Anthropic updates SDKs and Claude Code with new features and fixes
ByPulseAugur Editorial·[457 sources]·
Anthropic has released updates across its SDKs and the Claude Code application. The Python SDK has seen versions v0.125.0 and v0.124.0 released, while the TypeScript SDK has updated to v0.120.0 and v0.119.0. Claude Code has received significant updates in versions v2.1.236 and v2.1.235, introducing new features like environment variables for default models, idle notifications, and enhanced sandbox security, alongside numerous bug fixes and performance improvements.
AI
IMPACT
These updates likely improve developer experience and stability for users interacting with Anthropic's models.
RANK_REASON
Multiple releases of SDKs and a code editor application.
<h2>What's Changed</h2> <ul> <li>Ollama's app now follows the system appearance again, restoring dark mode support</li> <li>Fixed the macOS app to properly hand off to an already-running instance instead of starting a second one</li> <li>The Claude Desktop proxy no longer interru…
<h2>What's changed</h2> <ul> <li>Added <code>PreModelSwitch</code> and <code>PostModelSwitch</code> hook events (block, confirm, or annotate a model switch); <code>SessionStart</code> resume hooks now receive session staleness and the estimated re-cache cost</li> <li>Added live s…
<h2>What's changed</h2> <ul> <li>Added <code>--restricted</code> (or <code>CLAUDE_CODE_RESTRICTED=1</code>): removes the built-in tools that run commands or code and <code>WebFetch</code> (unless named in <code>--tools</code>), keeps file tools inside the working directory, refus…
<h2>What's changed</h2> <ul> <li>Added the <code>SendFeedback</code> tool: when something goes wrong in a session, Claude can draft a feedback report for you to review and send from <code>/feedback</code> (turn off with the <code>feedbackDrafts</code> setting)</li> <li>Added <cod…
<h2>What's Changed</h2> <h3>Claude Desktop</h3> <p>Developers can now easily configure Claude Desktop to seamlessly work with Ollama as a third-party gateway provider.</p> <a href="https://private-user-images.githubusercontent.com/29360864/641249150-c02fd93b-f599-40a9-83c3-d0555c…
<h2>What's changed</h2> <ul> <li>Added a startup warning for Bash allow rules with a wildcard before the subcommand (e.g. <code>Bash(git * main)</code>), since they also match options inserted before the subcommand</li> <li>Added an Auto mode tab to <code>/permissions</code> for …
<h2>Overview</h2> <p>llama.cpp 0.3.0 introduces the dots3-note multimodal model (with a new DSA-ISWA KV cache), MTP support for GLM-4.5-Air, and tensor-split (<code>-sm tensor</code>) plus multi-sequence rollback fixes for DeepSeek 4. ggml is bumped to v0.22.0 (meta-backend tenso…
<h2>What's changed</h2> <ul> <li>Fixed a crash on startup on Linux distributions that ship glibc 2.44 (for example Arch Linux, CachyOS and Fedora Rawhide)</li> </ul>
<h2>What's changed</h2> <ul> <li>Added a Loops breakdown to <code>/usage</code>: per-loop run count, total tokens, tokens per run, and last run, so runaway or chatty <code>/loop</code> tasks are easy to spot</li> <li>Added <code>modelPicker</code> setting: curate the <code>/model…
<h2>What's changed</h2> <ul> <li>Cost estimates (<code>/cost</code>, status line, <code>--max-budget-usd</code>) now include the 1.1× US-only-inference premium for data-residency workspaces</li> <li>Added the one-time fullscreen renderer offer on Bedrock, Vertex, Foundry and othe…
<h2>Overview</h2> <p>New version has been released.</p> <p><strong>Nightly build:</strong> <a href="https://github.com/ggml-org/llama.cpp/releases/tag/b10566">b10566</a></p> <p><strong>Web UI:</strong> the <code>nightly-tag.txt</code> asset contains the tag of the corresponding n…
<h2>What's changed</h2> <ul> <li>Added a <code>keybindingFlavor</code> setting: set it to <code>"readline"</code> to make Ctrl+W in the prompt delete back to the previous whitespace, as in Bash; the default (<code>"classic"</code>) is unchanged</li> <li>Plugin marketplaces: <code…
<h2>1.0.0 (2026-08-20)</h2> <p>Full Changelog: <a href="https://github.com/anthropics/anthropic-sdk-python/compare/v0.125.0...v1.0.0">v0.125.0...v1.0.0</a></p> <h3>⚠ BREAKING CHANGES</h3> <ul> <li><strong>client:</strong> upgrade to httpx2 and some minor breaking changes. See MIG…
<h2>What's changed</h2> <ul> <li>Fixed prompt caching for sessions using an LLM gateway or custom base URL</li> <li>Added a built-in "Concise" output style: Claude leads with results and skips preamble and narration, while doing the work just as thoroughly. Select it under Output…
<h2>What's Changed</h2> <ul> <li>Add a model metadata cache to reduce Ollama’s per-request overhead</li> </ul> <h2>New Contributors</h2> <ul> <li><a class="user-mention notranslate" href="https://github.com/gaugarg-nv">@gaugarg-nv</a> made their first contribution in <a class="is…
<h2>What's changed</h2> <ul> <li>Added <code>ANTHROPIC_DEFAULT_MODEL</code> environment variable: sets the model new sessions start on, while a <code>/model</code> pick still overrides it and persists across restarts (unlike <code>ANTHROPIC_MODEL</code>)</li> <li>Added <code>noti…
<h2>0.124.0 (2026-08-19)</h2> <p>Full Changelog: <a href="https://github.com/anthropics/anthropic-sdk-python/compare/v0.123.0...v0.124.0">v0.123.0...v0.124.0</a></p> <h3>Features</h3> <ul> <li><strong>api:</strong> Files and Skills APIs are now GA; add computer use and browser us…
<h2>What's changed</h2> <ul> <li>Added an optional <code>spellcheck</code> setting that underlines misspelled words in the prompt input as you type, using your installed <code>aspell</code>, <code>hunspell</code>, or <code>ispell</code></li> <li>Fixed whole-prompt-cache invalidat…
<h2>What's changed</h2> <ul> <li>Added the optional <code>CLAUDE_CODE_PROJECT_DIR_NAME</code> environment variable: hosts that give each session its own config directory can choose a short name for the per-project transcript directory</li> <li>Added the <code>selection:clear</cod…
<h2>What's changed</h2> <ul> <li>Added GitLab merge request URL support to the <code>--worktree</code> flag and the <code>claude agents</code> view (where MRs display as <code>!N</code>)</li> <li>Added an opt-in <code>forward_user_identity</code> apps gateway setting on Anthropic…
<h2>What's changed</h2> <ul> <li>Subagent forking is now on by default: a <code>subagent_type: "fork"</code> subagent inherits the full conversation and prompt cache, and non-teammate agent spawns in interactive sessions now run in the background by default</li> <li>Type <code>@<…
<h2>0.122.0 (2026-08-13)</h2> <p>Full Changelog: <a href="https://github.com/anthropics/anthropic-sdk-python/compare/v0.121.0...v0.122.0">v0.121.0...v0.122.0</a></p> <h3>Features</h3> <ul> <li><strong>api:</strong> add output_behavior to dream creation (create a new memory store …
<h2>What's Changed</h2> <ul> <li>Models that don't set a <code>repeat_penalty</code> now default to 1.0 (off) instead of 1.1, matching other engines and speeding up speculative decoding; set a per-model parameter if an older model repeats itself.</li> <li>Faster prefill on NVFP4 …
<h2>What's changed</h2> <ul> <li>Fixed MCP OAuth sign-in failing with a redirect URI mismatch for servers that use a pre-registered OAuth client, such as Slack</li> </ul>
<h2>What's Changed</h2> <ul> <li>Models that don't set a <code>repeat_penalty</code> now default to 1.0 (off) instead of 1.1, matching other engines and speeding up speculative decoding; set a per-model parameter if an older model repeats itself.</li> <li>Faster prefill on NVFP4 …
<h2>What's changed</h2> <ul> <li>Documented <code>claude remote-control --continue</code> for resuming the most recent Remote Control session</li> <li>Added server-supplied Claude Code hook support for self-hosted runner sessions, matching managed-environment behavior</li> <li>Ad…
<h2>What's changed</h2> <ul> <li>Fixed interactive sessions that could stop redrawing entirely, while the process kept running, after a rare internal layout error</li> <li>Fixed <code>git</code> / Git Bash not being found on Windows when Claude Code is launched from a parent fold…
<h2>NVIDIA Nemotron 3.5 Lightning</h2> <p><a href="https://ollama.com/library/nemotron-3.5-lightning" rel="nofollow">NVIDIA Nemotron 3.5 Lightning</a> is an open 30B mixture-of-experts (MoE) model with 3B active parameters built for that execution layer of always-on agents. It is…
<h2>Muse Glimmer</h2> <p>Muse Glimmer is now available on all platforms. Muse Glimmer can power coding agent applications such as Claude Code, Codex, Pi and more, as well as long-running personal assistants such as OpenClaw and Hermes.</p> <p>Ollama's MLX engine provides state-of…
<h2>What's changed</h2> <ul> <li>Fixed feature flags being evaluated without the user's subscription tier when a session started with an expired login token, which could wrongly prompt Max plan users to enable usage credits for Fable</li> <li>Fixed every Bash command failing unde…
<h2>Muse Glimmer</h2> <blockquote> <p>Note: Muse Glimmer is currently available via initial support via Ollama's MLX engine on Apple Silicon. Additional support and optimizations for Apple Silicon, NVIDIA, AMD, and other platforms will be available in the coming days.</p> </block…
<h1>Release v5.15.0</h1> <h2>New Model additions</h2> <h3>Meta Muse Glimmer</h3> <p>Muse Glimmer, released today, is Meta’s new multimodal model, especially designed for agentic use cases. Distilled from Muse to 30B parameters, and released under the Apache 2.0 license, it can be…
<h2>What's changed</h2> <ul> <li>Added gateway spend-limit support to Claude Code's usage warning; the limit-reached message now names the cap, its reset time, and the operator's message (requires the gateway on 2.1.225)</li> <li>Added a workspace trust prompt to <code>claude age…
<h2>What's changed</h2> <ul> <li>Added self-hosted environments: <code>claude self-hosted-runner</code> turns your own machines or containers into a place Claude Code web, mobile, and desktop sessions can run, on Team and Enterprise plans</li> <li>Added <code>archive</code> plugi…
<h2>What's changed</h2> <ul> <li>Added owner wildcard entries (<code>"owner/*"</code>) to the <code>strictKnownMarketplaces</code> and <code>blockedMarketplaces</code> managed settings for allowing or blocking all marketplace repos under a GitHub org</li> <li>Added a warning when…
<h2>What's Changed</h2> <ul> <li>Qwen3.5 is faster on Apple GPUs: the MLX engine now uses the model's MTP head for speculative decoding automatically</li> <li><code>/v1/chat/completions</code> streaming now matches OpenAI's wire format: <code>role</code> only on the first chunk, …
<h2>What's changed</h2> <ul> <li>Fixed worktree-isolated sessions and their subagents being able to run destructive git commands against the main checkout; isolation now applies to file edits and Bash in every session type</li> <li>Fixed PreToolUse auto-allow hooks bypassing tool…
<h2>What's changed</h2> <ul> <li>[VSCode] Added Focus view: a chat-menu toggle that hides tool activity behind an expandable per-turn summary with a live running-tool indicator, toggled with <code>Ctrl+Alt+F</code> or the "Claude Code: Toggle Focus view" command</li> <li>Added <c…
<h2>What's Changed</h2> <ul> <li>Fixed an MLX Metal bug that could reduce output quality for NVFP4 models, particularly Laguna.</li> </ul> <p><strong>Full Changelog</strong>: <a class="commit-link" href="https://github.com/ollama/ollama/compare/v0.32.4...v0.32.5"><tt>v0.32.4...v0…
<h2>What's Changed</h2> <ul> <li>x/create: quantize lm_head at 8-bit in the requested family by <a class="user-mention notranslate" href="https://github.com/jessegross">@jessegross</a> in <a class="issue-link js-issue-link" href="https://github.com/ollama/ollama/pull/17357">#1735…
<h2>What's changed</h2> <ul> <li>Added Claude Opus 5 (<code>claude-opus-5</code>), now the default Opus model — 1M context, fast mode at $10/$50 per Mtok</li> <li>Added <code>sandbox.network.strictAllowlist</code> setting to deny non-allowlisted hosts for sandboxed commands witho…
<h2>What's Changed</h2> <ul> <li>Fixed model downloads that stall before sending data.</li> <li>Improved integrations: restored Claude Code Channels, fixed Anthropic thinking streams, and made Hermes Desktop respect <code>--force-build</code>.</li> <li>Expanded GPU support with C…
<h2>What's changed</h2> <ul> <li>Changed <code>/code-review</code> to run as a background subagent, so review work no longer fills your conversation and keeps stacked slash commands as its review target</li> <li>Added screen-reader announcements of deleted text for word and line …
<h2>What's changed</h2> <ul> <li>Added emoji shortcode autocomplete in the prompt input: type <code>:heart:</code> to insert ❤️, or <code>:hea</code> for suggestions — disable with the <code>emojiCompletionEnabled</code> setting</li> <li>Added warnings when transcript writes are …
<h2>What's changed</h2> <ul> <li>Added <code>sandbox.filesystem.disabled</code> setting to skip filesystem isolation while keeping network egress control</li> <li>Fixed a slowdown in long sessions where message normalization cost grew quadratically with the number of turns, causi…
<h2>What's changed</h2> <ul> <li>Claude no longer runs the <code>/verify</code> and <code>/code-review</code> skills on its own; invoke them with <code>/verify</code> or <code>/code-review</code> when you want them</li> </ul>
<h2>What's changed</h2> <ul> <li>Fixed single-segment <code>dir/**</code> allow rules like <code>Edit(src/**)</code> auto-approving writes to nested <code>dir/</code> directories anywhere in the tree instead of only <code><cwd>/dir</code></li> <li>Fixed a permission-check b…
<h2>What's changed</h2> <ul> <li><code>/fork</code> now copies your conversation into a new background session (its own row in <code>claude agents</code>) while you keep working; the in-session subagent it used to launch is now <code>/subtask</code></li> <li>Added <code>claude au…
<h2>What's changed</h2> <ul> <li>Added <code>--forward-subagent-text</code> flag and <code>CLAUDE_CODE_FORWARD_SUBAGENT_TEXT</code> environment variable to include subagent text and thinking in stream-json output</li> <li>Fixed permission previews relayed to chat channels not neu…
<p>cmd: put current working dir in the system prompt (<a class="issue-link js-issue-link" href="https://github.com/ollama/ollama/pull/17188">#17188</a>)</p>
<p>cmd: put current working dir in the system prompt (<a class="issue-link js-issue-link" href="https://github.com/ollama/ollama/pull/17188">#17188</a>)</p>
<h2>What's changed</h2> <ul> <li>Added a live elapsed-time counter to the collapsed tool summary line so long-running tool calls visibly tick instead of looking stuck</li> <li>Added a startup warning for <code>Write(path)</code>, <code>NotebookEdit(path)</code>, and <code>Glob(pa…
<h2>What's changed</h2> <ul> <li>Fixed /model and other dialogs being blocked in <code>claude agents</code> background sessions (reverts an overly broad guard)</li> </ul>
<h2>What's Changed</h2> <ul> <li>New interactive agent experience: running <code>ollama</code> now launches an agent to help you code and delegate work</li> </ul> <div class="snippet-clipboard-content notranslate position-relative overflow-auto"><pre class="notranslate"><code>❯ o…
<h2>What's changed</h2> <ul> <li>Auto mode is now available without <code>CLAUDE_CODE_ENABLE_AUTO_MODE</code> opt-in on Bedrock, Vertex AI, and Foundry; disable via <code>disableAutoMode</code> in settings</li> <li>Fixed the terminal freezing and keystrokes lagging while streamin…
<h2>What's changed</h2> <ul> <li>Added directory path suggestions to <code>/cd</code>, matching <code>/add-dir</code> behavior</li> <li>Added a <code>/doctor</code> check that proposes trimming checked-in <code>CLAUDE.md</code> files by cutting content Claude could derive from th…
<h2>What's changed</h2> <ul> <li>Added an auto mode rule that blocks tampering with session transcript files</li> <li>Fixed <code>--json-schema</code> silently producing unstructured output when the schema was invalid, and schemas using the <code>format</code> keyword being rejec…
<h2>What's changed</h2> <ul> <li>Fixed hook events not streaming during SessionStart hooks in headless sessions, which could cause remote workers to be idle-reaped mid-hook</li> </ul>
<h2>What's changed</h2> <ul> <li>Added a warning when your login is about to expire, so you can re-authenticate before background sessions are interrupted</li> <li>Added a grey ⏸ badge to the footer when in manual permission mode, making the active mode always visible</li> <li>Ad…
<h2>What's changed</h2> <ul> <li>Added a "Dynamic workflow size" setting in <code>/config</code> for controlling how large Claude generally makes dynamic workflows (small/medium/large agent counts) — an advisory guideline, not an enforced cap</li> <li>Added <code>workflow.run_id<…
<h2>What's changed</h2> <ul> <li>Changed <code>AskUserQuestion</code> dialogs to no longer auto-continue by default; opt into an idle timeout via <code>/config</code></li> <li>Changed the "default" permission mode to "Manual" across the CLI, <code>--help</code>, VS Code, and JetB…
<h2>What's changed</h2> <ul> <li>Stacked slash-skill invocations like <code>/skill-a /skill-b do XYZ</code> now load all leading skills (up to 5), not just the first</li> <li>Fixed SSL certificate errors (TLS-inspecting proxies, missing <code>NODE_EXTRA_CA_CERTS</code>, expired c…
<h2>What's changed</h2> <ul> <li>Claude in Chrome is now generally available</li> <li>Added background agent notifications in <code>claude agents</code> — sessions that need input or finish now fire the <code>Notification</code> hook (<code>agent_needs_input</code> / <code>agent_…
<h2>What's changed</h2> <ul> <li>Introducing Claude Sonnet 5: now the default model in Claude Code, with a native 1M-token context window and promotional pricing of $2/$10 per Mtok through August 31. Update to version 2.1.197 for access. <a href="https://www.anthropic.com/news/cl…
<h2>What's changed</h2> <ul> <li>Added support for organization default models — admins set it in the org console; it shows as "Org default" (or "Role default") in <code>/model</code> when you haven't picked one yourself</li> <li>Added readable default names for sessions at start…
<p>launch: check for min version for hermes desktop (<a class="issue-link js-issue-link" href="https://github.com/ollama/ollama/pull/16912">#16912</a>)</p>
<h2>0.113.0 (2026-06-29)</h2> <p>Full Changelog: <a href="https://github.com/anthropics/anthropic-sdk-python/compare/v0.112.0...v0.113.0">v0.112.0...v0.113.0</a></p> <h3>Features</h3> <ul> <li><strong>api:</strong> add support for 20260318 web fetch and support tools (<a href="ht…
<h2>What's changed</h2> <ul> <li>Added <code>autoMode.classifyAllShell</code> setting to route all Bash/PowerShell commands through the auto-mode classifier instead of only arbitrary-code-execution patterns</li> <li>Added auto-mode denial reasons to the transcript, the denial toa…
<h2>What's changed</h2> <ul> <li>Added <code>/rewind</code> support for resuming a conversation from before <code>/clear</code> was run</li> <li>Fixed scroll position jumping to the bottom while reading earlier output during a streaming response</li> <li>Fixed background agents r…
<h2>What's changed</h2> <ul> <li>Added <code>sandbox.credentials</code> setting to block sandboxed commands from reading credential files and secret environment variables</li> <li>Added org-configured model restrictions to the model picker, <code>--model</code>, <code>/model</cod…
<h2>What's changed</h2> <ul> <li>Added <code>claude mcp login <name></code> and <code>claude mcp logout <name></code> to authenticate MCP servers from the CLI without opening the interactive <code>/mcp</code> menu, with <code>--no-browser</code> stdin redirect support…
<h2>What's changed</h2> <ul> <li>The stream-stall hint now reads "Waiting for API response · will retry in …" instead of "No response from API · Retrying in …", and triggers after 20s of silence instead of 10s</li> </ul>
<h2>What's changed</h2> <ul> <li>Added <code>/config key=value</code> syntax to set any setting from the prompt (e.g. <code>/config thinking=false</code>) — works in interactive, <code>-p</code>, and Remote Control</li> <li>Added <code>sandbox.allowAppleEvents</code> opt-in setti…
<h2>What's changed</h2> <ul> <li>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"</li> <li>Fixed mouse-wheel scrolling in WSL2 under Windows Terminal and VS Code (regressi…
<h2>What's changed</h2> <ul> <li>Added <code>Tool(param:value)</code> syntax for permission rules to match a tool's input parameters (with <code>*</code> wildcard), e.g. <code>Agent(model:opus)</code> to block Opus subagents</li> <li>Skills in nested <code>.claude/skills</code> d…
<h2>What's changed</h2> <ul> <li>Session titles are now generated in the language of your conversation (set the <code>language</code> setting to pin a specific language)</li> <li>Added <code>footerLinksRegexes</code> setting for regex-matched link badges in the footer row, config…
<h2>What's changed</h2> <ul> <li>Added <code>enforceAvailableModels</code> managed setting — when enabled, the <code>availableModels</code> allowlist also constrains the Default model (a Default that would resolve to a disallowed model now falls back to the first allowed model), …
<h2>What's changed</h2> <ul> <li>Added <code>wheelScrollAccelerationEnabled</code> setting to disable mouse-wheel scroll acceleration in fullscreen mode</li> <li>Fixed the <code>/model</code> picker hiding the model family that Default resolves to — Opus now appears as its own ro…
<h2>What's changed</h2> <ul> <li>Fixed Fable 5 model names with a <code>[1m]</code> suffix not being normalized — Fable 5 includes 1M context by default, so the suffix is now stripped automatically</li> <li>Fixed a spurious "sandbox dependencies missing" startup warning on Window…
<h2>What's changed</h2> <ul> <li>Sub-agents can now spawn their own sub-agents (up to 5 levels deep)</li> <li>Amazon Bedrock now reads the AWS region from <code>~/.aws</code> config files when <code>AWS_REGION</code> isn't set, matching AWS SDK precedence; <code>/status</code> sh…
<h2>What's changed</h2> <ul> <li>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. <a href="https://www.anthropic.com/new…
<h2>0.108.0 (2026-06-09)</h2> <p>Full Changelog: <a href="https://github.com/anthropics/anthropic-sdk-python/compare/v0.107.1...v0.108.0">v0.107.1...v0.108.0</a></p> <h3>Features</h3> <ul> <li><strong>api:</strong> add support for claude-mythos-5 and claude-fable-5, with support …
<h2>What's changed</h2> <ul> <li>Added <code>--safe-mode</code> flag (and <code>CLAUDE_CODE_SAFE_MODE</code>) to start Claude Code with all customizations (CLAUDE.md, plugins, skills, hooks, MCP servers) disabled for troubleshooting</li> <li>Added <code>/cd</code> command to move…
<p>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.</p> <div class="snippet-clipboard-content notranslate position…
<h2>What's changed</h2> <ul> <li>Added <code>fallbackModel</code> setting to configure up to three fallback models tried in order when the primary model is overloaded or unavailable; <code>--fallback-model</code> now also applies to interactive sessions</li> <li>Added glob patter…
<h2>0.106.0 (2026-06-05)</h2> <p>Full Changelog: <a href="https://github.com/anthropics/anthropic-sdk-python/compare/v0.105.2...v0.106.0">v0.105.2...v0.106.0</a></p> <h3>Features</h3> <ul> <li><strong>api:</strong> mark Claude Opus 4.1 as deprecated (<a href="https://github.com/a…
<h2>What's changed</h2> <ul> <li>Added <code>requiredMinimumVersion</code> and <code>requiredMaximumVersion</code> managed settings — Claude Code refuses to start if its version is outside the allowed range and directs the user to an approved version</li> <li>Added <code>/plugin …
<h2>What's changed</h2> <ul> <li><code>claude agents --json</code> now includes <code>waitingFor</code> showing what a waiting session is blocked on (e.g. permission prompt)</li> <li><code>--tools</code>: explicitly listing Grep/Glob now provides the dedicated search tools on nat…
<h2>What's Changed</h2> <ul> <li>models: add support for gemma4-12b by <a class="user-mention notranslate" href="https://github.com/pdevine">@pdevine</a> in <a class="issue-link js-issue-link" href="https://github.com/ollama/ollama/pull/16457">#16457</a></li> </ul> <p><strong>Ful…
<h2>What's changed</h2> <ul> <li><code>OTEL_RESOURCE_ATTRIBUTES</code> values are now included as labels on metric datapoints, so you can slice usage metrics by custom dimensions like team or repo</li> <li><code>claude agents</code> rows now show <code>done/total</code> before th…
<h2>What's changed</h2> <ul> <li>Added a prompt before writing to shell startup files (<code>.zshenv</code>, <code>.zlogin</code>, <code>.bash_login</code>) and <code>~/.config/git/</code>, which could otherwise lead to unintended command execution</li> <li><code>acceptEdits</cod…
<h2>What's changed</h2> <ul> <li>Auto mode is now available on Bedrock, Vertex, and Foundry for Opus 4.7 and Opus 4.8. Opt in by setting <code>CLAUDE_CODE_ENABLE_AUTO_MODE=1</code></li> </ul>
<h2>What's changed</h2> <ul> <li>Plugins in <code>.claude/skills</code> directories are now automatically loaded, no marketplace required</li> <li>Added <code>claude plugin init <name></code> to scaffold a new plugin in <code>.claude/skills</code></li> <li>Added autocomplet…
<h2>What's changed</h2> <ul> <li>Opus 4.8 is here! Now defaults to high effort · /effort xhigh for your hardest tasks</li> <li>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 t…
<h2>What's changed</h2> <ul> <li>Added <code>skipLfs</code> option to <code>github</code>/<code>git</code> plugin marketplace sources to skip Git LFS downloads during clone and update</li> <li>Claude Code now shows a one-time notice when your npm global install can't auto-update;…
<p>This version of Ollama will change the architecture to directly support llama.cpp instead of building on top of GGML, and allows for compatibility with GGUF file format. MLX is used to accelerate model inference on Apple Silicon.</p> <p>While in pre-release we'd love <a href="…
<p>This version of Ollama will change the architecture to directly support llama.cpp instead of building on top of GGML, and allows for compatibility with GGUF file format. MLX is used to accelerate model inference on Apple Silicon.</p> <p>While in pre-release we'd love <a href="…
<h2>What's changed</h2> <ul> <li><code>/code-review --fix</code> now applies review findings to your working tree after the review, surfacing reuse, simplification, and efficiency suggestions; <code>/simplify</code> now invokes <code>/code-review --fix</code></li> <li>Skills and …
<h2>What's changed</h2> <ul> <li><code>/usage</code> now shows a per-category breakdown of what's driving your limits usage — skills, subagents, plugins, and per-MCP-server cost</li> <li><code>/diff</code> detail view can now be scrolled with the keyboard (arrows, <code>j</code>/…
<p>This version of Ollama will change the architecture to directly support llama.cpp instead of building on top of GGML, and allows for compatibility with GGUF file format. MLX is used to accelerate model inference on Apple Silicon.</p> <p>While in pre-release we'd love <a href="…
<h2>What's changed</h2> <ul> <li>Fixed the Bash tool returning exit code 127 on every command for some users (a regression introduced in 2.1.147)</li> </ul>
<h2>What's changed</h2> <ul> <li>Added the <code>Workflow</code> tool for deterministic multi-agent orchestration. It is off by default — set <code>CLAUDE_CODE_WORKFLOWS=1</code> to enable</li> <li>Pinned background sessions (<code>Ctrl+T</code> in <code>claude agents</code>) now…
<h2>What's changed</h2> <ul> <li>Renamed <code>/simplify</code> to <code>/code-review</code> with an optional effort level (e.g. <code>/code-review high</code>)</li> <li>Auto mode no longer suppresses <code>AskUserQuestion</code> when the user or a skill explicitly relies on it</…
<h2>What's changed</h2> <ul> <li>Added <code>claude agents --json</code> to list live Claude sessions as JSON for scripting (tmux-resurrect, status bars, session pickers)</li> <li>Added <code>agent_id</code> and <code>parent_agent_id</code> attributes to <code>claude_code.tool</c…
<h2>What's changed</h2> <ul> <li>Added <code>/resume</code> support for background sessions — sessions started via <code>claude --bg</code> or agent view now appear alongside interactive ones, marked with <code>bg</code></li> <li>Added elapsed duration to background subagent comp…
<h2>What's changed</h2> <ul> <li>Added plugin dependency enforcement: <code>claude plugin disable</code> now refuses when another enabled plugin depends on the target (with a copy-pasteable disable-chain hint), and <code>claude plugin enable</code> force-enables transitive depend…
<h2>What's changed</h2> <ul> <li>Added <code>terminalSequence</code> field to hook JSON output so hooks can emit desktop notifications, window titles, and bells without a controlling terminal</li> <li>Added <code>CLAUDE_CODE_PLUGIN_PREFER_HTTPS</code> to clone GitHub plugin sourc…
<h2>What's changed</h2> <ul> <li>Added agent view (Research Preview): a single list of every Claude Code session — running, blocked on you, or done. Run <code>claude agents</code> to get started. See <a href="https://code.claude.com/docs/en/agent-view" rel="nofollow">https://code…
<h2>What's changed</h2> <ul> <li>Added <code>CLAUDE_CODE_ENABLE_FEEDBACK_SURVEY_FOR_OTEL</code> to re-enable the session quality survey for enterprises capturing responses through OpenTelemetry</li> <li>Added <code>settings.autoMode.hard_deny</code> for auto mode classifier rules…
<h2>What's changed</h2> <ul> <li>Added <code>worktree.baseRef</code> setting (<code>fresh</code> | <code>head</code>) to choose whether <code>--worktree</code>, <code>EnterWorktree</code>, and agent-isolation worktrees branch from <code>origin/<default></code> or local <cod…
<h2>What's changed</h2> <ul> <li>Added <code>CLAUDE_CODE_SESSION_ID</code> environment variable to the Bash tool subprocess environment, matching the <code>session_id</code> passed to hooks</li> <li>Added <code>CLAUDE_CODE_DISABLE_ALTERNATE_SCREEN=1</code> env var to opt out of t…
<h2>What's changed</h2> <ul> <li>Fixed VS Code extension failing to activate on Windows due to a hardcoded build path in the bundled SDK (<code>createRequire</code> polyfill bug)</li> <li>Fixed Mantle endpoint authentication failing with missing <code>x-api-key</code> header</li>…
<h2>What's changed</h2> <ul> <li>Added <code>--plugin-url <url></code> flag to fetch a plugin <code>.zip</code> archive from a URL for the current session</li> <li>Added <code>CLAUDE_CODE_FORCE_SYNC_OUTPUT=1</code> env var to force-enable synchronized output on terminals th…
<h2>What's changed</h2> <ul> <li>Bare <code>/color</code> (no args) now picks a random session color</li> <li><code>/mcp</code> now shows the tool count for connected servers and flags servers that connected with 0 tools</li> <li><code>--plugin-dir</code> now accepts <code>.zip</…
<h2>What's changed</h2> <ul> <li>The <code>/model</code> picker now lists models from your gateway's <code>/v1/models</code> endpoint when <code>ANTHROPIC_BASE_URL</code> points at an Anthropic-compatible gateway</li> <li> <ul> <li>Added <code>claude project purge [path]</code> t…
<h2>What's changed</h2> <ul> <li>Fixed OAuth authentication failing with a 401 retry loop when <code>CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1</code> is set</li> </ul>
<h2>What's changed</h2> <ul> <li>Added <code>ANTHROPIC_BEDROCK_SERVICE_TIER</code> environment variable to select a Bedrock service tier (<code>default</code>, <code>flex</code>, or <code>priority</code>), sent as the <code>X-Amzn-Bedrock-Service-Tier</code> header</li> <li>Pasti…
<h2>What's changed</h2> <ul> <li>Added <code>alwaysLoad</code> option to MCP server config — when <code>true</code>, all tools from that server skip tool-search deferral and are always available</li> <li>Added <code>claude plugin prune</code> to remove orphaned auto-installed plu…
<h2>What's changed</h2> <ul> <li><code>/config</code> settings (theme, editor mode, verbose, etc.) now persist to <code>~/.claude/settings.json</code> and participate in project/local/policy override precedence</li> <li>Added <code>prUrlTemplate</code> setting to point the footer…
<h2>What's changed</h2> <ul> <li>Added vim visual mode (<code>v</code>) and visual-line mode (<code>V</code>) with selection, operators, and visual feedback</li> <li>Merged <code>/cost</code> and <code>/stats</code> into <code>/usage</code> — both remain as typing shortcuts that …
<h2>What's changed</h2> <ul> <li>Forked subagents can now be enabled on external builds by setting <code>CLAUDE_CODE_FORK_SUBAGENT=1</code></li> <li>Agent frontmatter <code>mcpServers</code> are now loaded for main-thread agent sessions via <code>--agent</code></li> <li>Improved …
<h2>What's changed</h2> <ul> <li><code>/resume</code> on large sessions is significantly faster (up to 67% on 40MB+ sessions) and handles sessions with many dead-fork entries more efficiently</li> <li>Faster MCP startup when multiple stdio servers are configured; <code>resources/…
<h2>0.95.0 (2026-04-14)</h2> <p>Full Changelog: <a href="https://github.com/anthropics/anthropic-sdk-python/compare/v0.94.1...v0.95.0">v0.94.1...v0.95.0</a></p> <h3>Features</h3> <ul> <li><strong>api:</strong> mark Sonnet and Opus 4 as deprecated (<a href="https://github.com/anth…
<h3>New Features</h3> <ul> <li><strong>MCP 2.x support for in-process SDK MCP servers</strong>: The SDK now supports <code>mcp</code> 2.x alongside 1.x (dependency widened to <code>mcp>=1.23.0,<3.0.0</code>). In-process servers are served over mcp's own in-memory transport …
Claude Agent SDK (Python) — Releases
TIER_1(SK)·github-actions[bot]·
<h3>New Features</h3> <ul> <li><strong><code>ConversationResetMessage</code> for conversation reset events</strong>: The SDK now surfaces the CLI's <code>conversation_reset</code> frame as a <code>ConversationResetMessage</code> dataclass, letting applications detect when a <code…
Claude Agent SDK (Python) — Releases
TIER_1(SK)·github-actions[bot]·
<h3>Breaking Changes</h3> <ul> <li><strong>Skill name validation in <code>ClaudeAgentOptions.skills</code></strong>: Skill names containing parentheses, commas, control characters, wildcards (<code>*</code>, <code>:*</code>), leading <code>/</code>, surrounding whitespace, or sur…
Claude Agent SDK (Python) — Releases
TIER_1(SK)·github-actions[bot]·
<h3>Bug Fixes</h3> <ul> <li><strong>Fixed premature stdin closure when background tasks are in flight</strong>: <code>query()</code> no longer closes stdin on the first <code>result</code> frame when background tasks (e.g. <code>run_in_background: true</code> subagents) are still…
Claude Agent SDK (Python) — Releases
TIER_1(SK)·github-actions[bot]·
<h3>Bug Fixes</h3> <ul> <li><strong>Fixed argv flag injection via <code>resume</code> and <code>session_id</code> options</strong>: <code>--resume</code> and <code>--session-id</code> are now passed as single <code>=</code>-joined argv tokens (e.g. <code>--resume=<value></c…
Claude Agent SDK (Python) — Releases
TIER_1(SK)·github-actions[bot]·
<h3>Internal/Other Changes</h3> <ul> <li>Updated bundled Claude CLI to version 2.1.207</li> <li>Fixed CI workspace trust so Claude Code honors project-scoped permission grants in checkout directories (<a class="issue-link js-issue-link" href="https://github.com/anthropics/claude-…
Claude Agent SDK (Python) — Releases
TIER_1(SK)·github-actions[bot]·
<h3>Internal/Other Changes</h3> <ul> <li>Switched test suite from <code>pytest-asyncio</code> to anyio's pytest plugin, running every async test under both asyncio and trio backends to catch backend-specific regressions in CI (<a class="issue-link js-issue-link" href="https://git…
Claude Agent SDK (Python) — Releases
TIER_1(SK)·github-actions[bot]·
<h3>Internal/Other Changes</h3> <ul> <li>Updated bundled Claude CLI to version 2.1.150</li> <li>Switched CI workflows from static API key to Workload Identity Federation for Claude authentication, using short-lived tokens instead of long-lived secrets (<a class="issue-link js-iss…
Claude Agent SDK (Python) — Releases
TIER_1(SK)·github-actions[bot]·
<h3>Breaking</h3> <ul> <li><strong>Breaking:</strong> MCP servers now connect in the background by default; sessions start immediately and slow servers report <code>status: "pending"</code> in <code>init</code> until ready. Set <code>MCP_CONNECTION_NONBLOCKING=0</code> to restore…
Claude Agent SDK (Python) — Releases
TIER_1(SK)·github-actions[bot]·
<h3>Bug Fixes</h3> <ul> <li><strong>Actionable error messages after error results</strong>: Replaced the generic <code>Command failed with exit code 1</code> exception raised after an error result with one carrying the result's actual error text (e.g. "Reached maximum number of t…
Claude Agent SDK (Python) — Releases
TIER_1(SK)·github-actions[bot]·
<h3>New Features</h3> <ul> <li><strong>API error status on result messages</strong>: Added <code>api_error_status: int | None</code> to <code>ResultMessage</code>, surfacing the HTTP status code (e.g. 429, 500, 529) from failing API calls. This provides a safe-to-log field for cl…
Claude Agent SDK (Python) — Releases
TIER_1(SK)·github-actions[bot]·
<h3>New Features</h3> <ul> <li><strong>Hook event streaming</strong>: Added <code>include_hook_events</code> option to <code>ClaudeAgentOptions</code>. When set, hook events (PreToolUse, PostToolUse, Stop, etc.) are emitted by the CLI and yielded from the message stream as <code>…
Claude Agent SDK (Python) — Releases
TIER_1(SK)·github-actions[bot]·
<h3>New Features</h3> <ul> <li><strong>Eager session store flushing</strong>: Added <code>session_store_flush</code> option to <code>ClaudeAgentOptions</code> (<code>"batched"</code> or <code>"eager"</code>). When set to <code>"eager"</code>, the transcript mirror delivers frames…
Claude Agent SDK (Python) — Releases
TIER_1(SK)·github-actions[bot]·
<h3>Documentation</h3> <ul> <li>Added docstrings to <code>ClaudeAgentOptions</code> fields for improved IDE autocompletion and inline documentation (<a class="issue-link js-issue-link" href="https://github.com/anthropics/claude-agent-sdk-python/pull/873">#873</a>)</li> </ul> <h3>…
Claude Agent SDK (Python) — Releases
TIER_1(SK)·github-actions[bot]·
<h3>Bug Fixes</h3> <ul> <li><strong>Trio compatibility restored</strong>: Fixed <code>RuntimeError: no running event loop</code> when using <code>ClaudeSDKClient</code> or <code>query()</code> under trio, a regression introduced in v0.1.51. Uses sniffio-based dispatch to select t…
Claude Agent SDK (Python) — Releases
TIER_1(SK)·github-actions[bot]·
<h3>New Features</h3> <ul> <li><strong>SessionStore adapter</strong>: Full SessionStore support at parity with the TypeScript SDK. Includes a <code>SessionStore</code> protocol with 5 methods (<code>append</code>, <code>load</code>, <code>list_sessions</code>, <code>delete</code>…
<h2>What's Changed</h2> <ul> <li>Fix minimax music not working on non dynamic vram. by <a class="user-mention notranslate" href="https://github.com/comfyanonymous">@comfyanonymous</a> in <a class="issue-link js-issue-link" href="https://github.com/Comfy-Org/ComfyUI/pull/15588">#1…
<p><a href="https://unsloth.ai/" rel="nofollow">Unsloth Desktop</a> is here! The first desktop app to run and train AI models locally. Research, export and deploy from the same open-source app on Windows, macOS and Linux.</p> <h2>v0.1.702-beta Update (August 13th)</h2> <ul> <li>A…
<h2><a href="https://github.com/openai/openai-python/compare/v2.54.0...v3.0.0">3.0.0</a> (2026-08-12)</h2> <h3>⚠ BREAKING CHANGES</h3> <ul> <li><strong>api:</strong> HTTPX2 is now the default HTTP client, and <code>httpx</code> is no longer installed automatically. Applications u…
<h2>What's Changed</h2> <ul> <li>Make it easier to debug nested tensors. by <a class="user-mention notranslate" href="https://github.com/comfyanonymous">@comfyanonymous</a> in <a class="issue-link js-issue-link" href="https://github.com/Comfy-Org/ComfyUI/pull/15383">#15383</a></l…
<h1>Highlights</h1> <p><em>582 PRs from 194 contributors.</em></p> <p><strong>Kimi K3 day-0 support</strong>: A 2.8T-parameter multimodal LatentMoE (896 experts, top-16, routed in a 3584-dim latent space) with a 1M-token context, 69 KDA linear-attention layers interleaved with 24…
<p>The major change in this version is added support for int8 convrot models.</p> <h2>What's Changed</h2> <ul> <li>chore(openapi): sync shared API contract from cloud@363764b by <a class="user-mention notranslate" href="https://github.com/comfy-pr-bot">@comfy-pr-bot</a> in <a cla…
<h2>What's Changed</h2> <ul> <li>chore(openapi): sync shared API contract from cloud@00ef9cc by <a class="user-mention notranslate" href="https://github.com/comfy-pr-bot">@comfy-pr-bot</a> in <a class="issue-link js-issue-link" href="https://github.com/Comfy-Org/ComfyUI/pull/1442…
<h2>What's Changed</h2> <ul> <li>Add test that each model has unique identifiers (CORE-134) by <a class="user-mention notranslate" href="https://github.com/Talmaj">@Talmaj</a> in <a class="issue-link js-issue-link" href="https://github.com/Comfy-Org/ComfyUI/pull/13654">#13654</a>…
<h2>What's Changed</h2> <ul> <li>[Partner Nodes] new Flux2ImageNode and GrokImageEditNodeV2 nodes by <a class="user-mention notranslate" href="https://github.com/bigcat88">@bigcat88</a> in <a class="issue-link js-issue-link" href="https://github.com/Comfy-Org/ComfyUI/pull/13814">…
<h2>What's Changed</h2> <ul> <li>Read audio and video at the same time in video loader node. by <a class="user-mention notranslate" href="https://github.com/comfyanonymous">@comfyanonymous</a> in <a class="issue-link js-issue-link" href="https://github.com/Comfy-Org/ComfyUI/pull/…
<h1>Highlights</h1> <ul> <li> <p><strong>CUDA 13 + Torch 2.11</strong>: Default CUDA version moves to 13.0 across SGLang, sgl-kernel, and Docker images, and PyTorch is upgraded from 2.9 to 2.11 — modernizing the build matrix and unlocking newer kernels: <a class="issue-link js-is…
<h1>vLLM v0.20.1</h1> <p>This is a patch release on top of <code>v0.20.0</code> primarily focused on <strong>DeepSeek V4 stabilization and performance improvements</strong>, along with several important bug fixes.</p> <h3>DeepSeek V4</h3> <ul> <li>Base model support (<a class="is…
<h2>What's Changed</h2> <ul> <li>feat: SUPIR model support (CORE-17) by <a class="user-mention notranslate" href="https://github.com/kijai">@kijai</a> in <a class="issue-link js-issue-link" href="https://github.com/Comfy-Org/ComfyUI/pull/13250">#13250</a></li> <li>Some optimizati…
<p>This is a patch release on top of <code>v0.19.0</code> with Transformers v5.5.3 upgrade and bug fixes for Gemma4:</p> <ul> <li>Update to transformers v5 (<a class="issue-link js-issue-link" href="https://github.com/vllm-project/vllm/pull/30566">#30566</a>)</li> <li>[Bugfix] Fi…
<p><strong>Full Changelog</strong>: <a class="commit-link" href="https://github.com/sgl-project/sglang/compare/v0.5.10...v0.5.10.post1"><tt>v0.5.10...v0.5.10.post1</tt></a></p> <p>Bumps flashinfer from v0.6.7.post2 to v0.6.7.post3 to resolve an issue in its jit cubin downloader.<…
<h1>Highlights</h1> <ul> <li> <p><strong>Piecewise CUDA Graph Enabled by Default</strong>: Piecewise CUDA graph capture is now the default execution mode, reducing memory overhead and improving throughput for models with complex control flow patterns: <a class="issue-link js-issu…
<h1>vLLM v0.19.0</h1> <h2>Highlights</h2> <p>This release features 448 commits from 197 contributors (54 new)!</p> <ul> <li><strong>Gemma 4 support</strong>: Full Google Gemma 4 architecture support including MoE, multimodal, reasoning, and tool-use capabilities (<a class="issue-…
<h1>Highlights</h1> <ul> <li> <p><strong>Piecewise CUDA Graph Enabled by Default</strong>: Piecewise CUDA graph capture is now the default execution mode, reducing memory overhead and improving throughput for models with complex control flow patterns: <a class="issue-link js-issu…
<h2>2.26.0 (2026-03-05)</h2> <p>Full Changelog: <a href="https://github.com/openai/openai-python/compare/v2.25.0...v2.26.0">v2.25.0...v2.26.0</a></p> <h3>Features</h3> <ul> <li><strong>api:</strong> The GA ComputerTool now uses the CompuerTool class. The 'computer_use_preview' to…
<h1>Highlights</h1> <ul> <li> <p><strong>LoRA Weight Loading Overlap with Computation</strong>: Overlap LoRA weight loading with computation during inference, reducing TTFT by ~78% and TPOT by ~34.88% on large adaptors: <a class="issue-link js-issue-link" href="https://github.com…
<h1>Highlights</h1> <ul> <li>Up to 1.5x faster across the board for all major diffusion models <a href="https://lmsys.org/blog/2026-01-16-sglang-diffusion/" rel="nofollow">https://lmsys.org/blog/2026-01-16-sglang-diffusion/</a></li> <li>Close to linear scaling with chunked pipeli…
dev.to — Claude Code tag
TIER_1Deutsch(DE)·JessYT·
<h1> Claude Code unlocked background again — Fast mode is now 4.7 </h1> <p>Bottom line first. <strong>Claude Code's Fast mode default auto-switched to Opus 4.7.</strong> The same changelog batch also shipped 8 new <code>claude agents</code> CLI flags, an option to turn off worktr…
<h2> Introduction </h2> <p>Everyone knows that the MAX plan lets you "use more."</p> <p>That's not what I want to know. <strong>What actually changes with MAX?</strong> When I looked into it, I found that some features often assumed to be "MAX-exclusive" were not, while other dif…
dev.to — Claude Code tag
TIER_1English(EN)·Jula Markova·
<p>I spent a session with Claude Code (Opus 4.7) doing something odd. Instead of giving it tasks, I asked it to reflect on its own thinking. Not what it knows. How it <em>operates</em>.</p> <p>What came back was specific enough to be useful. </p> <p>One conversation = One experim…
dev.to — Claude Code tag
TIER_1English(EN)·Alaric·
<p>I've been using Claude Code daily for the past few months. The output quality is great, but the API bill at the end of the month was painful. After some experimentation, I found a few habits that consistently cut my token consumption by 25–35% without sacrificing code quality.…
dev.to — Claude Code tag
TIER_1Nederlands(NL)·speedy_devv·
<p>Your Claude Code bill went up twice in 30 days. You felt it on the invoice before you understood why.</p> <p>On June 15, 2026, Anthropic moves Agent SDK, <code>claude -p</code>, and Claude Code GitHub Actions onto a separate metered credit pool that does not roll over. Once th…
Medium — Claude tag
TIER_1English(EN)·Bhavin Mecwan·
<h1> Claude's "Go to Sleep" Bug Explained: Why It Happens and How to Keep Coding </h1> <p><strong>TL;DR:</strong> Claude has been telling developers to "get some rest" mid-coding session, even at 9 a.m., and the behaviour has been growing for months. Anthropic staffer Sam McAllis…
<p>I tested cheap vs expensive LLMs across 3 real agent tasks. The cheap model won every time.<br /> Everyone tells you to use the best model you can afford. I built a toolkit to test that assumption with data, and the results surprised me.<br /> Over the past few weeks, I built …
<!-- SC_OFF --><div class="md"><p>Backstory: when the "Build with Opus 4.7" hackathon was announced, I had the thesis but not the project. I was obsessing over the tokenomics of agents; how to make your tokens go further, and shared that angle in the application even wi…
