Context window & memory limits
Context-length overflows, compaction issues, and heap/out-of-memory crashes.
6822 related issues · 851 open · 5971 resolved · peaked at 912 open (2026-08)
Backlog trend over time
The line shows how many issues in this topic were open at the end of each month, derived by
counting each issue from its creation date until it was closed. First-party data from the
anthropics/claude-code tracker.
All context window & memory limits issues
Ranked by community engagement (reactions and comments).
- Allow MCP tools to be available only to subagent
- CC v2.1.100+ inflates cache_creation by ~20K tokens vs v2.1.98 — same payload, server-side
- [BUG] [URGENT!!!] Claude Code is hanging / freezing / stuck on heaps of prompts for 5-20minutes or more.
- [BUG] Pro Max 5x Quota Exhausted in 1.5 Hours Despite Moderate Usage
- [FEATURE] VSCode Extension: Display context usage percentage in UI
- [FEATURE] Allow setting plan naming scheme per-repo
- [Feature Request] Claude Desktop: Option to execute commands in WSL instead of Windows
- Feature Request: Enable 1M Context Window for Claude Code
- Claude.ai MCP servers auto-injected into Claude Code without opt-in — causes OOM crashes on resource-constrained systems
- Messages disappear from terminal display during conversation after v2.1.89 update
- [BUG] Error during compaction
- [FEATURE] Allow slash command usage over remote-control
- [Feature Request] Enhanced /compact with file-backed summaries and selective restoration
- [BUG] Auto-compact not triggering on Claude.ai (web & desktop) despite being marked as fixed
- [BUG] CLI output formatting artifacts break copy/paste - workarounds waste tokens
- [BUG] Critical memory regression in 2.1.27 - OOM crash on simple input
- [FEATURE] Auto-continue after subscription rate limit resets
- Claude Code Memory Leak - Process Grows to 120+ GB RAM and Gets OOM Killed
- [BUG] No working mechanism to review previous context after compaction, plan-mode clear, or branch navigation — data preserved but UI inaccessible
- Slash commands not supported in /remote-control UI
- [BUG] Extremely rapid token consumption. There appears to be a critical issue with token calculation and quota management. Users, including myself, are experiencing an unusually high rate of token consumption
- Critical Memory Leak: Claude Code Consumed 129GB RAM and Caused System Freeze
- [FEATURE] Add status bar to Desktop App
- Sibling tool call errored: parallel tool calls cascade-fail when one fails
- Feature request: Native Zellij support as alternative to tmux for Agent Teams and /terminal-setup
- [Feature Request] Add 'claude model list' CLI command for non-interactive model queries
- [BUG] Claude Code defaults to 1M context on fresh session with no workaround on Pro plan
- [BUG] Abnormal / inflated rate limit / session usage
- Expose rate limit usage (session %, weekly %) to statusLine configuration
- [FEATURE] Add user-configurable keyboard shortcut actions
- Feature Request: CLI Commands for MCP Server Enable/Disable (Hook Automation Support)
- [Bug] Potential session/cache leakage between workspace instances or consumer accounts
- [FEATURE] PostCompact Hook Event and Compaction Content Control
- [BUG] Scheduled tasks cannot access MCP connectors until a user message warms the session
- [FEATURE] Smart Session Rename
- Recurring crashes: JavaScript Heap Out of Memory while 'thinking'
- [BUG] Fable 5 prompts 'usage credits required' on Max plan from 2026-07-20, the day it became standard on Max (saved model claude-fable-5[1m])
- [FEATURE] Add --no-auto-compact command switch to Disable the auto-compaction
- [BUG] resume flag fails to maintain conversation context after hitting usage/context limits
- [Bug] Auto-Compact Erases Entire Chat History Without Warning
- [BUG] Statusline context_window JSON contains cumulative tokens instead of current context usage
- [FEATURE] Skill invocation tracking and usage analytics
- [BUG] Conversation compaction intermittently corrupts conversation state: “Compaction failed unexpectedly” and silent prompt submission failures
- [CRITICAL] Context auto-compact stuck at 0% - Tool Unusable
- [BUG] API Error: 500 {"type":"error","error":{"type":"api_error","message":"Internal server error"}}
- [BUG] Cowork (Not Claude Code) 1M context window unavailable on Max 5x — regression from March 20
- Feature Request: Persistent Memory Across Context Compactions (59 compactions, built our own)
- [FEATURE] VSCode extension auto-includes opened files as context — should be opt-in by default
- [BUG] Error loop between 'context low' and '/compact'
- [BUG] Latest version aggressively hides all previous output during active session
- [BUG] Memory leak in long-running idle Claude Code sessions
- [FEATURE] Expose token usage and cost data in hook inputs
- Feature: Enter/resume existing worktrees, configurable branch naming, hook removal control
- Allow curl
- Add dynamic loading/unloading of MCP servers during active sessions
- [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
- [Bug] Plan mode resurfaces old plans after session compaction with Claude 4.5 Opus
- [FEATURE] Expose rate limit/session usage data to statusLine configuration
- [BUG] 2.1.286 idle compaction silently discards working context in long-running sessions; no opt-out, logged as "manual"
- [Bug] Anthropic API Error: Usage credits required for 1M context window with opus-plan model
- [BUG] [1M] Sonnet 1M context window disappeared after Claude Code update to v2.1.45 — regression on Max plan ($200/mo)
- [Bug] /context command reports 200K max for Claude Opus 4.6 instead of 1M
- [BUG] Claude forgets everything in CLAUDE.md after compaction
- [BUG] Edit tool silently converts tabs to spaces, causing repeated match failures on tab-indented files
- [BUG] claude starts and 3 seconds later exits.
- [FEATURE] Support slash commands (/clear, /compact) from Channels (Telegram/Discord)
- [BUG] "Request too large (max 20MB)" error on small files (99KB PNG)
- /compact fails with 'Conversation too long' when context limit is reached
- Subagents fail with 'prompt is too long' when user has many MCP servers (tool definitions exceed 200k)
- Rename the conversation
- [CRITICAL] Subagent spawning and subagent pattern bugs trigger infinite recursion, infinite token usage, grossly inefficient token usage, and lost accumulated subagent work.
- [BUG] VS Code Extension has an incomplete slash command list compared to the CLI version
- Both /compact command and auto-compaction broken - 'conversation too long' error
- [BUG] Extreme token consumption — quota depleted in minutes with normal usage
- [Bug] Auto-compact never triggers despite statusline reporting "100% context used" (v2.1.153, Max sub, 200K mode)
- [FEATURE] Provide way to exclude parent CLAUDE.md files from auto-loading in subdirectories
- [FEATURE] Claude-invocable conditional /compact for automated workflows
- Feature request: auto-compact on idle timeout to prevent cache expiry cost
- Opus 4.6 (1M context) hits 'API Error: Rate limit reached' on Max subscription
- Feature request: Session persistence & reconnection for Remote Control server mode
- Fable 5 model behavior: 16 min of silent tool calls, then AskUserQuestion about never-shared findings during incident response
- [Feature Request] Subagents should inherit parent agent context to avoid redundant codebase scanning
- Feature Request: Add Context Pruning as Alternative to Compacting
- Add --max-context flag to cap context window usage
- [BUG] Auto compact does not trigger at 100% context window and Claude Code stops itself on cli
- Sonnet 4.6 1M context unavailable on Max 20x plan - only Opus 1M appears in /model
- [Feature Request] Session Checkpointing and Branching
- [BUG] API Error: Connection closed mid-response — occurs immediately in new context window
- [BUG] Context limit reached · /compact or /clear to continue
- [FEATURE] Add support for 1M Context on Claude Sonnet 4.5
- Feature Request: Restore Time & Token Indicators + Add Context Usage Display
- [BUG] Skill `model:` frontmatter triggers 429 "Extra usage required" on 2.1.76 when session uses opus[1m]
- [FEATURE] Allow Claude to self-initiate context compaction
- [BUG] Conversation compaction intermittently fails or deadlocks chats (claude.ai web/mobile, post–Jan 15 regression)
- JSON Parsing Error: Invalid Low Surrogate in Request Body
- Feature Request: Runtime MCP Server Toggle
- [BUG] No postCompact hook
- Opus 4.6 shows 200K context instead of 1M on Claude Max plan (v2.1.75)
- [BUG] Claude Code consistently degrades in performance over long sessions
- API Request Failures: Persistent 529 Overloaded Errors
- [BUG] /rate-limit-options command repeatedly auto-executes after session reset, causing excessive token consumption
- Feature Request: 1M Context with Max Plans in CC
- [BUG] Terminal laggy scrolling and jumping with long history
- Cowork: Context compaction permanently removes scrollable conversation history from UI
- Skills consume full token count at startup instead of progressive disclosure (frontmatter only)
- SessionStart hooks not working for new conversations
- [Feature Request] Expose how much context is left before auto-compact
- [BUG] /compact causes Claude Code to ignore CLAUDE.md
- [FEATURE] Tool result transform hook for content sanitization
- Feature Request: Show active skill in status line
- [BUG] Keep hitting "Request size exceeds model context window"
- Opus 4.6 comprehensive regression: loops, memory loss, ignored instructions - daily professional user report
- [FEATURE] Bring 1M context window to Max plan subscribers
- Model fabricates tool output (and even a user instruction) when a parallel batch is partially cancelled / appears empty
- [BUG] Opus 4.6 with [1m] context window returns "long context beta not available" on Max subscription
- [BUG] slash command auto-complete is broken (highlighted command doesn't match what I'm typing)
- A session cannot determine whether its auto-memory index loaded whole, truncated, or not at all
- Prompt bar UI bug in v2.1.23: text disappears, lines compact
- [BUG] Token Limit Hard-Stop Without Warning or Auto-Compaction
- [BUG] Turning auto-compact OFF won't allow to continue until you fill the 200K tokens window anymore (it worked before).
- Anthropic API 529 Overloaded Error During Compaction Process
- [FEATURE] Indexed transcript references in compaction summaries for surgical context recovery
- [FEATURE] Expose Agent Context in Hook Event Payloads for Multi-Agent Observability
- Include effort level in statusLine hook input
- [FEATURE] Claude clear context for itself
- [BUG] Terminal clears frequently and for no reason, hiding conversation history
- [FEATURE] Claude Desktop - Archive individual conversations from the sidebar
- Expose token usage data to statusline scripts
- Chat Branching: Spawn side-chain conversations with selective merging back to main
- [BUG] Compact Conversation Infinite Loop
- Desktop app: bring back the context-usage indicator (or make the footer widget configurable)
- [FEATURE] Add setting to configure default option in plan mode approval dialog
- [Bug] /compact and auto-compact fail with 'Tool names must be unique' when MCP servers are configured
- [BUG] Agent-team teammate pane crashes with "<Box> can't be nested inside <Text>" when ※ recap renders inline markdown code spans
- Rewind history lost after compaction in sessions with many rewinds (branching tree)
- [BUG]
- Feature Request: Pro Plan 5-Hour Window Usage Visibility
- [BUG] Silent context degradation — tool results cleared without notification on 1M context sessions this issue documents three separate mechanisms (microcompact, cached microcompact, session memory compact)
- [Feature Request] Configurable autocompact context %
- [A11y feature request] Built-in option to speak Claude's responses aloud
- [BUG] Prompt is too long (Claude for VS Code)
- [BUG] API Error: 400. Each `tool_use` block must have a corresponding `tool_result` block in the next
- Feature request: make the auto-memory MEMORY.md compaction reminder threshold configurable
- [Bug] Context limit reached with 32k tokens free space and auto-compact disabled
- [BUG] Plan mode broken - "Auto mode is unavailable for your plan" blocks all input
- [BUG] /context command no longer display in chat window on VS Code ext version 2.1.45
- [FEATURE] Ask questions for compaction
- [FEATURE] Configurable Auto-Compact Threshold in VS Code Extension
- [BUG] Appeal Form Redirect Loop After Account Restriction
- VSCode extension v2.1.141: "Unhandled case: [object Object]" banner from assertNever on unknown streaming-event types
- Opus 1M context on Max plan requires extra usage despite docs saying 'included with subscription'
- [BUG] Claude Desktop Drops/Reverts Long Multi-Step Tasks Without Warning
- Context low warning and /compact failure despite having 86% free context space
- [PROPOSAL] Expose compact/session lifecycle hooks for external memory layers
- Fable 5 → API-only: please reconsider a subscription path (👍 + comment here if it affects you)
- [FEATURE] Add /fork (conversation branching) support to VS Code extension
- [Bug] File loading adds 70% token overhead due to line number formatting
- [BUG] CLAUDE.md instructions completely ignored after context compaction
- VS Code extension: add a verbose toggle equivalent to CLI Ctrl+O
- Compaction fails with 'Conversation too long' at 48% context usage (Opus 4.6)
- [FEATURE] Expose /usage and /context data in statusLine JSON
- Add a setting option to force re-reading of CLAUDE.md after /compact
- Terminal scrollback wiped during session (alternate screen buffer cleared on redraw)
- [BUG] API Error: Rate limit reached incorrect in CLI
- Feature Request: Expose rate limit data in statusline JSON input
- Explore agent always fails with "Prompt is too long" when many MCP tools are connected
- Feature: Expose session ID as $CLAUDE_SESSION_ID environment variable
- Compaction Failure: Conversation Length Exceeds Limit
- [FEATURE] UserInputChange hook — expose the prompt input buffer to hooks, mirroring MessageDisplay
- Feature Request: Expose Max/Pro plan usage limits for status line display
- [BUG] Context percentage mismatch between /context, statusline API, and internal limit trigger
- [Feature Request] Include actual context window usage in statusline JSON
- Auto-compact fails with Opus 4.5 extended thinking blocks
- API Error: Stream idle timeout - partial response received
- [BUG] Context window defaulting back to 200k
- [BUG] 1M context window removed from Desktop Code tab model picker after v1.1.7714 update on Max plan
- [BUG] Instant auto-compaction not instant - compaction takes same time as before v2.0.64
- Feature: Long-context (≈1M) support for Claude Sonnet 4 in Claude Code
- Opus 4.8 intermittently emits malformed tool calls: stray `count`/`call` token, then tool call without `antml:` prefix rendered as plain text
- Max plan: 1M context window shows 200k, Remote Control unavailable
- [BUG] Claude Desktop: Send button silently fails - message disappears when context is high
- Feature Request: Add PreCompact and PostCompact hooks for custom context management
- [Bug] VSCode Extension: User-level rules (~/.claude/rules/) not loading into context
- Feature request: per-agent auto-compact window (separate boundaries for coordinator session vs subagents)
- Remote Control regression: server-injected `<system-reminder>Message sent at …>` prefix breaks slash commands from mobile/web
- Agent team lost when lead's context gets compacted during long session
- [Bug] Anthropic API Error: Usage credits required for 1M context window
- [BUG] Session name lost after context compaction
- Session permanently stuck on 'Rate limit reached' after transient rate limit
- Compaction clears screen - can't scroll up to see previous context
- [Bug] Manual Compaction Fails with "Conversation Too Long" Error
- [BUG] workings with agents makes the terminal super slow and hangs often
- [BUG] Desktop app: context-window usage no longer shown anywhere — ring and usage popover list only plan windows
- [Bug] System events delivered as user-role messages cause model to fabricate user consent and act on it
- [FEATURE] Visible context window usage indicator in Cowork
- [Feature] Subagent's TaskOutput should return final result text, not full JSONL log
- [Bug] Compaction Fails Unexpectedly with "Conversation Too Long" Error
- [Feature Request] Migrate Claude Code to Toad Terminal UI Framework
- New Hook suggestion: PostCompact
- [BUG] Auto compact off, but asking me to compact before 100% context usage