The API layer issues on Linux — page 3
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 201–300
Ranked by community engagement (reactions weighted over comments). Listing the top 300 of 354 matches; the statistics above cover all 354.
- [BUG] env variables not taking effect after the first query
- spawn ENOENT when using pathToClaudeCodeExecutable in Docker container
- [Bug] Incorrect model routing: Sonnet being used instead of requested Opus model
- [BUG] Excessive Retry Delays When Fast Model Returns 401 - No Configurable Fallback
- [Bug] Anthropic API: Overly Strict Usage Policy Filtering
- [BUG] in claude sdk (typescript or python or `-p`), MultiEdit failed due to "Cannot read properties of undefined (reading 'map')"
- Invalid API Request: Empty Message Content in Todo List Generation
- Bug Report: Unspecified Issue Requires Further Investigation
- Missing Tool Result Block for Tool Use ID toolu_01YC4iYdsqrqqrUbjyzSutGh
- Invalid Tool Result Block: Missing Corresponding Tool Result for Tool Use ID
- "API Request Failure: Session Invalidated After Subagent Interruption"
- I'll help you generate an appropriate GitHub issue title based on the information provided. Issue Title: "API Request Validation Error: Missing Thinking Block in Message" Rationale: - Focuses on the specific API error encountered - Highlights the key tec
- [Bug] Anthropic API Error: 400 Could not process image
- [Bug] Anthropic API Error: Output blocked by content filtering policy
- Remote-control: Sending image from mobile crashes session with API 400 - missing media_type field
- [BUG] API Error 400 : opusplan, planning works, generating code results in this error
- [Bug] Anthropic API Error: Rate Limit Reached on conversation initialization
- Intermittent API Error 500 during Claude Code sessions
- [Bug] Anthropic API Error: HTTP 500 Internal Server Error
- [Bug] Weekly rate limit discrepancy between Claude Code CLI and dashboard UI
- [BUG] API Error: max_tokens: 250001 > 128000 and thinking.budget_tokens error on Opus 4.6 and Opus 4.5 (Linux)
- [BUG] Task tool model parameter silently ignored for team agents - inherits parent model
- [BUG] False positive Usage Policy violation on legitimate comparative genomics research (Opus)
- [BUG] 400 response (content filter) activated by Chinese pinyin
- [BUG] v2.1.20 breaks Ollama gpt-oss support
- [BUG] I am now getting on any interaction with claude codeAPI Error: 400 {"type":"error","error":{"type":"invalid_request_error","message":"Output blocked by content filtering policy"}
- Very sluggish text input (1000-2000ms per char) , frequent...
- Claude Code CLI crashes during context summarization - "Failed to get summary response from streaming"
- /compact and auto-compact fail with 500 Internal Server Error on Opus 4.5
- [Bug] Anthropic API Error: Cannot modify thinking blocks in assistant message during compaction
- Weekly limit reached · resets 10am (Asia/Seoul) · /upgrade to Max or turn on /extra-usage
- [Feature Request] Add programmatic theme control API and system theme change detection
- [BUG]
- [Bug] Anthropic API Error: Internal Server Error (500)
- [BUG] "invalid_request_error","message":"messages.213.content.0.type: Expected `thinking` or `redacted_thinking`, but found `text`.
- [Feature Request] Add API endpoint for retrieving weekly token usage statistics
- [BUG] REPORT - ERRORE API 400 RICORRENTE
- [Bug] Anthropic API Error: Concurrent Query Blocking
- Bug Report
- Bug Report
- [Bug] Performance Issue: Excessive Resource Consumption Preventing Execution
- Bug Report
- [Bug Report: Unclear User Feedback]
- Bug Report
- [BUG] `/clear` command injects non json-lines data in streaming usage
- Claude code execution fails in-between session, Api error 401 is shown. its an authentication.
- API Request Timeout Failures Preventing Claude Code Execution
- API Key Configuration Breaks CLI Functionality
- [BUG] API Error overloaded_error
- Anthropic API Timeout Handling Fails in Client Request Loop
- [BUG] Extremely long time to first token
- Image Upload Size Limit Exceeded: Request Blocked by API Validation
- API Request Timeout Persisting After Ops 4 Mitigation
- Bug Report PeriodicExportingMetricReader: metrics export failed
- claude-code sdk mode (-p) has a very long warm up time on slower devices
- Invalid Model Name Prevents API Request with No Model Discovery Option
- Invalid JSON Encoding in API Request Body
- Docker Container Restart and API Request Validation Errors
- Missing Tool Result Block in API Request Handling
- API Request Failures: Repeated 529 Overloaded Errors
- [Bug] Anthropic API Error: Unspecified
- [Bug] Anthropic API Error: Invalid Tool Property Name Format
- [Bug] Anthropic API Error: 429 rate-limit errors persist despite available quota on Max plan
- [BUG] firstParty dispatch returns 401 "User not found" for a valid OAuth token that the standard API accepts (VSCode remote-SSH ext 2.1.185)
- [Bug] Anthropic API errors occurring intermittently throughout day
- [Bug] Incomplete token streaming response from Anthropic API
- I appreciate the message, but I need clarification. Your message appears to be in Ukrainian/Russian and translates roughly to "plus karma for creativity," which doesn't describe a technical bug or feature request for Claude Code. To generate a proper GitH
- [Bug] Anthropic API Error: Output blocked by content filtering policy
- [Bug] Anthropic API Error: 500 Internal Server Error
- [BUG]
- [Bug] Anthropic API Error: False Positive Content Filtering on Safe Output
- [Bug] Claude Code incorrectly flags legitimate phishing analysis as policy violation
- [Bug] Anthropic API Error: Model claude-3-5-sonnet-20241022 not available on account tier
- [BUG] claude code prefilling assistant messages when using claude model 4.6+
- Content filter blocks benign queries ("live forever", Korean text)
- API Error: 500 Internal server error on every new request
- [Bug] Anthropic API Error: HTTP 500 Internal Server Error
- [Bug] Claude Code CLI Not Functioning
- [Bug] Content filtering incorrectly blocks country names and flags in output
- [Bug] Anthropic API Error: Output blocked by content filtering policy
- [BUG] API Error: Rate limit reached
- [BUG] API Error 400 invalid_union / invalid_type on v2.1.69 (regression from v2.1.63)
- [Bug] Anthropic API Error: Internal server error (500) and I have 2x Max account !!! so in Paris 2x 180 euros / month !!!!!!
- [BUG] [Google Vertex] Opus 4.6 model name is not valid for the count_tokens API in Google Vertex
- [Feature Request] Add configurable token budget limits (max_context_tokens, max_turns)
- [BUG] Agent teams ignore ANTHROPIC_DEFAULT_*_MODEL env vars when using Azure AI Foundry
- [BUG] warn for ec2 iam role issue
- API Error 400: tool_use ids without tool_result blocks in non-interactive (-p) mode
- [BUG] claude --continue cause abnormal traffic spike and account rate-limit/ban
- [BUG] Large requests fail with connection error after 15-30min runtime, short requests still work
- [BUG] exceed context limit
- [BUG] Session unrecoverable after "image dimensions exceed max allowed size" API error
- [Feature Request] Auto-resume on rate limit with configurable retry behavior
- Opus 4.5 is suddenly useless
- Content filter on .gitignore causes cascading tool_use_id errors and session crash
- [Bug] Message compacting fails with Anthropic API error on thinking block modification
- [BUG] Facing 400 Bad request few times
- Internal server error
- [Bug] Anthropic API Error: No assistant message found
- [Feature Request] Freedom of Autonomous Sampling Temperature Control for Claude (PRO●CHOICE)