26.2.0
## What's changed - Added `claude agents --json` to list live Claude sessions as JSON for scripting (tmux-resurrect, status bars, session pickers) - Added `agent_id` and `parent_agent_id` attributes to `claude_code.tool` OTEL spans, and fixed trace parenting so background subagent spans nest under
At Google I/O we released Gemini 3.5, our latest series of models combining frontier intelligence with action.
## 0.103.1 (2026-05-19) Full Changelog: [v0.103.0...v0.103.1](https://github.com/anthropics/anthropic-sdk-python/compare/v0.103.0...v0.103.1) ### Bug Fixes * **runner:** skip tool calls SessionToolRunner does not own ([#1817](https://github.com/anthropics/anthropic-sdk-python/issues/1817)) ([9425
## 0.97.1 (2026-05-19) Full Changelog: [sdk-v0.97.0...sdk-v0.97.1](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.97.0...sdk-v0.97.1) ### Bug Fixes * **runner:** skip tool calls SessionToolRunner does not own ([9987379](https://github.com/anthropics/anthropic-sdk-typescript
## 0.29.2 (2026-05-19) Full Changelog: [bedrock-sdk-v0.29.1...bedrock-sdk-v0.29.2](https://github.com/anthropics/anthropic-sdk-typescript/compare/bedrock-sdk-v0.29.1...bedrock-sdk-v0.29.2) ### Bug Fixes * align @types/node in sub-packages to fix CI build ([#1017](https://github.com/anthropics/ant
## 0.16.1 (2026-05-19) Full Changelog: [vertex-sdk-v0.16.0...vertex-sdk-v0.16.1](https://github.com/anthropics/anthropic-sdk-typescript/compare/vertex-sdk-v0.16.0...vertex-sdk-v0.16.1) ### Bug Fixes * align @types/node in sub-packages to fix CI build ([#1017](https://github.com/anthropics/anthrop
## 0.97.0 (2026-05-19) Full Changelog: [sdk-v0.96.0...sdk-v0.97.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.96.0...sdk-v0.97.0) ### Features * **client:** Add support for self-hosted sandboxes in CMA with sandbox helpers ([659a343](https://github.com/anthropics/anthro
## 0.103.0 (2026-05-19) Full Changelog: [v0.102.0...v0.103.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.102.0...v0.103.0) ### Features * **client:** Add support for self-hosted sandboxes in CMA with sandbox helpers ([e5625b0](https://github.com/anthropics/anthropic-sdk-python/
## What's changed - Added `/resume` support for background sessions — sessions started via `claude --bg` or agent view now appear alongside interactive ones, marked with `bg` - Added elapsed duration to background subagent completion notifications (e.g. "Agent completed · 3h 2m 5s") - The `/plugin`
### Patch Changes - [#16771](https://github.com/withastro/astro/pull/16771) [`07c8805`](https://github.com/withastro/astro/commit/07c880500926e3337798ca906d9422c880c6e148) Thanks [@ematipico](https://github.com/ematipico)! - Fixes `position` prop on `<Image>` and `<Picture>` components breaking C
### Patch Changes - fix(print): handle `svelte:body` and fix keyframe percentage double-printing ([#18234](https://github.com/sveltejs/svelte/pull/18234)) - fix: execute uninitialized derived even if it's destroyed ([#18228](https://github.com/sveltejs/svelte/pull/18228)) - fix: use named s
### Patch Changes - [#16661](https://github.com/withastro/astro/pull/16661) [`03b8f7f`](https://github.com/withastro/astro/commit/03b8f7f7644cc1d9e738a8221d6bd377399538c0) Thanks [@ocavue](https://github.com/ocavue)! - Updates `typescript` to v6. No changes are needed from users.
### Patch Changes - [#16723](https://github.com/withastro/astro/pull/16723) [`0f10bfe`](https://github.com/withastro/astro/commit/0f10bfe70d443ebe5474a72f59c3a3e745831b98) Thanks [@matthewp](https://github.com/matthewp)! - Adds `fetchFile` option to `experimental.advancedRouting` to customize or
### Patch Changes - [#16719](https://github.com/withastro/astro/pull/16719) [`2b1df12`](https://github.com/withastro/astro/commit/2b1df120f14ae44ade0cfcc8c6bf17071061cd28) Thanks [@alexisintech](https://github.com/alexisintech)! - fix MDX syntax highlighting for indented astro codeblocks
### Patch Changes - [#16661](https://github.com/withastro/astro/pull/16661) [`03b8f7f`](https://github.com/withastro/astro/commit/03b8f7f7644cc1d9e738a8221d6bd377399538c0) Thanks [@ocavue](https://github.com/ocavue)! - Updates `typescript` to v6. No changes are needed from users. - Updated dep
### Patch Changes - [#16708](https://github.com/withastro/astro/pull/16708) [`bb709ff`](https://github.com/withastro/astro/commit/bb709ffdd45ab936eba6e2ce69dd0cb2ed75bfe4) Thanks [@fkatsuhiro](https://github.com/fkatsuhiro)! - Fixed a bug where a cascade of reloads would cause the page to crash d
### Patch Changes - [#16661](https://github.com/withastro/astro/pull/16661) [`03b8f7f`](https://github.com/withastro/astro/commit/03b8f7f7644cc1d9e738a8221d6bd377399538c0) Thanks [@ocavue](https://github.com/ocavue)! - Updates `typescript` to v6. No changes are needed from users. - Updated dep
### Patch Changes - [#16661](https://github.com/withastro/astro/pull/16661) [`03b8f7f`](https://github.com/withastro/astro/commit/03b8f7f7644cc1d9e738a8221d6bd377399538c0) Thanks [@ocavue](https://github.com/ocavue)! - Updates `typescript` to v6. No changes are needed from users.
## [2.4.0](https://github.com/googleapis/python-genai/compare/v2.3.0...v2.4.0) (2026-05-17) ### Features * Support Agent and Environment APIs. ([ef20d6b](https://github.com/googleapis/python-genai/commit/ef20d6ba54a183280c046a4346c125168d5f8a95)) ### Bug Fixes * Output_text for turns that don'
## What's Changed * feat: add prepare_extension() for batch video extension by @double-di in https://github.com/xai-org/xai-sdk-python/pull/141 **Full Changelog**: https://github.com/xai-org/xai-sdk-python/compare/v1.12.2...v1.13.0
## 6.38.0 (2026-05-13) Full Changelog: [v6.37.0...v6.38.0](https://github.com/openai/openai-node/compare/v6.37.0...v6.38.0) ### Features * **api:** add service_tier parameter to responses compact method ([423e838](https://github.com/openai/openai-node/commit/423e838c498bd1b77f3b732cfc43c54fc5d261
## 2.37.0 (2026-05-13) Full Changelog: [v2.36.0...v2.37.0](https://github.com/openai/openai-python/compare/v2.36.0...v2.37.0) ### Features * **api:** add service_tier parameter to responses compact method ([625827c](https://github.com/openai/openai-python/commit/625827c5509ece3c40e5002be37a9bd9d9
## What's changed - Added plugin dependency enforcement: `claude plugin disable` now refuses when another enabled plugin depends on the target (with a copy-pasteable disable-chain hint), and `claude plugin enable` force-enables transitive dependencies - Added projected context cost (per-turn and pe
## [2.3.0](https://github.com/googleapis/python-genai/compare/v2.2.0...v2.3.0) (2026-05-15) ### Features * Add content union to UserInputStep ([a5059a8](https://github.com/googleapis/python-genai/commit/a5059a82dc596f9555dd3221aa6e7414d50df24a)) * Interaction.{output_text,output_image,output_audi
## What's changed - Added new `claude agents` flags: `--add-dir`, `--settings`, `--mcp-config`, `--plugin-dir`, `--permission-mode`, `--model`, `--effort`, and `--dangerously-skip-permissions` to configure dispatched background sessions - Fast mode now uses Opus 4.7 by default (previously Opus 4.6)
### Patch Changes - fix: prevent XSS on `hydratable` from user contents ([`a16ebc67bbcf8f708360195687e1b2719463e1a4`](https://github.com/sveltejs/svelte/commit/a16ebc67bbcf8f708360195687e1b2719463e1a4)) - chore: bump devalue ([#18219](https://github.com/sveltejs/svelte/pull/18219)) - fix: d
### Patch Changes - fix: leave stale promises to wait for a later resolution, instead of rejecting ([#18180](https://github.com/sveltejs/svelte/pull/18180)) - fix: keep dependencies of `$state.eager/pending` ([#18218](https://github.com/sveltejs/svelte/pull/18218)) - fix: reapply context af
### Patch Changes - [#16737](https://github.com/withastro/astro/pull/16737) [`bd84f33`](https://github.com/withastro/astro/commit/bd84f33d68cfa7d077e0a638970e28b0a9bd83db) Thanks [@matthewp](https://github.com/matthewp)! - Fixes a reflected XSS vulnerability where slot names on hydrated component
Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/v8.0.13/packages/vite/CHANGELOG.md) for details.
## Codex App Ollama 0.24 includes support for the Codex App, OpenAI's desktop experience for working on Codex threads in parallel with built-in worktree support and git functionality. ```bash ollama launch codex-app ``` <img width="2088" height="1404" alt="CleanShot 2026-05-14 at 15 04 18
## What's changed - Added `terminalSequence` field to hook JSON output so hooks can emit desktop notifications, window titles, and bells without a controlling terminal - Added `CLAUDE_CODE_PLUGIN_PREFER_HTTPS` to clone GitHub plugin sources over HTTPS instead of SSH, for environments without a GitH
## What's Changed * `ollama launch opencode` now supports vision models with image inputs * Fixed formatting of Claude tool results when using local image paths **Full Changelog**: https://github.com/ollama/ollama/compare/v0.23.3...v0.23.4
## 0.102.0 (2026-05-13) Full Changelog: [v0.101.0...v0.102.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.101.0...v0.102.0) ### Features * **api:** Add BetaManagedAgentsSearchResultBlock types ([3681f10](https://github.com/anthropics/anthropic-sdk-python/commit/3681f1042608b6be4
## 0.96.0 (2026-05-13) Full Changelog: [sdk-v0.95.2...sdk-v0.96.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.95.2...sdk-v0.96.0) ### Features * **api:** Add BetaManagedAgentsSearchResultBlock types ([08f02f3](https://github.com/anthropics/anthropic-sdk-typescript/commi
### Patch Changes - Updated dependencies \[[`d365c97`](https://github.com/withastro/astro/commit/d365c975ba2d88fc1dbdfe698df2bf9e2eafadce)]: - @astrojs/internal-helpers@0.9.1
### Patch Changes - [#16642](https://github.com/withastro/astro/pull/16642) [`53059be`](https://github.com/withastro/astro/commit/53059bec978a5124fc61a23035cefbfc93754a01) Thanks [@ocavue](https://github.com/ocavue)! - Adds support for TypeScript v6 to peer dependencies range.
### Patch Changes - [#16716](https://github.com/withastro/astro/pull/16716) [`04fdbb2`](https://github.com/withastro/astro/commit/04fdbb29978d5a00acfb956538e54256ae24b486) Thanks [@delucis](https://github.com/delucis)! - Drops support for versions of VS Code below 1.101.0 [May 2025]
### Patch Changes - Updated dependencies \[[`d365c97`](https://github.com/withastro/astro/commit/d365c975ba2d88fc1dbdfe698df2bf9e2eafadce)]: - @astrojs/internal-helpers@0.9.1
### Patch Changes - [#16716](https://github.com/withastro/astro/pull/16716) [`04fdbb2`](https://github.com/withastro/astro/commit/04fdbb29978d5a00acfb956538e54256ae24b486) Thanks [@delucis](https://github.com/delucis)! - Updates internal dependencies - Updated dependencies \[[`d365c97`](https:
### Patch Changes - [#16716](https://github.com/withastro/astro/pull/16716) [`04fdbb2`](https://github.com/withastro/astro/commit/04fdbb29978d5a00acfb956538e54256ae24b486) Thanks [@delucis](https://github.com/delucis)! - Drops support for versions of VS Code below 1.101.0 [May 2025]
### Patch Changes - Updated dependencies \[[`d365c97`](https://github.com/withastro/astro/commit/d365c975ba2d88fc1dbdfe698df2bf9e2eafadce)]: - @astrojs/internal-helpers@0.9.1
### Patch Changes - [#15723](https://github.com/withastro/astro/pull/15723) [`9256345`](https://github.com/withastro/astro/commit/92563452ce866d9f9b950ad4b2adc808d10e8014) Thanks [@rururux](https://github.com/rururux)! - Fixes an issue where the `<Prism />` component failed to work in Cloudflare
### Patch Changes - [#16675](https://github.com/withastro/astro/pull/16675) [`11d4592`](https://github.com/withastro/astro/commit/11d4592e9498e900b433ba94abed9cd615a9350b) Thanks [@ascorbic](https://github.com/ascorbic)! - Fixes a regression where `Astro.cache` was `undefined` when `experimental.
Ollama 0.30 is now available, with improved compatibility and performance using [llama.cpp](https://github.com/ggml-org/llama.cpp). This augments the MLX engine on Apple Silicon, bringing support to a wider range of hardware. This release brings support for a wider range of models, including GGUF
## [2.2.0](https://github.com/googleapis/python-genai/compare/v2.1.0...v2.2.0) (2026-05-12) ### Features * Added missing FunctionCallResultDelta type and `arguments` field to the ArgumentDelta type ([b0131f8](https://github.com/googleapis/python-genai/commit/b0131f80c2da97926bcef00b4abef9334272ee
## What's changed - Improved Agent tool `subagent_type` matching to accept case- and separator-insensitive values (e.g. `"Code Reviewer"` resolves to `code-reviewer`) - Updated agent color palette - Fixed `/goal` silently hanging when `disableAllHooks` or `allowManagedHooksOnly` is set — now shows
## [2.1.0](https://github.com/googleapis/python-genai/compare/v2.0.1...v2.1.0) (2026-05-12) ### Features * Add gemini-3.1-flash-lite to model options ([2d5e0fa](https://github.com/googleapis/python-genai/commit/2d5e0fad56e323cfbd16728655eb1ede8e6625f5)) * Add parameters to video response_format.
## What's Changed * mlx: refined model push behavior by @dhiltgen in https://github.com/ollama/ollama/pull/15431 * test: integration test hardening by @dhiltgen in https://github.com/ollama/ollama/pull/13532 * app: harden update flows by @dhiltgen in https://github.com/ollama/ollama/pull/16100 *
## What's changed - Added agent view (Research Preview): a single list of every Claude Code session — running, blocked on you, or done. Run `claude agents` to get started. See https://code.claude.com/docs/en/agent-view - Added `/goal` command: set a completion condition and Claude keeps working acr
## 0.101.0 (2026-05-11) Full Changelog: [v0.100.0...v0.101.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.100.0...v0.101.0) ### Features * **aws:** Add AWS client for Claude Platform on AWS ([1e70e3a](https://github.com/anthropics/anthropic-sdk-python/commit/1e70e3a21d57a9672168
## 0.3.0 (2026-06-05) Full Changelog: [foundry-sdk-v0.2.4...foundry-sdk-v0.3.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/foundry-sdk-v0.2.4...foundry-sdk-v0.3.0) ### Features * **api:** mark Claude Opus 4.1 as deprecated ([4ee46f2](https://github.com/anthropics/anthropic-sdk
## 0.95.2 (2026-05-11) Full Changelog: [sdk-v0.95.1...sdk-v0.95.2](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.95.1...sdk-v0.95.2)
Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/create-vite@9.0.7/packages/create-vite/CHANGELOG.md) for details.
Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/v8.0.12/packages/vite/CHANGELOG.md) for details.
## What's changed - Internal fixes
## [2.0.1](https://github.com/googleapis/python-genai/compare/v2.0.0...v2.0.1) (2026-05-09) ### Bug Fixes * Update response_format field names to snake_case. ([97142b1](https://github.com/googleapis/python-genai/commit/97142b11fa71ccb5b6b844662db5d4478a50da4c))
## What's changed - [VSCode] Fixed extension failing to activate on Windows
### Added - Add `@container-size` utility ([#18901](https://github.com/tailwindlabs/tailwindcss/pull/18901)) - Add `scrollbar-{auto,thin,none}` utilities for `scrollbar-width`, and `scrollbar-thumb-*` / `scrollbar-track-*` color utilities for `scrollbar-color` ([#19981](https://github.com/tailwi
## What's changed - Added `CLAUDE_CODE_ENABLE_FEEDBACK_SURVEY_FOR_OTEL` to re-enable the session quality survey for enterprises capturing responses through OpenTelemetry - Added `settings.autoMode.hard_deny` for auto mode classifier rules that block unconditionally regardless of user intent or allo
## What's changed - Added `worktree.baseRef` setting (`fresh` | `head`) to choose whether `--worktree`, `EnterWorktree`, and agent-isolation worktrees branch from `origin/<default>` or local `HEAD`. **Note:** the default `fresh` changes `EnterWorktree`'s base back to `origin/<default>` (it has been
## What's Changed * `ollama launch` no longer includes Claude Desktop due to the third-party integration being limited to Anthropic models. * Use `ollama launch claude-desktop --restore` to restore Claude Desktop to its normal state. * `/api/show` responses are now cached, improving median lat
This release contains security fixes for the following advisories: High: - [GHSA-8h8q-6873-q5fj: Denial of Service with Server Components](https://github.com/vercel/next.js/security/advisories/GHSA-8h8q-6873-q5fj) - [GHSA-267c-6grr-h53f: Middleware / Proxy bypass in App Router applications via
> [!NOTE] > This release contains security fixes and backported bug fixes. It does **not** include all pending features/changes on canary. ### Security Fixes The following advisories have been addressed: **High:** - [GHSA-8h8q-6873-q5fj: Denial of Service with Server Components](https://g
## [2.0.0](https://github.com/googleapis/js-genai/compare/v1.52.0...v2.0.0) (2026-05-07) ### ⚠ BREAKING CHANGES - Interactions Only Note: The breaking changes are only in interactions. `GenerateContent` usage in unaffected. Refer to https://ai.google.dev/gemini-api/docs/interactions-breaking-chan
### Patch Changes - [#16646](https://github.com/withastro/astro/pull/16646) [`15fbc41`](https://github.com/withastro/astro/commit/15fbc41bb2fe64e8aee15acbe01abb4792145e8a) Thanks [@matthewp](https://github.com/matthewp)! - Fixes local images returning 404 on non-prerendered pages when using the g
## 6.37.0 (2026-05-07) Full Changelog: [v6.36.0...v6.37.0](https://github.com/openai/openai-node/compare/v6.36.0...v6.37.0) ### Features * **api:** add quantity field to admin organization usage responses ([273a8f7](https://github.com/openai/openai-node/commit/273a8f73e65839fb4d2ebc2a54ccc38383bd
## 2.36.0 (2026-05-07) Full Changelog: [v2.35.1...v2.36.0](https://github.com/openai/openai-python/compare/v2.35.1...v2.36.0) ### Features * **api:** manual updates ([13c639c](https://github.com/openai/openai-python/commit/13c639cc7d57e4fbd4406563511e15eeb88a54b2)) * **api:** realtime 2 ([8fe0ab8
## 0.95.1 (2026-05-07) Full Changelog: [sdk-v0.95.0...sdk-v0.95.1](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.95.0...sdk-v0.95.1) ### Chores * redact api-key headers in debug logs ([fad8fee](https://github.com/anthropics/anthropic-sdk-typescript/commit/fad8feeb51d1b9baf
### Minor Changes - [#16639](https://github.com/withastro/astro/pull/16639) [`4d72482`](https://github.com/withastro/astro/commit/4d7248223b919bfd3557fba6f56b4474b4bd58c7) Thanks [@ematipico](https://github.com/ematipico)! - The adapter now depends on Astro 6.3.0.
### Minor Changes - [#16639](https://github.com/withastro/astro/pull/16639) [`4d72482`](https://github.com/withastro/astro/commit/4d7248223b919bfd3557fba6f56b4474b4bd58c7) Thanks [@ematipico](https://github.com/ematipico)! - The adapter now depends on Astro 6.3.0.
# Generated by Speakeasy CLI [mistralai 2.4.5](https://pypi.org/project/mistralai/2.4.5) ## Python SDK Changes: * `mistral.workflows.executions.stream()`: `response.[].data.data.union(CustomTaskInProgressResponse).attributes.payload` **Changed** (Breaking ⚠️) * `mistral.workflows.events.get_stream_
### Patch Changes - [#16627](https://github.com/withastro/astro/pull/16627) [`5778cb7`](https://github.com/withastro/astro/commit/5778cb75515112e605da2aba5331646818802bc8) Thanks [@Princesseuh](https://github.com/Princesseuh)! - Fixes unintended dependency on the `typescript` package being availa
### Patch Changes - [#16260](https://github.com/withastro/astro/pull/16260) [`354e231`](https://github.com/withastro/astro/commit/354e23191f6a85fd466b512d378959cc12aebb01) Thanks [@gameroman](https://github.com/gameroman)! - Refactors internal config logic to remove the `dlv` dependency in favor
### Minor Changes - [#16366](https://github.com/withastro/astro/pull/16366) [`d69f858`](https://github.com/withastro/astro/commit/d69f858475bee448d0873df4579e1c635223c248) Thanks [@matthewp](https://github.com/matthewp)! - Adds a new `experimental.advancedRouting` option that lets you take full c
### Minor Changes - [#16519](https://github.com/withastro/astro/pull/16519) [`1b1c218`](https://github.com/withastro/astro/commit/1b1c218c2cf76806f94afbd1cdc2af27c8abc6d0) Thanks [@louisescher](https://github.com/louisescher)! - Adds support for redirecting URLs in remote image optimization.
Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/v8.0.11/packages/vite/CHANGELOG.md) for details.
Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/v7.3.3/packages/vite/CHANGELOG.md) for details.
## What's Changed * Add none and medium reasoning effort levels by @shawnthapa in https://github.com/xai-org/xai-sdk-python/pull/139 * Bump version from 1.12.1 to 1.12.2 by @shawnthapa in https://github.com/xai-org/xai-sdk-python/pull/140 **Full Changelog**: https://github.com/xai-org/xai-sdk-pyth
## What's changed - Added `CLAUDE_CODE_SESSION_ID` environment variable to the Bash tool subprocess environment, matching the `session_id` passed to hooks - Added `CLAUDE_CODE_DISABLE_ALTERNATE_SCREEN=1` env var to opt out of the fullscreen alternate-screen renderer and keep the conversation in the
## 2.35.1 (2026-05-06) Full Changelog: [v2.35.0...v2.35.1](https://github.com/openai/openai-python/compare/v2.35.0...v2.35.1) ### Bug Fixes * **api:** fix imagegen `size` enum regression ([4484653](https://github.com/openai/openai-python/commit/44846536bc3b02c393daa5bae70a85de04c7f621))
This release contains security fixes for the following advisories: High: - [GHSA-8h8q-6873-q5fj: Denial of Service with Server Components](https://github.com/vercel/next.js/security/advisories/GHSA-8h8q-6873-q5fj) - [GHSA-267c-6grr-h53f: Middleware / Proxy bypass in App Router applications via
This release contains security fixes for the following advisories: High: - [GHSA-8h8q-6873-q5fj: Denial of Service with Server Components](https://github.com/vercel/next.js/security/advisories/GHSA-8h8q-6873-q5fj) - [GHSA-267c-6grr-h53f: Middleware / Proxy bypass in App Router applications via
## 2.35.0 (2026-05-06) Full Changelog: [v2.34.0...v2.35.0](https://github.com/openai/openai-python/compare/v2.34.0...v2.35.0) ### Features * **api:** update image 2 ([0ba55d7](https://github.com/openai/openai-python/commit/0ba55d7569565045426e1587906a70d5682a4bba)) * **api:** manual updates ([72b
## React Server Components - Type hardening and performance improvements ([#36425](https://github.com/facebook/react/pull/36425) by @eps1lon and @unstubbable)
## React Server Components - Type hardening and performance improvements ([#36425](https://github.com/facebook/react/pull/36425) by @eps1lon and @unstubbable)
## React Server Components - Type hardening and performance improvements ([#36425](https://github.com/facebook/react/pull/36425) by @eps1lon and @unstubbable)
## 0.95.0 (2026-05-06) Full Changelog: [sdk-v0.94.0...sdk-v0.95.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.94.0...sdk-v0.95.0) ### Features * **api:** add support for Managed Agents multiagents and outcomes, webhooks, vault validation ([e0c0e9b](https://github.com/an
## 0.100.0 (2026-05-06) Full Changelog: [v0.99.0...v0.100.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.99.0...v0.100.0) ### Features * **api:** add support for Managed Agents multiagents and outcomes, webhooks, vault validation ([3b3deee](https://github.com/anthropics/anthropi
## What's changed - Fixed VS Code extension failing to activate on Windows due to a hardcoded build path in the bundled SDK (`createRequire` polyfill bug) - Fixed Mantle endpoint authentication failing with missing `x-api-key` header
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.
## What's changed - Added `--plugin-url <url>` flag to fetch a plugin `.zip` archive from a URL for the current session - Added `CLAUDE_CODE_FORCE_SYNC_OUTPUT=1` env var to force-enable synchronized output on terminals that auto-detection misses (e.g. Emacs `eat`) - Added `CLAUDE_CODE_PACKAGE_MANAG
Node.js v26.1.0
## Gemma 4 MTP (Multi-token Processing) for the MLX runner Gemma 4 MTP speculative decoding is now supported on Macs. This can give over a 2x speed increase for the Gemma 4 31B model on coding tasks. ``` ollama run gemma4:31b-coding-mtp-bf16 ``` ## What's Changed * Update MLX and MLX-C wit
## 0.99.0 (2026-05-05) Full Changelog: [v0.98.1...v0.99.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.98.1...v0.99.0) ### Features * **client:** allow targeting a workspace for OIDC federation token exchange ([4ba8067](https://github.com/anthropics/anthropic-sdk-python/commit/4
## 0.94.0 (2026-05-05) Full Changelog: [sdk-v0.93.0...sdk-v0.94.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.93.0...sdk-v0.94.0) ### Features * **client:** allow targeting a workspace for OIDC federation token exchange ([bde6620](https://github.com/anthropics/anthropic
At Google I/O we released Gemini 3.5, our latest series of models combining frontier intelligence with action.
Node.js v26.0.0
## What's changed - Bare `/color` (no args) now picks a random session color - `/mcp` now shows the tool count for connected servers and flags servers that connected with 0 tools - `--plugin-dir` now accepts `.zip` plugin archives in addition to directories - `--channels` now works with console (AP
## [1.52.0](https://github.com/googleapis/js-genai/compare/v1.51.0...v1.52.0) (2026-05-04) ### Features * [Python] Multimodal file search ([e626bef](https://github.com/googleapis/js-genai/commit/e626bef1a780a54b5b3fe04f062adf708335bd58)) * Multimodal file search ([54caf6b](https://github.com/goog
## [1.75.0](https://github.com/googleapis/python-genai/compare/v1.74.0...v1.75.0) (2026-05-04) ### Features * [Python] Multimodal file search ([fe5d69e](https://github.com/googleapis/python-genai/commit/fe5d69e04026e82314dfb93f47e184e01c993a22)) ### Bug Fixes * Avoid caching stale token in asy
## 0.98.1 (2026-05-04) Full Changelog: [v0.98.0...v0.98.1](https://github.com/anthropics/anthropic-sdk-python/compare/v0.98.0...v0.98.1) ### Chores * fix typo in example ([#1754](https://github.com/anthropics/anthropic-sdk-python/issues/1754)) ([de8ba13](https://github.com/anthropics/anthropic-sd
## 6.36.0 (2026-05-01) Full Changelog: [v6.35.0...v6.36.0](https://github.com/openai/openai-node/compare/v6.35.0...v6.36.0) ### Features * **api:** add group_type/user metadata fields, update types across admin resources ([cc52f97](https://github.com/openai/openai-node/commit/cc52f9755e3ce3b29ea2
## 2.34.0 (2026-05-04) Full Changelog: [v2.33.0...v2.34.0](https://github.com/openai/openai-python/compare/v2.33.0...v2.34.0) ### Features * **api:** add external_key_id to projects, email/metadata params to users, update types ([2d232ee](https://github.com/openai/openai-python/commit/2d232eebb2f
## 0.98.0 (2026-05-04) Full Changelog: [v0.97.0...v0.98.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.97.0...v0.98.0) ### Features * **api:** improve Managed Agents APIs ([7faf393](https://github.com/anthropics/anthropic-sdk-python/commit/7faf3939a803420e7efd85cc18b67b97b429c17
## 0.93.0 (2026-05-04) Full Changelog: [sdk-v0.92.0...sdk-v0.93.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.92.0...sdk-v0.93.0) ### Features * **client:** add Workload Identity Federation, interactive OAuth, and auth profiles ([d5d6abd](https://github.com/anthropics/a
### Patch Changes - [#16552](https://github.com/withastro/astro/pull/16552) [`409f6ef`](https://github.com/withastro/astro/commit/409f6efb0cfef5b40c5e0058726bc4edbb24e2ab) Thanks [@web-dev0521](https://github.com/web-dev0521)! - Fixes an issue where existing KV namespace bindings were silently re
### Patch Changes - [#16292](https://github.com/withastro/astro/pull/16292) [`00f48ee`](https://github.com/withastro/astro/commit/00f48ee25fdc072df93210fa2d6d24ea649d4ab1) Thanks [@p-linnane](https://github.com/p-linnane)! - Fixes head metadata propagation in dev for adapters that load modules in
## Claude Desktop Claude Desktop is now supported with Ollama Launch. Claude Cowork and Claude Code are supported within the Claude Desktop App. ``` ollama launch claude-desktop ``` ### Claude Cowork <img width="1272" height="872" alt="ca1" src="https://github.com/user-attachments/asse
## What's changed - The `/model` picker now lists models from your gateway's `/v1/models` endpoint when `ANTHROPIC_BASE_URL` points at an Anthropic-compatible gateway - - Added `claude project purge [path]` to delete all Claude Code state for a project (transcripts, tasks, file history, config entr
## What's Changed * Update the CHANGELOG with missing entries by @Omar-V2 in https://github.com/xai-org/xai-sdk-python/pull/135 * Add grok-4.3 to ChatModel by @shawnthapa in https://github.com/xai-org/xai-sdk-python/pull/137 * Bump version from 1.12.0 to 1.12.1 by @shawnthapa in https://github.com/x
## 0.29.1 (2026-04-30) Full Changelog: [bedrock-sdk-v0.29.0...bedrock-sdk-v0.29.1](https://github.com/anthropics/anthropic-sdk-typescript/compare/bedrock-sdk-v0.29.0...bedrock-sdk-v0.29.1) ### Bug Fixes * **bedrock:** throw APIError for error events delivered in chunk frames ([#1021](https://gith
## 0.92.0 (2026-04-30) Full Changelog: [sdk-v0.91.1...sdk-v0.92.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.91.1...sdk-v0.92.0) ### Features * **api:** improve Managed Agents APIs ([ca1bf4a](https://github.com/anthropics/anthropic-sdk-typescript/commit/ca1bf4a9b278fdd
### Patch Changes - Bumped `@remix-run/*` dependencies: - [`fetch-router@0.18.2`](https://github.com/remix-run/remix/releases/tag/fetch-router@0.18.2)
### Patch Changes - Bumped `@remix-run/*` dependencies: - [`fetch-router@0.18.2`](https://github.com/remix-run/remix/releases/tag/fetch-router@0.18.2)
### Patch Changes - Bumped `@remix-run/*` dependencies: - [`fetch-router@0.18.2`](https://github.com/remix-run/remix/releases/tag/fetch-router@0.18.2)
### Patch Changes - Bumped `@remix-run/*` dependencies: - [`fetch-router@0.18.2`](https://github.com/remix-run/remix/releases/tag/fetch-router@0.18.2)
### Patch Changes - Bumped `@remix-run/*` dependencies: - [`session@0.4.2`](https://github.com/remix-run/remix/releases/tag/session@0.4.2)
### Patch Changes - Improve request throughput so `node-fetch-server` is now on par with native `node:http` performance in the request-inspection benchmark, while preserving Fetch API request handlers. The main optimizations lazily materialize `Request` and `Headers` objects, specialize handlers by
### Patch Changes - [#16531](https://github.com/withastro/astro/pull/16531) [`76db01d`](https://github.com/withastro/astro/commit/76db01d332a4029f46f6df7a60fae14278321d2c) Thanks [@rodrigosdev](https://github.com/rodrigosdev)! - Fixes config validation for omitted `integrations` fields with newer
### Patch Changes - [#16534](https://github.com/withastro/astro/pull/16534) [`5cf6c51`](https://github.com/withastro/astro/commit/5cf6c51188b52d22f133ea9373da0080f74701f9) Thanks [@matthewp](https://github.com/matthewp)! - Fixes compatibility with Zod 4.4.0 for the `server` config property and er
### Patch Changes - [#17027](https://github.com/withastro/astro/pull/17027) [`241250b`](https://github.com/withastro/astro/commit/241250bf126f39c86a8aedd38df106e533301752) Thanks [@ocavue](https://github.com/ocavue)! - Triggers beta prereleases for packages that are still on alpha
### Patch Changes - [#17027](https://github.com/withastro/astro/pull/17027) [`241250b`](https://github.com/withastro/astro/commit/241250bf126f39c86a8aedd38df106e533301752) Thanks [@ocavue](https://github.com/ocavue)! - Triggers beta prereleases for packages that are still on alpha
# Generated by Speakeasy CLI [mistralai 2.4.4](https://pypi.org/project/mistralai/2.4.4) ## Python SDK Changes: * `mistral.beta.libraries.update()`: `request.name` **Changed** (Breaking ⚠️) * `mistral.beta.libraries.documents.update()`: `request.name` **Changed** (Breaking ⚠️) * `mistral.beta.rag.
### Minor Changes - [#16187](https://github.com/withastro/astro/pull/16187) [`fe58071`](https://github.com/withastro/astro/commit/fe58071817f447f832d9ce4341c0b5991d3c0cda) Thanks [@gllmt](https://github.com/gllmt)! - Adds a `waitUntil` option to the `RenderOptions` so that adapters can forward ru
### Minor Changes - [#16187](https://github.com/withastro/astro/pull/16187) [`fe58071`](https://github.com/withastro/astro/commit/fe58071817f447f832d9ce4341c0b5991d3c0cda) Thanks [@gllmt](https://github.com/gllmt)! - Adds a `waitUntil` option to the `RenderOptions` so that adapters can forward ru
> 4.4.3 is the next patch release. v4.4.4 was published with no changes due to an issue running the release script for v4.4.3. ## 👉 Changelog [compare changes](https://github.com/nuxt/nuxt/compare/v4.4.2...v4.4.3) ### 🔥 Performance - **nitro:** Directly import nuxt package version ([#34567
> 3.21.3 is the next patch release. v3.21.4 was published with no changes due to an issue running the release script for v3.21.3. ## 👉 Changelog [compare changes](https://github.com/nuxt/nuxt/compare/v3.21.2...v3.21.3) ### 🔥 Performance - **nuxt:** Batch-resolve typescript hoist paths with
## [1.51.0](https://github.com/googleapis/js-genai/compare/v1.50.1...v1.51.0) (2026-04-29) ### Features * [Interactions] Add FileCitation.{custom_metadata,media_id,page_number} ([9e08ba9](https://github.com/googleapis/js-genai/commit/9e08ba923452a7028931ba4d054290115514578e)) * Add `output_info`
## [1.74.0](https://github.com/googleapis/python-genai/compare/v1.73.1...v1.74.0) (2026-04-29) ### Features * [Interactions] Add FileCitation.{custom_metadata,media_id,page_number} ([aed41ec](https://github.com/googleapis/python-genai/commit/aed41ecf4940f63446fc3e22744663be4d1057a6)) * Add `outpu
## What's Changed * docs: add video generation and extension documentation to README by @double-di in https://github.com/xai-org/xai-sdk-python/pull/127 * Add collection descriptions, field definition updates, and bytes chunking by @Omar-V2 in https://github.com/xai-org/xai-sdk-python/pull/130 * Add
### Patch Changes - Bumped `@remix-run/*` dependencies: - [`fs@0.4.3`](https://github.com/remix-run/remix/releases/tag/fs@0.4.3) - [`mime@0.4.1`](https://github.com/remix-run/remix/releases/tag/mime@0.4.1) - [`response@0.3.3`](https://github.com/remix-run/remix/releases/tag/response@0.3.3)
### Patch Changes - Fix parsing tar entries whose file body ends exactly at a chunk boundary.
### Patch Changes - Bumped `@remix-run/*` dependencies: - [`fetch-router@0.20.0`](https://github.com/remix-run/remix/releases/tag/fetch-router@0.20.0)
### Patch Changes - Bumped `@remix-run/*` dependencies: - [`node-tsx@0.1.1`](https://github.com/remix-run/remix/releases/tag/node-tsx@0.1.1) - [`terminal@0.1.1`](https://github.com/remix-run/remix/releases/tag/terminal@0.1.1)
## What's changed - Fixed OAuth authentication failing with a 401 retry loop when `CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1` is set
## What's changed - Added `ANTHROPIC_BEDROCK_SERVICE_TIER` environment variable to select a Bedrock service tier (`default`, `flex`, or `priority`), sent as the `X-Amzn-Bedrock-Service-Tier` header - Pasting a PR URL into the `/resume` search box now finds the session that created that PR (GitHub,
## What's Changed * Updated the **Gemma 4** renderer for thinking and tool calling improvements * Model recommendations are now updated without updating Ollama * Aligned the desktop app's launch page with `ollama launch` integrations * Fixed the Poolside integration title in `ollama launch`
### 2.7.14 / 2026.04.28 - feat(ext/node): add fs.Utf8Stream - feat(upgrade): delta updates via bsdiff patches (#33274) - fix(bundle): treat CSS same-document fragment URLs as external (#33492) - fix(cache): add missing CacheStorage.keys() and Cache.keys() methods (#33275) - fix(config): don't
## New models * NVIDIA's [Nemotron 3 Omni](https://ollama.com/library/nemotron3) * Poolside's first open-weight coding model - [Laguna XS.2](https://ollama.com/library/laguna-xs.2) **Full Changelog**: https://github.com/ollama/ollama/compare/v0.21.2...v0.22.0
## 6.35.0 (2026-04-28) Full Changelog: [v6.34.0...v6.35.0](https://github.com/openai/openai-node/compare/v6.34.0...v6.35.0) ### Features * **api:** Add detail to InputFileContent ([910ec5d](https://github.com/openai/openai-node/commit/910ec5d3b7c551eee367f0b10e84856b9eb171eb)) * **api:** add OAut
## 2.33.0 (2026-04-28) Full Changelog: [v2.32.0...v2.33.0](https://github.com/openai/openai-python/compare/v2.32.0...v2.33.0) ### Features * **api:** api update ([18f834a](https://github.com/openai/openai-python/commit/18f834a54f92ea827452471a46a4f442f251e2c8)) ### Bug Fixes * **api:** correct
### Patch Changes - [#16498](https://github.com/withastro/astro/pull/16498) [`4efe020`](https://github.com/withastro/astro/commit/4efe02066d236590d948db4d5474253b8217ffdb) Thanks [@matthewp](https://github.com/matthewp)! - Fixes the dependency scan failing with "No matching export for import 'def
### Minor Changes - [#16289](https://github.com/withastro/astro/pull/16289) [`5d580c0`](https://github.com/withastro/astro/commit/5d580c0b743f9e87befd74e45721f1b5ac9fa166) Thanks [@maxmalkin](https://github.com/maxmalkin)! - Adds a new `getDbError()` helper exported from `astro:db`. It walks the
### Patch Changes - [#16479](https://github.com/withastro/astro/pull/16479) [`1058428`](https://github.com/withastro/astro/commit/1058428df2d13878c6130787636dd1778273a934) Thanks [@matthewp](https://github.com/matthewp)! - Fixes a spurious `[WARN] [content] Content config not loaded` warning duri
### Minor Changes - [#16466](https://github.com/withastro/astro/pull/16466) [`31b6198`](https://github.com/withastro/astro/commit/31b619824424974d04de8669a5f803b235361cff) Thanks [@fkatsuhiro](https://github.com/fkatsuhiro)! - This change updates the Svelte integration's type shims to treat non-c
### Patch Changes - [#16471](https://github.com/withastro/astro/pull/16471) [`f56bb3f`](https://github.com/withastro/astro/commit/f56bb3fb8fdee7839805a6514016001fff0787d7) Thanks [@delucis](https://github.com/delucis)! - Adds support for TypeScript v6 to peer dependencies range - Updated depen
### Patch Changes - [#15908](https://github.com/withastro/astro/pull/15908) [`8c62159`](https://github.com/withastro/astro/commit/8c62159eac6a77c32ac533e81d9c561409993db9) Thanks [@felmonon](https://github.com/felmonon)! - Keep generated `AstroComponent` suffixes in language-server output while r
## What's changed - Added `alwaysLoad` option to MCP server config — when `true`, all tools from that server skip tool-search deferral and are always available - Added `claude plugin prune` to remove orphaned auto-installed plugin dependencies; `plugin uninstall --prune` cascades - Added a type-to-
# Generated by Speakeasy CLI [mistralai 2.4.3](https://pypi.org/project/mistralai/2.4.3) ## Python SDK Changes: * `mistral.ocr.process()`: `request.id` **Removed** (Breaking ⚠️) * `mistral.beta.rag.ingestion_pipeline_configurations.register()`: **Added** Generated with [Speakeasy CLI 1.761.1](http
## 0.91.1 (2026-04-24) Full Changelog: [sdk-v0.91.0...sdk-v0.91.1](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.91.0...sdk-v0.91.1) ### Bug Fixes * **memory:** use restrictive file mode for memory files ([#901](https://github.com/anthropics/anthropic-sdk-typescript/issues
## What's Changed * api: accept "max" as a think value by @ParthSareen in https://github.com/ollama/ollama/pull/15787 * openai: map responses reasoning effort to think by @ParthSareen in https://github.com/ollama/ollama/pull/15789 **Full Changelog**: https://github.com/ollama/ollama/compare/v
### Patch Changes - fix: don't mark deriveds while an effect is updating ([#18124](https://github.com/sveltejs/svelte/pull/18124)) - fix: do not dispatch introstart event with animation of animate directive ([#18122](https://github.com/sveltejs/svelte/pull/18122))
## What's changed - `/config` settings (theme, editor mode, verbose, etc.) now persist to `~/.claude/settings.json` and participate in project/local/policy override precedence - Added `prUrlTemplate` setting to point the footer PR badge at a custom code-review URL instead of github.com - Added `CLA
## 0.97.0 (2026-04-23) Full Changelog: [v0.96.0...v0.97.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.96.0...v0.97.0) ### Features * **api:** CMA Memory public beta ([fc30ebe](https://github.com/anthropics/anthropic-sdk-python/commit/fc30ebe5ca81204faa0b1d756b61dad176e37dcb))
## 0.29.0 (2026-04-23) Full Changelog: [bedrock-sdk-v0.28.1...bedrock-sdk-v0.29.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/bedrock-sdk-v0.28.1...bedrock-sdk-v0.29.0) ### Features * **bedrock:** use auth header for mantle client ([#866](https://github.com/anthropics/anthropi
## 0.91.0 (2026-04-23) Full Changelog: [sdk-v0.90.0...sdk-v0.91.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.90.0...sdk-v0.91.0) ### Features * **api:** CMA Memory public beta ([ddf732f](https://github.com/anthropics/anthropic-sdk-typescript/commit/ddf732f5f35c123f963f
# Generated by Speakeasy CLI [mistralai 2.4.2](https://pypi.org/project/mistralai/2.4.2) ## Python SDK Changes: * `mistral.beta.observability.chat_completion_events.search()`: `response.completion_events.results[].extra_fields.Map<extra_fields>.union(Map<string>)` **Added** (Breaking ⚠️) * `mistral
### Patch Changes - [#16458](https://github.com/withastro/astro/pull/16458) [`8cb1f42`](https://github.com/withastro/astro/commit/8cb1f42e378bfe6d2989f7c4edb3ccd45eca1f4f) Thanks [@matthewp](https://github.com/matthewp)! - Fixes Cloudflare dev and build failures caused by `@cloudflare/vite-plugin
Explore the GPT-5.5 Bio Bug Bounty: a red-teaming challenge to find universal jailbreaks for bio safety risks, with rewards up to $25,000.
Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/create-vite@9.0.6/packages/create-vite/CHANGELOG.md) for details.
Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/v8.0.10/packages/vite/CHANGELOG.md) for details.
## What's Changed * Improved reliability of the OpenClaw onboarding flow in `ollama launch` * Recommended models in `ollama launch` now appear in a fixed, canonical order * OpenClaw integration now bundles Ollama's web search plugin in OpenClaw ## New Contributors * @madflow made their
## What's changed - Added vim visual mode (`v`) and visual-line mode (`V`) with selection, operators, and visual feedback - Merged `/cost` and `/stats` into `/usage` — both remain as typing shortcuts that open the relevant tab - Create and switch between named custom themes from `/theme`, or hand-e
### Minor Changes - BREAKING CHANGE: Remix UI component render functions no longer receive props as an argument. Type component props on `Handle<Props>` and read current values from `handle.props` in both setup and render code. - Updated `anchor(floating, anchorTarget, options)` to accept either a
### Patch Changes - Bumped `@remix-run/*` dependencies: - [`fetch-router@0.18.1`](https://github.com/remix-run/remix/releases/tag/fetch-router@0.18.1)
### Patch Changes - Bumped `@remix-run/*` dependencies: - [`fetch-router@0.18.1`](https://github.com/remix-run/remix/releases/tag/fetch-router@0.18.1)
### Patch Changes - Bumped `@remix-run/*` dependencies: - [`fetch-router@0.18.2`](https://github.com/remix-run/remix/releases/tag/fetch-router@0.18.2)
### Patch Changes - Matches return decoded values for params in hostname ```ts pattern = new RoutePattern('://:subdomain.example.com/posts/:slug') url = new URL('https://café.example.com/posts/123') pattern.match(url)?.params.subdomain // Before -> 'xn--caf-dma' // After -> 'café'
### Patch Changes - Bumped `@remix-run/*` dependencies: - [`route-pattern@0.20.1`](https://github.com/remix-run/remix/releases/tag/route-pattern@0.20.1)
### Patch Changes - Updated dependencies \[[`99464ed`](https://github.com/withastro/astro/commit/99464edb5fc0968f6497328e106f26ab393668bd), [`f3485c3`](https://github.com/withastro/astro/commit/f3485c3458bc8bf70c152126e418c24f489ded9d)]: - @astrojs/internal-helpers@0.9.0 - @astrojs/un
### Patch Changes - Updated dependencies \[[`99464ed`](https://github.com/withastro/astro/commit/99464edb5fc0968f6497328e106f26ab393668bd), [`f3485c3`](https://github.com/withastro/astro/commit/f3485c3458bc8bf70c152126e418c24f489ded9d)]: - @astrojs/internal-helpers@0.9.0
### Patch Changes - [#16486](https://github.com/withastro/astro/pull/16486) [`0bae1a5`](https://github.com/withastro/astro/commit/0bae1a51f0f271403d43f5ec0ae031c9c614fd3c) Thanks [@cyphercodes](https://github.com/cyphercodes)! - Fix forwarded serverless requests with streamed bodies by preserving
### Patch Changes - [#16424](https://github.com/withastro/astro/pull/16424) [`3fcdaf1`](https://github.com/withastro/astro/commit/3fcdaf1d0613315c3d9902b66e6a70becfec3c88) Thanks [@matthewp](https://github.com/matthewp)! - Improves how `@astrojs/upgrade` spawns package manager commands so it uses
### Patch Changes - [#16419](https://github.com/withastro/astro/pull/16419) [`f3485c3`](https://github.com/withastro/astro/commit/f3485c3458bc8bf70c152126e418c24f489ded9d) Thanks [@matthewp](https://github.com/matthewp)! - Hardens nested object and package metadata lookups to ignore prototype key
### Patch Changes - [#16448](https://github.com/withastro/astro/pull/16448) [`99464ed`](https://github.com/withastro/astro/commit/99464edb5fc0968f6497328e106f26ab393668bd) Thanks [@matthewp](https://github.com/matthewp)! - Updates vite, picomatch, and unstorage to latest patch versions - [#164
### Patch Changes - Updated dependencies [[`f732f3c`](https://github.com/withastro/astro/commit/f732f3cc716342a63e5b03815243ba10964b89dc)]: - @astrojs/internal-helpers@0.10.0
### 2.7.13 / 2026.04.22 - feat(ext/node): implement node:repl module (#32799) - feat(ext/node): rewrite node:http with llhttp and native TCPWrap (#33208) - feat(upgrade): support installing from a PR (#33252) - fix(audit): migrate to bulk advisory endpoint (#33292) - fix(console): find nodejs
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.
## What's Changed ### Kimi CLI You can now install and run the Kimi CLI through Ollama. ``` ollama launch kimi --model kimi-k2.6:cloud ``` Kimi CLI with Kimi K2.6 excels at long horizon agentic execution tasks through a multi-agent system. * **MLX runner adds logprobs support** for comp
## What's changed - Forked subagents can now be enabled on external builds by setting `CLAUDE_CODE_FORK_SUBAGENT=1` - Agent frontmatter `mcpServers` are now loaded for main-thread agent sessions via `--agent` - Improved `/model`: selections now persist across restarts even when the project pins a d
# Generated by Speakeasy CLI [@mistralai/mistralai 2.2.1](https://www.npmjs.com/package/@mistralai/mistralai/v/2.2.1) ## Typescript SDK Changes: * `mistral.fim.complete()`: * `request` **Changed** * `response.choices[]` **Changed** (Breaking ⚠️) * `mistral.beta.agents.get()`: `response.metad
# Generated by Speakeasy CLI [mistralai 2.4.1](https://pypi.org/project/mistralai/2.4.1) ## Python SDK Changes: * `mistral.beta.conversations.restart_stream()`: * `request` **Changed** (Breaking ⚠️) * `response.[].data.union(message.output.delta).content.union(OutputContentChunks).union(Think
### Fixed - Ensure imports in `@import` and `@plugin` still resolve correctly when using Vite aliases in `@tailwindcss/vite` ([#19947](https://github.com/tailwindlabs/tailwindcss/pull/19947))
We’re releasing a new batch of seven unsolved problems which have come up in the course of our research at OpenAI.
## What's changed - `/resume` on large sessions is significantly faster (up to 67% on 40MB+ sessions) and handles sessions with many dead-fork entries more efficiently - Faster MCP startup when multiple stdio servers are configured; `resources/templates/list` is now deferred to first `@`-mention -
### Fixed - Canonicalization: improve canonicalizations for `tracking-*` utilities by preferring non-negative utilities (e.g. `-tracking-tighter` → `tracking-wider`) ([#19827](https://github.com/tailwindlabs/tailwindcss/pull/19827)) - Fix crash due to invalid characters in candidate (exceeding v
The open source Git project just released Git 2.54. Here is GitHub’s look at some of the most interesting features and changes introduced since last time. The post Highlights from Git 2.54 appeared first on The GitHub Blog.
Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/create-vite@9.0.5/packages/create-vite/CHANGELOG.md) for details.
Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/v8.0.9/packages/vite/CHANGELOG.md) for details.
### Patch Changes - [#16257](https://github.com/withastro/astro/pull/16257) [`e0b240e`](https://github.com/withastro/astro/commit/e0b240edea4db632138def3a9003b4b12e12f765) Thanks [@gameroman](https://github.com/gameroman)! - Removed `debug` dependency
### Patch Changes - [#16367](https://github.com/withastro/astro/pull/16367) [`a6866a7`](https://github.com/withastro/astro/commit/a6866a7ef086627f8f8237274361d8acc2f85121) Thanks [@ematipico](https://github.com/ematipico)! - Fixes an issue where build output files could contain special characters
## What's changed - Fixed a crash in the permission dialog when an agent teams teammate requested tool permission
**Note:** 7.1.0 accidentally removed the `component-hook-factories` rule, causing errors for users who referenced it in their ESLint config. This is now fixed. - Add deprecated no-op `component-hook-factories` rule for backwards compatibility. ([@mofeiZ](https://github.com/mofeiZ) in [#36307](htt
This release adds ESLint v10 support, improves performance by skipping compilation for non-React files, and includes compiler lint improvements including better `set-state-in-effect` detection, improved ref validation, and more helpful error reporting. - Add ESLint v10 support. ([@azat-io](https:
## What's changed - Changed the CLI to spawn a native Claude Code binary (via a per-platform optional dependency) instead of bundled JavaScript - Added `sandbox.network.deniedDomains` setting to block specific domains even when a broader `allowedDomains` wildcard would otherwise permit them - Fulls
### Misc Changes - Rename prefetch option `force-runtime` to `allow-runtime`: #94568 - Remove unstable_instant agent hints; insights validate by default: #94577 - [turbopack] Use an arena for `JSValue`s: #94297 - Stabilize export const prefetch: #94571 - Fix node:stream leak in webpack edge b
For release notes, check out the [release announcement blog post](https://devblogs.microsoft.com/typescript/announcing-typescript-6-0/). * [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). * [fixe
## Hermes Agent ``` ollama launch hermes ``` Hermes learns with you, automatically creating skills to better serve your workflows. Great for research and engineering tasks. <img width="1329" height="946" alt="image" src="https://github.com/user-attachments/assets/771d3383-95ed-4652-81e5-c
## What's changed - Fixed "claude-opus-4-7 is temporarily unavailable" for auto mode
## What's changed - Claude Opus 4.7 xhigh is now available! Use /effort to tune speed vs. intelligence - Auto mode is now available for Max subscribers when using Opus 4.7 - Added `xhigh` effort level for Opus 4.7, sitting between `high` and `max`. Available via `/effort`, `--effort`, and the model
## 0.96.0 (2026-04-16) Full Changelog: [v0.95.0...v0.96.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.95.0...v0.96.0) ### Features * **api:** add claude-opus-4-7, token budgets and user_profiles ([0aa2a0d](https://github.com/anthropics/anthropic-sdk-python/commit/0aa2a0d4388a39
## 0.90.0 (2026-04-16) Full Changelog: [sdk-v0.89.0...sdk-v0.90.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.89.0...sdk-v0.90.0) ### Features * **api:** add claude-opus-4-7, token budgets and user_profiles ([b26134b](https://github.com/anthropics/anthropic-sdk-typescri
The Rust team is happy to announce a new version of Rust, 1.95.0. 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 1.95.0 with: $ rustup update stable If you don't have it already, yo
> [!NOTE] > This release is backporting bug fixes. It does **not** include all pending features/changes on canary. ### Core Changes - chore: Bump reqwest to 0.13.2 (Fixes Google Fonts with Turbopack for Windows on ARM64) (#92713) - Turbopack: fix filesystem watcher config not applying follow
## 2.32.0 (2026-04-15) Full Changelog: [v2.31.0...v2.32.0](https://github.com/openai/openai-python/compare/v2.31.0...v2.32.0) ### Features * **api:** Add detail to InputFileContent ([60de21d](https://github.com/openai/openai-python/commit/60de21d1fcfbcadea0d9b8d884c73c9dc49d14ff)) * **api:** add
## What's changed - Added `/tui` command and `tui` setting — run `/tui fullscreen` to switch to flicker-free rendering in the same conversation - Changed `Ctrl+O` to toggle between normal and verbose transcript only; focus view is now toggled separately with the new `/focus` command - Added pus
### Patch Changes - [#16027](https://github.com/withastro/astro/pull/16027) [`c62516b`](https://github.com/withastro/astro/commit/c62516bbbf8fdf95d38293440d28221c048c41f0) Thanks [@fkatsuhiro](https://github.com/fkatsuhiro)! - Fixes a bug where remote image dimensions were not validated during st
### Patch Changes - [#16027](https://github.com/withastro/astro/pull/16027) [`c62516b`](https://github.com/withastro/astro/commit/c62516bbbf8fdf95d38293440d28221c048c41f0) Thanks [@fkatsuhiro](https://github.com/fkatsuhiro)! - Fixes a bug where remote image dimensions were not validated during st
### Patch Changes - [#16320](https://github.com/withastro/astro/pull/16320) [`a43eb4b`](https://github.com/withastro/astro/commit/a43eb4b40b4f81530e3c9b5e2959495900320433) Thanks [@matthewp](https://github.com/matthewp)! - Uses `redirect: 'manual'` for remote image fetches in the Cloudflare bindi
### Patch Changes - Updated dependencies \[[`99464ed`](https://github.com/withastro/astro/commit/99464edb5fc0968f6497328e106f26ab393668bd), [`f3485c3`](https://github.com/withastro/astro/commit/f3485c3458bc8bf70c152126e418c24f489ded9d)]: - @astrojs/internal-helpers@0.9.0
## What's changed - Improved the extended-thinking indicator with a rotating progress hint
Node.js v24.15.0
## [1.50.1](https://github.com/googleapis/js-genai/compare/v1.50.0...v1.50.1) (2026-04-14) ### Bug Fixes * Refactor Webhook types in GenAI SDKs for easier useage ([5100abc](https://github.com/googleapis/js-genai/commit/5100abc2cec39c29a297545fe89a22b9ba2149bf)) * Rename `webhooks.retrieve` to `we
## [1.73.1](https://github.com/googleapis/python-genai/compare/v1.73.0...v1.73.1) (2026-04-14) ### Bug Fixes * Refactor Webhook types in GenAI SDKs for easier useage ([3f36ca1](https://github.com/googleapis/python-genai/commit/3f36ca11b30904c8f82dd3e7e3b59eff3bde6a3b)) * Rename `webhooks.retrieve
## What's changed - Added `ENABLE_PROMPT_CACHING_1H` env var to opt into 1-hour prompt cache TTL on API key, Bedrock, Vertex, and Foundry (`ENABLE_PROMPT_CACHING_1H_BEDROCK` is deprecated but still honored), and `FORCE_PROMPT_CACHING_5M` to force 5-minute TTL - Added recap feature to provide contex
## 0.89.0 (2026-04-14) Full Changelog: [sdk-v0.88.0...sdk-v0.89.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.88.0...sdk-v0.89.0) ### Features * **api:** manual updates ([57c2a11](https://github.com/anthropics/anthropic-sdk-typescript/commit/57c2a11c61ef9dfdad49a3ab91c4
## 0.95.0 (2026-04-14) Full Changelog: [v0.94.1...v0.95.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.94.1...v0.95.0) ### Features * **api:** mark Sonnet and Opus 4 as deprecated ([0c1e773](https://github.com/anthropics/anthropic-sdk-python/commit/0c1e7736394585dd021b53c1f87383
# Generated by Speakeasy CLI ## 2026-04-14 15:56:48 ### Changes Based on: - OpenAPI Doc 1.0.0 - Speakeasy CLI 1.761.1 (2.879.6) https://github.com/speakeasy-api/speakeasy ### Generated - [python v2.4.0rc2] . ### Releases - [PyPI v2.4.0rc2] https://pypi.org/project/mistralai/2.4.0rc2 - . Publishin
### Patch Changes - fix: never mark a child effect root as inert ([#18111](https://github.com/sveltejs/svelte/pull/18111)) - fix: reset context after waiting on blockers of `@const` expressions ([#18100](https://github.com/sveltejs/svelte/pull/18100)) - fix: keep flushing new eager effects
## What's changed - Show thinking hints sooner during long operations
## What's Changed * ROCm: Update to ROCm 7.2.1 on Linux by @saman-amd in https://github.com/ollama/ollama/pull/15483 * gemma4: fix nothink case renderer by @drifkin in https://github.com/ollama/ollama/pull/15553 * gemma4: fix compiler error on metal by @dhiltgen in https://github.com/ollama/ollam
## What's Changed * Fix quality of gemma:e2b and gemma:e4b when thinking is disabled * ROCm: Update to ROCm 7.2.1 on Linux by @saman-amd in https://github.com/ollama/ollama/pull/15483 **Full Changelog**: https://github.com/ollama/ollama/compare/v0.20.6...v0.20.7
## What's changed - Added `path` parameter to the `EnterWorktree` tool to switch into an existing worktree of the current repository - Added PreCompact hook support: hooks can now block compaction by exiting with code 2 or returning `{"decision":"block"}` - Added background monitor support for plug
## [1.73.0](https://github.com/googleapis/python-genai/compare/v1.72.0...v1.73.0) (2026-04-13) > [!CAUTION] > **CRITICAL WARNING:** Do **not** use this version if you are implementing or relying on **webhooks**. This release contains known issues regarding webhook sdk. Please use v1.74.0 or late
## [1.50.0](https://github.com/googleapis/js-genai/compare/v1.49.0...v1.50.0) (2026-04-13) > [!CAUTION] > **CRITICAL WARNING:** Do **not** use this version if you are implementing or relying on **webhooks**. This release contains known issues regarding webhook sdk. Please use v1.51.0 or later.
## 0.94.1 (2026-04-13) Full Changelog: [v0.94.0...v0.94.1](https://github.com/anthropics/anthropic-sdk-python/compare/v0.94.0...v0.94.1) ### Bug Fixes * **streaming:** add missing events ([c6a06d8](https://github.com/anthropics/anthropic-sdk-python/commit/c6a06d80b7e87bc034bd6ade950c735da02a0be3)
### Patch Changes - [#16210](https://github.com/withastro/astro/pull/16210) [`e030bd0`](https://github.com/withastro/astro/commit/e030bd058457505b605ef573cfc71239baa963f0) Thanks [@matthewp](https://github.com/matthewp)! - Fixes `.svelte` files in `node_modules` failing with `Unknown file extensi
### Patch Changes - [#16210](https://github.com/withastro/astro/pull/16210) [`e030bd0`](https://github.com/withastro/astro/commit/e030bd058457505b605ef573cfc71239baa963f0) Thanks [@matthewp](https://github.com/matthewp)! - Fixes `.svelte` files in `node_modules` failing with `Unknown file extensi
### Patch Changes - [#16265](https://github.com/withastro/astro/pull/16265) [`7fe40bc`](https://github.com/withastro/astro/commit/7fe40bc7381d981dedad16625d89c00e31cd8fd0) Thanks [@ChrisLaRocque](https://github.com/ChrisLaRocque)! - Updates `@qwik.dev/partytown` to 0.13.2
### Patch Changes - [#16202](https://github.com/withastro/astro/pull/16202) [`b5c2fba`](https://github.com/withastro/astro/commit/b5c2fba8bf2bc315db94e525f12f7661dd357822) Thanks [@matthewp](https://github.com/matthewp)! - Fixes Actions failing with `ActionsWithoutServerOutputError` when using `o
## What's Changed * Gemma 4 tool calling ability is improved and updated to use Google's latest post-launch fixes * Parallel tool calling improved for streaming responses * [Hermes agent](https://docs.ollama.com/integrations/hermes) Ollama integration guide is now available * Ollama app is upda
## 0.94.0 (2026-04-10) Full Changelog: [v0.93.0...v0.94.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.93.0...v0.94.0) ### Features * vertex eu region ([#1658](https://github.com/anthropics/anthropic-sdk-python/issues/1658)) ([b7e157d](https://github.com/anthropics/anthropic-sdk
## 0.16.0 (2026-04-10) Full Changelog: [vertex-sdk-v0.15.0...vertex-sdk-v0.16.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/vertex-sdk-v0.15.0...vertex-sdk-v0.16.0) ### Features * vertex eu region ([#882](https://github.com/anthropics/anthropic-sdk-typescript/issues/882)) ([19
## 0.88.0 (2026-04-10) Full Changelog: [sdk-v0.87.0...sdk-v0.88.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.87.0...sdk-v0.88.0) ### Features * vertex eu region ([#882](https://github.com/anthropics/anthropic-sdk-typescript/issues/882)) ([1933857](https://github.com/an
## What's changed - Added `/team-onboarding` command to generate a teammate ramp-up guide from your local Claude Code usage - Added OS CA certificate store trust by default, so enterprise TLS proxies work without extra setup (set `CLAUDE_CODE_CERT_STORE=bundled` to use only bundled CAs) - `/ultrapl
# Generated by Speakeasy CLI [mistralai 2.3.2](https://pypi.org/project/mistralai/2.3.2) ## Python SDK Changes: * `mistral.chat.complete()`: `response.choices[].messages[]` **Changed** (Breaking ⚠️) * `mistral.agents.complete()`: `response.choices[].messages[]` **Changed** (Breaking ⚠️) * `mistral
### Patch Changes - fix: ensure proper HMR updates for dynamic components ([#18079](https://github.com/sveltejs/svelte/pull/18079)) - fix: correctly calculate `@const` blockers ([#18039](https://github.com/sveltejs/svelte/pull/18039)) - fix: freeze deriveds once their containing effects are
## [1.72.0](https://github.com/googleapis/python-genai/compare/v1.71.0...v1.72.0) (2026-04-09) ### Features * Add "eu" as a supported service location for Vertex AI platform. ([888a731](https://github.com/googleapis/python-genai/commit/888a73159db17a8f08f928ee1a85e80db1a85a1a)) * Add Live Avatar
### 2.7.12 / 2026.04.09 - feat(ext/node): add fs.SyncWriteStream (#33226) - feat(ext/node): add llhttp-based HTTPParser with native cppgc binding (#33202) - feat(ext/node): add native TLSWrap cppgc object (Rust core) (#33183) - feat: native uv_pipe_t implementation with NativePipe and FdTable
## What's changed - Added interactive Google Vertex AI setup wizard accessible from the login screen when selecting "3rd-party platform", guiding you through GCP authentication, project and region configuration, credential verification, and model pinning - Added `CLAUDE_CODE_PERFORCE_MODE` env var:
## 0.93.0 (2026-04-09) Full Changelog: [v0.92.0...v0.93.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.92.0...v0.93.0) ### Features * **api:** Add beta advisor tool ([4297dca](https://github.com/anthropics/anthropic-sdk-python/commit/4297dca285441b185ea9e3d18b7f912102b54be2))
## 0.87.0 (2026-04-09) Full Changelog: [sdk-v0.86.1...sdk-v0.87.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.86.1...sdk-v0.87.0) ### Features * **api:** Add beta advisor tool ([1e99a8d](https://github.com/anthropics/anthropic-sdk-typescript/commit/1e99a8db387b8dbc2ce5c
## OpenClaw channel setup with `ollama launch` <img width="1074" height="654" alt="image" src="https://github.com/user-attachments/assets/300ec082-c18a-4911-b3fe-82a7bc74a000" /> ## What's Changed - OpenClaw channel setup: connect WhatsApp, Telegram, Discord, and other messaging channels thro
Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/v8.0.8/packages/vite/CHANGELOG.md) for details.
## What's changed - Added focus view toggle (`Ctrl+O`) in `NO_FLICKER` mode showing prompt, one-line tool summary with edit diffstats, and final response - Added `refreshInterval` status line setting to re-run the status line command every N seconds - Added `workspace.git_worktree` to the status li
## 6.34.0 (2026-04-08) Full Changelog: [v6.33.0...v6.34.0](https://github.com/openai/openai-node/compare/v6.33.0...v6.34.0) ### Features * **api:** add phase field to Message in conversations ([eb7cbc1](https://github.com/openai/openai-node/commit/eb7cbc1cb9d8f3189b4db6b59a6ff2c45376a598)) * **cl
## 2.31.0 (2026-04-08) Full Changelog: [v2.30.0...v2.31.0](https://github.com/openai/openai-python/compare/v2.30.0...v2.31.0) ### Features * **api:** add phase field to conversations message ([3e5834e](https://github.com/openai/openai-python/commit/3e5834efb39b24e019a29dc54d890c67d18cbb54)) * **a
## 0.28.1 (2026-04-08) Full Changelog: [bedrock-sdk-v0.28.0...bedrock-sdk-v0.28.1](https://github.com/anthropics/anthropic-sdk-typescript/compare/bedrock-sdk-v0.28.0...bedrock-sdk-v0.28.1) ### Chores * update @anthropic-ai/sdk dependency version ([#870](https://github.com/anthropics/anthropic-sdk
## 0.86.1 (2026-04-08) Full Changelog: [sdk-v0.86.0...sdk-v0.86.1](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.86.0...sdk-v0.86.1) ### Chores * update @anthropic-ai/sdk dependency version ([#870](https://github.com/anthropics/anthropic-sdk-typescript/issues/870)) ([03634
Please refer the following changelogs for more information about this security release: https://vercel.com/changelog/summary-of-cve-2026-23869
## [1.49.0](https://github.com/googleapis/js-genai/compare/v1.48.0...v1.49.0) (2026-04-08) ### Features * Introduce TYPE_L16 audio content and optional fields. ([c62cb9a](https://github.com/googleapis/js-genai/commit/c62cb9a1025990ef52adf3fb5d379e180c27eb36))
> [!NOTE] > This release is backporting security and bug fixes. For more information about the fixed security vulnerability, please see https://vercel.com/changelog/summary-of-cve-2026-23869. The release does **not** include all pending features/changes on canary. ### Core Changes - Ensure ap
## React Server Components - Add more cycle protections ([#36236](https://github.com/facebook/react/pull/36236) by @eps1lon and @unstubbable)
## React Server Components - Add more cycle protections ([#36236](https://github.com/facebook/react/pull/36236) by @eps1lon and @unstubbable)
## React Server Components - Add more cycle protections ([#36236](https://github.com/facebook/react/pull/36236) by @eps1lon and @unstubbable)
## [1.71.0](https://github.com/googleapis/python-genai/compare/v1.70.0...v1.71.0) (2026-04-08) ### Features * Introduce TYPE_L16 audio content and optional fields. ([07e932f](https://github.com/googleapis/python-genai/commit/07e932f9bc8dcb224ced2b35061ede9df25432cb)) ### Documentation * Remove
## 0.2.5 (2026-04-08) Full Changelog: [aws-sdk-v0.2.4...aws-sdk-v0.2.5](https://github.com/anthropics/anthropic-sdk-typescript/compare/aws-sdk-v0.2.4...aws-sdk-v0.2.5) ### Chores * **internal:** version bump ([eb97e85](https://github.com/anthropics/anthropic-sdk-typescript/commit/eb97e8577279fb15
## 0.86.0 (2026-04-08) Full Changelog: [sdk-v0.85.0...sdk-v0.86.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.85.0...sdk-v0.86.0) ### Features * **api:** add support for Claude Managed Agents ([2ef732a](https://github.com/anthropics/anthropic-sdk-typescript/commit/2ef73
## 0.92.0 (2026-04-08) Full Changelog: [v0.91.0...v0.92.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.91.0...v0.92.0) ### Features * **api:** add support for Claude Managed Agents ([5b879a7](https://github.com/anthropics/anthropic-sdk-python/commit/5b879a7d929bd93332d777bed067b
### Patch Changes - [#16225](https://github.com/withastro/astro/pull/16225) [`756e7be`](https://github.com/withastro/astro/commit/756e7be510a315516f6aa1647c93d11e8b43f5a9) Thanks [@travisbreaks](https://github.com/travisbreaks)! - Fixes `ERR_MULTIPLE_CONSUMERS` error when using Cloudflare Queues
### Patch Changes - [#16171](https://github.com/withastro/astro/pull/16171) [`5bcd03c`](https://github.com/withastro/astro/commit/5bcd03c1852cb7a7e165017089cc39c111599530) Thanks [@Desel72](https://github.com/Desel72)! - Fixes a build error that occurred when a pre-rendered page used the `<Pictur
## What's changed - Fixed Bedrock requests failing with `403 "Authorization header is missing"` when using `AWS_BEARER_TOKEN_BEDROCK` or `CLAUDE_CODE_SKIP_BEDROCK_AUTH` (regression in 2.1.94)
## What's changed - Added support for Amazon Bedrock powered by Mantle, set `CLAUDE_CODE_USE_MANTLE=1` - Changed default effort level from medium to high for API-key, Bedrock/Vertex/Foundry, Team, and Enterprise users (control this with `/effort`) - Added compact `Slacked #channel` header with a cl
### Patch Changes - fix: invalidate `@const` tags based on visible references in legacy mode ([#18041](https://github.com/sveltejs/svelte/pull/18041)) - fix: handle parens in template expressions more robustly ([#18075](https://github.com/sveltejs/svelte/pull/18075)) - fix: disallow `--` in
## 0.91.0 (2026-04-07) Full Changelog: [v0.90.0...v0.91.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.90.0...v0.91.0) ### Features * **client:** Create Bedrock Mantle client ([#1616](https://github.com/anthropics/anthropic-sdk-python/issues/1616)) ([fd195a2](https://github.com/
## 0.28.0 (2026-04-07) Full Changelog: [bedrock-sdk-v0.27.0...bedrock-sdk-v0.28.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/bedrock-sdk-v0.27.0...bedrock-sdk-v0.28.0) ### Features * **client:** Create Bedrock Mantle client ([#810](https://github.com/anthropics/anthropic-sdk-
## 0.85.0 (2026-04-07) Full Changelog: [sdk-v0.84.0...sdk-v0.85.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.84.0...sdk-v0.85.0) ### Features * **client:** Create Bedrock Mantle client ([#810](https://github.com/anthropics/anthropic-sdk-typescript/issues/810)) ([2f1f4a
## 0.90.0 (2026-04-07) Full Changelog: [v0.89.0...v0.90.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.89.0...v0.90.0) ### Features * **api:** Add support for claude-mythos-preview ([fc7ddd8](https://github.com/anthropics/anthropic-sdk-python/commit/fc7ddd8e0296a578f09c7fa2baf00
## What's Changed * mlx: Improve M5 performance with NAX * gemma4: enable flash attention **Full Changelog**: https://github.com/ollama/ollama/compare/v0.20.3...v0.20.4
## 0.84.0 (2026-04-07) Full Changelog: [sdk-v0.83.0...sdk-v0.84.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.83.0...sdk-v0.84.0) ### Features * **api:** Add support for claude-mythos-preview ([d4057b0](https://github.com/anthropics/anthropic-sdk-typescript/commit/d4057
Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/v8.0.7/packages/vite/CHANGELOG.md) for details.
# Generated by Speakeasy CLI [mistralai 2.3.1](https://pypi.org/project/mistralai/2.3.1) ## Python SDK Changes: * `mistral.ocr.process()`: * `request` **Changed** (Breaking ⚠️) * `response.pages[]` **Changed** * `mistral.chat.complete()`: `response.choices[]` **Changed** * `mistral.fim.compl
Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/v8.0.6/packages/vite/CHANGELOG.md) for details.
## What's Changed * Gemma 4 Tool Calling improvements * Added latest models to Ollama App * OpenClaw fixes for launching TUI **Full Changelog**: https://github.com/ollama/ollama/compare/v0.20.2...v0.20.3
### Patch Changes - [#16197](https://github.com/withastro/astro/pull/16197) [`21f9fe2`](https://github.com/withastro/astro/commit/21f9fe29f5de442a3e0672ea36dbe690491f3e8c) Thanks [@SchahinRohani](https://github.com/SchahinRohani)! - Remove unused re-exports from assets/utils barrel file to fix Vi
Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/v6.4.2/packages/vite/CHANGELOG.md) for details.
Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/v7.3.2/packages/vite/CHANGELOG.md) for details.
Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/v8.0.5/packages/vite/CHANGELOG.md) for details.
Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/create-vite@9.0.4/packages/create-vite/CHANGELOG.md) for details.
Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/v8.0.4/packages/vite/CHANGELOG.md) for details.
## What's Changed * app: default app home view to new chat instead of launch by @jmorganca in https://github.com/ollama/ollama/pull/15312 **Full Changelog**: https://github.com/ollama/ollama/compare/v0.20.1...v0.20.2
## What's changed - Added `forceRemoteSettingsRefresh` policy setting: when set, the CLI blocks startup until remote managed settings are freshly fetched, and exits if the fetch fails (fail-closed) - Added interactive Bedrock setup wizard accessible from the login screen when selecting "3rd-party p
## What's Changed * bench: add prompt calibration, context size flag, and NumCtx reporting by @dhiltgen in https://github.com/ollama/ollama/pull/15158 * model/parsers: fix gemma4 arg parsing when quoted strings contain " by @drifkin in https://github.com/ollama/ollama/pull/15254 * ggml: skip cubl
## 0.89.0 (2026-04-03) Full Changelog: [v0.88.0...v0.89.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.88.0...v0.89.0) ### Features * **vertex:** add support for US multi-region endpoint ([4e732da](https://github.com/anthropics/anthropic-sdk-python/commit/4e732dada087146cfeff1f4
## 0.15.0 (2026-04-03) Full Changelog: [vertex-sdk-v0.14.4...vertex-sdk-v0.15.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/vertex-sdk-v0.14.4...vertex-sdk-v0.15.0) ### Features * **vertex:** add support for US multi-region endpoint ([5e5aea7](https://github.com/anthropics/ant
## 0.83.0 (2026-04-03) Full Changelog: [sdk-v0.82.0...sdk-v0.83.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.82.0...sdk-v0.83.0) ### Features * **vertex:** add support for US multi-region endpoint ([5e5aea7](https://github.com/anthropics/anthropic-sdk-typescript/commit
# Generated by Speakeasy CLI [mistralai 2.3.0](https://pypi.org/project/mistralai/2.3.0) ## Python SDK Changes: * `mistral.models.list()`: `response.data[].union(fine-tuned).job` **Changed** (Breaking ⚠️) * `mistral.models.retrieve()`: `response.union(fine-tuned).job` **Changed** (Breaking ⚠️) * `
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.
## What's changed - Added MCP tool result persistence override via `_meta["anthropic/maxResultSizeChars"]` annotation (up to 500K), allowing larger results like DB schemas to pass through without truncation - Added `disableSkillShellExecution` setting to disable inline shell execution in skills, cu
<img width="3748" height="1290" alt="Gemma 4" src="https://github.com/user-attachments/assets/c4727579-47b1-4c7b-8aa2-28eda15b71f5" /> ## Gemma 4 **Effective 2B (E2B)** ``` ollama run gemma4:e2b ``` **Effective 4B (E4B)** ``` ollama run gemma4:e4b ``` **26B (Mixture of Experts mod
## What's changed - Added `/powerup` — interactive lessons teaching Claude Code features with animated demos - Added `CLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE` env var to keep the existing marketplace cache when `git pull` fails, useful in offline environments - Added `.husky` to protected di
### Patch Changes - [#16161](https://github.com/withastro/astro/pull/16161) [`b51f297`](https://github.com/withastro/astro/commit/b51f2972d4c5d877f9087b86bb2b1d62c8293be5) Thanks [@matthewp](https://github.com/matthewp)! - Fixes a dev rendering issue with the Cloudflare adapter where head metadat
### Patch Changes - [#16180](https://github.com/withastro/astro/pull/16180) [`1d1448c`](https://github.com/withastro/astro/commit/1d1448c2c0e1a149709ada5d00a74f1cd7c1142b) Thanks [@matthewp](https://github.com/matthewp)! - Pre-optimizes `@preact/signals` and `preact/hooks` in the Vite dep optimiz
### Patch Changes - [#16034](https://github.com/withastro/astro/pull/16034) [`814406d`](https://github.com/withastro/astro/commit/814406de7dc3ea014b47d2d886d55c45e4e1c034) Thanks [@alexanderniebuhr](https://github.com/alexanderniebuhr)! - Fixes generated redirect files to respect Astro’s `trailin
### Patch Changes - Updated dependencies \[[`814406d`](https://github.com/withastro/astro/commit/814406de7dc3ea014b47d2d886d55c45e4e1c034)]: - @astrojs/underscore-redirects@1.0.3
### Patch Changes - Updated dependencies \[[`814406d`](https://github.com/withastro/astro/commit/814406de7dc3ea014b47d2d886d55c45e4e1c034)]: - @astrojs/underscore-redirects@1.0.3
## 0.88.0 (2026-04-01) Full Changelog: [v0.87.0...v0.88.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.87.0...v0.88.0) ### Features * **api:** add structured stop_details to message responses ([fd82d6b](https://github.com/anthropics/anthropic-sdk-python/commit/fd82d6b87ef0db5b29
## 0.2.0 (2026-04-01) Full Changelog: [aws-sdk-v0.1.0...aws-sdk-v0.2.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/aws-sdk-v0.1.0...aws-sdk-v0.2.0) ### Features * prepare aws package ([#782](https://github.com/anthropics/anthropic-sdk-typescript/issues/782)) ([f351d4d](https:/
## 0.27.0 (2026-04-01) Full Changelog: [bedrock-sdk-v0.26.4...bedrock-sdk-v0.27.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/bedrock-sdk-v0.26.4...bedrock-sdk-v0.27.0) ### Features * support API keys in Bedrock SDK ([#824](https://github.com/anthropics/anthropic-sdk-typescrip
## 0.82.0 (2026-04-01) Full Changelog: [sdk-v0.81.0...sdk-v0.82.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.81.0...sdk-v0.82.0) ### Features * **api:** add structured stop_details to message responses ([031328a](https://github.com/anthropics/anthropic-sdk-typescript/c
Eight years ago, we launched 1.1.1.1 to build a faster, more private Internet. Today, we’re sharing the results of our latest independent examination. The result: our privacy protections are working exactly as promised.
### 2.7.11 / 2026.04.01 - feat: add alpha and beta release channel support (#33098) - fix(ext/node): fire fs.watch events for immediate writes (#32935) (#32989) - fix(watch): reduce graceful shutdown timeout from 5s to 500ms (#33099)
## [1.48.0](https://github.com/googleapis/js-genai/compare/v1.47.0...v1.48.0) (2026-03-31) ### Features * Support dedicated TextAnnotationDelta for streaming tool responses ([89552ba](https://github.com/googleapis/js-genai/commit/89552baa732f41a8d733893ccccb8dd00cd9d27f)) ### Bug Fixes * Fix s
## [1.70.0](https://github.com/googleapis/python-genai/compare/v1.69.0...v1.70.0) (2026-03-31) ### Features * Support dedicated TextAnnotationDelta for streaming tool responses ([5c820f2](https://github.com/googleapis/python-genai/commit/5c820f26122c911dd9d7d48bdd4156ade46c3636)) ### Bug Fixes
## What's changed - Added `"defer"` permission decision to `PreToolUse` hooks — headless sessions can pause at a tool call and resume with `-p --resume` to have the hook re-evaluate - Added `CLAUDE_CODE_NO_FLICKER=1` environment variable to opt into flicker-free alt-screen rendering with virtualize
## 0.87.0 (2026-03-31) Full Changelog: [v0.86.0...v0.87.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.86.0...v0.87.0) ### Features * **client:** add error type field to APIStatusError ([#1587](https://github.com/anthropics/anthropic-sdk-python/issues/1587)) ([dd563c0](https://g
## 0.81.0 (2026-03-31) Full Changelog: [sdk-v0.80.0...sdk-v0.81.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.80.0...sdk-v0.81.0) ### Features * add .type field to APIError for error kind identification ([#790](https://github.com/anthropics/anthropic-sdk-typescript/issu
### 2.7.10 / 2026.03.31 - feat: add include and exclude fields to compile config (#33024) - fix(ext/http): gracefully handle consumed external in OTel ops (#33027) - fix(ext/node): `process.argv[0]` is equivalent to execPath (#28915) - fix(ext/node): add chacha20-poly1305 cipher support (#3308
Node.js v25.9.0
## What's changed - Added `CLAUDE_CODE_NO_FLICKER=1` environment variable to opt into flicker-free alt-screen rendering with virtualized scrollback - Added `PermissionDenied` hook that fires after auto mode classifier denials — return `{retry: true}` to tell the model it can retry - Added named sub
### Patch Changes - [#16151](https://github.com/withastro/astro/pull/16151) [`4978165`](https://github.com/withastro/astro/commit/4978165af4ca4c672edad904d7b6c85fc3647dd9) Thanks [@matthewp](https://github.com/matthewp)! - Fixes a dev-mode crash loop in the Cloudflare adapter when using Starlight
# Generated by Speakeasy CLI [@mistralai/mistralai 2.2.0](https://www.npmjs.com/package/@mistralai/mistralai/v/2.2.0) ## Typescript SDK Changes: * `mistral.models.update()`: `response` **Changed** (Breaking ⚠️) * `mistral.beta.connectors.listTools()`: `response` **Changed** (Breaking ⚠️) * `mistra
### Patch Changes - Updated dependencies \[[`d365c97`](https://github.com/withastro/astro/commit/d365c975ba2d88fc1dbdfe698df2bf9e2eafadce)]: - @astrojs/internal-helpers@0.9.1
### Patch Changes - [#16109](https://github.com/withastro/astro/pull/16109) [`c887b4a`](https://github.com/withastro/astro/commit/c887b4a60329b704f18e9aad6106034aac7e7ab6) Thanks [@matthewp](https://github.com/matthewp)! - Fix HMR crash when editing content collection files caused by Vite's SSR t
### Patch Changes - [#16104](https://github.com/withastro/astro/pull/16104) [`47a394d`](https://github.com/withastro/astro/commit/47a394d7cf2eb735fcee8e90830737f9e900a274) Thanks [@matthewp](https://github.com/matthewp)! - Fixes `astro preview` ignoring `vite.preview.allowedHosts` set in `astro.c
### Patch Changes - fix: correctly handle bindings on the server ([#18009](https://github.com/sveltejs/svelte/pull/18009)) - fix: prevent hydration error on async `{@html ...}` ([#17999](https://github.com/sveltejs/svelte/pull/17999)) - fix: cleanup `superTypeParameters` in `ClassDeclaratio
## What's changed - Fixed messages in Cowork Dispatch not getting delivered
## [1.47.0](https://github.com/googleapis/js-genai/compare/v1.46.0...v1.47.0) (2026-03-27) ### Features * Add custom_metadata to FileSearchResult. ([083a1e3](https://github.com/googleapis/js-genai/commit/083a1e3c22731c1712d7caab2f5d1323ca8779ad)) * Add labels field to Veo configs ([930c9c3](https
## [1.69.0](https://github.com/googleapis/python-genai/compare/v1.68.0...v1.69.0) (2026-03-27) ### Features * Add consent_audio and voice_consent_signature and AsyncSession.setup_complete ([69a02c4](https://github.com/googleapis/python-genai/commit/69a02c48e452202cdfbcfe81655da19e238fbdef)) * Add
## What's changed - Added `X-Claude-Code-Session-Id` header to API requests so proxies can aggregate requests by session without parsing the body - Added `.jj` and `.sl` to VCS directory exclusion lists so Grep and file autocomplete don't descend into Jujutsu or Sapling metadata - Fixed `--resume`
## What's Changed * Support inline file attachments by @shawnthapa in https://github.com/xai-org/xai-sdk-python/pull/122 * Add url support for FileContent by @shawnthapa in https://github.com/xai-org/xai-sdk-python/pull/123 * Bump version from 1.10.0 to 1.11.0 by @shawnthapa in https://github.com/xa
<img width="480" alt="image" src="https://github.com/user-attachments/assets/1b5ca980-b9d5-490e-99b9-f0f7b9af2c32" /> ## Ollama is now powered by MLX on Apple Silicon in preview Ollama on Apple silicon [is now built](https://ollama.com/blog/mlx) on top of Apple’s machine learning framework, ML
### 2.7.9 / 2026.03.27 - fix(cli): show clean error instead of panic for invalid --unsafely-ignore-certificate-errors value (#32868) - fix(compile): strip duplicate exe path from argv when standalone binary relaunches (#33016) - fix(compile): use execPath for process.argv[1] in standalone
## What's Changed * ggml: force flash attention off for grok by @rick-github in https://github.com/ollama/ollama/pull/15050 * mlx: fix KV cache snapshot memory leak by @jessegross in https://github.com/ollama/ollama/pull/15065 * mlxrunner: schedule periodic snapshots during prefill by @jessegross
## What's changed - Added `CLAUDE_CODE_MCP_SERVER_NAME` and `CLAUDE_CODE_MCP_SERVER_URL` environment variables to MCP `headersHelper` scripts, allowing one helper to serve multiple servers - Added conditional `if` field for hooks using permission rule syntax (e.g., `Bash(git *)`) to filter when the
### Patch Changes - Updated dependencies \[[`f3485c3`](https://github.com/withastro/astro/commit/f3485c3458bc8bf70c152126e418c24f489ded9d)]: - @astrojs/markdown-remark@7.1.1
### Patch Changes - [#16105](https://github.com/withastro/astro/pull/16105) [`23d60de`](https://github.com/withastro/astro/commit/23d60dee6eae3d7148ef87f8b44c3d7470fef0ed) Thanks [@matthewp](https://github.com/matthewp)! - Fix dev toolbar audit crash when encountering the `image` ARIA role - [
### Minor Changes - [#15804](https://github.com/withastro/astro/pull/15804) [`a5e7232`](https://github.com/withastro/astro/commit/a5e723217f30020ae82ca67190794150e9e94e15) Thanks [@merlinnot](https://github.com/merlinnot)! - Allows setting codec-specific defaults for Astro's built-in Sharp image
### Patch Changes - [#15604](https://github.com/withastro/astro/pull/15604) [`3e1ac66`](https://github.com/withastro/astro/commit/3e1ac6675d80776dc72c8a8e5f7de35aa57f56e3) Thanks [@pierreeurope](https://github.com/pierreeurope)! - Adds a temporary workaround for a Svelte bug causing empty class a
### Patch Changes - [#16002](https://github.com/withastro/astro/pull/16002) [`846f27f`](https://github.com/withastro/astro/commit/846f27f4be8508f728d237e93fcac7c6ec8227b2) Thanks [@buley](https://github.com/buley)! - Fixes file descriptor leaks from read streams that were not destroyed on client
### Patch Changes - [#16037](https://github.com/withastro/astro/pull/16037) [`fdd2c5a`](https://github.com/withastro/astro/commit/fdd2c5a2f0eb63332b018df01b2c1eb0d5c8a102) Thanks [@blimmer](https://github.com/blimmer)! - Unpin `fast-xml-parser` to `^5.5.7` to resolve entity expansion CVEs
### Minor Changes - [#15862](https://github.com/withastro/astro/pull/15862) [`06fba3a`](https://github.com/withastro/astro/commit/06fba3a9636ef45a6aedd35e04b1d67b7cf00c82) Thanks [@crutchcorn](https://github.com/crutchcorn)! - Adds support for passing a Babel config to the Preact Vite Plugin:
### Patch Changes - [#15455](https://github.com/withastro/astro/pull/15455) [`babf57f`](https://github.com/withastro/astro/commit/babf57f83f47d4cd1fa73a55863718b71c8eebf0) Thanks [@AhmadYasser1](https://github.com/AhmadYasser1)! - Fixes i18n fallback pages missing from the generated sitemap when
### Patch Changes - [#16069](https://github.com/withastro/astro/pull/16069) [`c9a5807`](https://github.com/withastro/astro/commit/c9a58073a340959f081b66d2ff50c1f2445b6b05) Thanks [@Princesseuh](https://github.com/Princesseuh)! - Updates the minimum supported version of VS Code to 1.92.0 (July 202
### Patch Changes - [#16170](https://github.com/withastro/astro/pull/16170) [`d0fe1ec`](https://github.com/withastro/astro/commit/d0fe1ec216f8f322392e34ce40378d022e495cef) Thanks [@bittoby](https://github.com/bittoby)! - Fixes edge middleware `next()` dropping the HTTP method and body when forwar
Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/v8.0.3/packages/vite/CHANGELOG.md) for details.
## What's changed - Added PowerShell tool for Windows as an opt-in preview. Learn more at https://code.claude.com/docs/en/tools-reference#powershell-tool - Added `ANTHROPIC_DEFAULT_{OPUS,SONNET,HAIKU}_MODEL_SUPPORTS` env vars to override effort/thinking capability detection for pinned default model
The Rust team has published a new point release of Rust, 1.94.1. 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 1.94.1 is as easy as: rustup update stable If you don't have
### Patch Changes - Bumped `@remix-run/*` dependencies: - [`fetch-router@0.18.1`](https://github.com/remix-run/remix/releases/tag/fetch-router@0.18.1)
### Patch Changes - Bumped `@remix-run/*` dependencies: - [`fetch-router@0.18.0`](https://github.com/remix-run/remix/releases/tag/fetch-router@0.18.0)
### Minor Changes - Add a `signal` option to `renderToStream()` so request aborts can cancel pending frame rendering without invoking `onError` (see #11431). ### Patch Changes - Add explicit public API types for UI component, mixin, scheduler, stylesheet, animation, and theme helpers so generated
### Minor Changes - BREAKING CHANGE: Middleware must now explicitly continue the request chain by calling `next()` or return a `Response`. The router no longer calls `next()` automatically when middleware returns `undefined`; instead, it throws an error to catch missing continuation bugs early.
## 6.33.0 (2026-03-25) Full Changelog: [v6.32.0...v6.33.0](https://github.com/openai/openai-node/compare/v6.32.0...v6.33.0) ### Features * **api:** add keys field to computer action types ([27a850e](https://github.com/openai/openai-node/commit/27a850e8a698cde5b7e05da70d8babb1205b2830)) * **client
## 2.30.0 (2026-03-25) Full Changelog: [v2.29.0...v2.30.0](https://github.com/openai/openai-python/compare/v2.29.0...v2.30.0) ### Features * **api:** add keys field to Click/DoubleClick/Drag/Move/Scroll computer actions ([ee1bbed](https://github.com/openai/openai-python/commit/ee1bbeddbb38dab8175
### 2.7.8 / 2026.03.25 - feat(core): implement NodeRuntime CDP domain and fix --inspect-brk blocking (#32714) - feat(ext/crypto): implement P-521 sign, verify, and ECDH derive (#32602) - feat(ext/napi): add node_api_create_object_with_named_properties (#32906) - feat(ext/telemetry): add con
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.
## What's changed - Added `managed-settings.d/` drop-in directory alongside `managed-settings.json`, letting separate teams deploy independent policy fragments that merge alphabetically - Added `CwdChanged` and `FileChanged` hook events for reactive environment management (e.g., direnv) - Added `sa
## Visual Studio Code Microsoft Visual Studio Code now directly integrates with Ollama via GitHub Copilot. If you have Ollama installed, any local or cloud model from Ollama can be selected for use within visual studio code. <img width="3410" height="2076" alt="Ollama screenshot 2026-03-2
## What's Changed * Add video extension API and reference_image_urls support by @Omar-V2 in https://github.com/xai-org/xai-sdk-python/pull/120 * Prepare to release v1.10.0 of the xAI Python SDK by @Omar-V2 in https://github.com/xai-org/xai-sdk-python/pull/121 **Full Changelog**: https://github.com
Node.js v24.14.1
Node.js v25.8.2
We are excited to announce the release of PyTorch® 2.11 (release notes)! The PyTorch 2.11 release features the following changes: Differentiable Collectives for Distributed Training FlexAttention now has a FlashAttention-4...
Changes since langchain-openai==1.1.11 fix(openai): bump min core version (#36180) release(openai): 1.1.12 (#36178) fix(core,model-profiles): add missing `ModelProfile` fields, warn on schema drift (#36129) fix(openai): support phase parameter (#36161) fix(openai): preserve namespace field in strea
Changes since langchain-core==1.2.20 release(core): 1.2.21 (#36179) fix(core,model-profiles): add missing `ModelProfile` fields, warn on schema drift (#36129) chore(core): remove stale blockbuster allowlist for deleted context module (#36168) ci: suppress pytest streaming output in CI (#36092)
# Generated by Speakeasy CLI [mistralai 2.1.3](https://pypi.org/project/mistralai/2.1.3) ## Python SDK Changes: * `mistral.beta.connectors.list_tools()`: **Added** Generated with [Speakeasy CLI 1.754.0](https://github.com/speakeasy-api/speakeasy/releases) Publishing Completed
# Generated by Speakeasy CLI [@mistralai/mistralai 2.1.2](https://www.npmjs.com/package/@mistralai/mistralai/v/2.1.2) ## Typescript SDK Changes: * `mistral.beta.connectors.listTools()`: **Added** Generated with [Speakeasy CLI 1.751.1](https://github.com/speakeasy-api/speakeasy/releases) Publishin
### Minor Changes - feat: export TweenOptions, SpringOptions, SpringUpdateOptions and Updater from svelte/motion ([#17967](https://github.com/sveltejs/svelte/pull/17967)) ### Patch Changes - fix: ensure HMR wrapper forwards correct start/end nodes to active effect ([#17985](https://github.com
Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/plugin-legacy@8.0.2/packages/plugin-legacy/CHANGELOG.md) for details.
### Core Changes - Support type cast expressions in page static info extractor: #92837 - Fix dev mode hydration failure when page is served from HTTP cache: #92892 - [devtools] Preserve full code frames in browser overlay: #92621 - Enable prefetchInlining by default: #92863 - Replace deprecated `mo
### Patch Changes - fix: hydration comments during hmr ([#17975](https://github.com/sveltejs/svelte/pull/17975)) - fix: null out `effect.b` in `destroy_effect` ([#17980](https://github.com/sveltejs/svelte/pull/17980)) - fix: group sync statements ([#17977](https://github.com/sveltejs/svelte
## What's changed - Added `--bare` flag for scripted `-p` calls — skips hooks, LSP, plugin sync, and skill directory walks; requires `ANTHROPIC_API_KEY` or an `apiKeyHelper` via `--settings` (OAuth and keychain auth disabled); auto-memory fully disabled - Added `--channels` permission relay — chann
### Patch Changes - Updated dependencies \[[`3b8d473`](https://github.com/withastro/astro/commit/3b8d473768bf7d356a21a0a432e6a33f90928a9e)]: - @astrojs/underscore-redirects@1.0.2
### Patch Changes - Updated dependencies \[[`3b8d473`](https://github.com/withastro/astro/commit/3b8d473768bf7d356a21a0a432e6a33f90928a9e)]: - @astrojs/underscore-redirects@1.0.2
### Patch Changes - [#15978](https://github.com/withastro/astro/pull/15978) [`6d182fe`](https://github.com/withastro/astro/commit/6d182fe267586e2ee57113ad559912a456019306) Thanks [@seroperson](https://github.com/seroperson)! - Fixes a bug where Astro Actions didn't properly support nested object
### Patch Changes - [#15979](https://github.com/withastro/astro/pull/15979) [`3b8d473`](https://github.com/withastro/astro/commit/3b8d473768bf7d356a21a0a432e6a33f90928a9e) Thanks [@alexanderniebuhr](https://github.com/alexanderniebuhr)! - Fixes an issue where redirects in `_redirects` file where
# Generated by Speakeasy CLI [@mistralai/mistralai 2.1.1](https://www.npmjs.com/package/@mistralai/mistralai/v/2.1.1) ## Typescript SDK Changes: * `mistral.beta.conversations.start()`: * `request.tools[]` **Changed** (Breaking ⚠️) * `mistral.beta.conversations.list()`: `response.[].union(ModelC
# Generated by Speakeasy CLI [@mistralai/mistralai 2.1.0](https://www.npmjs.com/package/@mistralai/mistralai/v/2.1.0) ## Typescript SDK Changes: * `mistral.beta.agents.updateVersion()`: `response` **Changed** (Breaking ⚠️) * `mistral.beta.agents.get()`: `response` **Changed** (Breaking ⚠️) * `mist
## What's Changed * Update grok-4.20 and multi-agent model variants in ChatModel by @shawnthapa in https://github.com/xai-org/xai-sdk-python/pull/117 * Bump version from 1.9.0 to 1.9.1 by @shawnthapa in https://github.com/xai-org/xai-sdk-python/pull/118 **Full Changelog**: https://github.com/xai-o
## What's changed - Added `rate_limits` field to statusline scripts for displaying Claude.ai rate limit usage (5-hour and 7-day windows with `used_percentage` and `resets_at`) - Added `source: 'settings'` plugin marketplace source — declare plugin entries inline in settings.json - Added CLI tool us
Kimi K2.5 is now on Workers AI, helping you power agents entirely on Cloudflare’s Developer Platform. Learn how we optimized our inference stack and reduced inference costs for internal agent use cases.
### Patch Changes - [#15950](https://github.com/withastro/astro/pull/15950) [`acce5e8`](https://github.com/withastro/astro/commit/acce5e84046f1f459a8f37686cf6054e2243f5ad) Thanks [@matthewp](https://github.com/matthewp)! - Fixes a build regression in projects with multiple frontend integrations w
### Patch Changes - [#15961](https://github.com/withastro/astro/pull/15961) [`7e8d0ee`](https://github.com/withastro/astro/commit/7e8d0ee9ca2e473a276ed5d400e40965ace4c3e8) Thanks [@matthewp](https://github.com/matthewp)! - Fix Cloudflare dev SSR dependency optimization to compile `.svelte.js` and
### Patch Changes - [#16224](https://github.com/withastro/astro/pull/16224) [`a2b9eeb`](https://github.com/withastro/astro/commit/a2b9eeb14e300c9b6ce1d6ea423d20f4ef9d92f5) Thanks [@fkatsuhiro](https://github.com/fkatsuhiro)! - Fix React 19 "Float" mechanism injecting <link rel="preload"> into Ast
### Patch Changes - [#16079](https://github.com/withastro/astro/pull/16079) [`aa26636`](https://github.com/withastro/astro/commit/aa266364fe9e105317b66e218fe04567307fb57f) Thanks [@empoulter-uclan](https://github.com/empoulter-uclan)! - Fix vercel ISR path rewrite
> [!NOTE] > This release is backporting bug fixes. It does **not** include all pending features/changes on canary. ### Core Changes - feat(next/image): add lru disk cache and images.maximumDiskCacheSize (#91660) - Fix(pages-router): restore Content-Length and ETag for /_next/data/ JSON respons
### 2.7.7 / 2026.03.19 - fix(core): implement select fallback on macOS (#32812) - fix(ext/node): add disabled process function stubs in worker threads (#32809) - fix(ext/node): add key/IV length validation for aes-128-cbc and ecb cipher modes (#32824) - fix(ext/node): improve node:dns modul
Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/create-vite@9.0.3/packages/create-vite/CHANGELOG.md) for details.
Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/plugin-legacy@8.0.1/packages/plugin-legacy/CHANGELOG.md) for details.
## What's Changed * feat: add image/video batch support and input_file_id by @double-di in https://github.com/xai-org/xai-sdk-python/pull/112 * Fix unknown status handling in polling loops by @Omar-V2 in https://github.com/xai-org/xai-sdk-python/pull/113 * Use model type aliases in image and vide
## What's changed - Added `--console` flag to `claude auth login` for Anthropic Console (API billing) authentication - Added "Show turn duration" toggle to the `/config` menu - Fixed `claude -p` hanging when spawned as a subprocess without explicit stdin (e.g. Python `subprocess.run`) - Fixed Ctrl+
## 0.86.0 (2026-03-18) Full Changelog: [v0.85.0...v0.86.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.85.0...v0.86.0) ### Features * add support for filesystem memory tools ([#1247](https://github.com/anthropics/anthropic-sdk-python/issues/1247)) ([235d218](https://github.com/a
## 0.80.0 (2026-03-18) Full Changelog: [sdk-v0.79.0...sdk-v0.80.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.79.0...sdk-v0.80.0) ### Features * **api:** manual updates ([dd12f1a](https://github.com/anthropics/anthropic-sdk-typescript/commit/dd12f1a29c4a8f4554caa8c7023b
Changes since langchain-core==1.2.19 release(core): 1.2.20 (#36085) fix(core): trace invocation params in metadata (#36080) feat: Add LangSmith integration metadata to create_agent and init_chat_model (#35810) feat(core): harden anti-ssrf (#35960) ci: avoid unnecessary dep installs in lint targets
### Patch Changes - [#15965](https://github.com/withastro/astro/pull/15965) [`2dca307`](https://github.com/withastro/astro/commit/2dca3074ed3de24bd23d0a17fd10a168660b2ac1) Thanks [@matthewp](https://github.com/matthewp)! - Fixes client hydration for components imported through Node.js subpath imp
### Patch Changes - [#15864](https://github.com/withastro/astro/pull/15864) [`d3c7de9`](https://github.com/withastro/astro/commit/d3c7de9253e9cb31fa5c4bf9f4bdf59dd1ada7b0) Thanks [@florian-lefebvre](https://github.com/florian-lefebvre)! - Removes temporary support for Node >=20.19.1 because Stack
### Patch Changes - [#15943](https://github.com/withastro/astro/pull/15943) [`1a627e2`](https://github.com/withastro/astro/commit/1a627e25267f8525e11237a1422c228f1bfc2ef1) Thanks [@alexanderdombroski](https://github.com/alexanderdombroski)! - Improves astro file templates to be scoped to `.astro`
### Patch Changes - [#15864](https://github.com/withastro/astro/pull/15864) [`d3c7de9`](https://github.com/withastro/astro/commit/d3c7de9253e9cb31fa5c4bf9f4bdf59dd1ada7b0) Thanks [@florian-lefebvre](https://github.com/florian-lefebvre)! - Removes temporary support for Node >=20.19.1 because Stack
### Patch Changes - [#15864](https://github.com/withastro/astro/pull/15864) [`d3c7de9`](https://github.com/withastro/astro/commit/d3c7de9253e9cb31fa5c4bf9f4bdf59dd1ada7b0) Thanks [@florian-lefebvre](https://github.com/florian-lefebvre)! - Removes temporary support for Node >=20.19.1 because Stack
### Patch Changes - [#15378](https://github.com/withastro/astro/pull/15378) [`a8a926e`](https://github.com/withastro/astro/commit/a8a926eecc2fb9a2e48a63afcf444d3ca2921a9c) Thanks [@dmgawel](https://github.com/dmgawel)! - Fix React hydration errors when using conditional slot rendering - [#1514
### Added - Support Vite 8 in `@tailwindcss/vite` ([#19790](https://github.com/tailwindlabs/tailwindcss/pull/19790)) ### Fixed - Don't crash when candidates contain prototype properties like `row-constructor` ([#19725](https://github.com/tailwindlabs/tailwindcss/pull/19725)) - Canonicalize
# Generated by Speakeasy CLI [mistralai 2.0.5](https://pypi.org/project/mistralai/2.0.5) ## Python SDK Changes: * `mistral.beta.connectors.get_auth_url()`: **Added** * `mistral.chat.complete()`: `request.reasoning_effort` **Added** * `mistral.chat.stream()`: `request.reasoning_effort` **Added** *
### 2.7.6 / 2026.03.18 - feat(core): add cloneable resource registry for structured clone (#32672) - feat(core): update v8 to 146.8.0 with foreground task ownership (#32771) - feat(eval): auto-detect CJS vs ESM in deno eval (#32472) - feat(ext/node): add MIMEType, convertProcessSignalToExitCod
## What's Changed * Add extra check to ensure `npm` and `git` are installed before installing OpenClaw * Claude Code will now be faster when run locally, due to preventing cache breakages * Fix to correctly support `ollama launch openclaw --model <model>` * Register Ollama's websearch package co
> [!NOTE] > This release is backporting bug fixes. It does **not** include all pending features/changes on canary. ### Core Changes - backport: Move expanded adapters docs to API reference (#92115) (#92129) - Backport: TypeScript v6 deprecations for baseUrl and moduleResolution (#92130) - [
## [1.46.0](https://github.com/googleapis/js-genai/compare/v1.45.0...v1.46.0) (2026-03-17) ### Breaking changes * [Interactions] Breaking change to Interactions API to refactor TextContent annotations to use specific citation types ([9fa8b1d](https://github.com/googleapis/js-genai/commit/9fa8b1db3
## [1.68.0](https://github.com/googleapis/python-genai/compare/v1.67.0...v1.68.0) (2026-03-17) ### Breaking changes * [Interactions] Breaking change to Interactions API to refactor TextContent annotations to use specific citation types ([6c3379f](https://github.com/googleapis/python-genai/commit/6
## What's changed - Added `StopFailure` hook event that fires when the turn ends due to an API error (rate limit, auth failure, etc.) - Added `${CLAUDE_PLUGIN_DATA}` variable for plugin persistent state that survives plugin updates; `/plugin uninstall` prompts before deleting it - Added `effort`, `
### Minor Changes - feat: allow `css`, `runes`, `customElement` compiler options to be functions ([#17951](https://github.com/sveltejs/svelte/pull/17951)) ### Patch Changes - fix: reinstate reactivity loss tracking ([#17801](https://github.com/sveltejs/svelte/pull/17801))
Changes since langchain-anthropic==1.3.5 release(anthropic): 1.4 (#36018) feat(anthropic): AnthropicPromptCachingMiddleware: apply explicit caching to system message and tool definitions (#35969) feat(anthropic): delegate cache_control kwarg to anthropic top-level param (#35967) chore(model-profile
## 2.29.0 (2026-03-17) Full Changelog: [v2.28.0...v2.29.0](https://github.com/openai/openai-python/compare/v2.28.0...v2.29.0) ### Features * **api:** 5.4 nano and mini model slugs ([3b45666](https://github.com/openai/openai-python/commit/3b456661f77ca3196aceb5ab3350664a63481114)) * **api:** add /
## 6.32.0 (2026-03-17) Full Changelog: [v6.31.0...v6.32.0](https://github.com/openai/openai-node/compare/v6.31.0...v6.32.0) ### Features * **api:** 5.4 nano and mini model slugs ([068df6d](https://github.com/openai/openai-node/commit/068df6d625d7faa76dfac160065f1ca550539ba8))
### Patch Changes - fix: ensure `$inspect` after top level await doesn't break builds ([#17943](https://github.com/sveltejs/svelte/pull/17943)) - fix: resume inert effects when they come from offscreen ([#17942](https://github.com/sveltejs/svelte/pull/17942)) - fix: don't eagerly access not
## What's changed - Increased default maximum output token limits for Claude Opus 4.6 to 64k tokens, and the upper bound for Opus 4.6 and Sonnet 4.6 models to 128k tokens - Added `allowRead` sandbox filesystem setting to re-allow read access within `denyRead` regions - `/copy` now accepts an option
### Web Search and Fetch in OpenClaw Ollama now ships with web search and web fetch plugin for OpenClaw. This allows Ollama's models (local or cloud) to search the web for the latest content and news. This also allows OpenClaw with Ollama to be able to fetch the web and extract readable content f
> [!NOTE] > This release is backporting bug fixes. It does **not** include all pending features/changes on canary. ### Core Changes - fix: patch http-proxy to prevent request smuggling in rewrites (See: [CVE-2026-29057](https://github.com/vercel/next.js/security/advisories/GHSA-ggv3-7p47-pfv8))
> [!NOTE] > This release is backporting bug fixes. It does **not** include all pending features/changes on canary. ### Core Changes - [Cache Components] Prevent streaming fetch calls from hanging in dev (#89194) - Apply server actions transform to node_modules in route handlers (#89380) - ens
## 6.31.0 (2026-03-16) Full Changelog: [v6.30.1...v6.31.0](https://github.com/openai/openai-node/compare/v6.30.1...v6.31.0) ### Features * **api:** add in/nin filter types to ComparisonFilter ([b2eda27](https://github.com/openai/openai-node/commit/b2eda274418ceb9bbdb3778cb6a5ee28090df8ad))
## 6.30.1 (2026-03-16) Full Changelog: [v6.30.0...v6.30.1](https://github.com/openai/openai-node/compare/v6.30.0...v6.30.1) ### Chores * **internal:** tweak CI branches ([25f5d74](https://github.com/openai/openai-node/commit/25f5d74c1fc16e3303fcb87022f5f0559b052cbf))
## What's Changed * Handle video generation failure case by @Omar-V2 in https://github.com/xai-org/xai-sdk-python/pull/110 * Prepare to release v1.8.2 of the xAI Python SDK by @Omar-V2 in https://github.com/xai-org/xai-sdk-python/pull/111 **Full Changelog**: https://github.com/xai-org/xai-sdk-pyth
## 0.79.0 (2026-03-16) Full Changelog: [sdk-v0.78.0...sdk-v0.79.0](https://github.com/anthropics/anthropic-sdk-typescript/compare/sdk-v0.78.0...sdk-v0.79.0) ### Features * add support for filesystem memory tools ([#599](https://github.com/anthropics/anthropic-sdk-typescript/issues/599)) ([1064199
## 0.85.0 (2026-03-16) Full Changelog: [v0.84.0...v0.85.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.84.0...v0.85.0) ### Features * **api:** chore(config): clean up model enum list ([#31](https://github.com/anthropics/anthropic-sdk-python/issues/31)) ([cce1a5b](https://github.
# Generated by Speakeasy CLI [mistralai 2.0.4](https://pypi.org/project/mistralai/2.0.4) ## Python SDK Changes: * `mistral.beta.observability.judges.judge_conversation()`: **Added** * `mistral.chat.complete()`: `request.guardrails` **Added** * `mistral.chat.stream()`: `request.guardrails` **Added*
## 6.30.0 (2026-03-16) Full Changelog: [v6.29.0...v6.30.0](https://github.com/openai/openai-node/compare/v6.29.0...v6.30.0) ### Features * **api:** add /v1/videos endpoint option to batches ([271d879](https://github.com/openai/openai-node/commit/271d87979f16950900f4253915bdda319b7fe935)) * **api:
### Patch Changes - [#15895](https://github.com/withastro/astro/pull/15895) [`7b4b254`](https://github.com/withastro/astro/commit/7b4b2549437eb099c5e96025dcf8d24ea56f30d0) Thanks [@Princesseuh](https://github.com/Princesseuh)! - Updates Volar services to 0.0.70. This updates notably mean that the
### Patch Changes - [#15959](https://github.com/withastro/astro/pull/15959) [`335a204`](https://github.com/withastro/astro/commit/335a204161f5a7293c128db570901d4f8639c6ed) Thanks [@matthewp](https://github.com/matthewp)! - Fix Vercel serverless path override handling so override values are only a
### Patch Changes - [#15934](https://github.com/withastro/astro/pull/15934) [`6f8f0bc`](https://github.com/withastro/astro/commit/6f8f0bc4e22e958ccc2164acb1aa8cce21c43148) Thanks [@ematipico](https://github.com/ematipico)! - Updates the Astro `peerDependencies#astro` to be `6.0.0`. - Updated d
### Patch Changes - [#15891](https://github.com/withastro/astro/pull/15891) [`b889231`](https://github.com/withastro/astro/commit/b88923114e3cfe30c945680a62c7bd7f667bbf4d) Thanks [@matthewp](https://github.com/matthewp)! - Fix dev routing for `server:defer` islands when adapters opt into handling
### Patch Changes - [#15864](https://github.com/withastro/astro/pull/15864) [`d3c7de9`](https://github.com/withastro/astro/commit/d3c7de9253e9cb31fa5c4bf9f4bdf59dd1ada7b0) Thanks [@florian-lefebvre](https://github.com/florian-lefebvre)! - Removes temporary support for Node >=20.19.1 because Stack
### Patch Changes - [#15934](https://github.com/withastro/astro/pull/15934) [`6f8f0bc`](https://github.com/withastro/astro/commit/6f8f0bc4e22e958ccc2164acb1aa8cce21c43148) Thanks [@ematipico](https://github.com/ematipico)! - Updates the Astro `peerDependencies#astro` to be `6.0.0`.
# Generated by Speakeasy CLI [mistralai 2.0.3](https://pypi.org/project/mistralai/2.0.3) ## Python SDK Changes: * `mistral.beta.conversations.append_stream()`: * `request.inputs.union(Array<InputEntries>)[].union(MessageInputEntry).content.union(Array<MessageInputContentChunks>)[].union(ThinkChu
### Patch Changes - fix: update `select.__value` on `change` ([#17745](https://github.com/sveltejs/svelte/pull/17745)) - chore: add `invariant` helper for debugging ([#17929](https://github.com/sveltejs/svelte/pull/17929)) - fix: ensure deriveds values are correct across batches ([#17917](h
Changes since langchain-anthropic==1.3.4 release(anthropic): 1.3.5 (#35873) fix(anthropic): Ignore general usage cache_creation fields if more specific fields are set (#35845) perf(.github): set a timeout on get min versions HTTP calls (#35851) feat(model-profiles): new fields + `Makefile` target (
## What's changed - Added MCP elicitation support — MCP servers can now request structured input mid-task via an interactive dialog (form fields or browser URL) - Added new `Elicitation` and `ElicitationResult` hooks to intercept and override responses before they're sent back - Added `-n` / `--nam
Ollama 0.18 includes improved performance for OpenClaw and Ollama’s [cloud models](https://ollama.com/search?c=cloud), including the new Nemotron-3-Super model by NVIDIA designed for high-performance agentic reasoning tasks. ### Improved OpenClaw performance with Kimi-K2.5 This release of Olla
## 6.29.0 (2026-03-13) Full Changelog: [v6.28.0...v6.29.0](https://github.com/openai/openai-node/compare/v6.28.0...v6.29.0) ### Features * **api:** custom voices ([a11307a](https://github.com/openai/openai-node/commit/a11307afab49299fdf7e7ed3675d3e277d9b5c60))
## 2.28.0 (2026-03-13) Full Changelog: [v2.27.0...v2.28.0](https://github.com/openai/openai-python/compare/v2.27.0...v2.28.0) ### Features * **api:** custom voices ([50dc060](https://github.com/openai/openai-python/commit/50dc060b55767615419219ef567d31210517e613))
## 6.28.0 (2026-03-13) Full Changelog: [v6.27.0...v6.28.0](https://github.com/openai/openai-node/compare/v6.27.0...v6.28.0) ### Features * **api:** manual updates ([d543959](https://github.com/openai/openai-node/commit/d54395976aa4c1c1864bb45dbaf81ec1d66b8c6b)) * **api:** manual updates ([4f87840
## 2.27.0 (2026-03-13) Full Changelog: [v2.26.0...v2.27.0](https://github.com/openai/openai-python/compare/v2.26.0...v2.27.0) ### Features * **api:** api update ([60ab24a](https://github.com/openai/openai-python/commit/60ab24ae722a7fa280eb4b2273da4ded1f930231)) * **api:** manual updates ([b244b09
Changes since langchain-mistralai==1.1.1 release(mistralai): 1.1.2 (#35835) feat(model-profiles): new fields + `Makefile` target (#35788) fix(model-profiles): sort generated profiles by model ID for stable diffs (#35344) chore: bump model profiles (#35294) fix(mistralai): update test (#35270) fix(m
Changes since langchain-classic==1.0.2 release(langchain): 1.0.3 (#35834) chore(core): move BaseCrossEncoder to langchain-core (#35809) chore: bump tornado from 6.5.2 to 6.5.5 in /libs/langchain (#35773) release(langchain_v1): 1.2.11 (#35723) chore: bump the minor-and-patch group across 3 directori
# Generated by Speakeasy CLI [mistralai 2.0.2](https://pypi.org/project/mistralai/2.0.2) ## Python SDK Changes: * `mistral.beta.conversations.start()`: `response.guardrails[]` **Changed** (Breaking ⚠️) * `mistral.beta.conversations.append()`: `response.guardrails[]` **Changed** (Breaking ⚠️) * `mi
Changes since langchain-core==1.2.18 release(core): 1.2.19 (#35832) chore(core): move BaseCrossEncoder to langchain-core (#35809) chore: bump tornado from 6.5.2 to 6.5.5 in /libs/core (#35775)
Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/create-vite@9.0.2/packages/create-vite/CHANGELOG.md) for details.
## [1.67.0](https://github.com/googleapis/python-genai/compare/v1.66.0...v1.67.0) (2026-03-12) > [!CAUTION] > **Known Issue:** > This release contains a bug where the `typing-extensions` lower bound is set too low, which causes the SDK to break in some environments. > > **Recommended Actions:
## [1.45.0](https://github.com/googleapis/js-genai/compare/v1.44.0...v1.45.0) (2026-03-12) ### Features * Add inference_generation_config to EvaluationConfig for Tuning ([b4ac722](https://github.com/googleapis/js-genai/commit/b4ac722b0225ef3f06b82f5dcb19d423efe63599)) * enable language code for a
TL;DR We recently demonstrated a +30.2% training speedup for Llama4 Scout with equivalent convergence to bfloat16, by using MXFP8 MoE training primitives in TorchAO! This is ~81% of the theoretical...
Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/create-vite@9.0.1/packages/create-vite/CHANGELOG.md) for details.
### Patch Changes - [#15870](https://github.com/withastro/astro/pull/15870) [`920f10b`](https://github.com/withastro/astro/commit/920f10bb3a49da8355967df99c32c43cc9f53b46) Thanks [@matthewp](https://github.com/matthewp)! - Prebundle `astro/toolbar` in dev when custom dev toolbar apps are register
### Patch Changes - [#15815](https://github.com/withastro/astro/pull/15815) [`d1872ee`](https://github.com/withastro/astro/commit/d1872ee6456e4a8ed821ee2b357465a116690be1) Thanks [@matthewp](https://github.com/matthewp)! - Prebundle additional Astro runtime dependencies for Cloudflare development
### Patch Changes - [#15868](https://github.com/withastro/astro/pull/15868) [`bb2b8f5`](https://github.com/withastro/astro/commit/bb2b8f5cd3c9f3140b4bb0fb5a1d4c62b41883b8) Thanks [@ematipico](https://github.com/ematipico)! - Fixes an issue where the adapter would cause a series of warnings during
### Patch Changes - [#15934](https://github.com/withastro/astro/pull/15934) [`6f8f0bc`](https://github.com/withastro/astro/commit/6f8f0bc4e22e958ccc2164acb1aa8cce21c43148) Thanks [@ematipico](https://github.com/ematipico)! - Updates the Astro `peerDependencies#astro` to be `6.0.0`.
Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/create-vite@9.0.0/packages/create-vite/CHANGELOG.md) for details.
### Patch Changes - fix: remove `untrack` circular dependency ([#17910](https://github.com/sveltejs/svelte/pull/17910)) - fix: recover from errors that leave a corrupted effect tree ([#17888](https://github.com/sveltejs/svelte/pull/17888)) - fix: properly lazily evaluate RHS when checking f
> 4.4.0/4.4.2 is the next minor release (v4.4.2 was published with no changes due to a publishing failure) ## 👀 Highlights ### 🏭 `createUseFetch` and `createUseAsyncData` You can now create **custom instances** of `useFetch` and `useAsyncData` with your own default options ([#32300](https
# Generated by Speakeasy CLI [mistralai 2.0.1](https://pypi.org/project/mistralai/2.0.1) ## Python SDK Changes: * `mistral.chat.complete()`: * `request.messages[].union(user).content.union(Array<ContentChunk>)[].union(audio_url)` **Removed** (Breaking ⚠️) * `response.choices[].message.content
## What's changed - Added actionable suggestions to `/context` command — identifies context-heavy tools, memory bloat, and capacity warnings with specific optimization tips - Added `autoMemoryDirectory` setting to configure a custom directory for auto-memory storage - Fixed memory leak where stream
The rustup team is happy to announce the release of rustup version 1.29.0. Rustup is the recommended tool to install Rust, a programming language that empowers everyone to build reliable and efficient software. What's new in rustup 1.29.0 Following the footsteps of many package managers in the purs
## What's changed - Added `modelOverrides` setting to map model picker entries to custom provider model IDs (e.g. Bedrock inference profile ARNs) - Added actionable guidance when OAuth login or connectivity checks fail due to SSL certificate errors (corporate proxies, `NODE_EXTRA_CA_CERTS`) - Fixed
### Patch Changes - [#16969](https://github.com/withastro/astro/pull/16969) [`4a31f90`](https://github.com/withastro/astro/commit/4a31f90c765bcd1c4af8b85160b74a0da338cfe7) Thanks [@Princesseuh](https://github.com/Princesseuh)! - Adds support for Prism syntax highlighting to the Sätteri Markdown a
### Minor Changes - [#15711](https://github.com/withastro/astro/pull/15711) [`b2bd27b`](https://github.com/withastro/astro/commit/b2bd27bcb605d1e44e94ab922a8d7d2aa685149d) Thanks [@OliverSpeir](https://github.com/OliverSpeir)! - Adds a `prerenderEnvironment` option to the Cloudflare adapter.
### 2.7.5 / 2026.03.11 - feat(coverage): add function coverage to summary and HTML reports (#32507) - feat(doc): support npm packages in `deno doc` (#32435) - feat(ext/node): add `node_api_create_object_with_properties` API (#31443) - feat(ext/node): implement KeyObject.toCryptoKey() and Ke
## What's Changed * Update grok-4.20 beta and multi-agent model variants in ChatModel by @shawnthapa in https://github.com/xai-org/xai-sdk-python/pull/107 * Bump version from 1.8.0 to 1.8.1 by @shawnthapa in https://github.com/xai-org/xai-sdk-python/pull/109 **Full Changelog**: https://github.com/
### Patch Changes - fix: re-process batch if new root effects were scheduled ([#17895](https://github.com/sveltejs/svelte/pull/17895))
### Patch Changes - [#16955](https://github.com/withastro/astro/pull/16955) [`9a93d68`](https://github.com/withastro/astro/commit/9a93d68429aa15e76f07268863badfbda7b59d23) Thanks [@Princesseuh](https://github.com/Princesseuh)! - Updates Sätteri processor to v0.8.0. See [its changelog](https://git
### Patch Changes - [#15825](https://github.com/withastro/astro/pull/15825) [`2cfe935`](https://github.com/withastro/astro/commit/2cfe935db452fce91553784157e31c26bb3b2a05) Thanks [@Princesseuh](https://github.com/Princesseuh)! - Fixes failed publish for 2.16.11.
### Patch Changes - [#15864](https://github.com/withastro/astro/pull/15864) [`d3c7de9`](https://github.com/withastro/astro/commit/d3c7de9253e9cb31fa5c4bf9f4bdf59dd1ada7b0) Thanks [@florian-lefebvre](https://github.com/florian-lefebvre)! - Removes temporary support for Node >=20.19.1 because Stack
### Patch Changes - Updated dependencies \[[`c2cd371`](https://github.com/withastro/astro/commit/c2cd371f9f2003ab8c9ce70a24fc0af40c5de531)]: - @astrojs/internal-helpers@0.7.6
### Patch Changes - Updated dependencies \[[`c2cd371`](https://github.com/withastro/astro/commit/c2cd371f9f2003ab8c9ce70a24fc0af40c5de531)]: - @astrojs/internal-helpers@0.7.6 - @astrojs/markdown-remark@6.3.11
# Generated by Speakeasy CLI ## 2026-03-10 10:56:01 ### Changes Based on: - OpenAPI Doc 1.0.0 - Speakeasy CLI 1.690.1 (2.797.1) https://github.com/speakeasy-api/speakeasy ### Generated - [typescript v1.15.1] . ### Releases - [NPM v1.15.1] https://www.npmjs.com/package/@mistralai/mistralai/v/1.15.1
### Patch Changes - [#15187](https://github.com/withastro/astro/pull/15187) [`bbb5811`](https://github.com/withastro/astro/commit/bbb5811eb801a42dc091bb09ea19d6cde3033795) Thanks [@matthewp](https://github.com/matthewp)! - Update to Astro 6 beta - [#14956](https://github.com/withastro/astro/pu
### Minor Changes - [#14427](https://github.com/withastro/astro/pull/14427) [`e131261`](https://github.com/withastro/astro/commit/e1312615b39c59ebc05d5bb905ee0960b50ad3cf) Thanks [@florian-lefebvre](https://github.com/florian-lefebvre)! - Increases minimum Node.js version to 22.12.0 - ([v6 upgrad
### Patch Changes - [#15187](https://github.com/withastro/astro/pull/15187) [`bbb5811`](https://github.com/withastro/astro/commit/bbb5811eb801a42dc091bb09ea19d6cde3033795) Thanks [@matthewp](https://github.com/matthewp)! - Update to Astro 6 beta - [#14956](https://github.com/withastro/astro/pu
## What's Changed * parsers: repair unclosed arg_value tags in GLM tool calls by @BruceMacD in https://github.com/ollama/ollama/pull/14656 * Reapply "don't require pulling stubs for cloud models" again by @jmorganca in https://github.com/ollama/ollama/pull/14608 * docs: format compat docs by @mxy
## What's changed - Changed tool search to bypass the third-party proxy gate when the environment variable is set (replaces `CLAUDE_CODE_PROXY_SUPPORTS_TOOL_REFERENCE`, now removed) - Added `w` key in `/copy` to write the focused selection directly to a file, bypassing the clipboard (useful over SS
### Patch Changes - fix: better `bind:this` cleanup timing ([#17885](https://github.com/sveltejs/svelte/pull/17885))
Node.js v25.8.1
Changes since langchain-openai==1.1.10 fix(openai): bump min core version (#35705) release(openai): 1.1.11 (#35703) fix(openai): update responses API model detection for pro and codex models (#35594) feat(openai): support tool search (#35582) chore: bump langgraph from 1.0.8 to 1.0.10rc1 in /libs/p
Changes since langchain-core==1.2.17 release(core): 1.2.18 (#35704) fix(core): fix double backticks in deprecation docstring for alternative_import (#35658) fix(core): preserve default_factory when generating tool call schema (#35550) feat(openai): support tool search (#35582) chore: bump the minor
### Patch Changes - fix: `{@html}` no longer duplicates content inside `contenteditable` elements ([#17853](https://github.com/sveltejs/svelte/pull/17853)) - fix: don't access inert block effects ([#17882](https://github.com/sveltejs/svelte/pull/17882)) - fix: handle asnyc updates within pe
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.
LeRobot v0.5.0: Scaling Every Dimension
## What's changed - Added `/loop` command to run a prompt or slash command on a recurring interval (e.g. `/loop 5m check the deploy`) - Added cron scheduling tools for recurring prompts within a session - Added `voice:pushToTalk` keybinding to make the voice activation key rebindable in `keybinding
Changes since langchain==0.3.27 fix(langchain): bump minimum langchain-core to 0.3.73 (#35608) release(langchain): 0.3.28 (#35607) fix(langchain): backport patch ReDoS vulnerability in MRKL and ReAct action regex (CVE-2024-58340) (#35603) feat(core,langchain,text-splitters): (v0.3) use uuid7 for ru
Changes since langchain-classic==1.0.1 release(langchain): bump langchain-classic to 1.0.2 (#35601) fix(langchain-classic): patch ReDoS vulnerability in MRKL and ReAct action regex (CVE-2024-58340) (#35598) chore: bump the langchain-deps group across 3 directories with 7 updates (#35513) chore: bum
For release notes, check out the [release announcement blog post](https://devblogs.microsoft.com/typescript/announcing-typescript-6-0-rc/). * [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). * [f
## What's changed - Fixed API 400 errors when using `ANTHROPIC_BASE_URL` with a third-party gateway — tool search now correctly detects proxy endpoints and disables `tool_reference` blocks - Fixed `API Error: 400 This model does not support the effort parameter` when using custom Bedrock inference
## 6.27.0 (2026-03-05) Full Changelog: [v6.26.0...v6.27.0](https://github.com/openai/openai-node/compare/v6.26.0...v6.27.0) ### Features * **api:** The GA ComputerTool now uses the CompuerTool class. The 'computer_use_preview' tool is moved to ComputerUsePreview ([0206188](https://github.com/open
## 2.26.0 (2026-03-05) Full Changelog: [v2.25.0...v2.26.0](https://github.com/openai/openai-python/compare/v2.25.0...v2.26.0) ### Features * **api:** The GA ComputerTool now uses the CompuerTool class. The 'computer_use_preview' tool is moved to ComputerUsePreview ([78f5b3c](https://github.com/op
## 6.26.0 (2026-03-05) Full Changelog: [v6.25.0...v6.26.0](https://github.com/openai/openai-node/compare/v6.25.0...v6.26.0) ### Features * **api:** gpt-5.4, tool search tool, and new computer tool ([1d1e5a9](https://github.com/openai/openai-node/commit/1d1e5a9b5aeb11b0e940b4532dcd6a3fcc23898a))
## 2.25.0 (2026-03-05) Full Changelog: [v2.24.0...v2.25.0](https://github.com/openai/openai-python/compare/v2.24.0...v2.25.0) ### Features * **api:** gpt-5.4, tool search tool, and new computer tool ([6b2043f](https://github.com/openai/openai-python/commit/6b2043f3d63058f5582eab7a7705b30a3d5536f0
### 2.7.4 / 2026.03.05 - fix(core): uv_compat cleanup and fixes (#32458) - fix(deploy): correctly handle version lookup (#32489) - fix(ext/node): deep `assert` compatibility (#32434) - fix(ext/node): use sync writes for TTY stdout/stderr WriteStream (#32488) - fix(test): restart all tests on
GPT-5.4 Thinking System Card
### Minor Changes - [#15778](https://github.com/withastro/astro/pull/15778) [`4ebc1e3`](https://github.com/withastro/astro/commit/4ebc1e328ac40e892078031ed9dfecf60691fd56) Thanks [@ematipico](https://github.com/ematipico)! - Added a new entry point called `/request`, which exposes utilities to wo
## What's Changed * Add grok-imagine-image-pro to ImageGenerationModel by @shawnthapa in https://github.com/xai-org/xai-sdk-python/pull/103 * Add agent_count parameter to chat API for multi-agent models by @shawnthapa in https://github.com/xai-org/xai-sdk-python/pull/104 * Add grok-4.20 experimental
## What's Changed * Allow thinking levels such as `"medium"` to correctly interpreted in Ollama's API for all thinking models * Add context length to support compaction when using `ollama launch` **Full Changelog**: https://github.com/ollama/ollama/compare/v0.17.6...v0.17.7
## What's changed - Added the `/claude-api` skill for building applications with the Claude API and Anthropic SDK - Added Ctrl+U on an empty bash prompt (`!`) to exit bash mode, matching `escape` and `backspace` - Added numeric keypad support for selecting options in Claude's interview questions (p
The Rust team is happy to announce a new version of Rust, 1.94.0. 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 1.94.0 with: $ rustup update stable If you don't have it already, y
## [1.44.0](https://github.com/googleapis/js-genai/compare/v1.43.0...v1.44.0) (2026-03-04) ### Features * Add gemini-3.1-flash-image-preview model ([175603b](https://github.com/googleapis/js-genai/commit/175603bacbc593a437264f807a411143cdccbd0a)) * Support signature for all Interaction tool types
## [1.66.0](https://github.com/googleapis/python-genai/compare/v1.65.0...v1.66.0) (2026-03-03) ### Features * Add gemini-3.1-flash-image-preview model ([dd52cc2](https://github.com/googleapis/python-genai/commit/dd52cc288be297e74cb689be9260b917ea90e06b)) * Support signature for all Interaction to
Changes since langchain-openrouter==0.0.2 fix(openrouter): include role in sdk `model_construct` for min dep compat (#35562) release(openrouter): 0.1.0 (#35560) feat(openrouter): add streaming token usage support (#35559) feat(fireworks,groq,openrouter): add standard model property (#35542) feat(op
## New Model additions ### EuroBERT <img width="1080" height="1080" alt="image" src="https://github.com/user-attachments/assets/33603f42-5435-421a-9641-baf72faacb22" /> EuroBERT is a multilingual encoder model based on a refreshed transformer architecture, akin to Llama but with bidirection
### 2.7.3 / 2026.03.04 - fix(deploy): dont use jsr api for deploy subcommand (#32441) - fix(ext/node): handle partial writes to process.stdout/stderr (#32433) - fix(ext/node): make UDP socket ops synchronous, implement missing dgram methods (#32381) - fix(ext/node): support HTTP over Window
## 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 TTS is now available across Google products.
### 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
### Minor Changes
### Patch Changes - Bumped `@remix-run/*` dependencies: - [`fetch-router@0.18.0`](https://github.com/remix-run/remix/releases/tag/fetch-router@0.18.0)
### 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
### Patch Changes - Bumped `@remix-run/*` dependencies: - [`cookie@0.5.4`](https://github.com/remix-run/remix/releases/tag/cookie@0.5.4) - [`fetch-router@0.19.2`](https://github.com/remix-run/remix/releases/tag/fetch-router@0.19.2)
### Minor Changes - Migrated `@remix-run/test` from the `tsx` package to Remix's internal `@remix-run/node-tsx` module loader. BREAKING CHANGE: `.ts`, `.tsx`, and `.jsx` module loading in `@remix-run/test` now uses Remix's internal `@remix-run/node-tsx` loader. Test modules are still transformed
### 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
A technical release focused on improving developer experience and parity with the Python SDK v2. ## What's new ### Schema naming conventions 42 request/response types renamed to follow consistent conventions: - Request bodies: `{Verb}{Entity}Request` (e.g. `CreateAgentRequest`) - Responses: `{Ver
## [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 - [#17027](https://github.com/withastro/astro/pull/17027) [`241250b`](https://github.com/withastro/astro/commit/241250bf126f39c86a8aedd38df106e533301752) Thanks [@ocavue](https://github.com/ocavue)! - Triggers beta prereleases for packages that are still on alpha
## 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 v25.7.0
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.
Node.js v24.14.0
## 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
Gemini 3.1 Flash TTS is now available across Google products.
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):
Gemini can turn hundreds of pages of notes into study guides or flashcards — or organize a semester’s worth of learning.
### 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
### Major Changes - [#14427](https://github.com/withastro/astro/pull/14427) [`e131261`](https://github.com/withastro/astro/commit/e1312615b39c59ebc05d5bb905ee0960b50ad3cf) Thanks [@florian-lefebvre](https://github.com/florian-lefebvre)! - Increases minimum Node.js version to 22.12.0 - ([v6 upgrad
> [!TIP] > **Check out our Next v16.2 [Blog Post](https://nextjs.org/blog/next-16-2) to learn more about this release.** ### Core Changes - Upgrade React from `f93b9fd4-20251217` to `65eec428-20251218`: #87323 - Turbopack: Create junction points instead of symlinks on Windows: #87606 - Tu
## 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
### Major Changes - [#15413](https://github.com/withastro/astro/pull/15413) [`736216b`](https://github.com/withastro/astro/commit/736216b2c46f758c6b4a607ccfadcc191c1d56b4) Thanks [@florian-lefebvre](https://github.com/florian-lefebvre)! - Removes the deprecated `@astrojs/vercel/serverless` and `@
### Patch Changes - [#17027](https://github.com/withastro/astro/pull/17027) [`241250b`](https://github.com/withastro/astro/commit/241250bf126f39c86a8aedd38df106e533301752) Thanks [@ocavue](https://github.com/ocavue)! - Triggers beta prereleases for packages that are still on alpha
### Patch Changes - Updated dependencies \[[`745e632`](https://github.com/withastro/astro/commit/745e632fc590e41a5701509e9cc4ed971bdddf74)]: - @astrojs/internal-helpers@0.8.0-beta.2 - @astrojs/underscore-redirects@1.0.0
### Patch Changes - [#16661](https://github.com/withastro/astro/pull/16661) [`03b8f7f`](https://github.com/withastro/astro/commit/03b8f7f7644cc1d9e738a8221d6bd377399538c0) Thanks [@ocavue](https://github.com/ocavue)! - Updates `typescript` to v6. No changes are needed from users. - Updated dep
### Patch Changes - [#17027](https://github.com/withastro/astro/pull/17027) [`241250b`](https://github.com/withastro/astro/commit/241250bf126f39c86a8aedd38df106e533301752) Thanks [@ocavue](https://github.com/ocavue)! - Triggers beta prereleases for packages that are still on alpha
### Patch Changes - Updated dependencies \[[`4ebc1e3`](https://github.com/withastro/astro/commit/4ebc1e328ac40e892078031ed9dfecf60691fd56), [`4e7f3e8`](https://github.com/withastro/astro/commit/4e7f3e8e6849c314a0ab031ebd7f23fb982f0529)]: - @astrojs/internal-helpers@0.8.0-beta.3 - @ast
### 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==1.2.12 release(langchain): 1.2.13 (#36111) ci: suppress pytest streaming output in CI (#36092) feat: Add LangSmith integration metadata to create_agent and init_chat_model (#35810) ci: avoid unnecessary dep installs in lint targets (#36046) chore: bump pyasn1 from 0.6.2 to
### 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)) -
This afternoon, we sent the following email to our global team. One of our core values at Cloudflare is transparency, and we believe it's important that you hear this directly from us because it’s a major moment at Cloudflare.
GitHub Universe is back: returning to the historic Fort Mason Center in San Francisco on October 28–29, 2026. The post GitHub Universe is back: All together now, in the agentic era 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
February gave us only twenty-eight days, but we made them count. From new Agent Builder capabilities to production monitoring insights, here's your monthly roundup of updates from the LangChain team. What’s new for LangChain? LangSmith 🔨 Agent Builder now has a central chat with all
Building fewer targets by default On 2026-05-01, docs.rs will make a breaking change to its build behavior. Today, if a crate does not define a targets list in its docs.rs metadata, docs.rs builds documentation for a default list of five targets. Starting on 2026-05-01, docs.rs will instead build do
How to train a new language model from scratch using Transformers and Tokenizers
## 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==1.2.11 release(langchain_v1): 1.2.12 (#35770) feat: tracing for wrap model + tool call (#35765)
The world of AI is expanding beyond the cloud, reaching devices that fit in the palm of your hand. Running PyTorch models on these tiny systems, where memory is measured...
Introducing a $100 AI Ultra plan — plus, new features and benefits for Google AI Plus, Pro and Ultra subscribers.
GPT-5.3-Codex is a Codex-native agent that pairs frontier coding performance with general reasoning to support long-horizon, real-world technical work.
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/plugin-legacy@8.0.0/packages/plugin-legacy/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==1.2.10 release(langchain_v1): 1.2.11 (#35723) fix(langchain): normalize custom detector output to prevent KeyError in hash/mask strategies (#35651) chore: bump the minor-and-patch group across 3 directories with 7 updates (#35605) chore(langchain): switch refs from gemini-3
## 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 Flight Recorder in Go 1.25 In 2024 we introduced the world to more powerful Go execution traces. In that blog post we gave a sneak peek into some of the new functionality we could unlock with our new execution tracer, including flight recording. We’re happy to announce that flight record
## 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
> 3.21.5 is the next patch release. ## 👉 Changelog [compare changes](https://github.com/nuxt/nuxt/compare/v3.21.4...v3.21.5) ### 🔥 Performance - **kit:** Cache layer roots and short-circuit `isIgnored` relative ([#35015](https://github.com/nuxt/nuxt/pull/35015)) ### 🩹 Fixes - **nitr
## 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 - BREAKING CHANGE: Middleware consumed through `remix/router` and `remix/fetch-router` must now explicitly continue the request chain by calling `next()` or return a `Response`. Middleware that returned `undefined` without calling `next()` now throws at runtime instead of im
### 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@0.19.2`](https://github.com/remix-run/remix/releases/tag/fetch-router@0.19.2)
### Patch Changes - Bumped `@remix-run/*` dependencies: - [`fetch-router@0.20.0`](https://github.com/remix-run/remix/releases/tag/fetch-router@0.20.0)
### Minor Changes - BREAKING CHANGE: `parseMultipart()`, `parseMultipartStream()`, and `parseMultipartRequest()` now enforce finite default `maxParts` and `maxTotalSize` limits, and add `MaxPartsExceededError` and `MaxTotalSizeExceededError` for handling multipart envelope limit failures. Apps t
### Minor Changes - BREAKING CHANGE: `MultipartPart.headers` is now a plain decoded object keyed by lower-case header name instead of a native `Headers` instance. Access part headers with bracket notation like `part.headers['content-type']` instead of `part.headers.get('content-type')`. This let
### Minor Changes - Add timeout and abort signal support to `@remix-run/test`. Tests and lifecycle hooks can now pass `{ timeout, signal }`. Timed-out tests fail and abort `t.signal`, so async work that accepts an `AbortSignal` can cancel promptly. Tests and suites can also use string `skip`/`to
### Minor Changes - BREAKING CHANGE: Action objects now use `handler` instead of `action`. This applies to the object form accepted by `router.get(...)`, `router.post(...)`, and `router.map(...)`, and to `BuildAction` object definitions. - BREAKING CHANGE: Remove `context.storage`, `context.ses
## 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
## What's Changed This release candidate was focused mostly on `quantization` support with the new dynamic weight loader, and a few notable 🚨 breaking changes🚨: 1. Default dtype for any model when using `from_pretrained` is now `auto`! * Default auto 🚨 🚨 by @ArthurZucker in https://gith
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
Overview We are excited to introduce the highlights of Intel® Core™ Ultra Series 3 processors and the advancements we have made in PyTorch to enable users to unlock a wider...
## [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 16:28:14 ### 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-gcp ### Releases - [NPM v1.7.0] https://www.npmjs.com/package/@mistralai
# Generated by Speakeasy CLI [@mistralai/mistralai 1.12.0](https://www.npmjs.com/package/@mistralai/mistralai/v/1.12.0) ## SDK Changes Detected: * `mistral.beta.conversations.restart()`: * `request.conversationRestartRequest.inputs.[array].[]` **Changed** **Breaking** :warning: * `response.ou
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 v25.3.0
Node.js v24.13.0
## 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-
This GPT-5 system card addendum provides updated safety metrics for GPT-5.1 Instant and Thinking, including new evaluations for mental health and emotional reliance.
### 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