One multiplexed gateway process serves every profile, but several per-turn
reads still went through state frozen from the LAUNCH profile:
- `_current_max_iterations` re-bridged `agent.max_turns`/`sessions.*` from the
module constant `_hermes_home` into one process-wide HERMES_MAX_ITERATIONS,
so every secondary ran with the default profile's turn budget. A routed turn
(HERMES_HOME override) now resolves `agent.max_turns` from its own config.
- `_refresh_fallback_model` read `_hermes_home/config.yaml` into one runner-wide
slot, so secondaries fell back through the default's provider/model with their
own keys. It now reads the active gateway home and keeps a last-known-good
chain per home.
- `_load_prefill_messages` resolved relative paths against the launch home.
- `agent/auxiliary_client._AUTH_JSON_PATH` was an import-time constant, so a
secondary's compression/title/vision calls authenticated to Nous with the
default profile's token when it had no pool entry. Resolved per call via
`hermes_cli.auth._auth_file_path()` (patched constant still wins in tests).
- `gateway/hooks.HOOKS_DIR` was frozen at import and one `HookRegistry` was
loaded outside any profile scope, so secondaries' `hooks/` never ran and the
default profile's handlers received every profile's messages, responses and
user ids. `HOOKS_DIR` now resolves per call (salvaged from #56508) and the
runner holds one registry per served home, picked from the active scope at
emit time and front-loaded under each secondary's startup scope.
- Shell-hook subprocesses inherited the launch `os.environ` (default HERMES_HOME
and the default profile's secrets). They now get the routed HERMES_HOME via
`build_subprocess_env`, scrubbed under multiplexing, and the stdin payload
carries `profile` so one script can tell which profile fired it.
- Media-delivery policy (`gateway.strict`, `media_delivery_allow_dirs`,
`trust_recent_files*`) was bridged once into env at startup and read from env
per delivery; under a HERMES_HOME override the validator now reads the routed
profile's config. Single-profile runs keep the env-bridge contract.
Audit: /tmp/mux_audit F3, F4, F6 (auth.json half), F7, F12 (media). Live repro
(temp HERMES_HOME A with profiles/B): before, B saw max_iterations 7,
fallback A/fallback, TOKEN_A, A's hooks, strict=A; after, all B's values.
gateway/hooks.py::HOOKS_DIR is resolved once at import time via
get_hermes_home(), which is a context-local ContextVar under the
multiplexed gateway (multiple profiles sharing one process, each owning
its own Gateway/HookRegistry instance). Freezing the path at import time
pins every later HookRegistry.discover_and_load() call to whichever
profile's HERMES_HOME was active when this module was first imported --
so a later-starting profile silently discovers and executes the FIRST
profile's hook handlers (arbitrary Python code, not just data) against
its own live event context, including session_id/message/response text.
Same bug class already fixed for cache dirs, skills_hub, rich_sent_store,
and the OAuth/auth.json/sessions.json/checkpoint/sticker-cache paths.
Add a per-call resolver, following the established "respect an existing
test monkeypatch of the constant, otherwise re-resolve through
get_hermes_home()" pattern so the existing test seam in
tests/gateway/test_hooks.py keeps working unmodified.
(cherry picked from commit 1e4f96af681de90b942ccb77e3f96ee03913ddc2)
Adds thread_id and chat_type to the agent:start/end plugin hook context
(via getattr with safe defaults; both are real `source` attrs already used
in gateway/run.py). agent:end inherits them via **hook_ctx. Purely additive
— no prompt/history mutation. Documents the full ctx dict in hooks.py.
Co-authored-by: SNooZyy2 <SNooZyy2@users.noreply.github.com>
Dashboard plugin API routes (web_server._mount_plugin_api_routes) and
gateway event hooks (gateway.hooks.HookRegistry.discover_and_load) both
loaded Python files via importlib.util.spec_from_file_location +
exec_module without registering the resulting module in sys.modules.
That breaks any plugin or hook handler that uses `from __future__ import
annotations` together with a Pydantic BaseModel / dataclass / anything
that introspects `__module__`: at first request Pydantic tries to
resolve string-form type hints against the defining module's namespace,
can't find it by name, and raises:
PydanticUserError: TypeAdapter[...] is not fully defined;
you should define ... and all referenced types,
then call `.rebuild()` on the instance.
This is what broke the kanban dashboard's 'triage' button — POST
/api/plugins/kanban/tasks validated against CreateTaskBody (a Pydantic
model in a file using `from __future__ import annotations`) and
returned 500 on every click.
The fix, applied symmetrically to both loaders:
1. Compute module_name once.
2. Register the module in sys.modules BEFORE exec_module.
3. On exec_module failure, pop the half-initialized stub so subsequent
reloads don't pick up broken state.
GETs were unaffected because they don't build a body TypeAdapter, which
is why this only surfaced when users started POSTing.
BOOT.md was merged in PR #3733 before the feature was ready — the
built-in hook spawned a bare AIAgent() with no model/runtime kwargs,
which immediately 401s on any provider with a custom endpoint. Three
separate community PRs (#5240, #12514, #14992) tried to paper over it.
Remove the BOOT.md hook entirely and its user-facing docs/tips. Keep
the gateway/builtin_hooks/ package and the HookRegistry._register_builtin_hooks()
hook-point intact as the extension surface for future always-on
gateway hooks.
Closes#5239.
Co-authored-by: teknium1 <teknium@users.noreply.github.com>
Plugin slash commands now surface as first-class commands in every gateway
enumerator — Discord native slash picker, Telegram BotCommand menu, Slack
/hermes subcommand map — without a separate per-platform plugin API.
The existing 'command:<name>' gateway hook gains a decision protocol via
HookRegistry.emit_collect(): handlers that return a dict with
{'decision': 'deny'|'handled'|'rewrite'|'allow'} can intercept slash
command dispatch before core handling runs, unifying what would otherwise
have been a parallel 'pre_gateway_command' hook surface.
Changes:
- gateway/hooks.py: add HookRegistry.emit_collect() that fires the same
handler set as emit() but collects non-None return values. Backward
compatible — fire-and-forget telemetry hooks still work via emit().
- hermes_cli/plugins.py: add optional 'args_hint' param to
register_command() so plugins can opt into argument-aware native UI
registration (Discord arg picker, future platforms).
- hermes_cli/commands.py: add _iter_plugin_command_entries() helper and
merge plugin commands into telegram_bot_commands() and
slack_subcommand_map(). New is_gateway_known_command() recognizes both
built-in and plugin commands so the gateway hook fires for either.
- gateway/platforms/discord.py: extract _build_auto_slash_command helper
from the COMMAND_REGISTRY auto-register loop and reuse it for
plugin-registered commands. Built-in name conflicts are skipped.
- gateway/run.py: before normal slash dispatch, call emit_collect on
command:<canonical> and honor deny/handled/rewrite/allow decisions.
Hook now fires for plugin commands too.
- scripts/release.py: AUTHOR_MAP entry for @Magaav.
- Tests: emit_collect semantics, plugin command surfacing per platform,
decision protocol (deny/handled/rewrite/allow + non-dict tolerance),
Discord plugin auto-registration + conflict skipping, is_gateway_known_command.
Salvaged from #14131 (@Magaav). Original PR added a parallel
'pre_gateway_command' hook and a platform-keyed plugin command
registry; this re-implementation reuses the existing 'command:<name>'
hook and treats plugin commands as platform-agnostic so the same
capability reaches Telegram and Slack without new API surface.
Co-authored-by: Magaav <73175452+Magaav@users.noreply.github.com>
The gateway now ships with a built-in boot-md hook that checks for
~/.hermes/BOOT.md on every startup. If the file exists, the agent
executes its instructions in a background thread. No installation
or configuration needed — just create the file.
No BOOT.md = zero overhead (the hook silently returns).
Implementation:
- gateway/builtin_hooks/boot_md.py: handler with boot prompt,
background thread, [SILENT] suppression, error handling
- gateway/hooks.py: _register_builtin_hooks() called at the start
of discover_and_load() to wire in built-in hooks
- Docs updated: hooks page documents BOOT.md as a built-in feature
Based on PR #1432 by @bayrakdarerdem. session:start was already on main; this adds the session:end event.
Co-authored-by: bayrakdarerdem <bayrakdarerdem@users.noreply.github.com>
Teknium