feat(state): complete activity-state coverage for Claude / Codex / OpenCode

[madarco]

Summary

Stacks on top of PR #10 (the drive / agent / queue wait-for commands). PR #10 wired the command surface but the underlying state machine was lopsided: Claude reported 6 states, Codex hooks were staged but didn't fire (codex-cli 0.133.0 bug; confirmed still unreliable in 0.134.0), and OpenCode had no state reporting at all. This change makes all three agents report state symmetrically, adds first-class compacting and error states, and ships an OpenCode plugin to bridge its plugin-only extension surface.

Claude — fill in the missing hooks

• PreCompact → compacting; PostCompact → working --clear-pending (defensive against /compact mid-plan).
• StopFailure → error (cleared naturally by next UserPromptSubmit).
• SubagentStart/SubagentStop → working (subagents keep state at working from the parent's view; explicit re-assertions tighten the catchall PreToolUse race).
• Adds 'compacting' | 'error' to ClaudeActivityState (shared by Codex/OpenCode via AgentActivityState).

Codex — tmux-pane scraper as the actual mechanism

Codex's ~/.codex/hooks.json firing is still unreliable in 0.134.0 even with --enable hooks --dangerously-bypass-hook-trust. The fallback (per plan approval): a small packages/ctl/src/codex-scraper.ts polls tmux capture-pane -p -t codex every 1s, matches against an ordered pattern table, pushes through the existing codex-state socket op only on transitions (no 1Hz heartbeat). Patterns cover trust dialogs / permission prompts (waiting), /compact (compacting), error frames (error), codex-specific active-work TUI fragments (working), and the model·cwd idle footer (idle). The hooks.json shape is also fixed (top-level → { hooks: { Event: [...] } } to match codex 0.134.0's HooksFile struct) and startCodexSession now passes --enable hooks --dangerously-bypass-hook-trust — defense-in-depth for when codex's JSON-hook firing eventually becomes reliable.

OpenCode — first-class plugin

OpenCode has no hooks system but does have a plugin event bus. New packages/sandbox-docker/scripts/opencode-agentbox-plugin.js subscribes to session.idle, permission.asked, tool.execute.before, session.compacted, session.error, etc. and shells agentbox-ctl opencode-state for each transition. Baked into the image; seeded into <vol>/config/plugins/agentbox-state.js by a new seedOpencodePlugin helper (mirrors seedCodexHooks). New opencode-state socket op + setOpencodeState reporter method + state field on BoxStatusOpencode so the host can agent state <opencode-box> / agent wait-for waiting <opencode-box>.

Surface in agentbox agent + skill doc

• agent wait-for compacting | error now work.
• ~/.claude/skills/agentbox/SKILL.md updated: the agent section is no longer Claude-only and documents the three sources (Claude hooks / Codex scraper / OpenCode plugin).

Test plan

• pnpm -r typecheck clean
• pnpm lint clean
• pnpm -r test — 327 + 1 skipped (cloud-e2e); 22 new tests:
  • status-reporter.test.ts (+3): compacting round-trip, error non-sticky, subagent re-assertion.
  • codex-scraper.test.ts (+12): pattern table priority + false-positive guards (the directory-trust prompt's "Working with untrusted contents" must NOT match working), change-detection across session up/down, baseline idle on session reappearance.
  • agent-state.test.ts (+4): new compacting / error matchers; stale-payload guard.
• Live-verified on a fresh docker box:
  • Created with agentbox codex --no-attach, the scraper picked up the directory-trust dialog as waiting, then the model·cwd idle footer as idle after the trust prompts cleared. Confirms the daemon-scraper wiring + the new pattern table on a real codex 0.134.0 TUI.
• OpenCode plugin live-verify deferred — requires an OpenCode provider login set up; the seed step + opencode-state wire op are unit-validated.
• Cloud provider parity (Daytona / Hetzner) — these snapshots pick up the new managed-settings / hooks file / plugin automatically on the next agentbox prepare. No code changes needed.

---

Note

Medium Risk
Changes how host automation observes agent readiness (new states, 1s Codex tmux scraping, plugin-spawned ctl calls); misclassified pane patterns could skew wait-for, but no auth or data-path changes.

Overview
Symmetric activity reporting for Claude, Codex, and OpenCode: shared states now include compacting and error, and the host can agent wait-for on them.

Claude adds managed-settings hooks for compaction (PreCompact / PostCompact with --clear-pending), turn failures (StopFailure → error), and subagent lifecycle (re-assert working).

Codex treats unreliable JSON hooks as defense-in-depth: the ctl daemon runs a tmux pane scraper (~1s capture-pane, ordered regex table, updates only on transitions) as the production path. Hooks JSON is reshaped to Codex 0.134’s { hooks: { … } } layout, and startCodexSession passes --enable hooks and --dangerously-bypass-hook-trust.

OpenCode gets a baked plugin that maps bus events to agentbox-ctl opencode-state, plus seedOpencodePlugin, socket/client/reporter wiring, and state / updatedAt on box status (parity with Codex). Runtime staging and the box image copy the plugin alongside existing hook assets.

Tests cover scraper patterns, reporter compaction/error behavior, wait-state matching, and a less flaky supervisor parallelism timing threshold.

^{Reviewed by Cursor Bugbot for commit c9f445f. Configure here.}