Model behaviour issues on macOS — page 2
Issues the maintainers labelled both platform:macos and area:model.
2,520 issues · 662 open · 1,858 resolved (74%) · first seen May 20, 2025
Is this getting better or worse?
This class of problem is still growing. 1510 new reports in the last 90 days vs 654 in the 90 before — +131%. The open backlog peaked at 681 in 2026-07 and sits at 662 today.
Derived by counting each matching issue from its creation date until it closed. First-party
computation over the anthropics/claude-code tracker — the trend is not published
anywhere upstream.
Which builds report this
1,908 of these reports name the Claude Code build they were running, spanning 181 releases. Heaviest reporters:
- Claude Code v2.1.198
- Claude Code v2.1.170
- Claude Code v2.1.201
- Claude Code v2.1.207
- Claude Code v2.1.197
- Claude Code v2.1.199
- Claude Code v2.1.212
- Claude Code v2.1.211
Report volume, not a defect count: an issue can mention a build without that build having caused the failure. Versions come from the version string in the bug-report template, matched against real published tags.
Do these get fixed?
Median time to close is 35 days across 1,858 closures. Of the 1,858 closures with a recorded reason, 13% were closed as completed and 1,611 as not-planned or duplicate. The most recent completed fix landed in 2026-08.
Workarounds reported by the community
208 of these issues post a workaround someone says worked. The highest-engagement ones:
- [Bug] Anthropic API Error: Model's tool call could not be parsed (retry also failed)
- This issue makes claude code unusable... Quick workaround:
Found in the thread of #62123 · still open - [BUG] Opus 4.6 removed from Claude Desktop Code tab model picker after Opus 4.7 release
- …he option to use Opus 4.6 but not the "Coding" tab? Anyone has a workaround for the Desktop App?
Found in the thread of #49689 · resolved - Model setting changes globally across all sessions (regression)
- …ly in , so changing it in one session affects all sessions. Workaround 1 — Use project-level model override: Set the model per-project in : Project-level settings override the global setting, so each project can have its…
Found in the thread of #20745 · resolved - [BUG] Claude clobbers correct typographic marks and can't be told otherwise
- …ization code - Any scenario where Unicode precision matters Workaround: Use Unicode escape sequences (e.g., ) instead of literal Unicode characters. ------------ I've not yet tested the workaround, but I imagine it'd wor…
Found in the thread of #1599 · still open - [BUG] Claude Code defaults to 1M context on fresh session with no workaround on Pro plan
- …ars immediately without any prompt or file loaded Attempted workarounds — none resolved it: - — same error - — same error - → with Pro credentials only — same error Expected behavior: Standard context window used by defa…
Found in the description of #62063 · resolved
Excerpts are quoted from the linked issue so you can judge relevance before opening it. Threads that only ask for a workaround, or report that there is none, are excluded. These are community suggestions, not official guidance from Anthropic — read the full thread before applying one.
Matching issues 101–200
Ranked by community engagement (reactions weighted over comments). Listing the top 300 of 2,520 matches; the statistics above cover all 2,520.
- [Bug] Missing Fable 5 option in /advisor command choices
- [Bug] Opus 4.8: Tool calls serialized as plain text instead of tool_use blocks in high-composition sessions
- [BUG] Persistent AUP false positives — 40+ per 4 sessions, across unrelated projects (psychology book, web app, infra, bot)
- [BUG]Claude Code ignores CLAUDE.md rules repeatedly despite acknowledgment
- [BUG] Opus 4.7/4.8 token usage regressed 2-3x after update; Opus 4.8 also disconnects frequently
- Opus 4.6 1M context window disappeared — was working, now gone
- [Bug] Claude Code ignores memory and claude.md files during execution
- [BUG] Ultrathink not setting effort to max, sets it to high instead.
- [BUG] CLAUDE HALLUCINATING AND LIES since 2 days
- Agent output and permission-prompt rate increase as work becomes mechanical, inverse to cognitive load
- [Bug] Performance Regression: Reduced Capability in Claude Opus Model
- Max Account Token Incorrectly Generates Pro Account Credentials
- Fable 5: assistant text emitted before a tool call in the same turn is not shown to the user, but the model assumes it was
- [BUG] In VSCode extension, is model switching via /model isolated per chat session? Seems like it might not be.
- [Bug] Opus 4.7 performance degradation and excessive token consumption
- [Bug] Opus 4.7 performance degradation: excessive context consumption and task failures compared to Opus 4.6
- [BUG] Quality Deterioration
- [BUG] Output blocked by context filtering policy when generating BSL license text
- Claude Not Reading Claude.md
- [Bug] Claude Code fails to recognize MAX subscription tier - defaults to Pro restrictions
- Authentication Error: Claude Pro Users Unable to Access Opus 4
- [Bug] Anthropic API Error: Excessive false positive blocks on document reading requests
- [BUG] Advisor blocks Fable 5 usage
- Tool call intermittently emitted as literal "count" (antml: prefix dropped, "could not be parsed") in long Opus 4.8 1M-context sessions
- [BUG] Opus 4.8 medium effort spends 46k output tokens on hidden thinking for a simple coding turn
- [BUG] Model picker shows Opus 4.7 (200K) but session silently runs in 1M context — burned 18% of 5-hour Max limit on a small prompt
- [Bug] Anthropic API Error: Usage Policy violation on non-policy-violating prompts
- [Bug] Claude ignores plan mode and continues executing despite acknowledgment
- [BUG] Heavily degraded model performance during off peak business hours (March 17, 2026)
- [BUG] Bash tool "avoid cd" instruction causes systematic failure in SSH remote commands
- Model inserts hard line breaks in MCP tool parameters, breaking Slack/Gmail draft formatting
- [BUG] Getting incorrect "exceeded the 32000 output token maximum"
- Sonnet and Opus ClaudecodeCLI: API Error: 500 {"type":"error","error":{"type":"api_error","...
- [BUG] Skill frontmatter `model:` field documented but not working
- API Request Size Exceeds Context Window Limit
- False positive on Claude Code Usage Policy classifier — please stop over-flagging legitimate engineering work
- [Bug] Global claude.md instructions not being consistently applied
- `opus` alias defaults to Opus 4.1 on Vertex AI, but Opus 4.5 on direct API
- Invalid Thinking Block Parameters in API Request
- [BUG] Fable 5 thinking blocks come back empty ("thinking":"") in VS Code extension 2.1.233 — Opus 5 unaffected, worked on 2.1.228
- [BUG] API ignores explicit thinking display:"summarized" for Opus 4.8 / Sonnet 5 since 2026-07-16 — empty thinking blocks; server-side (request verified delivered)
- [Bug] Anthropic API Error: Invalid or Inaccessible Model claude-fable-5
- Regression (since 2026-05-29): intermittent "tool call was malformed and could not be parsed" — tool_use block absent on a stop_reason=tool_use turn
- [BUG] CLI 2.1.145 sends literal "claude-opus-4-7[1m]" as model name on session resume, hits 404, silently falls back to 200K
- [BUG] Opus 4.6 keeps getting stuck on the official Claude Code Web
- [BUG] model: opus alias resolves to Opus 4.1 instead of available Opus 4.5 on Bedrock
- [BUG] API 400 error: assistant message thinking blocks serialized with `text` before `thinking` in conversation replay
- [Bug] Claude Opus 4.5 ignores instructions, significant degradation since Jan 14
- [Bug] Incorrect Usage Limit Message for Claude Opus Model
- [BUG] 🚨 Critical: Output Corruption Persisted Beyond Official Fix Date
- [BUG] /model setting does not persist across sessions despite “future sessions” claim
- [Bug] Model ignores scope constraints and executes agent recommendations beyond user's explicit request
- [BUG] Generated markdown missing required blank lines before code blocks and lists (CommonMark violation)
- [Bug] Fable 5 safety classifier false-positives on authorized defensive security audits
- Tool calls intermittently fail with "malformed and could not be parsed"; markup rendered as chat text
- [Bug] Claude Code (Opus) repeatedly violated locked memory rules, caused WABA suspension, DNS email outage, and partner relationship damage — business-critical multi-incident report
- [BUG] Persistent false-positive AUP violation blocks entire AI research project (Opus 4.7)
- Opus 4.6: model does not re-examine self-imposed assumptions after documenting their cost as a weakness
- Language instruction ignored: Claude responds in Japanese despite explicit Traditional Chinese requirement in CLAUDE.md
- Opus 4.6 is getting dumber
- [BUG] Horribly degraded performance on all models.
- [Bug] Extended thinking hangs indefinitely, consuming all tokens without returning results
- Opus 4.6 with 1M context unavailable for Max 5x subscriber
- Agent repeatedly suggests stopping instead of continuing during long sessions
- [Bug] Degraded code generation quality and increased correction rate
- [Bug] Code Quality Regression: Reduced Instruction Adherence in 2.1.x
- [Bug] Sonnet 4.5 context window fills up prematurely with large files
- Invalid Model Name in Model Selection Command
- [BUG] Opus subagents are being billed as Fable usage
- [Bug] Fable 5 model unavailable due to overly broad safety filtering on biology topics
- Conversation permanently blocked after credential-related context — rewind doesn't help
- Claude Code ignores CLAUDE.md/memory, and suspected Opus 4.7 capability regression requiring excessive token usage
- Bedrock: thinking.type.enabled not supported by newer models behind inference profile ARNs
- [BUG] API issue: `thinking` or `redacted_thinking` blocks in the latest assistant message cannot be modified. These blocks must remain as they were in the original response."
- [BUG] API Error: 400 {"type":"error","error":{"type":"invalid_request_error","message":"system: Invalid model name"}}
- "Image Loading Failure: Unrecoverable Error with Large Image Files"
- [Bug] `opusplan` silently falls back to Sonnet during plan mode (no signal)
- [Bug] Still reproducing on 2.1.186: assistant hallucinates fake user/system turns with stop_reason=null (re-report of #64791, wrongly auto-closed)
- [Bug] Claude Opus 4.8 emits malformed tool calls with parsing errors
- [BUG] Claude Code repeatedly overrides explicit directives in the same session
- [BUG] Claude Code Opus 4.6 has become extremely dumb and expensive for serious programming tasks
- [Bug] Model reliability regression: overclaiming completion, silent deferral, and unverified fixes in Claude Code
- [Bug] 1M context window incorrectly shown as extra billable usage on Max plan
- Model performance degradation observed in claude-sonnet-4-6 (increased basic errors, reduced comprehension)
- Opus 4.6: Model ignores loaded context, requires constant user correction
- CRITICAL: Claude Code regression — model now consistently fails basic tasks and hallucinates in code analysis
- [Bug] Claude Code ignores configured rules and skips required review steps
- [BUG] False positive Usage Policy violations - 11 in single session on benign content
- [Bug] Claude prioritizes speed over correctness - fundamentally wrong priority system for a coding agent
- [Bug] Opus 4.5 missing from Claude Code model picker menu
- [BUG] Pro account switching to sonnet[1m] started throwing API 400 error
- [Bug] Claude Code: Limited Model Selection and Frequent Context Compaction/
- [Bug] Anthropic API: Unable to Access Claude Opus with Max Subscription
- Critical Bug: Claude Code CLI is making excessive background API calls, ignoring model configuration, and console reporting inconsistencies
- Routines: model selector missing from create and edit forms — runs silently fall back to default model
- [BUG] Usage credits required for 1M context" blocks all requests on Pro plan — first use of the day, quota available, Sonnet selected
- [BUG] Agent tool `model` parameter silently overridden by CLAUDE_CODE_SUBAGENT_MODEL — no signal in tool_result or transcript
- [BUG] Opus 4.7 (1M context) severe latency regression starting evening of Apr 24, 2026
- Opus 4.6 quality regression — confident but unverified claims increasing over time
- [BUG] Opus produces garbled multi-script output (Cyrillic/CJK/Tibetan mixed into English), triggers misleading usage policy violation