hermes-agent/gateway
Teknium c66ecf0bc3
feat(delegation): async background subagents via delegate_task(background=true) (#40946)
* feat(delegation): async background subagents via delegate_task(background=true)

delegate_task(background=true) dispatches a subagent that runs in the
background and returns a handle immediately, so the user and model keep
working while it runs. The full result — plus the original task source —
re-enters the conversation as a new turn when the subagent finishes,
riding the same completion-queue rail as terminal background processes.

- tools/async_delegation.py: daemon-executor registry, capacity cap,
  rich self-contained completion event pushed onto the shared
  process_registry.completion_queue (type='async_delegation').
- delegate_tool.py: background param + single-task dispatch branch;
  batch async rejected (v1).
- process_registry.py: format_process_notification renders the rich
  task-source block (goal/context/toolsets/model/status/result).
- gateway/run.py: dedicated _async_delegation_watcher drains + injects
  results into the originating session (idle + post-turn), session_key
  routing enrichment, shutdown interrupt of dangling delegations.
- config: delegation.max_async_children (default 3).

Reuses the existing idle-drain wiring rather than mutating a running
agent loop, preserving message-role alternation and prompt-cache
invariants. 13 targeted tests; CLI + gateway paths E2E-verified.

* test(delegation): make async non-blocking tests environment-independent

CI 'test (5)' flaked on a cold, 8-worker runner: the first
delegate_task(background=true) call measured 2.27s of one-time setup
(config load + child-agent construction + imports), tripping the
elapsed < 1.0 wall-clock assertion. That assertion was testing setup
overhead, not blocking.

Replace the wall-clock thresholds with the real invariant: dispatch
returns while the child is still gated (active_count == 1, completion
queue empty), which a synchronous impl could not do. Keep only a loose
4s sanity backstop well under the runner's 5s gate.

* fix(delegation): harden async background delegation

Follow-up review fixes:
- Detach background child from parent._active_children at dispatch —
  otherwise parent-turn interrupts (Ctrl+C, mid-turn steering), cache
  evicts (release_clients), and session close (/new) kill/close the
  detached subagent mid-run, defeating the point of background mode.
  Lifecycle is owned by the async registry's interrupt_fn.
- Make the capacity check atomic with the record insert (TOCTOU: two
  concurrent dispatches could both pass active_count() and exceed the cap).
- TUI dedup: key async_delegation events by delegation_id — the
  fallthrough keyed them all as ("", type), suppressing every completion
  after the first in the desktop/TUI status feed.
- CLI /stop now interrupts running background delegations and /agents
  lists them (they live outside the process registry and were invisible).
- Drop stray unbalanced ']' line from the re-injection block and the
  unused _ASYNC_DEFAULT import.

Tests: detach-at-dispatch + concurrent-capacity race added (15 total in
test_async_delegation.py); 137 delegate + 140 process-registry/notify/watch
+ 7 TUI dedup tests pass.

* fix(delegation): harden async background completion drains
2026-06-15 13:33:12 -07:00
..
assets fix: improve telegram topic mode setup 2026-05-04 12:07:17 -07:00
builtin_hooks remove: BOOT.md built-in hook (#17093) 2026-04-28 09:50:27 -07:00
platforms fix(telegram): avoid rich final duplicate previews (#46206) 2026-06-14 11:13:38 -07:00
__init__.py docs(gateway): mention Weixin in gateway help and docstrings 2026-05-12 17:08:51 -07:00
authz_mixin.py fix(gateway): preserve WeCom per-group sender allowlists 2026-06-13 07:18:54 -07:00
channel_directory.py fix: harden WhatsApp target alias salvage 2026-06-15 05:51:47 -07:00
config.py fix(telegram): avoid rich final duplicate previews (#46206) 2026-06-14 11:13:38 -07:00
delivery.py fix(gateway): drop outbound silence-narration messages pre-send 2026-05-29 19:06:05 -07:00
display_config.py Merge commit '6110aed9b' into feat/whatsapp-cloud-api 2026-06-10 21:39:22 -04:00
hooks.py feat(hooks): expose thread_id and chat_type in agent:start/end context (#41672) 2026-06-07 19:16:36 -07:00
kanban_watchers.py refactor(gateway): extract kanban watcher loops into GatewayKanbanWatchersMixin (god-file Phase 3) 2026-06-07 23:14:18 -07:00
memory_monitor.py Port from cline/cline#10343: periodic gateway memory logging (#27102) 2026-05-16 12:55:23 -07:00
mirror.py refactor(gateway): drop _append_to_jsonl from mirror 2026-05-20 13:00:57 -07:00
pairing.py fix(gateway): preserve WhatsApp pairing approvals across JID/LID alias flips 2026-05-23 01:46:34 -07:00
platform_registry.py refactor(plugins): add apply_yaml_config_fn registry hook 2026-05-13 22:20:30 -07:00
response_filters.py fix(gateway): suppress exact silence tokens without mutating history 2026-06-14 03:25:08 -07:00
restart.py fix(gateway): address restart review feedback 2026-04-10 21:18:34 -07:00
run.py feat(delegation): async background subagents via delegate_task(background=true) (#40946) 2026-06-15 13:33:12 -07:00
runtime_footer.py chore: prune unused imports and duplicate import redefinitions 2026-05-28 22:26:25 -07:00
session.py fix(matrix): isolate room context and restore reliable inbound dispatch (#18505) 2026-06-11 07:41:43 -04:00
session_context.py fix(api-server): bind request session context for tools 2026-06-08 20:52:08 -07:00
shutdown_forensics.py chore: ruff auto-fixes — collapsible-else-if, if-stmt-min-max, dict.fromkeys (#23926) 2026-05-11 11:03:29 -07:00
slash_access.py feat(gateway): per-platform admin/user split for slash commands (salvage of #4443) (#23373) 2026-05-10 12:33:54 -07:00
slash_commands.py fix: harden salvaged session and browser improvements 2026-06-15 07:46:34 -07:00
status.py fix(gateway): evict scoped lock when PID+start_time match but process is not a gateway 2026-06-15 05:25:07 -07:00
sticker_cache.py fix: guard yaml.safe_load, flock unlock, TOCTOU races, and atomic writes 2026-05-19 00:12:41 -07:00
stream_consumer.py fix(telegram): avoid rich final duplicate previews (#46206) 2026-06-14 11:13:38 -07:00
stream_dispatch.py feat(gateway): structured stream-event protocol + Telegram draft formatting parity (#37250) 2026-06-02 00:33:50 -07:00
stream_events.py feat(gateway): structured stream-event protocol + Telegram draft formatting parity (#37250) 2026-06-02 00:33:50 -07:00
whatsapp_identity.py fix(whatsapp_identity): pin identifier regex to ASCII, clarify it's defense-in-depth 2026-04-26 20:48:31 -07:00