Model behaviour issues on VS Code — page 3
Issues the maintainers labelled both platform:vscode and area:model.
599 issues · 154 open · 445 resolved (74%) · first seen Feb 26, 2026
Is this getting better or worse?
This class of problem is holding steady. 238 new reports in the last 90 days vs 275 in the 90 before — -13%. The open backlog peaked at 163 in 2026-08 and sits at 154 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
475 of these reports name the Claude Code build they were running, spanning 152 releases. Heaviest reporters:
- Claude Code v2.1.170
- Claude Code v2.1.198
- Claude Code v2.1.263
- Claude Code v2.1.207
- Claude Code v2.1.210
- Claude Code v2.1.278
- Claude Code v2.1.241
- Claude Code v2.1.197
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 36 days across 445 closures. Of the 445 closures with a recorded reason, 8% were closed as completed and 409 as not-planned or duplicate. The most recent completed fix landed in 2026-10.
Workarounds reported by the community
47 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 - Opus 4.7 thinking summaries not rendered (VSCode extension 2.1.112)
- …ith a capability table), but the suffix variant is missing: Workaround None found that works — the filter strips 4.6 at a later stage, so a byte-level rename of → (length-preserving) has no effect. Users on 4.7[1m] lose…
Found in the description of #49902 · still open - Claude Code changed default model to 1M context without notifying Pro users
- …overnight. I lost hours trying to debug the issue, applying workarounds (environment variables, settings.json), and ultimately had to downgrade to a smaller context model — losing functionality I was already using and pa…
Found in the description of #62199 · still open - [BUG] Server-side experiment (`x-cc-atis`) silently removed Opus 4.8 thinking summaries, and the CLI silently self-updated even with `autoUpdates: false`. No notice, no opt-in, settings silently overridden.
- …de gap, posted the analysis ( and built and shared a public workaround so other affected users could get summaries back: a launcher that injects , the one lever that is not interactivity-gated, plus an extension patch an…
Found in the description of #75607 · still open - [MODEL] Opus 4.8 starts hallucinating results before parallel tasks finish
- …e upstream fix is unknown) 1. is the only durable user-side workaround for both hazards, per longitudinal data in [ 62123 comment 4569840435]( (4.6 clean → 4.7 onset → 4.8 worst, including 1M context). @timmywheels named…
Found in the thread of #63884 · still open
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 201–300
Ranked by community engagement (reactions weighted over comments). Listing the top 300 of 599 matches; the statistics above cover all 599.
- [Bug] Anthropic API Error: Model refuses continuation with AUP message in valid session
- [Bug] Anthropic API Error: Account flagged by safeguards, CVP review pending
- [Bug] Anthropic API Error: Safety filter blocks legitimate code generation requests
- [Bug] Model behavior degradation: Poor task planning and requirement adherence
- [Bug] Models ignoring claude.md configuration directives across versions
- [Bug] CVP Safety Filter False Positive with Active Exemption
- Repeated hard-stop "API Error: Sonnet 5 can't help with this. Start a new session to continue" errors
- [Bug] Tool Integration Flagging Safety Guardrails
- [Bug] Fable model not available in Claude Code
- Agent invents new deliverables instead of following the user's defined workflow step, then repairs its invention through repeated corrections
- I don't have a bug report to analyze in your message. Please provide the actual bug report or issue description you'd like me to create a GitHub issue title for.
- Opus 4.8: thinking blocks emitted with empty text — unexpandable Thinking UI in VSCode
- [Bug] Fable 5 safeguard incorrectly flags benign parser conversation messages
- [Bug] Session summary request fails during website development workflow
- [Bug] Unclear error message for unsupported or restricted operations
- [Bug] Incorrect Content Policy Flag on Safe Development Code
- [Bug] Excessive token consumption on small projects with incomplete analysis
- [Bug] Claude Code enters infinite loop with repeated false positive "fix is in" declarations and excessive processing delays
- [Bug] Model unexpectedly downgraded from Claude 3.5 Sonnet to Claude 3 Opus
- Fable 5's safeguards flagged this message...
- [Bug] Federated learning security research incorrectly flagged as cybersecurity work
- [Feature Request] Add model selection prompt for Fable subagent creation
- Assistant messages intended for the user are emitted as (encrypted) thinking blocks during tool loops — user sees only 'Thought for Ns', content unrecoverable
- [Bug] Legitimate request incorrectly flagged as security violation
- [MODEL] Any
- [Bug] Fable 5 model unsupported for design and organization tasks
- Model behavior: agent substitutes easier implementations for explicit specs, makes unverified 'done' claims, games user-defined enforcement hooks (7-day pattern)
- Sessions rerouted from pinned claude-fable-5[1m] to Opus 4.8
- [Bug] Web scraping tool calls flagged as security violation for public data
- [Bug] False positive completion status reported for active task
- [Bug] Model unexpectedly switched to Opus during multi-page HTML refactoring task
- [Bug] Security safeguards incorrectly flag defensive vulnerability analysis as offensive content
- [BUG] Fable 5 safety classifier flags UI/frontend work — trigger appears to be project files in context, not prompts
- [Feature Request] Add security study mode to distinguish legitimate cybersecurity learning from malicious activity
- [BUG] Fable 5 safeguards over-flag routine health/biology work and reroute mid-turn
- [Bug] Model unexpectedly switched from Claude Fable to Claude Opus
- [Bug] Silent model substitution to non-selected model despite Max plan subscription
- [Bug] Silent model downgrade mid-session without user notification
- [Feature Request] Support for authorized web security testing workflows
- [Feature Request] Allow overridable safety filters for academic research on emergent capabilities of sorting algorithms
- [Bug] Incorrect Content Policy Flag on Process Design Translation Task
- [Bug] Safeguard triggered for skeleton medical app scaffold code
- [Bug] Claude Code blocks security hardening on user-owned projects
- [BUG] Model committed with no user request, then quoted a confabulated commit-request message (absent from session JSONL)
- [Bug] Inappropriate Content Filter Blocking Valid Research Discussion
- [Bug] Incorrect task classification for biology and cybersecurity tasks
- [BUG]
- [Bug Report] Insufficient error details provided for diagnosis
- [BUG] Session falls back from Fable 5 to Opus 4.8 mid-task with no way to opt out
- [Bug] 1Password Integration: Inconsistent Reference Handling and Vault Access Management
- [Bug] Merge conflict resolution overwrites non-conflicted files causing silent feature loss
- [Bug] Claude Code LLM functions perform below expected capability level despite adequate context provided
- [Bug] Model behavior degradation or unexpected responses
- [Bug] Multiple instances of task hallucinations and incorrect completion reporting
- [FEATURE] Allow downgrade to previous version when current model has problems
- [BUG] Creating zip file in windows for linux
- [BUG] Claude offers/accepts pasting secrets (API keys, tokens, passwords) directly into chat with no upfront warning
- [Bug] Claude refusing explicit user requests with "no I can't do it" responses
- honesty across platforms
- claude-sonnet-4-6
- [Bug] Agent stuck in repetitive loop on multi-criteria optimization tasks
- [Bug] CLI fails to run tests when 2FA authentication is required
- [Bug] Intent Classifier Misclassification: UI Layout Task Incorrectly Categorized as Biology/Cybersecurity
- [MODEL] Fable: grounding discipline in directed synthesis appears regressed vs Opus 4.8 on the same workflow
- [Bug] Misleading downgrade notification displayed despite no model downgrade occurring
- [Bug] Model defaulting to Opus when fable configuration intended
- [Bug] Agent commits changes prematurely without waiting for user revision
- Third-party Polish text leaked into assistant response mid-stream (possible cross-request contamination)
- [Bug] Anthropic API Error: Usage Policy Violation blocking all requests
- [Bug] Safety Filters Over-Flagging Legitimate Content on Claude Code Operations
- [Bug] Anthropic API Error: Policy Violation on Legitimate Security Operations
- [Bug] Model unexpectedly switches to Claude Opus 4 during execution mid-task. Should give option to stop task instead of switching models.
- [Bug Report] Unable to generate issue title - no bug report content provided
- [Bug] Model reverts to Opus unexpectedly during code review
- [Bug] Safety filters incorrectly flagging valid code as unsafe
- [Bug Report] Unable to process empty bug report
- [Bug] Anthropic API Error: Overly Restrictive Content Policy Blocking Legitimate Username Collision Detection
- False positive: implementing authentication for one's own app flagged as a security concern
- [BUG]
- I don't have any bug report content to generate a GitHub issue title from. Please provide the bug report or issue description, and I'll create an appropriate technical title for you.
- [Bug] Anthropic API Error: Security Policy Violation on Legitimate Code Project
- Opus 4.8 in Claude Code: deflects bugs to external systems, band-aids instead of root-causing, over-steers the user, ignores stored rules
- [Bug] Claude Code incorrectly flags sanitized synthetic healthcare data as PHI
- [BUG] https://github.com/anthropics/claude-code/issues
- [Bug] Excessive verbosity in unprompted detailed responses
- [Bug] Claude Code not respecting user-defined rules and constraints inconsistently
- [Feature Request] Allow Claude Code to access and retrieve credentials
- [BUG] Sonnet repeated violated explicit guidelines about commands not to execute
- [BUG] Max plan requires Usage Credits balance for 1M context — should be included
- [Bug] Anthropic API: Opus 4.7/4.8 Missing Tool Use Block with tool_use Stop Reason
- [Bug] Claude Code API response latency degradation
- [MODEL]
- [Feature Request] Implement proactive unit test coverage recommendations for recurring bugs
- [BUG] False positive safety filter block for Polish-language security audit question in own PHP CRM project (VSCode extension)
- Claude fails to execute session-start protocol defined in CLAUDE.md
- [BUG] Model suffix [1m] in settings.json ignored — context window capped at 200k instead of 1M
- [Feature Request] Improve proactive suggestion of alternative methods and best practices
- [BUG] Constant lying- when WILL IT END!!??
- [BUG] Opus 4.7 standard unavailable in VS Code extension
- [Bug] Claude ignores explicit instructions to avoid shortcuts despite custom hooks and memory configuration