docs: Claude Code v2.1.154 - Opus 4.8 default + dynamic workflows

content/CHANGELOG.md

@@ -1,5 +1,52 @@
 # Changelog
 
+## 2.1.154
+
+- Opus 4.8 is here! Now defaults to high effort · /effort xhigh for your hardest tasks
+- Introducing dynamic workflows: ask Claude to create a workflow and it orchestrates work across tens to hundreds of agents in the background, so you can take on larger, more complex tasks. Run `/workflows` to view your runs
+- Fast mode on Opus 4.8 is now available at a fraction of its previous cost: 2x the standard rate for 2.5x the speed
+- The lean system prompt is now the default for all models except Haiku, Sonnet, and Opus 4.7 and earlier
+- Claude now reserves the multiple-choice question prompt for decisions it genuinely cannot make itself, instead of asking when it already has enough context to proceed
+- `/simplify` now runs a cleanup-only review (reuse, simplification, efficiency, altitude) and applies the fixes, instead of running the full `/code-review --fix` bug-hunting review
+- Renamed the `/effort` slider labels from "Speed"/"Intelligence" to "Faster"/"Smarter" for clarity
+- `claude agents`: type `! <command>` to run a shell command as a background session you can attach to and detach from. Also available as `claude --bg --exec '<command>'`
+- `claude agents`: `/logout` now signs you out instead of being sent to a background session
+- `←←` to open the agents view now works on Bedrock, Vertex, Foundry, and with telemetry disabled
+- Claude in Chrome: pick which connected browser to use via `/chrome` → "Select browser…", or in-chat when a browser action runs with multiple connected
+- Plugins can now declare `defaultEnabled: false` in `plugin.json` or a marketplace entry; enable them with `/plugin` or `claude plugin enable`. Dependencies of enabled plugins are still enabled automatically
+- The `/plugin` Discover tab now pins plugins whose relevance signals match the current directory with a "suggested for this directory" annotation
+- Streaming tool execution is now always enabled, including when telemetry is disabled or on Bedrock/Vertex/Foundry (previously behind a feature flag)
+- Stdio MCP server subprocesses now receive `CLAUDE_CODE_SESSION_ID` and `CLAUDECODE=1` in their environment
+- `claude mcp list`/`get` now show unapproved `.mcp.json` servers as `⏸ Pending approval` instead of auto-approving and connecting when output is piped
+- `/remote-control` autocomplete now shows "Disconnect Remote Control" when Remote Control is already active
+- Added Claude Opus 4.8 support and 4.7 → 4.8 migration guidance to the `/claude-api` skill
+- Deprecated `CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE` (will be removed on 06/01). To use fast mode on Opus 4.6, switch with `/model claude-opus-4-6[1m]` and then `/fast on`
+- Improved the auto-mode classifier's detection of data exfiltration, particularly bulk transfers of repository contents
+- Fixed `rm -rf $HOME` not being blocked as a dangerous path when `HOME` has a trailing slash
+- Fixed `$TMPDIR` resolving to different directories in sandboxed vs unsandboxed Bash commands within the same session
+- Fixed unreadable highlighted-row text in `claude agents` when the Claude Code theme doesn't match the terminal background
+- Fixed background-agent completion notifications triggering premature "out of context" behavior on some 1M-context models
+- Fixed background-session classifier losing the user's goal when a scheduled `/command` fires
+- Fixed pinned background sessions respawning every minute after a Claude Code update, causing repeated agent-start notifications and process churn at idle
+- Fixed background sessions stuck at "blocked", "running", or "working" not retiring after the idle grace period
+- Fixed subagents in background sessions bypassing the worktree-isolation guard and writing to the shared checkout
+- Fixed orphaned `claude --bg-pty-host` processes spinning at 100% CPU after the daemon exits on macOS
+- Fixed number key shortcuts not working for options shown below the divider in option dialogs
+- Fixed `worktree.baseRef: "head"` resolving to the main checkout's HEAD instead of the current worktree's HEAD when spawning subagents or calling `EnterWorktree` from inside a linked worktree
+- Fixed a stray leading space on wrapped lines when the previous line ended exactly at the terminal width
+- Fixed intermittent terminal rendering corruption in VS Code by capping the number of distinct colors the thinking spinner produces
+- Fixed plan file names including `[Image #N]` / `[Pasted text #N]` placeholders when a plan-mode prompt starts with pasted images or text
+- Fixed a phantom expand/click affordance on colored tool output: short ANSI-colored lines that fit on screen no longer show a "ctrl+o to expand" hint
+- Fixed a single invalid `allowedMcpServers`/`deniedMcpServers` entry in managed settings discarding all managed-settings policy; the bad entry is now dropped with a `claude doctor` warning
+- Fixed API 400 errors on models that don't support the effort parameter when `CLAUDE_CODE_ALWAYS_ENABLE_EFFORT` is set
+- Windows: Fixed update failures caused by `claude.exe` being in use showing a generic error instead of telling you to close other sessions and retry
+- Removed the stale "& for background" hint from the shortcuts help panel
+- [VSCode] Auto mode no longer requires the bypass-permissions setting to appear in the mode picker, and a dismissable notice on the new-session screen explains auto mode the first time it's active
+- Fixed the task panel below the prompt showing a stray unselectable "main" row when only a workflow is running
+- Fixed /mcp tools list and tool detail rendering when MCP servers have long or multi-line tool names or long descriptions
+- Fixed the /model picker not showing fast mode pricing on the Default option for API (pay-as-you-go) users when fast mode is on
+- Fixed auto mode incorrectly blocking actions with "could not evaluate this action" when the safety classifier ran out of output tokens while reasoning
+
 ## 2.1.153
 
 - Added `skipLfs` option to `github`/`git` plugin marketplace sources to skip Git LFS downloads during clone and update

content/blog/research/interpretability-dreams.md

@@ -3,6 +3,8 @@ Title: Interpretability Dreams
 URL Source: https://www.anthropic.com/research/interpretability-dreams
 
 Markdown Content:
+# Interpretability Dreams \ Anthropic
+
 [Skip to main content](https://www.anthropic.com/research/interpretability-dreams#main-content)[Skip to footer](https://www.anthropic.com/research/interpretability-dreams#footer)
 
 [](https://www.anthropic.com/)
@@ -158,5 +160,3 @@ Privacy choices*   [Privacy policy](https://www.anthropic.com/legal/privacy)
 *   [](https://www.linkedin.com/company/anthropicresearch)
 *   [](https://x.com/AnthropicAI)
 *   [](https://www.youtube.com/@anthropic-ai)
-
-# Interpretability Dreams \ Anthropic

content/blog/research/introducing-anthropic-science.md

@@ -0,0 +1,52 @@
+Title: Introducing our Science Blog
+
+URL Source: https://www.anthropic.com/research/introducing-anthropic-science
+
+Markdown Content:
+_We’re launching a new blog about AI and science. We’ll share work happening at Anthropic and elsewhere, our collaborations with external researchers and labs, and discuss practical workflows for scientists using AI in their research._
+
+Increasing the pace of scientific progress is a core part of Anthropic’s mission. [_Machines of Loving Grace_](https://www.darioamodei.com/essay/machines-of-loving-grace) describes the prospect of a “compressed 21st century” in which decades of scientific progress occur over just a few years. We’re starting to see what the early stages of that compression look like: AI is helping mathematicians to [discover](https://www-cs-faculty.stanford.edu/~knuth/papers/claude-cycles.pdf)[new proofs](https://www.math.inc/sphere-packing), individual researchers to [run computational analyses](https://scottdodelson.substack.com/p/evolving-dark-energy-and-ai) that once required dedicated teams, and biologists to [identify functional gene relationships](https://www.biorxiv.org/content/10.1101/2025.05.26.656231v1.full.pdf) across datasets of millions of cells.
+
+Just as computers took on the task of computation, AI is now taking on parts of _cognition_. As a side effect of this shift, work that used to require years of specialized training can increasingly be done more quickly and cheaply with AI. The rate of progress raises sociological questions about the practice of science and the role of scientific institutions: What should research apprenticeship look like? How do we maintain trust in the literature when AI becomes more central to producing it? What does it even mean to be a scientist when the bottleneck shifts from execution to management?
+
+Although the pace of improvement is rapid, some of these questions may feel premature today—AI’s scientific capabilities are, in many ways, still in beta. While models already seem superhuman at certain parts of the scientific workflow, they can also hallucinate results, be overly sycophantic, and get stuck on problems a domain practitioner would find trivial. Fields Medalist Timothy Gowers captured this tension well, [writing](https://x.com/wtgowers/status/1984340187003175298?s=20) that “it looks as though we have entered the brief but enjoyable era where our research is greatly sped up by AI but AI still needs us.”
+
+AI will alter the scientific process in ways that are only starting to become apparent. This blog will discuss the upsides and challenges of the current moment for AI and science, exploring the excitement as it unfolds.
+
+### What we’ll cover
+
+In this blog, we’ll share three main types of posts:
+
+*   **Features:** Articles on a specific result or line of work, with enough detail to understand both the science and the role AI played in producing it. We’ll publish stories both from Anthropic researchers and guest contributors and collaborators.
+*   **Workflows:** Practical guides for researchers who want to use AI in their own work across various domains in the natural and formal sciences.
+*   **Field notes:** Roundups of developments across the field, including notable results, new tools, and open questions.
+
+We’re publishing two pieces alongside this introduction: Matthew Schwartz’s “[Vibe physics: The AI grad student](https://www.anthropic.com/research/vibe-physics),” a spotlight on supervising Claude through a real theoretical physics calculation, and [a tutorial on orchestrating long-running tasks for scientific computation](https://www.anthropic.com/research/long-running-Claude).
+
+### **Science at Anthropic**
+
+Anthropic has several initiatives aimed at accelerating scientific progress. Our [AI for Science](https://www.anthropic.com/news/ai-for-science-program) program provides API credits to researchers working on high-impact projects across biology, physics, chemistry, and other fields. [Claude for Life Sciences](https://www.anthropic.com/news/claude-for-life-sciences) is dedicated to making Claude useful for life sciences researchers and R&D teams, with partnerships across research institutions, pharma, and biotech. We recently shared some early [results of these programs](https://www.anthropic.com/news/accelerating-scientific-research). And we’re a [core partner](https://www.anthropic.com/news/genesis-mission-partnership) in the [Genesis Mission](http://genesis.energy.gov/), a multi-billion-dollar initiative across industry, academia, and government to accelerate American science with AI.
+
+Beyond these dedicated efforts, researchers across Anthropic are working to improve our models' core scientific capabilities and safely accelerate AI-assisted discovery. Many come from biophysics, chemistry, and neuroscience. We'll be reporting on their work and on efforts elsewhere in the field.
+
+If you have something you want to see covered here, please reach out to us at scienceblog@anthropic.com.
+
+## Related content
+
+### Coding agents in the social sciences
+
+Results from a survey of 1,260 social scientists about AI and coding agent use.
+
+[Read more](https://www.anthropic.com/research/coding-agents-social-sciences)
+
+### Project Glasswing: An initial update
+
+An early update on what we've learned from Project Glasswing.
+
+[Read more](https://www.anthropic.com/research/glasswing-initial-update)
+
+### 2028: Two scenarios for global AI leadership
+
+Our views on the AI competition between the US and China.
+
+[Read more](https://www.anthropic.com/research/2028-ai-leadership)