Agents issues on VS Code
Issues the maintainers labelled both platform:vscode and area:agents.
70 issues · 20 open · 50 resolved (71%) · first seen Feb 25, 2026
Is this getting better or worse?
This class of problem is converging. 28 new reports in the last 90 days vs 41 in the 90 before — -32%. The open backlog peaked at 20 in 2026-08 and sits at 20 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
48 of these reports name the Claude Code build they were running, spanning 40 releases. Heaviest reporters:
- Claude Code v2.1.123
- Claude Code v2.1.247
- Claude Code v2.1.201
- Claude Code v2.1.158
- Claude Code v2.1.156
- Claude Code v2.1.92
- Claude Code v2.1.89
- Claude Code v2.1.250
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 50 closures. Of the 50 closures with a recorded reason, 12% were closed as completed and 44 as not-planned or duplicate. The most recent completed fix landed in 2026-08.
Workarounds reported by the community
13 of these issues post a workaround someone says worked. The highest-engagement ones:
- [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 - [BUG] 2.1.114 regression: background subagents cannot write to paths listed in permissions.allow — works in 2.1.112
- …rmation Tests performed during diagnosis Test 0 — Discarded workaround as unsafe: The known workaround for the related pre-existing bug 40502 ( in subagent frontmatter) was tested and rejected because it disables the ent…
Found in the description of #50267 · resolved - [BUG] VSCode: background agent output streams into foreground chat, disrupting active conversation
- …ines against that seems an unusually lopsided cost/benefit. Workarounds meanwhile 1. — removes from the Agent tool schema entirely; results return as collapsed tool results. 2. per spawn. Note synchronous is not serial —…
Found in the thread of #64651 · still open - [Critical] Background agents cannot be stopped, Claude lies about stopping, massive token waste (~1.4M tokens), inconsistent statements
- …nage to debug their own projects. Of course, these are only temporary fixes — not permanent solutions. Our problems can only be fully resolved by Anthropic. I asked my Claude to look through the issues it has read and se…
Found in the thread of #41461 · resolved - [BUG] Sub-agent permission mode inheritance broken — permissionMode frontmatter and parent acceptEdits both ineffective for Edit tool calls
- …eritance is currently broken, this is the only project-tier workaround), OR (c) Provide an explicit project-tier permission-policy mechanism for sub-agents (e.g., .claude/agents-settings.json or a subagents block in .cla…
Found in the description of #57118 · 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 1–70
Ranked by community engagement (reactions weighted over comments).
- [MODEL] Opus 4.8 starts hallucinating results before parallel tasks finish
- Sonnet model returns 'Rate limit reached' despite 0% usage
- VS Code: [ Claude Extention ] Can't see what subagents are doing or if they're stuck.
- [BUG] 2.1.114 regression: background subagents cannot write to paths listed in permissions.allow — works in 2.1.112
- [BUG] VSCode: background agent output streams into foreground chat, disrupting active conversation
- [BUG] Custom agent cannot be invoked with @-mention in VSCode extension
- [Critical] Background agents cannot be stopped, Claude lies about stopping, massive token waste (~1.4M tokens), inconsistent statements
- [BUG] Default custom agent in VSCode extension is ignoring the "tool" directive
- [Bug] Random text insertion in agent harness under high concurrent load (20+ agents)
- [Feature Request] [VS Code] Invoke a custom subagent as the main conversation agent
- [Feature Request] Add per-subagent observability (model, effort) to /agents Running tab and agent JSON output
- [BUG] Claude Code over-consumes context by not delegating bulky operations to subagents
- [BUG] Claude Code — Per-Agent Permission Control Gap
- [Bug] Sub-agents stuck in infinite loops consuming excessive tokens
- [BUG] Workflow harness retries indefinitely on HTTP 429 rate_limit — 97 agents, 2M tokens burned in 34 seconds ()
- [BUG] Sub-agent permission mode inheritance broken — permissionMode frontmatter and parent acceptEdits both ineffective for Edit tool calls
- [Bug] Background sub-agent output files empty (0 bytes) on Windows
- [Bug] Unexpected high token consumption with non-Claude subagents and orchestrator models
- [Bug] Unexpected high token consumption with multi-agent Opus orchestrator spawning Sonnet agents
- [FEATURE] VSCode Extension: Missing @agent syntax support and unclear agent call visualization
- [Bug] Excessive agent spawning causes token bloat for simple code analysis tasks
- Sub-agent attempts `exit_plan_mode` as Bash command, fails with Exit code 127
- [BUG] Subagent grep outlives its session, ate 11 GB of RAM
- After compaction and subagent return, Main agent set's itself from Sonnet 4.6 to Opus 4.7 without user interaction
- Scheduled Task: Claude Remote failed to switch branches, regressed prior fixes, and consumed tokens without progress
- [BUG] Agent tries to find outside of the project
- [BUG] Sub-agent file writes lost — ephemeral Write tool results not persisted to working directory
- [BUG] - Endless loop and excessive tool calls by sub agents contributing to massive spike in token consumption (Max plan user)
- [Bug] Agent Teams split-panes mode disabled in VSCode terminal with tmux
- Agent Teams state is wiped on session restart — teams and tasks do not persist
- [Feature Request] Isolate subagent execution environments to prevent tool call (and other) conflicts
- [BUG]
- Agent Teams: Permission requests should show as native UI popups in VS Code extension, not as chat messages
- [BUG] Background subagent tool calls silently denied — permission dialog never surfaced
- Agent tool internal output (agentId, file paths, instructions) exposed in mobile UI
- Peer SendMessage reply nudge stamps from= with agent-type name, not reachable session ID, causing infinite unreachable-address loop
- Subagent tool calls: PreToolUse denials don't surface to the parent, and hook payload carries the parent's session_id
- [BUG] Recent VSC extension update seems to have Claude hanging up occasionally.
- Parallel subagent file edits clobber each other in the IDE diff editor (N−1 spurious permission-denials); diff-review lock is per-agent, not per-IDE-connection
- [BUG] Issue while creating agent on Windows.
- [Bug] Child agent inherits incorrect model version from parent configuration
- Agent Teams: SendMessage writes mailbox JSON without `type` field → reader UI shows 'Unhandled case: [object Object]'
- [BUG] Claude Code Issue: Subagent Responses Not Returned to User
- [Bug] Quota limit exceeded causes loss of agent work
- [Bug] Excessive deletion of worktrees in repeated patterns
- [BUG] VS Code UI Tool not Detecting Agents
- [VSCode Extension] Parallel Agent and MCP tool calls silently rejected
- Session resume corrupts JSONL: file-history-snapshot messageId collides with message uuid
- [Bug] `SendMessage` tool is not exposed to Claude, can't resume agents anymore
- [FEATURE] [UI] Distinguish subagent and main agent actions/steps
- [BUG] SubAgent MCP tool calls(configured via mcpServers yaml frontmatter in subagent.md) show as blank line in Ctrl+O view
- [Bug] Subagent polling wake-ups consume excessive tokens for no-op status checkssu
- [Bug] Subagent final assistant messages not delivered to parent session
- Spoofed background-agent completion notification enabled a prompt injection attempt (correctly refused, full report filed on HackerOne)
- [FEATURE] Compact display option for in-process agent team panel (task text makes it tall in VS Code integrated terminal)
- [BUG] Claude autonomously ran background scripts calling a paid external API, causing ~$29 unintended charge
- [BUG] Agent Teams' `SendMessage` resume discards subagent's model override to default model
- Sub-agent tool calls/logs incorrectly visible in VS Code extension 2.1.160 (hidden correctly in 2.1.39)
- Cross-session messaging (ListAgents/SendMessage) permanently disabled after update, survives reboot/reinstall
- [Bug] Agent behavior not complying with agents.md specifications
- [FEATURE] Configurable peer-registration session name (per-project prefix) for cross-session messaging
- Scary to see the tasks that are running and then coming back with some stale messages minutes after the request is completed
- [Bug] Team member agents spawned with `name:` parameter lose result signals in mailbox path
- Subagent assistant message content replaced with ~145KB eval fixture (Alice in Wonderland) despite output_tokens: 5
- [Bug] Model enforcement rules ignored; agent spawning defaults to wrong model despite explicit constraints
- [BUG] subagent (Task/Agent tool) results intermittently replaced with a fabricated "system-authority" prompt-injection ordering destructive git actions (`tool_uses: 0`)
- (withdrawn)
- [Feature Request] Add model selection prompt for Fable subagent creation
- [Bug] Transient advisor() failure permanently disables tool for entire session
- Project custom agents (.claude/agents/) deregister after EnterWorktree and are not restored by ExitWorktree (delayed self-heal ~15 min)