Claude Code v2.1.156
Released May 29, 2026 (3 months ago).
229 issues reference this build
18 still open
211 resolved (92%)
"References this build" means the issue body mentions running 2.1.156 (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 v2.1.156
Ranked by community engagement (reactions and comments).
- [BUG] Inline KaTeX math (`$...$`) no longer renders in chat output — only block `$$...$$` works (regression)
- [BUG] Error: Error during compaction: API Error: Usage credits required for 1M context · turn on usage credits at claude.ai/settings/usage, or use --model to switch to standard context
- Opus 4.8 not selectable in CLI `/model` despite being available on account
- [BUG] Opus 4.8 repeatedly emits malformed tool_use blocks, entire response discarded (4.7 works fine)
- [Bug] Parallel tool calls trigger persistent "Cancelled" errors
- [Bug] Agent spams no-op echo probe commands to flush shell output
- [BUG] AUP/cyber-safeguard false positives on legitimate own-software hardening; one hit contaminates entire session
- [BUG] API 400 "messages[1].role must be either 'user' or 'assistant', but got 'system'" (v2.1.156)
- [BUG] Stale "Pull request status couldn't be checked" on archived sessions whose repo/worktree was deleted
- Effort/model selection ("ultracode") reverts to "extra" when switching chats
- [BUG] /claude-api bundled skill saturates context unconditionally — ~77% spike from neutral question
- [BUG] /compact fails with cyber safeguards false positive during legitimate defensive security session
- [Bug] "workflow" keyword conflicts with tool trigger syntax
- Opus claude-opus-4-8 emits unparseable tool calls at ~1.5% rate; opus-4-7 and sonnet-4-6 have 0% failure rate
- [Bug] Claude 4.8 Opus hallucinating tool outputs without execution
- [Bug] Anthropic API Error: Usage credits required for 1M context with 1M context disabled
- [BUG] Claude Code for VS Code API Error: 400 messages[1].role must be either 'user' or 'assistant', but got 'system'
- [BUG] Opus 4.8 in Claude Code declares work "verified" / "done" without running the canonical build — false-green regression vs. Opus 4.7
- [Bug] Claude Opus 4.8: Tool call parsing fails when extended thinking is triggered
- Doing useless tool call wasting token
- [Bug] /compact fails with "Usage credits required for 1M context" even after /model set to Sonnet 4.6
- VS Code extension ignores sandbox settings.json / /sandbox unavailable (approval-fatigue fix unreachable in IDE)
- [BUG] CLAUDE_CODE_DISABLE_1M_CONTEXT ignored in 2.1.156
- Bash/Read tool results intermittently return empty (then flush late, redundantly) on Linux — NOT length/concurrency-correlated; same symptom as stale-closed #36038
- [BUG] Bash and Read tool outputs arriving one turn late
- Code-tab Customize -> Skills is missing skills that are present in ~/.claude/skills (non-deterministic; / menu and engine load them all)
- [BUG] Desktop local-agent (Claude Code): 900s session idle timeout tears down the computer-use connector and never re-registers it on resume
- [Bug] Opus 4.7 & 4.8 — silent stuck-turn: stop_reason=tool_use with no tool_use block (Sonnet 4.6 unaffected)
- [BUG] ClaudeCodeManager-VM Checksum Mismatch on macOS Apple Silicon — v1.9659.2
- Model Opus 4.8 False positive safety block: innocent Gmail MCP question blocked as "cyber threat"
Changelog
What's changed
- Fixed an issue when using Opus 4.8 where thinking blocks were modified, leading to API errors.