8000 boot-agents.sh reports "launched + armed" while the pane is waiting on a Claude Code prompt (#24) by simon-inkie · Pull Request #54 · simon-inkie/inkie-deck · GitHub
[go: up one dir, main page]

Skip to content

boot-agents.sh reports "launched + armed" while the pane is waiting on a Claude Code prompt (#24) - #54

Closed
simon-inkie wants to merge 5 commits into
mainfrom
24-boot-agents-status-u181xn
Closed

simon-inkie wants to merge 5 commits into
mainfrom
24-boot-agents-status-u181xn

Conversation

@simon-inkie
Copy link
Copy Markdown
Owner

Requested by Simon · project thread

Closes #24

Before: boot-agents.sh printed "N launched + armed" as soon as it had typed a launch command. A fresh agent stuck on Claude Code's folder trust screen counted as a success, and auto-arm could press Enter on "No, exit".

After: the script checks each Claude agent's pane after launch and reports it as ready, waiting on a Claude Code prompt, or not running. For the trust screen it names the choice to make and warns about Enter. If any agent is waiting on a prompt, it exits 3. Auto-arm skips panes that are not ready. INSTALL.md tier 3 has a new "First boot" section, which also covers the permission mode.

How: there is a pure classifier, boot_pane_state, over captured pane text. A pane that is not ready is one with no rule-anchored composer, so prompts are not enumerated; only the trust screen is named. A pane that check_idle (from bin/pane-idle) reads as busy counts as ready. Fresh panes are polled against one shared deadline (BOOT_READY_TIMEOUT_SECS, default 30). Already-running Claude panes are sampled once.

Known limits:

  • Only claude agents are checked. Codex keeps its own launch verification.
  • A pane whose runtime is not running is reported but still exits 0. INSTALL.md and the rig document exit 0 for a machine with no model CLI.
  • Both are listed as follow-ups in the SPEC.

SPEC: .specs/24-boot-agents-status-u181xn/SPEC.md

Test plan:

  • 16 new cases in packages/base/test/boot-agents.test.sh. They cover trust-screen fixtures (unnumbered, numbered, older boxed), an unknown offer, a menu under a rule, ready, busy, and prose that quotes the label. The poller's early exits are covered too. Two end-to-end runs use a stub tmux: trust exits 3 and is not armed, ready exits 0 and is armed.
  • These pass: typecheck, check:boundaries, check:leaks, check:licence, check:lib-version and check:dashes.
  • pnpm test has 4 failures that fail the same way on main in the same container: create-agent "CANNOT VERIFY", and the inbox, inbox-push and pane-idle shell suites. That container has claude on PATH and no UTF-8 locale.

🤖 Generated with Claude Code

https://claude.ai/code/session_018wj1S6xHUPXDVTCw8vQxHx


Generated by Claude Code

claude added 3 commits October 7, 2026 14:29
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Signed-off-by: Claude <noreply@anthropic.com>
…#24)

boot-agents.sh now samples each claude agent's pane after launch and
reports it ready, waiting on a Claude Code prompt, or not running. The
folder trust screen is named with the choice to make. Any agent waiting
on a prompt gives exit 3, and auto-arm skips panes that are not ready.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Signed-off-by: Claude <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Signed-off-by: Claude <noreply@anthropic.com>
@simon-inkie simon-inkie self-assigned this Oct 7, 2026
claude added 2 commits October 7, 2026 15:12
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Signed-off-by: Claude <noreply@anthropic.com>
Addresses the review of #54: a launch refused with skipped:<reason> is
reported as not launched instead of already up, readiness is polled in
rounds so one stuck agent cannot starve the rest into a false exit 3,
and INSTALL.md first boot is corrected and documents the timeout.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Signed-off-by: Claude <noreply@anthropic.com>
@simon-inkie
Copy link
Copy Markdown
Owner Author

Review leg: Aggy (AI review agent). Verdict: changes needed (superseded by earlier PR #46).
Checked: matches issue #24 for Claude agents; negative-detection readiness and prompt polling implemented; SPEC present and consistent; public-repo hygiene clean.
Note: Mutually exclusive with earlier PR #46, which provides multi-runtime readiness detection (including OpenAI Codex approval dialogs) and specific prompt guidance. Recommend closing in favor of PR #46.
Merge decision stays with the maintainer.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

boot-agents.sh reports "launched + armed" while the pane is waiting on a Claude Code prompt

2 participants

0