The API layer issues on Linux
Issues the maintainers labelled both platform:linux and area:api.
354 issues · 18 open · 336 resolved (95%) · first seen May 7, 2025
Is this getting better or worse?
This class of problem is converging. 26 new reports in the last 90 days vs 47 in the 90 before — -45%. The open backlog peaked at 85 in 2025-12 and sits at 18 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
141 of these reports name the Claude Code build they were running, spanning 65 releases. Heaviest reporters:
- Claude Code v2.1.29
- Claude Code v2.1.19
- Claude Code v2.0.76
- Claude Code v2.1.37
- Claude Code v2.1.104
- Claude Code v2.1.109
- Claude Code v2.1.38
- Claude Code v2.1.17
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 30 days across 336 closures. Of the 336 closures with a recorded reason, 33% were closed as completed and 226 as not-planned or duplicate. The most recent completed fix landed in 2026-08.
Workarounds reported by the community
51 of these issues post a workaround someone says worked. The highest-engagement ones:
- [BUG] Oversized image breaks conversation permanently - no way to recover without starting new chat
- …retry without failed images, or client-side image resizing Workaround Currently, users must start a new conversation and manually reconstruct any important context.
Found in the description of #13480 · resolved - [BUG] No Response From API 2.1.181, 2.1.183 (constantly)
- …-URL clients. Filed 69759 with the gateway-specific detail. Workaround that's holding for us: pin to 2.1.179 + so the background updater doesn't re-bump past it.
Found in the thread of #69358 · resolved - Claude Code: constantly seeing 'API Error (Request timed out...)' - Retrying in .. seconds.. (attempt x/10)'
- …tep tasks, which can exceed the default API timeout limits. As a workaround, you can increase the API timeout by setting the API TIMEOUT MS environment variable before launching Claude Code. For example, you can use the…
Found in the thread of #2728 · resolved - [BUG] max_tokens must be greater than thinking.budget_tokens
- workaround is possible by editing settings.json (in my case in ~/.claude/settings.json), by setting the "alwaysThinkingEnabled" to false.
Found in the thread of #8756 · still open - API Error 400: thinking blocks order error on first tool use after clean install
- Another workaround is to use agents, it seems they are not affected by the bug.. It seems only the main claude get the error after using tools.
Found in the thread of #20692 · 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 354 matches; the statistics above cover all 354.
- [BUG] Oversized image breaks conversation permanently - no way to recover without starting new chat
- [BUG] No Response From API 2.1.181, 2.1.183 (constantly)
- Claude Code: constantly seeing 'API Error (Request timed out...)' - Retrying in .. seconds.. (attempt x/10)'
- [BUG] max_tokens must be greater than thinking.budget_tokens
- API Error 400: thinking blocks order error on first tool use after clean install
- [BUG] Freshly installed Claude Code ignores settings.json
- [BUG] Session broken -> API Error: 400 {"type":"error","error":{"type":"invalid_request_error","message":"The request body is not valid JSON: no low surrogate in string: line 1 column 410559 (char 410558)"}}
- [BUG] API Error: "invalid_request_error" "The request body is not valid JSON"
- Long Context Beta Not Available for Current Subscription
- API Request Failures: Persistent 529 Overloaded Errors
- [BUG] API Error: Connection closed mid-response — occurs immediately in new context window
- [BUG] API Error: 500
- Invalid API Model Name in Request
- [BUG] CLAUDE_CODE_MAX_OUTPUT_TOKENS has no effect on Opus 4.6 — output stays capped at 32000
- [Bug] Anthropic API Error: 500 Server Overload
- [Bug] Anthropic API Error: Long context beta unavailable for Max plan with Claude Opus 4.6 1M
- [BUG] Inconsistent and Undisclosed Quota Accounting Changes in Claude Max Plan. Legal liability claim ready.
- @anthropic-ai/claude-code SDK fails with "spawn node ENOENT" in Docker containers despite working CLI
- [BUG] /usage shows 47% weekly used in 3 hours of Opus. Max plan.. should be 40 hours per week
- [BUG] CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS doesn't remove ?beta=true query params and anthropic-beta headers
- [Bug] Anthropic API Error: 500 Overloaded Service Unavailable
- [BUG] undefined is not an object (evaluating '$.input_tokens')
- [BUG] Rate limit errors triggered by unthrottled keystroke API calls in Claude Code Web interface
- Bug Report: Path Patterns in allowedTools Not Honored in Non-Interactive Mode
- [BUG] Interrupting session during tool calls permanently corrupts conversation with tool_use/tool_result API errors
- [Bug] Anthropic API Error: Invalid tool_result block without corresponding tool_use
- User interrupt during streaming can freeze whitespace-only text block into history, causing persistent 400 errors
- API Error (Internet connection is unreliable)
- Claude Code CLI Unusable: APIErrorterminated + Offline Flickering + Extreme Execution Delays
- [Bug] API Error 400 - Tool Use Concurrency Issues - Widespread Regression Affecting All Platforms
- [BUG] Task tool `model` parameter returns 404 - Blocks cost-optimized workflows (10-30x unnecessary spending)
- [BUG] `ANTHROPIC_BASE_URL` ignored during setup
- [Bug] Anthropic API Error: Request Timed Out
- [Bug] Anthropic API Error: Assistant message thinking block must be first
- Bug Report
- Claude Code crashes when reading large PDF files - tool_use/tool_result block mismatch
- [Bug] Environment Variable CLAUDE_CODE_MAX_OUTPUT_TOKENS Not Respected
- [Bug] SSE stream stalls in long-running sessions without message_stop event
- [BUG] Literal "HERMES.md" in git commit messages triggers 400 "out of extra usage" on Max OAuth (content filter false-positive misclassified as quota error)
- [BUG] Extremely slow thinking/response time on WSL2 - works fine on native Linux
- [BUG] API timeout retry regression in 1.0.8
- API stream hangs mid-response on complex generation tasks (all models: Opus, Sonnet, Haiku)
- [Bug] Intermittent "No response from API" errors on Linux requiring automatic retry
- [BUG] NO_PROXY stopped working in 2.1.23
- Systematic Service Failures - $440 Refund Request After Month of Critical Bugs (WSL2)
- API Request Failure: Overloaded Service (Error 529)
- [BUG] Usage is consumed just by opening Claude Code without sending any prompt
- [BUG] It seems Digital Ocean IPs cannot access Claude Code atm
- Compaction fails with 400 error when thinking blocks present in assistant message
- [BUG] SDK (TypeScript at least) fails to invoke hooks
- Despite thinking being enabled, I can not run slash-commands due to clear_thinking_20251015 strategy
- Connection Timeout: Persistent API Request Failure After 10 Retry Attempts
- [BUG] Constant API Error and request timeouts
- [BUG] Conversation Compaction Corrupts Tool Use/Result Pairs
- [BUG][Typescript SDK] `canUseTool` callback in the Claude Code SDK is not working
- OpenAI API: Unexpected Opus 4 Availability Restriction in Pro Plan
- [BUG] Claude Code Pro API Error: Rate limit reached on brand new Pro account with 0-2% usage
- API Error 500 - Internal server error on every request
- [BUG] Streaming output tokens are incomplete in session.jsonl compared to /cost
- [BUG] Verified Evidence: Claude Code Delivers 10% of Requested Thinking Budget While Charging Full Price
- [BUG] API Error (Request timed out) in Remote SSH Dev Container on Linux Host
- Error compacting conversation Context left until auto-compact: 0%
- [BUG] Parallel Claude Code sessions started right after 5-hour limit resets — first 3–4 work, the rest fail with "Server is temporarily limiting requests (not your usage limit) · Rate limited"
- [Bug] Anthropic API Error: 500 Internal Server Error
- [BUG] How is this possible to be at 62% opus for a week when using for few hours with 5 code files - Max Plan 20x
- [BUG] [Bug] Anthropic API Error: Persistent 500 Internal Server Error across all models
- [BUG] settings.json Proxy Configuration Doesn't Work for Claude (But CLI Does)
- [BUG] Conversations that have errors during chat title generation (i.e., what the chat is about) don't appear in --resume list
- [Bug] No assistant message found in API response
- [BUG] Permissions Issue
- [BUG] API Error 500
- Claude code cli all models are down - it is happening more...
- [BUG] API Error: 500
- [BUG] Statusline API used_percentage significantly underreports context usage
- [Bug] Anthropic API Error: Opus model inaccessible from Claude Code despite Team plan access
- [BUG] Session halts after receiving 400 API error (Output blocked by content filtering policy)
- API Error: 500
- : Getting API Error: 500, I am completly dead in the water
- [Bug] Anthropic API Error: Internal server error (500)
- [BUG] ⎿ API Error (Request timed out.) · Retrying in 1 seconds… (attempt 1/10)
- [FEATURE] Programmatic artifact share-with-org + delete from headless/server CLI sessions
- OAuth Authentication Broken in WSL2 - Cannot Login or Use API
- [BUG] @agent-explore "Out of Credits" on $100 Max Plan
- [Bug] Anthropic API Error: Server Overloaded (500)
- [BUG] claude with model sonnet[1m] doesn't accept single messages > 200.000 tokens
- Internal Server Error in API Request Processing
- [BUG] API Error 404 / ECONNREFUSED
- [Bug] Anthropic API Error: Concurrent Tool Use Causing 400 Bad Request
- Usage Quota Not Resetting at Scheduled Time for Max Customer
- [BUG]
- Bug Report all messages must have non-empty content except for the optional final assistant message
- [BUG] Claude breaks when interrupted while using certain tools
- [Bug] Anthropic API Error: 500 Internal Server Error should auto-recover
- False positive Usage Policy violation on scientific chemistry codebase
- [BUG] Extreme latency (60-96 seconds) for trivial queries on Max $200/month subscription
- [BUG] --agent Flag Not Working for Non Interactive (Affects SDK)
- [Bug] /context command fails with: Anthropic API Error: Invalid message format with thinking blocks and tool use
- [BUG] Improper Flagging of Usage Policy Violation
- [Bug] Anthropic API Error: Unexpected Usage Policy Violation During Web Development Task
- [BUG] API Error: Unexpected value(s) `interleaved-thinking-2025-05-14` for the `anthropic-beta` header. when using via Vertex AI