changelog

Cline's v4.1.22 release adds two new model providers, refreshes default models across more than a dozen gateways including a switch to GPT-6.1 Sol, and fixes bugs in Anthropic content-filter handling, Bedrock inference profiles, and reasoning token accounting.

Vercel released @ai-sdk/openai version 3.0.121, a patch that adds SDK support for a model string called 'GPT-6.1 Sol.' OpenAI has not publicly announced or confirmed this model, and no specs, pricing, or benchmarks are available.

Vercel's @ai-sdk/openai package version 2.0.132 quietly adds support for a model identifier called 'GPT-6.1 Sol.' OpenAI has not confirmed the model's existence, specs, or release date.

OpenAI shipped v3.22.0 of the openai-python library, adding computer use support to the beta agents API. The release is a client library update, not a new model.

OpenAI released v3.21.0 of its official Python SDK on September 29, 2026, adding a constant for a new 'GPT-6.1 Sol' model identifier. No pricing, benchmarks, or capability details have been disclosed.

Anthropic's anthropic-sdk-python v1.9.0 release adds a reference to an unannounced 'claude-sonnet-5-5' model ID, a new between_tools thinking type, and the ability to run tool calls while a reply streams. No pricing, context window, or benchmark data for the model has been disclosed.

Vercel released version 4.0.78 of @ai-sdk/openai, a patch that adds support for setting reasoningEffort to 'none' for GPT-6 Sol and Luna models. The update also introduces validation logic that warns on unsupported request-level effort updates and rejects invalid historical ones.

Cline's v4.1.21 update adds a new OpenAI-compatible provider called ai&, refreshes its model catalog to 6,386 models across 209 providers, and fixes a bug that ended tasks prematurely when local models hit output-token limits. Eleven unpinned providers, including GitHub Copilot and Vertex, now default to Claude Opus 5.5.

OpenAI released v3.19.0 of its Python SDK on September 22, 2026, adding GCP external storage support and a code reference to an unannounced research model called GPT-Rosalind. The release also ships five bug fixes covering WebSocket handling, retry logic, and async compatibility.

OpenAI has updated its prompt caching system for GPT-6, adding explicit cache breakpoints, new diagnostic tools, and finer-grained controls. The company claims the changes improve cache hit rates and reduce both latency and cost for repeated-context API calls.

OpenAI has published a changelog describing improved prompt caching for GPT-6, claiming higher cache hit rates, new diagnostic tooling, and explicit cache breakpoints. The update targets developers running high-volume, repetitive-prompt workloads who want lower latency and cost.

OpenAI's openai-python SDK v3.18.0 release adds two new model identifiers, 'GPT-6 Sol' and 'GPT-6 Luna,' to its codebase. No official model announcement, specifications, or pricing has been released alongside this change.

Anthropic released v1.8.0 of its Python SDK, adding support for the claude-opus-5-5 model, inline tool definitions, and beta MCP tool-list pinning. The release also fixes a Python 3.13 exit crash and several tool-handling bugs.

Vercel released version 3.0.134 of its @ai-sdk/xai provider package, adding support for a Grok 4.7 model ID. The patch also bumps two internal dependencies, provider-utils and openai-compatible.

Vercel released version 2.0.95 of its @ai-sdk/xai provider package, a patch update that adds a model identifier for Grok 4.7. The change lets developers targeting xAI models through the Vercel AI SDK reference the new model string in their code.

Vercel released @ai-sdk/xai version 5.0.5, a patch update that adds a model ID for 'grok 4.7' to its xAI provider package. The change lets developers targeting xAI models through the Vercel AI SDK reference the new identifier in their code.

OpenAI released v3.15.0 of its Python SDK on September 18, 2026, adding managed Responses WebSocket sessions, prompt-cache prewarming, compaction progress events, and audio-mini model choices. The release also fixes a bug affecting chat stream moderation results.

Cline CLI v3.0.62 introduces automatic retry logic for transient provider errors, fixes performance stalls in large workspaces, and refreshes its bundled model catalog from 5,788 to 6,079 models. The release also previews Cline Desktop, a new native app for open-weight models.

OpenAI shipped v3.13.0 of its openai-python library, adding support for a new Agents API. The release is a client-library update, not a new model.

OpenAI shipped v3.12.0 of its Python SDK on September 10, 2026, adding client support for a new Live API and fixing three bugs related to async streaming and type annotations. The release contains no new model weights.

OpenAI released v3.10.0 of its official Python SDK, adding support for GPT Image 2.5 models and image generation options, plus new expiration fields for service-account API keys. The release does not include pricing, benchmark, or model card details.

Vercel released @ai-sdk/openai version 4.0.60, a patch update that adds reasoning configuration support referencing 'GPT-6' in the codebase. OpenAI has not announced a GPT-6 model, making this an early SDK-side scaffolding change rather than confirmation of a new release.

OpenAI has published detailed prompting guidance for GPT-6 Astra, addressing the model's tendency to over-clarify, over-test, and use clichéd AI phrasing. The documentation includes specific prompts to encourage more autonomous action and a blocklist of banned words and phrases.

The openai-python SDK v3.8.0 release notes, dated September 3, 2026, list a feature addition for 'gpt-6-astra' — a model name not previously confirmed by OpenAI. No official announcement, pricing, or specifications have been released.

Cline Desktop v0.0.19 fixes a memory leak where session status updates carried full conversation transcripts to every connected client, ballooning process memory to tens of gigabytes on long tasks. The release also adds seven new model providers and changes default models for several existing ones.

Ollama's v0.33.0 pre-release adds direct model management inside Claude Desktop's menu bar and fixes a caching bug that could force reprocessing of tens of thousands of tokens. The release also disables a Claude Code system message that was breaking KV cache hits on every request.

Cline's v4.1.11 update adds inline image generation for supported models and fixes a code actions bug that broke on VS Code 1.134. The release also expands the model catalog with eight new providers including AMD, Arcee, and RunInfra.

Anthropic released v0.124.0 of its Python SDK, graduating the Files and Skills APIs to general availability and introducing new computer use and browser use toolsets. The release is available now on GitHub.

OpenAI released v3.1.0 of its Python client library, adding support for a new 'Ultrafast' tier, WebSocket stream IDs, and structured MCP/WebSocket error handling. The release also formally deprecates the Sora video API and strips out remaining Stainless SDK-generation infrastructure.

Vercel shipped a patch release of @ai-sdk/google-vertex (v4.0.182) that adds support for a model identifier called 'gemini-3.7-flash.' Google has not publicly announced this model, and no official details on pricing, context window, or benchmarks exist yet.

Cline's CLI v3.0.54 release fixes a major bug that made the Claude Code provider unusable for agentic work, along with tool-call JSON truncation handling and token telemetry that was overcounting cache-heavy sessions by roughly 5x. The update also changes how Managed Hub daemons handle version conflicts between multiple Cline installs.

Vercel released version 4.0.37 of its @ai-sdk/xai package, adding support for Grok 4.6 model IDs and a new 'xhigh' reasoning effort level. The patch update lets developers using the Vercel AI SDK target xAI's newest model IDs directly.

Vercel released @ai-sdk/xai version 3.0.119, a patch update that adds model IDs for Grok 4.6 and introduces support for an 'xhigh' reasoning effort parameter. The change lets developers using the Vercel AI SDK target xAI's newer model directly through the existing provider interface.

Vercel shipped @ai-sdk/xai version 2.0.86, a patch release that adds support for Grok 4.6 models in its xAI provider integration. The update lets developers using the Vercel AI SDK route requests to Grok 4.6 without custom API handling.

Vercel released @ai-sdk/xai version 4.0.36, adding support for xAI's grok-imagine-video-1.5 model with native 1080p resolution and a new referenceVoiceIds parameter for reference-to-video audio. The update also fixes a routing bug that misdirected certain video generation requests.

Anthropic released version 0.121.0 of its Python SDK on August 7, 2026, introducing a new beta for mid-conversation tool changes, session budgets, an advisor tool, pinned inference location, and skills auto-loading from GitHub. The update also removes retired Claude Opus 4.1 models from the API.

Cline released CLI v3.0.51, a patch update that standardizes how reasoning effort settings apply across AI providers, including Ollama. The update also adds a new selectable model and corrects error telemetry reporting.

GitHub has retired the Copilot Billing Preview app, removing it from availability entirely. Copilot spend tracking and management now happens directly within GitHub's standard billing settings.

OpenAI released version 2.53.0 of its Python SDK, adding type definitions referencing a model called 'gpt-5.5' along with new tool name/namespace fields for the Responses API. OpenAI has not made any public announcement about a GPT-5.5 model.

DeepSeek has published a new routing endpoint, deepseek-v4-flash-latest, that always points to the newest model in its V4 Flash family. The endpoint offers a 1,049K token context window and pricing of $0.09/M input and $0.18/M output tokens via OpenRouter.

GitHub deprecated Gemini 2.5 Pro and Gemini 3 Flash across all Copilot experiences effective July 31, 2026. The models are no longer available in Copilot Chat, inline edits, ask and agent modes, or code completions.

Cline's SDK v0.0.67 pulls reasoning effort and budget controls from the models.dev catalog to match each provider's actual capabilities, while fixing a bug that forced redundant re-compaction calls on every turn. The release also adds session forking for editing earlier prompts and makes MCP server timeouts configurable.

Cline's CLI v3.0.47 release adds full support for free Cline models with usage-limit indicators, makes settings persist across restarts, and upgrades the terminal UI stack. Agentic compaction is now the default context-management strategy, alongside several stability fixes.

Kilo Code released JetBrains plugin version 7.0.11, adding a signed, GitHub-hosted bundled CLI for offline installs and adaptive thinking support for Claude Opus and Sonnet 5+ model identifiers across Anthropic, AI Gateway, and Bedrock providers. The update also fixes session data loss and stale CLI cleanup issues.

Cline's v4.0.11 release adds provider support for Claude Opus 5 (including 1M context window variants) across six integrations and introduces Moonshot Kimi K3 support. The update also fixes a pricing bug that overstated costs for Opus 1M-context requests above 200k tokens.

The anthropic-sdk-python v0.120.0 release adds a reference to a model identifier called claude-opus-5, the first public sign of a next-generation Opus model. Anthropic has not issued an official announcement, and no pricing, context window, or benchmark data has been disclosed.

Vercel released version 4.0.10 of its xAI SDK provider, adding support for the Grok-4.5 model and introducing video reference inputs for reference-to-video generation. The update extends the existing image reference capability to handle video inputs.

OpenCode v1.15.13 introduces custom session metadata storage through its API and SDK. The release fixes a bug where Anthropic's Opus 4.7+ adaptive reasoning returned empty thinking blocks instead of summarized thinking.

Google has modified Gemini's compute-based usage limits introduced at I/O 2026 after users reported depleting quotas too quickly. The company is now capping how much quota a single Gemini 3.1 Pro prompt can consume and making all 3.1 Flash-Lite prompts free.

Cursor has integrated its AI code editor into Microsoft Teams, allowing developers to delegate coding tasks by mentioning @Cursor in any Teams channel. The integration automatically selects repositories and AI models, reads thread context, and generates pull requests for team review.