feat(subagent): persist sub-agent runs and let orchestrator relay user messages

[senamakel]

Summary

Implements checkpoint + replay for sub-agent delegations so they can pause for user input and resume with full conversation history, instead of requiring a full re-spawn from scratch.

Closes #3049.

What changed

Rust core:

• SubagentRunStatus enum (Completed | AwaitingUser) and SubagentCheckpointData for serializing paused sub-agent state
• Turn engine detects ask_user_clarification tool calls inside sub-agents and exits the loop early
• Sub-agent runner checkpoints full conversation history to {workspace}/.openhuman/subagent_checkpoints/{task_id}.json
• spawn_subagent returns structured [SUBAGENT_AWAITING_USER] envelope with task_id, agent_id, and question
• New continue_subagent tool: loads checkpoint, appends user's answer, resumes the same sub-agent
• Re-enabled dedicated_thread parameter (was disabled since Showcase worker/subagent threads with a dedicated UI surface #1624) — all delegations now get persistent worker threads
• SubagentAwaitingUser variants added to DomainEvent, AgentProgress, and SubagentActivity turn state
• Socket bridge emits subagent_awaiting_user events to the frontend

Frontend (app/):

• awaiting_user added to ToolTimelineEntryStatus union
• SubagentDrawer renders awaiting status with amber indicator
• ChatRuntimeProvider processes subagent_awaiting_user socket events
• chatService subscribes to the new event
• i18n: statusAwaitingUser key added to all 14 locales with real translations

Flow

User → Orchestrator → spawn researcher (persisted)
                       Researcher → ask_user_clarification("Which repo?")
                       ← early exit, checkpoint saved
                       ← [SUBAGENT_AWAITING_USER] envelope
       Orchestrator → User: "Which repo?"
User → Orchestrator → continue_subagent(task_id, "the main repo")
                       ← checkpoint loaded, user answer appended
                       Researcher → final answer
       Orchestrator → User: synthesis

Test plan

• cargo check --manifest-path Cargo.toml — compiles clean
• cargo check --manifest-path app/src-tauri/Cargo.toml — Tauri shell compiles
• pnpm typecheck — no TypeScript errors
• pnpm lint — only pre-existing warnings (0 errors)
• New E2E spec chat-harness-subagent-continue.spec.ts: spawn → clarification → user answer → continue → complete
• Existing E2E chat-harness-subagent.spec.ts still passes (one-shot flow unaffected)
• Checkpoint cleanup: file removed after successful continuation

[coderabbitai]

Warning

Review limit reached

@senamakel, we couldn't start this review because you've reached your PR review rate limit.

More reviews will be available in 17 minutes and 9 seconds. Learn how PR review limits work.

Your organization has run out of usage credits. Purchase more in the billing tab.

⌛ How to resolve this issue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

We recommend that you space out your commits to avoid hitting the rate limit.

🚦 How do rate limits work?

CodeRabbit enforces hourly rate limits for each developer per organization.

Our paid plans include higher PR review limits than trial, open-source, and free plans. In all cases, reviews become available again over time. During sustained high-volume PR review activity, CodeRabbit may temporarily slow when the next review becomes available.

Please see our Fair Usage Limits Policy for further information.

ℹ️ Review info

⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Pro

Run ID: c2bd786c-9c91-48e6-8005-a0b8c72c03e8

📥 Commits

Reviewing files that changed from the base of the PR and between 4e221e9 and 6b2e698.

📒 Files selected for processing (46)

• app/src/lib/i18n/ar.ts
• app/src/lib/i18n/bn.ts
• app/src/lib/i18n/de.ts
• app/src/lib/i18n/en.ts
• app/src/lib/i18n/es.ts
• app/src/lib/i18n/fr.ts
• app/src/lib/i18n/hi.ts
• app/src/lib/i18n/id.ts
• app/src/lib/i18n/it.ts
• app/src/lib/i18n/ko.ts
• app/src/lib/i18n/pl.ts
• app/src/lib/i18n/pt.ts
• app/src/lib/i18n/ru.ts
• app/src/lib/i18n/zh-CN.ts
• app/src/pages/conversations/components/SubagentDrawer.tsx
• app/src/providers/ChatRuntimeProvider.tsx
• app/src/services/chatService.ts
• app/src/store/chatRuntimeSlice.ts
• app/test/e2e/specs/chat-harness-subagent-continue.spec.ts
• src/core/event_bus/events.rs
• src/openhuman/agent/harness/engine/core.rs
• src/openhuman/agent/harness/session/turn.rs
• src/openhuman/agent/harness/subagent_runner/mod.rs
• src/openhuman/agent/harness/subagent_runner/ops.rs
• src/openhuman/agent/harness/subagent_runner/ops_tests.rs
• src/openhuman/agent/harness/subagent_runner/types.rs
• src/openhuman/agent/harness/tool_loop.rs
• src/openhuman/agent/progress.rs
• src/openhuman/agent/tools/delegate_to_personality.rs
• src/openhuman/agent_orchestration/ops.rs
• src/openhuman/agent_orchestration/tools.rs
• src/openhuman/agent_orchestration/tools/continue_subagent.rs
• src/openhuman/agent_orchestration/tools/dispatch.rs
• src/openhuman/agent_orchestration/tools/spawn_parallel_agents.rs
• src/openhuman/agent_orchestration/tools/spawn_subagent.rs
• src/openhuman/agent_orchestration/tools/spawn_worker_thread.rs
• src/openhuman/channels/providers/web.rs
• src/openhuman/skills/run_log.rs
• src/openhuman/threads/turn_state/mirror.rs
• src/openhuman/threads/turn_state/mirror_tests.rs
• src/openhuman/threads/turn_state/types.rs
• src/openhuman/tools/ops.rs
• tests/inference_agent_raw_coverage_e2e.rs
• tests/memory_core_threads_raw_coverage_e2e.rs
• tests/memory_raw_coverage_e2e.rs
• tests/memory_threads_raw_coverage_e2e.rs

---

_{Comment @coderabbitai help to get the list of available commands and usage tips.}