Weekly digest: every breaking change, retirement and price change across 20+ coding agents, one email.
Form not loading? Subscribe here.
Latest
2026-10-17 · 6 changes · plan
- -Computer use
- +Computer use Integration recipes
- +Driver reference
2026-10-17 · 3 changes · release
- +October 16, 2026
- +See Your Runner's Desktop
- +See and use your macOS runner's desktop, so you can try the iOS app Amp is building for you.
2026-10-17 · 5 changes · retirement
- -Computer use
- +Computer use Integration recipes
- +Driver reference
2026-10-17 · 3 changes · release
- GPT-6 models (such as gpt-6-sol and gpt-6.1-sol) work on OpenAI and Azure OpenAI-compatible endpoints. Before, every request was rejected because Cline sent maxtokens instead of maxcompletiontokens
- The Cline provider's default model is Claude Sonnet 5.5 again, which is back at the top of Cline's recommended list
- Refreshed the model catalog. Adds the CommandCode and Reflection providers. Default models change for 302.AI (Gemini 4 Argon), Eden AI and Prime Inference (Muse Spark Open), CoreWeave (Reflection Beam
2026-10-17 · 3 changes · release
- GPT-6 models (such as gpt-6-sol and gpt-6.1-sol) work on OpenAI and Azure OpenAI-compatible endpoints. Before, every request was rejected because Cline sent maxtokens instead of maxcompletiontokens
- With no model chosen, the Cline provider uses Claude Sonnet 5.5 again, which is back at the top of Cline's recommended list
- Refreshed the model catalog. Adds the CommandCode and Reflection providers. Default models change for 302.AI (Gemini 4 Argon), Eden AI and Prime Inference (Muse Spark Open), CoreWeave (Reflection Beam
2026-10-17 · 4 changes · release
- OpenAI-compatible requests for GPT-6 models (gpt-6-sol, gpt-6.1-sol, gpt-6-1-sol, and later gpt-5 through gpt-9 ids) send maxcompletiontokens instead of maxtokens, so OpenAI and Azure no longer reject
- The hub daemon records which client started it (CLINEHUBLAUNCHERCLIENT, CLINEHUBLAUNCHERVERSION, CLINEHUBLAUNCHERTRANSPORT) and publishes that as OTel resource attributes. SSH remote hubs report the l
- The telemetry self-check report includes tracesexporter
2026-10-16 · 63 changes · release
- Added CLAUDECODEAUTOMODEMODEL to choose the model the client-side auto mode classifier uses; it does not change the model for server-side auto mode
- Added an Idle compaction row to /config for turning idle compaction off or back on; the notices shown after an idle compaction now say how to turn it off
- Added a notice to /design-sync and /design-login that standalone Claude Design (claude.ai/design) closes by December 14, 2026
2026-10-16 · 10 changes · release
- List remote agents for the mobile app.
- Bundle Kilo CLI v7.8.13.
- Prevent editor context ignore-file loading from blocking the JetBrains UI thread.
2026-10-16 · 1 changes · retirement
2026-10-16 · 31 changes · release
- AIgateway declarative provider #12528
- Propagate W3C trace context from ACP prompts to MCP tool calls #12697
- Surface provider x-request-id on responses and errors #12587
2026-10-16 · 1 changes · release
- Improvements
- Configure model reasoning options to generate reasoning variants, replacing catalog variants while preserving your configured variant overrides.
2026-10-16 · 5 changes · release
- Marketplace plugins such as goal load again. In 0.0.46 they failed with Cannot find module '@cline/sdk' because the packaged app didn't include the SDK packages plugins import
- The Cloud sessions toggle is gone from Settings. Cloud sessions are on wherever they are available
- When a provider error interrupts a response mid-stream, Cline retries it up to 3 times before failing the turn
2026-10-16 · 9 changes · release
- Cline Cloud sessions, rolling out gradually: run a task in a hosted sandbox on a GitHub repo and branch you pick. Turn it on in Settings. Cloud tasks show in Recent and History with their status, noti
- With no model chosen, the Cline provider now uses Gemini 4 Argon, the new first model in Cline's recommended list. OpenRouter stays on Claude Sonnet 5.5.
- Refreshed the model catalog. Adds the Boundless and Standard Compute providers, and SambaNova now comes from the catalog with MiniMax M3 as its default. The Cline recommended list adds Gemini 4 Argon
2026-10-16 · 7 changes · release
- Plugins now run in a worker instead of directly inside the hub. If this build can't run plugins, Cline says so in cline config tools, cline hub plugins, and the session-start warnings instead of quiet
- When a provider error interrupts a response mid-stream, Cline retries it up to 3 times before failing the turn
- Failed model requests now log the provider's request id, which makes support tickets easier to trace
2026-10-16 · 9 changes · release
- Plugins now run only in worker threads (the default, CLINEPLUGINMODE=worker) or in the subprocess sandbox (sandbox). The inprocess mode is removed, along with its silent fallback. A host that ships no
- Provider errors that arrive after a model stream has started are retried up to 3 times, and the final failure is reported as an error in logs and Langfuse traces. Exhausted retries no longer also trig
- Model request failure logs include the provider's request id
2026-10-16 · 5 changes · release
- OpenCode 1 now stays on the 1.x release line: update checks use only the npm opencode-ai latest version, so 1.x installs are never offered a 2.x build as a regular update.
- Upgrading to OpenCode 2 remains a separate, explicit choice through the 2.0 offer in /update or opencode upgrade --major.
- Fix upgrades for installs managed by yarn.
2026-10-16 · 0 changes · release
- @GitHub in Slack and Teams now supports working across multiple repositories in a single conversation. Whether you’re creating issues, opening pull requests, or investigating bugs, you can work across
- The post Multi-repository support and other improvements for GitHub in Slack and Teams appeared first on The GitHub Blog .
2026-10-16 · 107 changes · release
- The Gateway keeps running after the computer sleeps or the system clock jumps, instead of restarting itself because its ownership heartbeat looked stale. (#170790) Thanks @AnvinaLI, @sgh6688, @waynega
- Gateway shutdown and restart no longer hang on a stalled transcript worker or in-flight session lifecycle events. (#170493, #170555) Thanks @Oldrich333.
- Tlon group DMs no longer treat other participants as the owner, closing an owner-impersonation path. (#165801) Thanks @eleqtrizit.
2026-10-16 · 0 changes · release
- Cloud agents can now build and share interactive canvases. The Environments API is available in beta, environments support up to 300 repos, and large environments load 5x faster.
2026-10-15 · 243 changes · release
- New Features
- Open /config to search preferences across categories, change supported settings immediately, and see which changes require a restart. (#52990, #53429)
- Send a follow-up while Codex is responding to steer it immediately. Interrupting a turn also stops active Code Mode cells and their nested tool calls. (#51812, #51835)
2026-10-15 · 0 changes · release
- We will deprecate the following models across all GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions) on November 16th, 2026: Model Deprecation
- The post Upcoming deprecation of selected GitHub Copilot models in mid-November appeared first on The GitHub Blog .
2026-10-15 · 51 changes · release
- Added CLAUDECODERETRYWATCHDOGMAXUSAGELIMITWAITMS so unattended retry mode (CLAUDECODERETRYWATCHDOG) ends a request at a usage limit that resets too far away instead of waiting
- Added OpenTelemetry tracing guidance to the claude-api skill, including setting up trace destinations with the ant CLI
- Added the % motion to vim mode: jump to the matching bracket, alone or with d/c/y
2026-10-15 · 1 changes · release
- Session sharing has been discontinued. Existing share links and session-sharing commands are no longer available, and importing sessions from share URLs is unsupported.
2026-10-15 · 32 changes · release
- New Features
- Choose where /share uploads: sessionShareDestination selects auto, gist, or radius. See Sessions and context and Export or share a session.
- Cache-preserving thinking level changes on OpenAI GPT-6: changing the thinking level mid-session with an API key keeps the prompt cache.
2026-10-15 · 38 changes · release
- Show and edit agent models from the agents list.
- Configure transcript display, with a live preview and localized settings.
- Reuse the Core submenu in the prompt bar menu.
2026-10-15 · 186 changes · release
- <!-- Release notes generated using configuration in .github/release.yml at 8a415cb628db88844e0196bdfdcce83b4f88d812 -->
- fix(managed-agent): connector and broker robustness from the #12692 R2 review by @wenshao in https://github.com/QwenLM/qwen-code/pull/13330
- feat(managed-agent): H4e-b2 the lead's mailbox over Session messages by @wenshao in https://github.com/QwenLM/qwen-code/pull/13892
2026-10-15 · 103 changes · release
- Bundled CLI Version
- This SDK release bundles CLI version: 0.25.2
- Source: CLI built from source (same branch/ref as SDK)
2026-10-15 · 186 changes · release
- <!-- qwen-release-notes:v1 -->
- See the complete change list below.
- Breaking Changes
2026-10-15 · 0 changes · release
- Agentic autofix for code scanning alerts is now generally available. It remediates alerts by working across your codebase the way a developer would: it explores relevant files, proposes a fix,…
- The post Agentic autofix for code scanning alerts general availability appeared first on The GitHub Blog .
2026-10-15 · 99 changes · release
- This is a gateway-only extended-stable release, which is our current equivalent to LTS. This release is OpenClaw from the end of September 2026, plus critical security updates, reliability and perform
- Safer September upgrades: updates on the 2026.9 line keep state, plugin data, service ownership, and Windows state paths intact, and refuse automatic restore over unattributed Doctor writes. (#160167,
- Updates that finish on pnpm, npm, and Windows: pnpm 12 Gateway services and launchers survive native updates, retained updater runtimes no longer block npm recovery, and Windows updates no longer roll
2026-10-15 · 55 changes · release
- Minor Changes
- #15030 d749650 - Route Kilo Gateway traffic (chat, models, embeddings, autocomplete, transcription) through https://ai-gateway.kilo.ai/api/v1 by default, and support a KILOAIGATEWAYURL environment var
- Minor Changes
2026-10-15 · 221 changes · release
- Hermes Agent v0.22.2
- Release Date: October 15, 2026
- v0.22.1 was built from the wrong commit. It shipped unreleased gateway work, and the Microsoft Store app could stick on "Connecting." 0.22.2 is the release 0.22.1 was meant to be.
2026-10-14 · 701 changes · release
- Hermes Agent v0.22.1 (rc.5-v0.22.1)
- Release Date: October 14, 2026
- This is a patch release, with a handful of fixes for the Windows Store, plugin updates, and more.
2026-10-14 · 0 changes · release
- HydraFusion has an updated model pool, improved orchestration workflows, and introduces HydraFusion Max. Both HydraFusion and HydraFusion Max are available across VS Code, the GitHub Copilot app, and
- The post HydraFusion updates and new Max option appeared first on The GitHub Blog .
2026-10-14 · 6 changes · release
- Add support for Gemini 4 Argon
- Command hooks complete reliably even when child-exit signals are lost under Node
- MCP status and /mcp commands stay synced to the active session after split-view session switches
2026-10-14 · 88 changes · release
- Added virtualText to a mod's prompt decorations: text drawn in the prompt box that never enters the draft or the submitted prompt
- Added cachecreation5mtokens and cachecreation1htokens to the OpenTelemetry apirequest event, splitting cache writes by lifetime
- Added $.ui.view({ agentId }) for mods: shows an agent's transcript in the main view when you ask, and $.ui.view({}) goes back
2026-10-14 · 75 changes · release
- This week's release includes Git tag creation, the ability to drag Terminal tabs into the Agent Panel, and pre-filling of the File Finder's search query with text selected in the editor or terminal.
- Improved Agent Panel terminal support by allowing Terminal tabs to be dragged into it. (#60582; thanks cppcoffee)
- Improved custom Amazon Bedrock model support with configurable tool use, images, and thinking. (#64953; thanks mpyuglgwkxcmodyrpo)
2026-10-14 · 238 changes · release
- Hermes Agent v0.22.0
- Release Date: October 13, 2026
- Since v0.21.0: ~24,200 commits · ~6,080 merged PRs · ~15,600 files changed · ~2,045,000 insertions · ~1,140,000 deletions · ~7,180 issues closed · ~2,520 contributors
2026-10-14 · 190 changes · release
- Added CLAUDECODEDISABLEFILEMENTIONS environment variable: Claude gets the paths of @ file mentions to read with its file tools, not the files' contents
- Added idle compaction in the terminal: a 200K+ token conversation left idle for about 54 minutes is compacted before its one-hour prompt cache expires, so your next message doesn't reprocess it all
- Added CLAUDECODEIDLECOMPACTMINTOKENS to change idle compaction's 200K-token minimum; "idleCompaction": false in settings.json turns it off. Both need v2.1.290 or later
2026-10-13 · 17 changes · release
- refactor(a2a-server): implement V1 to V2 settings migration logic by @jvargassanchez-dot in https://github.com/google-gemini/gemini-cli/pull/29450
- fix(acp): bridge PromptResponse.usage and emit usageupdate notifications (#29389) by @elberthc-byte in https://github.com/google-gemini/gemini-cli/pull/29549
- Changelog for v0.63.0-preview.0 by @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/29565
2026-10-13 · 0 changes · release
- Gemini 4 Argon, Google’s newest frontier model, is now generally available in GitHub Copilot. It is designed for complex coding, agentic, and reasoning tasks. In early testing, Gemini 4 Argon…
- The post Gemini 4 Argon in GitHub Copilot appeared first on The GitHub Blog .
2026-10-13 · 25 changes · release
- Add agent-scoped declarative hooks for custom agents
- Remote plugin marketplace and plugin fetches retry once with your signed-in GitHub token after HTTPS auth fails.
- Streamed responses behind TLS-intercepting proxies complete when closenotify is omitted
2026-10-13 · 0 changes · release
- Enterprise administrators can now require supported GitHub Copilot clients to retrieve current server-managed settings at startup instead of relying on a cached policy. We are also adding minimum clie
- The post Enterprise managed settings enforcement updates appeared first on The GitHub Blog .
2026-10-13 · 15 changes · release
- A new outline along the left edge of the conversation lists each prompt you sent. Hover a mark to preview the prompt, and click it to jump there
- Plugins that fail to load or error during a session now show a status line in the chat naming the plugin and the error, instead of silently losing their tools
- You can cancel a Cline Cloud sign-in while it is waiting for the browser
2026-10-13 · 13 changes · release
- With no model chosen, the Cline and OpenRouter providers now use Claude Sonnet 5.5. For Cline, that's the first model in Cline's recommended list.
- Selecting ai& shows its own API key and model picker, instead of the generic OpenAI-compatible form with base URL and custom headers.
- Refreshed the model catalog. Adds Claude Haiku 5.5 and the AI/ML API, LowRouter, and Prime Inference providers. The Cline free list adds Step 5 Preview. The v0 provider now offers only its default mod
2026-10-13 · 16 changes · release
- <!-- openclaw-release-publication:docs-v1 -->
- OpenClaw v2026.10.3
- commits · 79 pull requests · 99 contributors
2026-10-13 · 13 changes · release
- Plugins now load inside the hub instead of a separate node or bun process, so the CLI no longer needs a JavaScript runtime on your PATH to run plugins. A plugin that fails to load no longer silently l
- --thinking now applies in ACP mode (--acp). Before, ACP sessions always ran with reasoning off
- cline hook accepts agenterror events. Before, it exited with an error and no response
2026-10-13 · 13 changes · release
- Plugins load in-process through one registry per process instead of a node/bun subprocess, so the compiled CLI and its hub no longer need a runtime on PATH, and plugins can use the Bun global under th
- Turning reasoning off now works on every provider, not just a fixed list. Models whose catalog entry has no off option are sent nothing and keep their default, and models without a reasoning capabilit
- The cline provider's default model is the first entry of the Cline recommended-models list, falling back to anthropic/claude-sonnet-5.5. CLINEDEFAULTMODELID moves from Claude Sonnet 5 to Claude Sonnet
2026-10-13 · 0 changes · release
- Origin integrates with over 20 apps for deployments, CI, code review, security, monitoring, and project management, and the marketplace is now open to public submissions.
2026-10-12 · 43 changes · release
- New Features
- Per-key OpenRouter model lists: with an OpenRouter key, Pi lists only the models that key may use, with the key's context size, max output, and prices, including regional endpoints set in models.json.
- Published configuration schemas: add $schema to settings.json, models.json, keybindings, and themes for editor validation and completion. See Settings, Models, Keybindings, and Themes.
2026-10-12 · 0 changes · release
- Enterprise administrators can now use telemetry in managed settings to attribute GitHub Copilot activity to a user without collecting their prompts, responses, or tool content. The telemetry.capture.i
- The post Client telemetry user attribution and configurable capture appeared first on The GitHub Blog .
2026-10-12 · 3 changes · release
- (2026-10-12)
- <!-- Release notes generated using configuration in .github/release.yml at main -->
- fix(docker): copy MARS web bridge modules into the image by @VascoSch92 in https://github.com/OpenHands/OpenHands/pull/18343
2026-10-12 · 9 changes · release
- Interactive sandbox settings suggest possible environment secrets and let you add masking hosts before saving.
- Make model IDs in /model and /config model case-insensitive and save canonical IDs
- Keep /allow-all available during startup while enterprise policy is still resolving
2026-10-12 · 6 changes · release
- Fixed an issue where no fonts would show for the markdown preview configurations in the settings UI. (#65447)
- Fixed edit predictions retaining single worktree files (#65400)
- Fixed the remote projects picker sometimes reserving more space than needed. (#65391)
2026-10-12 · 67 changes · release
- (2026-10-12)
- <!-- Release notes generated using configuration in .github/release.yml at main -->
- feat(verify-openhands): drive the mock-LLM e2e behaviors on DeepSeek and map the gaps by @enyst in https://github.com/OpenHands/OpenHands/pull/18191
2026-10-12 · 7 changes · release
- Hermes Agent v0.21.7
- Release Date: October 11, 2026
- Patch release. This tag rolls up the ~204 PRs merged since v0.21.6 into a stable release for the desktop app (macOS Apple silicon, Windows), the Microsoft Store and MSIX, the installer, Docker and Her
2026-10-12 · 123 changes · release
- Updates from 2026.10.1: the first upgrade from stable 2026.10.1 now completes cleanly, successful in-place updates no longer end in errors, and Windows, cloned-filesystem, and private-Node update path
- Doctor and update recovery: Doctor no longer stops on residual legacy imports, stale Gateway locks, slow state inspection, memory reindex locks, or allowlists for removed channel accounts, and stale-r
- Provider-native compaction: OpenAI and Anthropic API-key routes now default to provider-native compaction, and compaction recovers when the primary auth profile is cooling down. (#168164, #166459) Tha
2026-10-11 · 103 changes · release
- Bundled CLI Version
- This SDK release bundles CLI version: 0.25.1
- Source: CLI built from source (same branch/ref as SDK)
2026-10-11 · 627 changes · release
- <!-- Release notes generated using configuration in .github/release.yml at c1a8218f38203e272e6e965778ed6a2795cfeed7 -->
- fix(serve): preserve session creation failure diagnostics by @callmeYe in https://github.com/QwenLM/qwen-code/pull/12331
- feat(sdk-java): Add managed runtime attestation client by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/12522
2026-10-11 · 194 changes · release
- <!-- qwen-release-notes:v1 -->
- See the complete change list below.
- Breaking Changes
2026-10-11 · 8 changes · release
- Improvements
- Run opencode upgrade --major to upgrade to OpenCode 2.
- Allow the OpenAI ultrafast service tier.
2026-10-10 · 16 changes · release
- <!-- openclaw-release-publication:docs-v1 -->
- OpenClaw v2026.10.1
- ,055 commits · 2,425 pull requests · 402 contributors
2026-10-10 · 0 changes · release
- This update brings more control over default models and MCP server in GitHub Copilot for JetBrains. It also makes diagnostics easier to address, improves chat navigation and account controls, and…
- The post New controls and chat improvements in Copilot for JetBrains appeared first on The GitHub Blog .
2026-10-09 · 0 changes · release
- This week’s updates make Copilot easier to use across accounts and environments, with more control over what agents can access and how you manage their work. GitHub Copilot Claude Haiku…
- The post GitHub Copilot weekly releases — October 5 appeared first on The GitHub Blog .
2026-10-09 · 2 changes · release
- Fixed a TUI crash when asynchronous questions contain multiple lines, preserving line breaks and complete hyperlink destinations. (#51866)
- Fixed startup failures caused by differences between a running background server's feature settings and CLI defaults. Compatibility checks now apply only to explicit command-line feature overrides. (#
- Full Changelog: https://github.com/openai/codex/compare/rust-v0.162.0...rust-v0.162.1
2026-10-09 · 79 changes · release
- Added a code key to the Claude apps gateway's managed.policies[]: the same settings as cli, also applied in Claude Desktop's Code tab; beside desktop, it turns on Claude Desktop's gateway mode
- Added autoCompactWindow to subagent frontmatter and --agents definitions, so a subagent can auto-compact earlier than the main conversation's window
- Added CLAUDECODEWORKFLOWSUBAGENTMODEL to run every workflow agent on one model while other subagents keep theirs
2026-10-09 · 4 changes · release
- Use native Microsoft Entra broker authentication on macOS when available, with browser fallback.
- copilot config supports sandbox credential injectHosts keys, with key completion in Bash, Zsh, and Fish.
- context now applies to new and resumed ACP sessions instead of silently using the default or previously saved context tier
2026-10-09 · 1 changes · release
- This fixes new GPT-6 models via Copilot!
- dc75b0911bf5dea2cbaec64af557f7a45: fix: route newer Copilot models through the Responses API (#4048) (@DaVinci42)
- <summary>Verifying the artifacts</summary>
2026-10-08 · 59 changes · release
- (2026-10-08)
- <!-- Release notes generated using configuration in .github/release.yml at main -->
- feat(apps): add authenticated backend view helper by @neubig in https://github.com/OpenHands/OpenHands/pull/17656
2026-10-08 · 8 changes · release
- Add Claude Haiku 5.5 to model selection and --model completions
- copilot mcp add recovers cleanly after interrupted MCP config initialization
- MCP enable/disable now works before server discovery without starting MCP servers
2026-10-08 · 143 changes · release
- Added onFailure: "block" for command and HTTP hooks: a hook that can't start, times out, or exits with an unexpected code blocks the action instead of letting it through
- Added Program Status Protocol (OSC 7501) support: terminals that implement it can show whether Claude Code is working, waiting on you, or done
- Added quoted text to the /copy picker, so a drafted message copies without its > markers
2026-10-08 · 0 changes · release
- This release adds new billing and license controls for Copilot code review admins: Billing: Organization owners can bill Copilot code reviews from members with a Copilot license to the organization’s…
- The post Copilot code review: New organization billing options and controls appeared first on The GitHub Blog .
2026-10-08 · 239 changes · release
- New Features
- Add tools for creating and listing managed Git worktrees from trusted local projects when the worktrees feature is enabled. (#50148)
- Pin tasks in the agent Command Center with p and keep them in a shared Pinned group when supported by the server. (#51500)
2026-10-08 · 25 changes · release
- Prompt for goose mode during first-time configure #12629
- HTML session export with an interactive viewer #11977
- Adaptive thinking for Claude Sonnet and Haiku 5.5 #12761
2026-10-08 · 23 changes · release
- Rex, OSC 7501, xAI/Grok OAuth and more
- Hey! There’s some good quality of life stuff in this release. Let’s take a look!
- It’s Rex Time
2026-10-08 · 9 changes · release
- Hermes Agent v0.21.6
- Release Date: October 8, 2026
- Patch release. This tag rolls up the ~2,100 PRs merged since v0.21.5 into a stable tagged release for Docker and Hermes Cloud. Full curated notes for this window ship with v0.22.0.
2026-10-08 · 16 changes · release
- <!-- openclaw-release-publication:docs-v1 -->
- OpenClaw v2026.9.9
- commits · 112 pull requests · 92 contributors
2026-10-08 · 7 changes · release
- SSH remotes start again. Since 0.0.38, connecting to an SSH environment failed with SyntaxError: Invalid character
- On SSH environments, the git branch label no longer opens two new SSH logins every 5 seconds. It checks every 30 seconds now, and switching branches from the picker still updates it right away
- Long model names in the composer show in full when the row has room, and only truncate when it runs out
2026-10-08 · 12 changes · release
- Commit message generation and tasks with reasoning off no longer fail with a 400 error on GPT-6 Astra, GPT-6.1 Sol, Claude Fable 5 or Claude Opus 5.5
- Cline no longer exits about 3 seconds after an MCP server or hook quits before reading all of its input
- Settings migrated from the VS Code extension no longer add an empty SAP AI Core provider
2026-10-08 · 5 changes · release
- The AI SDK moves together to one release line: ai 7.0.120 and every @ai-sdk/ package on @ai-sdk/provider-utils 5.0.50 (previously ai 7.0.79 with packages bumped one by one). Turning reasoning off no l
- Stdio MCP clients handle EPIPE when a server exits before reading all of its input. Previously that raised an uncaught exception on the host process. The SAP AI Core provider also no longer installs w
- The legacy provider-settings migration no longer adds an empty sapaicore entry to providers.json. It used to do this for every migrated user, because the extension writes sapAiCoreUseOrchestrationMode