Lets orchestrators (e.g. an account-management service provisioning a
Hermes VPS) seed an OAuth refresh credential non-interactively instead of
walking the user through `hermes setup` + the device-flow login dance.
Matches the existing first-boot-only pattern used for .env, config.yaml,
and SOUL.md.
If HERMES_AUTH_JSON_BOOTSTRAP is set and $HERMES_HOME/auth.json doesn't
already exist, write the env var's contents to auth.json with mode 600.
The `[ ! -f ... ]` guard is critical: it ensures that on container
restart the rotated refresh token Hermes wrote back to the persistent
volume is never clobbered by the now-stale value the orchestrator
originally seeded.
Generic name (not Nous-specific) so the feature is reusable by any future
orchestrator.
Adds role='leaf'|'orchestrator' to delegate_task. With max_spawn_depth>=2,
an orchestrator child retains the 'delegation' toolset and can spawn its
own workers; leaf children cannot delegate further (identical to today).
Default posture is flat — max_spawn_depth=1 means a depth-0 parent's
children land at the depth-1 floor and orchestrator role silently
degrades to leaf. Users opt into nested delegation by raising
max_spawn_depth to 2 or 3 in config.yaml.
Also threads acp_command/acp_args through the main agent loop's delegate
dispatch (previously silently dropped in the schema) via a new
_dispatch_delegate_task helper, and adds a DelegateEvent enum with
legacy-string back-compat for gateway/ACP/CLI progress consumers.
Config (hermes_cli/config.py defaults):
delegation.max_concurrent_children: 3 # floor-only, no upper cap
delegation.max_spawn_depth: 1 # 1=flat (default), 2-3 unlock nested
delegation.orchestrator_enabled: true # global kill switch
Salvaged from @pefontana's PR #11215. Overrides vs. the original PR:
concurrency stays at 3 (PR bumped to 5 + cap 8 — we keep the floor only,
no hard ceiling); max_spawn_depth defaults to 1 (PR defaulted to 2 which
silently enabled one level of orchestration for every user).
Co-authored-by: pefontana <fontana.pedro93@gmail.com>
The prior form of this test asserted on CLI_CONFIG["delegation"] after
importing cli, which only passed by accident of pytest-xdist worker
scheduling. cli._hermes_home is frozen at module import time (cli.py:76),
before the tests/conftest.py autouse HERMES_HOME-isolation fixture can
fire, so CLI_CONFIG ends up populated by deep-merging the contributor's
actual ~/.hermes/config.yaml over the defaults (cli.py:359-366). Any
contributor (like me) who still has the legacy key set in their own
config causes a false failure the moment another test file in the same
xdist worker imports cli at module level.
Asserting on the source of load_cli_config() instead sidesteps all of
that: the test now checks the defaults literal directly and is
independent of user config, HERMES_HOME, import order, and worker
scheduling.
Demonstrated failure mode before this fix:
pytest tests/hermes_cli/test_config_drift.py \
tests/hermes_cli/test_skills_hub.py -o addopts=""
-> FAILED (CLI_CONFIG["delegation"] contained "default_toolsets"
from the user's ~/.hermes/config.yaml)
Part of Initiative 2 / M0.5.
Matches the default-config removal in the preceding commit.
default_toolsets was documented for users to set but was never actually
read at runtime, so showing it in the example config and the delegation
user guide was misleading.
No deprecation note is added: the key was always a no-op, so users who
copied it from the example continue to see no behavior change. Their
config.yaml still parses; the key is just silently unused, same as
before.
Part of Initiative 2 / M0.5.
delegation.default_toolsets was declared in cli.py's CLI_CONFIG default
dict and documented in cli-config.yaml.example, but never read: none of
tools/delegate_tool.py, _load_config(), or any call site ever looked it
up. The live fallback is the DEFAULT_TOOLSETS module constant at
tools/delegate_tool.py:101, which stays as-is.
hermes_cli/config.py's DEFAULT_CONFIG["delegation"] already omits the
key — this commit aligns cli.py with that.
Adds a regression test in tests/hermes_cli/test_config_drift.py so a
future refactor that re-adds the key without wiring it up to
_load_config() fails loudly.
Part of Initiative 2 / M0.5.
Users can declare shell scripts in config.yaml under a hooks: block that
fire on plugin-hook events (pre_tool_call, post_tool_call, pre_llm_call,
subagent_stop, etc). Scripts receive JSON on stdin, can return JSON on
stdout to block tool calls or inject context pre-LLM.
Key design:
- Registers closures on existing PluginManager._hooks dict — zero changes
to invoke_hook() call sites
- subprocess.run(shell=False) via shlex.split — no shell injection
- First-use consent per (event, command) pair, persisted to allowlist JSON
- Bypass via --accept-hooks, HERMES_ACCEPT_HOOKS=1, or hooks_auto_accept
- hermes hooks list/test/revoke/doctor CLI subcommands
- Adds subagent_stop hook event fired after delegate_task children exit
- Claude Code compatible response shapes accepted
Cherry-picked from PR #13143 by @pefontana.
Two fixes from PR review:
1. Session expiry was looking in _running_agents for the cached agent,
but idle expired sessions live in _agent_cache. Now checks
_agent_cache first, falls back to _running_agents.
2. Global cleanup in stop() was missing process_registry.kill_all(),
so background processes from agents evicted without close() (branch,
fallback) survived shutdown.
Use getattr guard for _agent_cache_lock in _handle_reset_command
because test fixtures may create GatewayRunner without calling
__init__, leaving the attribute unset.
Fixes e2e test failure: test_new_resets_session,
test_new_then_status_reflects_reset, test_new_is_idempotent.
Add 9 tests covering the full zombie process prevention chain:
- TestZombieReproduction: demonstrates that processes survive when
references are dropped without explicit cleanup (the original bug)
- TestAgentCloseMethod: verifies close() calls all cleanup functions,
is idempotent, propagates to children, and continues cleanup even
when individual steps fail
- TestGatewayCleanupWiring: verifies stop() calls close() and that
_evict_cached_agent() does NOT call close() (since it's also used
for non-destructive cache refreshes)
- TestDelegationCleanup: calls the real _run_single_child function and
verifies close() is called on the child agent
Ref: #7131
Call child.close() in the _run_single_child finally block after
unregistering the child from the parent's active children list.
Previously child AIAgent instances were only removed from the tracking
list but never had their resources released — the OpenAI/httpx client
and any tool subprocesses relied entirely on garbage collection.
Ref: #7131
Wire AIAgent.close() into every gateway code path where an agent's
session is actually ending:
- stop(): close all running agents after interrupt + memory shutdown,
then call cleanup_all_environments() and cleanup_all_browsers() as
a global catch-all
- _session_expiry_watcher(): close agents when sessions expire after
the 5-minute idle timeout
- _handle_reset_command(): close the old agent before evicting it from
cache on /new or /reset
Note: _evict_cached_agent() intentionally does NOT call close() because
it is also used for non-destructive cache refreshes (model switch,
branch, fallback) where tool resources should persist.
Ref: #7131
Add a close() method to AIAgent that acts as a single entry point for
releasing all resources held by an agent instance. This prevents zombie
process accumulation on long-running gateway deployments by explicitly
cleaning up:
- Background processes tracked in ProcessRegistry
- Terminal sandbox environments
- Browser daemon sessions
- Active child agents (subagent delegation)
- OpenAI/httpx client connections
Each cleanup step is independently guarded so a failure in one does not
prevent the rest. The method is idempotent and safe to call multiple
times.
Also simplifies the background review cleanup to use close() instead
of manually closing the OpenAI client.
Ref: #7131
Move e2e tests into tests.yml as a parallel job instead of a separate
workflow. Unit tests now also ignore tests/e2e/ to avoid running them
twice. Both jobs appear as independent checks in the PR.
New test classes:
- TestSessionLifecycle: /new then /status sequence, idempotent resets
- TestAuthorization: unauthorized users get pairing code, not commands
- TestSendFailureResilience: pipeline survives send() failures
Additional command coverage: /provider, /verbose, /personality, /yolo.
Note: /provider test is xfail - found a real bug where model_cfg is
referenced unbound when config.yaml is absent (run.py:3247).
Separate workflow for gateway e2e tests, runs on push/PR to main.
Same Python 3.11 + uv setup as existing tests.yml but targets only
tests/e2e/ with verbose output.
Tests /help, /status, /new, /stop, /commands through the full adapter
background-task pipeline. Validates command dispatch, session lifecycle,
and response delivery without any LLM involvement.
Fixtures and helpers for driving messages through the full async
pipeline: adapter.handle_message → background task → GatewayRunner
command dispatch → adapter.send (mocked).
Uses the established _make_runner pattern (object.__new__) to skip
filesystem side effects while exercising real command dispatch logic.
pefontana