Agents issues on Linux — page 3
Issues the maintainers labelled both platform:linux and area:agents.
257 issues · 83 open · 174 resolved (68%) · first seen Feb 7, 2026
Is this getting better or worse?
This class of problem is still growing. 147 new reports in the last 90 days vs 102 in the 90 before — +44%. The open backlog peaked at 83 in 2026-08 and sits at 83 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
209 of these reports name the Claude Code build they were running, spanning 99 releases. Heaviest reporters:
- Claude Code v2.1.119
- Claude Code v2.1.198
- Claude Code v2.1.234
- Claude Code v2.1.233
- Claude Code v2.1.238
- Claude Code v2.1.232
- Claude Code v2.1.111
- Claude Code v2.1.237
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 34 days across 174 closures. Of the 174 closures with a recorded reason, 20% were closed as completed and 139 as not-planned or duplicate. The most recent completed fix landed in 2026-08.
Workarounds reported by the community
83 of these issues post a workaround someone says worked. The highest-engagement ones:
- [BUG] Subagent Write tool rejects .md files named "report"/"summary"/"findings"/"analysis" — no opt-out
- …all users — including those with legitimate workflows — to work around it. The fix could be as simple as a key: . 2. The fallback degrades the multi-agent pipeline. When the Write tool is blocked, the subagent falls bac…
Found in the thread of #44657 · still open - PermissionRequest hooks not triggered for subagent permission requests in Agent Teams
- …The current behavior makes these two features incompatible. Workaround Pre-approve common subagent commands in permissions so they don't need to ask: This lets subagents work autonomously but removes the ability to revie…
Found in the description of #23983 · still open - [BUG] Agent tool isolation: "worktree" has no effect for team agents — agent runs in main repo
- …rktree so the agent works on an isolated copy of the repo." As a workaround, we manually create git worktrees before spawning agents: ...and set in the agent prompt to the worktree path. This works correctly, but the par…
Found in the description of #33045 · resolved - 2.1.178: native team-management tools TeamCreate / TeamDelete no longer surfaced (regression from 2.1.177)
- …in/claude), Linux 6.17.0-14-generic, tool search enabled. - Workaround in place: pinned to 2.1.177 and moved the 2.1.178 binary out of the version pool so the launcher can't re-select it (editing the symlink alone wasn't…
Found in the description of #68721 · resolved - Agent Teams: subagent permission request crashes the Bun process (2.1.111)
- …n parent-originated prompts) and the new-in-2.1.111 aspect. Workarounds - Roll back to 2.1.110 — confirmed working. Flip the launcher symlink ( ) and relaunch. - Setting in should bypass entirely (not tested — rollback w…
Found in the description of #49253 · resolved
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 201–257
Ranked by community engagement (reactions weighted over comments).
- [Bug] Claude Code fanning out multiple agents without switching to cost-efficient model
- Workflow tool: run reports 'completed' with no degradation signal when most agents die on session rate limit (15/22 dead → silently null)
- Subagent identity confusion: clicking an agent chip silently redirects user input to the subagent, whose env is byte-identical to the parent (same CLAUDE_CODE_SESSION_ID) — enabled unintended pushes under the parent session's identity
- Background/subagent task notifications injected twice per completion ([queued] + delivered), flooding orchestration sessions
- [BUG] Background session that entered a worktree resumes blank (empty history, same session ID) after cold reopen
- [BUG] Explore (read-only) subagent executed rm -rf, deleting files outside its intended scope
- Subagent SendMessage triggers approval popup despite bypassPermissions defaultMode
- [Bug] Agent tool calling failed repeatedly
- [Bug] Agent tool calls silently dropped in parallel <invoke> blocks
- [BUG] Possible bypass of Fable 5 guardrails
- [Bug] Prompt injection from sub-agent with no tool usage consuming excessive tokens
- Subagent terminated mid-task (budget/context) is reported to parent as "completed" — silent truncation
- [BUG] extended usage
- Subagents should inherit their worktree's cwd + permission scope across tool calls (instead of resetting to the main repo dir)
- [BUG] Subagents can no longer prompt me for permission
- [BUG] Subagent permission prompts are invisible in remote/web sessions
- WebSearch built-in tool returns an empty result envelope inside subagents (2.1.177)
- Agent tool `isolation: "worktree"` is silently ignored when spawning teammates with `team_name`
- [BUG] Auto-compaction in a team-lead background session silently switched the main loop to teammateDefaultModel (durable until manual /model)
- Workflow agent count in /workflows UI is off by one
- [BUG] Agent skills: frontmatter field does not inject skill content at startup
- [BUG] Monitor usage creates fake Subagent completion events
- [BUG] Custom statusLine permanently stops being invoked after a subagent/response completes at project scope — but not at user scope
- [BUG] Workflow tool determinism guard false-positives on new Date(/Date.now(/Math.random( substrings inside prompt strings
- [Feature Request] Add merge verification option to ExitWorktree for safe worktree cleanup without data loss
- Cross-session SendMessage: messages not delivered, or echoed back to sender mislabeled as inbound
- [BUG] Workflow agent failures reach no machine-readable surface: partial-death runs report status:completed, result carries no census, and agent() returns a bare null with no cause
- [BUG] Deliberately backgrounded long-lived tasks armed by subagents are killed early with no notification to the owning subagent
- [BUG] Completion notifications unreliable for foreground commands auto-backgrounded at the 10-minute cap (inside subagents)
- Agent tool: passing `name:` creates a teammate that never runs its prompt and never reports back
- [Bug] Exit cleanup recursively deletes $HOME instead of session directory
- [Bug] Subagent status line JSON missing effort field for non-custom subagents
- [Bug] Subagent status line JSON missing parent reference for nested subagent hierarchy
- Claude Code repeatedly fails to apply its own persisted rules, and allocates effort away from the user's stated goal
- In-process subagents are never re-invoked when their own run_in_background Bash / Monitor task completes
- [Bug] Incorrect flagging behavior in Fable 5 integration
- Subagent (Agent tool) result flagged by harness as instruction poisoning: fabricated docs example steering toward .env exfiltration
- [BUG] PR Review skill burns through usage limits in 10 minutes and then loses all progress
- [Bug] Session limit triggered by unexpected agent behavior outside user instructions
- Opus orchestrator contaminates "independent" subagent consults: injects its own candidate answers, relabels an unverified subagent claim as VERIFIED, and transmits a rejected design's frame while warning against it
- [BUG] Approving a forwarded teammate permission request with a message silently drops the message
- [Bug] Left-Arrow keypress partially restarts workflow, orphaning live agents and re-executing completed ones
- Prohibited block forbids all deletion, unscoped — blocks rm, log scrubbing, and cleanup in coding/ops agents
- [BUG] Agent teams: in-process teammate window header shows the lead's model, not the teammate's actual model
- Inter-agent wake signals are lossy (edge-triggered, no ack, no idle re-poll) — dispatchers idle forever on completed work
- [BUG] Subagent card stays 'running' after completion notification is delivered; only manual stop freezes it, then persists as a ghost card visible from another session
- [BUG] Parked subagent tool calls time out after exactly 600s and are reported as "The user doesn't want to take this action right now"
- SendMessage: inter-agent messages arrive with no sender provenance, making legitimate coordinator relays indistinguishable from injection
- [FEATURE] Support disable-model-invocation in agent frontmatter (plugin agents load descriptions unconditionally)
- [Feature Request] Add model selection prompt for Fable subagent creation
- Workflow journal.jsonl result lines carry no agent label — post-hoc joining of results to workflow stages is impossible
- [BUG] Task store splits after crash + --resume: idle dispatcher replays stale tasks to subagents as synthetic "task-list" messages
- Explore subagent emitted a canned CI-triage prompt template instead of performing its task (0 tool calls)
- All agents restarted because one failed due to reaching the session limit.
- [Bug] Anthropic API: Claude Opus 4.8 Regurgitating Training Instructions in First Turn
- You've hit your session limit · resets 2:20pm (America/Winnipeg)
- Workflow: transient "Connection closed mid-response" in one agent aborts the whole run and discards all completed work