product hub
Claude Code
Anthropic coding-agent product for terminal and software-development workflows.
Names and model IDs
Source-linked relationships
Timeline
124 published changes
DeepSeek-V4.1-Flash-1017 Update
DeepSeek-V4.1-Flash-1017 Update DeepSeek V4.1 Flash has been upgraded to DeepSeek-V4.1-Flash-1017. The official web and APP models have also been updated to the new version. The API calling method and pricing remain unchanged — simply use deepseek-flash to access the latest model. Performance–cost Pareto improvement Compared with the previous DeepSeek V4.1, the new model delivers substantial improvements across benchmarks: HLE (w/o tools): 42.6 (44.0*) Terminal-Bench 4.0: 42.3 DeepSWE v1.1: 77.0 ProgramBench: 29.1 NL2Repo-Bench: 68.2 Automation-Bench v1.0.6: 60.5 Agents' Last Exam: 35.4 Apex Bench v1.1: 72.1 Chartography (w/tools): 83.0 BabyVision (w/tools): 92.5 ZeroBench-main (w/tools): 51.0 * Tested only on the pure-text subset of the HLE benchmark set. Terminal-Bench 4.0 was tested with the Claude Code framework, and DeepSWE with the Mini-SWE-V2 framework. ZeroBench-main was evaluated with Pass@5. While improving performance, we also reduced the model's task runtime and output length, enabling users to complete tasks at lower cost and higher speed and achieving a new performance–cost Pareto optimum across multiple harnesses. We specifically optimized for DeepSeek Harness, Ten
v2.1.330
## What's changed - Added sign-in to organizations managed in Anthropic's Enterprise Admin Console: after `claude auth login`, Claude Code applies the organization's settings and uses its cloud provider or gateway - Added easel, a built-in mod that draws charts when asked and under MCP metrics results, on Pro, Max and, where available, Team and Enterprise on macOS and Linux; turn automatic charts off in `/config` - Added `CLAUDE_CODE_FULL_SIGN_IN_LINK=1` to print the full sign-in link, if the short one shows an error or a script reads values from it - Self-hosted runner: Added `--start-dir` / `SELF_HOSTED_RUNNER_START_DIR` to have Claude start its work in a folder of a repository, while settings and hooks load as without it - Added a notice in cloud and self-hosted runner sessions when a plugin marketplace can't be fetched because its repository isn't one of the session's - Self-hosted runner: Added a notice when Anthropic-managed git refuses a plugin's own repository, naming the plugin and what to do - Added `commandPrinted` to `claude plugin install --json` results, true when the plugin's install command wrote to stderr, and `commandFailed` when it exited with an error, was kille
DeepSeek-V4.1-Flash-1017 Update
DeepSeek-V4.1-Flash-1017 Update DeepSeek V4.1 Flash has been upgraded to DeepSeek-V4.1-Flash-1017. The official web and APP models have also been updated to the new version. The API calling method and pricing remain unchanged — simply use deepseek-flash to access the latest model. Performance–cost Pareto improvement Compared with the previous DeepSeek V4.1, the new model delivers substantial improvements across benchmarks: HLE (w/o tools): 42.6 (44.0*) Terminal-Bench 4.0: 42.3 DeepSWE v1.1: 77.0 ProgramBench: 29.1 NL2Repo-Bench: 68.2 Automation-Bench v1.0.6: 60.5 Agents' Last Exam: 35.4 Apex Bench v1.1: 72.1 Chartography (w/tools): 83.0 BabyVision (w/tools): 92.5 ZeroBench-main (w/tools): 51.0 * Tested only on the pure-text subset of the HLE benchmark set. Terminal-Bench 4.0 was tested with the Claude Code framework, and DeepSWE with the Mini-SWE-V2 framework. ZeroBench-main was evaluated with Pass@5. While improving performance, we also reduced the model's task runtime and output length, enabling users to complete tasks at lower cost and higher speed and achieving a new performance–cost Pareto optimum across multiple harnesses. We specifically optimized for DeepSeek Harness, Ten
v2.1.329
## What's changed - Added a trust dialog warning that says where a folder's hooks are declared - Added a warning in the conversation, in Claude Desktop and other non-interactive hosts, when hooks in managed settings fail to load - Added this session's scheduled tasks, `/loop` wakeups, the goal and this conversation's forks to `/tasks`; x stops one after asking - Added a "Server message" row to a server's page in `/mcp` that shows the JSON-RPC error message of a remote HTTP MCP server that refuses the connection - Added a "Marketplace auto-update" row to `/status` that names managed marketplaces that get no automatic updates, and why - Added support for turning on Code Mode while OpenTelemetry events and metrics are enabled; each tool call the code makes sends its events; tracing still keeps it off - Fixed `~/.claude.json` sometimes being reset to defaults when a network stall or file lock made it unreadable and cleared during a save - Fixed repeated sign-outs on macOS when Claude Code could read the Keychain but not save to it. That session now stops at expiry and says why, and other sessions stay signed in - Fixed `/terminal-setup` corrupting VS Code settings or keybindings files
Show HN: Zpup – Zdog style 3D scenes in JSON, SVG from any angle
Hi. I made small project called Zpup. It takes small 3D scene written in JSON and gives back a flat SVG from any angle. There is no JavaScript in the file, so it works in img-tag or README. I needed 3D for small project at my company, and Zdog make big impression on me. But Zdog has not had a release for several years, so I wanted to make modern version. One thing works different. Zdog sorts each shape by one point. so small thing on big floor gets covered when you turn it. Zpup compares the shapes that overlap. You can see both in the README. I wrote it with Claude Code Fable 5.2. No canvas renderer, no text shape, and it is 0.2 version. Playground: https://rxolve.github.io/zpup Feedback is always welcome :)
v2.1.328
## What's changed - Added auto mode for Claude Opus 4.6 and Sonnet 4.6 on Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry and Claude apps gateway; interactive sessions with no permission mode start in it - Added `"onFailure": "block"` for `mcp_tool` hooks, as for command and HTTP hooks: a hook whose call fails blocks the action - Added a warning when a message from a session that skips permission prompts may be held and dropped by a cloud session - Added a notice in `/status` and `claude doctor` when an OpenTelemetry exporter has no endpoint and its data would likely be lost - Added `CLAUDE_CODE_DISABLE_DEFERRED_TOOL_RESUME`, which lets a host stop `claude -p --resume` and `--continue` from running a tool call that a hook deferred - Added support for apps that embed Claude Code to switch on the policy plugin's `allowManagedModsOnly` option; an admin's managed settings still win - Added a startup warning to the Claude apps gateway when a policy's `maxEffortLevel` is not a valid effort level - Self-hosted runner: Added `--repository-folder` to name the folder that sessions use for a repository at `--capacity 1`, in place of its path under the base folder, which can't
Show HN: Robotics needs better CAD, so I wrote a B-rep kernel and 3,487 tests
Hey HN, I’m Tony. I’m a co-founder of Springcraft, where we have been doing a lot of CAD modeling for robot parts. Our team kept running into limitations with existing kernels, and so I decided to write a new B-rep kernel and a new comprehensive, kernel-agnostic B-rep conformance test suite. Both are available today under MIT licenses. The kernel, springrep, is written in safe Rust with no dependencies. It covers a broad range of our mechanical CAD needs, including advanced fillets, sweeps, lofts, shells, offsets, STEP and exact measurements and queries. Claude Code made it feasible to write this, but it took a lot of time and care to get it right. The test suite, brep-conformance, has 3,487 cases covering the modeling operations common across kernels: booleans, fillets, chamfers, shells, offsets, sweeps, lofts, STEP, and queries with expected answers coming from closed forms and exact geometry. It caught hundreds of bugs, edge cases, and hot spots in springrep that our own tests had missed, and now springrep passes all of it. We’ve also run it on a few popular open-source kernels and anyone can run it on theirs. This is the first version, so there are surely mistakes in the test a
DeepSeek-V4.1-Flash-1017 Update
DeepSeek-V4.1-Flash-1017 Update DeepSeek V4.1 Flash has been upgraded to DeepSeek-V4.1-Flash-1017. The official web and APP models have also been updated to the new version. The API calling method and pricing remain unchanged — simply use deepseek-flash to access the latest model. Performance–cost Pareto improvement Compared with the previous DeepSeek V4.1, the new model delivers substantial improvements across benchmarks: HLE (w/o tools): 42.6 (44.0*) Terminal-Bench 4.0: 42.3 DeepSWE v1.1: 77.0 ProgramBench: 29.1 NL2Repo-Bench: 68.2 Automation-Bench v1.0.6: 60.5 Agents' Last Exam: 35.4 Apex Bench v1.1: 72.1 Chartography (w/tools): 83.0 BabyVision (w/tools): 92.5 ZeroBench-main (w/tools): 51.0 * Tested only on the pure-text subset of the HLE benchmark set. Terminal-Bench 4.0 was tested with the Claude Code framework, and DeepSWE with the Mini-SWE-V2 framework. ZeroBench-main was evaluated with Pass@5. While improving performance, we also reduced the model's task runtime and output length, enabling users to complete tasks at lower cost and higher speed and achieving a new performance–cost Pareto optimum across multiple harnesses. We specifically optimized for DeepSeek Harness, Ten
Show HN: Terminess, a harness that runs the official Claude Code and Codex CLIs
TLDR: I built a terminal (harness) for Claude Code and Codex that works the official way, on your own subs. Anthropic stopped Claude subs working in 3P harnesses in Feb, 9 months of suffering later, I decided to build one that plays by their rules, a terminal (harness) that runs Claude Code and Codex (and others), together. (I am not claiming that this is a Deepseek harness killer lol, but it works really well for me) I use a number of agents in tandem, on my laptop and my server. Checking them from my phone took 4+ apps and I was losing hours away from my laptop, and copying context between them ate the rest. Terminess puts it all in one place. It complies with all their terms. Terminess runs the real claude and codex CLIs, unmodified, signed in with your own plans, exactly as your reg mac terminal or iTerm would. It doesn’t read, store or reuse your login tokens, and never proxies your requests, so nothing about it works around Anthropic's or OpenAI's terms (currently). Underneath is its own terminal engine, written from scratch for agent work. - Sessions live on your Mac or your own server, so agents keep going with the lid shut - You can start on your phone and pick it up on yo
v2.1.327
## What's changed - Added a confirmation before `/install-github-app` changes a repository - Added `claude mcp add-json -` to read the server's JSON from stdin, so tokens can stay off the command line; not available inside a Claude Code session - Added a line when a resumed session's earlier messages can't be loaded - Added a list in `/status` of broken agent, skill, command and output style files, keybinding errors, an unavailable sandbox, ignored permission settings and hook matchers that never match - Added a note in `/config` when other settings override a row - Added `x-claude-code-managed-settings-checksum` to the gateway hint headers; sent where managed settings set `CLAUDE_CODE_GATEWAY_HINT_HEADERS=1`, including where they already do - Added support for naming a session's billing group with the `attributionProject` setting, for Claude apps gateways that set `admin.billing_group_tag` - Added `/tui classic` as the name for the non-fullscreen renderer; `/tui default` still works - Remote Control: Fixed stopping the server in worktree mode deleting a running session's git-ignored files, such as `.env` - Fixed self-hosted runners with `--use-anthropic-git-proxy` deleting a non-e
DeepSeek-V4.1-Flash-1017 Update
DeepSeek-V4.1-Flash-1017 Update DeepSeek V4.1 Flash has been upgraded to DeepSeek-V4.1-Flash-1017. The official web and APP models have also been updated to the new version. The API calling method and pricing remain unchanged — simply use deepseek-flash to access the latest model. Performance–cost Pareto improvement Compared with the previous DeepSeek V4.1, the new model delivers substantial improvements across benchmarks: HLE (w/o tools): 42.6 (44.0*) Terminal-Bench 4.0: 42.3 DeepSWE v1.1: 77.0 ProgramBench: 29.1 NL2Repo-Bench: 68.2 Automation-Bench v1.0.6: 60.5 Agents' Last Exam: 35.4 Apex Bench v1.1: 72.1 Chartography (w/tools): 83.0 BabyVision (w/tools): 92.5 ZeroBench-main (w/tools): 51.0 * Tested only on the pure-text subset of the HLE benchmark set. Terminal-Bench 4.0 was tested with the Claude Code framework, and DeepSWE with the Mini-SWE-V2 framework. ZeroBench-main was evaluated with Pass@5. While improving performance, we also reduced the model's task runtime and output length, enabling users to complete tasks at lower cost and higher speed and achieving a new performance–cost Pareto optimum across multiple harnesses. We specifically optimized for DeepSeek Harness, Ten
v2.1.326
## What's changed - Added support for turning on Code Mode while agent teams are enabled; if you already turned it on, sessions with teams on now start in Code Mode - Added a startup warning when an `--allowedTools`, `--disallowedTools` or `--tools` value has an entry that doesn't look like a complete rule - Added a message explaining why MCP servers stop loading when an administrator adds `managed-mcp.json` during a session - Added a row to `/status` that says when your provider or an environment variable such as `DISABLE_TELEMETRY` turns features off - Added a note in `/plugin` and `claude plugin list` when a malformed `plugin.json` field such as `author` or `homepage` is ignored - Added Ctrl+O to show hidden startup notices - Added a hint in the empty prompt that says what to do after a request fails - Added an `esc to stop` footer hint in a subagent's view where Esc would stop it - Added `OTEL_RESOURCE_INCLUDE_HOST` to include `host.name` and `host.id` in OpenTelemetry resource attributes (off by default) - Added `overflowX="scroll"` on a mod's `Box`, and `maxLines` and `wrap="clip"` on its `Text` - Fixed `cp` of a file being refused when only its source was covered by an `Edit
Does Anyone Use Happier.dev?
It seems to provide a way to have a single view of sessions across multiple agents and harnesses - I'm planning to use it so I can use Claude Code and Goose + OpenRouter in one place, and possibly orchestrate activity across the two. Just wondering whether anyone has any experience of it, what your thoughts are, and whether there are alternatives I should be looking at?
DeepSeek-V4.1-Flash-1017 Update
DeepSeek-V4.1-Flash-1017 Update DeepSeek V4.1 Flash has been upgraded to DeepSeek-V4.1-Flash-1017. The official web and APP models have also been updated to the new version. The API calling method and pricing remain unchanged — simply use deepseek-flash to access the latest model. Performance–cost Pareto improvement Compared with the previous DeepSeek V4.1, the new model delivers substantial improvements across benchmarks: HLE (w/o tools): 42.6 (44.0*) Terminal-Bench 4.0: 42.3 DeepSWE v1.1: 77.0 ProgramBench: 29.1 NL2Repo-Bench: 68.2 Automation-Bench v1.0.6: 60.5 Agents' Last Exam: 35.4 Apex Bench v1.1: 72.1 Chartography (w/tools): 83.0 BabyVision (w/tools): 92.5 ZeroBench-main (w/tools): 51.0 * Tested only on the pure-text subset of the HLE benchmark set. Terminal-Bench 4.0 was tested with the Claude Code framework, and DeepSWE with the Mini-SWE-V2 framework. ZeroBench-main was evaluated with Pass@5. While improving performance, we also reduced the model's task runtime and output length, enabling users to complete tasks at lower cost and higher speed and achieving a new performance–cost Pareto optimum across multiple harnesses. We specifically optimized for DeepSeek Harness, Ten
In 1 in 6 repos with both files, Claude Code never loads the AGENTS.md
Source-linked update: In 1 in 6 repos with both files, Claude Code never loads the AGENTS.md
DeepSeek-V4.1-Flash-1017 Update
DeepSeek-V4.1-Flash-1017 Update DeepSeek V4.1 Flash has been upgraded to DeepSeek-V4.1-Flash-1017. The official web and APP models have also been updated to the new version. The API calling method and pricing remain unchanged — simply use deepseek-flash to access the latest model. Performance–cost Pareto improvement Compared with the previous DeepSeek V4.1, the new model delivers substantial improvements across benchmarks: HLE (w/o tools): 42.6 (44.0*) Terminal-Bench 4.0: 42.3 DeepSWE v1.1: 77.0 ProgramBench: 29.1 NL2Repo-Bench: 68.2 Automation-Bench v1.0.6: 60.5 Agents' Last Exam: 35.4 Apex Bench v1.1: 72.1 Chartography (w/tools): 83.0 BabyVision (w/tools): 92.5 ZeroBench-main (w/tools): 51.0 * Tested only on the pure-text subset of the HLE benchmark set. Terminal-Bench 4.0 was tested with the Claude Code framework, and DeepSWE with the Mini-SWE-V2 framework. ZeroBench-main was evaluated with Pass@5. While improving performance, we also reduced the model's task runtime and output length, enabling users to complete tasks at lower cost and higher speed and achieving a new performance–cost Pareto optimum across multiple harnesses. We specifically optimized for DeepSeek Harness, Ten
v2.1.325
## What's changed - Fixed a security issue in how zstd-compressed responses are decoded - Added a spinner tip in VS Code and similar integrated terminals about re-running a notebook cell, shown once Claude has read or edited a Jupyter notebook - Added a line under the error shown when your organization's policy blocks a request, saying how to continue: run `/rewind` and change the message, or run `/clear` - Added a note for Claude when a sandboxed `git checkout`, `git stash` or autostash pull cannot update protected files such as those in `.claude` - Fixed `/security-review` and skills' inline git commands stopping with an error in worktrees of bare repositories, `--separate-git-dir` checkouts and Android `repo` checkouts - Fixed subagents with their own model being moved to the plan-mode model when the model setting is `opusplan` or `haiku` - Fixed subagents on a different model sizing file reads and MCP results with the main session's model - Fixed sessions on many third-party gateways and Foundry stopping with a context length error on every turn instead of compacting - Fixed recent turns sometimes going missing from a resumed session after Claude Code stopped without a clean ex
Show HN: Langfuse AI Gateway, open source rust gateway to trace every LLM call
Hi HN, this is Max, Marc and Clemens, co-founders of Langfuse, the open source tool for agent & observability & evals ( https://github.com/langfuse/langfuse ). It’s been a minute since our last Show HN in August 2023 ( https://news.ycombinator.com/item?id=37310070 ) - we’ve been busy building out and serving our tracing & eval pieces over the past years and have been very lucky to build a successful company and open source project around it. Today, we are happy to show the beta of Langfuse AI Gateway: https://github.com/langfuse/langfuse/tree/main/ai-gateway . You may ask, why an AI Gateway as our second product: it’s been one our community’s strongest asks + integration pattern that we’ve seen. We want to offer a scalable, reliable and secure way to solve for the gateway use case in the same way that we’ve done with tracing/evals over the past years. And we’ve recently grown our team with some excellent folks - expect to see more bigger bets from us. Our observability SDKs currently see the code you instrument. Much of a company's model traffic runs through code that is not or cannot be easily instrumented: coding agents like Pi, Claude Code and Codex, internal tools, scripts etc.
DeepSeek-V4.1-Flash-1017 Update
DeepSeek-V4.1-Flash-1017 Update DeepSeek V4.1 Flash has been upgraded to DeepSeek-V4.1-Flash-1017. The official web and APP models have also been updated to the new version. The API calling method and pricing remain unchanged — simply use deepseek-flash to access the latest model. Performance–cost Pareto improvement Compared with the previous DeepSeek V4.1, the new model delivers substantial improvements across benchmarks: HLE (w/o tools): 42.6 (44.0*) Terminal-Bench 4.0: 42.3 DeepSWE v1.1: 77.0 ProgramBench: 29.1 NL2Repo-Bench: 68.2 Automation-Bench v1.0.6: 60.5 Agents' Last Exam: 35.4 Apex Bench v1.1: 72.1 Chartography (w/tools): 83.0 BabyVision (w/tools): 92.5 ZeroBench-main (w/tools): 51.0 * Tested only on the pure-text subset of the HLE benchmark set. Terminal-Bench 4.0 was tested with the Claude Code framework, and DeepSWE with the Mini-SWE-V2 framework. ZeroBench-main was evaluated with Pass@5. While improving performance, we also reduced the model's task runtime and output length, enabling users to complete tasks at lower cost and higher speed and achieving a new performance–cost Pareto optimum across multiple harnesses. We specifically optimized for DeepSeek Harness, Ten
DeepSeek-V4.1-Flash-1017 Update
DeepSeek-V4.1-Flash-1017 Update DeepSeek V4.1 Flash has been upgraded to DeepSeek-V4.1-Flash-1017. The official web and APP models have also been updated to the new version. The API calling method and pricing remain unchanged — simply use deepseek-flash to access the latest model. Performance–cost Pareto improvement Compared with the previous DeepSeek V4.1, the new model delivers substantial improvements across benchmarks: HLE (w/o tools): 42.6 (44.0*) Terminal-Bench 4.0: 42.3 DeepSWE v1.1: 77.0 ProgramBench: 29.1 NL2Repo-Bench: 68.2 Automation-Bench v1.0.6: 60.5 Agents' Last Exam: 35.4 Apex Bench v1.1: 72.1 Chartography (w/tools): 83.0 BabyVision (w/tools): 92.5 ZeroBench-main (w/tools): 51.0 * Tested only on the pure-text subset of the HLE benchmark set. Terminal-Bench 4.0 was tested with the Claude Code framework, and DeepSWE with the Mini-SWE-V2 framework. ZeroBench-main was evaluated with Pass@5. While improving performance, we also reduced the model's task runtime and output length, enabling users to complete tasks at lower cost and higher speed and achieving a new performance–cost Pareto optimum across multiple harnesses. We specifically optimized for DeepSeek Harness, Ten
v2.1.321
## What's changed - Added Claude Fable 5.2 (`claude-fable-5-2`), now the default Fable model — 1M context, $8/$40 per Mtok with $0.20/Mtok cache reads - Added `--settings ` to `claude remote-control`, which applies a settings file to every session it starts; if the file changes, no new session starts until you restart `claude remote-control` - Fixed MCP OAuth requests sending secrets such as refresh tokens to another host when a server redirected them - Fixed a case where a read-only Bash command ran outside the sandbox without a permission prompt - Fixed a case where Bash permission checks judged a file write from the wrong folder and didn't prompt - Fixed deny rules and protected-file prompts not applying to the file that a `cp` or `mv` into a directory writes - Fixed the "Draws from usage credits" note showing after a switch to Fable on Enterprise seats whose plan includes Fable - Fixed the fallback model sometimes declining a request or mentioning a stopped response when the first model was blocked before replying - Fixed `claude mcp login` printing a SEP-2352 issuer warning each time you sign in again to a server that Claude Code registered with - Fixed `NotebookEdit` deleting
DeepSeek-V4.1-Flash-1017 Update
DeepSeek-V4.1-Flash-1017 Update DeepSeek V4.1 Flash has been upgraded to DeepSeek-V4.1-Flash-1017. The official web and APP models have also been updated to the new version. The API calling method and pricing remain unchanged — simply use deepseek-flash to access the latest model. Performance–cost Pareto improvement Compared with the previous DeepSeek V4.1, the new model delivers substantial improvements across benchmarks: HLE (w/o tools): 42.6 (44.0*) Terminal-Bench 4.0: 42.3 DeepSWE v1.1: 77.0 ProgramBench: 29.1 NL2Repo-Bench: 68.2 Automation-Bench v1.0.6: 60.5 Agents' Last Exam: 35.4 Apex Bench v1.1: 72.1 Chartography (w/tools): 83.0 BabyVision (w/tools): 92.5 ZeroBench-main (w/tools): 51.0 * Tested only on the pure-text subset of the HLE benchmark set. Terminal-Bench 4.0 was tested with the Claude Code framework, and DeepSWE with the Mini-SWE-V2 framework. ZeroBench-main was evaluated with Pass@5. While improving performance, we also reduced the model's task runtime and output length, enabling users to complete tasks at lower cost and higher speed and achieving a new performance–cost Pareto optimum across multiple harnesses. We specifically optimized for DeepSeek Harness, Ten
DeepSeek-V4.1-Flash-1017 Update
DeepSeek-V4.1-Flash-1017 Update DeepSeek V4.1 Flash has been upgraded to DeepSeek-V4.1-Flash-1017. The official web and APP models have also been updated to the new version. The API calling method and pricing remain unchanged — simply use deepseek-flash to access the latest model. Performance–cost Pareto improvement Compared with the previous DeepSeek V4.1, the new model delivers substantial improvements across benchmarks: HLE (w/o tools): 42.6 (44.0*) Terminal-Bench 4.0: 42.3 DeepSWE v1.1: 77.0 ProgramBench: 29.1 NL2Repo-Bench: 68.2 Automation-Bench v1.0.6: 60.5 Agents' Last Exam: 35.4 Apex Bench v1.1: 72.1 Chartography (w/tools): 83.0 BabyVision (w/tools): 92.5 ZeroBench-main (w/tools): 51.0 * Tested only on the pure-text subset of the HLE benchmark set. Terminal-Bench 4.0 was tested with the Claude Code framework, and DeepSWE with the Mini-SWE-V2 framework. ZeroBench-main was evaluated with Pass@5. While improving performance, we also reduced the model's task runtime and output length, enabling users to complete tasks at lower cost and higher speed and achieving a new performance–cost Pareto optimum across multiple harnesses. We specifically optimized for DeepSeek Harness, Ten
v2.1.319
## What's changed - Changed auto mode with telemetry or feature flags off, including behind LLM gateways: calls the server can't check are asked about or denied, with no fallback to the built-in classifier; set `CLAUDE_CODE_AUTO_MODE_SERVER=0` to keep using it (Bedrock, Vertex and Foundry are unchanged) - Changed auto mode behind an LLM gateway: `CLAUDE_CODE_AUTO_MODE_SERVER=1` turns on the server-side check even with `CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS` set; if managed settings set the latter, they must set the `1` too - Added support for MCP tasks in the terminal: when an MCP server runs a tool call as a task, Claude Code moves it to the background right away and tells Claude the result when it finishes - Added the `CLAUDE_CODE_DISABLE_MCP_TASK_BACKGROUND` environment variable to make Claude Code wait for an MCP task inside its tool call instead of moving it to the background right away - Added `permissions.denyInsteadOfPrompting` setting: a tool call that would wait on a permission prompt is denied and the turn continues, in terminal sessions, subagents and teammates - Added `/claude-api latency-optimize` to find where your Claude API code makes people wait and try faster se
Plugin to Create Product Videos
Previously, every time I launched a new product, I had to create a video demo to show the users how the product works and often end up with many versions from various angles. Those are tedious and yet hard work since operating the product while explaining how it works precisely according to a script is not easy. There were many back and forth. Once that's been done, editing the video is another time consuming part, not to mention putting together the voiceover(VO) and background music (BGM) which basically requires a professional studio team to come out one. Nowadays Claude Code Opus 5.5 and the like can do a decent job by creating a product demo which is a good start. But the AI smell is very strong. And the biggest pain happens when we want to update some part of the video since the AI video generators typically fixes one part but breaks another. So the back and forth is still there. That's why we build Fluxcut (fluxcut.dev) with a product demo video engine as the filming studio putting together scripting, timeline arrangement, footage section, voiceover, background music and thumbnail so that creators have an all-in-one solution for the product demo. While we design the engine o
DeepSeek-V4.1-Flash-1017 Update
DeepSeek-V4.1-Flash-1017 Update DeepSeek V4.1 Flash has been upgraded to DeepSeek-V4.1-Flash-1017. The official web and APP models have also been updated to the new version. The API calling method and pricing remain unchanged — simply use deepseek-flash to access the latest model. Performance–cost Pareto improvement Compared with the previous DeepSeek V4.1, the new model delivers substantial improvements across benchmarks: HLE (w/o tools): 42.6 (44.0*) Terminal-Bench 4.0: 42.3 DeepSWE v1.1: 77.0 ProgramBench: 29.1 NL2Repo-Bench: 68.2 Automation-Bench v1.0.6: 60.5 Agents' Last Exam: 35.4 Apex Bench v1.1: 72.1 Chartography (w/tools): 83.0 BabyVision (w/tools): 92.5 ZeroBench-main (w/tools): 51.0 * Tested only on the pure-text subset of the HLE benchmark set. Terminal-Bench 4.0 was tested with the Claude Code framework, and DeepSWE with the Mini-SWE-V2 framework. ZeroBench-main was evaluated with Pass@5. While improving performance, we also reduced the model's task runtime and output length, enabling users to complete tasks at lower cost and higher speed and achieving a new performance–cost Pareto optimum across multiple harnesses. We specifically optimized for DeepSeek Harness, Ten
Ask HN: Advice on local efficient analogical retrieval?
So.. I've been running my own archive of conversations, voice recordings, documents, and etc for AI agents (mostly Claude Code) for past 6 month. Currently, when i ask or it answers something it runs hook that checks previous conversations, lists up potential related conversations. The intention is not only to retreive relative memories, but also to be able to connect 2 or more conversations that looks irrelevant but extract some kind of pattern or insight from it. In other words, I want my model to partially go off on a tangent, in a good way... For example; Let's say I bring up topic on investing on OKLO as a potential 10x company. So I say I will keep it small but don't cut loss, only buy more from time to time. I want model to be able to bring up the memory that I also regularly buy things from my few favorite small restuarants just to keep them alive. Maybe connect those 2, and be able to tell that in perspective, I may have a consistant view on spending money. I even have few conversations on that exact topic as well. It just doesn't use similar keywords. I feel like maybe the obstacle is that model can't come up with the direction that the conversation could develop to a bro
v2.1.318
## What's changed - Added a record of your answer when Claude Code asks to turn on the mods it writes in a session - Added `assume_role` on `mantle` upstreams of the Claude apps gateway, for a role in another AWS account and for per-developer AWS cost attribution - Added an `effort` option to a mod's `$.model.fork`, so a quick side job can run at `low` whatever effort the session uses; the result reports the effort sent - Added the date a stored claude.ai sign-in ends to `claude auth status` (`loginExpiresAt`) and to `claude -p` JSON results (`credential_expires_at`) - Added a one-line stderr warning to `claude -p` text output, starting 10 days before a stored claude.ai sign-in ends - Fixed `--continue` sometimes losing the earlier conversation after a malformed tool call's retries ran out (regression in 2.1.314) - Fixed macOS sessions with many running Bash commands stalling while memory grew - Fixed permission prompts being answered by keys typed just after sending a message, or before a slow prompt appeared - Fixed `/logout`, `claude auth logout` and `claude mcp remove` reporting success, and changes to trust, consent or MCP settings being dropped with no word, when the config f
DeepSeek-V4.1-Flash-1017 Update
DeepSeek-V4.1-Flash-1017 Update DeepSeek V4.1 Flash has been upgraded to DeepSeek-V4.1-Flash-1017. The official web and APP models have also been updated to the new version. The API calling method and pricing remain unchanged — simply use deepseek-flash to access the latest model. Performance–cost Pareto improvement Compared with the previous DeepSeek V4.1, the new model delivers substantial improvements across benchmarks: HLE (w/o tools): 42.6 (44.0*) Terminal-Bench 4.0: 42.3 DeepSWE v1.1: 77.0 ProgramBench: 29.1 NL2Repo-Bench: 68.2 Automation-Bench v1.0.6: 60.5 Agents' Last Exam: 35.4 Apex Bench v1.1: 72.1 Chartography (w/tools): 83.0 BabyVision (w/tools): 92.5 ZeroBench-main (w/tools): 51.0 * Tested only on the pure-text subset of the HLE benchmark set. Terminal-Bench 4.0 was tested with the Claude Code framework, and DeepSWE with the Mini-SWE-V2 framework. ZeroBench-main was evaluated with Pass@5. While improving performance, we also reduced the model's task runtime and output length, enabling users to complete tasks at lower cost and higher speed and achieving a new performance–cost Pareto optimum across multiple harnesses. We specifically optimized for DeepSeek Harness, Ten
Show HN: Site/app blocker and usage tracker specifically for Linux
This was my first experiment with AI assisted coding. Backstory: I had a bunch of scripts to block sites on my work machines by redirecting them 127.0.0.1 etc. and they sort of worked. I needed something more serious and tried to get some commercial applications but there was nothing that really worked the way I wanted to (especially not on Linux). In Oct 2025 or so, I picked up aider and started building this out. Halfway through, I switched to Claude Code and used this as a vehicle to learn how to use assistants. It blocks sites and apps on a schedule, and takes away your sudo during the hours you choose so you can’t just turn it off. I added several features like tracking usage, giving recommendations etc. and It's been actually very useful for me hence I decided to open source and productize it. Have a few users so far too. It's been a nice learning experience for me. Not just for the implementation but also about the launch and marketing all assisted by AI. Really looking forward to feedback from the folks here.
v2.1.317
## What's changed - Added a warning to `/schedule` when a new cloud scheduled task gets connectors you did not ask for, with how to remove them - Added a check that asks before a web or shell tool call sends your account email address to the network - Added `onFailure: "block"` for Agent SDK hook callbacks, so a callback that fails blocks the action instead of letting it run - Added a notice in Claude Desktop's Code tab when your organization's remote managed settings haven't loaded for the session, and another once they do - Added a notice when auto mode's check has no answer for a subagent's tool call, which used to leave nothing in the main view - Added `anthropic.plan`, `anthropic.seat_type`, `anthropic.provider` and `anthropic.custom_base_url` to OTel metrics, events and spans - Added a cost report to the Claude apps gateway admin API, `GET /v1/organizations/analytics/cost`, for reading past spend over a date range in total, per developer, per day or per IdP group - Added a daily record of each developer's IdP groups on Claude apps gateways with `admin:` set, kept for `admin.identity_retention_days`, which the cost report groups by - Added `CLAUDE_CODE_DISABLE_NESTED_SESSION_I
Friday: Run Claude Code and Codex as a crew on your computer (open source)
Source-linked update: Friday: Run Claude Code and Codex as a crew on your computer (open source)
DeepSeek-V4.1-Flash-1017 Update
DeepSeek-V4.1-Flash-1017 Update DeepSeek V4.1 Flash has been upgraded to DeepSeek-V4.1-Flash-1017. The official web and APP models have also been updated to the new version. The API calling method and pricing remain unchanged — simply use deepseek-flash to access the latest model. Performance–cost Pareto improvement Compared with the previous DeepSeek V4.1, the new model delivers substantial improvements across benchmarks: HLE (w/o tools): 42.6 (44.0*) Terminal-Bench 4.0: 42.3 DeepSWE v1.1: 77.0 ProgramBench: 29.1 NL2Repo-Bench: 68.2 Automation-Bench v1.0.6: 60.5 Agents' Last Exam: 35.4 Apex Bench v1.1: 72.1 Chartography (w/tools): 83.0 BabyVision (w/tools): 92.5 ZeroBench-main (w/tools): 51.0 * Tested only on the pure-text subset of the HLE benchmark set. Terminal-Bench 4.0 was tested with the Claude Code framework, and DeepSWE with the Mini-SWE-V2 framework. ZeroBench-main was evaluated with Pass@5. While improving performance, we also reduced the model's task runtime and output length, enabling users to complete tasks at lower cost and higher speed and achieving a new performance–cost Pareto optimum across multiple harnesses. We specifically optimized for DeepSeek Harness, Ten
v2.1.316
## What's changed - Added `CLAUDE_CODE_DISABLE_ULTRATHINK`, which turns the `ultrathink` keyword off - Added pooled group budgets to the Claude apps gateway: one monthly budget that a group's members share, on top of each member's own limit, set with `pooled_budget` on the spend limits admin API - Added `CLAUDE_CODE_DISABLE_LOOPED_CROSS_CERT_DROP` to keep system cross-certificates that certify each other in a loop, for servers whose private CA needs one - Added `CLAUDE_CODE_SUBAGENT_EFFORT` to set the effort level subagents run at when nothing else names one, instead of inheriting the session's - Added `managed.policy_mode: layered` to the Claude apps gateway: every policy that matches a developer applies, each merged over the ones listed below it, not only the first - Added `guardrail.input_tagging` on Claude apps gateway Bedrock upstreams, which wraps prompts in the input tags that an Amazon Bedrock guardrail's prompt attacks filter needs; `all_messages_and_system` also tags the system prompt - Deprecated fast mode for Opus 4.8 as of October 30, 2026; it will be removed on November 30, 2026. After removal, fast mode requests on Opus 4.8 return an error and do not fall back to sta
DeepSeek-V4.1-Flash-1017 Update
DeepSeek-V4.1-Flash-1017 Update DeepSeek V4.1 Flash has been upgraded to DeepSeek-V4.1-Flash-1017. The official web and APP models have also been updated to the new version. The API calling method and pricing remain unchanged — simply use deepseek-flash to access the latest model. Performance–cost Pareto improvement Compared with the previous DeepSeek V4.1, the new model delivers substantial improvements across benchmarks: HLE (w/o tools): 42.6 (44.0*) Terminal-Bench 4.0: 42.3 DeepSWE v1.1: 77.0 ProgramBench: 29.1 NL2Repo-Bench: 68.2 Automation-Bench v1.0.6: 60.5 Agents' Last Exam: 35.4 Apex Bench v1.1: 72.1 Chartography (w/tools): 83.0 BabyVision (w/tools): 92.5 ZeroBench-main (w/tools): 51.0 * Tested only on the pure-text subset of the HLE benchmark set. Terminal-Bench 4.0 was tested with the Claude Code framework, and DeepSWE with the Mini-SWE-V2 framework. ZeroBench-main was evaluated with Pass@5. While improving performance, we also reduced the model's task runtime and output length, enabling users to complete tasks at lower cost and higher speed and achieving a new performance–cost Pareto optimum across multiple harnesses. We specifically optimized for DeepSeek Harness, Ten
v2.1.314
## What's changed - Added `permissions.blockWritesOutsideWorkingDirectories`: Write, Edit and NotebookEdit refuse paths outside the working directories in every permission mode - Added an optional `groups` list to Claude apps gateway upstreams: only developers in the listed IdP groups are sent to that upstream, on failover too - Added `guardrail_trace` to Claude apps gateway Bedrock upstreams, to log which Amazon Bedrock guardrail filter fired on a request, without the matched text - Added idle compaction to VS Code and Claude Desktop's Code tab: a 200K+ token conversation left idle is summarized, and the summary is used on your next message if the prompt cache has expired - Fixed sessions failing turn after turn with "Invalid effort level" when an organization's admin caps a model's effort: Claude Code now lowers the effort, retries, and says which level it uses - Fixed `claude -p` exiting with code 0 and no output when startup failed; it now prints the error and exits 1 - Fixed Bedrock sessions with many images failing every turn and `/compact` with "400 Input is too long." instead of removing older images and compacting - Fixed Microsoft Foundry sessions failing when the resourc
DeepSeek-V4.1-Flash-1017 Update
DeepSeek-V4.1-Flash-1017 Update DeepSeek V4.1 Flash has been upgraded to DeepSeek-V4.1-Flash-1017. The official web and APP models have also been updated to the new version. The API calling method and pricing remain unchanged — simply use deepseek-flash to access the latest model. Performance–cost Pareto improvement Compared with the previous DeepSeek V4.1, the new model delivers substantial improvements across benchmarks: HLE (w/o tools): 42.6 (44.0*) Terminal-Bench 4.0: 42.3 DeepSWE v1.1: 77.0 ProgramBench: 29.1 NL2Repo-Bench: 68.2 Automation-Bench v1.0.6: 60.5 Agents' Last Exam: 35.4 Apex Bench v1.1: 72.1 Chartography (w/tools): 83.0 BabyVision (w/tools): 92.5 ZeroBench-main (w/tools): 51.0 * Tested only on the pure-text subset of the HLE benchmark set. Terminal-Bench 4.0 was tested with the Claude Code framework, and DeepSWE with the Mini-SWE-V2 framework. ZeroBench-main was evaluated with Pass@5. While improving performance, we also reduced the model's task runtime and output length, enabling users to complete tasks at lower cost and higher speed and achieving a new performance–cost Pareto optimum across multiple harnesses. We specifically optimized for DeepSeek Harness, Ten
Show HN: Multi-platform remote-control for any harness
I was fed up with codex and opencode not having good mobile remote control apps. I loved using claude code from my phone, but i hop between harnesses and i didn't want to be locked into Claude Code just for the mobile remote control. I also hated the shabby pi.dev remote control that i found online. So I figured we needed a unified solution. This is Jep, a multi-harness gateway, with a http client that you can connect any frontend to.
v2.1.312
## What's changed - Added `oidc.user_id_claim` to the Claude apps gateway, to identify people by an id_token claim other than `sub`, such as Microsoft Entra ID's `oid` - Added click to send: in fullscreen, clicking the "to send now" hint under a queued message sends it right away, as its key does - Fixed managed settings and organization policy not being fetched for the rest of the session after signing in from the VS Code extension - Fixed Claude overwriting a very large CLAUDE.md, rules file or @-included file in a subdirectory after seeing only its start; Write now asks Claude to read it all or edit in place - Fixed per-directory and `paths:` skills not being found after a Bash `cd` deeper into a git repository - Fixed a rare case where the first reply after resuming a session in the terminal could be missing the next time the session was resumed - Fixed a command with an invalid name stopping all commands from loading, which could leave `claude -p` with no output - Fixed the Read tool sometimes failing on PDF pages with "pdftoppm failed: Could not write image" when the clean-up of old session files ran at the same time - Fixed the spinner, OpenTelemetry `effort` values and tran
DeepSeek-V4.1-Flash-1017 Update
DeepSeek-V4.1-Flash-1017 Update DeepSeek V4.1 Flash has been upgraded to DeepSeek-V4.1-Flash-1017. The official web and APP models have also been updated to the new version. The API calling method and pricing remain unchanged — simply use deepseek-flash to access the latest model. Performance–cost Pareto improvement Compared with the previous DeepSeek V4.1, the new model delivers substantial improvements across benchmarks: HLE (w/o tools): 42.6 (44.0*) Terminal-Bench 4.0: 42.3 DeepSWE v1.1: 77.0 ProgramBench: 29.1 NL2Repo-Bench: 68.2 Automation-Bench v1.0.6: 60.5 Agents' Last Exam: 35.4 Apex Bench v1.1: 72.1 Chartography (w/tools): 83.0 BabyVision (w/tools): 92.5 ZeroBench-main (w/tools): 51.0 * Tested only on the pure-text subset of the HLE benchmark set. Terminal-Bench 4.0 was tested with the Claude Code framework, and DeepSWE with the Mini-SWE-V2 framework. ZeroBench-main was evaluated with Pass@5. While improving performance, we also reduced the model's task runtime and output length, enabling users to complete tasks at lower cost and higher speed and achieving a new performance–cost Pareto optimum across multiple harnesses. We specifically optimized for DeepSeek Harness, Ten
v2.1.311
## What's changed - Added `--hold-idle-file` and `--max-hold-min` to `self-hosted-runner`, to keep an idle session while your host reports processes it left running - Added a tip for the Explanatory output style, shown when you ask Claude for explanations - Fixed long freezes at startup and after reading or editing files when a CLAUDE.md file holds a very long list item - Fixed interrupting Claude not taking effect until a timeout while an MCP server had not answered a resource read or a skill was still downloading - Fixed standard-context sessions stopping with "Usage credits required for 1M context" when a request ran over 200K tokens; Claude Code now compacts the conversation and continues - Fixed Write and Edit stalling for up to 5 seconds after they ran, and reporting 0 lines changed, when changing thousands of lines in a file - Fixed subagents being unable to use MCP tools from servers that finish connecting after the subagent starts - Fixed Claude seeing stale MEMORY.md and CLAUDE.md content right after automatic compaction when those files were edited earlier in the session - Fixed `claude -p` and SDK sessions saving transcript messages out of order or keeping messages that
DeepSeek-V4.1-Flash-1017 Update
DeepSeek-V4.1-Flash-1017 Update DeepSeek V4.1 Flash has been upgraded to DeepSeek-V4.1-Flash-1017. The official web and APP models have also been updated to the new version. The API calling method and pricing remain unchanged — simply use deepseek-flash to access the latest model. Performance–cost Pareto improvement Compared with the previous DeepSeek V4.1, the new model delivers substantial improvements across benchmarks: HLE (w/o tools): 42.6 (44.0*) Terminal-Bench 4.0: 42.3 DeepSWE v1.1: 77.0 ProgramBench: 29.1 NL2Repo-Bench: 68.2 Automation-Bench v1.0.6: 60.5 Agents' Last Exam: 35.4 Apex Bench v1.1: 72.1 Chartography (w/tools): 83.0 BabyVision (w/tools): 92.5 ZeroBench-main (w/tools): 51.0 * Tested only on the pure-text subset of the HLE benchmark set. Terminal-Bench 4.0 was tested with the Claude Code framework, and DeepSWE with the Mini-SWE-V2 framework. ZeroBench-main was evaluated with Pass@5. While improving performance, we also reduced the model's task runtime and output length, enabling users to complete tasks at lower cost and higher speed and achieving a new performance–cost Pareto optimum across multiple harnesses. We specifically optimized for DeepSeek Harness, Ten
Show HN: Claude Code(and others) embedded in your app
I started this project in 2024 when I got fascinated with LLMs, and what I did was a coding agent (CLI -> interactive -> GUI). I also added an integration with Vite for having it embedded inside my apps(mostly games). Few months ago I pivoted it to become a low profile AI provider wrapper library (think jQuery for LLM usage), because I realized there is no point to have custom coding agent. Recently I did yet another pivot, and now it is a solution that allows you to embed Claude Code inside of your app, and use it directly from there for 1. development, 2. every day ops and automate the tasks in the app In theory all you need to try it is this command: `npx genaicode embed`, I wonder if anyone would like to give it a try, and let me know how it worked!
v2.1.310
## What's changed - Added the Monitor tool and plugin monitors on Bedrock, Vertex, and Foundry, and when telemetry or nonessential traffic is disabled; long foreground sleeps are now blocked there too - Fixed requests failing behind some gateways and compatible servers that reject the `effort-2025-11-24` beta value or mid-conversation system messages; Claude Code now retries without them - Fixed background cleanup deleting some recent files, such as pasted images, when `cleanupPeriodDays` is set to a very large value - Fixed compaction after a "Prompt is too long" error keeping too much of a conversation with dense text, such as base64 or SVG, so the next request could fail again - Fixed file read permission prompts not showing where a symbolic link leads - Fixed a question's auto-continue timeout firing the moment the external editor closed after a long edit - Windows: Fixed PreToolUse and PermissionRequest hooks letting a tool call through when Git Bash is missing and the hook's command is only quoted strings, such as a quoted path - Improved auto mode's prompt before the first read outside the working directories: it now says when blocking those reads makes shell commands ask fo
DeepSeek-V4.1-Flash-1017 Update
DeepSeek-V4.1-Flash-1017 Update DeepSeek V4.1 Flash has been upgraded to DeepSeek-V4.1-Flash-1017. The official web and APP models have also been updated to the new version. The API calling method and pricing remain unchanged — simply use deepseek-flash to access the latest model. Performance–cost Pareto improvement Compared with the previous DeepSeek V4.1, the new model delivers substantial improvements across benchmarks: HLE (w/o tools): 42.6 (44.0*) Terminal-Bench 4.0: 42.3 DeepSWE v1.1: 77.0 ProgramBench: 29.1 NL2Repo-Bench: 68.2 Automation-Bench v1.0.6: 60.5 Agents' Last Exam: 35.4 Apex Bench v1.1: 72.1 Chartography (w/tools): 83.0 BabyVision (w/tools): 92.5 ZeroBench-main (w/tools): 51.0 * Tested only on the pure-text subset of the HLE benchmark set. Terminal-Bench 4.0 was tested with the Claude Code framework, and DeepSWE with the Mini-SWE-V2 framework. ZeroBench-main was evaluated with Pass@5. While improving performance, we also reduced the model's task runtime and output length, enabling users to complete tasks at lower cost and higher speed and achieving a new performance–cost Pareto optimum across multiple harnesses. We specifically optimized for DeepSeek Harness, Ten
v2.1.309
## What's changed - Fixed sandboxed Bash commands on macOS and Linux running the shell's startup files outside the sandbox before each command - Fixed macOS sandbox `denyWrite` glob patterns not applying at a path's real location when the pattern's folder is reached through a symlink - Fixed sandboxed commands and auto-accepted edits being able to modify the MCP config file passed with `--mcp-config` - Fixed a disabled MCP server being reconnected by a later permission prompt in print and SDK sessions - Fixed the Bash permission check trusting a variable set by a command whose redirect can fail to open - Fixed Bash permission checks not prompting for some compound commands that change directory before running git when the `cd` is wrapped or prefixed, as they do for a plain `cd` - Fixed an `Edit(path)` deny rule not blocking a Bash redirect to that path in some commands that also held a subshell - Fixed worktree-isolated sessions accepting some locale-prefixed commands the isolation guard should refuse - Fixed worktree-isolated sessions on zsh accepting some arithmetic commands that the isolation guard should refuse - Fixed worktrees and branch checkouts that Claude Code creates so
v2.1.308
## What's changed - Bug fixes and reliability improvements
v2.1.307
## What's changed - Added `/claude-api api-version` to move Claude API code to API version `2026-10-21` - Added the `claude_code.safety_event` OpenTelemetry event for each tool call a permission rule, auto mode, a safety check, a hook or the sandbox stopped, prompted or sent back - Fixed requests failing with a model-not-found error when `CLAUDE_CODE_DISABLE_1M_CONTEXT` is set and the model is an alias with the `[1m]` suffix, such as `opus[1m]` - Fixed the `prompt-caching-scope` beta header being sent behind custom `ANTHROPIC_BASE_URL` gateways and on Foundry, where it has no effect - Fixed MCP servers showing "needs authentication" in `claude -p` on macOS while the login keychain was locked; they now say why, and the next run after an unlock connects without a new sign-in - Fixed MCP servers being reported as timed out, and staying failed in headless runs, when a macOS or Linux computer went to sleep while they were connecting - Fixed HTTP MCP tool calls being sent twice when the connection closed mid-call; only read-only or idempotent tools are now retried - Fixed a turn sometimes starting without an SDK MCP server's latest tools when a background task was running - Fixed some "A
DeepSeek-V4.1-Flash-1017 Update
DeepSeek-V4.1-Flash-1017 Update DeepSeek V4.1 Flash has been upgraded to DeepSeek-V4.1-Flash-1017. The official web and APP models have also been updated to the new version. The API calling method and pricing remain unchanged — simply use deepseek-flash to access the latest model. Performance–cost Pareto improvement Compared with the previous DeepSeek V4.1, the new model delivers substantial improvements across benchmarks: HLE (w/o tools): 42.6 (44.0*) Terminal-Bench 4.0: 42.3 DeepSWE v1.1: 77.0 ProgramBench: 29.1 NL2Repo-Bench: 68.2 Automation-Bench v1.0.6: 60.5 Agents' Last Exam: 35.4 Apex Bench v1.1: 72.1 Chartography (w/tools): 83.0 BabyVision (w/tools): 92.5 ZeroBench-main (w/tools): 51.0 * Tested only on the pure-text subset of the HLE benchmark set. Terminal-Bench 4.0 was tested with the Claude Code framework, and DeepSWE with the Mini-SWE-V2 framework. ZeroBench-main was evaluated with Pass@5. While improving performance, we also reduced the model's task runtime and output length, enabling users to complete tasks at lower cost and higher speed and achieving a new performance–cost Pareto optimum across multiple harnesses. We specifically optimized for DeepSeek Harness, Ten
v2.1.306
## What's changed - Fixed `claude -p` inside cloud sessions reporting "Not logged in" when started without the session's environment variables - Fixed an API error being replaced by "prompt is too long", and an unneeded compaction, in sessions with many MCP tools
APIDir Delta · controlled rollout
Join the source-linked pricing update waitlist.
Confirm your address to join the waitlist. Editorial delivery starts only after sender, suppression, and evidence checks are active.