Skip to content

Sessions auto-archiving every 30-90 min when launched from specific cwd bucket (since 2026-05-09) #59451

Closed as not planned
Closed as not planned
Sessions auto-archiving every 30-90 min when launched from specific cwd bucket (since 2026-05-09)#59451
Labels
area:agent-viewclaude agents TUI / --bg / FleetView / daemon bg sessionsarea:corebugSomething isn't workingplatform:macosIssue specifically occurs on macOSstaleIssue is inactive

Description

@gohfastur
gohfastur
opened on May 15, 2026

Summary

Claude Code sessions launched from /Users/jason/.openclaw/ are being auto-archived in FleetView every 30-90 minutes of activity, dropping the mobile bridge. Identically-configured sessions launched from sibling working directories under /Users/jason/.openclaw/workspace/ survive normally for hours. The behavior started on or about 2026-05-09 and is now happening multiple times per day on Fuse-development work specifically.

This is a re-report extending the 2026-05-12 internal write-up — issue has persisted through 2026-05-15 with no improvement.

Environment

  • claude-code 2.1.121 (Homebrew, installed 2026-04-27, unchanged since)
  • macOS Darwin 25.3.0 / Apple Silicon
  • Model: claude-opus-4-7[1m] (1M context, xhigh effort; also reproduced at medium)
  • Mobile bridge attached (Claude Code mobile app)
  • MCP servers: obsidian only

Repro

  1. Launch Claude Code from /Users/jason/.openclaw (NOT the /workspace/ subdir)
  2. Begin Fuse-development work (heavy tool use, large MCP/skill load)
  3. Within 30-90 min the session disappears from FleetView Active and the mobile bridge loses access
  4. CLI session itself often remains usable until the next turn fails

Differential — identical config, different behavior

Sessions that survive normally (run for hours):

  • APEX session at cwd /Users/jason/.openclaw/workspace/...
  • FOV session at cwd /Users/jason/.openclaw/workspace/...
  • Alpha session at cwd /Users/jason/.openclaw/workspace/...
  • This very report is being filed from a workspace-bucket session that has survived 2+ hours of heavy Fuse work today (2026-05-15).

Sessions that get archived:

  • Fuse sessions launched from cwd /Users/jason/.openclaw/ (parent dir, different bucket string)

Evidence — transcript churn (parent bucket only)

~/.claude/projects/-Users-jason--openclaw/
  2026-05-12 01:05  3.8 MB session
  2026-05-12 02:16  8.0 MB session  ← archived mid-work
  2026-05-12 03:01  1.6 MB session  ← archived mid-work
  2026-05-12 03:06  1.7 MB session  ← archived mid-work
  2026-05-12 03:10  1.2 MB session

2026-05-08 had 7 sessions across 3 hours (same pattern). 2026-05-15 (today): previous Fuse session "stopped responding" mid-flight, presumed archive event.

Hypothesis

Server-side policy keyed off project-dir bucket name or transcript density per bucket. The -Users-jason--openclaw bucket has ~83 stored transcripts; the workspace sibling buckets have 1-52 each. The dense bucket appears to trip something the sparse ones don't.

Local config signals (~/.claude.json cachedGrowthBookFeatures)

  • tengu_bridge_repl_v2_config.teardown_archive_timeout_ms = 1500
  • tengu_bridge_repl_v2_config.session_keepalive_interval_ms = 0
  • tengu_bridge_repl_v2_config.session_keepalive_interval_v2_ms = 0
  • tengu_bridge_repl_v2_config.non_exclusive_heartbeat_interval_ms = 180000
  • tengu_bridge_repl_v2_config.http_timeout_ms = 10000
  • tengu_lapis_finch = True
  • tengu_shale_finch = True

When it started

On or about 2026-05-09. No claude-code binary update has happened since 2026-04-27; no ~/.claude/settings.json or workspace settings.local.json touched in 14+ days. The behavior change correlates only with GrowthBook feature-flag refreshes, which write to ~/.claude.json on every launch.

Ask

Please look at server-side session-archive policy / feature-flag changes for account jason@fuse.fit (or subpej@gmail.com) since 2026-05-09:

  1. Which flag or policy is triggering archive on this account/cwd?
  2. Why only the -Users-jason--openclaw bucket and not sibling workspace/* buckets?
  3. Can keepalive be enabled for heavy multi-hour Fuse-development sessions, or teardown grace raised from 1500 ms?

Impact

Workflow blocker is operationally severe — each archive event drops the mobile bridge, breaks remote control from my phone, and forces a restart that loses session context. Losing ~2 hours of compounding work per day to this since 2026-05-09. Alpha launch shipped 2026-05-15 with this still degrading productivity.

Activity

  1. github-actions
    added
    bugSomething isn't working
    platform:macosIssue specifically occurs on macOS
    area:agent-viewclaude agents TUI / --bg / FleetView / daemon bg sessions
    area:core
    on May 15, 2026

  2. github-actions commented on May 15, 2026

    @github-actions
    github-actionsbot
    on May 15, 2026 – with GitHub Actions

    Found 3 possible duplicate issues:

    1. Sessions auto-archiving within 30-90 min (only one project-dir bucket affected, started ~2026-05-09) #58446
    2. [Web/Desktop UI] Active session auto-archived every ~5 minutes during normal interaction #59449
    3. Cowork desktop: session auto-archives in <60s of inactivity (Windows) #57945

    This issue will be automatically closed as a duplicate in 3 days.

    • If your issue is a duplicate, please close it and 👍 the existing issue instead
    • To prevent auto-closure, add a comment or 👎 this comment

    🤖 Generated with Claude Code

  3. gohfastur commented on May 15, 2026

    @gohfastur
    gohfastur
    on May 15, 2026
    Author

    Update 2026-05-15 ~16:20 UTC — workaround invalidated

    The "launch from /Users/jason/.openclaw/workspace/ instead of parent" workaround I described above does NOT work. A session opened from the workspace cwd today is auto-archiving every ~30 min just like sessions from the parent bucket. The cwd-bucket theory was wrong, or at least incomplete.

    Updated hypotheses (none confirmed):

    1. Transcript size threshold — heavy-tool-use sessions accumulate large transcripts fast
    2. MCP load / connection cycling (obsidian was still "connecting" on multiple turns; could trip teardown)
    3. Account-scoped feature flag, regardless of cwd
    4. Write-heavy activity pattern (bash + Edit + commit churn) vs read-heavy

    Still no Anthropic response on the original report. Operationally severe on alpha-ship-day; we're losing context every 30 min and re-loading the full startup gate each time.

    Anyone from the Claude Code team — please pull session-archive logs for account jason@fuse.fit or subpej@gmail.com for 2026-05-15 16:00-17:00 UTC. The "stop" decisions should show up server-side with a reason.

  4. elivitan commented on May 25, 2026

    @elivitan
    elivitan
    on May 25, 2026

    Corroboration — different platform, different trigger, same outcome (2026-05-25)

    Hitting this on Windows 11, claude-code latest, model claude-opus-4-7[1m]. My trigger profile is different from the original report but the symptom is the same: sessions silently drop out of FleetView Active, no user action.

    What's different about my repro

    The session that gets archived is idle and waiting on a permission prompt — specifically, sitting on "approve this commit?" or "approve this push?" for ~5-10 min while I review the diff in another window. It's not heavy-tool-use or transcript-density driven in my case. The session has zero in-flight tool calls; it's literally blocked on me.

    That should be the exact state auto-archive is supposed to exclude. "Awaiting user input" ≠ "idle / abandoned."

    Environment

    • claude-code on Windows 11 Pro (PowerShell)
    • Model: claude-opus-4-7[1m] (1M context)
    • Multiple parallel sessions across git worktrees (wt-* pattern)
    • MCP: ccd_session_mgmt, computer-use, Claude_in_Chrome, Claude_Preview, several others
    • No remote/mobile bridge — desktop FleetView only
    • Same behavior on both Opus 4.6 and 4.7

    Why this is operationally severe (echoing OP)

    • Each archive event drops the pending commit confirmation — when I come back from reviewing the diff, the prompt is gone and the work is stranded mid-state
    • I run multi-worktree parallel sessions where each one frequently pauses for approval; auto-archive on idle effectively penalizes the safety-pause pattern
    • No setting in ~/.claude/settings.json to disable or extend the timeout (checked, also nothing documented)

    Asks

    1. Please treat "awaiting user permission / input" as a non-archive state regardless of idle time — that's the user explicitly being asked to act, not the session being abandoned
    2. Surface a configurable sessionArchiveIdleMs (or equivalent) in settings.json
    3. Optional: a "session pinned" toggle in the FleetView chip so users can opt specific sessions out

    Happy to attach transcripts or ~/.claude/projects/ timing data if a Claude Code engineer wants to look — just ping.

  5. darioabc commented on May 26, 2026

    @darioabc
    darioabc
    on May 26, 2026

    +1, still reproducing on 2.1.150 (latest as of today) on macOS Darwin 25.3.0 arm64. Active sessions getting auto-archived during normal interaction — updating from 2.1.143 → 2.1.150 did not resolve it.

    Came in via #59449 (closed as dup of this).

  6. m-ret commented on May 26, 2026

    @m-ret
    m-ret
    on May 26, 2026

    This is happening to me on Linux Ubuntu. Session keeps auto-archiving. I'm running sessions remotely so this is screwing up my workflow right now.

  7. akivavh commented on May 26, 2026

    @akivavh
    akivavh
    on May 26, 2026

    same here hope it gets noticed, interrupting my workflow and i like using the desktop app

  8. theodore-eng commented on May 27, 2026

    @theodore-eng
    theodore-eng
    on May 27, 2026

    +1 — hitting this on macOS Claude Desktop today (2026-05-27). Session was actively in use, no /exit, no manual archive, no inactivity (continuous work for several hours). Showed up under 'archived' in the /resume picker. Project: a Next.js portal app, working directory is a git repo under ~/dev/. Happy to share more telemetry / a screen recording if it helps narrow the cwd-bucket trigger.

  9. cognitivefabric commented on Jun 3, 2026

    @cognitivefabric
    cognitivefabric
    on Jun 3, 2026

    "ccAutoArchiveOnPrClose: true" flag is the cause

  10. github-actions
    added
    staleIssue is inactive
    on Jun 22, 2026

  11. github-actions commented on Jul 7, 2026

    @github-actions
    github-actionsbot
    on Jul 7, 2026 – with GitHub Actions

    Closing for now — inactive for too long. Please open a new issue if this is still relevant.

  12. github-actions
    closed this as not plannedon Jul 7, 2026

  13. github-actions commented on Sep 8, 2026

    @github-actions
    github-actionsbot
    on Sep 8, 2026 – with GitHub Actions

    This issue has been automatically locked since it was closed and has not had any activity for 7 days. If you're experiencing a similar issue, please file a new issue and reference this one if it's relevant.

  14. github-actions
    locked as resolved and limited conversation to collaborators on Sep 8, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    area:agent-viewclaude agents TUI / --bg / FleetView / daemon bg sessionsarea:corebugSomething isn't workingplatform:macosIssue specifically occurs on macOSstaleIssue is inactive

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions