Claude Code v2.1.154
Released May 28, 2026 (3 months ago).
141 issues reference this build
5 still open
136 resolved (96%)
"References this build" means the issue body mentions running 2.1.154 (from the
bug-report template). It reflects report volume, not a proven defect count — an issue may mention a
version without being caused by it. First-party data from the anthropics/claude-code tracker.
Top issues reported on v2.1.154
Ranked by community engagement (reactions and comments).
- Opus 4.8 returns empty thinking blocks — no thinking shown in chat (same regression as Opus 4.7 #49268)
- [Bug] Anthropic API Error: Cannot modify thinking blocks in assistant message
- [Bug] Anthropic API Error: Cannot modify thinking blocks in assistant message
- [BUG] API Error: 400 Failed to deserialize the JSON body into the target type
- [Bug] Anthropic API Error: Cannot modify thinking blocks in assistant message
- messages.11.content.11: `thinking` or `redacted_thinking` blocks in the latest assistant message cannot be modified.
- [Bug] Anthropic API Error: Cannot Modify Thinking Blocks in Assistant Messages
- [Bug] Anthropic API Error: Cannot modify thinking blocks in assistant message
- Persistent 400 'thinking blocks in the latest assistant message cannot be modified' — interleaved thinking persisted with empty text + signature bricks sessions
- [Bug] Anthropic API Error: Cannot modify thinking blocks in assistant messages
- [Bug] Anthropic API Error: Cannot modify thinking blocks in assistant message
- Opus 4.8: backgrounded task completions (subagents AND Bash) crash with 400 "thinking blocks cannot be modified"
- [Bug] Anthropic API Error: Tool Call Parsing Failure
- Opus 4.8: thinking blocks broken by context compaction — 400 error on every turn after first compaction
- [BUG] CLI 2.1.154 breaks with API Error 422 - Invalid message role "system"
- [Bug] Anthropic API Error: Cannot modify thinking blocks in assistant messages
- context_window_size reported as 200000 for claude-opus-4-8 (1M-context model) → "100% context used" clamps prematurely
- 2.1.154 regression: bridge/remote-control session replay re-sends persisted (empty-text, signed) thinking blocks -> 400 'thinking blocks cannot be modified', session unrecoverable
- [BUG] Anthropic API error: thinking blocks
- [Bug] Anthropic API Error: Thinking blocks cannot be modified with extended thinking mode
- [Bug] Anthropic API Error: Cannot modify thinking blocks in assistant messages
- [MODEL] Opus 4.8 fabricated a present-tense user request and persisted on an invented task context
- [Bug] Anthropic API Error: Cannot modify thinking blocks in assistant message
- [BUG] 2.1.154 appears to send messages[].role="system" to Anthropic-compatible providers, causing schema parse failures
- [Bug] Anthropic API Error: Cannot modify thinking blocks in assistant messages
- [Bug] Anthropic API Error: Cannot modify thinking blocks in assistant messages
- [Bug] Anthropic API Error: 400 Bad Request with Redacted Thinking - 0 4.7 & 4.8
- [Bug] Anthropic API Error: Cannot Modify Thinking Blocks in Assistant Messages
- [Bug] Persistent Anthropic API Connection Errors
- [Bug] Anthropic API Error: Cannot modify thinking blocks in assistant message
Changelog
What's changed
- 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
/workflowsto 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
/simplifynow runs a cleanup-only review (reuse, simplification, efficiency, altitude) and applies the fixes, instead of running the full/code-review --fixbug-hunting review- Renamed the
/effortslider 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 asclaude --bg --exec '<command>'claude agents:/logoutnow 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: falseinplugin.jsonor a marketplace entry; enable them with/pluginorclaude plugin enable. Dependencies of enabled plugins are still enabled automatically - The
/pluginDiscover 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_IDandCLAUDECODE=1in their environment claude mcp list/getnow show unapproved.mcp.jsonservers as⏸ Pending approvalinstead of auto-approving and connecting when output is piped/remote-controlautocomplete 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-apiskill - 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 $HOMEnot being blocked as a dangerous path whenHOMEhas a trailing slash - Fixed
$TMPDIRresolving to different directories in sandboxed vs unsandboxed Bash commands within the same session - Fixed unreadable highlighted-row text in
claude agentswhen 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
/commandfires - 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-hostprocesses 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 instea