Model behaviour issues on VS Code
Issues the maintainers labelled both platform:vscode and area:model.
463 issues · 168 open · 295 resolved (64%) · first seen Feb 26, 2026
Is this getting better or worse?
This class of problem is still growing. 286 new reports in the last 90 days vs 170 in the 90 before — +68%. The open backlog peaked at 168 in 2026-08 and sits at 168 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
355 of these reports name the Claude Code build they were running, spanning 120 releases. Heaviest reporters:
- Claude Code v2.1.170
- Claude Code v2.1.198
- Claude Code v2.1.207
- Claude Code v2.1.210
- Claude Code v2.1.197
- Claude Code v2.1.158
- Claude Code v2.1.239
- Claude Code v2.1.235
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 295 closures. Of the 295 closures with a recorded reason, 10% were closed as completed and 265 as not-planned or duplicate. The most recent completed fix landed in 2026-08.
Workarounds reported by the community
37 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 1–100
Ranked by community engagement (reactions weighted over comments). Listing the top 300 of 463 matches; the statistics above cover all 463.
- [Bug] Anthropic API Error: Model's tool call could not be parsed (retry also failed)
- Opus 4.7 thinking summaries not rendered (VSCode extension 2.1.112)
- Claude Code changed default model to 1M context without notifying Pro users
- CLAUDE.md hard rules and persistent memory instructions consistently ignored — violations escalate with each session despite repeated explicit reinforcement
- [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.
- [BUG] VS Code extension blocks Fable 5 with "requires usage credits" while account has 20% of weekly Fable allowance remaining (Max plan)
- [BUG] Tool-use markup generated as "court" instead of "antml:invoke" (malformed/parse error, tool not executed)
- [MODEL] Opus 4.8 starts hallucinating results before parallel tasks finish
- [BUG] 400 "output_config.effort 'xhigh' is not supported when thinking is disabled" on Opus 4.8 despite alwaysThinkingEnabled: true (VS Code, 2.1.205–2.1.207)
- Opus 4.8 returns empty thinking blocks — no thinking shown in chat (same regression as Opus 4.7 #49268)
- [BUG] Opus 4.7 thinking renders empty/unexpandable stub in VS Code extension
- [Bug] Fable 5 incorrectly requires usage credits on Max 20x plan despite available weekly allowance
- [BUG] Usage credits required for 1M context - Pro plan blocked despite 17% usage
- [Bug] Tool-use block markup intermittently corrupted with stray token prefix
- Opus model quality regression — significant degradation starting ~April 15, 2026
- [Bug] Fable 5 writes user-facing output into hidden thinking instead of a text block — same as #66112, fixed for Opus but still reproduces on Fable
- [BUG] Claude code quality (Opus 4.6) has degraded
- [BUG] Claude Code for VSCode don't loading models list
- Doing useless tool call wasting token
- [BUG] In VSCode extension, is model switching via /model isolated per chat session? Seems like it might not be.
- Claude Code VS Code extension forces 1M context on Pro plan - Windows
- VS Code extension ignores project-level model setting
- [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] Opus 4.8 missing from /model picker in CLI and VS Code extension
- Language instruction ignored: Claude responds in Japanese despite explicit Traditional Chinese requirement in CLAUDE.md
- [Bug] Extended thinking hangs indefinitely, consuming all tokens without returning results
- [BUG] Fable 5 advisor silently disabled by its own safety classifier — no Opus fallback, generic "unavailable", sticky-off for the session
- [Bug] Claude 4.8 model stuck in infinite loop executing spurious bash commands
- Claude Code ignores CLAUDE.md/memory, and suspected Opus 4.7 capability regression requiring excessive token usage
- [BUG] [VS Code Sidebar] Fable 5 doesn't show text responses in chat
- [BUG] False positive usage policy violation on computational biology research content
- [BUG] Switching to mimo-v2.5-pro fails after reading images in mimo-v2.5
- [Bug] Opus 4.8 responses not displayed after tool use — quota consumed with no output
- [BUG] Claude Model Missmatch
- [Regression] Opus 4.7 delivers worse quality at higher token cost vs 4.6 for production coding workloads
- Claude Opus - Poor algorithm anticipation and performance in code generation
- Model re-attempts denied tool call after user explicitly says 'no'
- [FEATURE] VS Code extension: no session-only model selection - every picker click persists to settings.json
- Tool calls rendered as raw text and fail to parse with claude-opus-4-8 in VS Code extension
- [Bug] Claude model performance regression: instruction following and task completion degradation
- Opus 4.7: Excessive confirmation friction blocks autonomous workflows — regression vs Sonnet 4.6
- [MODEL] claude-opus-4-8 hallucinated destructive OS commands (rm -rf / del /s /q) as prompt-injection warnings — confirmed clean via JSONL
- [Bug] Anthropic API Error: Content Policy Violation Blocks Code Scanning Analysis
- [Bug]: Fable 5 flags benign greeting ("hi") due to security-related filenames in system-injected git context
- [Bug] Anthropic API Error: Usage credits required for 1M context window
- [BUG] VSCode extension forces 1M context on Sonnet 4.6 for Pro users with no way to opt out**
- [BUG] New version burns through all tokens in minutes, doesn't allow Opus 4.6 use, doesn't allow downgrade.
- [BUG] Claude Code for VS Code: cannot choose Sonnet 4.6
- [BUG] CLAUDE.md file ignored and another.md in sub directory given priority
- Bug Report — claude-sonnet-4-6 — Systematic Behavioral Degradation in Long Sessions
- [BUG] Claude Code for VS Code selects the wrong model, mismatches whats displayed in UI.
- [BUG] VS Code extension: model switching broken since 2.1.86
- Output enters an infinite loop repeating the token "court"
- [BUG] Fable 5 thinking blocks render as empty unclickable stubs in VS Code extension (v2.1.170)
- [BUG] Thinking text empty / "Thought for Xs" not expandable on Opus 4.7+ in VS Code extension — fallback thinking-config branch omits `display`
- [BUG] AUP repeatedly throwing false positives - live issue ongoing - hundreds of similar reports
- Security blocked trying to defend my system!
- Opus 4.7 [1M] at max effort + thinking ON: Severe task quality regression, plus silent downgrade of effort setting mid-session
- [BUG] Global claude.md rules ignores (vscode + claude plugin, macos) All data lost, rule to make backup ignored! I lost two days of my manual work!
- Cost estimation blind spots when building agent systems with Claude Code
- [BUG] claude code is broken, unable to use in vscode
- [Bug] VSCode extension ignores model selection and reverts to Opus despite Sonnet configuration
- [BUG] Opus 4.6 at 1m context actually is Opus 4.5
- [Bug] Claude Code ignores explicit instructions to read source code, proceeds with guessing instead
- Claude fabricates task requirements when tool execution fails silently
- [MODEL] Claude Code is being lazy
- [Bug] I am not able to use the model claude-fable-5
- [BUG] Claude misspells username in working directory path, causing permission prompts
- [Bug] Agent avoids Edit tools causing duplicate calls and rapid context exhaustion
- [Bug] Claude generates fabricated content instead of requesting clarification
- [Bug] Claude Code 4.7 High Token Usage and Context Limitations
- Claude Code repeatedly ignores agreed approaches, hacks instead of reading code, and wastes user time on trivial problems
- Model fails to update all version locations despite explicit checklist in CLAUDE.md
- [BUG] Claude repeatedly executes git commit/push/branch operations despite explicit CLAUDE.md rules forbidding them without user permission
- [MODEL] Opus 4.6 expands scope to unrequested files, cycles through solutions reactively instead of reading codebase
- [MODEL] Opus 4.6 via VSCODE Ext
- [BUG] Model ignores explicit step-by-step confirmation instructions despite re-acknowledgment.
- Claude Code drafts public bug reports containing sensitive project information without anonymising
- [Bug] Credit usage calculation shows inaccurate percentage on Max plan
- [Bug] Fable 5 cybersecurity classifier produces false positives on legitimate infrastructure administration and PDF processing tasks
- [Bug] API Error: Usage credits required for 1M context with standard model selected
- [BUG] False-positive Usage Policy (AUP) violation on benign FPGA/hardware engineering waveform analysis
- [BUG] Constant AUP violation errors when Claude Code reads raw data files (example included)
- [BUG] Claude Code Caused Production Server Outage and Data Loss
- [BUG] Claude did not follow instructions from its MD file multiple times
- [BUG] Excessive unproductive use of credits on simple question
- [BUG] model changes automatically during one task
- [BUG] Edit tool gets stuck targeting wrong file in a loop (path contamination)
- [BUG] Claude Code systematically ignores rules from memory/CLAUDE.md on every edit/write
- Claude Code destroyed gitignored files with unnecessary git clean -fd during branch creation
- Benign coding work was stopped by reasoning_extraction; drafting a follow-up comment to report that event was then refused as cyber
- False-positive reasoning_extraction refusal blocks both benign thinking-summary discussion and incident investigation
- /model: picker checkmark tracks the default instead of the active session override; full model ID silently drops the [1m] suffix
- Claude Code for VSCode is not loading models list [2]
- Claude acts on phantom/hallucinated instructions and defends them with circular reasoning when challenged
- [Bug] Claude ignores CLAUDE.md rules and over-relies on memory, causing stale state issues
- VS Code model picker shows stale model name after selecting default model
- [BUG] own claude said to me when it was terrible and made me lost money, time and reach the limit improperly.
- [Bug] Infinite thinking loop consuming all tokens without tool execution
- [Bug] Claude Opus ignoring documented project context for Docker configuration