Files
hermes-agent/hermes_cli/config.py

4131 lines
166 KiB
Python
Raw Normal View History

"""
Configuration management for Hermes Agent.
Config files are stored in ~/.hermes/ for easy access:
- ~/.hermes/config.yaml - All settings (model, toolsets, terminal, etc.)
- ~/.hermes/.env - API keys and secrets
This module provides:
- hermes config - Show current configuration
- hermes config edit - Open config in editor
- hermes config set - Set a specific value
- hermes config wizard - Re-run setup wizard
"""
import copy
import logging
import os
import platform
import re
import stat
import subprocess
import sys
import tempfile
from dataclasses import dataclass
from pathlib import Path
from typing import Dict, Any, Optional, List, Tuple
logger = logging.getLogger(__name__)
_IS_WINDOWS = platform.system() == "Windows"
_ENV_VAR_NAME_RE = re.compile(r"^[A-Za-z_][A-Za-z0-9_]*$")
_LAST_EXPANDED_CONFIG_BY_PATH: Dict[str, Any] = {}
# Env var names written to .env that aren't in OPTIONAL_ENV_VARS
# (managed by setup/provider flows directly).
_EXTRA_ENV_KEYS = frozenset({
"OPENAI_API_KEY", "OPENAI_BASE_URL",
"ANTHROPIC_API_KEY", "ANTHROPIC_TOKEN",
"DISCORD_HOME_CHANNEL", "TELEGRAM_HOME_CHANNEL",
"SIGNAL_ACCOUNT", "SIGNAL_HTTP_URL",
"SIGNAL_ALLOWED_USERS", "SIGNAL_GROUP_ALLOWED_USERS",
"DINGTALK_CLIENT_ID", "DINGTALK_CLIENT_SECRET",
"FEISHU_APP_ID", "FEISHU_APP_SECRET", "FEISHU_ENCRYPT_KEY", "FEISHU_VERIFICATION_TOKEN",
"WECOM_BOT_ID", "WECOM_SECRET",
"WECOM_CALLBACK_CORP_ID", "WECOM_CALLBACK_CORP_SECRET", "WECOM_CALLBACK_AGENT_ID",
"WECOM_CALLBACK_TOKEN", "WECOM_CALLBACK_ENCODING_AES_KEY",
"WECOM_CALLBACK_HOST", "WECOM_CALLBACK_PORT",
"WEIXIN_ACCOUNT_ID", "WEIXIN_TOKEN", "WEIXIN_BASE_URL", "WEIXIN_CDN_BASE_URL",
"WEIXIN_HOME_CHANNEL", "WEIXIN_HOME_CHANNEL_NAME", "WEIXIN_DM_POLICY", "WEIXIN_GROUP_POLICY",
"WEIXIN_ALLOWED_USERS", "WEIXIN_GROUP_ALLOWED_USERS", "WEIXIN_ALLOW_ALL_USERS",
"BLUEBUBBLES_SERVER_URL", "BLUEBUBBLES_PASSWORD",
"QQ_APP_ID", "QQ_CLIENT_SECRET", "QQBOT_HOME_CHANNEL", "QQBOT_HOME_CHANNEL_NAME",
fix(qqbot): add back-compat for env var rename; drop qrcode core dep Follow-up to WideLee's salvaged PR #11582. Back-compat for QQ_HOME_CHANNEL → QQBOT_HOME_CHANNEL rename: - gateway/config.py reads QQBOT_HOME_CHANNEL, falls back to QQ_HOME_CHANNEL with a one-shot deprecation warning so users on the old name aren't silently broken. - cron/scheduler.py: _HOME_TARGET_ENV_VARS['qqbot'] now maps to the new name; _get_home_target_chat_id falls back to the legacy name via a _LEGACY_HOME_TARGET_ENV_VARS table. - hermes_cli/status.py + hermes_cli/setup.py: honor both names when displaying or checking for missing home channels. - hermes_cli/config.py: keep legacy QQ_HOME_CHANNEL[_NAME] in _EXTRA_ENV_KEYS so .env sanitization still recognizes them. Scope cleanup: - Drop qrcode from core dependencies and requirements.txt (remains in messaging/dingtalk/feishu extras). _qqbot_render_qr already degrades gracefully when qrcode is missing, printing a 'pip install qrcode' tip and falling back to URL-only display. - Restore @staticmethod on QQAdapter._detect_message_type (it doesn't use self). Revert the test change that was only needed when it was converted to an instance method. - Reset uv.lock to origin/main; the PR's stale lock also included unrelated changes (atroposlib source URL, hermes-agent version bump, fastapi additions) that don't belong. Verified E2E: - Existing user (QQ_HOME_CHANNEL set): gateway + cron both pick up the legacy name; deprecation warning logs once. - Fresh user (QQBOT_HOME_CHANNEL set): gateway + cron use new name, no warning. - Both set: new name wins on both surfaces. Targeted tests: 296 passed, 4 skipped (qqbot + cron + hermes_cli).
2026-04-17 15:29:15 -07:00
"QQ_HOME_CHANNEL", "QQ_HOME_CHANNEL_NAME", # legacy aliases (pre-rename, still read for back-compat)
"QQ_ALLOWED_USERS", "QQ_GROUP_ALLOWED_USERS", "QQ_ALLOW_ALL_USERS", "QQ_MARKDOWN_SUPPORT",
"QQ_STT_API_KEY", "QQ_STT_BASE_URL", "QQ_STT_MODEL",
"TERMINAL_ENV", "TERMINAL_SSH_KEY", "TERMINAL_SSH_PORT",
"WHATSAPP_MODE", "WHATSAPP_ENABLED",
"MATTERMOST_HOME_CHANNEL", "MATTERMOST_REPLY_MODE",
"MATRIX_PASSWORD", "MATRIX_ENCRYPTION", "MATRIX_DEVICE_ID", "MATRIX_HOME_ROOM",
"MATRIX_REQUIRE_MENTION", "MATRIX_FREE_RESPONSE_ROOMS", "MATRIX_AUTO_THREAD",
"MATRIX_RECOVERY_KEY",
})
import yaml
2026-02-20 23:23:32 -08:00
from hermes_cli.colors import Colors, color
from hermes_cli.default_soul import DEFAULT_SOUL_MD
feat: nix flake — uv2nix build, NixOS module, persistent container mode (#20) * feat: nix flake, uv2nix build, dev shell and home manager * fixed nix run, updated docs for setup * feat(nix): NixOS module with persistent container mode, managed guards, checks - Replace homeModules.nix with nixosModules.nix (two deployment modes) - Mode A (native): hardened systemd service with ProtectSystem=strict - Mode B (container): persistent Ubuntu container with /nix/store bind-mount, identity-hash-based recreation, GC root protection, symlink-based updates - Add HERMES_MANAGED guards blocking CLI config mutation (config set, setup, gateway install/uninstall) when running under NixOS module - Add nix/checks.nix with build-time verification (binary, CLI, managed guard) - Remove container.nix (no Nix-built OCI image; pulls ubuntu:24.04 at runtime) - Simplify packages.nix (drop fetchFromGitHub submodules, PYTHONPATH wrappers) - Rewrite docs/nixos-setup.md with full options reference, container architecture, secrets management, and troubleshooting guide Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * Update config.py * feat(nix): add CI workflow and enhanced build checks - GitHub Actions workflow for nix flake check + build on linux/macOS - Entry point sync check to catch pyproject.toml drift - Expanded managed-guard check to cover config edit - Wrap hermes-acp binary in Nix package - Fix Path type mismatch in is_managed() * Update MCP server package name; bundled skills support * fix reading .env. instead have container user a common mounted .env file * feat(nix): container entrypoint with privilege drop and sudo provisioning Container was running as non-root via --user, which broke apt/pip installs and caused crashes when $HOME didn't exist. Replace --user with a Nix-built entrypoint script that provisions the hermes user, sudo (NOPASSWD), and /home/hermes inside the container on first boot, then drops privileges via setpriv. Writable layer persists so setup only runs once. Also expands MCP server options to support HTTP transport and sampling. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix group and user creation in container mode * feat(nix): persistent /home/hermes and MESSAGING_CWD in container mode Container mode now bind-mounts ${stateDir}/home to /home/hermes so the agent's home directory survives container recreation. Previously it lived in the writable layer and was lost on image/volume/options changes. Also passes MESSAGING_CWD to the container so the agent finds its workspace and documents, matching native mode behavior. Other changes: - Extract containerDataDir/containerHomeDir bindings (no more magic strings) - Fix entrypoint chown to run unconditionally (volume mounts always exist) - Add schema field to container identity hash for auto-recreation - Add idempotency test (Scenario G) to config-roundtrip check * docs: add Nix & NixOS setup guide to docs site Add comprehensive Nix documentation to the Docusaurus site at website/docs/getting-started/nix-setup.md, covering nix run/profile install, NixOS module (native + container modes), declarative settings, secrets management, MCP servers, managed mode, container architecture, dev shell, flake checks, and full options reference. - Register nix-setup in sidebar after installation page - Add Nix callout tip to installation.md linking to new guide - Add canonical version pointer in docs/nixos-setup.md * docs: remove docs/nixos-setup.md, consolidate into website docs Backfill missing details (restart/restartSec in full example, gateway.pid, 0750 permissions, docker inspect commands) into the canonical website/docs/getting-started/nix-setup.md and delete the old standalone file. * fix(nix): add compression.protect_last_n and target_ratio to config-keys.json New keys were added to DEFAULT_CONFIG on main, causing the config-drift check to fail in CI. * fix(nix): skip checks on aarch64-darwin (onnxruntime wheel missing) The full Python venv includes onnxruntime (via faster-whisper/STT) which lacks a compatible uv2nix wheel on aarch64-darwin. Gate all checks behind stdenv.hostPlatform.isLinux. The package and devShell still evaluate on macOS. * fix(nix): skip flake check and build on macOS CI onnxruntime (transitive dep via faster-whisper) lacks a compatible uv2nix wheel on aarch64-darwin. Run full checks and build on Linux only; macOS CI verifies the flake evaluates without building. * fix(nix): preserve container writable layer across nixos-rebuild The container identity hash included the entrypoint's Nix store path, which changes on every nixpkgs update (due to runtimeShell/stdenv input-addressing). This caused false-positive identity mismatches, triggering container recreation and losing the persistent writable layer. - Use stable symlink (current-entrypoint) like current-package already does - Remove entrypoint from identity hash (only image/volumes/options matter) - Add GC root for entrypoint so nix-collect-garbage doesn't break it - Remove global HERMES_HOME env var from addToSystemPackages (conflicted with interactive CLI use, service already sets its own) --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-26 01:08:02 +05:30
# =============================================================================
# Managed mode (NixOS declarative config)
# =============================================================================
_MANAGED_TRUE_VALUES = ("true", "1", "yes")
_MANAGED_SYSTEM_NAMES = {
"brew": "Homebrew",
"homebrew": "Homebrew",
"nix": "NixOS",
"nixos": "NixOS",
}
def get_managed_system() -> Optional[str]:
"""Return the package manager owning this install, if any."""
raw = os.getenv("HERMES_MANAGED", "").strip()
if raw:
normalized = raw.lower()
if normalized in _MANAGED_TRUE_VALUES:
return "NixOS"
return _MANAGED_SYSTEM_NAMES.get(normalized, raw)
managed_marker = get_hermes_home() / ".managed"
if managed_marker.exists():
return "NixOS"
return None
feat: nix flake — uv2nix build, NixOS module, persistent container mode (#20) * feat: nix flake, uv2nix build, dev shell and home manager * fixed nix run, updated docs for setup * feat(nix): NixOS module with persistent container mode, managed guards, checks - Replace homeModules.nix with nixosModules.nix (two deployment modes) - Mode A (native): hardened systemd service with ProtectSystem=strict - Mode B (container): persistent Ubuntu container with /nix/store bind-mount, identity-hash-based recreation, GC root protection, symlink-based updates - Add HERMES_MANAGED guards blocking CLI config mutation (config set, setup, gateway install/uninstall) when running under NixOS module - Add nix/checks.nix with build-time verification (binary, CLI, managed guard) - Remove container.nix (no Nix-built OCI image; pulls ubuntu:24.04 at runtime) - Simplify packages.nix (drop fetchFromGitHub submodules, PYTHONPATH wrappers) - Rewrite docs/nixos-setup.md with full options reference, container architecture, secrets management, and troubleshooting guide Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * Update config.py * feat(nix): add CI workflow and enhanced build checks - GitHub Actions workflow for nix flake check + build on linux/macOS - Entry point sync check to catch pyproject.toml drift - Expanded managed-guard check to cover config edit - Wrap hermes-acp binary in Nix package - Fix Path type mismatch in is_managed() * Update MCP server package name; bundled skills support * fix reading .env. instead have container user a common mounted .env file * feat(nix): container entrypoint with privilege drop and sudo provisioning Container was running as non-root via --user, which broke apt/pip installs and caused crashes when $HOME didn't exist. Replace --user with a Nix-built entrypoint script that provisions the hermes user, sudo (NOPASSWD), and /home/hermes inside the container on first boot, then drops privileges via setpriv. Writable layer persists so setup only runs once. Also expands MCP server options to support HTTP transport and sampling. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix group and user creation in container mode * feat(nix): persistent /home/hermes and MESSAGING_CWD in container mode Container mode now bind-mounts ${stateDir}/home to /home/hermes so the agent's home directory survives container recreation. Previously it lived in the writable layer and was lost on image/volume/options changes. Also passes MESSAGING_CWD to the container so the agent finds its workspace and documents, matching native mode behavior. Other changes: - Extract containerDataDir/containerHomeDir bindings (no more magic strings) - Fix entrypoint chown to run unconditionally (volume mounts always exist) - Add schema field to container identity hash for auto-recreation - Add idempotency test (Scenario G) to config-roundtrip check * docs: add Nix & NixOS setup guide to docs site Add comprehensive Nix documentation to the Docusaurus site at website/docs/getting-started/nix-setup.md, covering nix run/profile install, NixOS module (native + container modes), declarative settings, secrets management, MCP servers, managed mode, container architecture, dev shell, flake checks, and full options reference. - Register nix-setup in sidebar after installation page - Add Nix callout tip to installation.md linking to new guide - Add canonical version pointer in docs/nixos-setup.md * docs: remove docs/nixos-setup.md, consolidate into website docs Backfill missing details (restart/restartSec in full example, gateway.pid, 0750 permissions, docker inspect commands) into the canonical website/docs/getting-started/nix-setup.md and delete the old standalone file. * fix(nix): add compression.protect_last_n and target_ratio to config-keys.json New keys were added to DEFAULT_CONFIG on main, causing the config-drift check to fail in CI. * fix(nix): skip checks on aarch64-darwin (onnxruntime wheel missing) The full Python venv includes onnxruntime (via faster-whisper/STT) which lacks a compatible uv2nix wheel on aarch64-darwin. Gate all checks behind stdenv.hostPlatform.isLinux. The package and devShell still evaluate on macOS. * fix(nix): skip flake check and build on macOS CI onnxruntime (transitive dep via faster-whisper) lacks a compatible uv2nix wheel on aarch64-darwin. Run full checks and build on Linux only; macOS CI verifies the flake evaluates without building. * fix(nix): preserve container writable layer across nixos-rebuild The container identity hash included the entrypoint's Nix store path, which changes on every nixpkgs update (due to runtimeShell/stdenv input-addressing). This caused false-positive identity mismatches, triggering container recreation and losing the persistent writable layer. - Use stable symlink (current-entrypoint) like current-package already does - Remove entrypoint from identity hash (only image/volumes/options matter) - Add GC root for entrypoint so nix-collect-garbage doesn't break it - Remove global HERMES_HOME env var from addToSystemPackages (conflicted with interactive CLI use, service already sets its own) --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-26 01:08:02 +05:30
def is_managed() -> bool:
"""Check if Hermes is running in package-manager-managed mode.
feat: nix flake — uv2nix build, NixOS module, persistent container mode (#20) * feat: nix flake, uv2nix build, dev shell and home manager * fixed nix run, updated docs for setup * feat(nix): NixOS module with persistent container mode, managed guards, checks - Replace homeModules.nix with nixosModules.nix (two deployment modes) - Mode A (native): hardened systemd service with ProtectSystem=strict - Mode B (container): persistent Ubuntu container with /nix/store bind-mount, identity-hash-based recreation, GC root protection, symlink-based updates - Add HERMES_MANAGED guards blocking CLI config mutation (config set, setup, gateway install/uninstall) when running under NixOS module - Add nix/checks.nix with build-time verification (binary, CLI, managed guard) - Remove container.nix (no Nix-built OCI image; pulls ubuntu:24.04 at runtime) - Simplify packages.nix (drop fetchFromGitHub submodules, PYTHONPATH wrappers) - Rewrite docs/nixos-setup.md with full options reference, container architecture, secrets management, and troubleshooting guide Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * Update config.py * feat(nix): add CI workflow and enhanced build checks - GitHub Actions workflow for nix flake check + build on linux/macOS - Entry point sync check to catch pyproject.toml drift - Expanded managed-guard check to cover config edit - Wrap hermes-acp binary in Nix package - Fix Path type mismatch in is_managed() * Update MCP server package name; bundled skills support * fix reading .env. instead have container user a common mounted .env file * feat(nix): container entrypoint with privilege drop and sudo provisioning Container was running as non-root via --user, which broke apt/pip installs and caused crashes when $HOME didn't exist. Replace --user with a Nix-built entrypoint script that provisions the hermes user, sudo (NOPASSWD), and /home/hermes inside the container on first boot, then drops privileges via setpriv. Writable layer persists so setup only runs once. Also expands MCP server options to support HTTP transport and sampling. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix group and user creation in container mode * feat(nix): persistent /home/hermes and MESSAGING_CWD in container mode Container mode now bind-mounts ${stateDir}/home to /home/hermes so the agent's home directory survives container recreation. Previously it lived in the writable layer and was lost on image/volume/options changes. Also passes MESSAGING_CWD to the container so the agent finds its workspace and documents, matching native mode behavior. Other changes: - Extract containerDataDir/containerHomeDir bindings (no more magic strings) - Fix entrypoint chown to run unconditionally (volume mounts always exist) - Add schema field to container identity hash for auto-recreation - Add idempotency test (Scenario G) to config-roundtrip check * docs: add Nix & NixOS setup guide to docs site Add comprehensive Nix documentation to the Docusaurus site at website/docs/getting-started/nix-setup.md, covering nix run/profile install, NixOS module (native + container modes), declarative settings, secrets management, MCP servers, managed mode, container architecture, dev shell, flake checks, and full options reference. - Register nix-setup in sidebar after installation page - Add Nix callout tip to installation.md linking to new guide - Add canonical version pointer in docs/nixos-setup.md * docs: remove docs/nixos-setup.md, consolidate into website docs Backfill missing details (restart/restartSec in full example, gateway.pid, 0750 permissions, docker inspect commands) into the canonical website/docs/getting-started/nix-setup.md and delete the old standalone file. * fix(nix): add compression.protect_last_n and target_ratio to config-keys.json New keys were added to DEFAULT_CONFIG on main, causing the config-drift check to fail in CI. * fix(nix): skip checks on aarch64-darwin (onnxruntime wheel missing) The full Python venv includes onnxruntime (via faster-whisper/STT) which lacks a compatible uv2nix wheel on aarch64-darwin. Gate all checks behind stdenv.hostPlatform.isLinux. The package and devShell still evaluate on macOS. * fix(nix): skip flake check and build on macOS CI onnxruntime (transitive dep via faster-whisper) lacks a compatible uv2nix wheel on aarch64-darwin. Run full checks and build on Linux only; macOS CI verifies the flake evaluates without building. * fix(nix): preserve container writable layer across nixos-rebuild The container identity hash included the entrypoint's Nix store path, which changes on every nixpkgs update (due to runtimeShell/stdenv input-addressing). This caused false-positive identity mismatches, triggering container recreation and losing the persistent writable layer. - Use stable symlink (current-entrypoint) like current-package already does - Remove entrypoint from identity hash (only image/volumes/options matter) - Add GC root for entrypoint so nix-collect-garbage doesn't break it - Remove global HERMES_HOME env var from addToSystemPackages (conflicted with interactive CLI use, service already sets its own) --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-26 01:08:02 +05:30
Two signals: the HERMES_MANAGED env var (set by the systemd service),
or a .managed marker file in HERMES_HOME (set by the NixOS activation
script, so interactive shells also see it).
"""
return get_managed_system() is not None
def get_managed_update_command() -> Optional[str]:
"""Return the preferred upgrade command for a managed install."""
managed_system = get_managed_system()
if managed_system == "Homebrew":
return "brew upgrade hermes-agent"
if managed_system == "NixOS":
return "sudo nixos-rebuild switch"
return None
def recommended_update_command() -> str:
"""Return the best update command for the current installation."""
return get_managed_update_command() or "hermes update"
def format_managed_message(action: str = "modify this Hermes installation") -> str:
"""Build a user-facing error for managed installs."""
managed_system = get_managed_system() or "a package manager"
raw = os.getenv("HERMES_MANAGED", "").strip().lower()
if managed_system == "NixOS":
env_hint = "true" if raw in _MANAGED_TRUE_VALUES else raw or "true"
return (
f"Cannot {action}: this Hermes installation is managed by NixOS "
f"(HERMES_MANAGED={env_hint}).\n"
"Edit services.hermes-agent.settings in your configuration.nix and run:\n"
" sudo nixos-rebuild switch"
)
if managed_system == "Homebrew":
env_hint = raw or "homebrew"
return (
f"Cannot {action}: this Hermes installation is managed by Homebrew "
f"(HERMES_MANAGED={env_hint}).\n"
"Use:\n"
" brew upgrade hermes-agent"
)
return (
f"Cannot {action}: this Hermes installation is managed by {managed_system}.\n"
"Use your package manager to upgrade or reinstall Hermes."
)
feat: nix flake — uv2nix build, NixOS module, persistent container mode (#20) * feat: nix flake, uv2nix build, dev shell and home manager * fixed nix run, updated docs for setup * feat(nix): NixOS module with persistent container mode, managed guards, checks - Replace homeModules.nix with nixosModules.nix (two deployment modes) - Mode A (native): hardened systemd service with ProtectSystem=strict - Mode B (container): persistent Ubuntu container with /nix/store bind-mount, identity-hash-based recreation, GC root protection, symlink-based updates - Add HERMES_MANAGED guards blocking CLI config mutation (config set, setup, gateway install/uninstall) when running under NixOS module - Add nix/checks.nix with build-time verification (binary, CLI, managed guard) - Remove container.nix (no Nix-built OCI image; pulls ubuntu:24.04 at runtime) - Simplify packages.nix (drop fetchFromGitHub submodules, PYTHONPATH wrappers) - Rewrite docs/nixos-setup.md with full options reference, container architecture, secrets management, and troubleshooting guide Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * Update config.py * feat(nix): add CI workflow and enhanced build checks - GitHub Actions workflow for nix flake check + build on linux/macOS - Entry point sync check to catch pyproject.toml drift - Expanded managed-guard check to cover config edit - Wrap hermes-acp binary in Nix package - Fix Path type mismatch in is_managed() * Update MCP server package name; bundled skills support * fix reading .env. instead have container user a common mounted .env file * feat(nix): container entrypoint with privilege drop and sudo provisioning Container was running as non-root via --user, which broke apt/pip installs and caused crashes when $HOME didn't exist. Replace --user with a Nix-built entrypoint script that provisions the hermes user, sudo (NOPASSWD), and /home/hermes inside the container on first boot, then drops privileges via setpriv. Writable layer persists so setup only runs once. Also expands MCP server options to support HTTP transport and sampling. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix group and user creation in container mode * feat(nix): persistent /home/hermes and MESSAGING_CWD in container mode Container mode now bind-mounts ${stateDir}/home to /home/hermes so the agent's home directory survives container recreation. Previously it lived in the writable layer and was lost on image/volume/options changes. Also passes MESSAGING_CWD to the container so the agent finds its workspace and documents, matching native mode behavior. Other changes: - Extract containerDataDir/containerHomeDir bindings (no more magic strings) - Fix entrypoint chown to run unconditionally (volume mounts always exist) - Add schema field to container identity hash for auto-recreation - Add idempotency test (Scenario G) to config-roundtrip check * docs: add Nix & NixOS setup guide to docs site Add comprehensive Nix documentation to the Docusaurus site at website/docs/getting-started/nix-setup.md, covering nix run/profile install, NixOS module (native + container modes), declarative settings, secrets management, MCP servers, managed mode, container architecture, dev shell, flake checks, and full options reference. - Register nix-setup in sidebar after installation page - Add Nix callout tip to installation.md linking to new guide - Add canonical version pointer in docs/nixos-setup.md * docs: remove docs/nixos-setup.md, consolidate into website docs Backfill missing details (restart/restartSec in full example, gateway.pid, 0750 permissions, docker inspect commands) into the canonical website/docs/getting-started/nix-setup.md and delete the old standalone file. * fix(nix): add compression.protect_last_n and target_ratio to config-keys.json New keys were added to DEFAULT_CONFIG on main, causing the config-drift check to fail in CI. * fix(nix): skip checks on aarch64-darwin (onnxruntime wheel missing) The full Python venv includes onnxruntime (via faster-whisper/STT) which lacks a compatible uv2nix wheel on aarch64-darwin. Gate all checks behind stdenv.hostPlatform.isLinux. The package and devShell still evaluate on macOS. * fix(nix): skip flake check and build on macOS CI onnxruntime (transitive dep via faster-whisper) lacks a compatible uv2nix wheel on aarch64-darwin. Run full checks and build on Linux only; macOS CI verifies the flake evaluates without building. * fix(nix): preserve container writable layer across nixos-rebuild The container identity hash included the entrypoint's Nix store path, which changes on every nixpkgs update (due to runtimeShell/stdenv input-addressing). This caused false-positive identity mismatches, triggering container recreation and losing the persistent writable layer. - Use stable symlink (current-entrypoint) like current-package already does - Remove entrypoint from identity hash (only image/volumes/options matter) - Add GC root for entrypoint so nix-collect-garbage doesn't break it - Remove global HERMES_HOME env var from addToSystemPackages (conflicted with interactive CLI use, service already sets its own) --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-26 01:08:02 +05:30
def managed_error(action: str = "modify configuration"):
"""Print user-friendly error for managed mode."""
print(format_managed_message(action), file=sys.stderr)
feat: nix flake — uv2nix build, NixOS module, persistent container mode (#20) * feat: nix flake, uv2nix build, dev shell and home manager * fixed nix run, updated docs for setup * feat(nix): NixOS module with persistent container mode, managed guards, checks - Replace homeModules.nix with nixosModules.nix (two deployment modes) - Mode A (native): hardened systemd service with ProtectSystem=strict - Mode B (container): persistent Ubuntu container with /nix/store bind-mount, identity-hash-based recreation, GC root protection, symlink-based updates - Add HERMES_MANAGED guards blocking CLI config mutation (config set, setup, gateway install/uninstall) when running under NixOS module - Add nix/checks.nix with build-time verification (binary, CLI, managed guard) - Remove container.nix (no Nix-built OCI image; pulls ubuntu:24.04 at runtime) - Simplify packages.nix (drop fetchFromGitHub submodules, PYTHONPATH wrappers) - Rewrite docs/nixos-setup.md with full options reference, container architecture, secrets management, and troubleshooting guide Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * Update config.py * feat(nix): add CI workflow and enhanced build checks - GitHub Actions workflow for nix flake check + build on linux/macOS - Entry point sync check to catch pyproject.toml drift - Expanded managed-guard check to cover config edit - Wrap hermes-acp binary in Nix package - Fix Path type mismatch in is_managed() * Update MCP server package name; bundled skills support * fix reading .env. instead have container user a common mounted .env file * feat(nix): container entrypoint with privilege drop and sudo provisioning Container was running as non-root via --user, which broke apt/pip installs and caused crashes when $HOME didn't exist. Replace --user with a Nix-built entrypoint script that provisions the hermes user, sudo (NOPASSWD), and /home/hermes inside the container on first boot, then drops privileges via setpriv. Writable layer persists so setup only runs once. Also expands MCP server options to support HTTP transport and sampling. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix group and user creation in container mode * feat(nix): persistent /home/hermes and MESSAGING_CWD in container mode Container mode now bind-mounts ${stateDir}/home to /home/hermes so the agent's home directory survives container recreation. Previously it lived in the writable layer and was lost on image/volume/options changes. Also passes MESSAGING_CWD to the container so the agent finds its workspace and documents, matching native mode behavior. Other changes: - Extract containerDataDir/containerHomeDir bindings (no more magic strings) - Fix entrypoint chown to run unconditionally (volume mounts always exist) - Add schema field to container identity hash for auto-recreation - Add idempotency test (Scenario G) to config-roundtrip check * docs: add Nix & NixOS setup guide to docs site Add comprehensive Nix documentation to the Docusaurus site at website/docs/getting-started/nix-setup.md, covering nix run/profile install, NixOS module (native + container modes), declarative settings, secrets management, MCP servers, managed mode, container architecture, dev shell, flake checks, and full options reference. - Register nix-setup in sidebar after installation page - Add Nix callout tip to installation.md linking to new guide - Add canonical version pointer in docs/nixos-setup.md * docs: remove docs/nixos-setup.md, consolidate into website docs Backfill missing details (restart/restartSec in full example, gateway.pid, 0750 permissions, docker inspect commands) into the canonical website/docs/getting-started/nix-setup.md and delete the old standalone file. * fix(nix): add compression.protect_last_n and target_ratio to config-keys.json New keys were added to DEFAULT_CONFIG on main, causing the config-drift check to fail in CI. * fix(nix): skip checks on aarch64-darwin (onnxruntime wheel missing) The full Python venv includes onnxruntime (via faster-whisper/STT) which lacks a compatible uv2nix wheel on aarch64-darwin. Gate all checks behind stdenv.hostPlatform.isLinux. The package and devShell still evaluate on macOS. * fix(nix): skip flake check and build on macOS CI onnxruntime (transitive dep via faster-whisper) lacks a compatible uv2nix wheel on aarch64-darwin. Run full checks and build on Linux only; macOS CI verifies the flake evaluates without building. * fix(nix): preserve container writable layer across nixos-rebuild The container identity hash included the entrypoint's Nix store path, which changes on every nixpkgs update (due to runtimeShell/stdenv input-addressing). This caused false-positive identity mismatches, triggering container recreation and losing the persistent writable layer. - Use stable symlink (current-entrypoint) like current-package already does - Remove entrypoint from identity hash (only image/volumes/options matter) - Add GC root for entrypoint so nix-collect-garbage doesn't break it - Remove global HERMES_HOME env var from addToSystemPackages (conflicted with interactive CLI use, service already sets its own) --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-26 01:08:02 +05:30
feat(nix): container-aware CLI — auto-route into managed container (#7543) * feat(nix): container-aware CLI — auto-route all subcommands into managed container When container.enable = true, the host `hermes` CLI transparently execs every subcommand into the managed Docker/Podman container. A symlink bridge (~/.hermes -> /var/lib/hermes/.hermes) unifies state between host and container so sessions, config, and memories are shared. CLI changes: - Global routing before subcommand dispatch (all commands forwarded) - docker exec with -u exec_user, env passthrough (TERM, COLORTERM, LANG, LC_ALL), TTY-aware flags - Retry with spinner on failure (TTY: 5s, non-TTY: 10s silent) - Hard fail instead of silent fallback - HERMES_DEV=1 env var bypasses routing for development - No routing messages (invisible to user) NixOS module changes: - container.hostUsers option: lists users who get ~/.hermes symlink and automatic hermes group membership - Activation script creates symlink bridge (with backup of existing ~/.hermes dirs), writes exec_user to .container-mode - Cleanup on disable: removes symlinks + .container-mode + stops service - Warning when hostUsers set without addToSystemPackages * fix: address review — reuse sudo var, add chown -h on symlink update - hermes_cli/main.py: reuse the existing `sudo` variable instead of redundant `shutil.which("sudo")` call that could return None - nix/nixosModules.nix: add missing `chown -h` when updating an existing symlink target so ownership stays consistent with the fresh-create and backup-replace branches * fix: address remaining review items from cursor bugbot - hermes_cli/main.py: move container routing BEFORE parse_args() so --help, unrecognised flags, and all subcommands are forwarded transparently into the container instead of being intercepted by argparse on the host (high severity) - nix/nixosModules.nix: resolve home dirs via config.users.users.${user}.home instead of hardcoding /home/${user}, supporting users with custom home directories (medium severity) - nix/nixosModules.nix: gate hostUsers group membership on container.enable so setting hostUsers without container mode doesn't silently add users to the hermes group (low severity) * fix: simplify container routing — execvp, no retries, let it crash - Replace subprocess.run retry loop with os.execvp (no idle parent process) - Extract _probe_container helper for sudo detection with 15s timeout - Narrow exception handling: FileNotFoundError only in get_container_exec_info, catch TimeoutExpired specifically, remove silent except Exception: pass - Collapse needs_sudo + sudo into single sudo_path variable - Simplify NixOS symlink creation from 4 branches to 2 - Gate NixOS sudoers hint with "On NixOS:" prefix - Full test rewrite: 18 tests covering execvp, sudo probe, timeout, permissions --------- Co-authored-by: Hermes Agent <hermes@nousresearch.com>
2026-04-11 16:47:46 -07:00
# =============================================================================
# Container-aware CLI (NixOS container mode)
# =============================================================================
def get_container_exec_info() -> Optional[dict]:
"""Read container mode metadata from HERMES_HOME/.container-mode.
Returns a dict with keys: backend, container_name, exec_user, hermes_bin
or None if container mode is not active, we're already inside the
container, or HERMES_DEV=1 is set.
The .container-mode file is written by the NixOS activation script when
container.enable = true. It tells the host CLI to exec into the container
instead of running locally.
"""
if os.environ.get("HERMES_DEV") == "1":
return None
from hermes_constants import is_container
if is_container():
feat(nix): container-aware CLI — auto-route into managed container (#7543) * feat(nix): container-aware CLI — auto-route all subcommands into managed container When container.enable = true, the host `hermes` CLI transparently execs every subcommand into the managed Docker/Podman container. A symlink bridge (~/.hermes -> /var/lib/hermes/.hermes) unifies state between host and container so sessions, config, and memories are shared. CLI changes: - Global routing before subcommand dispatch (all commands forwarded) - docker exec with -u exec_user, env passthrough (TERM, COLORTERM, LANG, LC_ALL), TTY-aware flags - Retry with spinner on failure (TTY: 5s, non-TTY: 10s silent) - Hard fail instead of silent fallback - HERMES_DEV=1 env var bypasses routing for development - No routing messages (invisible to user) NixOS module changes: - container.hostUsers option: lists users who get ~/.hermes symlink and automatic hermes group membership - Activation script creates symlink bridge (with backup of existing ~/.hermes dirs), writes exec_user to .container-mode - Cleanup on disable: removes symlinks + .container-mode + stops service - Warning when hostUsers set without addToSystemPackages * fix: address review — reuse sudo var, add chown -h on symlink update - hermes_cli/main.py: reuse the existing `sudo` variable instead of redundant `shutil.which("sudo")` call that could return None - nix/nixosModules.nix: add missing `chown -h` when updating an existing symlink target so ownership stays consistent with the fresh-create and backup-replace branches * fix: address remaining review items from cursor bugbot - hermes_cli/main.py: move container routing BEFORE parse_args() so --help, unrecognised flags, and all subcommands are forwarded transparently into the container instead of being intercepted by argparse on the host (high severity) - nix/nixosModules.nix: resolve home dirs via config.users.users.${user}.home instead of hardcoding /home/${user}, supporting users with custom home directories (medium severity) - nix/nixosModules.nix: gate hostUsers group membership on container.enable so setting hostUsers without container mode doesn't silently add users to the hermes group (low severity) * fix: simplify container routing — execvp, no retries, let it crash - Replace subprocess.run retry loop with os.execvp (no idle parent process) - Extract _probe_container helper for sudo detection with 15s timeout - Narrow exception handling: FileNotFoundError only in get_container_exec_info, catch TimeoutExpired specifically, remove silent except Exception: pass - Collapse needs_sudo + sudo into single sudo_path variable - Simplify NixOS symlink creation from 4 branches to 2 - Gate NixOS sudoers hint with "On NixOS:" prefix - Full test rewrite: 18 tests covering execvp, sudo probe, timeout, permissions --------- Co-authored-by: Hermes Agent <hermes@nousresearch.com>
2026-04-11 16:47:46 -07:00
return None
container_mode_file = get_hermes_home() / ".container-mode"
try:
info = {}
with open(container_mode_file, "r") as f:
for line in f:
line = line.strip()
if "=" in line and not line.startswith("#"):
key, _, value = line.partition("=")
info[key.strip()] = value.strip()
except FileNotFoundError:
return None
# All other exceptions (PermissionError, malformed data, etc.) propagate
backend = info.get("backend", "docker")
container_name = info.get("container_name", "hermes-agent")
exec_user = info.get("exec_user", "hermes")
hermes_bin = info.get("hermes_bin", "/data/current-package/bin/hermes")
return {
"backend": backend,
"container_name": container_name,
"exec_user": exec_user,
"hermes_bin": hermes_bin,
}
# =============================================================================
# Config paths
# =============================================================================
# Re-export from hermes_constants — canonical definition lives there.
from hermes_constants import get_hermes_home # noqa: F811,E402
def get_config_path() -> Path:
"""Get the main config file path."""
return get_hermes_home() / "config.yaml"
def get_env_path() -> Path:
"""Get the .env file path (for API keys)."""
return get_hermes_home() / ".env"
def get_project_root() -> Path:
"""Get the project installation directory."""
return Path(__file__).parent.parent.resolve()
def _secure_dir(path):
"""Set directory to owner-only access (0700 by default). No-op on Windows.
fix(nix): make addToSystemPackages fully functional for interactive CLI (#6317) * fix(nix): export HERMES_HOME system-wide when addToSystemPackages is true The `addToSystemPackages` option's documentation (and the `:::tip` block in `website/docs/getting-started/nix-setup.md`) promises that enabling it both puts the `hermes` CLI on PATH and sets `HERMES_HOME` system-wide so interactive shells share state with the gateway service. The module only did the former, so running `hermes` in a user shell silently created a separate `~/.hermes/` directory instead of the managed `${stateDir}/.hermes`. Implement the documented behavior by also setting `environment.variables.HERMES_HOME = "${cfg.stateDir}/.hermes"` in the same mkIf block, and update the option description to match. Fixes #6044 * fix(nix): preserve group-readable permissions in managed mode The NixOS module sets HERMES_HOME directories to 0750 and files to 0640 so interactive users in the hermes group can share state with the gateway service. Two issues prevented this from working: 1. hermes_cli/config.py: _secure_dir() unconditionally chmod'd HERMES_HOME to 0700 on every startup, overwriting the NixOS module's 0750. Similarly, _secure_file() forced 0600 on config files. Both now skip in managed mode (detected via .managed marker or HERMES_MANAGED env var). 2. nix/nixosModules.nix: the .env file was created with 0600 (owner-only), while config.yaml was already 0640 (group-readable). Changed to 0640 for consistency — users granted hermes group membership should be able to read the managed .env. Verified with a NixOS VM integration test: a normal user in the hermes group can now run `hermes version` and `hermes config` against the managed HERMES_HOME without PermissionError. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: zerone0x <zerone0x@users.noreply.github.com> Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-08 15:39:53 -07:00
Skipped in managed mode the NixOS module sets group-readable
permissions (0750) so interactive users in the hermes group can
share state with the gateway service.
The mode can be overridden via the HERMES_HOME_MODE environment variable
(e.g. HERMES_HOME_MODE=0701) for deployments where a web server (nginx,
caddy, etc.) needs to traverse HERMES_HOME to reach a served subdirectory.
The execute-only bit on a directory permits cd-through without exposing
directory listings.
fix(nix): make addToSystemPackages fully functional for interactive CLI (#6317) * fix(nix): export HERMES_HOME system-wide when addToSystemPackages is true The `addToSystemPackages` option's documentation (and the `:::tip` block in `website/docs/getting-started/nix-setup.md`) promises that enabling it both puts the `hermes` CLI on PATH and sets `HERMES_HOME` system-wide so interactive shells share state with the gateway service. The module only did the former, so running `hermes` in a user shell silently created a separate `~/.hermes/` directory instead of the managed `${stateDir}/.hermes`. Implement the documented behavior by also setting `environment.variables.HERMES_HOME = "${cfg.stateDir}/.hermes"` in the same mkIf block, and update the option description to match. Fixes #6044 * fix(nix): preserve group-readable permissions in managed mode The NixOS module sets HERMES_HOME directories to 0750 and files to 0640 so interactive users in the hermes group can share state with the gateway service. Two issues prevented this from working: 1. hermes_cli/config.py: _secure_dir() unconditionally chmod'd HERMES_HOME to 0700 on every startup, overwriting the NixOS module's 0750. Similarly, _secure_file() forced 0600 on config files. Both now skip in managed mode (detected via .managed marker or HERMES_MANAGED env var). 2. nix/nixosModules.nix: the .env file was created with 0600 (owner-only), while config.yaml was already 0640 (group-readable). Changed to 0640 for consistency — users granted hermes group membership should be able to read the managed .env. Verified with a NixOS VM integration test: a normal user in the hermes group can now run `hermes version` and `hermes config` against the managed HERMES_HOME without PermissionError. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: zerone0x <zerone0x@users.noreply.github.com> Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-08 15:39:53 -07:00
"""
if is_managed():
return
try:
mode_str = os.environ.get("HERMES_HOME_MODE", "").strip()
mode = int(mode_str, 8) if mode_str else 0o700
except ValueError:
mode = 0o700
try:
os.chmod(path, mode)
except (OSError, NotImplementedError):
pass
def _is_container() -> bool:
"""Detect if we're running inside a Docker/Podman/LXC container.
When Hermes runs in a container with volume-mounted config files, forcing
0o600 permissions breaks multi-process setups where the gateway and
dashboard run as different UIDs or the volume mount requires broader
permissions.
"""
# Explicit opt-out
if os.environ.get("HERMES_CONTAINER") or os.environ.get("HERMES_SKIP_CHMOD"):
return True
# Docker / Podman marker file
if os.path.exists("/.dockerenv"):
return True
# LXC / cgroup-based detection
try:
with open("/proc/1/cgroup", "r") as f:
cgroup_content = f.read()
if "docker" in cgroup_content or "lxc" in cgroup_content or "kubepods" in cgroup_content:
return True
except (OSError, IOError):
pass
return False
def _secure_file(path):
fix(nix): make addToSystemPackages fully functional for interactive CLI (#6317) * fix(nix): export HERMES_HOME system-wide when addToSystemPackages is true The `addToSystemPackages` option's documentation (and the `:::tip` block in `website/docs/getting-started/nix-setup.md`) promises that enabling it both puts the `hermes` CLI on PATH and sets `HERMES_HOME` system-wide so interactive shells share state with the gateway service. The module only did the former, so running `hermes` in a user shell silently created a separate `~/.hermes/` directory instead of the managed `${stateDir}/.hermes`. Implement the documented behavior by also setting `environment.variables.HERMES_HOME = "${cfg.stateDir}/.hermes"` in the same mkIf block, and update the option description to match. Fixes #6044 * fix(nix): preserve group-readable permissions in managed mode The NixOS module sets HERMES_HOME directories to 0750 and files to 0640 so interactive users in the hermes group can share state with the gateway service. Two issues prevented this from working: 1. hermes_cli/config.py: _secure_dir() unconditionally chmod'd HERMES_HOME to 0700 on every startup, overwriting the NixOS module's 0750. Similarly, _secure_file() forced 0600 on config files. Both now skip in managed mode (detected via .managed marker or HERMES_MANAGED env var). 2. nix/nixosModules.nix: the .env file was created with 0600 (owner-only), while config.yaml was already 0640 (group-readable). Changed to 0640 for consistency — users granted hermes group membership should be able to read the managed .env. Verified with a NixOS VM integration test: a normal user in the hermes group can now run `hermes version` and `hermes config` against the managed HERMES_HOME without PermissionError. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: zerone0x <zerone0x@users.noreply.github.com> Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-08 15:39:53 -07:00
"""Set file to owner-only read/write (0600). No-op on Windows.
Skipped in managed mode the NixOS activation script sets
group-readable permissions (0640) on config files.
Skipped in containers Docker/Podman volume mounts often need broader
permissions. Set HERMES_SKIP_CHMOD=1 to force-skip on other systems.
fix(nix): make addToSystemPackages fully functional for interactive CLI (#6317) * fix(nix): export HERMES_HOME system-wide when addToSystemPackages is true The `addToSystemPackages` option's documentation (and the `:::tip` block in `website/docs/getting-started/nix-setup.md`) promises that enabling it both puts the `hermes` CLI on PATH and sets `HERMES_HOME` system-wide so interactive shells share state with the gateway service. The module only did the former, so running `hermes` in a user shell silently created a separate `~/.hermes/` directory instead of the managed `${stateDir}/.hermes`. Implement the documented behavior by also setting `environment.variables.HERMES_HOME = "${cfg.stateDir}/.hermes"` in the same mkIf block, and update the option description to match. Fixes #6044 * fix(nix): preserve group-readable permissions in managed mode The NixOS module sets HERMES_HOME directories to 0750 and files to 0640 so interactive users in the hermes group can share state with the gateway service. Two issues prevented this from working: 1. hermes_cli/config.py: _secure_dir() unconditionally chmod'd HERMES_HOME to 0700 on every startup, overwriting the NixOS module's 0750. Similarly, _secure_file() forced 0600 on config files. Both now skip in managed mode (detected via .managed marker or HERMES_MANAGED env var). 2. nix/nixosModules.nix: the .env file was created with 0600 (owner-only), while config.yaml was already 0640 (group-readable). Changed to 0640 for consistency — users granted hermes group membership should be able to read the managed .env. Verified with a NixOS VM integration test: a normal user in the hermes group can now run `hermes version` and `hermes config` against the managed HERMES_HOME without PermissionError. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: zerone0x <zerone0x@users.noreply.github.com> Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-08 15:39:53 -07:00
"""
if is_managed() or _is_container():
fix(nix): make addToSystemPackages fully functional for interactive CLI (#6317) * fix(nix): export HERMES_HOME system-wide when addToSystemPackages is true The `addToSystemPackages` option's documentation (and the `:::tip` block in `website/docs/getting-started/nix-setup.md`) promises that enabling it both puts the `hermes` CLI on PATH and sets `HERMES_HOME` system-wide so interactive shells share state with the gateway service. The module only did the former, so running `hermes` in a user shell silently created a separate `~/.hermes/` directory instead of the managed `${stateDir}/.hermes`. Implement the documented behavior by also setting `environment.variables.HERMES_HOME = "${cfg.stateDir}/.hermes"` in the same mkIf block, and update the option description to match. Fixes #6044 * fix(nix): preserve group-readable permissions in managed mode The NixOS module sets HERMES_HOME directories to 0750 and files to 0640 so interactive users in the hermes group can share state with the gateway service. Two issues prevented this from working: 1. hermes_cli/config.py: _secure_dir() unconditionally chmod'd HERMES_HOME to 0700 on every startup, overwriting the NixOS module's 0750. Similarly, _secure_file() forced 0600 on config files. Both now skip in managed mode (detected via .managed marker or HERMES_MANAGED env var). 2. nix/nixosModules.nix: the .env file was created with 0600 (owner-only), while config.yaml was already 0640 (group-readable). Changed to 0640 for consistency — users granted hermes group membership should be able to read the managed .env. Verified with a NixOS VM integration test: a normal user in the hermes group can now run `hermes version` and `hermes config` against the managed HERMES_HOME without PermissionError. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: zerone0x <zerone0x@users.noreply.github.com> Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-08 15:39:53 -07:00
return
try:
if os.path.exists(str(path)):
os.chmod(path, 0o600)
except (OSError, NotImplementedError):
pass
def _ensure_default_soul_md(home: Path) -> None:
"""Seed a default SOUL.md into HERMES_HOME if the user doesn't have one yet."""
soul_path = home / "SOUL.md"
if soul_path.exists():
return
soul_path.write_text(DEFAULT_SOUL_MD, encoding="utf-8")
_secure_file(soul_path)
def ensure_hermes_home():
feat(nix): shared-state permission model for interactive CLI users (#6796) * feat(nix): shared-state permission model for interactive CLI users Enable interactive CLI users in the hermes group to share full read-write state (sessions, memories, logs, cron) with the gateway service via a setgid + group-writable permission model. Changes: nix/nixosModules.nix: - Directories use setgid 2770 (was 0750) so new files inherit the hermes group. home/ stays 0750 (no interactive write needed). - Activation script creates HERMES_HOME subdirs (cron, sessions, logs, memories) — previously Python created them but managed mode now skips mkdir. - Activation migrates existing runtime files to group-writable (chmod g+rw). Nix-managed files (config.yaml, .env, .managed) stay 0640/0644. - Gateway systemd unit gets UMask=0007 so files it creates are 0660. hermes_cli/config.py: - ensure_hermes_home() splits into managed/unmanaged paths. Managed mode verifies dirs exist (raises RuntimeError if not) instead of creating them. Scoped umask(0o007) ensures SOUL.md is created as 0660. hermes_logging.py: - _ManagedRotatingFileHandler subclass applies chmod 0660 after log rotation in managed mode. RotatingFileHandler.doRollover() creates new files via open() which uses the process umask (0022 → 0644), not the scoped umask from ensure_hermes_home(). Verified with a 13-subtest NixOS VM integration test covering setgid, interactive writes, file ownership, migration, and gateway coexistence. Refs: #6044 * Fix managed log file mode on initial open Co-authored-by: Siddharth Balyan <alt-glitch@users.noreply.github.com> * refactor: simplify managed file handler and merge activation loops - Cache is_managed() result in handler __init__ instead of lazy-importing on every _open()/_chmod_if_managed() call. Avoids repeated stat+env checks on log rotation. - Merge two for-loops over the same subdir list in activation script into a single loop (mkdir + chown + chmod + find in one pass). --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Siddharth Balyan <alt-glitch@users.noreply.github.com>
2026-04-09 15:18:42 -07:00
"""Ensure ~/.hermes directory structure exists with secure permissions.
In managed mode (NixOS), dirs are created by the activation script with
setgid + group-writable (2770). We skip mkdir and set umask(0o007) so
any files created (e.g. SOUL.md) are group-writable (0660).
"""
home = get_hermes_home()
feat(nix): shared-state permission model for interactive CLI users (#6796) * feat(nix): shared-state permission model for interactive CLI users Enable interactive CLI users in the hermes group to share full read-write state (sessions, memories, logs, cron) with the gateway service via a setgid + group-writable permission model. Changes: nix/nixosModules.nix: - Directories use setgid 2770 (was 0750) so new files inherit the hermes group. home/ stays 0750 (no interactive write needed). - Activation script creates HERMES_HOME subdirs (cron, sessions, logs, memories) — previously Python created them but managed mode now skips mkdir. - Activation migrates existing runtime files to group-writable (chmod g+rw). Nix-managed files (config.yaml, .env, .managed) stay 0640/0644. - Gateway systemd unit gets UMask=0007 so files it creates are 0660. hermes_cli/config.py: - ensure_hermes_home() splits into managed/unmanaged paths. Managed mode verifies dirs exist (raises RuntimeError if not) instead of creating them. Scoped umask(0o007) ensures SOUL.md is created as 0660. hermes_logging.py: - _ManagedRotatingFileHandler subclass applies chmod 0660 after log rotation in managed mode. RotatingFileHandler.doRollover() creates new files via open() which uses the process umask (0022 → 0644), not the scoped umask from ensure_hermes_home(). Verified with a 13-subtest NixOS VM integration test covering setgid, interactive writes, file ownership, migration, and gateway coexistence. Refs: #6044 * Fix managed log file mode on initial open Co-authored-by: Siddharth Balyan <alt-glitch@users.noreply.github.com> * refactor: simplify managed file handler and merge activation loops - Cache is_managed() result in handler __init__ instead of lazy-importing on every _open()/_chmod_if_managed() call. Avoids repeated stat+env checks on log rotation. - Merge two for-loops over the same subdir list in activation script into a single loop (mkdir + chown + chmod + find in one pass). --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Siddharth Balyan <alt-glitch@users.noreply.github.com>
2026-04-09 15:18:42 -07:00
if is_managed():
old_umask = os.umask(0o007)
try:
_ensure_hermes_home_managed(home)
finally:
os.umask(old_umask)
else:
home.mkdir(parents=True, exist_ok=True)
_secure_dir(home)
for subdir in ("cron", "sessions", "logs", "memories"):
d = home / subdir
d.mkdir(parents=True, exist_ok=True)
_secure_dir(d)
_ensure_default_soul_md(home)
def _ensure_hermes_home_managed(home: Path):
"""Managed-mode variant: verify dirs exist (activation creates them), seed SOUL.md."""
if not home.is_dir():
raise RuntimeError(
f"HERMES_HOME {home} does not exist. "
"Run 'sudo nixos-rebuild switch' first."
)
for subdir in ("cron", "sessions", "logs", "memories"):
d = home / subdir
feat(nix): shared-state permission model for interactive CLI users (#6796) * feat(nix): shared-state permission model for interactive CLI users Enable interactive CLI users in the hermes group to share full read-write state (sessions, memories, logs, cron) with the gateway service via a setgid + group-writable permission model. Changes: nix/nixosModules.nix: - Directories use setgid 2770 (was 0750) so new files inherit the hermes group. home/ stays 0750 (no interactive write needed). - Activation script creates HERMES_HOME subdirs (cron, sessions, logs, memories) — previously Python created them but managed mode now skips mkdir. - Activation migrates existing runtime files to group-writable (chmod g+rw). Nix-managed files (config.yaml, .env, .managed) stay 0640/0644. - Gateway systemd unit gets UMask=0007 so files it creates are 0660. hermes_cli/config.py: - ensure_hermes_home() splits into managed/unmanaged paths. Managed mode verifies dirs exist (raises RuntimeError if not) instead of creating them. Scoped umask(0o007) ensures SOUL.md is created as 0660. hermes_logging.py: - _ManagedRotatingFileHandler subclass applies chmod 0660 after log rotation in managed mode. RotatingFileHandler.doRollover() creates new files via open() which uses the process umask (0022 → 0644), not the scoped umask from ensure_hermes_home(). Verified with a 13-subtest NixOS VM integration test covering setgid, interactive writes, file ownership, migration, and gateway coexistence. Refs: #6044 * Fix managed log file mode on initial open Co-authored-by: Siddharth Balyan <alt-glitch@users.noreply.github.com> * refactor: simplify managed file handler and merge activation loops - Cache is_managed() result in handler __init__ instead of lazy-importing on every _open()/_chmod_if_managed() call. Avoids repeated stat+env checks on log rotation. - Merge two for-loops over the same subdir list in activation script into a single loop (mkdir + chown + chmod + find in one pass). --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Siddharth Balyan <alt-glitch@users.noreply.github.com>
2026-04-09 15:18:42 -07:00
if not d.is_dir():
raise RuntimeError(
f"{d} does not exist. "
"Run 'sudo nixos-rebuild switch' first."
)
# Inside umask(0o007) scope — SOUL.md will be created as 0660
_ensure_default_soul_md(home)
# =============================================================================
# Config loading/saving
# =============================================================================
DEFAULT_CONFIG = {
"model": "",
"providers": {},
"fallback_providers": [],
feat(auth): same-provider credential pools with rotation, custom endpoint support, and interactive CLI (#2647) * feat(auth): add same-provider credential pools and rotation UX Add same-provider credential pooling so Hermes can rotate across multiple credentials for a single provider, recover from exhausted credentials without jumping providers immediately, and configure that behavior directly in hermes setup. - agent/credential_pool.py: persisted per-provider credential pools - hermes auth add/list/remove/reset CLI commands - 429/402/401 recovery with pool rotation in run_agent.py - Setup wizard integration for pool strategy configuration - Auto-seeding from env vars and existing OAuth state Co-authored-by: kshitijk4poor <82637225+kshitijk4poor@users.noreply.github.com> Salvaged from PR #2647 * fix(tests): prevent pool auto-seeding from host env in credential pool tests Tests for non-pool Anthropic paths and auth remove were failing when host env vars (ANTHROPIC_API_KEY) or file-backed OAuth credentials were present. The pool auto-seeding picked these up, causing unexpected pool entries in tests. - Mock _select_pool_entry in auxiliary_client OAuth flag tests - Clear Anthropic env vars and mock _seed_from_singletons in auth remove test * feat(auth): add thread safety, least_used strategy, and request counting - Add threading.Lock to CredentialPool for gateway thread safety (concurrent requests from multiple gateway sessions could race on pool state mutations without this) - Add 'least_used' rotation strategy that selects the credential with the lowest request_count, distributing load more evenly - Add request_count field to PooledCredential for usage tracking - Add mark_used() method to increment per-credential request counts - Wrap select(), mark_exhausted_and_rotate(), and try_refresh_current() with lock acquisition - Add tests: least_used selection, mark_used counting, concurrent thread safety (4 threads × 20 selects with no corruption) * feat(auth): add interactive mode for bare 'hermes auth' command When 'hermes auth' is called without a subcommand, it now launches an interactive wizard that: 1. Shows full credential pool status across all providers 2. Offers a menu: add, remove, reset cooldowns, set strategy 3. For OAuth-capable providers (anthropic, nous, openai-codex), the add flow explicitly asks 'API key or OAuth login?' — making it clear that both auth types are supported for the same provider 4. Strategy picker shows all 4 options (fill_first, round_robin, least_used, random) with the current selection marked 5. Remove flow shows entries with indices for easy selection The subcommand paths (hermes auth add/list/remove/reset) still work exactly as before for scripted/non-interactive use. * fix(tests): update runtime_provider tests for config.yaml source of truth (#4165) Tests were using OPENAI_BASE_URL env var which is no longer consulted after #4165. Updated to use model config (provider, base_url, api_key) which is the new single source of truth for custom endpoint URLs. * feat(auth): support custom endpoint credential pools keyed by provider name Custom OpenAI-compatible endpoints all share provider='custom', making the provider-keyed pool useless. Now pools for custom endpoints are keyed by 'custom:<normalized_name>' where the name comes from the custom_providers config list (auto-generated from URL hostname). - Pool key format: 'custom:together.ai', 'custom:local-(localhost:8080)' - load_pool('custom:name') seeds from custom_providers api_key AND model.api_key when base_url matches - hermes auth add/list now shows custom endpoints alongside registry providers - _resolve_openrouter_runtime and _resolve_named_custom_runtime check pool before falling back to single config key - 6 new tests covering custom pool keying, seeding, and listing * docs: add Excalidraw diagram of full credential pool flow Comprehensive architecture diagram showing: - Credential sources (env vars, auth.json OAuth, config.yaml, CLI) - Pool storage and auto-seeding - Runtime resolution paths (registry, custom, OpenRouter) - Error recovery (429 retry-then-rotate, 402 immediate, 401 refresh) - CLI management commands and strategy configuration Open at: https://excalidraw.com/#json=2Ycqhqpi6f12E_3ITyiwh,c7u9jSt5BwrmiVzHGbm87g * fix(tests): update setup wizard pool tests for unified select_provider_and_model flow The setup wizard now delegates to select_provider_and_model() instead of using its own prompt_choice-based provider picker. Tests needed: - Mock select_provider_and_model as no-op (provider pre-written to config) - Call _stub_tts BEFORE custom prompt_choice mock (it overwrites it) - Pre-write model.provider to config so the pool step is reached * docs: add comprehensive credential pool documentation - New page: website/docs/user-guide/features/credential-pools.md Full guide covering quick start, CLI commands, rotation strategies, error recovery, custom endpoint pools, auto-discovery, thread safety, architecture, and storage format. - Updated fallback-providers.md to reference credential pools as the first layer of resilience (same-provider rotation before cross-provider) - Added hermes auth to CLI commands reference with usage examples - Added credential_pool_strategies to configuration guide * chore: remove excalidraw diagram from repo (external link only) * refactor: simplify credential pool code — extract helpers, collapse extras, dedup patterns - _load_config_safe(): replace 4 identical try/except/import blocks - _iter_custom_providers(): shared generator for custom provider iteration - PooledCredential.extra dict: collapse 11 round-trip-only fields (token_type, scope, client_id, portal_base_url, obtained_at, expires_in, agent_key_id, agent_key_expires_in, agent_key_reused, agent_key_obtained_at, tls) into a single extra dict with __getattr__ for backward-compatible access - _available_entries(): shared exhaustion-check between select and peek - Dedup anthropic OAuth seeding (hermes_pkce + claude_code identical) - SimpleNamespace replaces class _Args boilerplate in auth_commands - _try_resolve_from_custom_pool(): shared pool-check in runtime_provider Net -17 lines. All 383 targeted tests pass. --------- Co-authored-by: kshitijk4poor <82637225+kshitijk4poor@users.noreply.github.com>
2026-03-31 03:10:01 -07:00
"credential_pool_strategies": {},
"toolsets": ["hermes-cli"],
2026-03-07 21:01:23 -08:00
"agent": {
"max_turns": 90,
# Inactivity timeout for gateway agent execution (seconds).
# The agent can run indefinitely as long as it's actively calling
# tools or receiving API responses. Only fires when the agent has
# been completely idle for this duration. 0 = unlimited.
"gateway_timeout": 1800,
# Graceful drain timeout for gateway stop/restart (seconds).
# The gateway stops accepting new work, waits for running agents
# to finish, then interrupts any remaining runs after the timeout.
# 0 = no drain, interrupt immediately.
"restart_drain_timeout": 60,
# Max app-level retry attempts for API errors (connection drops,
# provider timeouts, 5xx, etc.) before the agent surfaces the
# failure. The OpenAI SDK already does its own low-level retries
# (max_retries=2 default) for transient network errors; this is
# the Hermes-level retry loop that wraps the whole call. Lower
# this to 1 if you use fallback providers and want fast failover
# on flaky primaries; raise it if you prefer to tolerate longer
# provider hiccups on a single provider.
"api_max_retries": 3,
"service_tier": "",
# Tool-use enforcement: injects system prompt guidance that tells the
# model to actually call tools instead of describing intended actions.
# Values: "auto" (default — applies to gpt/codex models), true/false
# (force on/off for all models), or a list of model-name substrings
# to match (e.g. ["gpt", "codex", "gemini", "qwen"]).
"tool_use_enforcement": "auto",
# Staged inactivity warning: send a warning to the user at this
# threshold before escalating to a full timeout. The warning fires
# once per run and does not interrupt the agent. 0 = disable warning.
"gateway_timeout_warning": 900,
# Periodic "still working" notification interval (seconds).
# Sends a status message every N seconds so the user knows the
# agent hasn't died during long tasks. 0 = disable notifications.
fix(gateway): drain-aware hermes update + faster still-working pings (#14736) cmd_update no longer SIGKILLs in-flight agent runs, and users get 'still working' status every 3 min instead of 10. Two long-standing sources of '@user — agent gives up mid-task' reports on Telegram and other gateways. Drain-aware update: - New helper hermes_cli.gateway._graceful_restart_via_sigusr1(pid, drain_timeout) sends SIGUSR1 to the gateway and polls os.kill(pid, 0) until the process exits or the budget expires. - cmd_update's systemd loop now reads MainPID via 'systemctl show --property=MainPID --value' and tries the graceful path first. The gateway's existing SIGUSR1 handler -> request_restart(via_service= True) -> drain -> exit(75) is wired in gateway/run.py and is respawned by systemd's Restart=on-failure (and the explicit RestartForceExitStatus=75 on newer units). - Falls back to 'systemctl restart' when MainPID is unknown, the drain budget elapses, or the unit doesn't respawn after exit (older units missing Restart=on-failure). Old install behavior preserved. - Drain budget = max(restart_drain_timeout, 30s) + 15s margin so the drain loop in run_agent + final exit have room before fallback fires. Composes with #14728's tool-subprocess reaping. Notification interval: - agent.gateway_notify_interval default 600 -> 180. - HERMES_AGENT_NOTIFY_INTERVAL env-var fallback in gateway/run.py matched. - 9-minute weak-model spinning runs now ping at 3 min and 6 min instead of 27 seconds before completion, removing the 'is the bot dead?' reflex that drives gateway-restart cycles. Tests: - Two new tests in tests/hermes_cli/test_update_gateway_restart.py: one asserts SIGUSR1 is sent and 'systemctl restart' is NOT called when MainPID is known and the helper succeeds; one asserts the fallback fires when the helper returns False. - E2E: spawned detached bash processes confirm the helper returns True on SIGUSR1-handling exit (~0.5s) and False on SIGUSR1-ignoring processes (timeout). Verified non-existent PID and pid=0 edge cases. - 41/41 in test_update_gateway_restart.py (was 39, +2 new). - 154/154 in shutdown-related suites including #14728's new tests. Reported by @GeoffWellman and @ANT_1515 on X.
2026-04-23 14:01:57 -07:00
# Lower values mean faster feedback on slow tasks but more chat
# noise; 180s is a compromise that catches spinning weak-model runs
# (60+ tool iterations with tiny output) before users assume the
# bot is dead and /restart.
"gateway_notify_interval": 180,
2026-03-07 21:01:23 -08:00
},
"terminal": {
"backend": "local",
"modal_mode": "auto",
"cwd": ".", # Use current directory
"timeout": 180,
feat: env var passthrough for skills and user config (#2807) * feat: env var passthrough for skills and user config Skills that declare required_environment_variables now have those vars passed through to sandboxed execution environments (execute_code and terminal). Previously, execute_code stripped all vars containing KEY, TOKEN, SECRET, etc. and the terminal blocklist removed Hermes infrastructure vars — both blocked skill-declared env vars. Two passthrough sources: 1. Skill-scoped (automatic): when a skill is loaded via skill_view and declares required_environment_variables, vars that are present in the environment are registered in a session-scoped passthrough set. 2. Config-based (manual): terminal.env_passthrough in config.yaml lets users explicitly allowlist vars for non-skill use cases. Changes: - New module: tools/env_passthrough.py — shared passthrough registry - hermes_cli/config.py: add terminal.env_passthrough to DEFAULT_CONFIG - tools/skills_tool.py: register available skill env vars on load - tools/code_execution_tool.py: check passthrough before filtering - tools/environments/local.py: check passthrough in _sanitize_subprocess_env and _make_run_env - 19 new tests covering all layers * docs: add environment variable passthrough documentation Document the env var passthrough feature across four docs pages: - security.md: new 'Environment Variable Passthrough' section with full explanation, comparison table, and security considerations - code-execution.md: update security section, add passthrough subsection, fix comparison table - creating-skills.md: add tip about automatic sandbox passthrough - skills.md: add note about passthrough after secure setup docs Live-tested: launched interactive CLI, loaded a skill with required_environment_variables, verified TEST_SKILL_SECRET_KEY was accessible inside execute_code sandbox (value: passthrough-test-value-42).
2026-03-24 08:19:34 -07:00
# Environment variables to pass through to sandboxed execution
# (terminal and execute_code). Skill-declared required_environment_variables
# are passed through automatically; this list is for non-skill use cases.
"env_passthrough": [],
feat(skills+terminal): make bundled skill scripts runnable out of the box (#13384) * feat(skills): inject absolute skill dir and expand ${HERMES_SKILL_DIR} templates When a skill loads, the activation message now exposes the absolute skill directory and substitutes ${HERMES_SKILL_DIR} / ${HERMES_SESSION_ID} tokens in the SKILL.md body, so skills with bundled scripts can instruct the agent to run them by absolute path without an extra skill_view round-trip. Also adds opt-in inline-shell expansion: !`cmd` snippets in SKILL.md are pre-executed (with the skill directory as CWD) and their stdout is inlined into the message before the agent reads it. Off by default — enable via skills.inline_shell in config.yaml — because any snippet runs on the host without approval. Changes: - agent/skill_commands.py: template substitution, inline-shell expansion, absolute skill-dir header, supporting-files list now shows both relative and absolute forms. - hermes_cli/config.py: new skills.template_vars, skills.inline_shell, skills.inline_shell_timeout knobs. - tests/agent/test_skill_commands.py: coverage for header, both template tokens (present and missing session id), template_vars disable, inline-shell default-off, enabled, CWD, and timeout. - website/docs/developer-guide/creating-skills.md: documents the template tokens, the absolute-path header, and the opt-in inline shell with its security caveat. Validation: tests/agent/ 1591 passed (includes 9 new tests). E2E: loaded a real skill in an isolated HERMES_HOME; confirmed ${HERMES_SKILL_DIR} resolves to the absolute path, ${HERMES_SESSION_ID} resolves to the passed task_id, !`date` runs when opt-in is set, and stays literal when it isn't. * feat(terminal): source ~/.bashrc (and user-listed init files) into session snapshot bash login shells don't source ~/.bashrc, so tools that install themselves there — nvm, asdf, pyenv, cargo, custom PATH exports — stay invisible to the environment snapshot Hermes builds once per session. Under systemd or any context with a minimal parent env, that surfaces as 'node: command not found' in the terminal tool even though the binary is reachable from every interactive shell on the machine. Changes: - tools/environments/local.py: before the login-shell snapshot bootstrap runs, prepend guarded 'source <file>' lines for each resolved init file. Missing files are skipped, each source is wrapped with a '[ -r ... ] && . ... || true' guard so a broken rc can't abort the bootstrap. - hermes_cli/config.py: new terminal.shell_init_files (explicit list, supports ~ and ${VAR}) and terminal.auto_source_bashrc (default on) knobs. When shell_init_files is set it takes precedence; when it's empty and auto_source_bashrc is on, ~/.bashrc gets auto-sourced. - tests/tools/test_local_shell_init.py: 10 tests covering the resolver (auto-bashrc, missing file, explicit override, ~/${VAR} expansion, opt-out) and the prelude builder (quoting, guarded sourcing), plus a real-LocalEnvironment snapshot test that confirms exports in the init file land in subsequent commands' environment. - website/docs/reference/faq.md: documents the fix in Troubleshooting, including the zsh-user pattern of sourcing ~/.zshrc or nvm.sh directly via shell_init_files. Validation: 10/10 new tests pass; tests/tools/test_local_*.py 40/40 pass; tests/agent/ 1591/1591 pass; tests/hermes_cli/test_config.py 50/50 pass. E2E in an isolated HERMES_HOME: confirmed that a fake ~/.bashrc setting a marker var and PATH addition shows up in a real LocalEnvironment().execute() call, that auto_source_bashrc=false suppresses it, that an explicit shell_init_files entry wins over the auto default, and that a missing bashrc is silently skipped.
2026-04-21 00:39:19 -07:00
# Extra files to source in the login shell when building the
# per-session environment snapshot. Use this when tools like nvm,
# pyenv, asdf, or custom PATH entries are registered by files that
# a bash login shell would skip — most commonly ``~/.bashrc``
# (bash doesn't source bashrc in non-interactive login mode) or
# zsh-specific files like ``~/.zshrc`` / ``~/.zprofile``.
# Paths support ``~`` / ``${VAR}``. Missing files are silently
# skipped. When empty, Hermes auto-sources ``~/.profile``,
# ``~/.bash_profile``, and ``~/.bashrc`` (in that order) if the
feat(skills+terminal): make bundled skill scripts runnable out of the box (#13384) * feat(skills): inject absolute skill dir and expand ${HERMES_SKILL_DIR} templates When a skill loads, the activation message now exposes the absolute skill directory and substitutes ${HERMES_SKILL_DIR} / ${HERMES_SESSION_ID} tokens in the SKILL.md body, so skills with bundled scripts can instruct the agent to run them by absolute path without an extra skill_view round-trip. Also adds opt-in inline-shell expansion: !`cmd` snippets in SKILL.md are pre-executed (with the skill directory as CWD) and their stdout is inlined into the message before the agent reads it. Off by default — enable via skills.inline_shell in config.yaml — because any snippet runs on the host without approval. Changes: - agent/skill_commands.py: template substitution, inline-shell expansion, absolute skill-dir header, supporting-files list now shows both relative and absolute forms. - hermes_cli/config.py: new skills.template_vars, skills.inline_shell, skills.inline_shell_timeout knobs. - tests/agent/test_skill_commands.py: coverage for header, both template tokens (present and missing session id), template_vars disable, inline-shell default-off, enabled, CWD, and timeout. - website/docs/developer-guide/creating-skills.md: documents the template tokens, the absolute-path header, and the opt-in inline shell with its security caveat. Validation: tests/agent/ 1591 passed (includes 9 new tests). E2E: loaded a real skill in an isolated HERMES_HOME; confirmed ${HERMES_SKILL_DIR} resolves to the absolute path, ${HERMES_SESSION_ID} resolves to the passed task_id, !`date` runs when opt-in is set, and stays literal when it isn't. * feat(terminal): source ~/.bashrc (and user-listed init files) into session snapshot bash login shells don't source ~/.bashrc, so tools that install themselves there — nvm, asdf, pyenv, cargo, custom PATH exports — stay invisible to the environment snapshot Hermes builds once per session. Under systemd or any context with a minimal parent env, that surfaces as 'node: command not found' in the terminal tool even though the binary is reachable from every interactive shell on the machine. Changes: - tools/environments/local.py: before the login-shell snapshot bootstrap runs, prepend guarded 'source <file>' lines for each resolved init file. Missing files are skipped, each source is wrapped with a '[ -r ... ] && . ... || true' guard so a broken rc can't abort the bootstrap. - hermes_cli/config.py: new terminal.shell_init_files (explicit list, supports ~ and ${VAR}) and terminal.auto_source_bashrc (default on) knobs. When shell_init_files is set it takes precedence; when it's empty and auto_source_bashrc is on, ~/.bashrc gets auto-sourced. - tests/tools/test_local_shell_init.py: 10 tests covering the resolver (auto-bashrc, missing file, explicit override, ~/${VAR} expansion, opt-out) and the prelude builder (quoting, guarded sourcing), plus a real-LocalEnvironment snapshot test that confirms exports in the init file land in subsequent commands' environment. - website/docs/reference/faq.md: documents the fix in Troubleshooting, including the zsh-user pattern of sourcing ~/.zshrc or nvm.sh directly via shell_init_files. Validation: 10/10 new tests pass; tests/tools/test_local_*.py 40/40 pass; tests/agent/ 1591/1591 pass; tests/hermes_cli/test_config.py 50/50 pass. E2E in an isolated HERMES_HOME: confirmed that a fake ~/.bashrc setting a marker var and PATH addition shows up in a real LocalEnvironment().execute() call, that auto_source_bashrc=false suppresses it, that an explicit shell_init_files entry wins over the auto default, and that a missing bashrc is silently skipped.
2026-04-21 00:39:19 -07:00
# snapshot shell is bash (this is the ``auto_source_bashrc``
# behaviour — disable with that key if you want strict login-only
# semantics).
"shell_init_files": [],
# When true (default), Hermes sources the user's shell rc files
# (``~/.profile``, ``~/.bash_profile``, ``~/.bashrc``) in the
# login shell used to build the environment snapshot. This
# captures PATH additions, shell functions, and aliases — which a
# plain ``bash -l -c`` would otherwise miss because bash skips
# bashrc in non-interactive login mode, and because a default
# Debian/Ubuntu ``~/.bashrc`` short-circuits on non-interactive
# sources. ``~/.profile`` and ``~/.bash_profile`` are tried first
# because ``n`` / ``nvm`` / ``asdf`` installers typically write
# their PATH exports there without an interactivity guard. Turn
# this off if your rc files misbehave when sourced
feat(skills+terminal): make bundled skill scripts runnable out of the box (#13384) * feat(skills): inject absolute skill dir and expand ${HERMES_SKILL_DIR} templates When a skill loads, the activation message now exposes the absolute skill directory and substitutes ${HERMES_SKILL_DIR} / ${HERMES_SESSION_ID} tokens in the SKILL.md body, so skills with bundled scripts can instruct the agent to run them by absolute path without an extra skill_view round-trip. Also adds opt-in inline-shell expansion: !`cmd` snippets in SKILL.md are pre-executed (with the skill directory as CWD) and their stdout is inlined into the message before the agent reads it. Off by default — enable via skills.inline_shell in config.yaml — because any snippet runs on the host without approval. Changes: - agent/skill_commands.py: template substitution, inline-shell expansion, absolute skill-dir header, supporting-files list now shows both relative and absolute forms. - hermes_cli/config.py: new skills.template_vars, skills.inline_shell, skills.inline_shell_timeout knobs. - tests/agent/test_skill_commands.py: coverage for header, both template tokens (present and missing session id), template_vars disable, inline-shell default-off, enabled, CWD, and timeout. - website/docs/developer-guide/creating-skills.md: documents the template tokens, the absolute-path header, and the opt-in inline shell with its security caveat. Validation: tests/agent/ 1591 passed (includes 9 new tests). E2E: loaded a real skill in an isolated HERMES_HOME; confirmed ${HERMES_SKILL_DIR} resolves to the absolute path, ${HERMES_SESSION_ID} resolves to the passed task_id, !`date` runs when opt-in is set, and stays literal when it isn't. * feat(terminal): source ~/.bashrc (and user-listed init files) into session snapshot bash login shells don't source ~/.bashrc, so tools that install themselves there — nvm, asdf, pyenv, cargo, custom PATH exports — stay invisible to the environment snapshot Hermes builds once per session. Under systemd or any context with a minimal parent env, that surfaces as 'node: command not found' in the terminal tool even though the binary is reachable from every interactive shell on the machine. Changes: - tools/environments/local.py: before the login-shell snapshot bootstrap runs, prepend guarded 'source <file>' lines for each resolved init file. Missing files are skipped, each source is wrapped with a '[ -r ... ] && . ... || true' guard so a broken rc can't abort the bootstrap. - hermes_cli/config.py: new terminal.shell_init_files (explicit list, supports ~ and ${VAR}) and terminal.auto_source_bashrc (default on) knobs. When shell_init_files is set it takes precedence; when it's empty and auto_source_bashrc is on, ~/.bashrc gets auto-sourced. - tests/tools/test_local_shell_init.py: 10 tests covering the resolver (auto-bashrc, missing file, explicit override, ~/${VAR} expansion, opt-out) and the prelude builder (quoting, guarded sourcing), plus a real-LocalEnvironment snapshot test that confirms exports in the init file land in subsequent commands' environment. - website/docs/reference/faq.md: documents the fix in Troubleshooting, including the zsh-user pattern of sourcing ~/.zshrc or nvm.sh directly via shell_init_files. Validation: 10/10 new tests pass; tests/tools/test_local_*.py 40/40 pass; tests/agent/ 1591/1591 pass; tests/hermes_cli/test_config.py 50/50 pass. E2E in an isolated HERMES_HOME: confirmed that a fake ~/.bashrc setting a marker var and PATH addition shows up in a real LocalEnvironment().execute() call, that auto_source_bashrc=false suppresses it, that an explicit shell_init_files entry wins over the auto default, and that a missing bashrc is silently skipped.
2026-04-21 00:39:19 -07:00
# non-interactively (e.g. one that hard-exits on TTY checks).
"auto_source_bashrc": True,
"docker_image": "nikolaik/python-nodejs:python3.11-nodejs20",
"docker_forward_env": [],
# Explicit environment variables to set inside Docker containers.
# Unlike docker_forward_env (which reads values from the host process),
# docker_env lets you specify exact key-value pairs — useful when Hermes
# runs as a systemd service without access to the user's shell environment.
# Example: {"SSH_AUTH_SOCK": "/run/user/1000/ssh-agent.sock"}
"docker_env": {},
"singularity_image": "docker://nikolaik/python-nodejs:python3.11-nodejs20",
"modal_image": "nikolaik/python-nodejs:python3.11-nodejs20",
"daytona_image": "nikolaik/python-nodejs:python3.11-nodejs20",
# Container resource limits (docker, singularity, modal, daytona — ignored for local/ssh)
"container_cpu": 1,
"container_memory": 5120, # MB (default 5GB)
"container_disk": 51200, # MB (default 50GB)
"container_persistent": True, # Persist filesystem across sessions
# Docker volume mounts — share host directories with the container.
# Each entry is "host_path:container_path" (standard Docker -v syntax).
# Example:
# ["/home/user/projects:/workspace/projects",
# "/home/user/.hermes/cache/documents:/output"]
# For gateway MEDIA delivery, write inside Docker to /output/... and emit
# the host-visible path in MEDIA:, not the container path.
"docker_volumes": [],
# Explicit opt-in: mount the host cwd into /workspace for Docker sessions.
# Default off because passing host directories into a sandbox weakens isolation.
"docker_mount_cwd_to_workspace": False,
# Persistent shell — keep a long-lived bash shell across execute() calls
# so cwd/env vars/shell variables survive between commands.
# Enabled by default for non-local backends (SSH); local is always opt-in
# via TERMINAL_LOCAL_PERSISTENT env var.
"persistent_shell": True,
},
"browser": {
"inactivity_timeout": 120,
"command_timeout": 30, # Timeout for browser commands in seconds (screenshot, navigate, etc.)
feat: browser console/errors tool, annotated screenshots, auto-recording, and dogfood QA skill New browser capabilities and a built-in skill for agent-driven web QA. ## New tool: browser_console Returns console messages (log/warn/error/info) AND uncaught JavaScript exceptions in a single call. Uses agent-browser's 'console' and 'errors' commands through the existing session plumbing. Supports --clear to reset buffers. Verified working in both local and Browserbase cloud modes. ## Enhanced tool: browser_vision(annotate=True) New boolean parameter on browser_vision. When true, agent-browser overlays numbered [N] labels on interactive elements — each [N] maps to ref @eN. Annotation data (element name, role, bounding box) returned alongside the vision analysis. Useful for QA reports and spatial reasoning. ## Config: browser.record_sessions Auto-record browser sessions as WebM video files when enabled: - Starts recording on first browser_navigate - Stops and saves on browser_close - Saves to ~/.hermes/browser_recordings/ - Works in both local and cloud modes (verified) - Disabled by default ## Built-in skill: dogfood Systematic exploratory QA testing for web applications. Teaches the agent a 5-phase workflow: 1. Plan — accept URL, create output dirs, set scope 2. Explore — systematic crawl with annotated screenshots 3. Collect Evidence — screenshots, console errors, JS exceptions 4. Categorize — severity (Critical/High/Medium/Low) and category (Functional/Visual/Accessibility/Console/UX/Content) 5. Report — structured markdown with per-issue evidence Includes: - skills/dogfood/SKILL.md — full workflow instructions - skills/dogfood/references/issue-taxonomy.md — severity/category defs - skills/dogfood/templates/dogfood-report-template.md — report template ## Tests 21 new tests covering: - browser_console message/error parsing, clear flag, empty/failed states - browser_console schema registration - browser_vision annotate schema and flag passing - record_sessions config defaults and recording lifecycle - Dogfood skill file existence and content validation Addresses #315.
2026-03-08 21:02:14 -07:00
"record_sessions": False, # Auto-record browser sessions as WebM videos
"allow_private_urls": False, # Allow navigating to private/internal IPs (localhost, 192.168.x.x, etc.)
2026-04-17 15:03:31 -06:00
"cdp_url": "", # Optional persistent CDP endpoint for attaching to an existing Chromium/Chrome
feat(browser): CDP supervisor — dialog detection + response + cross-origin iframe eval (#14540) * docs: browser CDP supervisor design (for upcoming PR) Design doc ahead of implementation — dialog + iframe detection/interaction via a persistent CDP supervisor. Covers backend capability matrix (verified live 2026-04-23), architecture, lifecycle, policy, agent surface, PR split, non-goals, and test plan. Supersedes #12550. No code changes in this commit. * feat(browser): add persistent CDP supervisor for dialog + frame detection Single persistent CDP WebSocket per Hermes task_id that subscribes to Page/Runtime/Target events and maintains thread-safe state for pending dialogs, frame tree, and console errors. Supervisor lives in its own daemon thread running an asyncio loop; external callers use sync API (snapshot(), respond_to_dialog()) that bridges onto the loop. Auto-attaches to OOPIF child targets via Target.setAutoAttach{flatten:true} and enables Page+Runtime on each so iframe-origin dialogs surface through the same supervisor. Dialog policies: must_respond (default, 300s safety timeout), auto_dismiss, auto_accept. Frame tree capped at 30 entries + OOPIF depth 2 to keep snapshot payloads bounded on ad-heavy pages. E2E verified against real Chrome via smoke test — detects + responds to main-frame alerts, iframe-contentWindow alerts, preserves frame tree, graceful no-dialog error path, clean shutdown. No agent-facing tool wiring in this commit (comes next). * feat(browser): add browser_dialog tool wired to CDP supervisor Agent-facing response-only tool. Schema: action: 'accept' | 'dismiss' (required) prompt_text: response for prompt() dialogs (optional) dialog_id: disambiguate when multiple dialogs queued (optional) Handler: SUPERVISOR_REGISTRY.get(task_id).respond_to_dialog(...) check_fn shares _browser_cdp_check with browser_cdp so both surface and hide together. When no supervisor is attached (Camofox, default Playwright, or no browser session started yet), tool is hidden; if somehow invoked it returns a clear error pointing the agent to browser_navigate / /browser connect. Registered in _HERMES_CORE_TOOLS and the browser / hermes-acp / hermes-api-server toolsets alongside browser_cdp. * feat(browser): wire CDP supervisor into session lifecycle + browser_snapshot Supervisor lifecycle: * _get_session_info lazy-starts the supervisor after a session row is materialized — covers every backend code path (Browserbase, cdp_url override, /browser connect, future providers) with one hook. * cleanup_browser(task_id) stops the supervisor for that task first (before the backend tears down CDP). * cleanup_all_browsers() calls SUPERVISOR_REGISTRY.stop_all(). * /browser connect eagerly starts the supervisor for task 'default' so the first snapshot already shows pending_dialogs. * /browser disconnect stops the supervisor. CDP URL resolution for the supervisor: 1. BROWSER_CDP_URL / browser.cdp_url override. 2. Fallback: session_info['cdp_url'] from cloud providers (Browserbase). browser_snapshot merges supervisor state (pending_dialogs + frame_tree) into its JSON output when a supervisor is active — the agent reads pending_dialogs from the snapshot it already requests, then calls browser_dialog to respond. No extra tool surface. Config defaults: * browser.dialog_policy: 'must_respond' (new) * browser.dialog_timeout_s: 300 (new) No version bump — new keys deep-merge into existing browser section. Deadlock fix in supervisor event dispatch: * _on_dialog_opening and _on_target_attached used to await CDP calls while the reader was still processing an event — but only the reader can set the response Future, so the call timed out. * Both now fire asyncio.create_task(...) so the reader stays pumping. * auto_dismiss/auto_accept now actually close the dialog immediately. Tests (tests/tools/test_browser_supervisor.py, 11 tests, real Chrome): * supervisor start/snapshot * main-frame alert detection + dismiss * iframe.contentWindow alert * prompt() with prompt_text reply * respond with no pending dialog -> clean error * auto_dismiss clears on event * registry idempotency * registry stop -> snapshot reports inactive * browser_dialog tool no-supervisor error * browser_dialog invalid action * browser_dialog end-to-end via tool handler xdist-safe: chrome_cdp fixture uses a per-worker port. Skipped when google-chrome/chromium isn't installed. * docs(browser): document browser_dialog tool + CDP supervisor - user-guide/features/browser.md: new browser_dialog section with workflow, availability gate, and dialog_policy table - reference/tools-reference.md: row for browser_dialog, tool count bumped 53 -> 54, browser tools count 11 -> 12 - reference/toolsets-reference.md: browser_dialog added to browser toolset row with note on pending_dialogs / frame_tree snapshot fields Full design doc lives at developer-guide/browser-supervisor.md (committed earlier). * fix(browser): reconnect loop + recent_dialogs for Browserbase visibility Found via Browserbase E2E test that revealed two production-critical issues: 1. **Supervisor WebSocket drops when other clients disconnect.** Browserbase's CDP proxy tears down our long-lived WebSocket whenever a short-lived client (e.g. agent-browser CLI's per-command CDP connection) disconnects. Fixed with a reconnecting _run loop that re-attaches with exponential backoff on drops. _page_session_id and _child_sessions are reset on each reconnect; pending_dialogs and frames are preserved across reconnects. 2. **Browserbase auto-dismisses dialogs server-side within ~10ms.** Their Playwright-based CDP proxy dismisses alert/confirm/prompt before our Page.handleJavaScriptDialog call can respond. So pending_dialogs is empty by the time the agent reads a snapshot on Browserbase. Added a recent_dialogs ring buffer (capacity 20) that retains a DialogRecord for every dialog that opened, with a closed_by tag: * 'agent' — agent called browser_dialog * 'auto_policy' — local auto_dismiss/auto_accept fired * 'watchdog' — must_respond timeout auto-dismissed (300s default) * 'remote' — browser/backend closed it on us (Browserbase) Agents on Browserbase now see the dialog history with closed_by='remote' so they at least know a dialog fired, even though they couldn't respond. 3. **Page.javascriptDialogClosed matching bug.** The event doesn't include a 'message' field (CDP spec has only 'result' and 'userInput') but our _on_dialog_closed was matching on message. Fixed to match by session_id + oldest-first, with a safety assumption that only one dialog is in flight per session (the JS thread is blocked while a dialog is up). Docs + tests updated: * browser.md: new availability matrix showing the three backends and which mode (pending / recent / response) each supports * developer-guide/browser-supervisor.md: three-field snapshot schema with closed_by semantics * test_browser_supervisor.py: +test_recent_dialogs_ring_buffer (12/12 passing against real Chrome) E2E verified both backends: * Local Chrome via /browser connect: detect + respond full workflow (smoke_supervisor.py all 7 scenarios pass) * Browserbase: detect via recent_dialogs with closed_by='remote' (smoke_supervisor_browserbase_v2.py passes) Camofox remains out of scope (REST-only, no CDP) — tracked for upstream PR 3. * feat(browser): XHR bridge for dialog response on Browserbase (FIXED) Browserbase's CDP proxy auto-dismisses native JS dialogs within ~10ms, so Page.handleJavaScriptDialog calls lose the race. Solution: bypass native dialogs entirely. The supervisor now injects Page.addScriptToEvaluateOnNewDocument with a JavaScript override for window.alert/confirm/prompt. Those overrides perform a synchronous XMLHttpRequest to a magic host ('hermes-dialog-bridge.invalid'). We intercept those XHRs via Fetch.enable with a requestStage=Request pattern. Flow when a page calls alert('hi'): 1. window.alert override intercepts, builds XHR GET to http://hermes-dialog-bridge.invalid/?kind=alert&message=hi 2. Sync XHR blocks the page's JS thread (mirrors real dialog semantics) 3. Fetch.requestPaused fires on our WebSocket; supervisor surfaces it as a pending dialog with bridge_request_id set 4. Agent reads pending_dialogs from browser_snapshot, calls browser_dialog 5. Supervisor calls Fetch.fulfillRequest with JSON body: {accept: true|false, prompt_text: '...', dialog_id: 'd-N'} 6. The injected script parses the body, returns the appropriate value from the override (undefined for alert, bool for confirm, string|null for prompt) This works identically on Browserbase AND local Chrome — no native dialog ever fires, so Browserbase's auto-dismiss has nothing to race. Dialog policies (must_respond / auto_dismiss / auto_accept) all still work. Bridge is installed on every attached session (main page + OOPIF child sessions) so iframe dialogs are captured too. Native-dialog path kept as a fallback for backends that don't auto-dismiss (so a page that somehow bypasses our override — e.g. iframes that load after Fetch.enable but before the init-script runs — still gets observed via Page.javascriptDialogOpening). E2E VERIFIED: * Local Chrome: 13/13 pytest tests green (12 original + new test_bridge_captures_prompt_and_returns_reply_text that asserts window.__ret === 'AGENT-SUPPLIED-REPLY' after agent responds) * Browserbase: smoke_bb_bridge_v2.py runs 4/4 PASS: - alert('BB-ALERT-MSG') dismiss → page.alert_ret = undefined ✓ - prompt('BB-PROMPT-MSG', 'default-xyz') accept with 'AGENT-REPLY' → page.prompt_ret === 'AGENT-REPLY' ✓ - confirm('BB-CONFIRM-MSG') accept → page.confirm_ret === true ✓ - confirm('BB-CONFIRM-MSG') dismiss → page.confirm_ret === false ✓ Docs updated in browser.md and developer-guide/browser-supervisor.md — availability matrix now shows Browserbase at full parity with local Chrome for both detection and response. * feat(browser): cross-origin iframe interaction via browser_cdp(frame_id=...) Adds iframe interaction to the CDP supervisor PR (was queued as PR 2). Design: browser_cdp gets an optional frame_id parameter. When set, the tool looks up the frame in the supervisor's frame_tree, grabs its child cdp_session_id (OOPIF session), and dispatches the CDP call through the supervisor's already-connected WebSocket via run_coroutine_threadsafe. Why not stateless: on Browserbase, each fresh browser_cdp WebSocket must re-negotiate against a signed connectUrl. The session info carries a specific URL that can expire while the supervisor's long-lived connection stays valid. Routing via the supervisor sidesteps this. Agent workflow: 1. browser_snapshot → frame_tree.children[] shows OOPIFs with is_oopif=true 2. browser_cdp(method='Runtime.evaluate', frame_id=<OOPIF frame_id>, params={'expression': 'document.title', 'returnByValue': True}) 3. Supervisor dispatches the call on the OOPIF's child session Supervisor state fixes needed along the way: * _on_frame_detached now skips reason='swap' (frame migrating processes) * _on_frame_detached also skips when the frame is an OOPIF with a live child session — Browserbase fires spurious remove events when a same-origin iframe gets promoted to OOPIF * _on_target_detached clears cdp_session_id but KEEPS the frame record so the agent still sees the OOPIF in frame_tree during transient session flaps E2E VERIFIED on Browserbase (smoke_bb_iframe_agent_path.py): browser_cdp(method='Runtime.evaluate', params={'expression': 'document.title', 'returnByValue': True}, frame_id=<OOPIF>) → {'success': True, 'result': {'value': 'Example Domain'}} The iframe is <iframe src='https://example.com/'> inside a top-level data: URL page on a real Browserbase session. The agent Runtime.evaluates INSIDE the cross-origin iframe and gets example.com's title back. Tests (tests/tools/test_browser_supervisor.py — 16 pass total): * test_browser_cdp_frame_id_routes_via_supervisor — injects fake OOPIF, verifies routing via supervisor, Runtime.evaluate returns 1+1=2 * test_browser_cdp_frame_id_missing_supervisor — clean error when no supervisor attached * test_browser_cdp_frame_id_not_in_frame_tree — clean error on bad frame_id Docs (browser.md and developer-guide/browser-supervisor.md) updated with the iframe workflow, availability matrix now shows OOPIF eval as shipped for local Chrome + Browserbase. * test(browser): real-OOPIF E2E verified manually + chrome_cdp uses --site-per-process When asked 'did you test the iframe stuff' I had only done a mocked pytest (fake injected OOPIF) plus a Browserbase E2E. Closed the local-Chrome real-OOPIF gap by writing /tmp/dialog-iframe-test/ smoke_local_oopif.py: * 2 http servers on different hostnames (localhost:18905 + 127.0.0.1:18906) * Chrome with --site-per-process so the cross-origin iframe becomes a real OOPIF in its own process * Navigate, find OOPIF in supervisor.frame_tree, call browser_cdp(method='Runtime.evaluate', frame_id=<OOPIF>) which routes through the supervisor's child session * Asserts iframe document.title === 'INNER-FRAME-XYZ' (from the inner page, retrieved via OOPIF eval) PASSED on 2026-04-23. Tried to embed this as a pytest but hit an asyncio version quirk between venv (3.11) and the system python (3.13) — Page.navigate hangs in the pytest harness but works in standalone. Left a self-documenting skip test that points to the smoke script + describes the verification. chrome_cdp fixture now passes --site-per-process so future iframe tests can rely on OOPIF behavior. Result: 16 pass + 1 documented-skip = 17 tests in tests/tools/test_browser_supervisor.py. * docs(browser): add dialog_policy + dialog_timeout_s to configuration.md, fix tool count Pre-merge docs audit revealed two gaps: 1. user-guide/configuration.md browser config example was missing the two new dialog_* knobs. Added with a short table explaining must_respond / auto_dismiss / auto_accept semantics and a link to the feature page for the full workflow. 2. reference/tools-reference.md header said '54 built-in tools' — real count on main is 54, this branch adds browser_dialog so it's 55. Fixed the header. (browser count was already correctly bumped 11 -> 12 in the earlier docs commit.) No code changes.
2026-04-23 22:23:37 -07:00
# CDP supervisor — dialog + frame detection via a persistent WebSocket.
# Active only when a CDP-capable backend is attached (Browserbase or
# local Chrome via /browser connect). See
# website/docs/developer-guide/browser-supervisor.md.
"dialog_policy": "must_respond", # must_respond | auto_dismiss | auto_accept
"dialog_timeout_s": 300, # Safety auto-dismiss after N seconds under must_respond
"camofox": {
# When true, Hermes sends a stable profile-scoped userId to Camofox
# so the server maps it to a persistent Firefox profile automatically.
# When false (default), each session gets a random userId (ephemeral).
"managed_persistence": False,
},
},
# Filesystem checkpoints — automatic snapshots before destructive file ops.
# When enabled, the agent takes a snapshot of the working directory once per
# conversation turn (on first write_file/patch call). Use /rollback to restore.
"checkpoints": {
"enabled": True,
"max_snapshots": 50, # Max checkpoints to keep per directory
},
feat(file_tools): harden read_file with size guard, dedup, and device blocking (#4315) * feat(file_tools): harden read_file with size guard, dedup, and device blocking Three improvements to read_file_tool to reduce wasted context tokens and prevent process hangs: 1. Character-count guard: reads that produce more than 100K characters (≈25-35K tokens across tokenisers) are rejected with an error that tells the model to use offset+limit for a smaller range. The effective cap is min(file_size, 100K) so small files that happen to have long lines aren't over-penalised. Large truncated files also get a hint nudging toward targeted reads. 2. File-read deduplication: when the same (path, offset, limit) is read a second time and the file hasn't been modified (mtime unchanged), return a lightweight stub instead of re-sending the full content. Writes and patches naturally change mtime, so post-edit reads always return fresh content. The dedup cache is cleared on context compression — after compression the original read content is summarised away, so the model needs the full content again. 3. Device path blocking: paths like /dev/zero, /dev/random, /dev/stdin etc. are rejected before any I/O to prevent process hangs from infinite-output or blocking-input devices. Tests: 17 new tests covering all three features plus the dedup-reset- on-compression integration. All 52 file-read tests pass (35 existing + 17 new). Full tool suite (2124 tests) passes with 0 failures. * feat: make file_read_max_chars configurable, add docs Add file_read_max_chars to DEFAULT_CONFIG (default 100K). read_file_tool reads this on first call and caches for the process lifetime. Users on large-context models can raise it; users on small local models can lower it. Also adds a 'File Read Safety' section to the configuration docs explaining the char limit, dedup behavior, and example values.
2026-03-31 12:53:19 -07:00
# Maximum characters returned by a single read_file call. Reads that
# exceed this are rejected with guidance to use offset+limit.
# 100K chars ≈ 2535K tokens across typical tokenisers.
"file_read_max_chars": 100_000,
feat(skills): add design-md skill for Google's DESIGN.md spec (#14876) * feat(config): make tool output truncation limits configurable Port from anomalyco/opencode#23770: expose a new `tool_output` config section so users can tune the hardcoded truncation caps that apply to terminal output and read_file pagination. Three knobs under `tool_output`: - max_bytes (default 50_000) — terminal stdout/stderr cap - max_lines (default 2000) — read_file pagination cap - max_line_length (default 2000) — per-line cap in line-numbered view All three keep their existing hardcoded values as defaults, so behaviour is unchanged when the section is absent. Power users on big-context models can raise them; small-context local models can lower them. Implementation: - New `tools/tool_output_limits.py` reads the section with defensive fallback (missing/invalid values → defaults, never raises). - `tools/terminal_tool.py` MAX_OUTPUT_CHARS now comes from get_max_bytes(). - `tools/file_operations.py` normalize_read_pagination() and _add_line_numbers() now pull the limits at call time. - `hermes_cli/config.py` DEFAULT_CONFIG gains the `tool_output` section so `hermes setup` writes defaults into fresh configs. - Docs page `user-guide/configuration.md` gains a "Tool Output Truncation Limits" section with large-context and small-context example configs. Tests (18 new in tests/tools/test_tool_output_limits.py): - Default resolution with missing / malformed / non-dict config. - Full and partial user overrides. - Coercion of bad values (None, negative, wrong type, str int). - Shortcut accessors delegate correctly. - DEFAULT_CONFIG exposes the section with the right defaults. - Integration: normalize_read_pagination clamps to the configured max_lines. * feat(skills): add design-md skill for Google's DESIGN.md spec Built-in skill under skills/creative/ that teaches the agent to author, lint, diff, and export DESIGN.md files — Google's open-source (Apache-2.0) format for describing a visual identity to coding agents. Covers: - YAML front matter + markdown body anatomy - Full token schema (colors, typography, rounded, spacing, components) - Canonical section order + duplicate-heading rejection - Component property whitelist + variants-as-siblings pattern - CLI workflow via 'npx @google/design.md' (lint/diff/export/spec) - Lint rule reference including WCAG contrast checks - Common YAML pitfalls (quoted hex, negative dimensions, dotted refs) - Starter template at templates/starter.md Package verified live on npm (@google/design.md@0.1.1).
2026-04-23 21:51:19 -07:00
# Tool-output truncation thresholds. When terminal output or a
# single read_file page exceeds these limits, Hermes truncates the
# payload sent to the model (keeping head + tail for terminal,
# enforcing pagination for read_file). Tuning these trades context
# footprint against how much raw output the model can see in one
# shot. Ported from anomalyco/opencode PR #23770.
#
# - max_bytes: terminal_tool output cap, in chars
# (default 50_000 ≈ 12-15K tokens).
# - max_lines: read_file pagination cap — the maximum `limit`
# a single read_file call can request before
# being clamped (default 2000).
# - max_line_length: per-line cap applied when read_file emits a
# line-numbered view (default 2000 chars).
"tool_output": {
"max_bytes": 50_000,
"max_lines": 2000,
"max_line_length": 2000,
},
"compression": {
"enabled": True,
"threshold": 0.50, # compress when context usage exceeds this ratio
"target_ratio": 0.20, # fraction of threshold to preserve as recent tail
"protect_last_n": 20, # minimum recent messages to keep uncompressed
},
# Anthropic prompt caching (Claude via OpenRouter or native Anthropic API).
# cache_ttl must be "5m" or "1h" (Anthropic-supported tiers); other values are ignored.
"prompt_caching": {
"cache_ttl": "5m",
},
# AWS Bedrock provider configuration.
# Only used when model.provider is "bedrock".
"bedrock": {
"region": "", # AWS region for Bedrock API calls (empty = AWS_REGION env var → us-east-1)
"discovery": {
"enabled": True, # Auto-discover models via ListFoundationModels
"provider_filter": [], # Only show models from these providers (e.g. ["anthropic", "amazon"])
"refresh_interval": 3600, # Cache discovery results for this many seconds
},
"guardrail": {
# Amazon Bedrock Guardrails — content filtering and safety policies.
# Create a guardrail in the Bedrock console, then set the ID and version here.
# See: https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails.html
"guardrail_identifier": "", # e.g. "abc123def456"
"guardrail_version": "", # e.g. "1" or "DRAFT"
"stream_processing_mode": "async", # "sync" or "async"
"trace": "disabled", # "enabled", "disabled", or "enabled_full"
},
},
# Auxiliary model config — provider:model for each side task.
# Format: provider is the provider name, model is the model slug.
# "auto" for provider = auto-detect best available provider.
# Empty model = use provider's default auxiliary model.
# All tasks fall back to openrouter:google/gemini-3-flash-preview if
# the configured provider is unavailable.
"auxiliary": {
"vision": {
"provider": "auto", # auto | openrouter | nous | codex | custom
"model": "", # e.g. "google/gemini-2.5-flash", "gpt-4o"
"base_url": "", # direct OpenAI-compatible endpoint (takes precedence over provider)
"api_key": "", # API key for base_url (falls back to OPENAI_API_KEY)
"timeout": 120, # seconds — LLM API call timeout; vision payloads need generous timeout
"extra_body": {}, # OpenAI-compatible provider-specific request fields
fix: background task media delivery + vision download timeout (#3919) * feat(telegram): add webhook mode as alternative to polling When TELEGRAM_WEBHOOK_URL is set, the adapter starts an HTTP webhook server (via python-telegram-bot's start_webhook()) instead of long polling. This enables cloud platforms like Fly.io and Railway to auto-wake suspended machines on inbound HTTP traffic. Polling remains the default — no behavior change unless the env var is set. Env vars: TELEGRAM_WEBHOOK_URL Public HTTPS URL for Telegram to push to TELEGRAM_WEBHOOK_PORT Local listen port (default 8443) TELEGRAM_WEBHOOK_SECRET Secret token for update verification Cherry-picked and adapted from PR #2022 by SHL0MS. Preserved all current main enhancements (network error recovery, polling conflict detection, DM topics setup). Co-authored-by: SHL0MS <SHL0MS@users.noreply.github.com> * fix: send_document call in background task delivery + vision download timeout Two fixes salvaged from PR #2269 by amethystani: 1. gateway/run.py: adapter.send_file() → adapter.send_document() send_file() doesn't exist on BasePlatformAdapter. Background task media files were silently never delivered (AttributeError swallowed by except Exception: pass). 2. tools/vision_tools.py: configurable image download timeout via HERMES_VISION_DOWNLOAD_TIMEOUT env var (default 30s), plus guard against raise None when max_retries=0. The third fix in #2269 (opencode-go auth config) was already resolved on main. Co-authored-by: amethystani <amethystani@users.noreply.github.com> --------- Co-authored-by: SHL0MS <SHL0MS@users.noreply.github.com> Co-authored-by: amethystani <amethystani@users.noreply.github.com>
2026-03-30 02:59:39 -07:00
"download_timeout": 30, # seconds — image HTTP download timeout; increase for slow connections
},
"web_extract": {
"provider": "auto",
"model": "",
"base_url": "",
"api_key": "",
"timeout": 360, # seconds (6min) — per-attempt LLM summarization timeout; increase for slow local models
"extra_body": {},
},
"compression": {
"provider": "auto",
"model": "",
"base_url": "",
"api_key": "",
"timeout": 120, # seconds — compression summarises large contexts; increase for local models
"extra_body": {},
},
"session_search": {
"provider": "auto",
"model": "",
"base_url": "",
"api_key": "",
"timeout": 30,
"extra_body": {},
"max_concurrency": 3, # Clamp parallel summaries to avoid request-burst 429s on small providers
},
"skills_hub": {
"provider": "auto",
"model": "",
"base_url": "",
"api_key": "",
"timeout": 30,
"extra_body": {},
},
feat: smart approvals + /stop command (inspired by OpenAI Codex) * feat: smart approvals — LLM-based risk assessment for dangerous commands Adds a 'smart' approval mode that uses the auxiliary LLM to assess whether a flagged command is genuinely dangerous or a false positive, auto-approving low-risk commands without prompting the user. Inspired by OpenAI Codex's Smart Approvals guardian subagent (openai/codex#13860). Config (config.yaml): approvals: mode: manual # manual (default), smart, off Modes: - manual — current behavior, always prompt the user - smart — aux LLM evaluates risk: APPROVE (auto-allow), DENY (block), or ESCALATE (fall through to manual prompt) - off — skip all approval prompts (equivalent to --yolo) When smart mode auto-approves, the pattern gets session-level approval so subsequent uses of the same pattern don't trigger another LLM call. When it denies, the command is blocked without user prompt. When uncertain, it escalates to the normal manual approval flow. The LLM prompt is carefully scoped: it sees only the command text and the flagged reason, assesses actual risk vs false positive, and returns a single-word verdict. * feat: make smart approval model configurable via config.yaml Adds auxiliary.approval section to config.yaml with the same provider/model/base_url/api_key pattern as other aux tasks (vision, web_extract, compression, etc.). Config: auxiliary: approval: provider: auto model: '' # fast/cheap model recommended base_url: '' api_key: '' Bridged to env vars in both CLI and gateway paths so the aux client picks them up automatically. * feat: add /stop command to kill all background processes Adds a /stop slash command that kills all running background processes at once. Currently users have to process(list) then process(kill) for each one individually. Inspired by OpenAI Codex's separation of interrupt (Ctrl+C stops current turn) from /stop (cleans up background processes). See openai/codex#14602. Ctrl+C continues to only interrupt the active agent turn — background dev servers, watchers, etc. are preserved. /stop is the explicit way to clean them all up.
2026-03-16 06:20:11 -07:00
"approval": {
"provider": "auto",
"model": "", # fast/cheap model recommended (e.g. gemini-flash, haiku)
"base_url": "",
"api_key": "",
"timeout": 30,
"extra_body": {},
feat: smart approvals + /stop command (inspired by OpenAI Codex) * feat: smart approvals — LLM-based risk assessment for dangerous commands Adds a 'smart' approval mode that uses the auxiliary LLM to assess whether a flagged command is genuinely dangerous or a false positive, auto-approving low-risk commands without prompting the user. Inspired by OpenAI Codex's Smart Approvals guardian subagent (openai/codex#13860). Config (config.yaml): approvals: mode: manual # manual (default), smart, off Modes: - manual — current behavior, always prompt the user - smart — aux LLM evaluates risk: APPROVE (auto-allow), DENY (block), or ESCALATE (fall through to manual prompt) - off — skip all approval prompts (equivalent to --yolo) When smart mode auto-approves, the pattern gets session-level approval so subsequent uses of the same pattern don't trigger another LLM call. When it denies, the command is blocked without user prompt. When uncertain, it escalates to the normal manual approval flow. The LLM prompt is carefully scoped: it sees only the command text and the flagged reason, assesses actual risk vs false positive, and returns a single-word verdict. * feat: make smart approval model configurable via config.yaml Adds auxiliary.approval section to config.yaml with the same provider/model/base_url/api_key pattern as other aux tasks (vision, web_extract, compression, etc.). Config: auxiliary: approval: provider: auto model: '' # fast/cheap model recommended base_url: '' api_key: '' Bridged to env vars in both CLI and gateway paths so the aux client picks them up automatically. * feat: add /stop command to kill all background processes Adds a /stop slash command that kills all running background processes at once. Currently users have to process(list) then process(kill) for each one individually. Inspired by OpenAI Codex's separation of interrupt (Ctrl+C stops current turn) from /stop (cleans up background processes). See openai/codex#14602. Ctrl+C continues to only interrupt the active agent turn — background dev servers, watchers, etc. are preserved. /stop is the explicit way to clean them all up.
2026-03-16 06:20:11 -07:00
},
"mcp": {
"provider": "auto",
"model": "",
"base_url": "",
"api_key": "",
"timeout": 30,
"extra_body": {},
},
"title_generation": {
"provider": "auto",
"model": "",
"base_url": "",
"api_key": "",
"timeout": 30,
"extra_body": {},
},
},
"display": {
"compact": False,
"personality": "kawaii",
"resume_display": "full",
"busy_input_mode": "interrupt",
"bell_on_complete": False,
"show_reasoning": False,
"streaming": False,
"final_response_markdown": "strip", # render | strip | raw
"inline_diffs": True, # Show inline diff previews for write actions (write_file, patch, skill_manage)
"show_cost": False, # Show $ cost in the status bar (off by default)
"skin": "default",
2026-04-18 21:58:52 +02:00
"user_message_preview": { # CLI: how many submitted user-message lines to echo back in scrollback
"first_lines": 2,
"last_lines": 2,
},
"interim_assistant_messages": True, # Gateway: show natural mid-turn assistant status messages
feat: config-gated /verbose command for messaging gateway (#3262) * feat: config-gated /verbose command for messaging gateway Add gateway_config_gate field to CommandDef, allowing cli_only commands to be conditionally available in the gateway based on a config value. - CommandDef gains gateway_config_gate: str | None — a config dotpath that, when truthy, overrides cli_only for gateway surfaces - /verbose uses gateway_config_gate='display.tool_progress_command' - Default is off (cli_only behavior preserved) - When enabled, /verbose cycles tool_progress mode (off/new/all/verbose) in the gateway, saving to config.yaml — same cycle as the CLI - Gateway helpers (help, telegram menus, slack mapping) dynamically check config to include/exclude config-gated commands - GATEWAY_KNOWN_COMMANDS always includes config-gated commands so the gateway recognizes them and can respond appropriately - Handles YAML 1.1 bool coercion (bare 'off' parses as False) - 8 new tests for the config gate mechanism + gateway handler * docs: document gateway_config_gate and /verbose messaging support - AGENTS.md: add gateway_config_gate to CommandDef fields - slash-commands.md: note /verbose can be enabled for messaging, update Notes - configuration.md: add tool_progress_command to display section + usage note - cli.md: cross-link to config docs for messaging enablement - messaging/index.md: show tool_progress_command in config snippet - plugins.md: add gateway_config_gate to register_command parameter table
2026-03-26 14:41:04 -07:00
"tool_progress_command": False, # Enable /verbose command in messaging gateway
feat: per-platform display verbosity configuration (#8006) Add display.platforms section to config.yaml for per-platform overrides of display settings (tool_progress, show_reasoning, streaming, tool_preview_length). Each platform gets sensible built-in defaults based on capability tier: - High (telegram, discord): tool_progress=all, streaming follows global - Medium (slack, mattermost, matrix, feishu): tool_progress=new - Low (signal, whatsapp, bluebubbles, wecom, etc.): tool_progress=off, streaming=false - Minimal (email, sms, webhook, homeassistant): tool_progress=off, streaming=false Example config: display: platforms: telegram: tool_progress: all show_reasoning: true slack: tool_progress: off Resolution order: platform override > global setting > built-in platform default. Changes: - New gateway/display_config.py: resolver module with tier-based platform defaults - gateway/run.py: tool_progress, tool_preview_length, streaming, show_reasoning all resolve per-platform via the new resolver - /verbose command: now cycles tool_progress per-platform (saves to display.platforms.<platform>.tool_progress instead of global) - /reasoning show|hide: now saves show_reasoning per-platform - Config version 15 -> 16: migrates tool_progress_overrides into display.platforms - Backward compat: legacy tool_progress_overrides still read as fallback - 27 new tests for resolver, normalization, migration, backward compat - Updated verbose command tests for per-platform behavior Addresses community request for per-channel verbosity control (Guillaume Meyer, Nathan Danielsen) — high verbosity on backchannel Telegram, low on customer-facing Slack, none on email.
2026-04-11 17:20:34 -07:00
"tool_progress_overrides": {}, # DEPRECATED — use display.platforms instead
"tool_preview_length": 0, # Max chars for tool call previews (0 = no limit, show full paths/commands)
feat: per-platform display verbosity configuration (#8006) Add display.platforms section to config.yaml for per-platform overrides of display settings (tool_progress, show_reasoning, streaming, tool_preview_length). Each platform gets sensible built-in defaults based on capability tier: - High (telegram, discord): tool_progress=all, streaming follows global - Medium (slack, mattermost, matrix, feishu): tool_progress=new - Low (signal, whatsapp, bluebubbles, wecom, etc.): tool_progress=off, streaming=false - Minimal (email, sms, webhook, homeassistant): tool_progress=off, streaming=false Example config: display: platforms: telegram: tool_progress: all show_reasoning: true slack: tool_progress: off Resolution order: platform override > global setting > built-in platform default. Changes: - New gateway/display_config.py: resolver module with tier-based platform defaults - gateway/run.py: tool_progress, tool_preview_length, streaming, show_reasoning all resolve per-platform via the new resolver - /verbose command: now cycles tool_progress per-platform (saves to display.platforms.<platform>.tool_progress instead of global) - /reasoning show|hide: now saves show_reasoning per-platform - Config version 15 -> 16: migrates tool_progress_overrides into display.platforms - Backward compat: legacy tool_progress_overrides still read as fallback - 27 new tests for resolver, normalization, migration, backward compat - Updated verbose command tests for per-platform behavior Addresses community request for per-channel verbosity control (Guillaume Meyer, Nathan Danielsen) — high verbosity on backchannel Telegram, low on customer-facing Slack, none on email.
2026-04-11 17:20:34 -07:00
"platforms": {}, # Per-platform display overrides: {"telegram": {"tool_progress": "all"}, "slack": {"tool_progress": "off"}}
},
# Web dashboard settings
"dashboard": {
"theme": "default", # Dashboard visual theme: "default", "midnight", "ember", "mono", "cyberpunk", "rose"
},
# Privacy settings
"privacy": {
"redact_pii": False, # When True, hash user IDs and strip phone numbers from LLM context
},
# Text-to-speech configuration
# Each provider supports an optional `max_text_length:` override for the
# per-request input-character cap. Omit it to use the provider's documented
# limit (OpenAI 4096, xAI 15000, MiniMax 10000, ElevenLabs 5k-40k model-aware,
# Gemini 5000, Edge 5000, Mistral 4000, NeuTTS/KittenTTS 2000).
"tts": {
"provider": "edge", # "edge" (free) | "elevenlabs" (premium) | "openai" | "xai" | "minimax" | "mistral" | "neutts" (local)
"edge": {
"voice": "en-US-AriaNeural",
# Popular: AriaNeural, JennyNeural, AndrewNeural, BrianNeural, SoniaNeural
},
"elevenlabs": {
"voice_id": "pNInz6obpgDQGcFmaJgB", # Adam
"model_id": "eleven_multilingual_v2",
},
"openai": {
"model": "gpt-4o-mini-tts",
"voice": "alloy",
# Voices: alloy, echo, fable, onyx, nova, shimmer
},
"xai": {
"voice_id": "eve",
"language": "en",
"sample_rate": 24000,
"bit_rate": 128000,
},
"mistral": {
"model": "voxtral-mini-tts-2603",
"voice_id": "c69964a6-ab8b-4f8a-9465-ec0925096ec8", # Paul - Neutral
},
"neutts": {
"ref_audio": "", # Path to reference voice audio (empty = bundled default)
"ref_text": "", # Path to reference voice transcript (empty = bundled default)
"model": "neuphonic/neutts-air-q4-gguf", # HuggingFace model repo
"device": "cpu", # cpu, cuda, or mps
},
},
Add messaging platform enhancements: STT, stickers, Discord UX, Slack, pairing, hooks Major feature additions inspired by OpenClaw/ClawdBot integration analysis: Voice Message Transcription (STT): - Auto-transcribe voice/audio messages via OpenAI Whisper API - Download voice to ~/.hermes/audio_cache/ on Telegram/Discord/WhatsApp - Inject transcript as text so all models can understand voice input - Configurable model (whisper-1, gpt-4o-mini-transcribe, gpt-4o-transcribe) Telegram Sticker Understanding: - Describe static stickers via vision tool with JSON-backed cache - Cache keyed by file_unique_id avoids redundant API calls - Animated/video stickers get emoji-based fallback description Discord Rich UX: - Native slash commands (/ask, /reset, /status, /stop) via app_commands - Button-based exec approvals (Allow Once / Always Allow / Deny) - ExecApprovalView with user authorization and timeout handling Slack Integration: - Full SlackAdapter using slack-bolt with Socket Mode - DMs, channel messages (mention-gated), /hermes slash command - File attachment handling with bot-token-authenticated downloads DM Pairing System: - Code-based user authorization as alternative to static allowlists - 8-char codes from unambiguous alphabet, 1-hour expiry - Rate limiting, lockout after failed attempts, chmod 0600 on data - CLI: hermes pairing list/approve/revoke/clear-pending Event Hook System: - File-based hook discovery from ~/.hermes/hooks/ - HOOK.yaml + handler.py per hook, sync/async handler support - Events: gateway:startup, session:start/reset, agent:start/step/end - Wildcard matching (command:* catches all command events) Cross-Channel Messaging: - send_message agent tool for delivering to any connected platform - Enables cron job delivery and cross-platform notifications Human-Like Response Pacing: - Configurable delays between message chunks (off/natural/custom) - HERMES_HUMAN_DELAY_MODE env var with min/max ms settings Warm Injection Message Style: - Retrofitted image vision messages with friendly kawaii-consistent tone - All new injection messages (STT, stickers, errors) use warm style Also: updated config migration to prompt for optional keys interactively, bumped config version, updated README, AGENTS.md, .env.example, cli-config.yaml.example, install scripts, pyproject.toml, and toolsets.
2026-02-15 21:38:59 -08:00
"stt": {
"enabled": True,
"provider": "local", # "local" (free, faster-whisper) | "groq" | "openai" (Whisper API) | "mistral" (Voxtral Transcribe)
feat(stt): add free local whisper transcription via faster-whisper (#1185) * fix: Home Assistant event filtering now closed by default Previously, when no watch_domains or watch_entities were configured, ALL state_changed events passed through to the agent, causing users to be flooded with notifications for every HA entity change. Now events are dropped by default unless the user explicitly configures: - watch_domains: list of domains to monitor (e.g. climate, light) - watch_entities: list of specific entity IDs to monitor - watch_all: true (new option — opt-in to receive all events) A warning is logged at connect time if no filters are configured, guiding users to set up their HA platform config. All 49 gateway HA tests + 52 HA tool tests pass. * docs: update Home Assistant integration documentation - homeassistant.md: Fix event filtering docs to reflect closed-by-default behavior. Add watch_all option. Replace Python dict config example with YAML. Fix defaults table (was incorrectly showing 'all'). Add required configuration warning admonition. - environment-variables.md: Add HASS_TOKEN and HASS_URL to Messaging section. - messaging/index.md: Add Home Assistant to description, architecture diagram, platform toolsets table, and Next Steps links. * fix(terminal): strip provider env vars from background and PTY subprocesses Extends the env var blocklist from #1157 to also cover the two remaining leaky paths in process_registry.py: - spawn_local() PTY path (line 156) - spawn_local() background Popen path (line 197) Both were still using raw os.environ, leaking provider vars to background processes and interactive PTY sessions. Now uses the same dynamic _HERMES_PROVIDER_ENV_BLOCKLIST from local.py. Explicit env_vars passed to spawn_local() still override the blocklist, matching the existing behavior for callers that intentionally need these. Gap identified by PR #1004 (@PeterFile). * feat(delegate): add observability metadata to subagent results Enrich delegate_task results with metadata from the child AIAgent: - model: which model the child used - exit_reason: completed | interrupted | max_iterations - tokens.input / tokens.output: token counts - tool_trace: per-tool-call trace with byte sizes and ok/error status Tool trace uses tool_call_id matching to correctly pair parallel tool calls with their results, with a fallback for messages without IDs. Cherry-picked from PR #872 by @omerkaz, with fixes: - Fixed parallel tool call trace pairing (was always updating last entry) - Removed redundant 'iterations' field (identical to existing 'api_calls') - Added test for parallel tool call trace correctness Co-authored-by: omerkaz <omerkaz@users.noreply.github.com> * feat(stt): add free local whisper transcription via faster-whisper Replace OpenAI-only STT with a dual-provider system mirroring the TTS architecture (Edge TTS free / ElevenLabs paid): STT: faster-whisper local (free, default) / OpenAI Whisper API (paid) Changes: - tools/transcription_tools.py: Full rewrite with provider dispatch, config loading, local faster-whisper backend, and OpenAI API backend. Auto-downloads model (~150MB for 'base') on first voice message. Singleton model instance reused across calls. - pyproject.toml: Add faster-whisper>=1.0.0 as core dependency - hermes_cli/config.py: Expand stt config to match TTS pattern with provider selection and per-provider model settings - agent/context_compressor.py: Fix .strip() crash when LLM returns non-string content (dict from llama.cpp, None). Fixes #1100 partially. - tests/: 23 new tests for STT providers + 2 for compressor fix - docs/: Updated Voice & TTS page with STT provider table, model sizes, config examples, and fallback behavior Fallback behavior: - Local not installed → OpenAI API (if key set) - OpenAI key not set → local whisper (if installed) - Neither → graceful error message to user Co-authored-by: Jah-yee <Jah-yee@users.noreply.github.com> --------- Co-authored-by: omerkaz <omerkaz@users.noreply.github.com> Co-authored-by: Jah-yee <Jah-yee@users.noreply.github.com>
2026-03-13 11:11:05 -07:00
"local": {
"model": "base", # tiny, base, small, medium, large-v3
"language": "", # auto-detect by default; set to "en", "es", "fr", etc. to force
feat(stt): add free local whisper transcription via faster-whisper (#1185) * fix: Home Assistant event filtering now closed by default Previously, when no watch_domains or watch_entities were configured, ALL state_changed events passed through to the agent, causing users to be flooded with notifications for every HA entity change. Now events are dropped by default unless the user explicitly configures: - watch_domains: list of domains to monitor (e.g. climate, light) - watch_entities: list of specific entity IDs to monitor - watch_all: true (new option — opt-in to receive all events) A warning is logged at connect time if no filters are configured, guiding users to set up their HA platform config. All 49 gateway HA tests + 52 HA tool tests pass. * docs: update Home Assistant integration documentation - homeassistant.md: Fix event filtering docs to reflect closed-by-default behavior. Add watch_all option. Replace Python dict config example with YAML. Fix defaults table (was incorrectly showing 'all'). Add required configuration warning admonition. - environment-variables.md: Add HASS_TOKEN and HASS_URL to Messaging section. - messaging/index.md: Add Home Assistant to description, architecture diagram, platform toolsets table, and Next Steps links. * fix(terminal): strip provider env vars from background and PTY subprocesses Extends the env var blocklist from #1157 to also cover the two remaining leaky paths in process_registry.py: - spawn_local() PTY path (line 156) - spawn_local() background Popen path (line 197) Both were still using raw os.environ, leaking provider vars to background processes and interactive PTY sessions. Now uses the same dynamic _HERMES_PROVIDER_ENV_BLOCKLIST from local.py. Explicit env_vars passed to spawn_local() still override the blocklist, matching the existing behavior for callers that intentionally need these. Gap identified by PR #1004 (@PeterFile). * feat(delegate): add observability metadata to subagent results Enrich delegate_task results with metadata from the child AIAgent: - model: which model the child used - exit_reason: completed | interrupted | max_iterations - tokens.input / tokens.output: token counts - tool_trace: per-tool-call trace with byte sizes and ok/error status Tool trace uses tool_call_id matching to correctly pair parallel tool calls with their results, with a fallback for messages without IDs. Cherry-picked from PR #872 by @omerkaz, with fixes: - Fixed parallel tool call trace pairing (was always updating last entry) - Removed redundant 'iterations' field (identical to existing 'api_calls') - Added test for parallel tool call trace correctness Co-authored-by: omerkaz <omerkaz@users.noreply.github.com> * feat(stt): add free local whisper transcription via faster-whisper Replace OpenAI-only STT with a dual-provider system mirroring the TTS architecture (Edge TTS free / ElevenLabs paid): STT: faster-whisper local (free, default) / OpenAI Whisper API (paid) Changes: - tools/transcription_tools.py: Full rewrite with provider dispatch, config loading, local faster-whisper backend, and OpenAI API backend. Auto-downloads model (~150MB for 'base') on first voice message. Singleton model instance reused across calls. - pyproject.toml: Add faster-whisper>=1.0.0 as core dependency - hermes_cli/config.py: Expand stt config to match TTS pattern with provider selection and per-provider model settings - agent/context_compressor.py: Fix .strip() crash when LLM returns non-string content (dict from llama.cpp, None). Fixes #1100 partially. - tests/: 23 new tests for STT providers + 2 for compressor fix - docs/: Updated Voice & TTS page with STT provider table, model sizes, config examples, and fallback behavior Fallback behavior: - Local not installed → OpenAI API (if key set) - OpenAI key not set → local whisper (if installed) - Neither → graceful error message to user Co-authored-by: Jah-yee <Jah-yee@users.noreply.github.com> --------- Co-authored-by: omerkaz <omerkaz@users.noreply.github.com> Co-authored-by: Jah-yee <Jah-yee@users.noreply.github.com>
2026-03-13 11:11:05 -07:00
},
"openai": {
"model": "whisper-1", # whisper-1, gpt-4o-mini-transcribe, gpt-4o-transcribe
},
"mistral": {
"model": "voxtral-mini-latest", # voxtral-mini-latest, voxtral-mini-2602
},
Add messaging platform enhancements: STT, stickers, Discord UX, Slack, pairing, hooks Major feature additions inspired by OpenClaw/ClawdBot integration analysis: Voice Message Transcription (STT): - Auto-transcribe voice/audio messages via OpenAI Whisper API - Download voice to ~/.hermes/audio_cache/ on Telegram/Discord/WhatsApp - Inject transcript as text so all models can understand voice input - Configurable model (whisper-1, gpt-4o-mini-transcribe, gpt-4o-transcribe) Telegram Sticker Understanding: - Describe static stickers via vision tool with JSON-backed cache - Cache keyed by file_unique_id avoids redundant API calls - Animated/video stickers get emoji-based fallback description Discord Rich UX: - Native slash commands (/ask, /reset, /status, /stop) via app_commands - Button-based exec approvals (Allow Once / Always Allow / Deny) - ExecApprovalView with user authorization and timeout handling Slack Integration: - Full SlackAdapter using slack-bolt with Socket Mode - DMs, channel messages (mention-gated), /hermes slash command - File attachment handling with bot-token-authenticated downloads DM Pairing System: - Code-based user authorization as alternative to static allowlists - 8-char codes from unambiguous alphabet, 1-hour expiry - Rate limiting, lockout after failed attempts, chmod 0600 on data - CLI: hermes pairing list/approve/revoke/clear-pending Event Hook System: - File-based hook discovery from ~/.hermes/hooks/ - HOOK.yaml + handler.py per hook, sync/async handler support - Events: gateway:startup, session:start/reset, agent:start/step/end - Wildcard matching (command:* catches all command events) Cross-Channel Messaging: - send_message agent tool for delivering to any connected platform - Enables cron job delivery and cross-platform notifications Human-Like Response Pacing: - Configurable delays between message chunks (off/natural/custom) - HERMES_HUMAN_DELAY_MODE env var with min/max ms settings Warm Injection Message Style: - Retrofitted image vision messages with friendly kawaii-consistent tone - All new injection messages (STT, stickers, errors) use warm style Also: updated config migration to prompt for optional keys interactively, bumped config version, updated README, AGENTS.md, .env.example, cli-config.yaml.example, install scripts, pyproject.toml, and toolsets.
2026-02-15 21:38:59 -08:00
},
"voice": {
"record_key": "ctrl+b",
"max_recording_seconds": 120,
"auto_tts": False,
2026-04-20 18:48:59 -06:00
"beep_enabled": True, # Play record start/stop beeps in CLI voice mode
"silence_threshold": 200, # RMS below this = silence (0-32767)
"silence_duration": 3.0, # Seconds of silence before auto-stop
},
Add messaging platform enhancements: STT, stickers, Discord UX, Slack, pairing, hooks Major feature additions inspired by OpenClaw/ClawdBot integration analysis: Voice Message Transcription (STT): - Auto-transcribe voice/audio messages via OpenAI Whisper API - Download voice to ~/.hermes/audio_cache/ on Telegram/Discord/WhatsApp - Inject transcript as text so all models can understand voice input - Configurable model (whisper-1, gpt-4o-mini-transcribe, gpt-4o-transcribe) Telegram Sticker Understanding: - Describe static stickers via vision tool with JSON-backed cache - Cache keyed by file_unique_id avoids redundant API calls - Animated/video stickers get emoji-based fallback description Discord Rich UX: - Native slash commands (/ask, /reset, /status, /stop) via app_commands - Button-based exec approvals (Allow Once / Always Allow / Deny) - ExecApprovalView with user authorization and timeout handling Slack Integration: - Full SlackAdapter using slack-bolt with Socket Mode - DMs, channel messages (mention-gated), /hermes slash command - File attachment handling with bot-token-authenticated downloads DM Pairing System: - Code-based user authorization as alternative to static allowlists - 8-char codes from unambiguous alphabet, 1-hour expiry - Rate limiting, lockout after failed attempts, chmod 0600 on data - CLI: hermes pairing list/approve/revoke/clear-pending Event Hook System: - File-based hook discovery from ~/.hermes/hooks/ - HOOK.yaml + handler.py per hook, sync/async handler support - Events: gateway:startup, session:start/reset, agent:start/step/end - Wildcard matching (command:* catches all command events) Cross-Channel Messaging: - send_message agent tool for delivering to any connected platform - Enables cron job delivery and cross-platform notifications Human-Like Response Pacing: - Configurable delays between message chunks (off/natural/custom) - HERMES_HUMAN_DELAY_MODE env var with min/max ms settings Warm Injection Message Style: - Retrofitted image vision messages with friendly kawaii-consistent tone - All new injection messages (STT, stickers, errors) use warm style Also: updated config migration to prompt for optional keys interactively, bumped config version, updated README, AGENTS.md, .env.example, cli-config.yaml.example, install scripts, pyproject.toml, and toolsets.
2026-02-15 21:38:59 -08:00
"human_delay": {
"mode": "off",
"min_ms": 800,
"max_ms": 2500,
},
# Context engine -- controls how the context window is managed when
# approaching the model's token limit.
# "compressor" = built-in lossy summarization (default).
# Set to a plugin name to activate an alternative engine (e.g. "lcm"
# for Lossless Context Management). The engine must be installed as
# a plugin in plugins/context_engine/<name>/ or ~/.hermes/plugins/.
"context": {
"engine": "compressor",
},
# Persistent memory -- bounded curated memory injected into system prompt
"memory": {
"memory_enabled": True,
"user_profile_enabled": True,
"memory_char_limit": 2200, # ~800 tokens at 2.75 chars/token
"user_char_limit": 1375, # ~500 tokens at 2.75 chars/token
feat(memory): pluggable memory provider interface with profile isolation, review fixes, and honcho CLI restoration (#4623) * feat(memory): add pluggable memory provider interface with profile isolation Introduces a pluggable MemoryProvider ABC so external memory backends can integrate with Hermes without modifying core files. Each backend becomes a plugin implementing a standard interface, orchestrated by MemoryManager. Key architecture: - agent/memory_provider.py — ABC with core + optional lifecycle hooks - agent/memory_manager.py — single integration point in the agent loop - agent/builtin_memory_provider.py — wraps existing MEMORY.md/USER.md Profile isolation fixes applied to all 6 shipped plugins: - Cognitive Memory: use get_hermes_home() instead of raw env var - Hindsight Memory: check $HERMES_HOME/hindsight/config.json first, fall back to legacy ~/.hindsight/ for backward compat - Hermes Memory Store: replace hardcoded ~/.hermes paths with get_hermes_home() for config loading and DB path defaults - Mem0 Memory: use get_hermes_home() instead of raw env var - RetainDB Memory: auto-derive profile-scoped project name from hermes_home path (hermes-<profile>), explicit env var overrides - OpenViking Memory: read-only, no local state, isolation via .env MemoryManager.initialize_all() now injects hermes_home into kwargs so every provider can resolve profile-scoped storage without importing get_hermes_home() themselves. Plugin system: adds register_memory_provider() to PluginContext and get_plugin_memory_providers() accessor. Based on PR #3825. 46 tests (37 unit + 5 E2E + 4 plugin registration). * refactor(memory): drop cognitive plugin, rewrite OpenViking as full provider Remove cognitive-memory plugin (#727) — core mechanics are broken: decay runs 24x too fast (hourly not daily), prefetch uses row ID as timestamp, search limited by importance not similarity. Rewrite openviking-memory plugin from a read-only search wrapper into a full bidirectional memory provider using the complete OpenViking session lifecycle API: - sync_turn: records user/assistant messages to OpenViking session (threaded, non-blocking) - on_session_end: commits session to trigger automatic memory extraction into 6 categories (profile, preferences, entities, events, cases, patterns) - prefetch: background semantic search via find() endpoint - on_memory_write: mirrors built-in memory writes to the session - is_available: checks env var only, no network calls (ABC compliance) Tools expanded from 3 to 5: - viking_search: semantic search with mode/scope/limit - viking_read: tiered content (abstract ~100tok / overview ~2k / full) - viking_browse: filesystem-style navigation (list/tree/stat) - viking_remember: explicit memory storage via session - viking_add_resource: ingest URLs/docs into knowledge base Uses direct HTTP via httpx (no openviking SDK dependency needed). Response truncation on viking_read to prevent context flooding. * fix(memory): harden Mem0 plugin — thread safety, non-blocking sync, circuit breaker - Remove redundant mem0_context tool (identical to mem0_search with rerank=true, top_k=5 — wastes a tool slot and confuses the model) - Thread sync_turn so it's non-blocking — Mem0's server-side LLM extraction can take 5-10s, was stalling the agent after every turn - Add threading.Lock around _get_client() for thread-safe lazy init (prefetch and sync threads could race on first client creation) - Add circuit breaker: after 5 consecutive API failures, pause calls for 120s instead of hammering a down server every turn. Auto-resets after cooldown. Logs a warning when tripped. - Track success/failure in prefetch, sync_turn, and all tool calls - Wait for previous sync to finish before starting a new one (prevents unbounded thread accumulation on rapid turns) - Clean up shutdown to join both prefetch and sync threads * fix(memory): enforce single external memory provider limit MemoryManager now rejects a second non-builtin provider with a warning. Built-in memory (MEMORY.md/USER.md) is always accepted. Only ONE external plugin provider is allowed at a time. This prevents tool schema bloat (some providers add 3-5 tools each) and conflicting memory backends. The warning message directs users to configure memory.provider in config.yaml to select which provider to activate. Updated all 47 tests to use builtin + one external pattern instead of multiple externals. Added test_second_external_rejected to verify the enforcement. * feat(memory): add ByteRover memory provider plugin Implements the ByteRover integration (from PR #3499 by hieuntg81) as a MemoryProvider plugin instead of direct run_agent.py modifications. ByteRover provides persistent memory via the brv CLI — a hierarchical knowledge tree with tiered retrieval (fuzzy text then LLM-driven search). Local-first with optional cloud sync. Plugin capabilities: - prefetch: background brv query for relevant context - sync_turn: curate conversation turns (threaded, non-blocking) - on_memory_write: mirror built-in memory writes to brv - on_pre_compress: extract insights before context compression Tools (3): - brv_query: search the knowledge tree - brv_curate: store facts/decisions/patterns - brv_status: check CLI version and context tree state Profile isolation: working directory at $HERMES_HOME/byterover/ (scoped per profile). Binary resolution cached with thread-safe double-checked locking. All write operations threaded to avoid blocking the agent (curate can take 120s with LLM processing). * fix(memory): thread remaining sync_turns, fix holographic, add config key Plugin fixes: - Hindsight: thread sync_turn (was blocking up to 30s via _run_in_thread) - RetainDB: thread sync_turn (was blocking on HTTP POST) - Both: shutdown now joins sync threads alongside prefetch threads Holographic retrieval fixes: - reason(): removed dead intersection_key computation (bundled but never used in scoring). Now reuses pre-computed entity_residuals directly, moved role_content encoding outside the inner loop. - contradict(): added _MAX_CONTRADICT_FACTS=500 scaling guard. Above 500 facts, only checks the most recently updated ones to avoid O(n^2) explosion (~125K comparisons at 500 is acceptable). Config: - Added memory.provider key to DEFAULT_CONFIG ("" = builtin only). No version bump needed (deep_merge handles new keys automatically). * feat(memory): extract Honcho as a MemoryProvider plugin Creates plugins/honcho-memory/ as a thin adapter over the existing honcho_integration/ package. All 4 Honcho tools (profile, search, context, conclude) move from the normal tool registry to the MemoryProvider interface. The plugin delegates all work to HonchoSessionManager — no Honcho logic is reimplemented. It uses the existing config chain: $HERMES_HOME/honcho.json -> ~/.honcho/config.json -> env vars. Lifecycle hooks: - initialize: creates HonchoSessionManager via existing client factory - prefetch: background dialectic query - sync_turn: records messages + flushes to API (threaded) - on_memory_write: mirrors user profile writes as conclusions - on_session_end: flushes all pending messages This is a prerequisite for the MemoryManager wiring in run_agent.py. Once wired, Honcho goes through the same provider interface as all other memory plugins, and the scattered Honcho code in run_agent.py can be consolidated into the single MemoryManager integration point. * feat(memory): wire MemoryManager into run_agent.py Adds 8 integration points for the external memory provider plugin, all purely additive (zero existing code modified): 1. Init (~L1130): Create MemoryManager, find matching plugin provider from memory.provider config, initialize with session context 2. Tool injection (~L1160): Append provider tool schemas to self.tools and self.valid_tool_names after memory_manager init 3. System prompt (~L2705): Add external provider's system_prompt_block alongside existing MEMORY.md/USER.md blocks 4. Tool routing (~L5362): Route provider tool calls through memory_manager.handle_tool_call() before the catchall handler 5. Memory write bridge (~L5353): Notify external provider via on_memory_write() when the built-in memory tool writes 6. Pre-compress (~L5233): Call on_pre_compress() before context compression discards messages 7. Prefetch (~L6421): Inject provider prefetch results into the current-turn user message (same pattern as Honcho turn context) 8. Turn sync + session end (~L8161, ~L8172): sync_all() after each completed turn, queue_prefetch_all() for next turn, on_session_end() + shutdown_all() at conversation end All hooks are wrapped in try/except — a failing provider never breaks the agent. The existing memory system, Honcho integration, and all other code paths are completely untouched. Full suite: 7222 passed, 4 pre-existing failures. * refactor(memory): remove legacy Honcho integration from core Extracts all Honcho-specific code from run_agent.py, model_tools.py, toolsets.py, and gateway/run.py. Honcho is now exclusively available as a memory provider plugin (plugins/honcho-memory/). Removed from run_agent.py (-457 lines): - Honcho init block (session manager creation, activation, config) - 8 Honcho methods: _honcho_should_activate, _strip_honcho_tools, _activate_honcho, _register_honcho_exit_hook, _queue_honcho_prefetch, _honcho_prefetch, _honcho_save_user_observation, _honcho_sync - _inject_honcho_turn_context module-level function - Honcho system prompt block (tool descriptions, CLI commands) - Honcho context injection in api_messages building - Honcho params from __init__ (honcho_session_key, honcho_manager, honcho_config) - HONCHO_TOOL_NAMES constant - All honcho-specific tool dispatch forwarding Removed from other files: - model_tools.py: honcho_tools import, honcho params from handle_function_call - toolsets.py: honcho toolset definition, honcho tools from core tools list - gateway/run.py: honcho params from AIAgent constructor calls Removed tests (-339 lines): - 9 Honcho-specific test methods from test_run_agent.py - TestHonchoAtexitFlush class from test_exit_cleanup_interrupt.py Restored two regex constants (_SURROGATE_RE, _BUDGET_WARNING_RE) that were accidentally removed during the honcho function extraction. The honcho_integration/ package is kept intact — the plugin delegates to it. tools/honcho_tools.py registry entries are now dead code (import commented out in model_tools.py) but the file is preserved for reference. Full suite: 7207 passed, 4 pre-existing failures. Zero regressions. * refactor(memory): restructure plugins, add CLI, clean gateway, migration notice Plugin restructure: - Move all memory plugins from plugins/<name>-memory/ to plugins/memory/<name>/ (byterover, hindsight, holographic, honcho, mem0, openviking, retaindb) - New plugins/memory/__init__.py discovery module that scans the directory directly, loading providers by name without the general plugin system - run_agent.py uses load_memory_provider() instead of get_plugin_memory_providers() CLI wiring: - hermes memory setup — interactive curses picker + config wizard - hermes memory status — show active provider, config, availability - hermes memory off — disable external provider (built-in only) - hermes honcho — now shows migration notice pointing to hermes memory setup Gateway cleanup: - Remove _get_or_create_gateway_honcho (already removed in prev commit) - Remove _shutdown_gateway_honcho and _shutdown_all_gateway_honcho methods - Remove all calls to shutdown methods (4 call sites) - Remove _honcho_managers/_honcho_configs dict references Dead code removal: - Delete tools/honcho_tools.py (279 lines, import was already commented out) - Delete tests/gateway/test_honcho_lifecycle.py (131 lines, tested removed methods) - Remove if False placeholder from run_agent.py Migration: - Honcho migration notice on startup: detects existing honcho.json or ~/.honcho/config.json, prints guidance to run hermes memory setup. Only fires when memory.provider is not set and not in quiet mode. Full suite: 7203 passed, 4 pre-existing failures. Zero regressions. * feat(memory): standardize plugin config + add per-plugin documentation Config architecture: - Add save_config(values, hermes_home) to MemoryProvider ABC - Honcho: writes to $HERMES_HOME/honcho.json (SDK native) - Mem0: writes to $HERMES_HOME/mem0.json - Hindsight: writes to $HERMES_HOME/hindsight/config.json - Holographic: writes to config.yaml under plugins.hermes-memory-store - OpenViking/RetainDB/ByteRover: env-var only (default no-op) Setup wizard (hermes memory setup): - Now calls provider.save_config() for non-secret config - Secrets still go to .env via env vars - Only memory.provider activation key goes to config.yaml Documentation: - README.md for each of the 7 providers in plugins/memory/<name>/ - Requirements, setup (wizard + manual), config reference, tools table - Consistent format across all providers The contract for new memory plugins: - get_config_schema() declares all fields (REQUIRED) - save_config() writes native config (REQUIRED if not env-var-only) - Secrets use env_var field in schema, written to .env by wizard - README.md in the plugin directory * docs: add memory providers user guide + developer guide New pages: - user-guide/features/memory-providers.md — comprehensive guide covering all 7 shipped providers (Honcho, OpenViking, Mem0, Hindsight, Holographic, RetainDB, ByteRover). Each with setup, config, tools, cost, and unique features. Includes comparison table and profile isolation notes. - developer-guide/memory-provider-plugin.md — how to build a new memory provider plugin. Covers ABC, required methods, config schema, save_config, threading contract, profile isolation, testing. Updated pages: - user-guide/features/memory.md — replaced Honcho section with link to new Memory Providers page - user-guide/features/honcho.md — replaced with migration redirect to the new Memory Providers page - sidebars.ts — added both new pages to navigation * fix(memory): auto-migrate Honcho users to memory provider plugin When honcho.json or ~/.honcho/config.json exists but memory.provider is not set, automatically set memory.provider: honcho in config.yaml and activate the plugin. The plugin reads the same config files, so all data and credentials are preserved. Zero user action needed. Persists the migration to config.yaml so it only fires once. Prints a one-line confirmation in non-quiet mode. * fix(memory): only auto-migrate Honcho when enabled + credentialed Check HonchoClientConfig.enabled AND (api_key OR base_url) before auto-migrating — not just file existence. Prevents false activation for users who disabled Honcho, stopped using it (config lingers), or have ~/.honcho/ from a different tool. * feat(memory): auto-install pip dependencies during hermes memory setup Reads pip_dependencies from plugin.yaml, checks which are missing, installs them via pip before config walkthrough. Also shows install guidance for external_dependencies (e.g. brv CLI for ByteRover). Updated all 7 plugin.yaml files with pip_dependencies: - honcho: honcho-ai - mem0: mem0ai - openviking: httpx - hindsight: hindsight-client - holographic: (none) - retaindb: requests - byterover: (external_dependencies for brv CLI) * fix: remove remaining Honcho crash risks from cli.py and gateway cli.py: removed Honcho session re-mapping block (would crash importing deleted tools/honcho_tools.py), Honcho flush on compress, Honcho session display on startup, Honcho shutdown on exit, honcho_session_key AIAgent param. gateway/run.py: removed honcho_session_key params from helper methods, sync_honcho param, _honcho.shutdown() block. tests: fixed test_cron_session_with_honcho_key_skipped (was passing removed honcho_key param to _flush_memories_for_session). * fix: include plugins/ in pyproject.toml package list Without this, plugins/memory/ wouldn't be included in non-editable installs. Hermes always runs from the repo checkout so this is belt- and-suspenders, but prevents breakage if the install method changes. * fix(memory): correct pip-to-import name mapping for dep checks The heuristic dep.replace('-', '_') fails for packages where the pip name differs from the import name: honcho-ai→honcho, mem0ai→mem0, hindsight-client→hindsight_client. Added explicit mapping table so hermes memory setup doesn't try to reinstall already-installed packages. * chore: remove dead code from old plugin memory registration path - hermes_cli/plugins.py: removed register_memory_provider(), _memory_providers list, get_plugin_memory_providers() — memory providers now use plugins/memory/ discovery, not the general plugin system - hermes_cli/main.py: stripped 74 lines of dead honcho argparse subparsers (setup, status, sessions, map, peer, mode, tokens, identity, migrate) — kept only the migration redirect - agent/memory_provider.py: updated docstring to reflect new registration path - tests: replaced TestPluginMemoryProviderRegistration with TestPluginMemoryDiscovery that tests the actual plugins/memory/ discovery system. Added 3 new tests (discover, load, nonexistent). * chore: delete dead honcho_integration/cli.py and its tests cli.py (794 lines) was the old 'hermes honcho' command handler — nobody calls it since cmd_honcho was replaced with a migration redirect. Deleted tests that imported from removed code: - tests/honcho_integration/test_cli.py (tested _resolve_api_key) - tests/honcho_integration/test_config_isolation.py (tested CLI config paths) - tests/tools/test_honcho_tools.py (tested the deleted tools/honcho_tools.py) Remaining honcho_integration/ files (actively used by the plugin): - client.py (445 lines) — config loading, SDK client creation - session.py (991 lines) — session management, queries, flush * refactor: move honcho_integration/ into the honcho plugin Moves client.py (445 lines) and session.py (991 lines) from the top-level honcho_integration/ package into plugins/memory/honcho/. No Honcho code remains in the main codebase. - plugins/memory/honcho/client.py — config loading, SDK client creation - plugins/memory/honcho/session.py — session management, queries, flush - Updated all imports: run_agent.py (auto-migration), hermes_cli/doctor.py, plugin __init__.py, session.py cross-import, all tests - Removed honcho_integration/ package and pyproject.toml entry - Renamed tests/honcho_integration/ → tests/honcho_plugin/ * docs: update architecture + gateway-internals for memory provider system - architecture.md: replaced honcho_integration/ with plugins/memory/ - gateway-internals.md: replaced Honcho-specific session routing and flush lifecycle docs with generic memory provider interface docs * fix: update stale mock path for resolve_active_host after honcho plugin migration * fix(memory): address review feedback — P0 lifecycle, ABC contract, honcho CLI restore Review feedback from Honcho devs (erosika): P0 — Provider lifecycle: - Remove on_session_end() + shutdown_all() from run_conversation() tail (was killing providers after every turn in multi-turn sessions) - Add shutdown_memory_provider() method on AIAgent for callers - Wire shutdown into CLI atexit, reset_conversation, gateway stop/expiry Bug fixes: - Remove sync_honcho=False kwarg from /btw callsites (TypeError crash) - Fix doctor.py references to dead 'hermes honcho setup' command - Cache prefetch_all() before tool loop (was re-calling every iteration) ABC contract hardening (all backwards-compatible): - Add session_id kwarg to prefetch/sync_turn/queue_prefetch - Make on_pre_compress() return str (provider insights in compression) - Add **kwargs to on_turn_start() for runtime context - Add on_delegation() hook for parent-side subagent observation - Document agent_context/agent_identity/agent_workspace kwargs on initialize() (prevents cron corruption, enables profile scoping) - Fix docstring: single external provider, not multiple Honcho CLI restoration: - Add plugins/memory/honcho/cli.py (from main's honcho_integration/cli.py with imports adapted to plugin path) - Restore full hermes honcho command with all subcommands (status, peer, mode, tokens, identity, enable/disable, sync, peers, --target-profile) - Restore auto-clone on profile creation + sync on hermes update - hermes honcho setup now redirects to hermes memory setup * fix(memory): wire on_delegation, skip_memory for cron/flush, fix ByteRover return type - Wire on_delegation() in delegate_tool.py — parent's memory provider is notified with task+result after each subagent completes - Add skip_memory=True to cron scheduler (prevents cron system prompts from corrupting user representations — closes #4052) - Add skip_memory=True to gateway flush agent (throwaway agent shouldn't activate memory provider) - Fix ByteRover on_pre_compress() return type: None -> str * fix(honcho): port profile isolation fixes from PR #4632 Ports 5 bug fixes found during profile testing (erosika's PR #4632): 1. 3-tier config resolution — resolve_config_path() now checks $HERMES_HOME/honcho.json → ~/.hermes/honcho.json → ~/.honcho/config.json (non-default profiles couldn't find shared host blocks) 2. Thread host=_host_key() through from_global_config() in cmd_setup, cmd_status, cmd_identity (--target-profile was being ignored) 3. Use bare profile name as aiPeer (not host key with dots) — Honcho's peer ID pattern is ^[a-zA-Z0-9_-]+$, dots are invalid 4. Wrap add_peers() in try/except — was fatal on new AI peers, killed all message uploads for the session 5. Gate Honcho clone behind --clone/--clone-all on profile create (bare create should be blank-slate) Also: sanitize assistant_peer_id via _sanitize_id() * fix(tests): add module cleanup fixture to test_cli_provider_resolution test_cli_provider_resolution._import_cli() wipes tools.*, cli, and run_agent from sys.modules to force fresh imports, but had no cleanup. This poisoned all subsequent tests on the same xdist worker — mocks targeting tools.file_tools, tools.send_message_tool, etc. patched the NEW module object while already-imported functions still referenced the OLD one. Caused ~25 cascade failures: send_message KeyError, process_registry FileNotFoundError, file_read_guards timeouts, read_loop_detection file-not-found, mcp_oauth None port, and provider_parity/codex_execution stale tool lists. Fix: autouse fixture saves all affected modules before each test and restores them after, matching the pattern in test_managed_browserbase_and_modal.py.
2026-04-02 15:33:51 -07:00
# External memory provider plugin (empty = built-in only).
# Set to a provider name to activate: "openviking", "mem0",
# "hindsight", "holographic", "retaindb", "byterover".
# Only ONE external provider is allowed at a time.
"provider": "",
},
# Subagent delegation — override the provider:model used by delegate_task
# so child agents can run on a different (cheaper/faster) provider and model.
# Uses the same runtime provider resolution as CLI/gateway startup, so all
# configured providers (OpenRouter, Nous, Z.ai, Kimi, etc.) are supported.
"delegation": {
"model": "", # e.g. "google/gemini-3-flash-preview" (empty = inherit parent model)
"provider": "", # e.g. "openrouter" (empty = inherit parent provider + credentials)
"base_url": "", # direct OpenAI-compatible endpoint for subagents
"api_key": "", # API key for delegation.base_url (falls back to OPENAI_API_KEY)
# When delegate_task narrows child toolsets explicitly, preserve any
# MCP toolsets the parent already has enabled. On by default so
# narrowing (e.g. toolsets=["web","browser"]) expresses "I want these
# extras" without silently stripping MCP tools the parent already has.
# Set to false for strict intersection.
"inherit_mcp_toolsets": True,
"max_iterations": 50, # per-subagent iteration cap (each subagent gets its own budget,
# independent of the parent's max_iterations)
"child_timeout_seconds": 600, # wall-clock timeout for each child agent (floor 30s,
# no ceiling). High-reasoning models on large tasks
# (e.g. gpt-5.5 xhigh, opus-4.6) need generous budgets;
# raise if children time out before producing output.
"reasoning_effort": "", # reasoning effort for subagents: "xhigh", "high", "medium",
# "low", "minimal", "none" (empty = inherit parent's level)
"max_concurrent_children": 3, # max parallel children per batch; floor of 1 enforced, no ceiling
# Orchestrator role controls (see tools/delegate_tool.py:_get_max_spawn_depth
# and _get_orchestrator_enabled). Values are clamped to [1, 3] with a
# warning log if out of range.
"max_spawn_depth": 1, # depth cap (1 = flat [default], 2 = orchestrator→leaf, 3 = three-level)
"orchestrator_enabled": True, # kill switch for role="orchestrator"
# When a subagent hits a dangerous-command approval prompt, the parent's
# prompt_toolkit TUI owns stdin — a thread-local input() call from the
# subagent worker would deadlock the parent UI. To avoid the deadlock,
# subagent threads ALWAYS resolve approvals non-interactively:
# false (default) → auto-deny with a logger.warning audit line (safe)
# true → auto-approve "once" with a logger.warning audit line
# Flip to true only if you trust delegated work to run dangerous cmds
# without human review (cron pipelines, batch automation, etc.).
"subagent_auto_approve": False,
},
# Ephemeral prefill messages file — JSON list of {role, content} dicts
# injected at the start of every API call for few-shot priming.
# Never saved to sessions, logs, or trajectories.
"prefill_messages_file": "",
# Skills — external skill directories for sharing skills across tools/agents.
# Each path is expanded (~, ${VAR}) and resolved. Read-only — skill creation
# always goes to ~/.hermes/skills/.
"skills": {
"external_dirs": [], # e.g. ["~/.agents/skills", "/shared/team-skills"]
feat(skills+terminal): make bundled skill scripts runnable out of the box (#13384) * feat(skills): inject absolute skill dir and expand ${HERMES_SKILL_DIR} templates When a skill loads, the activation message now exposes the absolute skill directory and substitutes ${HERMES_SKILL_DIR} / ${HERMES_SESSION_ID} tokens in the SKILL.md body, so skills with bundled scripts can instruct the agent to run them by absolute path without an extra skill_view round-trip. Also adds opt-in inline-shell expansion: !`cmd` snippets in SKILL.md are pre-executed (with the skill directory as CWD) and their stdout is inlined into the message before the agent reads it. Off by default — enable via skills.inline_shell in config.yaml — because any snippet runs on the host without approval. Changes: - agent/skill_commands.py: template substitution, inline-shell expansion, absolute skill-dir header, supporting-files list now shows both relative and absolute forms. - hermes_cli/config.py: new skills.template_vars, skills.inline_shell, skills.inline_shell_timeout knobs. - tests/agent/test_skill_commands.py: coverage for header, both template tokens (present and missing session id), template_vars disable, inline-shell default-off, enabled, CWD, and timeout. - website/docs/developer-guide/creating-skills.md: documents the template tokens, the absolute-path header, and the opt-in inline shell with its security caveat. Validation: tests/agent/ 1591 passed (includes 9 new tests). E2E: loaded a real skill in an isolated HERMES_HOME; confirmed ${HERMES_SKILL_DIR} resolves to the absolute path, ${HERMES_SESSION_ID} resolves to the passed task_id, !`date` runs when opt-in is set, and stays literal when it isn't. * feat(terminal): source ~/.bashrc (and user-listed init files) into session snapshot bash login shells don't source ~/.bashrc, so tools that install themselves there — nvm, asdf, pyenv, cargo, custom PATH exports — stay invisible to the environment snapshot Hermes builds once per session. Under systemd or any context with a minimal parent env, that surfaces as 'node: command not found' in the terminal tool even though the binary is reachable from every interactive shell on the machine. Changes: - tools/environments/local.py: before the login-shell snapshot bootstrap runs, prepend guarded 'source <file>' lines for each resolved init file. Missing files are skipped, each source is wrapped with a '[ -r ... ] && . ... || true' guard so a broken rc can't abort the bootstrap. - hermes_cli/config.py: new terminal.shell_init_files (explicit list, supports ~ and ${VAR}) and terminal.auto_source_bashrc (default on) knobs. When shell_init_files is set it takes precedence; when it's empty and auto_source_bashrc is on, ~/.bashrc gets auto-sourced. - tests/tools/test_local_shell_init.py: 10 tests covering the resolver (auto-bashrc, missing file, explicit override, ~/${VAR} expansion, opt-out) and the prelude builder (quoting, guarded sourcing), plus a real-LocalEnvironment snapshot test that confirms exports in the init file land in subsequent commands' environment. - website/docs/reference/faq.md: documents the fix in Troubleshooting, including the zsh-user pattern of sourcing ~/.zshrc or nvm.sh directly via shell_init_files. Validation: 10/10 new tests pass; tests/tools/test_local_*.py 40/40 pass; tests/agent/ 1591/1591 pass; tests/hermes_cli/test_config.py 50/50 pass. E2E in an isolated HERMES_HOME: confirmed that a fake ~/.bashrc setting a marker var and PATH addition shows up in a real LocalEnvironment().execute() call, that auto_source_bashrc=false suppresses it, that an explicit shell_init_files entry wins over the auto default, and that a missing bashrc is silently skipped.
2026-04-21 00:39:19 -07:00
# Substitute ${HERMES_SKILL_DIR} and ${HERMES_SESSION_ID} in SKILL.md
# content with the absolute skill directory and the active session id
# before the agent sees it. Lets skill authors reference bundled
# scripts without the agent having to join paths.
"template_vars": True,
# Pre-execute inline shell snippets written as !`cmd` in SKILL.md
# body. Their stdout is inlined into the skill message before the
# agent reads it, so skills can inject dynamic context (dates, git
# state, detected tool versions, …). Off by default because any
# content from the skill author runs on the host without approval;
# only enable for skill sources you trust.
"inline_shell": False,
# Timeout (seconds) for each !`cmd` snippet when inline_shell is on.
"inline_shell_timeout": 10,
feat(skills-guard): gate agent-created scanner on config.skills.guard_agent_created (default off) Replaces the blanket 'always allow' change from the previous commit with an opt-in config flag so users who want belt-and-suspenders security can still get the keyword scan on skill_manage output. ## Default behavior (flag off) skill_manage(action='create'|'edit'|'patch') no longer runs the keyword scanner. The agent can write skills that mention risky keywords in prose (documenting what reviewers should watch for, describing cache-bust semantics in a PR-review skill, referencing AGENTS.md, etc.) without getting blocked. Rationale: the agent can already execute the same code paths via terminal() with no gate, so the scan adds friction without meaningful security against a compromised or malicious agent. ## Opt-in behavior (flag on) Set skills.guard_agent_created: true in config.yaml to get the original behavior back. Scanner runs on every skill_manage write; dangerous verdicts surface as a tool error the agent can react to (retry without the flagged content). ## External hub installs unaffected trusted/community sources (hermes skills install) always get scanned regardless of this flag. The gate is specifically for skill_manage, which only agents call. ## Changes - hermes_cli/config.py: add skills.guard_agent_created: False to DEFAULT_CONFIG - tools/skill_manager_tool.py: _guard_agent_created_enabled() reads the flag; _security_scan_skill() short-circuits to None when the flag is off - tools/skills_guard.py: restore INSTALL_POLICY['agent-created'] = ('allow', 'allow', 'ask') so the scan remains strict when it does run - tests/tools/test_skills_guard.py: restore original ask/force tests - tests/tools/test_skill_manager_tool.py: new TestSecurityScanGate class covering both flag states + config error handling ## Validation - tests/tools/test_skills_guard.py + test_skill_manager_tool.py: 115/115 pass - E2E: flagged-keyword skill creates with default config, blocks with flag on
2026-04-23 06:20:19 -07:00
# Run the keyword/pattern security scanner on skills the agent
# writes via skill_manage (create/edit/patch). Off by default
# because the agent can already execute the same code paths via
# terminal() with no gate, so the scan adds friction (blocks
# skills that mention risky keywords in prose) without meaningful
# security. Turn on if you want the belt-and-suspenders — a
# dangerous verdict will then surface as a tool error to the
# agent, which can retry with the flagged content removed.
# External hub installs (trusted/community sources) are always
# scanned regardless of this setting.
"guard_agent_created": False,
},
# Honcho AI-native memory -- reads ~/.honcho/config.json as single source of truth.
# This section is only needed for hermes-specific overrides; everything else
# (apiKey, workspace, peerName, sessions, enabled) comes from the global config.
"honcho": {},
# IANA timezone (e.g. "Asia/Kolkata", "America/New_York").
# Empty string means use server-local time.
"timezone": "",
# Discord platform settings (gateway mode)
"discord": {
"require_mention": True, # Require @mention to respond in server channels
"free_response_channels": "", # Comma-separated channel IDs where bot responds without mention
"allowed_channels": "", # If set, bot ONLY responds in these channel IDs (whitelist)
"auto_thread": True, # Auto-create threads on @mention in channels (like Slack)
"reactions": True, # Add 👀/✅/❌ reactions to messages during processing
"channel_prompts": {}, # Per-channel ephemeral system prompts (forum parents apply to child threads)
# discord / discord_admin tools: restrict which actions the agent may call.
feat: add Discord server introspection and management tool (#4753) * feat: add Discord server introspection and management tool Add a discord_server tool that gives the agent the ability to interact with Discord servers when running on the Discord gateway. Uses Discord REST API directly with the bot token — no dependency on the gateway adapter's discord.py client. The tool is only included in the hermes-discord toolset (zero cost for users on other platforms) and gated on DISCORD_BOT_TOKEN via check_fn. Actions (14): - Introspection: list_guilds, server_info, list_channels, channel_info, list_roles, member_info, search_members - Messages: fetch_messages, list_pins, pin_message, unpin_message - Management: create_thread, add_role, remove_role This addresses a gap where users on Discord could not ask Hermes to review server structure, channels, roles, or members — a task competing agents (OpenClaw) handle out of the box. Files changed: - tools/discord_tool.py (new): Tool implementation + registration - model_tools.py: Add to discovery list - toolsets.py: Add to hermes-discord toolset only - tests/tools/test_discord_tool.py (new): 43 tests covering all actions, validation, error handling, registration, and toolset scoping * feat(discord): intent-aware schema filtering + config allowlist + schema cleanup - _detect_capabilities() hits GET /applications/@me once per process to read GUILD_MEMBERS / MESSAGE_CONTENT privileged intent bits. - Schema is rebuilt per-session in model_tools.get_tool_definitions: hides search_members / member_info when GUILD_MEMBERS intent is off, annotates fetch_messages description when MESSAGE_CONTENT is off. - New config key discord.server_actions (comma-separated or YAML list) lets users restrict which actions the agent can call, intersected with intent availability. Unknown names are warned and dropped. - Defense-in-depth: runtime handler re-checks the allowlist so a stale cached schema cannot bypass a tightened config. - Schema description rewritten as an action-first manifest (signature per action) instead of per-parameter 'required for X, Y, Z' cross-refs. ~25% shorter; model can see each action's required params at a glance. - Added bounds: limit gets minimum=1 maximum=100, auto_archive_duration becomes an enum of the 4 valid Discord values. - 403 enrichment: runtime 403 errors are mapped to actionable guidance (which permission is missing and what to do about it) instead of the raw Discord error body. - 36 new tests: capability detection with caching and force refresh, config allowlist parsing (string/list/invalid/unknown), intent+allowlist intersection, dynamic schema build, runtime allowlist enforcement, 403 enrichment, and model_tools integration wiring.
2026-04-19 11:52:19 -07:00
# Default (empty) = all actions allowed (subject to bot privileged intents).
# Accepts comma-separated string ("list_guilds,list_channels,fetch_messages")
# or YAML list. Unknown names are dropped with a warning at load time.
# Actions: list_guilds, server_info, list_channels, channel_info,
# list_roles, member_info, search_members, fetch_messages, list_pins,
# pin_message, unpin_message, create_thread, add_role, remove_role.
"server_actions": "",
},
feat: OpenAI-compatible API server + WhatsApp configurable reply prefix (#1756) * feat: OpenAI-compatible API server platform adapter Salvaged from PR #956, updated for current main. Adds an HTTP API server as a gateway platform adapter that exposes hermes-agent via the OpenAI Chat Completions and Responses APIs. Any OpenAI-compatible frontend (Open WebUI, LobeChat, LibreChat, AnythingLLM, NextChat, ChatBox, etc.) can connect by pointing at http://localhost:8642/v1. Endpoints: - POST /v1/chat/completions — stateless Chat Completions API - POST /v1/responses — stateful Responses API with chaining - GET /v1/responses/{id} — retrieve stored response - DELETE /v1/responses/{id} — delete stored response - GET /v1/models — list hermes-agent as available model - GET /health — health check Features: - Real SSE streaming via stream_delta_callback (uses main's streaming) - In-memory LRU response store for Responses API conversation chaining - Named conversations via 'conversation' parameter - Bearer token auth (optional, via API_SERVER_KEY) - CORS support for browser-based frontends - System prompt layering (frontend system messages on top of core) - Real token usage tracking in responses Integration points: - Platform.API_SERVER in gateway/config.py - _create_adapter() branch in gateway/run.py - API_SERVER_* env vars in hermes_cli/config.py - Env var overrides in gateway/config.py _apply_env_overrides() Changes vs original PR #956: - Removed streaming infrastructure (already on main via stream_consumer.py) - Removed Telegram reply_to_mode (separate feature, not included) - Updated _resolve_model() -> _resolve_gateway_model() - Updated stream_callback -> stream_delta_callback - Updated connect()/disconnect() to use _mark_connected()/_mark_disconnected() - Adapted to current Platform enum (includes MATTERMOST, MATRIX, DINGTALK) Tests: 72 new tests, all passing Docs: API server guide, Open WebUI integration guide, env var reference * feat(whatsapp): make reply prefix configurable via config.yaml Reworked from PR #1764 (ifrederico) to use config.yaml instead of .env. The WhatsApp bridge prepends a header to every outgoing message. This was hardcoded to '⚕ *Hermes Agent*'. Users can now customize or disable it via config.yaml: whatsapp: reply_prefix: '' # disable header reply_prefix: '🤖 *My Bot*\n───\n' # custom prefix How it works: - load_gateway_config() reads whatsapp.reply_prefix from config.yaml and stores it in PlatformConfig.extra['reply_prefix'] - WhatsAppAdapter reads it from config.extra at init - When spawning bridge.js, the adapter passes it as WHATSAPP_REPLY_PREFIX in the subprocess environment - bridge.js handles undefined (default), empty (no header), or custom values with \\n escape support - Self-chat echo suppression uses the configured prefix Also fixes _config_version: was 9 but ENV_VARS_BY_VERSION had a key 10 (TAVILY_API_KEY), so existing users at v9 would never be prompted for Tavily. Bumped to 10 to close the gap. Added a regression test to prevent this from happening again. Credit: ifrederico (PR #1764) for the bridge.js implementation and the config version gap discovery. --------- Co-authored-by: Test <test@test.com>
2026-03-17 10:44:37 -07:00
# WhatsApp platform settings (gateway mode)
"whatsapp": {
# Reply prefix prepended to every outgoing WhatsApp message.
# Default (None) uses the built-in "⚕ *Hermes Agent*" header.
# Set to "" (empty string) to disable the header entirely.
# Supports \n for newlines, e.g. "🤖 *My Bot*\n──────\n"
},
# Telegram platform settings (gateway mode)
"telegram": {
"channel_prompts": {}, # Per-chat/topic ephemeral system prompts (topics inherit from parent group)
},
# Slack platform settings (gateway mode)
"slack": {
"channel_prompts": {}, # Per-channel ephemeral system prompts
},
# Mattermost platform settings (gateway mode)
"mattermost": {
"channel_prompts": {}, # Per-channel ephemeral system prompts
},
feat: smart approvals + /stop command (inspired by OpenAI Codex) * feat: smart approvals — LLM-based risk assessment for dangerous commands Adds a 'smart' approval mode that uses the auxiliary LLM to assess whether a flagged command is genuinely dangerous or a false positive, auto-approving low-risk commands without prompting the user. Inspired by OpenAI Codex's Smart Approvals guardian subagent (openai/codex#13860). Config (config.yaml): approvals: mode: manual # manual (default), smart, off Modes: - manual — current behavior, always prompt the user - smart — aux LLM evaluates risk: APPROVE (auto-allow), DENY (block), or ESCALATE (fall through to manual prompt) - off — skip all approval prompts (equivalent to --yolo) When smart mode auto-approves, the pattern gets session-level approval so subsequent uses of the same pattern don't trigger another LLM call. When it denies, the command is blocked without user prompt. When uncertain, it escalates to the normal manual approval flow. The LLM prompt is carefully scoped: it sees only the command text and the flagged reason, assesses actual risk vs false positive, and returns a single-word verdict. * feat: make smart approval model configurable via config.yaml Adds auxiliary.approval section to config.yaml with the same provider/model/base_url/api_key pattern as other aux tasks (vision, web_extract, compression, etc.). Config: auxiliary: approval: provider: auto model: '' # fast/cheap model recommended base_url: '' api_key: '' Bridged to env vars in both CLI and gateway paths so the aux client picks them up automatically. * feat: add /stop command to kill all background processes Adds a /stop slash command that kills all running background processes at once. Currently users have to process(list) then process(kill) for each one individually. Inspired by OpenAI Codex's separation of interrupt (Ctrl+C stops current turn) from /stop (cleans up background processes). See openai/codex#14602. Ctrl+C continues to only interrupt the active agent turn — background dev servers, watchers, etc. are preserved. /stop is the explicit way to clean them all up.
2026-03-16 06:20:11 -07:00
# Approval mode for dangerous commands:
# manual — always prompt the user (default)
# smart — use auxiliary LLM to auto-approve low-risk commands, prompt for high-risk
# off — skip all approval prompts (equivalent to --yolo)
#
# cron_mode — what to do when a cron job hits a dangerous command:
# deny — block the command and let the agent find another way (default, safe)
# approve — auto-approve all dangerous commands in cron jobs
feat: smart approvals + /stop command (inspired by OpenAI Codex) * feat: smart approvals — LLM-based risk assessment for dangerous commands Adds a 'smart' approval mode that uses the auxiliary LLM to assess whether a flagged command is genuinely dangerous or a false positive, auto-approving low-risk commands without prompting the user. Inspired by OpenAI Codex's Smart Approvals guardian subagent (openai/codex#13860). Config (config.yaml): approvals: mode: manual # manual (default), smart, off Modes: - manual — current behavior, always prompt the user - smart — aux LLM evaluates risk: APPROVE (auto-allow), DENY (block), or ESCALATE (fall through to manual prompt) - off — skip all approval prompts (equivalent to --yolo) When smart mode auto-approves, the pattern gets session-level approval so subsequent uses of the same pattern don't trigger another LLM call. When it denies, the command is blocked without user prompt. When uncertain, it escalates to the normal manual approval flow. The LLM prompt is carefully scoped: it sees only the command text and the flagged reason, assesses actual risk vs false positive, and returns a single-word verdict. * feat: make smart approval model configurable via config.yaml Adds auxiliary.approval section to config.yaml with the same provider/model/base_url/api_key pattern as other aux tasks (vision, web_extract, compression, etc.). Config: auxiliary: approval: provider: auto model: '' # fast/cheap model recommended base_url: '' api_key: '' Bridged to env vars in both CLI and gateway paths so the aux client picks them up automatically. * feat: add /stop command to kill all background processes Adds a /stop slash command that kills all running background processes at once. Currently users have to process(list) then process(kill) for each one individually. Inspired by OpenAI Codex's separation of interrupt (Ctrl+C stops current turn) from /stop (cleans up background processes). See openai/codex#14602. Ctrl+C continues to only interrupt the active agent turn — background dev servers, watchers, etc. are preserved. /stop is the explicit way to clean them all up.
2026-03-16 06:20:11 -07:00
"approvals": {
"mode": "manual",
"timeout": 60,
"cron_mode": "deny",
feat: smart approvals + /stop command (inspired by OpenAI Codex) * feat: smart approvals — LLM-based risk assessment for dangerous commands Adds a 'smart' approval mode that uses the auxiliary LLM to assess whether a flagged command is genuinely dangerous or a false positive, auto-approving low-risk commands without prompting the user. Inspired by OpenAI Codex's Smart Approvals guardian subagent (openai/codex#13860). Config (config.yaml): approvals: mode: manual # manual (default), smart, off Modes: - manual — current behavior, always prompt the user - smart — aux LLM evaluates risk: APPROVE (auto-allow), DENY (block), or ESCALATE (fall through to manual prompt) - off — skip all approval prompts (equivalent to --yolo) When smart mode auto-approves, the pattern gets session-level approval so subsequent uses of the same pattern don't trigger another LLM call. When it denies, the command is blocked without user prompt. When uncertain, it escalates to the normal manual approval flow. The LLM prompt is carefully scoped: it sees only the command text and the flagged reason, assesses actual risk vs false positive, and returns a single-word verdict. * feat: make smart approval model configurable via config.yaml Adds auxiliary.approval section to config.yaml with the same provider/model/base_url/api_key pattern as other aux tasks (vision, web_extract, compression, etc.). Config: auxiliary: approval: provider: auto model: '' # fast/cheap model recommended base_url: '' api_key: '' Bridged to env vars in both CLI and gateway paths so the aux client picks them up automatically. * feat: add /stop command to kill all background processes Adds a /stop slash command that kills all running background processes at once. Currently users have to process(list) then process(kill) for each one individually. Inspired by OpenAI Codex's separation of interrupt (Ctrl+C stops current turn) from /stop (cleans up background processes). See openai/codex#14602. Ctrl+C continues to only interrupt the active agent turn — background dev servers, watchers, etc. are preserved. /stop is the explicit way to clean them all up.
2026-03-16 06:20:11 -07:00
},
# Permanently allowed dangerous command patterns (added via "always" approval)
"command_allowlist": [],
# User-defined quick commands that bypass the agent loop (type: exec only)
"quick_commands": {},
# Shell-script hooks — declarative bridge that invokes shell scripts
# on plugin-hook events (pre_tool_call, post_tool_call, pre_llm_call,
# subagent_stop, etc.). Each entry maps an event name to a list of
# {matcher, command, timeout} dicts. First registration of a new
# command prompts the user for consent; subsequent runs reuse the
# stored approval from ~/.hermes/shell-hooks-allowlist.json.
# See `website/docs/user-guide/features/hooks.md` for schema + examples.
"hooks": {},
# Auto-accept shell-hook registrations without a TTY prompt. Also
# toggleable per-invocation via --accept-hooks or HERMES_ACCEPT_HOOKS=1.
# Gateway / cron / non-interactive runs need this (or one of the other
# channels) to pick up newly-added hooks.
"hooks_auto_accept": False,
# Custom personalities — add your own entries here
# Supports string format: {"name": "system prompt"}
# Or dict format: {"name": {"description": "...", "system_prompt": "...", "tone": "...", "style": "..."}}
"personalities": {},
feat(security): add tirith pre-exec command scanning Integrate tirith as a pre-execution security scanner that detects homograph URLs, pipe-to-interpreter patterns, terminal injection, zero-width Unicode, and environment variable manipulation — threats the existing 50-pattern dangerous command detector doesn't cover. Architecture: gather-then-decide — both tirith and the dangerous command detector run before any approval prompt, preventing gateway force=True replay from bypassing one check when only the other was shown to the user. New files: - tools/tirith_security.py: subprocess wrapper with auto-installer, mandatory cosign provenance verification, non-blocking background download, disk-persistent failure markers with retryable-cause tracking (cosign_missing auto-clears when cosign appears on PATH) - tests/tools/test_tirith_security.py: 62 tests covering exit code mapping, fail_open, cosign verification, background install, HERMES_HOME isolation, and failure recovery - tests/tools/test_command_guards.py: 21 integration tests for the combined guard orchestration Modified files: - tools/approval.py: add check_all_command_guards() orchestrator, add allow_permanent parameter to prompt_dangerous_approval() - tools/terminal_tool.py: replace _check_dangerous_command with consolidated check_all_command_guards - cli.py: update _approval_callback for allow_permanent kwarg, call ensure_installed() at startup - gateway/run.py: iterate pattern_keys list on replay approval, call ensure_installed() at startup - hermes_cli/config.py: add security config defaults, split commented sections for independent fallback - cli-config.yaml.example: document tirith security config
2026-03-11 14:20:32 +05:30
# Pre-exec security scanning via tirith
"security": {
"allow_private_urls": False, # Allow requests to private/internal IPs (for OpenWrt, proxies, VPNs)
feat(security): add tirith pre-exec command scanning Integrate tirith as a pre-execution security scanner that detects homograph URLs, pipe-to-interpreter patterns, terminal injection, zero-width Unicode, and environment variable manipulation — threats the existing 50-pattern dangerous command detector doesn't cover. Architecture: gather-then-decide — both tirith and the dangerous command detector run before any approval prompt, preventing gateway force=True replay from bypassing one check when only the other was shown to the user. New files: - tools/tirith_security.py: subprocess wrapper with auto-installer, mandatory cosign provenance verification, non-blocking background download, disk-persistent failure markers with retryable-cause tracking (cosign_missing auto-clears when cosign appears on PATH) - tests/tools/test_tirith_security.py: 62 tests covering exit code mapping, fail_open, cosign verification, background install, HERMES_HOME isolation, and failure recovery - tests/tools/test_command_guards.py: 21 integration tests for the combined guard orchestration Modified files: - tools/approval.py: add check_all_command_guards() orchestrator, add allow_permanent parameter to prompt_dangerous_approval() - tools/terminal_tool.py: replace _check_dangerous_command with consolidated check_all_command_guards - cli.py: update _approval_callback for allow_permanent kwarg, call ensure_installed() at startup - gateway/run.py: iterate pattern_keys list on replay approval, call ensure_installed() at startup - hermes_cli/config.py: add security config defaults, split commented sections for independent fallback - cli-config.yaml.example: document tirith security config
2026-03-11 14:20:32 +05:30
"redact_secrets": True,
"tirith_enabled": True,
"tirith_path": "tirith",
"tirith_timeout": 5,
"tirith_fail_open": True,
"website_blocklist": {
"enabled": False,
"domains": [],
"shared_files": [],
},
feat(security): add tirith pre-exec command scanning Integrate tirith as a pre-execution security scanner that detects homograph URLs, pipe-to-interpreter patterns, terminal injection, zero-width Unicode, and environment variable manipulation — threats the existing 50-pattern dangerous command detector doesn't cover. Architecture: gather-then-decide — both tirith and the dangerous command detector run before any approval prompt, preventing gateway force=True replay from bypassing one check when only the other was shown to the user. New files: - tools/tirith_security.py: subprocess wrapper with auto-installer, mandatory cosign provenance verification, non-blocking background download, disk-persistent failure markers with retryable-cause tracking (cosign_missing auto-clears when cosign appears on PATH) - tests/tools/test_tirith_security.py: 62 tests covering exit code mapping, fail_open, cosign verification, background install, HERMES_HOME isolation, and failure recovery - tests/tools/test_command_guards.py: 21 integration tests for the combined guard orchestration Modified files: - tools/approval.py: add check_all_command_guards() orchestrator, add allow_permanent parameter to prompt_dangerous_approval() - tools/terminal_tool.py: replace _check_dangerous_command with consolidated check_all_command_guards - cli.py: update _approval_callback for allow_permanent kwarg, call ensure_installed() at startup - gateway/run.py: iterate pattern_keys list on replay approval, call ensure_installed() at startup - hermes_cli/config.py: add security config defaults, split commented sections for independent fallback - cli-config.yaml.example: document tirith security config
2026-03-11 14:20:32 +05:30
},
"cron": {
# Wrap delivered cron responses with a header (task name) and footer
# ("The agent cannot see this message"). Set to false for clean output.
"wrap_response": True,
# Maximum number of due jobs to run in parallel per tick.
# null/0 = unbounded (limited only by thread count).
# 1 = serial (pre-v0.9 behaviour).
# Also overridable via HERMES_CRON_MAX_PARALLEL env var.
"max_parallel_jobs": None,
},
feat(execute_code): add project/strict execution modes, default to project (#11971) Weaker models (Gemma-class) repeatedly rediscover and forget that execute_code uses a different CWD and Python interpreter than terminal(), causing them to flip-flop on whether user files exist and to hit import errors on project dependencies like pandas. Adds a new 'code_execution.mode' config key (default 'project') that brings execute_code into line with terminal()'s filesystem/interpreter: project (new default): - cwd = session's TERMINAL_CWD (falls back to os.getcwd()) - python = active VIRTUAL_ENV/bin/python or CONDA_PREFIX/bin/python with a Python 3.8+ version check; falls back cleanly to sys.executable if no venv or the candidate fails - result : 'import pandas' works, '.env' resolves, matches terminal() strict (opt-in): - cwd = staging tmpdir (today's behavior) - python = sys.executable (today's behavior) - result : maximum reproducibility and isolation; project deps won't resolve Security-critical invariants are identical across both modes and covered by explicit regression tests: - env scrubbing (strips *_API_KEY, *_TOKEN, *_SECRET, *_PASSWORD, *_CREDENTIAL, *_PASSWD, *_AUTH substrings) - SANDBOX_ALLOWED_TOOLS whitelist (no execute_code recursion, no delegate_task, no MCP from inside scripts) - resource caps (5-min timeout, 50KB stdout, 50 tool calls) Deliberately avoids 'sandbox'/'isolated'/'cloud' language in tool descriptions (regression from commit 39b83f34 where agents on local backends falsely believed they were sandboxed and refused networking). Override via env var: HERMES_EXECUTE_CODE_MODE=strict|project
2026-04-18 01:46:25 -07:00
# execute_code settings — controls the tool used for programmatic tool calls.
"code_execution": {
# Execution mode:
# project (default) — scripts run in the session's working directory
# with the active virtualenv/conda env's python, so project deps
# (pandas, torch, project packages) and relative paths resolve.
# strict — scripts run in an isolated temp directory with
# hermes-agent's own python (sys.executable). Maximum isolation
# and reproducibility; project deps and relative paths won't work.
# Env scrubbing (strips *_API_KEY, *_TOKEN, *_SECRET, ...) and the
# tool whitelist apply identically in both modes.
"mode": "project",
},
# Logging — controls file logging to ~/.hermes/logs/.
# agent.log captures INFO+ (all agent activity); errors.log captures WARNING+.
"logging": {
"level": "INFO", # Minimum level for agent.log: DEBUG, INFO, WARNING
"max_size_mb": 5, # Max size per log file before rotation
"backup_count": 3, # Number of rotated backup files to keep
},
# Network settings — workarounds for connectivity issues.
"network": {
# Force IPv4 connections. On servers with broken or unreachable IPv6,
# Python tries AAAA records first and hangs for the full TCP timeout
# before falling back to IPv4. Set to true to skip IPv6 entirely.
"force_ipv4": False,
},
feat(state): auto-prune old sessions + VACUUM state.db at startup (#13861) * feat(state): auto-prune old sessions + VACUUM state.db at startup state.db accumulates every session, message, and FTS5 index entry forever. A heavy user (gateway + cron) reported 384MB with 982 sessions / 68K messages causing slowdown; manual 'hermes sessions prune --older-than 7' + VACUUM brought it to 43MB. The prune command and VACUUM are not wired to run automatically anywhere — sessions grew unbounded until users noticed. Changes: - hermes_state.py: new state_meta key/value table, vacuum() method, and maybe_auto_prune_and_vacuum() — idempotent via last-run timestamp in state_meta so it only actually executes once per min_interval_hours across all Hermes processes for a given HERMES_HOME. Never raises. - hermes_cli/config.py: new 'sessions:' block in DEFAULT_CONFIG (auto_prune=True, retention_days=90, vacuum_after_prune=True, min_interval_hours=24). Added to _KNOWN_ROOT_KEYS. - cli.py: call maintenance once at HermesCLI init (shared helper _run_state_db_auto_maintenance reads config and delegates to DB). - gateway/run.py: call maintenance once at GatewayRunner init. - Docs: user-guide/sessions.md rewrites 'Automatic Cleanup' section. Why VACUUM matters: SQLite does NOT shrink the file on DELETE — freed pages get reused on next INSERT. Without VACUUM, a delete-heavy DB stays bloated forever. VACUUM only runs when the prune actually removed rows, so tight DBs don't pay the I/O cost. Tests: 10 new tests in tests/test_hermes_state.py covering state_meta, vacuum, idempotency, interval skipping, VACUUM-only-when-needed, corrupt-marker recovery. All 246 existing state/config/gateway tests still pass. Verified E2E with real imports + isolated HERMES_HOME: DEFAULT_CONFIG exposes the new block, load_config() returns it for fresh installs, first call prunes+vacuums, second call within min_interval_hours skips, and the state_meta marker persists across connection close/reopen. * sessions.auto_prune defaults to false (opt-in) Session history powers session_search recall across past conversations, so silently pruning on startup could surprise users. Ship the machinery disabled and let users opt in when they notice state.db is hurting performance. - DEFAULT_CONFIG.sessions.auto_prune: True → False - Call-site fallbacks in cli.py and gateway/run.py match the new default (so unmigrated configs still see off) - Docs: flip 'Enable in config.yaml' framing + tip explains the tradeoff
2026-04-22 05:21:49 -07:00
# Session storage — controls automatic cleanup of ~/.hermes/state.db.
# state.db accumulates every session, message, tool call, and FTS5 index
# entry forever. Without auto-pruning, a heavy user (gateway + cron)
# reports 384MB+ databases with 68K+ messages, which slows down FTS5
# inserts, /resume listing, and insights queries.
"sessions": {
# When true, prune ended sessions older than retention_days once
# per (roughly) min_interval_hours at CLI/gateway/cron startup.
# Only touches ended sessions — active sessions are always preserved.
# Default false: session history is valuable for search recall, and
# silently deleting it could surprise users. Opt in explicitly.
"auto_prune": False,
# How many days of ended-session history to keep. Matches the
# default of ``hermes sessions prune``.
"retention_days": 90,
# VACUUM after a prune that actually deleted rows. SQLite does not
# reclaim disk space on DELETE — freed pages are just reused on
# subsequent INSERTs — so without VACUUM the file stays bloated
# even after pruning. VACUUM blocks writes for a few seconds per
# 100MB, so it only runs at startup, and only when prune deleted
# ≥1 session.
"vacuum_after_prune": True,
# Minimum hours between auto-maintenance runs (avoids repeating
# the sweep on every CLI invocation). Tracked via state_meta in
# state.db itself, so it's shared across all processes.
"min_interval_hours": 24,
},
# Config schema version - bump this when adding new required fields
"_config_version": 22,
}
# =============================================================================
# Config Migration System
# =============================================================================
# Track which env vars were introduced in each config version.
# Migration only mentions vars new since the user's previous version.
ENV_VARS_BY_VERSION: Dict[int, List[str]] = {
3: ["FIRECRAWL_API_KEY", "BROWSERBASE_API_KEY", "BROWSERBASE_PROJECT_ID", "FAL_KEY"],
4: ["VOICE_TOOLS_OPENAI_KEY", "ELEVENLABS_API_KEY"],
5: ["WHATSAPP_ENABLED", "WHATSAPP_MODE", "WHATSAPP_ALLOWED_USERS",
"SLACK_BOT_TOKEN", "SLACK_APP_TOKEN", "SLACK_ALLOWED_USERS"],
10: ["TAVILY_API_KEY"],
11: ["TERMINAL_MODAL_MODE"],
}
# Required environment variables with metadata for migration prompts.
# LLM provider is required but handled in the setup wizard's provider
# selection step (Nous Portal / OpenRouter / Custom endpoint), so this
# dict is intentionally empty — no single env var is universally required.
REQUIRED_ENV_VARS = {}
# Optional environment variables that enhance functionality
OPTIONAL_ENV_VARS = {
# ── Provider (handled in provider selection, not shown in checklists) ──
"NOUS_BASE_URL": {
"description": "Nous Portal base URL override",
"prompt": "Nous Portal base URL (leave empty for default)",
"url": None,
"password": False,
"category": "provider",
"advanced": True,
},
"OPENROUTER_API_KEY": {
"description": "OpenRouter API key (for vision, web scraping helpers, and MoA)",
"prompt": "OpenRouter API key",
"url": "https://openrouter.ai/keys",
"password": True,
"tools": ["vision_analyze", "mixture_of_agents"],
"category": "provider",
"advanced": True,
},
"GOOGLE_API_KEY": {
"description": "Google AI Studio API key (also recognized as GEMINI_API_KEY)",
"prompt": "Google AI Studio API key",
"url": "https://aistudio.google.com/app/apikey",
"password": True,
"category": "provider",
"advanced": True,
},
"GEMINI_API_KEY": {
"description": "Google AI Studio API key (alias for GOOGLE_API_KEY)",
"prompt": "Gemini API key",
"url": "https://aistudio.google.com/app/apikey",
"password": True,
"category": "provider",
"advanced": True,
},
"GEMINI_BASE_URL": {
"description": "Google AI Studio base URL override",
"prompt": "Gemini base URL (leave empty for default)",
"url": None,
"password": False,
"category": "provider",
"advanced": True,
},
"XAI_API_KEY": {
"description": "xAI API key",
"prompt": "xAI API key",
"url": "https://console.x.ai/",
"password": True,
"category": "provider",
"advanced": True,
},
"XAI_BASE_URL": {
"description": "xAI base URL override",
"prompt": "xAI base URL (leave empty for default)",
"url": None,
"password": False,
"category": "provider",
"advanced": True,
},
fix(providers): complete NVIDIA NIM parity with other providers Follow-up on the native NVIDIA NIM provider salvage. The original PR wired PROVIDER_REGISTRY + HERMES_OVERLAYS correctly but missed several touchpoints required for full parity with other OpenAI-compatible providers (xai, huggingface, deepseek, zai). Gaps closed: - hermes_cli/main.py: - Add 'nvidia' to the _model_flow_api_key_provider dispatch tuple so selecting 'NVIDIA NIM' in `hermes model` actually runs the api-key provider flow (previously fell through silently). - Add 'nvidia' to `hermes chat --provider` argparse choices so the documented test command (`hermes chat --provider nvidia --model ...`) parses successfully. - hermes_cli/config.py: Register NVIDIA_API_KEY and NVIDIA_BASE_URL in OPTIONAL_ENV_VARS so setup wizard can prompt for them and they're auto-added to the subprocess env blocklist. - hermes_cli/doctor.py: Add NVIDIA NIM row to `_apikey_providers` so `hermes doctor` probes https://integrate.api.nvidia.com/v1/models. - hermes_cli/dump.py: Add NVIDIA_API_KEY → 'nvidia' mapping for `hermes dump` credential masking. - tests/tools/test_local_env_blocklist.py: Extend registry_vars fixture with NVIDIA_API_KEY to verify it's blocked from leaking into subprocesses. - agent/model_metadata.py: Add 'nemotron' → 131072 context-length entry so all Nemotron variants get 128K context via substring match (rather than falling back to MINIMUM_CONTEXT_LENGTH). - hermes_cli/models.py: Fix hallucinated model ID 'nvidia/nemotron-3-nano-8b-a4b' → 'nvidia/nemotron-3-nano-30b-a3b' (verified against live integrate.api.nvidia.com/v1/models catalog). Expand curated list from 5 to 9 agentic models mapping to OpenRouter defaults per provider-guide convention: add qwen3.5-397b-a17b, deepseek-v3.2, llama-3.3-nemotron-super-49b-v1.5, gpt-oss-120b. - cli-config.yaml.example: Document 'nvidia' provider option. - scripts/release.py: Map asurla@nvidia.com → anniesurla in AUTHOR_MAP for CI attribution. E2E verified: `hermes chat --provider nvidia ...` now reaches NVIDIA's endpoint (returns 401 with bogus key instead of argparse error); `hermes doctor` detects NVIDIA NIM when NVIDIA_API_KEY is set.
2026-04-17 13:09:14 -07:00
"NVIDIA_API_KEY": {
"description": "NVIDIA NIM API key (build.nvidia.com or local NIM endpoint)",
"prompt": "NVIDIA NIM API key",
"url": "https://build.nvidia.com/",
"password": True,
"category": "provider",
"advanced": True,
},
"NVIDIA_BASE_URL": {
"description": "NVIDIA NIM base URL override (e.g. http://localhost:8000/v1 for local NIM)",
"prompt": "NVIDIA NIM base URL (leave empty for default)",
"url": None,
"password": False,
"category": "provider",
"advanced": True,
},
feat: add z.ai/GLM, Kimi/Moonshot, MiniMax as first-class providers Adds 4 new direct API-key providers (zai, kimi-coding, minimax, minimax-cn) to the inference provider system. All use standard OpenAI-compatible chat/completions endpoints with Bearer token auth. Core changes: - auth.py: Extended ProviderConfig with api_key_env_vars and base_url_env_var fields. Added providers to PROVIDER_REGISTRY. Added provider aliases (glm, z-ai, zhipu, kimi, moonshot). Added auto-detection of API-key providers in resolve_provider(). Added resolve_api_key_provider_credentials() and get_api_key_provider_status() helpers. - runtime_provider.py: Added generic API-key provider branch in resolve_runtime_provider() — any provider with auth_type='api_key' is automatically handled. - main.py: Added providers to hermes model menu with generic _model_flow_api_key_provider() flow. Updated _has_any_provider_configured() to check all provider env vars. Updated argparse --provider choices. - setup.py: Added providers to setup wizard with API key prompts and curated model lists. - config.py: Added env vars (GLM_API_KEY, KIMI_API_KEY, MINIMAX_API_KEY, etc.) to OPTIONAL_ENV_VARS. - status.py: Added API key display and provider status section. - doctor.py: Added connectivity checks for each provider endpoint. - cli.py: Updated provider docstrings. Docs: Updated README.md, .env.example, cli-config.yaml.example, cli-commands.md, environment-variables.md, configuration.md. Tests: 50 new tests covering registry, aliases, resolution, auto-detection, credential resolution, and runtime provider dispatch. Inspired by PR #33 (numman-ali) which proposed a provider registry approach. Credit to tars90percent (PR #473) and manuelschipper (PR #420) for related provider improvements merged earlier in this changeset.
2026-03-06 18:55:12 -08:00
"GLM_API_KEY": {
"description": "Z.AI / GLM API key (also recognized as ZAI_API_KEY / Z_AI_API_KEY)",
"prompt": "Z.AI / GLM API key",
"url": "https://z.ai/",
"password": True,
"category": "provider",
"advanced": True,
},
"ZAI_API_KEY": {
"description": "Z.AI API key (alias for GLM_API_KEY)",
"prompt": "Z.AI API key",
"url": "https://z.ai/",
"password": True,
"category": "provider",
"advanced": True,
},
"Z_AI_API_KEY": {
"description": "Z.AI API key (alias for GLM_API_KEY)",
"prompt": "Z.AI API key",
"url": "https://z.ai/",
"password": True,
"category": "provider",
"advanced": True,
},
"GLM_BASE_URL": {
"description": "Z.AI / GLM base URL override",
"prompt": "Z.AI / GLM base URL (leave empty for default)",
"url": None,
"password": False,
"category": "provider",
"advanced": True,
},
"KIMI_API_KEY": {
"description": "Kimi / Moonshot API key",
"prompt": "Kimi API key",
"url": "https://platform.moonshot.cn/",
"password": True,
"category": "provider",
"advanced": True,
},
"KIMI_BASE_URL": {
"description": "Kimi / Moonshot base URL override",
"prompt": "Kimi base URL (leave empty for default)",
"url": None,
"password": False,
"category": "provider",
"advanced": True,
},
"KIMI_CN_API_KEY": {
"description": "Kimi / Moonshot China API key",
"prompt": "Kimi (China) API key",
"url": "https://platform.moonshot.cn/",
"password": True,
"category": "provider",
"advanced": True,
},
"STEPFUN_API_KEY": {
"description": "StepFun Step Plan API key",
"prompt": "StepFun Step Plan API key",
"url": "https://platform.stepfun.com/",
"password": True,
"category": "provider",
"advanced": True,
},
"STEPFUN_BASE_URL": {
"description": "StepFun Step Plan base URL override",
"prompt": "StepFun Step Plan base URL (leave empty for default)",
"url": None,
"password": False,
"category": "provider",
"advanced": True,
},
"ARCEEAI_API_KEY": {
"description": "Arcee AI API key",
"prompt": "Arcee AI API key",
"url": "https://chat.arcee.ai/",
"password": True,
"category": "provider",
"advanced": True,
},
"ARCEE_BASE_URL": {
"description": "Arcee AI base URL override",
"prompt": "Arcee base URL (leave empty for default)",
"url": None,
"password": False,
"category": "provider",
"advanced": True,
},
feat: add z.ai/GLM, Kimi/Moonshot, MiniMax as first-class providers Adds 4 new direct API-key providers (zai, kimi-coding, minimax, minimax-cn) to the inference provider system. All use standard OpenAI-compatible chat/completions endpoints with Bearer token auth. Core changes: - auth.py: Extended ProviderConfig with api_key_env_vars and base_url_env_var fields. Added providers to PROVIDER_REGISTRY. Added provider aliases (glm, z-ai, zhipu, kimi, moonshot). Added auto-detection of API-key providers in resolve_provider(). Added resolve_api_key_provider_credentials() and get_api_key_provider_status() helpers. - runtime_provider.py: Added generic API-key provider branch in resolve_runtime_provider() — any provider with auth_type='api_key' is automatically handled. - main.py: Added providers to hermes model menu with generic _model_flow_api_key_provider() flow. Updated _has_any_provider_configured() to check all provider env vars. Updated argparse --provider choices. - setup.py: Added providers to setup wizard with API key prompts and curated model lists. - config.py: Added env vars (GLM_API_KEY, KIMI_API_KEY, MINIMAX_API_KEY, etc.) to OPTIONAL_ENV_VARS. - status.py: Added API key display and provider status section. - doctor.py: Added connectivity checks for each provider endpoint. - cli.py: Updated provider docstrings. Docs: Updated README.md, .env.example, cli-config.yaml.example, cli-commands.md, environment-variables.md, configuration.md. Tests: 50 new tests covering registry, aliases, resolution, auto-detection, credential resolution, and runtime provider dispatch. Inspired by PR #33 (numman-ali) which proposed a provider registry approach. Credit to tars90percent (PR #473) and manuelschipper (PR #420) for related provider improvements merged earlier in this changeset.
2026-03-06 18:55:12 -08:00
"MINIMAX_API_KEY": {
"description": "MiniMax API key (international)",
"prompt": "MiniMax API key",
"url": "https://www.minimax.io/",
"password": True,
"category": "provider",
"advanced": True,
},
"MINIMAX_BASE_URL": {
"description": "MiniMax base URL override",
"prompt": "MiniMax base URL (leave empty for default)",
"url": None,
"password": False,
"category": "provider",
"advanced": True,
},
"MINIMAX_CN_API_KEY": {
"description": "MiniMax API key (China endpoint)",
"prompt": "MiniMax (China) API key",
"url": "https://www.minimaxi.com/",
"password": True,
"category": "provider",
"advanced": True,
},
"MINIMAX_CN_BASE_URL": {
"description": "MiniMax (China) base URL override",
"prompt": "MiniMax (China) base URL (leave empty for default)",
"url": None,
"password": False,
"category": "provider",
"advanced": True,
},
"DEEPSEEK_API_KEY": {
"description": "DeepSeek API key for direct DeepSeek access",
"prompt": "DeepSeek API Key",
"url": "https://platform.deepseek.com/api_keys",
"password": True,
"category": "provider",
},
"DEEPSEEK_BASE_URL": {
"description": "Custom DeepSeek API base URL (advanced)",
"prompt": "DeepSeek Base URL",
"url": "",
"password": False,
"category": "provider",
},
"DASHSCOPE_API_KEY": {
"description": "Alibaba Cloud DashScope API key (Qwen + multi-provider models)",
"prompt": "DashScope API Key",
"url": "https://modelstudio.console.alibabacloud.com/",
"password": True,
"category": "provider",
},
"DASHSCOPE_BASE_URL": {
"description": "Custom DashScope base URL (default: coding-intl OpenAI-compat endpoint)",
"prompt": "DashScope Base URL",
"url": "",
"password": False,
"category": "provider",
"advanced": True,
},
"HERMES_QWEN_BASE_URL": {
"description": "Qwen Portal base URL override (default: https://portal.qwen.ai/v1)",
"prompt": "Qwen Portal base URL (leave empty for default)",
"url": None,
"password": False,
"category": "provider",
"advanced": True,
},
feat(gemini): add Google Gemini CLI OAuth provider via Cloud Code Assist (free + paid tiers) (#11270) * feat(gemini): add Google Gemini CLI OAuth provider via Cloud Code Assist Adds 'google-gemini-cli' as a first-class inference provider with native OAuth authentication against Google, hitting the Cloud Code Assist backend (cloudcode-pa.googleapis.com) that powers Google's official gemini-cli. Supports both the free tier (generous daily quota, personal accounts) and paid tiers (Standard/Enterprise via GCP projects). Architecture ============ Three new modules under agent/: 1. google_oauth.py (625 lines) — PKCE Authorization Code flow - Google's public gemini-cli desktop OAuth client baked in (env-var overrides supported) - Cross-process file lock (fcntl POSIX / msvcrt Windows) with thread-local re-entrancy - Packed refresh format 'refresh_token|project_id|managed_project_id' on disk - In-flight refresh deduplication — concurrent requests don't double-refresh - invalid_grant → wipe credentials, prompt re-login - Headless detection (SSH/HERMES_HEADLESS) → paste-mode fallback - Refresh 60 s before expiry, atomic write with fsync+replace 2. google_code_assist.py (350 lines) — Code Assist control plane - load_code_assist(): POST /v1internal:loadCodeAssist (prod → sandbox fallback) - onboard_user(): POST /v1internal:onboardUser with LRO polling up to 60 s - retrieve_user_quota(): POST /v1internal:retrieveUserQuota → QuotaBucket list - VPC-SC detection (SECURITY_POLICY_VIOLATED → force standard-tier) - resolve_project_context(): env → config → discovered → onboarded priority - Matches Google's gemini-cli User-Agent / X-Goog-Api-Client / Client-Metadata 3. gemini_cloudcode_adapter.py (640 lines) — OpenAI↔Gemini translation - GeminiCloudCodeClient mimics openai.OpenAI interface (.chat.completions.create) - Full message translation: system→systemInstruction, tool_calls↔functionCall, tool results→functionResponse with sentinel thoughtSignature - Tools → tools[].functionDeclarations, tool_choice → toolConfig modes - GenerationConfig pass-through (temperature, max_tokens, top_p, stop) - Thinking config normalization (thinkingBudget, thinkingLevel, includeThoughts) - Request envelope {project, model, user_prompt_id, request} - Streaming: SSE (?alt=sse) with thought-part → reasoning stream separation - Response unwrapping (Code Assist wraps Gemini response in 'response' field) - finishReason mapping to OpenAI convention (STOP→stop, MAX_TOKENS→length, etc.) Provider registration — all 9 touchpoints ========================================== - hermes_cli/auth.py: PROVIDER_REGISTRY, aliases, resolver, status fn, dispatch - hermes_cli/models.py: _PROVIDER_MODELS, CANONICAL_PROVIDERS, aliases - hermes_cli/providers.py: HermesOverlay, ALIASES - hermes_cli/config.py: OPTIONAL_ENV_VARS (HERMES_GEMINI_CLIENT_ID/_SECRET/_PROJECT_ID) - hermes_cli/runtime_provider.py: dispatch branch + pool-entry branch - hermes_cli/main.py: _model_flow_google_gemini_cli with upfront policy warning - hermes_cli/auth_commands.py: pool handler, _OAUTH_CAPABLE_PROVIDERS - hermes_cli/doctor.py: 'Google Gemini OAuth' health check - run_agent.py: single dispatch branch in _create_openai_client /gquota slash command ====================== Shows Code Assist quota buckets with 20-char progress bars, per (model, tokenType). Registered in hermes_cli/commands.py, handler _handle_gquota_command in cli.py. Attribution =========== Derived with significant reference to: - jenslys/opencode-gemini-auth (MIT) — OAuth flow shape, request envelope, public client credentials, retry semantics. Attribution preserved in module docstrings. - clawdbot/extensions/google — VPC-SC handling, project discovery pattern. - PR #10176 (@sliverp) — PKCE module structure. - PR #10779 (@newarthur) — cross-process file locking pattern. Supersedes PRs #6745, #10176, #10779 (to be closed on merge with credit). Upfront policy warning ====================== Google considers using the gemini-cli OAuth client with third-party software a policy violation. The interactive flow shows a clear warning and requires explicit 'y' confirmation before OAuth begins. Documented prominently in website/docs/integrations/providers.md. Tests ===== 74 new tests in tests/agent/test_gemini_cloudcode.py covering: - PKCE S256 roundtrip - Packed refresh format parse/format/roundtrip - Credential I/O (0600 perms, atomic write, packed on disk) - Token lifecycle (fresh/expiring/force-refresh/invalid_grant/rotation preservation) - Project ID env resolution (3 env vars, priority order) - Headless detection - VPC-SC detection (JSON-nested + text match) - loadCodeAssist parsing + VPC-SC → standard-tier fallback - onboardUser: free-tier allows empty project, paid requires it, LRO polling - retrieveUserQuota parsing - resolve_project_context: 3 short-circuit paths + discovery + onboarding - build_gemini_request: messages → contents, system separation, tool_calls, tool_results, tools[], tool_choice (auto/required/specific), generationConfig, thinkingConfig normalization - Code Assist envelope wrap shape - Response translation: text, functionCall, thought → reasoning, unwrapped response, empty candidates, finish_reason mapping - GeminiCloudCodeClient end-to-end with mocked HTTP - Provider registration (9 tests: registry, 4 alias forms, no-regression on google-gemini alias, models catalog, determine_api_mode, _OAUTH_CAPABLE_PROVIDERS preservation, config env vars) - Auth status dispatch (logged-in + not) - /gquota command registration - run_gemini_oauth_login_pure pool-dict shape All 74 pass. 349 total tests pass across directly-touched areas (existing test_api_key_providers, test_auth_qwen_provider, test_gemini_provider, test_cli_init, test_cli_provider_resolution, test_registry all still green). Coexistence with existing 'gemini' (API-key) provider ===================================================== The existing gemini API-key provider is completely untouched. Its alias 'google-gemini' still resolves to 'gemini', not 'google-gemini-cli'. Users can have both configured simultaneously; 'hermes model' shows both as separate options. * feat(gemini): ship Google's public gemini-cli OAuth client as default Pivots from 'scrape-from-local-gemini-cli' (clawdbot pattern) to 'ship-creds-in-source' (opencode-gemini-auth pattern) for zero-setup UX. These are Google's PUBLIC gemini-cli desktop OAuth credentials, published openly in Google's own open-source gemini-cli repository. Desktop OAuth clients are not confidential — PKCE provides the security, not the client_secret. Shipping them here matches opencode-gemini-auth (MIT) and Google's own distribution model. Resolution order is now: 1. HERMES_GEMINI_CLIENT_ID / _SECRET env vars (power users, custom GCP clients) 2. Shipped public defaults (common case — works out of the box) 3. Scrape from locally installed gemini-cli (fallback for forks that deliberately wipe the shipped defaults) 4. Helpful error with install / env-var hints The credential strings are composed piecewise at import time to keep reviewer intent explicit (each constant is paired with a comment about why it's non-confidential) and to bypass naive secret scanners. UX impact: users no longer need 'npm install -g @google/gemini-cli' as a prerequisite. Just 'hermes model' -> 'Google Gemini (OAuth)' works out of the box. Scrape path is retained as a safety net. Tests cover all four resolution steps (env / shipped default / scrape fallback / hard failure). 79 new unit tests pass (was 76, +3 for the new resolution behaviors).
2026-04-16 16:49:00 -07:00
"HERMES_GEMINI_CLIENT_ID": {
"description": "Google OAuth client ID for google-gemini-cli (optional; defaults to Google's public gemini-cli client)",
"prompt": "Google OAuth client ID (optional — leave empty to use the public default)",
"url": "https://console.cloud.google.com/apis/credentials",
"password": False,
"category": "provider",
"advanced": True,
},
"HERMES_GEMINI_CLIENT_SECRET": {
"description": "Google OAuth client secret for google-gemini-cli (optional)",
"prompt": "Google OAuth client secret (optional)",
"url": "https://console.cloud.google.com/apis/credentials",
"password": True,
"category": "provider",
"advanced": True,
},
"HERMES_GEMINI_PROJECT_ID": {
"description": "GCP project ID for paid Gemini tiers (free tier auto-provisions)",
"prompt": "GCP project ID for Gemini OAuth (leave empty for free tier)",
"url": None,
"password": False,
"category": "provider",
"advanced": True,
},
"OPENCODE_ZEN_API_KEY": {
"description": "OpenCode Zen API key (pay-as-you-go access to curated models)",
"prompt": "OpenCode Zen API key",
"url": "https://opencode.ai/auth",
"password": True,
"category": "provider",
"advanced": True,
},
"OPENCODE_ZEN_BASE_URL": {
"description": "OpenCode Zen base URL override",
"prompt": "OpenCode Zen base URL (leave empty for default)",
"url": None,
"password": False,
"category": "provider",
"advanced": True,
},
"OPENCODE_GO_API_KEY": {
"description": "OpenCode Go API key ($10/month subscription for open models)",
"prompt": "OpenCode Go API key",
"url": "https://opencode.ai/auth",
"password": True,
"category": "provider",
"advanced": True,
},
"OPENCODE_GO_BASE_URL": {
"description": "OpenCode Go base URL override",
"prompt": "OpenCode Go base URL (leave empty for default)",
"url": None,
"password": False,
"category": "provider",
"advanced": True,
},
"HF_TOKEN": {
"description": "Hugging Face token for Inference Providers (20+ open models via router.huggingface.co)",
"prompt": "Hugging Face Token",
"url": "https://huggingface.co/settings/tokens",
"password": True,
"category": "provider",
},
"HF_BASE_URL": {
"description": "Hugging Face Inference Providers base URL override",
"prompt": "HF base URL (leave empty for default)",
"url": None,
"password": False,
"category": "provider",
"advanced": True,
},
"OLLAMA_API_KEY": {
"description": "Ollama Cloud API key (ollama.com — cloud-hosted open models)",
"prompt": "Ollama Cloud API key",
"url": "https://ollama.com/settings",
"password": True,
"category": "provider",
"advanced": True,
},
"OLLAMA_BASE_URL": {
"description": "Ollama Cloud base URL override (default: https://ollama.com/v1)",
"prompt": "Ollama base URL (leave empty for default)",
"url": None,
"password": False,
"category": "provider",
"advanced": True,
},
"XIAOMI_API_KEY": {
"description": "Xiaomi MiMo API key for MiMo models (mimo-v2.5-pro, mimo-v2.5, mimo-v2-pro, mimo-v2-omni, mimo-v2-flash)",
"prompt": "Xiaomi MiMo API Key",
"url": "https://platform.xiaomimimo.com",
"password": True,
"category": "provider",
},
"XIAOMI_BASE_URL": {
"description": "Xiaomi MiMo base URL override (default: https://api.xiaomimimo.com/v1)",
"prompt": "Xiaomi base URL (leave empty for default)",
"url": None,
"password": False,
"category": "provider",
"advanced": True,
},
"AWS_REGION": {
"description": "AWS region for Bedrock API calls (e.g. us-east-1, eu-central-1)",
"prompt": "AWS Region",
"url": "https://docs.aws.amazon.com/bedrock/latest/userguide/bedrock-regions.html",
"password": False,
"category": "provider",
"advanced": True,
},
"AWS_PROFILE": {
"description": "AWS named profile for Bedrock authentication (from ~/.aws/credentials)",
"prompt": "AWS Profile",
"url": None,
"password": False,
"category": "provider",
"advanced": True,
},
"AZURE_FOUNDRY_API_KEY": {
"description": "Azure Foundry API key for custom Azure endpoints",
"prompt": "Azure Foundry API Key",
"url": "https://ai.azure.com/",
"password": True,
"category": "provider",
},
"AZURE_FOUNDRY_BASE_URL": {
"description": "Azure Foundry base URL (set via 'hermes model' for endpoint-specific config)",
"prompt": "Azure Foundry base URL",
"url": None,
"password": False,
"category": "provider",
"advanced": True,
},
# ── Tool API keys ──
"EXA_API_KEY": {
"description": "Exa API key for AI-native web search and contents",
"prompt": "Exa API key",
"url": "https://exa.ai/",
"tools": ["web_search", "web_extract"],
"password": True,
"category": "tool",
},
feat(web): add Parallel as alternative web search/extract backend (#1696) * feat(web): add Parallel as alternative web search/extract backend Adds Parallel (parallel.ai) as a drop-in alternative to Firecrawl for web_search and web_extract tools using the official parallel-web SDK. - Backend selection via WEB_SEARCH_BACKEND env var (auto/parallel/firecrawl) - Auto mode prefers Firecrawl when both keys present; Parallel when sole backend - web_crawl remains Firecrawl-only with clear error when unavailable - Lazy SDK imports, interrupt support, singleton clients - 16 new unit tests for backend selection and client config Co-authored-by: s-jag <s-jag@users.noreply.github.com> * fix: add PARALLEL_API_KEY to config registry and fix web_crawl policy tests Follow-up for Parallel backend integration: - Add PARALLEL_API_KEY to OPTIONAL_ENV_VARS (hermes doctor, env blocklist) - Add to set_config_value api_keys list (hermes config set) - Add to doctor keys display - Fix 2 web_crawl policy tests that didn't set FIRECRAWL_API_KEY (needed now that web_crawl has a Firecrawl availability guard) * refactor: explicit backend selection via hermes tools, not auto-detect Replace the auto-detect backend selection with explicit user choice: - hermes tools saves WEB_SEARCH_BACKEND to .env when user picks a provider - _get_backend() reads the explicit choice first - Fallback only for manual/legacy config (uses whichever key is present) - _is_provider_active() shows [active] for the selected web backend - Updated tests, docs, and .env.example to remove 'auto' mode language * refactor: use config.yaml for web backend, not env var Match the TTS/browser pattern — web.backend is stored in config.yaml (set by hermes tools), not as a WEB_SEARCH_BACKEND env var. - _load_web_config() reads web: section from config.yaml - _get_backend() reads web.backend from config, falls back to key detection - _configure_provider() saves to config dict (saved to config.yaml) - _is_provider_active() reads from config dict - Removed WEB_SEARCH_BACKEND from .env.example, set_config_value, docs - Updated all tests to mock _load_web_config instead of env vars --------- Co-authored-by: s-jag <s-jag@users.noreply.github.com>
2026-03-17 04:02:02 -07:00
"PARALLEL_API_KEY": {
"description": "Parallel API key for AI-native web search and extract",
"prompt": "Parallel API key",
"url": "https://parallel.ai/",
"tools": ["web_search", "web_extract"],
"password": True,
"category": "tool",
},
"FIRECRAWL_API_KEY": {
"description": "Firecrawl API key for web search and scraping",
"prompt": "Firecrawl API key",
"url": "https://firecrawl.dev/",
"tools": ["web_search", "web_extract"],
"password": True,
"category": "tool",
},
"FIRECRAWL_API_URL": {
"description": "Firecrawl API URL for self-hosted instances (optional)",
"prompt": "Firecrawl API URL (leave empty for cloud)",
"url": None,
"password": False,
"category": "tool",
"advanced": True,
},
"FIRECRAWL_GATEWAY_URL": {
"description": "Exact Firecrawl tool-gateway origin override for Nous Subscribers only (optional)",
"prompt": "Firecrawl gateway URL (leave empty to derive from domain)",
"url": None,
"password": False,
"category": "tool",
"advanced": True,
},
"TOOL_GATEWAY_DOMAIN": {
"description": "Shared tool-gateway domain suffix for Nous Subscribers only, used to derive vendor hosts, e.g. nousresearch.com -> firecrawl-gateway.nousresearch.com",
"prompt": "Tool-gateway domain suffix",
"url": None,
"password": False,
"category": "tool",
"advanced": True,
},
"TOOL_GATEWAY_SCHEME": {
"description": "Shared tool-gateway URL scheme for Nous Subscribers only, used to derive vendor hosts (`https` by default, set `http` for local gateway testing)",
"prompt": "Tool-gateway URL scheme",
"url": None,
"password": False,
"category": "tool",
"advanced": True,
},
"TOOL_GATEWAY_USER_TOKEN": {
"description": "Explicit Nous Subscriber access token for tool-gateway requests (optional; otherwise read from the Hermes auth store)",
"prompt": "Tool-gateway user token",
"url": None,
"password": True,
"category": "tool",
"advanced": True,
},
"TAVILY_API_KEY": {
"description": "Tavily API key for AI-native web search, extract, and crawl",
"prompt": "Tavily API key",
"url": "https://app.tavily.com/home",
"tools": ["web_search", "web_extract", "web_crawl"],
"password": True,
"category": "tool",
},
"BROWSERBASE_API_KEY": {
"description": "Browserbase API key for cloud browser (optional — local browser works without this)",
"prompt": "Browserbase API key",
"url": "https://browserbase.com/",
"tools": ["browser_navigate", "browser_click"],
"password": True,
"category": "tool",
},
"BROWSERBASE_PROJECT_ID": {
"description": "Browserbase project ID (optional — only needed for cloud browser)",
"prompt": "Browserbase project ID",
"url": "https://browserbase.com/",
"tools": ["browser_navigate", "browser_click"],
"password": False,
"category": "tool",
},
"BROWSER_USE_API_KEY": {
"description": "Browser Use API key for cloud browser (optional — local browser works without this)",
"prompt": "Browser Use API key",
"url": "https://browser-use.com/",
"tools": ["browser_navigate", "browser_click"],
"password": True,
"category": "tool",
},
"FIRECRAWL_BROWSER_TTL": {
"description": "Firecrawl browser session TTL in seconds (optional, default 300)",
"prompt": "Browser session TTL (seconds)",
"tools": ["browser_navigate", "browser_click"],
"password": False,
"category": "tool",
},
"CAMOFOX_URL": {
"description": "Camofox browser server URL for local anti-detection browsing (e.g. http://localhost:9377)",
"prompt": "Camofox server URL",
"url": "https://github.com/jo-inc/camofox-browser",
"tools": ["browser_navigate", "browser_click"],
"password": False,
"category": "tool",
},
"FAL_KEY": {
"description": "FAL API key for image generation",
"prompt": "FAL API key",
"url": "https://fal.ai/",
"tools": ["image_generate"],
"password": True,
"category": "tool",
},
"TINKER_API_KEY": {
"description": "Tinker API key for RL training",
"prompt": "Tinker API key",
"url": "https://tinker-console.thinkingmachines.ai/keys",
"tools": ["rl_start_training", "rl_check_status", "rl_stop_training"],
"password": True,
"category": "tool",
},
"WANDB_API_KEY": {
"description": "Weights & Biases API key for experiment tracking",
"prompt": "WandB API key",
"url": "https://wandb.ai/authorize",
"tools": ["rl_get_results", "rl_check_status"],
"password": True,
"category": "tool",
},
"VOICE_TOOLS_OPENAI_KEY": {
"description": "OpenAI API key for voice transcription (Whisper) and OpenAI TTS",
"prompt": "OpenAI API Key (for Whisper STT + TTS)",
"url": "https://platform.openai.com/api-keys",
"tools": ["voice_transcription", "openai_tts"],
"password": True,
"category": "tool",
},
"ELEVENLABS_API_KEY": {
"description": "ElevenLabs API key for premium text-to-speech voices",
"prompt": "ElevenLabs API key",
"url": "https://elevenlabs.io/",
Add messaging platform enhancements: STT, stickers, Discord UX, Slack, pairing, hooks Major feature additions inspired by OpenClaw/ClawdBot integration analysis: Voice Message Transcription (STT): - Auto-transcribe voice/audio messages via OpenAI Whisper API - Download voice to ~/.hermes/audio_cache/ on Telegram/Discord/WhatsApp - Inject transcript as text so all models can understand voice input - Configurable model (whisper-1, gpt-4o-mini-transcribe, gpt-4o-transcribe) Telegram Sticker Understanding: - Describe static stickers via vision tool with JSON-backed cache - Cache keyed by file_unique_id avoids redundant API calls - Animated/video stickers get emoji-based fallback description Discord Rich UX: - Native slash commands (/ask, /reset, /status, /stop) via app_commands - Button-based exec approvals (Allow Once / Always Allow / Deny) - ExecApprovalView with user authorization and timeout handling Slack Integration: - Full SlackAdapter using slack-bolt with Socket Mode - DMs, channel messages (mention-gated), /hermes slash command - File attachment handling with bot-token-authenticated downloads DM Pairing System: - Code-based user authorization as alternative to static allowlists - 8-char codes from unambiguous alphabet, 1-hour expiry - Rate limiting, lockout after failed attempts, chmod 0600 on data - CLI: hermes pairing list/approve/revoke/clear-pending Event Hook System: - File-based hook discovery from ~/.hermes/hooks/ - HOOK.yaml + handler.py per hook, sync/async handler support - Events: gateway:startup, session:start/reset, agent:start/step/end - Wildcard matching (command:* catches all command events) Cross-Channel Messaging: - send_message agent tool for delivering to any connected platform - Enables cron job delivery and cross-platform notifications Human-Like Response Pacing: - Configurable delays between message chunks (off/natural/custom) - HERMES_HUMAN_DELAY_MODE env var with min/max ms settings Warm Injection Message Style: - Retrofitted image vision messages with friendly kawaii-consistent tone - All new injection messages (STT, stickers, errors) use warm style Also: updated config migration to prompt for optional keys interactively, bumped config version, updated README, AGENTS.md, .env.example, cli-config.yaml.example, install scripts, pyproject.toml, and toolsets.
2026-02-15 21:38:59 -08:00
"password": True,
"category": "tool",
Add messaging platform enhancements: STT, stickers, Discord UX, Slack, pairing, hooks Major feature additions inspired by OpenClaw/ClawdBot integration analysis: Voice Message Transcription (STT): - Auto-transcribe voice/audio messages via OpenAI Whisper API - Download voice to ~/.hermes/audio_cache/ on Telegram/Discord/WhatsApp - Inject transcript as text so all models can understand voice input - Configurable model (whisper-1, gpt-4o-mini-transcribe, gpt-4o-transcribe) Telegram Sticker Understanding: - Describe static stickers via vision tool with JSON-backed cache - Cache keyed by file_unique_id avoids redundant API calls - Animated/video stickers get emoji-based fallback description Discord Rich UX: - Native slash commands (/ask, /reset, /status, /stop) via app_commands - Button-based exec approvals (Allow Once / Always Allow / Deny) - ExecApprovalView with user authorization and timeout handling Slack Integration: - Full SlackAdapter using slack-bolt with Socket Mode - DMs, channel messages (mention-gated), /hermes slash command - File attachment handling with bot-token-authenticated downloads DM Pairing System: - Code-based user authorization as alternative to static allowlists - 8-char codes from unambiguous alphabet, 1-hour expiry - Rate limiting, lockout after failed attempts, chmod 0600 on data - CLI: hermes pairing list/approve/revoke/clear-pending Event Hook System: - File-based hook discovery from ~/.hermes/hooks/ - HOOK.yaml + handler.py per hook, sync/async handler support - Events: gateway:startup, session:start/reset, agent:start/step/end - Wildcard matching (command:* catches all command events) Cross-Channel Messaging: - send_message agent tool for delivering to any connected platform - Enables cron job delivery and cross-platform notifications Human-Like Response Pacing: - Configurable delays between message chunks (off/natural/custom) - HERMES_HUMAN_DELAY_MODE env var with min/max ms settings Warm Injection Message Style: - Retrofitted image vision messages with friendly kawaii-consistent tone - All new injection messages (STT, stickers, errors) use warm style Also: updated config migration to prompt for optional keys interactively, bumped config version, updated README, AGENTS.md, .env.example, cli-config.yaml.example, install scripts, pyproject.toml, and toolsets.
2026-02-15 21:38:59 -08:00
},
"MISTRAL_API_KEY": {
"description": "Mistral API key for Voxtral TTS and transcription (STT)",
"prompt": "Mistral API key",
"url": "https://console.mistral.ai/",
"password": True,
"category": "tool",
},
"GITHUB_TOKEN": {
"description": "GitHub token for Skills Hub (higher API rate limits, skill publish)",
"prompt": "GitHub Token",
"url": "https://github.com/settings/tokens",
Add messaging platform enhancements: STT, stickers, Discord UX, Slack, pairing, hooks Major feature additions inspired by OpenClaw/ClawdBot integration analysis: Voice Message Transcription (STT): - Auto-transcribe voice/audio messages via OpenAI Whisper API - Download voice to ~/.hermes/audio_cache/ on Telegram/Discord/WhatsApp - Inject transcript as text so all models can understand voice input - Configurable model (whisper-1, gpt-4o-mini-transcribe, gpt-4o-transcribe) Telegram Sticker Understanding: - Describe static stickers via vision tool with JSON-backed cache - Cache keyed by file_unique_id avoids redundant API calls - Animated/video stickers get emoji-based fallback description Discord Rich UX: - Native slash commands (/ask, /reset, /status, /stop) via app_commands - Button-based exec approvals (Allow Once / Always Allow / Deny) - ExecApprovalView with user authorization and timeout handling Slack Integration: - Full SlackAdapter using slack-bolt with Socket Mode - DMs, channel messages (mention-gated), /hermes slash command - File attachment handling with bot-token-authenticated downloads DM Pairing System: - Code-based user authorization as alternative to static allowlists - 8-char codes from unambiguous alphabet, 1-hour expiry - Rate limiting, lockout after failed attempts, chmod 0600 on data - CLI: hermes pairing list/approve/revoke/clear-pending Event Hook System: - File-based hook discovery from ~/.hermes/hooks/ - HOOK.yaml + handler.py per hook, sync/async handler support - Events: gateway:startup, session:start/reset, agent:start/step/end - Wildcard matching (command:* catches all command events) Cross-Channel Messaging: - send_message agent tool for delivering to any connected platform - Enables cron job delivery and cross-platform notifications Human-Like Response Pacing: - Configurable delays between message chunks (off/natural/custom) - HERMES_HUMAN_DELAY_MODE env var with min/max ms settings Warm Injection Message Style: - Retrofitted image vision messages with friendly kawaii-consistent tone - All new injection messages (STT, stickers, errors) use warm style Also: updated config migration to prompt for optional keys interactively, bumped config version, updated README, AGENTS.md, .env.example, cli-config.yaml.example, install scripts, pyproject.toml, and toolsets.
2026-02-15 21:38:59 -08:00
"password": True,
"category": "tool",
Add messaging platform enhancements: STT, stickers, Discord UX, Slack, pairing, hooks Major feature additions inspired by OpenClaw/ClawdBot integration analysis: Voice Message Transcription (STT): - Auto-transcribe voice/audio messages via OpenAI Whisper API - Download voice to ~/.hermes/audio_cache/ on Telegram/Discord/WhatsApp - Inject transcript as text so all models can understand voice input - Configurable model (whisper-1, gpt-4o-mini-transcribe, gpt-4o-transcribe) Telegram Sticker Understanding: - Describe static stickers via vision tool with JSON-backed cache - Cache keyed by file_unique_id avoids redundant API calls - Animated/video stickers get emoji-based fallback description Discord Rich UX: - Native slash commands (/ask, /reset, /status, /stop) via app_commands - Button-based exec approvals (Allow Once / Always Allow / Deny) - ExecApprovalView with user authorization and timeout handling Slack Integration: - Full SlackAdapter using slack-bolt with Socket Mode - DMs, channel messages (mention-gated), /hermes slash command - File attachment handling with bot-token-authenticated downloads DM Pairing System: - Code-based user authorization as alternative to static allowlists - 8-char codes from unambiguous alphabet, 1-hour expiry - Rate limiting, lockout after failed attempts, chmod 0600 on data - CLI: hermes pairing list/approve/revoke/clear-pending Event Hook System: - File-based hook discovery from ~/.hermes/hooks/ - HOOK.yaml + handler.py per hook, sync/async handler support - Events: gateway:startup, session:start/reset, agent:start/step/end - Wildcard matching (command:* catches all command events) Cross-Channel Messaging: - send_message agent tool for delivering to any connected platform - Enables cron job delivery and cross-platform notifications Human-Like Response Pacing: - Configurable delays between message chunks (off/natural/custom) - HERMES_HUMAN_DELAY_MODE env var with min/max ms settings Warm Injection Message Style: - Retrofitted image vision messages with friendly kawaii-consistent tone - All new injection messages (STT, stickers, errors) use warm style Also: updated config migration to prompt for optional keys interactively, bumped config version, updated README, AGENTS.md, .env.example, cli-config.yaml.example, install scripts, pyproject.toml, and toolsets.
2026-02-15 21:38:59 -08:00
},
# ── Honcho ──
"HONCHO_API_KEY": {
"description": "Honcho API key for AI-native persistent memory",
"prompt": "Honcho API key",
"url": "https://app.honcho.dev",
"tools": ["honcho_context"],
"password": True,
"category": "tool",
},
"HONCHO_BASE_URL": {
"description": "Base URL for self-hosted Honcho instances (no API key needed)",
"prompt": "Honcho base URL (e.g. http://localhost:8000)",
"category": "tool",
},
# ── Messaging platforms ──
"TELEGRAM_BOT_TOKEN": {
"description": "Telegram bot token from @BotFather",
"prompt": "Telegram bot token",
"url": "https://t.me/BotFather",
"password": True,
"category": "messaging",
},
"TELEGRAM_ALLOWED_USERS": {
"description": "Comma-separated Telegram user IDs allowed to use the bot (get ID from @userinfobot)",
"prompt": "Allowed Telegram user IDs (comma-separated)",
"url": "https://t.me/userinfobot",
"password": False,
"category": "messaging",
},
"TELEGRAM_PROXY": {
"description": "Proxy URL for Telegram connections (overrides HTTPS_PROXY). Supports http://, https://, socks5://",
"prompt": "Telegram proxy URL (optional)",
"password": False,
"category": "messaging",
},
"DISCORD_BOT_TOKEN": {
"description": "Discord bot token from Developer Portal",
"prompt": "Discord bot token",
"url": "https://discord.com/developers/applications",
"password": True,
"category": "messaging",
},
"DISCORD_ALLOWED_USERS": {
"description": "Comma-separated Discord user IDs allowed to use the bot",
"prompt": "Allowed Discord user IDs (comma-separated)",
"url": None,
"password": False,
"category": "messaging",
},
"DISCORD_REPLY_TO_MODE": {
"description": "Discord reply threading mode: 'off' (no reply references), 'first' (reply on first message only, default), 'all' (reply on every chunk)",
"prompt": "Discord reply mode (off/first/all)",
"url": None,
"password": False,
"category": "messaging",
},
"SLACK_BOT_TOKEN": {
"description": "Slack bot token (xoxb-). Get from OAuth & Permissions after installing your app. "
"Required scopes: chat:write, app_mentions:read, channels:history, groups:history, "
"im:history, im:read, im:write, users:read, files:read, files:write",
"prompt": "Slack Bot Token (xoxb-...)",
"url": "https://api.slack.com/apps",
"password": True,
"category": "messaging",
},
"SLACK_APP_TOKEN": {
"description": "Slack app-level token (xapp-) for Socket Mode. Get from Basic Information → "
"App-Level Tokens. Also ensure Event Subscriptions include: message.im, "
"message.channels, message.groups, app_mention",
"prompt": "Slack App Token (xapp-...)",
"url": "https://api.slack.com/apps",
"password": True,
"category": "messaging",
},
"MATTERMOST_URL": {
"description": "Mattermost server URL (e.g. https://mm.example.com)",
"prompt": "Mattermost server URL",
"url": "https://mattermost.com/deploy/",
"password": False,
"category": "messaging",
},
"MATTERMOST_TOKEN": {
"description": "Mattermost bot token or personal access token",
"prompt": "Mattermost bot token",
"url": None,
"password": True,
"category": "messaging",
},
"MATTERMOST_ALLOWED_USERS": {
"description": "Comma-separated Mattermost user IDs allowed to use the bot",
"prompt": "Allowed Mattermost user IDs (comma-separated)",
"url": None,
"password": False,
"category": "messaging",
},
"MATTERMOST_REQUIRE_MENTION": {
"description": "Require @mention in Mattermost channels (default: true). Set to false to respond to all messages.",
"prompt": "Require @mention in channels",
"url": None,
"password": False,
"category": "messaging",
},
"MATTERMOST_FREE_RESPONSE_CHANNELS": {
"description": "Comma-separated Mattermost channel IDs where bot responds without @mention",
"prompt": "Free-response channel IDs (comma-separated)",
"url": None,
"password": False,
"category": "messaging",
},
"MATRIX_HOMESERVER": {
"description": "Matrix homeserver URL (e.g. https://matrix.example.org)",
"prompt": "Matrix homeserver URL",
"url": "https://matrix.org/ecosystem/servers/",
"password": False,
"category": "messaging",
},
"MATRIX_ACCESS_TOKEN": {
"description": "Matrix access token (preferred over password login)",
"prompt": "Matrix access token",
"url": None,
"password": True,
"category": "messaging",
},
"MATRIX_USER_ID": {
"description": "Matrix user ID (e.g. @hermes:example.org)",
"prompt": "Matrix user ID (@user:server)",
"url": None,
"password": False,
"category": "messaging",
},
"MATRIX_ALLOWED_USERS": {
"description": "Comma-separated Matrix user IDs allowed to use the bot (@user:server format)",
"prompt": "Allowed Matrix user IDs (comma-separated)",
"url": None,
"password": False,
"category": "messaging",
},
"MATRIX_REQUIRE_MENTION": {
"description": "Require @mention in Matrix rooms (default: true). Set to false to respond to all messages.",
"prompt": "Require @mention in rooms (true/false)",
"url": None,
"password": False,
"category": "messaging",
"advanced": True,
},
"MATRIX_FREE_RESPONSE_ROOMS": {
"description": "Comma-separated Matrix room IDs where bot responds without @mention",
"prompt": "Free-response room IDs (comma-separated)",
"url": None,
"password": False,
"category": "messaging",
"advanced": True,
},
"MATRIX_AUTO_THREAD": {
"description": "Auto-create threads for messages in Matrix rooms (default: true)",
"prompt": "Auto-create threads in rooms (true/false)",
"url": None,
"password": False,
"category": "messaging",
"advanced": True,
},
"MATRIX_DEVICE_ID": {
"description": "Stable Matrix device ID for E2EE persistence across restarts (e.g. HERMES_BOT)",
"prompt": "Matrix device ID (stable across restarts)",
"url": None,
"password": False,
"category": "messaging",
"advanced": True,
},
"MATRIX_RECOVERY_KEY": {
"description": "Matrix recovery key for cross-signing verification after device key rotation (from Element: Settings → Security → Recovery Key)",
"prompt": "Matrix recovery key",
"url": None,
"password": True,
"category": "messaging",
"advanced": True,
},
"BLUEBUBBLES_SERVER_URL": {
"description": "BlueBubbles server URL for iMessage integration (e.g. http://192.168.1.10:1234)",
"prompt": "BlueBubbles server URL",
"url": "https://bluebubbles.app/",
"password": False,
"category": "messaging",
},
"BLUEBUBBLES_PASSWORD": {
"description": "BlueBubbles server password (from BlueBubbles Server → Settings → API)",
"prompt": "BlueBubbles server password",
"url": None,
"password": True,
"category": "messaging",
},
"BLUEBUBBLES_ALLOWED_USERS": {
"description": "Comma-separated iMessage addresses (email or phone) allowed to use the bot",
"prompt": "Allowed iMessage addresses (comma-separated)",
"url": None,
"password": False,
"category": "messaging",
},
"BLUEBUBBLES_ALLOW_ALL_USERS": {
"description": "Allow all BlueBubbles users without allowlist",
"prompt": "Allow All BlueBubbles Users",
"category": "messaging",
},
"QQ_APP_ID": {
"description": "QQ Bot App ID from QQ Open Platform (q.qq.com)",
"prompt": "QQ App ID",
"url": "https://q.qq.com",
"category": "messaging",
},
"QQ_CLIENT_SECRET": {
"description": "QQ Bot Client Secret from QQ Open Platform",
"prompt": "QQ Client Secret",
"password": True,
"category": "messaging",
},
"QQ_ALLOWED_USERS": {
"description": "Comma-separated QQ user IDs allowed to use the bot",
"prompt": "QQ Allowed Users",
"category": "messaging",
},
"QQ_GROUP_ALLOWED_USERS": {
"description": "Comma-separated QQ group IDs allowed to interact with the bot",
"prompt": "QQ Group Allowed Users",
"category": "messaging",
},
"QQ_ALLOW_ALL_USERS": {
"description": "Allow all QQ users without an allowlist (true/false)",
"prompt": "Allow All QQ Users",
"category": "messaging",
},
"QQBOT_HOME_CHANNEL": {
"description": "Default QQ channel/group for cron delivery and notifications",
"prompt": "QQ Home Channel",
"category": "messaging",
},
"QQBOT_HOME_CHANNEL_NAME": {
"description": "Display name for the QQ home channel",
"prompt": "QQ Home Channel Name",
"category": "messaging",
},
"QQ_SANDBOX": {
"description": "Enable QQ sandbox mode for development testing (true/false)",
"prompt": "QQ Sandbox Mode",
"category": "messaging",
},
"GATEWAY_ALLOW_ALL_USERS": {
"description": "Allow all users to interact with messaging bots (true/false). Default: false.",
"prompt": "Allow all users (true/false)",
"url": None,
"password": False,
"category": "messaging",
"advanced": True,
},
feat: OpenAI-compatible API server + WhatsApp configurable reply prefix (#1756) * feat: OpenAI-compatible API server platform adapter Salvaged from PR #956, updated for current main. Adds an HTTP API server as a gateway platform adapter that exposes hermes-agent via the OpenAI Chat Completions and Responses APIs. Any OpenAI-compatible frontend (Open WebUI, LobeChat, LibreChat, AnythingLLM, NextChat, ChatBox, etc.) can connect by pointing at http://localhost:8642/v1. Endpoints: - POST /v1/chat/completions — stateless Chat Completions API - POST /v1/responses — stateful Responses API with chaining - GET /v1/responses/{id} — retrieve stored response - DELETE /v1/responses/{id} — delete stored response - GET /v1/models — list hermes-agent as available model - GET /health — health check Features: - Real SSE streaming via stream_delta_callback (uses main's streaming) - In-memory LRU response store for Responses API conversation chaining - Named conversations via 'conversation' parameter - Bearer token auth (optional, via API_SERVER_KEY) - CORS support for browser-based frontends - System prompt layering (frontend system messages on top of core) - Real token usage tracking in responses Integration points: - Platform.API_SERVER in gateway/config.py - _create_adapter() branch in gateway/run.py - API_SERVER_* env vars in hermes_cli/config.py - Env var overrides in gateway/config.py _apply_env_overrides() Changes vs original PR #956: - Removed streaming infrastructure (already on main via stream_consumer.py) - Removed Telegram reply_to_mode (separate feature, not included) - Updated _resolve_model() -> _resolve_gateway_model() - Updated stream_callback -> stream_delta_callback - Updated connect()/disconnect() to use _mark_connected()/_mark_disconnected() - Adapted to current Platform enum (includes MATTERMOST, MATRIX, DINGTALK) Tests: 72 new tests, all passing Docs: API server guide, Open WebUI integration guide, env var reference * feat(whatsapp): make reply prefix configurable via config.yaml Reworked from PR #1764 (ifrederico) to use config.yaml instead of .env. The WhatsApp bridge prepends a header to every outgoing message. This was hardcoded to '⚕ *Hermes Agent*'. Users can now customize or disable it via config.yaml: whatsapp: reply_prefix: '' # disable header reply_prefix: '🤖 *My Bot*\n───\n' # custom prefix How it works: - load_gateway_config() reads whatsapp.reply_prefix from config.yaml and stores it in PlatformConfig.extra['reply_prefix'] - WhatsAppAdapter reads it from config.extra at init - When spawning bridge.js, the adapter passes it as WHATSAPP_REPLY_PREFIX in the subprocess environment - bridge.js handles undefined (default), empty (no header), or custom values with \\n escape support - Self-chat echo suppression uses the configured prefix Also fixes _config_version: was 9 but ENV_VARS_BY_VERSION had a key 10 (TAVILY_API_KEY), so existing users at v9 would never be prompted for Tavily. Bumped to 10 to close the gap. Added a regression test to prevent this from happening again. Credit: ifrederico (PR #1764) for the bridge.js implementation and the config version gap discovery. --------- Co-authored-by: Test <test@test.com>
2026-03-17 10:44:37 -07:00
"API_SERVER_ENABLED": {
"description": "Enable the OpenAI-compatible API server (true/false). Allows frontends like Open WebUI, LobeChat, etc. to connect.",
"prompt": "Enable API server (true/false)",
"url": None,
"password": False,
"category": "messaging",
"advanced": True,
},
"API_SERVER_KEY": {
"description": "Bearer token for API server authentication. Required for non-loopback binding; server refuses to start without it. On loopback (127.0.0.1), all requests are allowed if empty.",
"prompt": "API server auth key (required for network access)",
feat: OpenAI-compatible API server + WhatsApp configurable reply prefix (#1756) * feat: OpenAI-compatible API server platform adapter Salvaged from PR #956, updated for current main. Adds an HTTP API server as a gateway platform adapter that exposes hermes-agent via the OpenAI Chat Completions and Responses APIs. Any OpenAI-compatible frontend (Open WebUI, LobeChat, LibreChat, AnythingLLM, NextChat, ChatBox, etc.) can connect by pointing at http://localhost:8642/v1. Endpoints: - POST /v1/chat/completions — stateless Chat Completions API - POST /v1/responses — stateful Responses API with chaining - GET /v1/responses/{id} — retrieve stored response - DELETE /v1/responses/{id} — delete stored response - GET /v1/models — list hermes-agent as available model - GET /health — health check Features: - Real SSE streaming via stream_delta_callback (uses main's streaming) - In-memory LRU response store for Responses API conversation chaining - Named conversations via 'conversation' parameter - Bearer token auth (optional, via API_SERVER_KEY) - CORS support for browser-based frontends - System prompt layering (frontend system messages on top of core) - Real token usage tracking in responses Integration points: - Platform.API_SERVER in gateway/config.py - _create_adapter() branch in gateway/run.py - API_SERVER_* env vars in hermes_cli/config.py - Env var overrides in gateway/config.py _apply_env_overrides() Changes vs original PR #956: - Removed streaming infrastructure (already on main via stream_consumer.py) - Removed Telegram reply_to_mode (separate feature, not included) - Updated _resolve_model() -> _resolve_gateway_model() - Updated stream_callback -> stream_delta_callback - Updated connect()/disconnect() to use _mark_connected()/_mark_disconnected() - Adapted to current Platform enum (includes MATTERMOST, MATRIX, DINGTALK) Tests: 72 new tests, all passing Docs: API server guide, Open WebUI integration guide, env var reference * feat(whatsapp): make reply prefix configurable via config.yaml Reworked from PR #1764 (ifrederico) to use config.yaml instead of .env. The WhatsApp bridge prepends a header to every outgoing message. This was hardcoded to '⚕ *Hermes Agent*'. Users can now customize or disable it via config.yaml: whatsapp: reply_prefix: '' # disable header reply_prefix: '🤖 *My Bot*\n───\n' # custom prefix How it works: - load_gateway_config() reads whatsapp.reply_prefix from config.yaml and stores it in PlatformConfig.extra['reply_prefix'] - WhatsAppAdapter reads it from config.extra at init - When spawning bridge.js, the adapter passes it as WHATSAPP_REPLY_PREFIX in the subprocess environment - bridge.js handles undefined (default), empty (no header), or custom values with \\n escape support - Self-chat echo suppression uses the configured prefix Also fixes _config_version: was 9 but ENV_VARS_BY_VERSION had a key 10 (TAVILY_API_KEY), so existing users at v9 would never be prompted for Tavily. Bumped to 10 to close the gap. Added a regression test to prevent this from happening again. Credit: ifrederico (PR #1764) for the bridge.js implementation and the config version gap discovery. --------- Co-authored-by: Test <test@test.com>
2026-03-17 10:44:37 -07:00
"url": None,
"password": True,
"category": "messaging",
"advanced": True,
},
"API_SERVER_PORT": {
"description": "Port for the API server (default: 8642).",
"prompt": "API server port",
"url": None,
"password": False,
"category": "messaging",
"advanced": True,
},
"API_SERVER_HOST": {
"description": "Host/bind address for the API server (default: 127.0.0.1). Use 0.0.0.0 for network access — server refuses to start without API_SERVER_KEY.",
feat: OpenAI-compatible API server + WhatsApp configurable reply prefix (#1756) * feat: OpenAI-compatible API server platform adapter Salvaged from PR #956, updated for current main. Adds an HTTP API server as a gateway platform adapter that exposes hermes-agent via the OpenAI Chat Completions and Responses APIs. Any OpenAI-compatible frontend (Open WebUI, LobeChat, LibreChat, AnythingLLM, NextChat, ChatBox, etc.) can connect by pointing at http://localhost:8642/v1. Endpoints: - POST /v1/chat/completions — stateless Chat Completions API - POST /v1/responses — stateful Responses API with chaining - GET /v1/responses/{id} — retrieve stored response - DELETE /v1/responses/{id} — delete stored response - GET /v1/models — list hermes-agent as available model - GET /health — health check Features: - Real SSE streaming via stream_delta_callback (uses main's streaming) - In-memory LRU response store for Responses API conversation chaining - Named conversations via 'conversation' parameter - Bearer token auth (optional, via API_SERVER_KEY) - CORS support for browser-based frontends - System prompt layering (frontend system messages on top of core) - Real token usage tracking in responses Integration points: - Platform.API_SERVER in gateway/config.py - _create_adapter() branch in gateway/run.py - API_SERVER_* env vars in hermes_cli/config.py - Env var overrides in gateway/config.py _apply_env_overrides() Changes vs original PR #956: - Removed streaming infrastructure (already on main via stream_consumer.py) - Removed Telegram reply_to_mode (separate feature, not included) - Updated _resolve_model() -> _resolve_gateway_model() - Updated stream_callback -> stream_delta_callback - Updated connect()/disconnect() to use _mark_connected()/_mark_disconnected() - Adapted to current Platform enum (includes MATTERMOST, MATRIX, DINGTALK) Tests: 72 new tests, all passing Docs: API server guide, Open WebUI integration guide, env var reference * feat(whatsapp): make reply prefix configurable via config.yaml Reworked from PR #1764 (ifrederico) to use config.yaml instead of .env. The WhatsApp bridge prepends a header to every outgoing message. This was hardcoded to '⚕ *Hermes Agent*'. Users can now customize or disable it via config.yaml: whatsapp: reply_prefix: '' # disable header reply_prefix: '🤖 *My Bot*\n───\n' # custom prefix How it works: - load_gateway_config() reads whatsapp.reply_prefix from config.yaml and stores it in PlatformConfig.extra['reply_prefix'] - WhatsAppAdapter reads it from config.extra at init - When spawning bridge.js, the adapter passes it as WHATSAPP_REPLY_PREFIX in the subprocess environment - bridge.js handles undefined (default), empty (no header), or custom values with \\n escape support - Self-chat echo suppression uses the configured prefix Also fixes _config_version: was 9 but ENV_VARS_BY_VERSION had a key 10 (TAVILY_API_KEY), so existing users at v9 would never be prompted for Tavily. Bumped to 10 to close the gap. Added a regression test to prevent this from happening again. Credit: ifrederico (PR #1764) for the bridge.js implementation and the config version gap discovery. --------- Co-authored-by: Test <test@test.com>
2026-03-17 10:44:37 -07:00
"prompt": "API server host",
"url": None,
"password": False,
"category": "messaging",
"advanced": True,
},
"API_SERVER_MODEL_NAME": {
"description": "Model name advertised on /v1/models. Defaults to the profile name (or 'hermes-agent' for the default profile). Useful for multi-user setups with OpenWebUI.",
"prompt": "API server model name",
"url": None,
"password": False,
"category": "messaging",
"advanced": True,
},
feat: gateway proxy mode — forward messages to remote API server When GATEWAY_PROXY_URL (or gateway.proxy_url in config.yaml) is set, the gateway becomes a thin relay: it handles platform I/O (encryption, threading, media) and delegates all agent work to a remote Hermes API server via POST /v1/chat/completions with SSE streaming. This enables the primary use case of running a Matrix E2EE gateway in Docker on Linux while the actual agent runs on the host (e.g. macOS) with full access to local files, memory, skills, and a unified session store. Works for any platform adapter, not just Matrix. Configuration: - GATEWAY_PROXY_URL env var (Docker-friendly) - gateway.proxy_url in config.yaml - GATEWAY_PROXY_KEY env var for API auth (matches API_SERVER_KEY) - X-Hermes-Session-Id header for session continuity Architecture: - _get_proxy_url() checks env var first, then config.yaml - _run_agent_via_proxy() handles HTTP forwarding with SSE streaming - _run_agent() delegates to proxy path when URL is configured - Platform streaming (GatewayStreamConsumer) works through proxy - Returns compatible result dict for session store recording Files changed: - gateway/run.py: proxy mode implementation (~250 lines) - hermes_cli/config.py: GATEWAY_PROXY_URL + GATEWAY_PROXY_KEY env vars - tests/gateway/test_proxy_mode.py: 17 tests covering config resolution, dispatch, HTTP forwarding, error handling, message filtering, and result shape validation Closes discussion from Cars29 re: Matrix gateway mixed-mode issue.
2026-04-14 10:33:02 -07:00
"GATEWAY_PROXY_URL": {
"description": "URL of a remote Hermes API server to forward messages to (proxy mode). When set, the gateway handles platform I/O only — all agent work is delegated to the remote server. Use for Docker E2EE containers that relay to a host agent. Also configurable via gateway.proxy_url in config.yaml.",
"prompt": "Remote Hermes API server URL (e.g. http://192.168.1.100:8642)",
"url": None,
"password": False,
"category": "messaging",
"advanced": True,
},
"GATEWAY_PROXY_KEY": {
"description": "Bearer token for authenticating with the remote Hermes API server (proxy mode). Must match the API_SERVER_KEY on the remote host.",
"prompt": "Remote API server auth key",
"url": None,
"password": True,
"category": "messaging",
"advanced": True,
},
feat(gateway): add webhook platform adapter for external event triggers Add a generic webhook platform adapter that receives HTTP POSTs from external services (GitHub, GitLab, JIRA, Stripe, etc.), validates HMAC signatures, transforms payloads into agent prompts, and routes responses back to the source or to another platform. Features: - Configurable routes with per-route HMAC secrets, event filters, prompt templates with dot-notation payload access, skill loading, and pluggable delivery (github_comment, telegram, discord, log) - HMAC signature validation (GitHub SHA-256, GitLab token, generic) - Rate limiting (30 req/min per route, configurable) - Idempotency cache (1hr TTL, prevents duplicate runs on retries) - Body size limits (1MB default, checked before reading payload) - Setup wizard integration with security warnings and docs links - 33 tests (29 unit + 4 integration), all passing Security: - HMAC secret required per route (startup validation) - Setup wizard warns about internet exposure for webhook/SMS platforms - Sandboxing (Docker/VM) recommended in docs for public-facing deployments Files changed: - gateway/config.py — Platform.WEBHOOK enum + env var overrides - gateway/platforms/webhook.py — WebhookAdapter (~420 lines) - gateway/run.py — factory wiring + auth bypass for webhook events - hermes_cli/config.py — WEBHOOK_* env var definitions - hermes_cli/setup.py — webhook section in setup_gateway() - tests/gateway/test_webhook_adapter.py — 29 unit tests - tests/gateway/test_webhook_integration.py — 4 integration tests - website/docs/user-guide/messaging/webhooks.md — full user docs - website/docs/reference/environment-variables.md — WEBHOOK_* vars - website/sidebars.ts — nav entry
2026-03-20 06:33:36 -07:00
"WEBHOOK_ENABLED": {
"description": "Enable the webhook platform adapter for receiving events from GitHub, GitLab, etc.",
"prompt": "Enable webhooks (true/false)",
"url": None,
"password": False,
"category": "messaging",
},
"WEBHOOK_PORT": {
"description": "Port for the webhook HTTP server (default: 8644).",
"prompt": "Webhook port",
"url": None,
"password": False,
"category": "messaging",
},
"WEBHOOK_SECRET": {
"description": "Global HMAC secret for webhook signature validation (overridable per route in config.yaml).",
"prompt": "Webhook secret",
"url": None,
"password": True,
"category": "messaging",
},
# ── Agent settings ──
# NOTE: MESSAGING_CWD was removed here — use terminal.cwd in config.yaml
# instead. The gateway reads TERMINAL_CWD (bridged from terminal.cwd).
"SUDO_PASSWORD": {
"description": "Sudo password for terminal commands requiring root access; set to an explicit empty string to try empty without prompting",
"prompt": "Sudo password",
"url": None,
"password": True,
"category": "setting",
},
"HERMES_MAX_ITERATIONS": {
docs: comprehensive AGENTS.md audit and corrections Major fixes: - Default model: claude-sonnet-4.6 → claude-opus-4.6 - max_iterations default: 60 → 90 (also fixed in config.py OPTIONAL_ENV_VARS description) - chat() signature: chat(user_message, task_id) → chat(message) - Agent loop: _run_agent_loop() doesn't exist, loop is in run_conversation() - Removed async/await references (agent is entirely synchronous) - KawaiiSpinner location: run_agent.py → agent/display.py - NOUS_API_KEY removed (not used by any tool), replaced with VOICE_TOOLS_OPENAI_KEY - OPENAI_API_KEY for Whisper → VOICE_TOOLS_OPENAI_KEY - check_for_missing_config() → check_config_version() + get_missing_env_vars() - Adding tools: '2 files' → '3 files' (tool + model_tools.py + toolsets.py) - Venv path: venv/ → .venv/ - Trajectory output path: trajectories/*.jsonl → trajectory_samples.jsonl - process_command() location clarified (HermesCLI in cli.py, not commands.py) - REQUIRED_ENV_VARS noted as intentionally empty - _config_version noted as currently at version 5 New content: - Project structure: added 40+ missing files across agent/, hermes_cli/, tools/, gateway/ - Full gateway/ directory listing with all modules and platforms/ - Added honcho_integration/, scripts/, tests/ directories - Added hermes_constants.py, hermes_time.py, trajectory_compressor.py, utils.py - CLI commands table: added 25+ missing commands (model, login, logout, whatsapp, skills subsystem, tools, insights, gateway start/stop/restart/status/uninstall, sessions export/delete/prune/stats, config path/env-path/show) - Gateway slash commands section with all 20+ commands - Platform toolsets: added hermes-cli, hermes-slack, hermes-homeassistant, hermes-gateway - Gateway: added Home Assistant as supported platform
2026-03-08 17:38:05 -07:00
"description": "Maximum tool-calling iterations per conversation (default: 90)",
"prompt": "Max iterations",
"url": None,
"password": False,
"category": "setting",
},
# HERMES_TOOL_PROGRESS and HERMES_TOOL_PROGRESS_MODE are deprecated —
# now configured via display.tool_progress in config.yaml (off|new|all|verbose).
# Gateway falls back to these env vars for backward compatibility.
"HERMES_TOOL_PROGRESS": {
"description": "(deprecated) Use display.tool_progress in config.yaml instead",
"prompt": "Tool progress (deprecated — use config.yaml)",
"url": None,
"password": False,
"category": "setting",
},
"HERMES_TOOL_PROGRESS_MODE": {
"description": "(deprecated) Use display.tool_progress in config.yaml instead",
"prompt": "Progress mode (deprecated — use config.yaml)",
"url": None,
"password": False,
"category": "setting",
},
"HERMES_PREFILL_MESSAGES_FILE": {
"description": "Path to JSON file with ephemeral prefill messages for few-shot priming",
"prompt": "Prefill messages file path",
"url": None,
"password": False,
"category": "setting",
},
"HERMES_EPHEMERAL_SYSTEM_PROMPT": {
"description": "Ephemeral system prompt injected at API-call time (never persisted to sessions)",
"prompt": "Ephemeral system prompt",
"url": None,
"password": False,
"category": "setting",
},
}
feat: ungate Tool Gateway — subscription-based access with per-tool opt-in Replace the HERMES_ENABLE_NOUS_MANAGED_TOOLS env-var feature flag with subscription-based detection. The Tool Gateway is now available to any paid Nous subscriber without needing a hidden env var. Core changes: - managed_nous_tools_enabled() checks get_nous_auth_status() + check_nous_free_tier() instead of an env var - New use_gateway config flag per tool section (web, tts, browser, image_gen) records explicit user opt-in and overrides direct API keys at runtime - New prefers_gateway(section) shared helper in tool_backend_helpers.py used by all 4 tool runtimes (web, tts, image gen, browser) UX flow: - hermes model: after Nous login/model selection, shows a curses prompt listing all gateway-eligible tools with current status. User chooses to enable all, enable only unconfigured tools, or skip. Defaults to Enable for new users, Skip when direct keys exist. - hermes tools: provider selection now manages use_gateway flag — selecting Nous Subscription sets it, selecting any other provider clears it - hermes status: renamed section to Nous Tool Gateway, added free-tier upgrade nudge for logged-in free users - curses_radiolist: new description parameter for multi-line context that survives the screen clear Runtime behavior: - Each tool runtime (web_tools, tts_tool, image_generation_tool, browser_use) checks prefers_gateway() before falling back to direct env-var credentials - get_nous_subscription_features() respects use_gateway flags, suppressing direct credential detection when the user opted in Removed: - HERMES_ENABLE_NOUS_MANAGED_TOOLS env var and all references - apply_nous_provider_defaults() silent TTS auto-set - get_nous_subscription_explainer_lines() static text - Override env var warnings (use_gateway handles this properly now)
2026-04-16 01:59:51 -04:00
# Tool Gateway env vars are always visible — they're useful for
# self-hosted / custom gateway setups regardless of subscription state.
def get_missing_env_vars(required_only: bool = False) -> List[Dict[str, Any]]:
"""
Check which environment variables are missing.
Returns list of dicts with var info for missing variables.
"""
missing = []
# Check required vars
for var_name, info in REQUIRED_ENV_VARS.items():
if not get_env_value(var_name):
missing.append({"name": var_name, **info, "is_required": True})
# Check optional vars (if not required_only)
if not required_only:
for var_name, info in OPTIONAL_ENV_VARS.items():
if not get_env_value(var_name):
missing.append({"name": var_name, **info, "is_required": False})
return missing
def _set_nested(config: dict, dotted_key: str, value):
"""Set a value at an arbitrarily nested dotted key path.
Creates intermediate dicts as needed, e.g. ``_set_nested(c, "a.b.c", 1)``
ensures ``c["a"]["b"]["c"] == 1``.
"""
parts = dotted_key.split(".")
current = config
for part in parts[:-1]:
if part not in current or not isinstance(current.get(part), dict):
current[part] = {}
current = current[part]
current[parts[-1]] = value
def get_missing_config_fields() -> List[Dict[str, Any]]:
"""
Check which config fields are missing or outdated (recursive).
Walks the DEFAULT_CONFIG tree at arbitrary depth and reports any keys
present in defaults but absent from the user's loaded config.
"""
config = load_config()
missing = []
def _check(defaults: dict, current: dict, prefix: str = ""):
for key, default_value in defaults.items():
if key.startswith('_'):
continue
full_key = key if not prefix else f"{prefix}.{key}"
if key not in current:
missing.append({
"key": full_key,
"default": default_value,
"description": f"New config option: {full_key}",
})
elif isinstance(default_value, dict) and isinstance(current.get(key), dict):
_check(default_value, current[key], full_key)
_check(DEFAULT_CONFIG, config)
return missing
def get_missing_skill_config_vars() -> List[Dict[str, Any]]:
"""Return skill-declared config vars that are missing or empty in config.yaml.
Scans all enabled skills for ``metadata.hermes.config`` entries, then checks
which ones are absent or empty under ``skills.config.<key>`` in the user's
config.yaml. Returns a list of dicts suitable for prompting.
"""
try:
from agent.skill_utils import discover_all_skill_config_vars, SKILL_CONFIG_PREFIX
except Exception:
return []
all_vars = discover_all_skill_config_vars()
if not all_vars:
return []
config = load_config()
missing: List[Dict[str, Any]] = []
for var in all_vars:
# Skill config is stored under skills.config.<logical_key>
storage_key = f"{SKILL_CONFIG_PREFIX}.{var['key']}"
parts = storage_key.split(".")
current = config
value = None
for part in parts:
if isinstance(current, dict) and part in current:
current = current[part]
value = current
else:
value = None
break
# Missing = key doesn't exist or is empty string
if value is None or (isinstance(value, str) and not value.strip()):
missing.append(var)
return missing
def _normalize_custom_provider_entry(
entry: Any,
*,
provider_key: str = "",
) -> Optional[Dict[str, Any]]:
"""Return a runtime-compatible custom provider entry or ``None``."""
if not isinstance(entry, dict):
return None
# Accept camelCase aliases commonly used in hand-written configs.
_CAMEL_ALIASES: Dict[str, str] = {
"apiKey": "api_key",
"baseUrl": "base_url",
"apiMode": "api_mode",
"keyEnv": "key_env",
"defaultModel": "default_model",
"contextLength": "context_length",
"rateLimitDelay": "rate_limit_delay",
}
_KNOWN_KEYS = {
"name", "api", "url", "base_url", "api_key", "key_env",
"api_mode", "transport", "model", "default_model", "models",
"context_length", "rate_limit_delay",
}
for camel, snake in _CAMEL_ALIASES.items():
if camel in entry and snake not in entry:
logger.warning(
"providers.%s: camelCase key '%s' auto-mapped to '%s' "
"(use snake_case to avoid this warning)",
provider_key or "?", camel, snake,
)
entry[snake] = entry[camel]
unknown = set(entry.keys()) - _KNOWN_KEYS - set(_CAMEL_ALIASES.keys())
if unknown:
logger.warning(
"providers.%s: unknown config keys ignored: %s",
provider_key or "?", ", ".join(sorted(unknown)),
)
from urllib.parse import urlparse
base_url = ""
for url_key in ("base_url", "url", "api"):
raw_url = entry.get(url_key)
if isinstance(raw_url, str) and raw_url.strip():
candidate = raw_url.strip()
parsed = urlparse(candidate)
if parsed.scheme and parsed.netloc:
base_url = candidate
break
else:
logger.warning(
"providers.%s: '%s' value '%s' is not a valid URL "
"(no scheme or host) — skipped",
provider_key or "?", url_key, candidate,
)
if not base_url:
return None
name = ""
raw_name = entry.get("name")
if isinstance(raw_name, str) and raw_name.strip():
name = raw_name.strip()
elif provider_key.strip():
name = provider_key.strip()
if not name:
return None
normalized: Dict[str, Any] = {
"name": name,
"base_url": base_url,
}
provider_key = provider_key.strip()
if provider_key:
normalized["provider_key"] = provider_key
api_key = entry.get("api_key")
if isinstance(api_key, str) and api_key.strip():
normalized["api_key"] = api_key.strip()
key_env = entry.get("key_env")
if isinstance(key_env, str) and key_env.strip():
normalized["key_env"] = key_env.strip()
api_mode = entry.get("api_mode") or entry.get("transport")
if isinstance(api_mode, str) and api_mode.strip():
normalized["api_mode"] = api_mode.strip()
model_name = entry.get("model") or entry.get("default_model")
if isinstance(model_name, str) and model_name.strip():
normalized["model"] = model_name.strip()
models = entry.get("models")
if isinstance(models, dict) and models:
normalized["models"] = models
elif isinstance(models, list) and models:
# Hand-edited configs (and older Hermes versions) write ``models`` as
# a plain list of model ids. Preserve them by converting to the dict
# shape downstream code expects; otherwise normalize silently drops
# the list and /model shows the provider with (0) models.
normalized["models"] = {
str(m): {} for m in models if isinstance(m, str) and m.strip()
}
context_length = entry.get("context_length")
if isinstance(context_length, int) and context_length > 0:
normalized["context_length"] = context_length
rate_limit_delay = entry.get("rate_limit_delay")
if isinstance(rate_limit_delay, (int, float)) and rate_limit_delay >= 0:
normalized["rate_limit_delay"] = rate_limit_delay
return normalized
def providers_dict_to_custom_providers(providers_dict: Any) -> List[Dict[str, Any]]:
"""Normalize ``providers`` config entries into the legacy custom-provider shape."""
if not isinstance(providers_dict, dict):
return []
custom_providers: List[Dict[str, Any]] = []
for key, entry in providers_dict.items():
normalized = _normalize_custom_provider_entry(entry, provider_key=str(key))
if normalized is not None:
custom_providers.append(normalized)
return custom_providers
def get_compatible_custom_providers(
config: Optional[Dict[str, Any]] = None,
) -> List[Dict[str, Any]]:
"""Return a deduplicated custom-provider view across legacy and v12+ config.
``custom_providers`` remains the on-disk legacy format, while ``providers``
is the newer keyed schema. Runtime and picker flows still need a single
list-shaped view, but we should not materialise that compatibility layer
back into config.yaml because it duplicates entries in UIs.
"""
if config is None:
config = load_config()
compatible: List[Dict[str, Any]] = []
seen_provider_keys: set = set()
seen_name_url_pairs: set = set()
def _append_if_new(entry: Optional[Dict[str, Any]]) -> None:
if entry is None:
return
provider_key = str(entry.get("provider_key", "") or "").strip().lower()
name = str(entry.get("name", "") or "").strip().lower()
base_url = str(entry.get("base_url", "") or "").strip().rstrip("/").lower()
model = str(entry.get("model", "") or "").strip().lower()
pair = (name, base_url, model)
if provider_key and provider_key in seen_provider_keys:
return
if name and base_url and pair in seen_name_url_pairs:
return
compatible.append(entry)
if provider_key:
seen_provider_keys.add(provider_key)
if name and base_url:
seen_name_url_pairs.add(pair)
custom_providers = config.get("custom_providers")
if custom_providers is not None:
if not isinstance(custom_providers, list):
return []
for entry in custom_providers:
_append_if_new(_normalize_custom_provider_entry(entry))
for entry in providers_dict_to_custom_providers(config.get("providers")):
_append_if_new(entry)
return compatible
fix(context): honor custom_providers context_length on /model switch + bump probe tier to 256K (#15844) Fixes #15779. Custom-provider per-model context_length (`custom_providers[].models.<id>.context_length`) is now honored across every resolution path, not just agent startup. Also adds 256K as the top probe tier and default fallback. ## What changed New helper `hermes_cli.config.get_custom_provider_context_length()` — single source of truth for the per-model override lookup, with trailing-slash-insensitive base-url matching. `agent.model_metadata.get_model_context_length()` gains an optional `custom_providers=` kwarg (step 0b — runs after explicit `config_context_length` but before every other probe). Wired through five call sites that previously either duplicated the lookup or ignored it entirely: - `run_agent.py` startup — refactored to use the new helper (dedups legacy inline loop, keeps invalid-value warning) - `AIAgent.switch_model()` — re-reads custom_providers from live config on every /model switch - `hermes_cli.model_switch.resolve_display_context_length()` — new `custom_providers=` kwarg - `gateway/run.py` /model confirmation (picker callback + text path) - `gateway/run.py` `_format_session_info` (/info) ## Context probe tiers `CONTEXT_PROBE_TIERS = [256_000, 128_000, 64_000, 32_000, 16_000, 8_000]` — was `[128_000, ...]`. `DEFAULT_FALLBACK_CONTEXT` follows tier[0], so unknown models now default to 256K. The stale `128000` literal in the OpenRouter metadata-miss path is replaced with `DEFAULT_FALLBACK_CONTEXT` for consistency. ## Repro (from #15779) ```yaml custom_providers: - name: my-custom-endpoint base_url: https://example.invalid/v1 model: gpt-5.5 models: gpt-5.5: context_length: 1050000 ``` `/model gpt-5.5 --provider custom:my-custom-endpoint` → previously "Context: 128,000", now "Context: 1,050,000". ## Tests - `tests/hermes_cli/test_custom_provider_context_length.py` — new file, 19 tests covering the helper, step-0b integration, and the 256K tier invariants - `tests/hermes_cli/test_model_switch_context_display.py` — added regression tests for #15779 through the display resolver - `tests/gateway/test_session_info.py` — updated default-fallback assertion (128K → 256K) - `tests/agent/test_model_metadata.py` — updated tier assertions for the new top tier
2026-04-25 18:47:53 -07:00
def get_custom_provider_context_length(
model: str,
base_url: str,
custom_providers: Optional[List[Dict[str, Any]]] = None,
config: Optional[Dict[str, Any]] = None,
) -> Optional[int]:
"""Look up a per-model ``context_length`` override from ``custom_providers``.
Matches any entry whose ``base_url`` equals ``base_url`` (trailing-slash
insensitive) and returns ``custom_providers[i].models.<model>.context_length``
if present and valid. Returns ``None`` when no override applies.
This is the single source of truth for custom-provider context overrides,
used by:
* ``AIAgent.__init__`` (startup resolution)
* ``AIAgent.switch_model`` (mid-session ``/model`` switch)
* ``hermes_cli.model_switch.resolve_display_context_length`` (``/model`` confirmation display)
* ``gateway.run._format_session_info`` (``/info`` display)
* ``agent.model_metadata.get_model_context_length`` (when custom_providers is threaded through)
Before this helper existed, the lookup was duplicated in ``run_agent.py``'s
startup path only; every other path (notably ``/model`` switch) fell back
to the 128K default. See #15779.
"""
if not model or not base_url:
return None
if custom_providers is None:
try:
custom_providers = get_compatible_custom_providers(config)
except Exception:
if config is None:
return None
raw = config.get("custom_providers")
custom_providers = raw if isinstance(raw, list) else []
if not isinstance(custom_providers, list):
return None
target_url = (base_url or "").rstrip("/")
if not target_url:
return None
for entry in custom_providers:
if not isinstance(entry, dict):
continue
entry_url = (entry.get("base_url") or "").rstrip("/")
if not entry_url or entry_url != target_url:
continue
models = entry.get("models")
if not isinstance(models, dict):
continue
model_cfg = models.get(model)
if not isinstance(model_cfg, dict):
continue
raw_ctx = model_cfg.get("context_length")
if raw_ctx is None:
continue
try:
ctx = int(raw_ctx)
except (TypeError, ValueError):
continue
if ctx > 0:
return ctx
return None
def check_config_version() -> Tuple[int, int]:
"""
Check config version.
Returns (current_version, latest_version).
"""
config = load_config()
current = config.get("_config_version", 0)
latest = DEFAULT_CONFIG.get("_config_version", 1)
return current, latest
# =============================================================================
# Config structure validation
# =============================================================================
# Fields that are valid at root level of config.yaml
_KNOWN_ROOT_KEYS = {
"_config_version", "model", "providers", "fallback_model",
"fallback_providers", "credential_pool_strategies", "toolsets",
"agent", "terminal", "display", "compression", "delegation",
"auxiliary", "custom_providers", "context", "memory", "gateway",
feat(state): auto-prune old sessions + VACUUM state.db at startup (#13861) * feat(state): auto-prune old sessions + VACUUM state.db at startup state.db accumulates every session, message, and FTS5 index entry forever. A heavy user (gateway + cron) reported 384MB with 982 sessions / 68K messages causing slowdown; manual 'hermes sessions prune --older-than 7' + VACUUM brought it to 43MB. The prune command and VACUUM are not wired to run automatically anywhere — sessions grew unbounded until users noticed. Changes: - hermes_state.py: new state_meta key/value table, vacuum() method, and maybe_auto_prune_and_vacuum() — idempotent via last-run timestamp in state_meta so it only actually executes once per min_interval_hours across all Hermes processes for a given HERMES_HOME. Never raises. - hermes_cli/config.py: new 'sessions:' block in DEFAULT_CONFIG (auto_prune=True, retention_days=90, vacuum_after_prune=True, min_interval_hours=24). Added to _KNOWN_ROOT_KEYS. - cli.py: call maintenance once at HermesCLI init (shared helper _run_state_db_auto_maintenance reads config and delegates to DB). - gateway/run.py: call maintenance once at GatewayRunner init. - Docs: user-guide/sessions.md rewrites 'Automatic Cleanup' section. Why VACUUM matters: SQLite does NOT shrink the file on DELETE — freed pages get reused on next INSERT. Without VACUUM, a delete-heavy DB stays bloated forever. VACUUM only runs when the prune actually removed rows, so tight DBs don't pay the I/O cost. Tests: 10 new tests in tests/test_hermes_state.py covering state_meta, vacuum, idempotency, interval skipping, VACUUM-only-when-needed, corrupt-marker recovery. All 246 existing state/config/gateway tests still pass. Verified E2E with real imports + isolated HERMES_HOME: DEFAULT_CONFIG exposes the new block, load_config() returns it for fresh installs, first call prunes+vacuums, second call within min_interval_hours skips, and the state_meta marker persists across connection close/reopen. * sessions.auto_prune defaults to false (opt-in) Session history powers session_search recall across past conversations, so silently pruning on startup could surprise users. Ship the machinery disabled and let users opt in when they notice state.db is hurting performance. - DEFAULT_CONFIG.sessions.auto_prune: True → False - Call-site fallbacks in cli.py and gateway/run.py match the new default (so unmigrated configs still see off) - Docs: flip 'Enable in config.yaml' framing + tip explains the tradeoff
2026-04-22 05:21:49 -07:00
"sessions",
}
# Valid fields inside a custom_providers list entry
_VALID_CUSTOM_PROVIDER_FIELDS = {
"name", "base_url", "api_key", "api_mode", "model", "models",
"context_length", "rate_limit_delay",
}
# Fields that look like they should be inside custom_providers, not at root
_CUSTOM_PROVIDER_LIKE_FIELDS = {"base_url", "api_key", "rate_limit_delay", "api_mode"}
@dataclass
class ConfigIssue:
"""A detected config structure problem."""
severity: str # "error", "warning"
message: str
hint: str
def validate_config_structure(config: Optional[Dict[str, Any]] = None) -> List["ConfigIssue"]:
"""Validate config.yaml structure and return a list of detected issues.
Catches common YAML formatting mistakes that produce confusing runtime
errors (like "Unknown provider") instead of clear diagnostics.
Can be called with a pre-loaded config dict, or will load from disk.
"""
if config is None:
try:
config = load_config()
except Exception:
return [ConfigIssue("error", "Could not load config.yaml", "Run 'hermes setup' to create a valid config")]
issues: List[ConfigIssue] = []
# ── custom_providers must be a list, not a dict ──────────────────────
cp = config.get("custom_providers")
if cp is not None:
if isinstance(cp, dict):
issues.append(ConfigIssue(
"error",
"custom_providers is a dict — it must be a YAML list (items prefixed with '-')",
"Change to:\n"
" custom_providers:\n"
" - name: my-provider\n"
" base_url: https://...\n"
" api_key: ...",
))
# Check if dict keys look like they should be list-entry fields
cp_keys = set(cp.keys()) if isinstance(cp, dict) else set()
suspicious = cp_keys & _CUSTOM_PROVIDER_LIKE_FIELDS
if suspicious:
issues.append(ConfigIssue(
"warning",
f"Root-level keys {sorted(suspicious)} look like custom_providers entry fields",
"These should be indented under a '- name: ...' list entry, not at root level",
))
elif isinstance(cp, list):
# Validate each entry in the list
for i, entry in enumerate(cp):
if not isinstance(entry, dict):
issues.append(ConfigIssue(
"warning",
f"custom_providers[{i}] is not a dict (got {type(entry).__name__})",
"Each entry should have at minimum: name, base_url",
))
continue
if not entry.get("name"):
issues.append(ConfigIssue(
"warning",
f"custom_providers[{i}] is missing 'name' field",
"Add a name, e.g.: name: my-provider",
))
if not entry.get("base_url"):
issues.append(ConfigIssue(
"warning",
f"custom_providers[{i}] is missing 'base_url' field",
"Add the API endpoint URL, e.g.: base_url: https://api.example.com/v1",
))
# ── fallback_model must be a top-level dict with provider + model ────
fb = config.get("fallback_model")
if fb is not None:
if not isinstance(fb, dict):
issues.append(ConfigIssue(
"error",
f"fallback_model should be a dict with 'provider' and 'model', got {type(fb).__name__}",
"Change to:\n"
" fallback_model:\n"
" provider: openrouter\n"
" model: anthropic/claude-sonnet-4",
))
elif fb:
if not fb.get("provider"):
issues.append(ConfigIssue(
"warning",
"fallback_model is missing 'provider' field — fallback will be disabled",
"Add: provider: openrouter (or another provider)",
))
if not fb.get("model"):
issues.append(ConfigIssue(
"warning",
"fallback_model is missing 'model' field — fallback will be disabled",
"Add: model: anthropic/claude-sonnet-4 (or another model)",
))
# ── Check for fallback_model accidentally nested inside custom_providers ──
if isinstance(cp, dict) and "fallback_model" not in config and "fallback_model" in (cp or {}):
issues.append(ConfigIssue(
"error",
"fallback_model appears inside custom_providers instead of at root level",
"Move fallback_model to the top level of config.yaml (no indentation)",
))
# ── model section: should exist when custom_providers is configured ──
model_cfg = config.get("model")
if cp and not model_cfg:
issues.append(ConfigIssue(
"warning",
"custom_providers defined but no 'model' section — Hermes won't know which provider to use",
"Add a model section:\n"
" model:\n"
" provider: custom\n"
" default: your-model-name\n"
" base_url: https://...",
))
# ── Root-level keys that look misplaced ──────────────────────────────
for key in config:
if key.startswith("_"):
continue
if key not in _KNOWN_ROOT_KEYS and key in _CUSTOM_PROVIDER_LIKE_FIELDS:
issues.append(ConfigIssue(
"warning",
f"Root-level key '{key}' looks misplaced — should it be under 'model:' or inside a 'custom_providers' entry?",
f"Move '{key}' under the appropriate section",
))
return issues
def print_config_warnings(config: Optional[Dict[str, Any]] = None) -> None:
"""Print config structure warnings to stderr at startup.
Called early in CLI and gateway init so users see problems before
they hit cryptic "Unknown provider" errors. Prints nothing if
config is healthy.
"""
try:
issues = validate_config_structure(config)
except Exception:
return
if not issues:
return
lines = ["\033[33m⚠ Config issues detected in config.yaml:\033[0m"]
for ci in issues:
marker = "\033[31m✗\033[0m" if ci.severity == "error" else "\033[33m⚠\033[0m"
lines.append(f" {marker} {ci.message}")
lines.append(" \033[2mRun 'hermes doctor' for fix suggestions.\033[0m")
sys.stderr.write("\n".join(lines) + "\n\n")
def warn_deprecated_cwd_env_vars(config: Optional[Dict[str, Any]] = None) -> None:
"""Warn if MESSAGING_CWD or TERMINAL_CWD is set in .env instead of config.yaml.
These env vars are deprecated the canonical setting is terminal.cwd
in config.yaml. Prints a migration hint to stderr.
"""
messaging_cwd = os.environ.get("MESSAGING_CWD")
terminal_cwd_env = os.environ.get("TERMINAL_CWD")
if config is None:
try:
config = load_config()
except Exception:
return
terminal_cfg = config.get("terminal", {})
config_cwd = terminal_cfg.get("cwd", ".") if isinstance(terminal_cfg, dict) else "."
# Only warn if config.yaml doesn't have an explicit path
config_has_explicit_cwd = config_cwd not in (".", "auto", "cwd", "")
lines: list[str] = []
if messaging_cwd:
lines.append(
f" \033[33m⚠\033[0m MESSAGING_CWD={messaging_cwd} found in .env — "
f"this is deprecated."
)
if terminal_cwd_env and not config_has_explicit_cwd:
# TERMINAL_CWD in env but not from config bridge — likely from .env
lines.append(
f" \033[33m⚠\033[0m TERMINAL_CWD={terminal_cwd_env} found in .env — "
f"this is deprecated."
)
if lines:
hint_path = os.environ.get("HERMES_HOME", "~/.hermes")
lines.insert(0, "\033[33m⚠ Deprecated .env settings detected:\033[0m")
lines.append(
f" \033[2mMove to config.yaml instead: "
f"terminal:\\n cwd: /your/project/path\033[0m"
)
lines.append(
f" \033[2mThen remove the old entries from {hint_path}/.env\033[0m"
)
sys.stderr.write("\n".join(lines) + "\n\n")
def migrate_config(interactive: bool = True, quiet: bool = False) -> Dict[str, Any]:
"""
Migrate config to latest version, prompting for new required fields.
Args:
interactive: If True, prompt user for missing values
quiet: If True, suppress output
Returns:
Dict with migration results: {"env_added": [...], "config_added": [...], "warnings": [...]}
"""
results = {"env_added": [], "config_added": [], "warnings": []}
# ── Always: sanitize .env (split concatenated keys) ──
try:
fixes = sanitize_env_file()
if fixes and not quiet:
print(f" ✓ Repaired .env file ({fixes} corrupted entries fixed)")
except Exception:
pass # best-effort; don't block migration on sanitize failure
# Check config version
current_ver, latest_ver = check_config_version()
# ── Version 3 → 4: migrate tool progress from .env to config.yaml ──
if current_ver < 4:
config = load_config()
display = config.get("display", {})
if not isinstance(display, dict):
display = {}
if "tool_progress" not in display:
old_enabled = get_env_value("HERMES_TOOL_PROGRESS")
old_mode = get_env_value("HERMES_TOOL_PROGRESS_MODE")
if old_enabled and old_enabled.lower() in ("false", "0", "no"):
display["tool_progress"] = "off"
results["config_added"].append("display.tool_progress=off (from HERMES_TOOL_PROGRESS=false)")
elif old_mode and old_mode.lower() in ("new", "all"):
display["tool_progress"] = old_mode.lower()
results["config_added"].append(f"display.tool_progress={old_mode.lower()} (from HERMES_TOOL_PROGRESS_MODE)")
else:
display["tool_progress"] = "all"
results["config_added"].append("display.tool_progress=all (default)")
config["display"] = display
save_config(config)
if not quiet:
print(f" ✓ Migrated tool progress to config.yaml: {display['tool_progress']}")
# ── Version 4 → 5: add timezone field ──
if current_ver < 5:
config = load_config()
if "timezone" not in config:
old_tz = os.getenv("HERMES_TIMEZONE", "")
if old_tz and old_tz.strip():
config["timezone"] = old_tz.strip()
results["config_added"].append(f"timezone={old_tz.strip()} (from HERMES_TIMEZONE)")
else:
config["timezone"] = ""
results["config_added"].append("timezone= (empty, uses server-local)")
save_config(config)
if not quiet:
tz_display = config["timezone"] or "(server-local)"
print(f" ✓ Added timezone to config.yaml: {tz_display}")
# ── Version 8 → 9: clear ANTHROPIC_TOKEN from .env ──
# The new Anthropic auth flow no longer uses this env var.
if current_ver < 9:
try:
old_token = get_env_value("ANTHROPIC_TOKEN")
if old_token:
save_env_value("ANTHROPIC_TOKEN", "")
if not quiet:
print(" ✓ Cleared ANTHROPIC_TOKEN from .env (no longer used)")
except Exception:
pass
# ── Version 11 → 12: migrate custom_providers list → providers dict ──
if current_ver < 12:
config = load_config()
custom_list = config.get("custom_providers")
if isinstance(custom_list, list) and custom_list:
providers_dict = config.get("providers", {})
if not isinstance(providers_dict, dict):
providers_dict = {}
migrated_count = 0
for entry in custom_list:
if not isinstance(entry, dict):
continue
old_name = entry.get("name", "")
old_url = entry.get("base_url", "") or entry.get("url", "") or ""
old_key = entry.get("api_key", "")
if not old_url:
continue # skip entries with no URL
# Generate a kebab-case key from the display name
key = old_name.strip().lower().replace(" ", "-").replace("(", "").replace(")", "")
# Remove consecutive hyphens and trailing hyphens
while "--" in key:
key = key.replace("--", "-")
key = key.strip("-")
if not key:
# Fallback: derive from URL hostname
try:
from urllib.parse import urlparse
parsed = urlparse(old_url)
key = (parsed.hostname or "endpoint").replace(".", "-")
except Exception:
key = f"endpoint-{migrated_count}"
# Don't overwrite existing entries
if key in providers_dict:
key = f"{key}-{migrated_count}"
new_entry = {"api": old_url}
if old_name:
new_entry["name"] = old_name
if old_key and old_key not in ("no-key", "no-key-required", ""):
new_entry["api_key"] = old_key
# Carry over model and api_mode if present
if entry.get("model"):
new_entry["default_model"] = entry["model"]
if entry.get("api_mode"):
new_entry["transport"] = entry["api_mode"]
providers_dict[key] = new_entry
migrated_count += 1
if migrated_count > 0:
config["providers"] = providers_dict
# Remove the old list — runtime reads via get_compatible_custom_providers()
config.pop("custom_providers", None)
save_config(config)
if not quiet:
print(f" ✓ Migrated {migrated_count} custom provider(s) to providers: section")
for key in list(providers_dict.keys())[-migrated_count:]:
ep = providers_dict[key]
print(f"{key}: {ep.get('api', '')}")
# ── Version 12 → 13: clear dead LLM_MODEL / OPENAI_MODEL from .env ──
# These env vars were written by the old setup wizard but nothing reads
# them anymore (config.yaml is the sole source of truth since March 2026).
# Stale entries cause user confusion — see issue report.
if current_ver < 13:
for dead_var in ("LLM_MODEL", "OPENAI_MODEL"):
try:
old_val = get_env_value(dead_var)
if old_val:
save_env_value(dead_var, "")
if not quiet:
print(f" ✓ Cleared {dead_var} from .env (no longer used — config.yaml is source of truth)")
except Exception:
pass
# ── Version 13 → 14: migrate legacy flat stt.model to provider section ──
# Old configs (and cli-config.yaml.example) had a flat `stt.model` key
# that was provider-agnostic. When the provider was "local" this caused
# OpenAI model names (e.g. "whisper-1") to be fed to faster-whisper,
# crashing with "Invalid model size". Move the value into the correct
# provider-specific section and remove the flat key.
if current_ver < 14:
# Read raw config (no defaults merged) to check what the user actually
# wrote, then apply changes to the merged config for saving.
raw = read_raw_config()
raw_stt = raw.get("stt", {})
if isinstance(raw_stt, dict) and "model" in raw_stt:
legacy_model = raw_stt["model"]
provider = raw_stt.get("provider", "local")
config = load_config()
stt = config.get("stt", {})
# Remove the legacy flat key
stt.pop("model", None)
# Place it in the appropriate provider section only if the
# user didn't already set a model there
if provider in ("local", "local_command"):
# Don't migrate an OpenAI model name into the local section
_local_models = {
"tiny.en", "tiny", "base.en", "base", "small.en", "small",
"medium.en", "medium", "large-v1", "large-v2", "large-v3",
"large", "distil-large-v2", "distil-medium.en",
"distil-small.en", "distil-large-v3", "distil-large-v3.5",
"large-v3-turbo", "turbo",
}
if legacy_model in _local_models:
# Check raw config — only set if user didn't already
# have a nested local.model
raw_local = raw_stt.get("local", {})
if not isinstance(raw_local, dict) or "model" not in raw_local:
local_cfg = stt.setdefault("local", {})
local_cfg["model"] = legacy_model
# else: drop it — it was an OpenAI model name, local section
# already defaults to "base" via DEFAULT_CONFIG
else:
# Cloud provider — put it in that provider's section only
# if user didn't already set a nested model
raw_provider = raw_stt.get(provider, {})
if not isinstance(raw_provider, dict) or "model" not in raw_provider:
provider_cfg = stt.setdefault(provider, {})
provider_cfg["model"] = legacy_model
config["stt"] = stt
save_config(config)
if not quiet:
print(f" ✓ Migrated legacy stt.model to provider-specific config")
# ── Version 14 → 15: add explicit gateway interim-message gate ──
if current_ver < 15:
config = read_raw_config()
display = config.get("display", {})
if not isinstance(display, dict):
display = {}
if "interim_assistant_messages" not in display:
display["interim_assistant_messages"] = True
config["display"] = display
results["config_added"].append("display.interim_assistant_messages=true (default)")
save_config(config)
if not quiet:
print(" ✓ Added display.interim_assistant_messages=true")
feat: per-platform display verbosity configuration (#8006) Add display.platforms section to config.yaml for per-platform overrides of display settings (tool_progress, show_reasoning, streaming, tool_preview_length). Each platform gets sensible built-in defaults based on capability tier: - High (telegram, discord): tool_progress=all, streaming follows global - Medium (slack, mattermost, matrix, feishu): tool_progress=new - Low (signal, whatsapp, bluebubbles, wecom, etc.): tool_progress=off, streaming=false - Minimal (email, sms, webhook, homeassistant): tool_progress=off, streaming=false Example config: display: platforms: telegram: tool_progress: all show_reasoning: true slack: tool_progress: off Resolution order: platform override > global setting > built-in platform default. Changes: - New gateway/display_config.py: resolver module with tier-based platform defaults - gateway/run.py: tool_progress, tool_preview_length, streaming, show_reasoning all resolve per-platform via the new resolver - /verbose command: now cycles tool_progress per-platform (saves to display.platforms.<platform>.tool_progress instead of global) - /reasoning show|hide: now saves show_reasoning per-platform - Config version 15 -> 16: migrates tool_progress_overrides into display.platforms - Backward compat: legacy tool_progress_overrides still read as fallback - 27 new tests for resolver, normalization, migration, backward compat - Updated verbose command tests for per-platform behavior Addresses community request for per-channel verbosity control (Guillaume Meyer, Nathan Danielsen) — high verbosity on backchannel Telegram, low on customer-facing Slack, none on email.
2026-04-11 17:20:34 -07:00
# ── Version 15 → 16: migrate tool_progress_overrides into display.platforms ──
if current_ver < 16:
config = read_raw_config()
display = config.get("display", {})
if not isinstance(display, dict):
display = {}
old_overrides = display.get("tool_progress_overrides")
if isinstance(old_overrides, dict) and old_overrides:
platforms = display.get("platforms", {})
if not isinstance(platforms, dict):
platforms = {}
for plat, mode in old_overrides.items():
if plat not in platforms:
platforms[plat] = {}
if "tool_progress" not in platforms[plat]:
platforms[plat]["tool_progress"] = mode
display["platforms"] = platforms
config["display"] = display
save_config(config)
if not quiet:
migrated = ", ".join(f"{p}={m}" for p, m in old_overrides.items())
print(f" ✓ Migrated tool_progress_overrides → display.platforms: {migrated}")
results["config_added"].append("display.platforms (migrated from tool_progress_overrides)")
# ── Version 16 → 17: remove legacy compression.summary_* keys ──
if current_ver < 17:
config = read_raw_config()
comp = config.get("compression", {})
if isinstance(comp, dict):
s_model = comp.pop("summary_model", None)
s_provider = comp.pop("summary_provider", None)
s_base_url = comp.pop("summary_base_url", None)
migrated_keys = []
# Migrate non-empty, non-default values to auxiliary.compression
if s_model and str(s_model).strip():
aux = config.setdefault("auxiliary", {})
aux_comp = aux.setdefault("compression", {})
if not aux_comp.get("model"):
aux_comp["model"] = str(s_model).strip()
migrated_keys.append(f"model={s_model}")
if s_provider and str(s_provider).strip() not in ("", "auto"):
aux = config.setdefault("auxiliary", {})
aux_comp = aux.setdefault("compression", {})
if not aux_comp.get("provider") or aux_comp.get("provider") == "auto":
aux_comp["provider"] = str(s_provider).strip()
migrated_keys.append(f"provider={s_provider}")
if s_base_url and str(s_base_url).strip():
aux = config.setdefault("auxiliary", {})
aux_comp = aux.setdefault("compression", {})
if not aux_comp.get("base_url"):
aux_comp["base_url"] = str(s_base_url).strip()
migrated_keys.append(f"base_url={s_base_url}")
if migrated_keys or s_model is not None or s_provider is not None or s_base_url is not None:
config["compression"] = comp
save_config(config)
if not quiet:
if migrated_keys:
print(f" ✓ Migrated compression.summary_* → auxiliary.compression: {', '.join(migrated_keys)}")
else:
print(" ✓ Removed unused compression.summary_* keys")
feat(plugins): make all plugins opt-in by default Plugins now require explicit consent to load. Discovery still finds every plugin — user-installed, bundled, and pip — so they all show up in `hermes plugins` and `/plugins`, but the loader only instantiates plugins whose name appears in `plugins.enabled` in config.yaml. This removes the previous ambient-execution risk where a newly-installed or bundled plugin could register hooks, tools, and commands on first run without the user opting in. The three-state model is now explicit: enabled — in plugins.enabled, loads on next session disabled — in plugins.disabled, never loads (wins over enabled) not enabled — discovered but never opted in (default for new installs) `hermes plugins install <repo>` prompts "Enable 'name' now? [y/N]" (defaults to no). New `--enable` / `--no-enable` flags skip the prompt for scripted installs. `hermes plugins enable/disable` manage both lists so a disabled plugin stays explicitly off even if something later adds it to enabled. Config migration (schema v20 → v21): existing user plugins already installed under ~/.hermes/plugins/ (minus anything in plugins.disabled) are auto-grandfathered into plugins.enabled so upgrades don't silently break working setups. Bundled plugins are NOT grandfathered — even existing users have to opt in explicitly. Also: HERMES_DISABLE_BUNDLED_PLUGINS env var removed (redundant with opt-in default), cmd_list now shows bundled + user plugins together with their three-state status, interactive UI tags bundled entries [bundled], docs updated across plugins.md and built-in-plugins.md. Validation: 442 plugin/config tests pass. E2E: fresh install discovers disk-cleanup but does not load it; `hermes plugins enable disk-cleanup` activates hooks; migration grandfathers existing user plugins correctly while leaving bundled plugins off.
2026-04-20 04:40:17 -07:00
# ── Version 20 → 21: plugins are now opt-in; grandfather existing user plugins ──
# The loader now requires plugins to appear in ``plugins.enabled`` before
# loading. Existing installs had all discovered plugins loading by default
# (minus anything in ``plugins.disabled``). To avoid silently breaking
# those setups on upgrade, populate ``plugins.enabled`` with the set of
# currently-installed user plugins that aren't already disabled.
#
# Bundled plugins (shipped in the repo itself) are NOT grandfathered —
# they ship off for everyone, including existing users, so any user who
# wants one has to opt in explicitly.
if current_ver < 21:
config = read_raw_config()
plugins_cfg = config.get("plugins")
if not isinstance(plugins_cfg, dict):
plugins_cfg = {}
# Only migrate if the enabled allow-list hasn't been set yet.
if "enabled" not in plugins_cfg:
disabled = plugins_cfg.get("disabled", []) or []
if not isinstance(disabled, list):
disabled = []
disabled_set = set(disabled)
# Scan ``$HERMES_HOME/plugins/`` for currently installed user plugins.
grandfathered: List[str] = []
try:
refactor: remove remaining redundant local imports (comprehensive sweep) Full AST-based scan of all .py files to find every case where a module or name is imported locally inside a function body but is already available at module level. This is the second pass — the first commit handled the known cases from the lint report; this one catches everything else. Files changed (19): cli.py — 16 removals: time as _time/_t/_tmod (×10), re / re as _re (×2), os as _os, sys, partial os from combo import, from model_tools import get_tool_definitions gateway/run.py — 8 removals: MessageEvent as _ME / MessageType as _MT (×3), os as _os2, MessageEvent+MessageType (×2), Platform, BasePlatformAdapter as _BaseAdapter run_agent.py — 6 removals: get_hermes_home as _ghh, partial (contextlib, os as _os), cleanup_vm, cleanup_browser, set_interrupt as _sif (×2), partial get_toolset_for_tool hermes_cli/main.py — 4 removals: get_hermes_home, time as _time, logging as _log, shutil hermes_cli/config.py — 1 removal: get_hermes_home as _ghome hermes_cli/runtime_provider.py — 1 removal: load_config as _load_bedrock_config hermes_cli/setup.py — 2 removals: importlib.util (×2) hermes_cli/nous_subscription.py — 1 removal: from hermes_cli.config import load_config hermes_cli/tools_config.py — 1 removal: from hermes_cli.config import load_config, save_config cron/scheduler.py — 3 removals: concurrent.futures, json as _json, from hermes_cli.config import load_config batch_runner.py — 1 removal: list_distributions as get_all_dists (kept print_distribution_info, not at top level) tools/send_message_tool.py — 2 removals: import os (×2) tools/skills_tool.py — 1 removal: logging as _logging tools/browser_camofox.py — 1 removal: from hermes_cli.config import load_config tools/image_generation_tool.py — 1 removal: import fal_client environments/tool_context.py — 1 removal: concurrent.futures gateway/platforms/bluebubbles.py — 1 removal: httpx as _httpx gateway/platforms/whatsapp.py — 1 removal: import asyncio tui_gateway/server.py — 2 removals: from datetime import datetime, import time All alias references (_time, _t, _tmod, _re, _os, _os2, _json, _ghh, _ghome, _sif, _ME, _MT, _BaseAdapter, _load_bedrock_config, _httpx, _logging, _log, get_all_dists) updated to use the top-level names.
2026-04-21 12:46:31 +05:30
user_plugins_dir = get_hermes_home() / "plugins"
feat(plugins): make all plugins opt-in by default Plugins now require explicit consent to load. Discovery still finds every plugin — user-installed, bundled, and pip — so they all show up in `hermes plugins` and `/plugins`, but the loader only instantiates plugins whose name appears in `plugins.enabled` in config.yaml. This removes the previous ambient-execution risk where a newly-installed or bundled plugin could register hooks, tools, and commands on first run without the user opting in. The three-state model is now explicit: enabled — in plugins.enabled, loads on next session disabled — in plugins.disabled, never loads (wins over enabled) not enabled — discovered but never opted in (default for new installs) `hermes plugins install <repo>` prompts "Enable 'name' now? [y/N]" (defaults to no). New `--enable` / `--no-enable` flags skip the prompt for scripted installs. `hermes plugins enable/disable` manage both lists so a disabled plugin stays explicitly off even if something later adds it to enabled. Config migration (schema v20 → v21): existing user plugins already installed under ~/.hermes/plugins/ (minus anything in plugins.disabled) are auto-grandfathered into plugins.enabled so upgrades don't silently break working setups. Bundled plugins are NOT grandfathered — even existing users have to opt in explicitly. Also: HERMES_DISABLE_BUNDLED_PLUGINS env var removed (redundant with opt-in default), cmd_list now shows bundled + user plugins together with their three-state status, interactive UI tags bundled entries [bundled], docs updated across plugins.md and built-in-plugins.md. Validation: 442 plugin/config tests pass. E2E: fresh install discovers disk-cleanup but does not load it; `hermes plugins enable disk-cleanup` activates hooks; migration grandfathers existing user plugins correctly while leaving bundled plugins off.
2026-04-20 04:40:17 -07:00
if user_plugins_dir.is_dir():
for child in sorted(user_plugins_dir.iterdir()):
if not child.is_dir():
continue
manifest_file = child / "plugin.yaml"
if not manifest_file.exists():
manifest_file = child / "plugin.yml"
if not manifest_file.exists():
continue
try:
with open(manifest_file) as _mf:
manifest = yaml.safe_load(_mf) or {}
except Exception:
manifest = {}
name = manifest.get("name") or child.name
if name in disabled_set:
continue
grandfathered.append(name)
except Exception:
grandfathered = []
plugins_cfg["enabled"] = grandfathered
config["plugins"] = plugins_cfg
save_config(config)
results["config_added"].append(
f"plugins.enabled (opt-in allow-list, {len(grandfathered)} grandfathered)"
)
if not quiet:
if grandfathered:
print(
f" ✓ Plugins now opt-in: grandfathered "
f"{len(grandfathered)} existing plugin(s) into plugins.enabled"
)
else:
print(
" ✓ Plugins now opt-in: no existing plugins to grandfather. "
"Use `hermes plugins enable <name>` to activate."
)
if current_ver < latest_ver and not quiet:
print(f"Config version: {current_ver}{latest_ver}")
# Check for missing required env vars
missing_env = get_missing_env_vars(required_only=True)
if missing_env and not quiet:
print("\n⚠️ Missing required environment variables:")
for var in missing_env:
print(f"{var['name']}: {var['description']}")
if interactive and missing_env:
print("\nLet's configure them now:\n")
for var in missing_env:
if var.get("url"):
print(f" Get your key at: {var['url']}")
if var.get("password"):
import getpass
value = getpass.getpass(f" {var['prompt']}: ")
else:
value = input(f" {var['prompt']}: ").strip()
if value:
save_env_value(var["name"], value)
results["env_added"].append(var["name"])
print(f" ✓ Saved {var['name']}")
else:
results["warnings"].append(f"Skipped {var['name']} - some features may not work")
print()
# Check for missing optional env vars and offer to configure interactively
# Skip "advanced" vars (like OPENAI_BASE_URL) -- those are for power users
Add messaging platform enhancements: STT, stickers, Discord UX, Slack, pairing, hooks Major feature additions inspired by OpenClaw/ClawdBot integration analysis: Voice Message Transcription (STT): - Auto-transcribe voice/audio messages via OpenAI Whisper API - Download voice to ~/.hermes/audio_cache/ on Telegram/Discord/WhatsApp - Inject transcript as text so all models can understand voice input - Configurable model (whisper-1, gpt-4o-mini-transcribe, gpt-4o-transcribe) Telegram Sticker Understanding: - Describe static stickers via vision tool with JSON-backed cache - Cache keyed by file_unique_id avoids redundant API calls - Animated/video stickers get emoji-based fallback description Discord Rich UX: - Native slash commands (/ask, /reset, /status, /stop) via app_commands - Button-based exec approvals (Allow Once / Always Allow / Deny) - ExecApprovalView with user authorization and timeout handling Slack Integration: - Full SlackAdapter using slack-bolt with Socket Mode - DMs, channel messages (mention-gated), /hermes slash command - File attachment handling with bot-token-authenticated downloads DM Pairing System: - Code-based user authorization as alternative to static allowlists - 8-char codes from unambiguous alphabet, 1-hour expiry - Rate limiting, lockout after failed attempts, chmod 0600 on data - CLI: hermes pairing list/approve/revoke/clear-pending Event Hook System: - File-based hook discovery from ~/.hermes/hooks/ - HOOK.yaml + handler.py per hook, sync/async handler support - Events: gateway:startup, session:start/reset, agent:start/step/end - Wildcard matching (command:* catches all command events) Cross-Channel Messaging: - send_message agent tool for delivering to any connected platform - Enables cron job delivery and cross-platform notifications Human-Like Response Pacing: - Configurable delays between message chunks (off/natural/custom) - HERMES_HUMAN_DELAY_MODE env var with min/max ms settings Warm Injection Message Style: - Retrofitted image vision messages with friendly kawaii-consistent tone - All new injection messages (STT, stickers, errors) use warm style Also: updated config migration to prompt for optional keys interactively, bumped config version, updated README, AGENTS.md, .env.example, cli-config.yaml.example, install scripts, pyproject.toml, and toolsets.
2026-02-15 21:38:59 -08:00
missing_optional = get_missing_env_vars(required_only=False)
required_names = {v["name"] for v in missing_env} if missing_env else set()
missing_optional = [
v for v in missing_optional
if v["name"] not in required_names and not v.get("advanced")
]
Add messaging platform enhancements: STT, stickers, Discord UX, Slack, pairing, hooks Major feature additions inspired by OpenClaw/ClawdBot integration analysis: Voice Message Transcription (STT): - Auto-transcribe voice/audio messages via OpenAI Whisper API - Download voice to ~/.hermes/audio_cache/ on Telegram/Discord/WhatsApp - Inject transcript as text so all models can understand voice input - Configurable model (whisper-1, gpt-4o-mini-transcribe, gpt-4o-transcribe) Telegram Sticker Understanding: - Describe static stickers via vision tool with JSON-backed cache - Cache keyed by file_unique_id avoids redundant API calls - Animated/video stickers get emoji-based fallback description Discord Rich UX: - Native slash commands (/ask, /reset, /status, /stop) via app_commands - Button-based exec approvals (Allow Once / Always Allow / Deny) - ExecApprovalView with user authorization and timeout handling Slack Integration: - Full SlackAdapter using slack-bolt with Socket Mode - DMs, channel messages (mention-gated), /hermes slash command - File attachment handling with bot-token-authenticated downloads DM Pairing System: - Code-based user authorization as alternative to static allowlists - 8-char codes from unambiguous alphabet, 1-hour expiry - Rate limiting, lockout after failed attempts, chmod 0600 on data - CLI: hermes pairing list/approve/revoke/clear-pending Event Hook System: - File-based hook discovery from ~/.hermes/hooks/ - HOOK.yaml + handler.py per hook, sync/async handler support - Events: gateway:startup, session:start/reset, agent:start/step/end - Wildcard matching (command:* catches all command events) Cross-Channel Messaging: - send_message agent tool for delivering to any connected platform - Enables cron job delivery and cross-platform notifications Human-Like Response Pacing: - Configurable delays between message chunks (off/natural/custom) - HERMES_HUMAN_DELAY_MODE env var with min/max ms settings Warm Injection Message Style: - Retrofitted image vision messages with friendly kawaii-consistent tone - All new injection messages (STT, stickers, errors) use warm style Also: updated config migration to prompt for optional keys interactively, bumped config version, updated README, AGENTS.md, .env.example, cli-config.yaml.example, install scripts, pyproject.toml, and toolsets.
2026-02-15 21:38:59 -08:00
# Only offer to configure env vars that are NEW since the user's previous version
new_var_names = set()
for ver in range(current_ver + 1, latest_ver + 1):
new_var_names.update(ENV_VARS_BY_VERSION.get(ver, []))
if new_var_names and interactive and not quiet:
new_and_unset = [
(name, OPTIONAL_ENV_VARS[name])
for name in sorted(new_var_names)
if not get_env_value(name) and name in OPTIONAL_ENV_VARS
]
if new_and_unset:
print(f"\n {len(new_and_unset)} new optional key(s) in this update:")
for name, info in new_and_unset:
print(f"{name}{info.get('description', '')}")
Add messaging platform enhancements: STT, stickers, Discord UX, Slack, pairing, hooks Major feature additions inspired by OpenClaw/ClawdBot integration analysis: Voice Message Transcription (STT): - Auto-transcribe voice/audio messages via OpenAI Whisper API - Download voice to ~/.hermes/audio_cache/ on Telegram/Discord/WhatsApp - Inject transcript as text so all models can understand voice input - Configurable model (whisper-1, gpt-4o-mini-transcribe, gpt-4o-transcribe) Telegram Sticker Understanding: - Describe static stickers via vision tool with JSON-backed cache - Cache keyed by file_unique_id avoids redundant API calls - Animated/video stickers get emoji-based fallback description Discord Rich UX: - Native slash commands (/ask, /reset, /status, /stop) via app_commands - Button-based exec approvals (Allow Once / Always Allow / Deny) - ExecApprovalView with user authorization and timeout handling Slack Integration: - Full SlackAdapter using slack-bolt with Socket Mode - DMs, channel messages (mention-gated), /hermes slash command - File attachment handling with bot-token-authenticated downloads DM Pairing System: - Code-based user authorization as alternative to static allowlists - 8-char codes from unambiguous alphabet, 1-hour expiry - Rate limiting, lockout after failed attempts, chmod 0600 on data - CLI: hermes pairing list/approve/revoke/clear-pending Event Hook System: - File-based hook discovery from ~/.hermes/hooks/ - HOOK.yaml + handler.py per hook, sync/async handler support - Events: gateway:startup, session:start/reset, agent:start/step/end - Wildcard matching (command:* catches all command events) Cross-Channel Messaging: - send_message agent tool for delivering to any connected platform - Enables cron job delivery and cross-platform notifications Human-Like Response Pacing: - Configurable delays between message chunks (off/natural/custom) - HERMES_HUMAN_DELAY_MODE env var with min/max ms settings Warm Injection Message Style: - Retrofitted image vision messages with friendly kawaii-consistent tone - All new injection messages (STT, stickers, errors) use warm style Also: updated config migration to prompt for optional keys interactively, bumped config version, updated README, AGENTS.md, .env.example, cli-config.yaml.example, install scripts, pyproject.toml, and toolsets.
2026-02-15 21:38:59 -08:00
print()
try:
answer = input(" Configure new keys? [y/N]: ").strip().lower()
except (EOFError, KeyboardInterrupt):
answer = "n"
if answer in ("y", "yes"):
Add messaging platform enhancements: STT, stickers, Discord UX, Slack, pairing, hooks Major feature additions inspired by OpenClaw/ClawdBot integration analysis: Voice Message Transcription (STT): - Auto-transcribe voice/audio messages via OpenAI Whisper API - Download voice to ~/.hermes/audio_cache/ on Telegram/Discord/WhatsApp - Inject transcript as text so all models can understand voice input - Configurable model (whisper-1, gpt-4o-mini-transcribe, gpt-4o-transcribe) Telegram Sticker Understanding: - Describe static stickers via vision tool with JSON-backed cache - Cache keyed by file_unique_id avoids redundant API calls - Animated/video stickers get emoji-based fallback description Discord Rich UX: - Native slash commands (/ask, /reset, /status, /stop) via app_commands - Button-based exec approvals (Allow Once / Always Allow / Deny) - ExecApprovalView with user authorization and timeout handling Slack Integration: - Full SlackAdapter using slack-bolt with Socket Mode - DMs, channel messages (mention-gated), /hermes slash command - File attachment handling with bot-token-authenticated downloads DM Pairing System: - Code-based user authorization as alternative to static allowlists - 8-char codes from unambiguous alphabet, 1-hour expiry - Rate limiting, lockout after failed attempts, chmod 0600 on data - CLI: hermes pairing list/approve/revoke/clear-pending Event Hook System: - File-based hook discovery from ~/.hermes/hooks/ - HOOK.yaml + handler.py per hook, sync/async handler support - Events: gateway:startup, session:start/reset, agent:start/step/end - Wildcard matching (command:* catches all command events) Cross-Channel Messaging: - send_message agent tool for delivering to any connected platform - Enables cron job delivery and cross-platform notifications Human-Like Response Pacing: - Configurable delays between message chunks (off/natural/custom) - HERMES_HUMAN_DELAY_MODE env var with min/max ms settings Warm Injection Message Style: - Retrofitted image vision messages with friendly kawaii-consistent tone - All new injection messages (STT, stickers, errors) use warm style Also: updated config migration to prompt for optional keys interactively, bumped config version, updated README, AGENTS.md, .env.example, cli-config.yaml.example, install scripts, pyproject.toml, and toolsets.
2026-02-15 21:38:59 -08:00
print()
for name, info in new_and_unset:
if info.get("url"):
print(f" {info.get('description', name)}")
print(f" Get your key at: {info['url']}")
else:
print(f" {info.get('description', name)}")
if info.get("password"):
import getpass
value = getpass.getpass(f" {info.get('prompt', name)} (Enter to skip): ")
else:
value = input(f" {info.get('prompt', name)} (Enter to skip): ").strip()
if value:
save_env_value(name, value)
results["env_added"].append(name)
print(f" ✓ Saved {name}")
print()
else:
print(" Set later with: hermes config set <key> <value>")
Add messaging platform enhancements: STT, stickers, Discord UX, Slack, pairing, hooks Major feature additions inspired by OpenClaw/ClawdBot integration analysis: Voice Message Transcription (STT): - Auto-transcribe voice/audio messages via OpenAI Whisper API - Download voice to ~/.hermes/audio_cache/ on Telegram/Discord/WhatsApp - Inject transcript as text so all models can understand voice input - Configurable model (whisper-1, gpt-4o-mini-transcribe, gpt-4o-transcribe) Telegram Sticker Understanding: - Describe static stickers via vision tool with JSON-backed cache - Cache keyed by file_unique_id avoids redundant API calls - Animated/video stickers get emoji-based fallback description Discord Rich UX: - Native slash commands (/ask, /reset, /status, /stop) via app_commands - Button-based exec approvals (Allow Once / Always Allow / Deny) - ExecApprovalView with user authorization and timeout handling Slack Integration: - Full SlackAdapter using slack-bolt with Socket Mode - DMs, channel messages (mention-gated), /hermes slash command - File attachment handling with bot-token-authenticated downloads DM Pairing System: - Code-based user authorization as alternative to static allowlists - 8-char codes from unambiguous alphabet, 1-hour expiry - Rate limiting, lockout after failed attempts, chmod 0600 on data - CLI: hermes pairing list/approve/revoke/clear-pending Event Hook System: - File-based hook discovery from ~/.hermes/hooks/ - HOOK.yaml + handler.py per hook, sync/async handler support - Events: gateway:startup, session:start/reset, agent:start/step/end - Wildcard matching (command:* catches all command events) Cross-Channel Messaging: - send_message agent tool for delivering to any connected platform - Enables cron job delivery and cross-platform notifications Human-Like Response Pacing: - Configurable delays between message chunks (off/natural/custom) - HERMES_HUMAN_DELAY_MODE env var with min/max ms settings Warm Injection Message Style: - Retrofitted image vision messages with friendly kawaii-consistent tone - All new injection messages (STT, stickers, errors) use warm style Also: updated config migration to prompt for optional keys interactively, bumped config version, updated README, AGENTS.md, .env.example, cli-config.yaml.example, install scripts, pyproject.toml, and toolsets.
2026-02-15 21:38:59 -08:00
# Check for missing config fields
missing_config = get_missing_config_fields()
if missing_config:
config = load_config()
for field in missing_config:
key = field["key"]
default = field["default"]
_set_nested(config, key, default)
results["config_added"].append(key)
if not quiet:
print(f" ✓ Added {key} = {default}")
# Update version and save
config["_config_version"] = latest_ver
save_config(config)
elif current_ver < latest_ver:
# Just update version
config = load_config()
config["_config_version"] = latest_ver
save_config(config)
# ── Skill-declared config vars ──────────────────────────────────────
# Skills can declare config.yaml settings they need via
# metadata.hermes.config in their SKILL.md frontmatter.
# Prompt for any that are missing/empty.
missing_skill_config = get_missing_skill_config_vars()
if missing_skill_config and interactive and not quiet:
print(f"\n {len(missing_skill_config)} skill setting(s) not configured:")
for var in missing_skill_config:
skill_name = var.get("skill", "unknown")
print(f"{var['key']}{var['description']} (from skill: {skill_name})")
print()
try:
answer = input(" Configure skill settings? [y/N]: ").strip().lower()
except (EOFError, KeyboardInterrupt):
answer = "n"
if answer in ("y", "yes"):
print()
config = load_config()
try:
from agent.skill_utils import SKILL_CONFIG_PREFIX
except Exception:
SKILL_CONFIG_PREFIX = "skills.config"
for var in missing_skill_config:
default = var.get("default", "")
default_hint = f" (default: {default})" if default else ""
value = input(f" {var['prompt']}{default_hint}: ").strip()
if not value and default:
value = str(default)
if value:
storage_key = f"{SKILL_CONFIG_PREFIX}.{var['key']}"
_set_nested(config, storage_key, value)
results["config_added"].append(var["key"])
print(f" ✓ Saved {var['key']} = {value}")
else:
results["warnings"].append(
f"Skipped {var['key']} — skill '{var.get('skill', '?')}' may ask for it later"
)
print()
save_config(config)
else:
print(" Set later with: hermes config set <key> <value>")
return results
def _deep_merge(base: dict, override: dict) -> dict:
"""Recursively merge *override* into *base*, preserving nested defaults.
Keys in *override* take precedence. If both values are dicts the merge
recurses, so a user who overrides only ``tts.elevenlabs.voice_id`` will
keep the default ``tts.elevenlabs.model_id`` intact.
"""
result = base.copy()
for key, value in override.items():
if (
key in result
and isinstance(result[key], dict)
and isinstance(value, dict)
):
result[key] = _deep_merge(result[key], value)
else:
result[key] = value
return result
def _expand_env_vars(obj):
"""Recursively expand ``${VAR}`` references in config values.
Only string values are processed; dict keys, numbers, booleans, and
None are left untouched. Unresolved references (variable not in
``os.environ``) are kept verbatim so callers can detect them.
"""
if isinstance(obj, str):
return re.sub(
r"\${([^}]+)}",
lambda m: os.environ.get(m.group(1), m.group(0)),
obj,
)
if isinstance(obj, dict):
return {k: _expand_env_vars(v) for k, v in obj.items()}
if isinstance(obj, list):
return [_expand_env_vars(item) for item in obj]
return obj
def _items_by_unique_name(items):
"""Return a name-indexed dict only when all items have unique string names."""
if not isinstance(items, list):
return None
indexed = {}
for item in items:
if not isinstance(item, dict) or not isinstance(item.get("name"), str):
return None
name = item["name"]
if name in indexed:
return None
indexed[name] = item
return indexed
def _preserve_env_ref_templates(current, raw, loaded_expanded=None):
"""Restore raw ``${VAR}`` templates when a value is otherwise unchanged.
``load_config()`` expands env refs for runtime use. When a caller later
persists that config after modifying some unrelated setting, keep the
original on-disk template instead of writing the expanded plaintext
secret back to ``config.yaml``.
Prefer preserving the raw template when ``current`` still matches either
the value previously returned by ``load_config()`` for this config path or
the current environment expansion of ``raw``. This handles env-var
rotation between load and save while still treating mixed literal/template
string edits as caller-owned once their rendered value diverges.
"""
if isinstance(current, str) and isinstance(raw, str) and re.search(r"\${[^}]+}", raw):
if current == raw:
return raw
if isinstance(loaded_expanded, str) and current == loaded_expanded:
return raw
if _expand_env_vars(raw) == current:
return raw
return current
if isinstance(current, dict) and isinstance(raw, dict):
return {
key: _preserve_env_ref_templates(
value,
raw.get(key),
loaded_expanded.get(key) if isinstance(loaded_expanded, dict) else None,
)
for key, value in current.items()
}
if isinstance(current, list) and isinstance(raw, list):
# Prefer matching named config objects (e.g. custom_providers) by name
# so harmless reordering doesn't drop the original template. If names
# are duplicated, fall back to positional matching instead of silently
# shadowing one entry.
current_by_name = _items_by_unique_name(current)
raw_by_name = _items_by_unique_name(raw)
loaded_by_name = _items_by_unique_name(loaded_expanded)
if current_by_name is not None and raw_by_name is not None:
return [
_preserve_env_ref_templates(
item,
raw_by_name.get(item.get("name")),
loaded_by_name.get(item.get("name")) if loaded_by_name is not None else None,
)
for item in current
]
return [
_preserve_env_ref_templates(
item,
raw[index] if index < len(raw) else None,
loaded_expanded[index]
if isinstance(loaded_expanded, list) and index < len(loaded_expanded)
else None,
)
for index, item in enumerate(current)
]
return current
def _normalize_root_model_keys(config: Dict[str, Any]) -> Dict[str, Any]:
"""Move stale root-level provider/base_url into model section.
Some users (or older code) placed ``provider:`` and ``base_url:`` at the
config root instead of inside ``model:``. These root-level keys are only
used as a fallback when the corresponding ``model.*`` key is empty they
never override an existing ``model.provider`` or ``model.base_url``.
After migration the root-level keys are removed so they can't cause
confusion on subsequent loads.
"""
# Only act if there are root-level keys to migrate
has_root = any(config.get(k) for k in ("provider", "base_url"))
if not has_root:
return config
config = dict(config)
model = config.get("model")
if not isinstance(model, dict):
model = {"default": model} if model else {}
config["model"] = model
for key in ("provider", "base_url"):
root_val = config.get(key)
if root_val and not model.get(key):
model[key] = root_val
config.pop(key, None)
return config
2026-03-07 21:01:23 -08:00
def _normalize_max_turns_config(config: Dict[str, Any]) -> Dict[str, Any]:
"""Normalize legacy root-level max_turns into agent.max_turns."""
config = dict(config)
agent_config = dict(config.get("agent") or {})
if "max_turns" in config and "max_turns" not in agent_config:
agent_config["max_turns"] = config["max_turns"]
if "max_turns" not in agent_config:
agent_config["max_turns"] = DEFAULT_CONFIG["agent"]["max_turns"]
config["agent"] = agent_config
config.pop("max_turns", None)
return config
def read_raw_config() -> Dict[str, Any]:
"""Read ~/.hermes/config.yaml as-is, without merging defaults or migrating.
Returns the raw YAML dict, or ``{}`` if the file doesn't exist or can't
be parsed. Use this for lightweight config reads where you just need a
single value and don't want the overhead of ``load_config()``'s deep-merge
+ migration pipeline.
"""
try:
config_path = get_config_path()
if config_path.exists():
with open(config_path, encoding="utf-8") as f:
return yaml.safe_load(f) or {}
except Exception:
pass
return {}
def load_config() -> Dict[str, Any]:
"""Load configuration from ~/.hermes/config.yaml."""
ensure_hermes_home()
config_path = get_config_path()
config = copy.deepcopy(DEFAULT_CONFIG)
if config_path.exists():
try:
with open(config_path, encoding="utf-8") as f:
user_config = yaml.safe_load(f) or {}
2026-03-07 21:01:23 -08:00
if "max_turns" in user_config:
agent_user_config = dict(user_config.get("agent") or {})
if agent_user_config.get("max_turns") is None:
agent_user_config["max_turns"] = user_config["max_turns"]
user_config["agent"] = agent_user_config
user_config.pop("max_turns", None)
config = _deep_merge(config, user_config)
except Exception as e:
print(f"Warning: Failed to load config: {e}")
normalized = _normalize_root_model_keys(_normalize_max_turns_config(config))
expanded = _expand_env_vars(normalized)
_LAST_EXPANDED_CONFIG_BY_PATH[str(config_path)] = copy.deepcopy(expanded)
return expanded
feat(security): add tirith pre-exec command scanning Integrate tirith as a pre-execution security scanner that detects homograph URLs, pipe-to-interpreter patterns, terminal injection, zero-width Unicode, and environment variable manipulation — threats the existing 50-pattern dangerous command detector doesn't cover. Architecture: gather-then-decide — both tirith and the dangerous command detector run before any approval prompt, preventing gateway force=True replay from bypassing one check when only the other was shown to the user. New files: - tools/tirith_security.py: subprocess wrapper with auto-installer, mandatory cosign provenance verification, non-blocking background download, disk-persistent failure markers with retryable-cause tracking (cosign_missing auto-clears when cosign appears on PATH) - tests/tools/test_tirith_security.py: 62 tests covering exit code mapping, fail_open, cosign verification, background install, HERMES_HOME isolation, and failure recovery - tests/tools/test_command_guards.py: 21 integration tests for the combined guard orchestration Modified files: - tools/approval.py: add check_all_command_guards() orchestrator, add allow_permanent parameter to prompt_dangerous_approval() - tools/terminal_tool.py: replace _check_dangerous_command with consolidated check_all_command_guards - cli.py: update _approval_callback for allow_permanent kwarg, call ensure_installed() at startup - gateway/run.py: iterate pattern_keys list on replay approval, call ensure_installed() at startup - hermes_cli/config.py: add security config defaults, split commented sections for independent fallback - cli-config.yaml.example: document tirith security config
2026-03-11 14:20:32 +05:30
_SECURITY_COMMENT = """
# ── Security ──────────────────────────────────────────────────────────
# API keys, tokens, and passwords are redacted from tool output by default.
# Set to false to see full values (useful for debugging auth issues).
feat(security): add tirith pre-exec command scanning Integrate tirith as a pre-execution security scanner that detects homograph URLs, pipe-to-interpreter patterns, terminal injection, zero-width Unicode, and environment variable manipulation — threats the existing 50-pattern dangerous command detector doesn't cover. Architecture: gather-then-decide — both tirith and the dangerous command detector run before any approval prompt, preventing gateway force=True replay from bypassing one check when only the other was shown to the user. New files: - tools/tirith_security.py: subprocess wrapper with auto-installer, mandatory cosign provenance verification, non-blocking background download, disk-persistent failure markers with retryable-cause tracking (cosign_missing auto-clears when cosign appears on PATH) - tests/tools/test_tirith_security.py: 62 tests covering exit code mapping, fail_open, cosign verification, background install, HERMES_HOME isolation, and failure recovery - tests/tools/test_command_guards.py: 21 integration tests for the combined guard orchestration Modified files: - tools/approval.py: add check_all_command_guards() orchestrator, add allow_permanent parameter to prompt_dangerous_approval() - tools/terminal_tool.py: replace _check_dangerous_command with consolidated check_all_command_guards - cli.py: update _approval_callback for allow_permanent kwarg, call ensure_installed() at startup - gateway/run.py: iterate pattern_keys list on replay approval, call ensure_installed() at startup - hermes_cli/config.py: add security config defaults, split commented sections for independent fallback - cli-config.yaml.example: document tirith security config
2026-03-11 14:20:32 +05:30
# tirith pre-exec scanning is enabled by default when the tirith binary
# is available. Configure via security.tirith_* keys or env vars
# (TIRITH_ENABLED, TIRITH_BIN, TIRITH_TIMEOUT, TIRITH_FAIL_OPEN).
#
# security:
# redact_secrets: false
feat(security): add tirith pre-exec command scanning Integrate tirith as a pre-execution security scanner that detects homograph URLs, pipe-to-interpreter patterns, terminal injection, zero-width Unicode, and environment variable manipulation — threats the existing 50-pattern dangerous command detector doesn't cover. Architecture: gather-then-decide — both tirith and the dangerous command detector run before any approval prompt, preventing gateway force=True replay from bypassing one check when only the other was shown to the user. New files: - tools/tirith_security.py: subprocess wrapper with auto-installer, mandatory cosign provenance verification, non-blocking background download, disk-persistent failure markers with retryable-cause tracking (cosign_missing auto-clears when cosign appears on PATH) - tests/tools/test_tirith_security.py: 62 tests covering exit code mapping, fail_open, cosign verification, background install, HERMES_HOME isolation, and failure recovery - tests/tools/test_command_guards.py: 21 integration tests for the combined guard orchestration Modified files: - tools/approval.py: add check_all_command_guards() orchestrator, add allow_permanent parameter to prompt_dangerous_approval() - tools/terminal_tool.py: replace _check_dangerous_command with consolidated check_all_command_guards - cli.py: update _approval_callback for allow_permanent kwarg, call ensure_installed() at startup - gateway/run.py: iterate pattern_keys list on replay approval, call ensure_installed() at startup - hermes_cli/config.py: add security config defaults, split commented sections for independent fallback - cli-config.yaml.example: document tirith security config
2026-03-11 14:20:32 +05:30
# tirith_enabled: true
# tirith_path: "tirith"
# tirith_timeout: 5
# tirith_fail_open: true
"""
feat(security): add tirith pre-exec command scanning Integrate tirith as a pre-execution security scanner that detects homograph URLs, pipe-to-interpreter patterns, terminal injection, zero-width Unicode, and environment variable manipulation — threats the existing 50-pattern dangerous command detector doesn't cover. Architecture: gather-then-decide — both tirith and the dangerous command detector run before any approval prompt, preventing gateway force=True replay from bypassing one check when only the other was shown to the user. New files: - tools/tirith_security.py: subprocess wrapper with auto-installer, mandatory cosign provenance verification, non-blocking background download, disk-persistent failure markers with retryable-cause tracking (cosign_missing auto-clears when cosign appears on PATH) - tests/tools/test_tirith_security.py: 62 tests covering exit code mapping, fail_open, cosign verification, background install, HERMES_HOME isolation, and failure recovery - tests/tools/test_command_guards.py: 21 integration tests for the combined guard orchestration Modified files: - tools/approval.py: add check_all_command_guards() orchestrator, add allow_permanent parameter to prompt_dangerous_approval() - tools/terminal_tool.py: replace _check_dangerous_command with consolidated check_all_command_guards - cli.py: update _approval_callback for allow_permanent kwarg, call ensure_installed() at startup - gateway/run.py: iterate pattern_keys list on replay approval, call ensure_installed() at startup - hermes_cli/config.py: add security config defaults, split commented sections for independent fallback - cli-config.yaml.example: document tirith security config
2026-03-11 14:20:32 +05:30
_FALLBACK_COMMENT = """
# ── Fallback Model ────────────────────────────────────────────────────
# Automatic provider failover when primary is unavailable.
# Uncomment and configure to enable. Triggers on rate limits (429),
# overload (529), service errors (503), or connection failures.
#
# Supported providers:
# openrouter (OPENROUTER_API_KEY) — routes to any model
# openai-codex (OAuth — hermes auth) — OpenAI Codex
# nous (OAuth — hermes auth) — Nous Portal
# zai (ZAI_API_KEY) — Z.AI / GLM
# kimi-coding (KIMI_API_KEY) — Kimi / Moonshot
# kimi-coding-cn (KIMI_CN_API_KEY) — Kimi / Moonshot (China)
# minimax (MINIMAX_API_KEY) — MiniMax
# minimax-cn (MINIMAX_CN_API_KEY) — MiniMax (China)
#
# For custom OpenAI-compatible endpoints, add base_url and key_env.
#
# fallback_model:
# provider: openrouter
# model: anthropic/claude-sonnet-4
"""
_COMMENTED_SECTIONS = """
# ── Security ──────────────────────────────────────────────────────────
# API keys, tokens, and passwords are redacted from tool output by default.
# Set to false to see full values (useful for debugging auth issues).
#
# security:
# redact_secrets: false
# ── Fallback Model ────────────────────────────────────────────────────
# Automatic provider failover when primary is unavailable.
# Uncomment and configure to enable. Triggers on rate limits (429),
# overload (529), service errors (503), or connection failures.
#
# Supported providers:
# openrouter (OPENROUTER_API_KEY) — routes to any model
# openai-codex (OAuth — hermes auth) — OpenAI Codex
# nous (OAuth — hermes auth) — Nous Portal
# zai (ZAI_API_KEY) — Z.AI / GLM
# kimi-coding (KIMI_API_KEY) — Kimi / Moonshot
# kimi-coding-cn (KIMI_CN_API_KEY) — Kimi / Moonshot (China)
# minimax (MINIMAX_API_KEY) — MiniMax
# minimax-cn (MINIMAX_CN_API_KEY) — MiniMax (China)
#
# For custom OpenAI-compatible endpoints, add base_url and key_env.
#
# fallback_model:
# provider: openrouter
# model: anthropic/claude-sonnet-4
"""
def save_config(config: Dict[str, Any]):
"""Save configuration to ~/.hermes/config.yaml."""
feat: nix flake — uv2nix build, NixOS module, persistent container mode (#20) * feat: nix flake, uv2nix build, dev shell and home manager * fixed nix run, updated docs for setup * feat(nix): NixOS module with persistent container mode, managed guards, checks - Replace homeModules.nix with nixosModules.nix (two deployment modes) - Mode A (native): hardened systemd service with ProtectSystem=strict - Mode B (container): persistent Ubuntu container with /nix/store bind-mount, identity-hash-based recreation, GC root protection, symlink-based updates - Add HERMES_MANAGED guards blocking CLI config mutation (config set, setup, gateway install/uninstall) when running under NixOS module - Add nix/checks.nix with build-time verification (binary, CLI, managed guard) - Remove container.nix (no Nix-built OCI image; pulls ubuntu:24.04 at runtime) - Simplify packages.nix (drop fetchFromGitHub submodules, PYTHONPATH wrappers) - Rewrite docs/nixos-setup.md with full options reference, container architecture, secrets management, and troubleshooting guide Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * Update config.py * feat(nix): add CI workflow and enhanced build checks - GitHub Actions workflow for nix flake check + build on linux/macOS - Entry point sync check to catch pyproject.toml drift - Expanded managed-guard check to cover config edit - Wrap hermes-acp binary in Nix package - Fix Path type mismatch in is_managed() * Update MCP server package name; bundled skills support * fix reading .env. instead have container user a common mounted .env file * feat(nix): container entrypoint with privilege drop and sudo provisioning Container was running as non-root via --user, which broke apt/pip installs and caused crashes when $HOME didn't exist. Replace --user with a Nix-built entrypoint script that provisions the hermes user, sudo (NOPASSWD), and /home/hermes inside the container on first boot, then drops privileges via setpriv. Writable layer persists so setup only runs once. Also expands MCP server options to support HTTP transport and sampling. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix group and user creation in container mode * feat(nix): persistent /home/hermes and MESSAGING_CWD in container mode Container mode now bind-mounts ${stateDir}/home to /home/hermes so the agent's home directory survives container recreation. Previously it lived in the writable layer and was lost on image/volume/options changes. Also passes MESSAGING_CWD to the container so the agent finds its workspace and documents, matching native mode behavior. Other changes: - Extract containerDataDir/containerHomeDir bindings (no more magic strings) - Fix entrypoint chown to run unconditionally (volume mounts always exist) - Add schema field to container identity hash for auto-recreation - Add idempotency test (Scenario G) to config-roundtrip check * docs: add Nix & NixOS setup guide to docs site Add comprehensive Nix documentation to the Docusaurus site at website/docs/getting-started/nix-setup.md, covering nix run/profile install, NixOS module (native + container modes), declarative settings, secrets management, MCP servers, managed mode, container architecture, dev shell, flake checks, and full options reference. - Register nix-setup in sidebar after installation page - Add Nix callout tip to installation.md linking to new guide - Add canonical version pointer in docs/nixos-setup.md * docs: remove docs/nixos-setup.md, consolidate into website docs Backfill missing details (restart/restartSec in full example, gateway.pid, 0750 permissions, docker inspect commands) into the canonical website/docs/getting-started/nix-setup.md and delete the old standalone file. * fix(nix): add compression.protect_last_n and target_ratio to config-keys.json New keys were added to DEFAULT_CONFIG on main, causing the config-drift check to fail in CI. * fix(nix): skip checks on aarch64-darwin (onnxruntime wheel missing) The full Python venv includes onnxruntime (via faster-whisper/STT) which lacks a compatible uv2nix wheel on aarch64-darwin. Gate all checks behind stdenv.hostPlatform.isLinux. The package and devShell still evaluate on macOS. * fix(nix): skip flake check and build on macOS CI onnxruntime (transitive dep via faster-whisper) lacks a compatible uv2nix wheel on aarch64-darwin. Run full checks and build on Linux only; macOS CI verifies the flake evaluates without building. * fix(nix): preserve container writable layer across nixos-rebuild The container identity hash included the entrypoint's Nix store path, which changes on every nixpkgs update (due to runtimeShell/stdenv input-addressing). This caused false-positive identity mismatches, triggering container recreation and losing the persistent writable layer. - Use stable symlink (current-entrypoint) like current-package already does - Remove entrypoint from identity hash (only image/volumes/options matter) - Add GC root for entrypoint so nix-collect-garbage doesn't break it - Remove global HERMES_HOME env var from addToSystemPackages (conflicted with interactive CLI use, service already sets its own) --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-26 01:08:02 +05:30
if is_managed():
managed_error("save configuration")
return
from utils import atomic_yaml_write
ensure_hermes_home()
config_path = get_config_path()
current_normalized = _normalize_root_model_keys(_normalize_max_turns_config(config))
normalized = current_normalized
raw_existing = _normalize_root_model_keys(_normalize_max_turns_config(read_raw_config()))
if raw_existing:
normalized = _preserve_env_ref_templates(
normalized,
raw_existing,
_LAST_EXPANDED_CONFIG_BY_PATH.get(str(config_path)),
)
# Build optional commented-out sections for features that are off by
# default or only relevant when explicitly configured.
feat(security): add tirith pre-exec command scanning Integrate tirith as a pre-execution security scanner that detects homograph URLs, pipe-to-interpreter patterns, terminal injection, zero-width Unicode, and environment variable manipulation — threats the existing 50-pattern dangerous command detector doesn't cover. Architecture: gather-then-decide — both tirith and the dangerous command detector run before any approval prompt, preventing gateway force=True replay from bypassing one check when only the other was shown to the user. New files: - tools/tirith_security.py: subprocess wrapper with auto-installer, mandatory cosign provenance verification, non-blocking background download, disk-persistent failure markers with retryable-cause tracking (cosign_missing auto-clears when cosign appears on PATH) - tests/tools/test_tirith_security.py: 62 tests covering exit code mapping, fail_open, cosign verification, background install, HERMES_HOME isolation, and failure recovery - tests/tools/test_command_guards.py: 21 integration tests for the combined guard orchestration Modified files: - tools/approval.py: add check_all_command_guards() orchestrator, add allow_permanent parameter to prompt_dangerous_approval() - tools/terminal_tool.py: replace _check_dangerous_command with consolidated check_all_command_guards - cli.py: update _approval_callback for allow_permanent kwarg, call ensure_installed() at startup - gateway/run.py: iterate pattern_keys list on replay approval, call ensure_installed() at startup - hermes_cli/config.py: add security config defaults, split commented sections for independent fallback - cli-config.yaml.example: document tirith security config
2026-03-11 14:20:32 +05:30
parts = []
sec = normalized.get("security", {})
if not sec or sec.get("redact_secrets") is None:
feat(security): add tirith pre-exec command scanning Integrate tirith as a pre-execution security scanner that detects homograph URLs, pipe-to-interpreter patterns, terminal injection, zero-width Unicode, and environment variable manipulation — threats the existing 50-pattern dangerous command detector doesn't cover. Architecture: gather-then-decide — both tirith and the dangerous command detector run before any approval prompt, preventing gateway force=True replay from bypassing one check when only the other was shown to the user. New files: - tools/tirith_security.py: subprocess wrapper with auto-installer, mandatory cosign provenance verification, non-blocking background download, disk-persistent failure markers with retryable-cause tracking (cosign_missing auto-clears when cosign appears on PATH) - tests/tools/test_tirith_security.py: 62 tests covering exit code mapping, fail_open, cosign verification, background install, HERMES_HOME isolation, and failure recovery - tests/tools/test_command_guards.py: 21 integration tests for the combined guard orchestration Modified files: - tools/approval.py: add check_all_command_guards() orchestrator, add allow_permanent parameter to prompt_dangerous_approval() - tools/terminal_tool.py: replace _check_dangerous_command with consolidated check_all_command_guards - cli.py: update _approval_callback for allow_permanent kwarg, call ensure_installed() at startup - gateway/run.py: iterate pattern_keys list on replay approval, call ensure_installed() at startup - hermes_cli/config.py: add security config defaults, split commented sections for independent fallback - cli-config.yaml.example: document tirith security config
2026-03-11 14:20:32 +05:30
parts.append(_SECURITY_COMMENT)
fb = normalized.get("fallback_model", {})
if not fb or not isinstance(fb, dict) or not (fb.get("provider") and fb.get("model")):
feat(security): add tirith pre-exec command scanning Integrate tirith as a pre-execution security scanner that detects homograph URLs, pipe-to-interpreter patterns, terminal injection, zero-width Unicode, and environment variable manipulation — threats the existing 50-pattern dangerous command detector doesn't cover. Architecture: gather-then-decide — both tirith and the dangerous command detector run before any approval prompt, preventing gateway force=True replay from bypassing one check when only the other was shown to the user. New files: - tools/tirith_security.py: subprocess wrapper with auto-installer, mandatory cosign provenance verification, non-blocking background download, disk-persistent failure markers with retryable-cause tracking (cosign_missing auto-clears when cosign appears on PATH) - tests/tools/test_tirith_security.py: 62 tests covering exit code mapping, fail_open, cosign verification, background install, HERMES_HOME isolation, and failure recovery - tests/tools/test_command_guards.py: 21 integration tests for the combined guard orchestration Modified files: - tools/approval.py: add check_all_command_guards() orchestrator, add allow_permanent parameter to prompt_dangerous_approval() - tools/terminal_tool.py: replace _check_dangerous_command with consolidated check_all_command_guards - cli.py: update _approval_callback for allow_permanent kwarg, call ensure_installed() at startup - gateway/run.py: iterate pattern_keys list on replay approval, call ensure_installed() at startup - hermes_cli/config.py: add security config defaults, split commented sections for independent fallback - cli-config.yaml.example: document tirith security config
2026-03-11 14:20:32 +05:30
parts.append(_FALLBACK_COMMENT)
atomic_yaml_write(
config_path,
normalized,
feat(security): add tirith pre-exec command scanning Integrate tirith as a pre-execution security scanner that detects homograph URLs, pipe-to-interpreter patterns, terminal injection, zero-width Unicode, and environment variable manipulation — threats the existing 50-pattern dangerous command detector doesn't cover. Architecture: gather-then-decide — both tirith and the dangerous command detector run before any approval prompt, preventing gateway force=True replay from bypassing one check when only the other was shown to the user. New files: - tools/tirith_security.py: subprocess wrapper with auto-installer, mandatory cosign provenance verification, non-blocking background download, disk-persistent failure markers with retryable-cause tracking (cosign_missing auto-clears when cosign appears on PATH) - tests/tools/test_tirith_security.py: 62 tests covering exit code mapping, fail_open, cosign verification, background install, HERMES_HOME isolation, and failure recovery - tests/tools/test_command_guards.py: 21 integration tests for the combined guard orchestration Modified files: - tools/approval.py: add check_all_command_guards() orchestrator, add allow_permanent parameter to prompt_dangerous_approval() - tools/terminal_tool.py: replace _check_dangerous_command with consolidated check_all_command_guards - cli.py: update _approval_callback for allow_permanent kwarg, call ensure_installed() at startup - gateway/run.py: iterate pattern_keys list on replay approval, call ensure_installed() at startup - hermes_cli/config.py: add security config defaults, split commented sections for independent fallback - cli-config.yaml.example: document tirith security config
2026-03-11 14:20:32 +05:30
extra_content="".join(parts) if parts else None,
)
_secure_file(config_path)
_LAST_EXPANDED_CONFIG_BY_PATH[str(config_path)] = copy.deepcopy(current_normalized)
def load_env() -> Dict[str, str]:
"""Load environment variables from ~/.hermes/.env.
Sanitizes lines before parsing so that corrupted files (e.g.
concatenated KEY=VALUE pairs on a single line) are handled
gracefully instead of producing mangled values such as duplicated
bot tokens. See #8908.
"""
env_path = get_env_path()
env_vars = {}
if env_path.exists():
# On Windows, open() defaults to the system locale (cp1252) which can
# fail on UTF-8 .env files. Use explicit UTF-8 only on Windows.
open_kw = {"encoding": "utf-8", "errors": "replace"} if _IS_WINDOWS else {}
with open(env_path, **open_kw) as f:
raw_lines = f.readlines()
# Sanitize before parsing: split concatenated lines & drop stale
# placeholders so corrupted .env files don't produce invalid tokens.
lines = _sanitize_env_lines(raw_lines)
for line in lines:
line = line.strip()
if line and not line.startswith('#') and '=' in line:
key, _, value = line.partition('=')
env_vars[key.strip()] = value.strip().strip('"\'')
return env_vars
def _sanitize_env_lines(lines: list) -> list:
"""Fix corrupted .env lines before reading or writing.
Handles two known corruption patterns:
1. Concatenated KEY=VALUE pairs on a single line (missing newline between
entries, e.g. ``ANTHROPIC_API_KEY=sk-...OPENAI_BASE_URL=https://...``).
2. Stale ``KEY=***`` placeholder entries left by incomplete setup runs.
Uses a known-keys set (OPTIONAL_ENV_VARS + _EXTRA_ENV_KEYS) so we only
split on real Hermes env var names, avoiding false positives from values
that happen to contain uppercase text with ``=``.
"""
# Build the known keys set lazily from OPTIONAL_ENV_VARS + extras.
# Done inside the function so OPTIONAL_ENV_VARS is guaranteed to be defined.
known_keys = set(OPTIONAL_ENV_VARS.keys()) | _EXTRA_ENV_KEYS
sanitized: list[str] = []
for line in lines:
raw = line.rstrip("\r\n")
stripped = raw.strip()
# Preserve blank lines and comments
if not stripped or stripped.startswith("#"):
sanitized.append(raw + "\n")
continue
# Detect concatenated KEY=VALUE pairs on one line.
# Search for known KEY= patterns at any position in the line.
split_positions = []
for key_name in known_keys:
needle = key_name + "="
idx = stripped.find(needle)
while idx >= 0:
split_positions.append(idx)
idx = stripped.find(needle, idx + len(needle))
if len(split_positions) > 1:
split_positions.sort()
# Deduplicate (shouldn't happen, but be safe)
split_positions = sorted(set(split_positions))
for i, pos in enumerate(split_positions):
end = split_positions[i + 1] if i + 1 < len(split_positions) else len(stripped)
part = stripped[pos:end].strip()
if part:
sanitized.append(part + "\n")
else:
sanitized.append(stripped + "\n")
return sanitized
def sanitize_env_file() -> int:
"""Read, sanitize, and rewrite ~/.hermes/.env in place.
Returns the number of lines that were fixed (concatenation splits +
placeholder removals). Returns 0 when no changes are needed.
"""
env_path = get_env_path()
if not env_path.exists():
return 0
read_kw = {"encoding": "utf-8", "errors": "replace"} if _IS_WINDOWS else {}
write_kw = {"encoding": "utf-8"} if _IS_WINDOWS else {}
with open(env_path, **read_kw) as f:
original_lines = f.readlines()
sanitized = _sanitize_env_lines(original_lines)
if sanitized == original_lines:
return 0
# Count fixes: difference in line count (from splits) + removed lines
fixes = abs(len(sanitized) - len(original_lines))
if fixes == 0:
# Lines changed content (e.g. *** removal) even if count is same
fixes = sum(1 for a, b in zip(original_lines, sanitized) if a != b)
fixes += abs(len(sanitized) - len(original_lines))
fd, tmp_path = tempfile.mkstemp(dir=str(env_path.parent), suffix=".tmp", prefix=".env_")
try:
with os.fdopen(fd, "w", **write_kw) as f:
f.writelines(sanitized)
f.flush()
os.fsync(f.fileno())
os.replace(tmp_path, env_path)
except BaseException:
try:
os.unlink(tmp_path)
except OSError:
pass
raise
_secure_file(env_path)
return fixes
def _check_non_ascii_credential(key: str, value: str) -> str:
"""Warn and strip non-ASCII characters from credential values.
API keys and tokens must be pure ASCII they are sent as HTTP header
values which httpx/httpcore encode as ASCII. Non-ASCII characters
(commonly introduced by copy-pasting from rich-text editors or PDFs
that substitute lookalike Unicode glyphs for ASCII letters) cause
``UnicodeEncodeError: 'ascii' codec can't encode character`` at
request time.
Returns the sanitized (ASCII-only) value. Prints a warning if any
non-ASCII characters were found and removed.
"""
try:
value.encode("ascii")
return value # all ASCII — nothing to do
except UnicodeEncodeError:
pass
# Build a readable list of the offending characters
bad_chars: list[str] = []
for i, ch in enumerate(value):
if ord(ch) > 127:
bad_chars.append(f" position {i}: {ch!r} (U+{ord(ch):04X})")
sanitized = value.encode("ascii", errors="ignore").decode("ascii")
print(
f"\n Warning: {key} contains non-ASCII characters that will break API requests.\n"
f" This usually happens when copy-pasting from a PDF, rich-text editor,\n"
f" or web page that substitutes lookalike Unicode glyphs for ASCII letters.\n"
f"\n"
+ "\n".join(f" {line}" for line in bad_chars[:5])
+ ("\n ... and more" if len(bad_chars) > 5 else "")
+ f"\n\n The non-ASCII characters have been stripped automatically.\n"
f" If authentication fails, re-copy the key from the provider's dashboard.\n",
file=sys.stderr,
)
return sanitized
def save_env_value(key: str, value: str):
"""Save or update a value in ~/.hermes/.env."""
feat: nix flake — uv2nix build, NixOS module, persistent container mode (#20) * feat: nix flake, uv2nix build, dev shell and home manager * fixed nix run, updated docs for setup * feat(nix): NixOS module with persistent container mode, managed guards, checks - Replace homeModules.nix with nixosModules.nix (two deployment modes) - Mode A (native): hardened systemd service with ProtectSystem=strict - Mode B (container): persistent Ubuntu container with /nix/store bind-mount, identity-hash-based recreation, GC root protection, symlink-based updates - Add HERMES_MANAGED guards blocking CLI config mutation (config set, setup, gateway install/uninstall) when running under NixOS module - Add nix/checks.nix with build-time verification (binary, CLI, managed guard) - Remove container.nix (no Nix-built OCI image; pulls ubuntu:24.04 at runtime) - Simplify packages.nix (drop fetchFromGitHub submodules, PYTHONPATH wrappers) - Rewrite docs/nixos-setup.md with full options reference, container architecture, secrets management, and troubleshooting guide Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * Update config.py * feat(nix): add CI workflow and enhanced build checks - GitHub Actions workflow for nix flake check + build on linux/macOS - Entry point sync check to catch pyproject.toml drift - Expanded managed-guard check to cover config edit - Wrap hermes-acp binary in Nix package - Fix Path type mismatch in is_managed() * Update MCP server package name; bundled skills support * fix reading .env. instead have container user a common mounted .env file * feat(nix): container entrypoint with privilege drop and sudo provisioning Container was running as non-root via --user, which broke apt/pip installs and caused crashes when $HOME didn't exist. Replace --user with a Nix-built entrypoint script that provisions the hermes user, sudo (NOPASSWD), and /home/hermes inside the container on first boot, then drops privileges via setpriv. Writable layer persists so setup only runs once. Also expands MCP server options to support HTTP transport and sampling. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix group and user creation in container mode * feat(nix): persistent /home/hermes and MESSAGING_CWD in container mode Container mode now bind-mounts ${stateDir}/home to /home/hermes so the agent's home directory survives container recreation. Previously it lived in the writable layer and was lost on image/volume/options changes. Also passes MESSAGING_CWD to the container so the agent finds its workspace and documents, matching native mode behavior. Other changes: - Extract containerDataDir/containerHomeDir bindings (no more magic strings) - Fix entrypoint chown to run unconditionally (volume mounts always exist) - Add schema field to container identity hash for auto-recreation - Add idempotency test (Scenario G) to config-roundtrip check * docs: add Nix & NixOS setup guide to docs site Add comprehensive Nix documentation to the Docusaurus site at website/docs/getting-started/nix-setup.md, covering nix run/profile install, NixOS module (native + container modes), declarative settings, secrets management, MCP servers, managed mode, container architecture, dev shell, flake checks, and full options reference. - Register nix-setup in sidebar after installation page - Add Nix callout tip to installation.md linking to new guide - Add canonical version pointer in docs/nixos-setup.md * docs: remove docs/nixos-setup.md, consolidate into website docs Backfill missing details (restart/restartSec in full example, gateway.pid, 0750 permissions, docker inspect commands) into the canonical website/docs/getting-started/nix-setup.md and delete the old standalone file. * fix(nix): add compression.protect_last_n and target_ratio to config-keys.json New keys were added to DEFAULT_CONFIG on main, causing the config-drift check to fail in CI. * fix(nix): skip checks on aarch64-darwin (onnxruntime wheel missing) The full Python venv includes onnxruntime (via faster-whisper/STT) which lacks a compatible uv2nix wheel on aarch64-darwin. Gate all checks behind stdenv.hostPlatform.isLinux. The package and devShell still evaluate on macOS. * fix(nix): skip flake check and build on macOS CI onnxruntime (transitive dep via faster-whisper) lacks a compatible uv2nix wheel on aarch64-darwin. Run full checks and build on Linux only; macOS CI verifies the flake evaluates without building. * fix(nix): preserve container writable layer across nixos-rebuild The container identity hash included the entrypoint's Nix store path, which changes on every nixpkgs update (due to runtimeShell/stdenv input-addressing). This caused false-positive identity mismatches, triggering container recreation and losing the persistent writable layer. - Use stable symlink (current-entrypoint) like current-package already does - Remove entrypoint from identity hash (only image/volumes/options matter) - Add GC root for entrypoint so nix-collect-garbage doesn't break it - Remove global HERMES_HOME env var from addToSystemPackages (conflicted with interactive CLI use, service already sets its own) --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-26 01:08:02 +05:30
if is_managed():
managed_error(f"set {key}")
return
if not _ENV_VAR_NAME_RE.match(key):
raise ValueError(f"Invalid environment variable name: {key!r}")
value = value.replace("\n", "").replace("\r", "")
# API keys / tokens must be ASCII — strip non-ASCII with a warning.
value = _check_non_ascii_credential(key, value)
ensure_hermes_home()
env_path = get_env_path()
# On Windows, open() defaults to the system locale (cp1252) which can
# cause OSError errno 22 on UTF-8 .env files.
read_kw = {"encoding": "utf-8", "errors": "replace"} if _IS_WINDOWS else {}
write_kw = {"encoding": "utf-8"} if _IS_WINDOWS else {}
lines = []
if env_path.exists():
with open(env_path, **read_kw) as f:
lines = f.readlines()
# Sanitize on every read: split concatenated keys, drop stale placeholders
lines = _sanitize_env_lines(lines)
# Find and update or append
found = False
for i, line in enumerate(lines):
if line.strip().startswith(f"{key}="):
lines[i] = f"{key}={value}\n"
found = True
break
if not found:
# Ensure there's a newline at the end of the file before appending
if lines and not lines[-1].endswith("\n"):
lines[-1] += "\n"
lines.append(f"{key}={value}\n")
fd, tmp_path = tempfile.mkstemp(dir=str(env_path.parent), suffix='.tmp', prefix='.env_')
# Preserve original permissions so Docker volume mounts aren't clobbered.
original_mode = None
if env_path.exists():
try:
original_mode = stat.S_IMODE(env_path.stat().st_mode)
except OSError:
pass
try:
with os.fdopen(fd, 'w', **write_kw) as f:
f.writelines(lines)
f.flush()
os.fsync(f.fileno())
os.replace(tmp_path, env_path)
# Restore original permissions before _secure_file may tighten them.
if original_mode is not None:
try:
os.chmod(env_path, original_mode)
except OSError:
pass
except BaseException:
try:
os.unlink(tmp_path)
except OSError:
pass
raise
_secure_file(env_path)
os.environ[key] = value
def remove_env_value(key: str) -> bool:
"""Remove a key from ~/.hermes/.env and os.environ.
Returns True if the key was found and removed, False otherwise.
"""
if is_managed():
managed_error(f"remove {key}")
return False
if not _ENV_VAR_NAME_RE.match(key):
raise ValueError(f"Invalid environment variable name: {key!r}")
env_path = get_env_path()
if not env_path.exists():
os.environ.pop(key, None)
return False
read_kw = {"encoding": "utf-8", "errors": "replace"} if _IS_WINDOWS else {}
write_kw = {"encoding": "utf-8"} if _IS_WINDOWS else {}
with open(env_path, **read_kw) as f:
lines = f.readlines()
lines = _sanitize_env_lines(lines)
new_lines = [line for line in lines if not line.strip().startswith(f"{key}=")]
found = len(new_lines) < len(lines)
if found:
fd, tmp_path = tempfile.mkstemp(dir=str(env_path.parent), suffix='.tmp', prefix='.env_')
# Preserve original permissions so Docker volume mounts aren't clobbered.
original_mode = None
try:
original_mode = stat.S_IMODE(env_path.stat().st_mode)
except OSError:
pass
try:
with os.fdopen(fd, 'w', **write_kw) as f:
f.writelines(new_lines)
f.flush()
os.fsync(f.fileno())
os.replace(tmp_path, env_path)
if original_mode is not None:
try:
os.chmod(env_path, original_mode)
except OSError:
pass
except BaseException:
try:
os.unlink(tmp_path)
except OSError:
pass
raise
_secure_file(env_path)
os.environ.pop(key, None)
return found
def save_anthropic_oauth_token(value: str, save_fn=None):
"""Persist an Anthropic OAuth/setup token and clear the API-key slot."""
writer = save_fn or save_env_value
writer("ANTHROPIC_TOKEN", value)
writer("ANTHROPIC_API_KEY", "")
def use_anthropic_claude_code_credentials(save_fn=None):
"""Use Claude Code's own credential files instead of persisting env tokens."""
writer = save_fn or save_env_value
writer("ANTHROPIC_TOKEN", "")
writer("ANTHROPIC_API_KEY", "")
def save_anthropic_api_key(value: str, save_fn=None):
"""Persist an Anthropic API key and clear the OAuth/setup-token slot."""
writer = save_fn or save_env_value
writer("ANTHROPIC_API_KEY", value)
writer("ANTHROPIC_TOKEN", "")
def save_env_value_secure(key: str, value: str) -> Dict[str, Any]:
save_env_value(key, value)
return {
"success": True,
"stored_as": key,
"validated": False,
}
feat: web UI dashboard for managing Hermes Agent (#8756) * feat: web UI dashboard for managing Hermes Agent (salvage of #8204/#7621) Adds an embedded web UI dashboard accessible via `hermes web`: - Status page: agent version, active sessions, gateway status, connected platforms - Config editor: schema-driven form with tabbed categories, import/export, reset - API Keys page: set, clear, and view redacted values with category grouping - Sessions, Skills, Cron, Logs, and Analytics pages Backend: - hermes_cli/web_server.py: FastAPI server with REST endpoints - hermes_cli/config.py: reload_env() utility for hot-reloading .env - hermes_cli/main.py: `hermes web` subcommand (--port, --host, --no-open) - cli.py / commands.py: /reload slash command for .env hot-reload - pyproject.toml: [web] optional dependency extra (fastapi + uvicorn) - Both update paths (git + zip) auto-build web frontend when npm available Frontend: - Vite + React + TypeScript + Tailwind v4 SPA in web/ - shadcn/ui-style components, Nous design language - Auto-refresh status page, toast notifications, masked password inputs Security: - Path traversal guard (resolve().is_relative_to()) on SPA file serving - CORS localhost-only via allow_origin_regex - Generic error messages (no internal leak), SessionDB handles closed properly Tests: 47 tests covering reload_env, redact_key, API endpoints, schema generation, path traversal, category merging, internal key stripping, and full config round-trip. Original work by @austinpickett (PR #1813), salvaged by @kshitijk4poor (PR #7621 → #8204), re-salvaged onto current main with stale-branch regressions removed. * fix(web): clean up status page cards, always rebuild on `hermes web` - Remove config version migration alert banner from status page - Remove config version card (internal noise, not surfaced in TUI) - Reorder status cards: Agent → Gateway → Active Sessions (3-col grid) - `hermes web` now always rebuilds from source before serving, preventing stale web_dist when editing frontend files * feat(web): full-text search across session messages - Add GET /api/sessions/search endpoint backed by FTS5 - Auto-append prefix wildcards so partial words match (e.g. 'nimb' → 'nimby') - Debounced search (300ms) with spinner in the search icon slot - Search results show FTS5 snippets with highlighted match delimiters - Expanding a search hit auto-scrolls to the first matching message - Matching messages get a warning ring + 'match' badge - Inline term highlighting within Markdown (text, bold, italic, headings, lists) - Clear button (x) on search input for quick reset --------- Co-authored-by: emozilla <emozilla@nousresearch.com>
2026-04-12 22:26:28 -07:00
def reload_env() -> int:
"""Re-read ~/.hermes/.env into os.environ. Returns count of vars updated.
Adds/updates vars that changed and removes vars that were deleted from
the .env file (but only vars known to Hermes OPTIONAL_ENV_VARS and
_EXTRA_ENV_KEYS to avoid clobbering unrelated environment).
"""
env_vars = load_env()
known_keys = set(OPTIONAL_ENV_VARS.keys()) | _EXTRA_ENV_KEYS
count = 0
for key, value in env_vars.items():
if os.environ.get(key) != value:
os.environ[key] = value
count += 1
# Remove known Hermes vars that are no longer in .env
for key in known_keys:
if key not in env_vars and key in os.environ:
del os.environ[key]
count += 1
return count
def get_env_value(key: str) -> Optional[str]:
"""Get a value from ~/.hermes/.env or environment."""
# Check environment first
if key in os.environ:
return os.environ[key]
# Then check .env file
env_vars = load_env()
return env_vars.get(key)
# =============================================================================
# Config display
# =============================================================================
def redact_key(key: str) -> str:
"""Redact an API key for display."""
if not key:
return color("(not set)", Colors.DIM)
if len(key) < 12:
return "***"
return key[:4] + "..." + key[-4:]
def show_config():
"""Display current configuration."""
config = load_config()
print()
print(color("┌─────────────────────────────────────────────────────────┐", Colors.CYAN))
print(color("│ ⚕ Hermes Configuration │", Colors.CYAN))
print(color("└─────────────────────────────────────────────────────────┘", Colors.CYAN))
# Paths
print()
print(color("◆ Paths", Colors.CYAN, Colors.BOLD))
print(f" Config: {get_config_path()}")
print(f" Secrets: {get_env_path()}")
print(f" Install: {get_project_root()}")
# API Keys
print()
print(color("◆ API Keys", Colors.CYAN, Colors.BOLD))
keys = [
("OPENROUTER_API_KEY", "OpenRouter"),
("VOICE_TOOLS_OPENAI_KEY", "OpenAI (STT/TTS)"),
("EXA_API_KEY", "Exa"),
feat(web): add Parallel as alternative web search/extract backend (#1696) * feat(web): add Parallel as alternative web search/extract backend Adds Parallel (parallel.ai) as a drop-in alternative to Firecrawl for web_search and web_extract tools using the official parallel-web SDK. - Backend selection via WEB_SEARCH_BACKEND env var (auto/parallel/firecrawl) - Auto mode prefers Firecrawl when both keys present; Parallel when sole backend - web_crawl remains Firecrawl-only with clear error when unavailable - Lazy SDK imports, interrupt support, singleton clients - 16 new unit tests for backend selection and client config Co-authored-by: s-jag <s-jag@users.noreply.github.com> * fix: add PARALLEL_API_KEY to config registry and fix web_crawl policy tests Follow-up for Parallel backend integration: - Add PARALLEL_API_KEY to OPTIONAL_ENV_VARS (hermes doctor, env blocklist) - Add to set_config_value api_keys list (hermes config set) - Add to doctor keys display - Fix 2 web_crawl policy tests that didn't set FIRECRAWL_API_KEY (needed now that web_crawl has a Firecrawl availability guard) * refactor: explicit backend selection via hermes tools, not auto-detect Replace the auto-detect backend selection with explicit user choice: - hermes tools saves WEB_SEARCH_BACKEND to .env when user picks a provider - _get_backend() reads the explicit choice first - Fallback only for manual/legacy config (uses whichever key is present) - _is_provider_active() shows [active] for the selected web backend - Updated tests, docs, and .env.example to remove 'auto' mode language * refactor: use config.yaml for web backend, not env var Match the TTS/browser pattern — web.backend is stored in config.yaml (set by hermes tools), not as a WEB_SEARCH_BACKEND env var. - _load_web_config() reads web: section from config.yaml - _get_backend() reads web.backend from config, falls back to key detection - _configure_provider() saves to config dict (saved to config.yaml) - _is_provider_active() reads from config dict - Removed WEB_SEARCH_BACKEND from .env.example, set_config_value, docs - Updated all tests to mock _load_web_config instead of env vars --------- Co-authored-by: s-jag <s-jag@users.noreply.github.com>
2026-03-17 04:02:02 -07:00
("PARALLEL_API_KEY", "Parallel"),
("FIRECRAWL_API_KEY", "Firecrawl"),
("TAVILY_API_KEY", "Tavily"),
("BROWSERBASE_API_KEY", "Browserbase"),
("BROWSER_USE_API_KEY", "Browser Use"),
("FAL_KEY", "FAL"),
]
for env_key, name in keys:
value = get_env_value(env_key)
print(f" {name:<14} {redact_key(value)}")
refactor: extract shared helpers to deduplicate repeated code patterns (#7917) * refactor: add shared helper modules for code deduplication New modules: - gateway/platforms/helpers.py: MessageDeduplicator, TextBatchAggregator, strip_markdown, ThreadParticipationTracker, redact_phone - hermes_cli/cli_output.py: print_info/success/warning/error, prompt helpers - tools/path_security.py: validate_within_dir, has_traversal_component - utils.py additions: safe_json_loads, read_json_file, read_jsonl, append_jsonl, env_str/lower/int/bool helpers - hermes_constants.py additions: get_config_path, get_skills_dir, get_logs_dir, get_env_path * refactor: migrate gateway adapters to shared helpers - MessageDeduplicator: discord, slack, dingtalk, wecom, weixin, mattermost - strip_markdown: bluebubbles, feishu, sms - redact_phone: sms, signal - ThreadParticipationTracker: discord, matrix - _acquire/_release_platform_lock: telegram, discord, slack, whatsapp, signal, weixin Net -316 lines across 19 files. * refactor: migrate CLI modules to shared helpers - tools_config.py: use cli_output print/prompt + curses_radiolist (-117 lines) - setup.py: use cli_output print helpers + curses_radiolist (-101 lines) - mcp_config.py: use cli_output prompt (-15 lines) - memory_setup.py: use curses_radiolist (-86 lines) Net -263 lines across 5 files. * refactor: migrate to shared utility helpers - safe_json_loads: agent/display.py (4 sites) - get_config_path: skill_utils.py, hermes_logging.py, hermes_time.py - get_skills_dir: skill_utils.py, prompt_builder.py - Token estimation dedup: skills_tool.py imports from model_metadata - Path security: skills_tool, cronjob_tools, skill_manager_tool, credential_files - Non-atomic YAML writes: doctor.py, config.py now use atomic_yaml_write - Platform dict: new platforms.py, skills_config + tools_config derive from it - Anthropic key: new get_anthropic_key() in auth.py, used by doctor/status/config/main * test: update tests for shared helper migrations - test_dingtalk: use _dedup.is_duplicate() instead of _is_duplicate() - test_mattermost: use _dedup instead of _seen_posts/_prune_seen - test_signal: import redact_phone from helpers instead of signal - test_discord_connect: _platform_lock_identity instead of _token_lock_identity - test_telegram_conflict: updated lock error message format - test_skill_manager_tool: 'escapes' instead of 'boundary' in error msgs
2026-04-11 13:59:52 -07:00
from hermes_cli.auth import get_anthropic_key
anthropic_value = get_anthropic_key()
print(f" {'Anthropic':<14} {redact_key(anthropic_value)}")
# Model settings
print()
print(color("◆ Model", Colors.CYAN, Colors.BOLD))
print(f" Model: {config.get('model', 'not set')}")
2026-03-07 21:01:23 -08:00
print(f" Max turns: {config.get('agent', {}).get('max_turns', DEFAULT_CONFIG['agent']['max_turns'])}")
# Display
print()
print(color("◆ Display", Colors.CYAN, Colors.BOLD))
display = config.get('display', {})
print(f" Personality: {display.get('personality', 'kawaii')}")
print(f" Reasoning: {'on' if display.get('show_reasoning', False) else 'off'}")
print(f" Bell: {'on' if display.get('bell_on_complete', False) else 'off'}")
2026-04-18 21:58:52 +02:00
ump = display.get('user_message_preview', {}) if isinstance(display.get('user_message_preview', {}), dict) else {}
ump_first = ump.get('first_lines', 2)
ump_last = ump.get('last_lines', 2)
print(f" User preview: first {ump_first} line(s), last {ump_last} line(s)")
# Terminal
print()
print(color("◆ Terminal", Colors.CYAN, Colors.BOLD))
terminal = config.get('terminal', {})
print(f" Backend: {terminal.get('backend', 'local')}")
print(f" Working dir: {terminal.get('cwd', '.')}")
print(f" Timeout: {terminal.get('timeout', 60)}s")
if terminal.get('backend') == 'docker':
print(f" Docker image: {terminal.get('docker_image', 'nikolaik/python-nodejs:python3.11-nodejs20')}")
elif terminal.get('backend') == 'singularity':
print(f" Image: {terminal.get('singularity_image', 'docker://nikolaik/python-nodejs:python3.11-nodejs20')}")
elif terminal.get('backend') == 'modal':
print(f" Modal image: {terminal.get('modal_image', 'nikolaik/python-nodejs:python3.11-nodejs20')}")
modal_token = get_env_value('MODAL_TOKEN_ID')
print(f" Modal token: {'configured' if modal_token else '(not set)'}")
elif terminal.get('backend') == 'daytona':
print(f" Daytona image: {terminal.get('daytona_image', 'nikolaik/python-nodejs:python3.11-nodejs20')}")
daytona_key = get_env_value('DAYTONA_API_KEY')
print(f" API key: {'configured' if daytona_key else '(not set)'}")
elif terminal.get('backend') == 'ssh':
ssh_host = get_env_value('TERMINAL_SSH_HOST')
ssh_user = get_env_value('TERMINAL_SSH_USER')
print(f" SSH host: {ssh_host or '(not set)'}")
print(f" SSH user: {ssh_user or '(not set)'}")
# Timezone
print()
print(color("◆ Timezone", Colors.CYAN, Colors.BOLD))
tz = config.get('timezone', '')
if tz:
print(f" Timezone: {tz}")
else:
print(f" Timezone: {color('(server-local)', Colors.DIM)}")
# Compression
print()
print(color("◆ Context Compression", Colors.CYAN, Colors.BOLD))
compression = config.get('compression', {})
enabled = compression.get('enabled', True)
print(f" Enabled: {'yes' if enabled else 'no'}")
if enabled:
print(f" Threshold: {compression.get('threshold', 0.50) * 100:.0f}%")
print(f" Target ratio: {compression.get('target_ratio', 0.20) * 100:.0f}% of threshold preserved")
print(f" Protect last: {compression.get('protect_last_n', 20)} messages")
_aux_comp = config.get('auxiliary', {}).get('compression', {})
_sm = _aux_comp.get('model', '') or '(auto)'
print(f" Model: {_sm}")
comp_provider = _aux_comp.get('provider', 'auto')
if comp_provider and comp_provider != 'auto':
print(f" Provider: {comp_provider}")
# Auxiliary models
auxiliary = config.get('auxiliary', {})
aux_tasks = {
"Vision": auxiliary.get('vision', {}),
"Web extract": auxiliary.get('web_extract', {}),
}
has_overrides = any(
t.get('provider', 'auto') != 'auto' or t.get('model', '')
for t in aux_tasks.values()
)
if has_overrides:
print()
print(color("◆ Auxiliary Models (overrides)", Colors.CYAN, Colors.BOLD))
for label, task_cfg in aux_tasks.items():
prov = task_cfg.get('provider', 'auto')
mdl = task_cfg.get('model', '')
if prov != 'auto' or mdl:
parts = [f"provider={prov}"]
if mdl:
parts.append(f"model={mdl}")
print(f" {label:12s} {', '.join(parts)}")
# Messaging
print()
print(color("◆ Messaging Platforms", Colors.CYAN, Colors.BOLD))
telegram_token = get_env_value('TELEGRAM_BOT_TOKEN')
discord_token = get_env_value('DISCORD_BOT_TOKEN')
print(f" Telegram: {'configured' if telegram_token else color('not configured', Colors.DIM)}")
print(f" Discord: {'configured' if discord_token else color('not configured', Colors.DIM)}")
# Skill config
try:
from agent.skill_utils import discover_all_skill_config_vars, resolve_skill_config_values
skill_vars = discover_all_skill_config_vars()
if skill_vars:
resolved = resolve_skill_config_values(skill_vars)
print()
print(color("◆ Skill Settings", Colors.CYAN, Colors.BOLD))
for var in skill_vars:
key = var["key"]
value = resolved.get(key, "")
skill_name = var.get("skill", "")
display_val = str(value) if value else color("(not set)", Colors.DIM)
print(f" {key:<20s} {display_val} {color(f'[{skill_name}]', Colors.DIM)}")
except Exception:
pass
print()
print(color("" * 60, Colors.DIM))
print(color(" hermes config edit # Edit config file", Colors.DIM))
print(color(" hermes config set <key> <value>", Colors.DIM))
print(color(" hermes setup # Run setup wizard", Colors.DIM))
print()
def edit_config():
"""Open config file in user's editor."""
feat: nix flake — uv2nix build, NixOS module, persistent container mode (#20) * feat: nix flake, uv2nix build, dev shell and home manager * fixed nix run, updated docs for setup * feat(nix): NixOS module with persistent container mode, managed guards, checks - Replace homeModules.nix with nixosModules.nix (two deployment modes) - Mode A (native): hardened systemd service with ProtectSystem=strict - Mode B (container): persistent Ubuntu container with /nix/store bind-mount, identity-hash-based recreation, GC root protection, symlink-based updates - Add HERMES_MANAGED guards blocking CLI config mutation (config set, setup, gateway install/uninstall) when running under NixOS module - Add nix/checks.nix with build-time verification (binary, CLI, managed guard) - Remove container.nix (no Nix-built OCI image; pulls ubuntu:24.04 at runtime) - Simplify packages.nix (drop fetchFromGitHub submodules, PYTHONPATH wrappers) - Rewrite docs/nixos-setup.md with full options reference, container architecture, secrets management, and troubleshooting guide Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * Update config.py * feat(nix): add CI workflow and enhanced build checks - GitHub Actions workflow for nix flake check + build on linux/macOS - Entry point sync check to catch pyproject.toml drift - Expanded managed-guard check to cover config edit - Wrap hermes-acp binary in Nix package - Fix Path type mismatch in is_managed() * Update MCP server package name; bundled skills support * fix reading .env. instead have container user a common mounted .env file * feat(nix): container entrypoint with privilege drop and sudo provisioning Container was running as non-root via --user, which broke apt/pip installs and caused crashes when $HOME didn't exist. Replace --user with a Nix-built entrypoint script that provisions the hermes user, sudo (NOPASSWD), and /home/hermes inside the container on first boot, then drops privileges via setpriv. Writable layer persists so setup only runs once. Also expands MCP server options to support HTTP transport and sampling. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix group and user creation in container mode * feat(nix): persistent /home/hermes and MESSAGING_CWD in container mode Container mode now bind-mounts ${stateDir}/home to /home/hermes so the agent's home directory survives container recreation. Previously it lived in the writable layer and was lost on image/volume/options changes. Also passes MESSAGING_CWD to the container so the agent finds its workspace and documents, matching native mode behavior. Other changes: - Extract containerDataDir/containerHomeDir bindings (no more magic strings) - Fix entrypoint chown to run unconditionally (volume mounts always exist) - Add schema field to container identity hash for auto-recreation - Add idempotency test (Scenario G) to config-roundtrip check * docs: add Nix & NixOS setup guide to docs site Add comprehensive Nix documentation to the Docusaurus site at website/docs/getting-started/nix-setup.md, covering nix run/profile install, NixOS module (native + container modes), declarative settings, secrets management, MCP servers, managed mode, container architecture, dev shell, flake checks, and full options reference. - Register nix-setup in sidebar after installation page - Add Nix callout tip to installation.md linking to new guide - Add canonical version pointer in docs/nixos-setup.md * docs: remove docs/nixos-setup.md, consolidate into website docs Backfill missing details (restart/restartSec in full example, gateway.pid, 0750 permissions, docker inspect commands) into the canonical website/docs/getting-started/nix-setup.md and delete the old standalone file. * fix(nix): add compression.protect_last_n and target_ratio to config-keys.json New keys were added to DEFAULT_CONFIG on main, causing the config-drift check to fail in CI. * fix(nix): skip checks on aarch64-darwin (onnxruntime wheel missing) The full Python venv includes onnxruntime (via faster-whisper/STT) which lacks a compatible uv2nix wheel on aarch64-darwin. Gate all checks behind stdenv.hostPlatform.isLinux. The package and devShell still evaluate on macOS. * fix(nix): skip flake check and build on macOS CI onnxruntime (transitive dep via faster-whisper) lacks a compatible uv2nix wheel on aarch64-darwin. Run full checks and build on Linux only; macOS CI verifies the flake evaluates without building. * fix(nix): preserve container writable layer across nixos-rebuild The container identity hash included the entrypoint's Nix store path, which changes on every nixpkgs update (due to runtimeShell/stdenv input-addressing). This caused false-positive identity mismatches, triggering container recreation and losing the persistent writable layer. - Use stable symlink (current-entrypoint) like current-package already does - Remove entrypoint from identity hash (only image/volumes/options matter) - Add GC root for entrypoint so nix-collect-garbage doesn't break it - Remove global HERMES_HOME env var from addToSystemPackages (conflicted with interactive CLI use, service already sets its own) --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-26 01:08:02 +05:30
if is_managed():
managed_error("edit configuration")
return
config_path = get_config_path()
# Ensure config exists
if not config_path.exists():
save_config(DEFAULT_CONFIG)
print(f"Created {config_path}")
# Find editor
editor = os.getenv('EDITOR') or os.getenv('VISUAL')
if not editor:
# Try common editors
for cmd in ['nano', 'vim', 'vi', 'code', 'notepad']:
import shutil
if shutil.which(cmd):
editor = cmd
break
if not editor:
print("No editor found. Config file is at:")
print(f" {config_path}")
return
print(f"Opening {config_path} in {editor}...")
subprocess.run([editor, str(config_path)])
def set_config_value(key: str, value: str):
"""Set a configuration value."""
feat: nix flake — uv2nix build, NixOS module, persistent container mode (#20) * feat: nix flake, uv2nix build, dev shell and home manager * fixed nix run, updated docs for setup * feat(nix): NixOS module with persistent container mode, managed guards, checks - Replace homeModules.nix with nixosModules.nix (two deployment modes) - Mode A (native): hardened systemd service with ProtectSystem=strict - Mode B (container): persistent Ubuntu container with /nix/store bind-mount, identity-hash-based recreation, GC root protection, symlink-based updates - Add HERMES_MANAGED guards blocking CLI config mutation (config set, setup, gateway install/uninstall) when running under NixOS module - Add nix/checks.nix with build-time verification (binary, CLI, managed guard) - Remove container.nix (no Nix-built OCI image; pulls ubuntu:24.04 at runtime) - Simplify packages.nix (drop fetchFromGitHub submodules, PYTHONPATH wrappers) - Rewrite docs/nixos-setup.md with full options reference, container architecture, secrets management, and troubleshooting guide Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * Update config.py * feat(nix): add CI workflow and enhanced build checks - GitHub Actions workflow for nix flake check + build on linux/macOS - Entry point sync check to catch pyproject.toml drift - Expanded managed-guard check to cover config edit - Wrap hermes-acp binary in Nix package - Fix Path type mismatch in is_managed() * Update MCP server package name; bundled skills support * fix reading .env. instead have container user a common mounted .env file * feat(nix): container entrypoint with privilege drop and sudo provisioning Container was running as non-root via --user, which broke apt/pip installs and caused crashes when $HOME didn't exist. Replace --user with a Nix-built entrypoint script that provisions the hermes user, sudo (NOPASSWD), and /home/hermes inside the container on first boot, then drops privileges via setpriv. Writable layer persists so setup only runs once. Also expands MCP server options to support HTTP transport and sampling. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix group and user creation in container mode * feat(nix): persistent /home/hermes and MESSAGING_CWD in container mode Container mode now bind-mounts ${stateDir}/home to /home/hermes so the agent's home directory survives container recreation. Previously it lived in the writable layer and was lost on image/volume/options changes. Also passes MESSAGING_CWD to the container so the agent finds its workspace and documents, matching native mode behavior. Other changes: - Extract containerDataDir/containerHomeDir bindings (no more magic strings) - Fix entrypoint chown to run unconditionally (volume mounts always exist) - Add schema field to container identity hash for auto-recreation - Add idempotency test (Scenario G) to config-roundtrip check * docs: add Nix & NixOS setup guide to docs site Add comprehensive Nix documentation to the Docusaurus site at website/docs/getting-started/nix-setup.md, covering nix run/profile install, NixOS module (native + container modes), declarative settings, secrets management, MCP servers, managed mode, container architecture, dev shell, flake checks, and full options reference. - Register nix-setup in sidebar after installation page - Add Nix callout tip to installation.md linking to new guide - Add canonical version pointer in docs/nixos-setup.md * docs: remove docs/nixos-setup.md, consolidate into website docs Backfill missing details (restart/restartSec in full example, gateway.pid, 0750 permissions, docker inspect commands) into the canonical website/docs/getting-started/nix-setup.md and delete the old standalone file. * fix(nix): add compression.protect_last_n and target_ratio to config-keys.json New keys were added to DEFAULT_CONFIG on main, causing the config-drift check to fail in CI. * fix(nix): skip checks on aarch64-darwin (onnxruntime wheel missing) The full Python venv includes onnxruntime (via faster-whisper/STT) which lacks a compatible uv2nix wheel on aarch64-darwin. Gate all checks behind stdenv.hostPlatform.isLinux. The package and devShell still evaluate on macOS. * fix(nix): skip flake check and build on macOS CI onnxruntime (transitive dep via faster-whisper) lacks a compatible uv2nix wheel on aarch64-darwin. Run full checks and build on Linux only; macOS CI verifies the flake evaluates without building. * fix(nix): preserve container writable layer across nixos-rebuild The container identity hash included the entrypoint's Nix store path, which changes on every nixpkgs update (due to runtimeShell/stdenv input-addressing). This caused false-positive identity mismatches, triggering container recreation and losing the persistent writable layer. - Use stable symlink (current-entrypoint) like current-package already does - Remove entrypoint from identity hash (only image/volumes/options matter) - Add GC root for entrypoint so nix-collect-garbage doesn't break it - Remove global HERMES_HOME env var from addToSystemPackages (conflicted with interactive CLI use, service already sets its own) --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-26 01:08:02 +05:30
if is_managed():
managed_error("set configuration values")
return
# Check if it's an API key (goes to .env)
api_keys = [
'OPENROUTER_API_KEY', 'OPENAI_API_KEY', 'ANTHROPIC_API_KEY', 'VOICE_TOOLS_OPENAI_KEY',
'EXA_API_KEY', 'PARALLEL_API_KEY', 'FIRECRAWL_API_KEY', 'FIRECRAWL_API_URL',
'FIRECRAWL_GATEWAY_URL', 'TOOL_GATEWAY_DOMAIN', 'TOOL_GATEWAY_SCHEME',
'TOOL_GATEWAY_USER_TOKEN', 'TAVILY_API_KEY',
'BROWSERBASE_API_KEY', 'BROWSERBASE_PROJECT_ID', 'BROWSER_USE_API_KEY',
'FAL_KEY', 'TELEGRAM_BOT_TOKEN', 'DISCORD_BOT_TOKEN',
'TERMINAL_SSH_HOST', 'TERMINAL_SSH_USER', 'TERMINAL_SSH_KEY',
'SUDO_PASSWORD', 'SLACK_BOT_TOKEN', 'SLACK_APP_TOKEN',
'GITHUB_TOKEN', 'HONCHO_API_KEY', 'WANDB_API_KEY',
'TINKER_API_KEY',
]
refactor: codebase-wide lint cleanup — unused imports, dead code, and inefficient patterns (#5821) Comprehensive cleanup across 80 files based on automated (ruff, pyflakes, vulture) and manual analysis of the entire codebase. Changes by category: Unused imports removed (~95 across 55 files): - Removed genuinely unused imports from all major subsystems - agent/, hermes_cli/, tools/, gateway/, plugins/, cron/ - Includes imports in try/except blocks that were truly unused (vs availability checks which were left alone) Unused variables removed (~25): - Removed dead variables: connected, inner, channels, last_exc, source, new_server_names, verify, pconfig, default_terminal, result, pending_handled, temperature, loop - Dropped unused argparse subparser assignments in hermes_cli/main.py (12 instances of add_parser() where result was never used) Dead code removed: - run_agent.py: Removed dead ternary (None if False else None) and surrounding unreachable branch in identity fallback - run_agent.py: Removed write-only attribute _last_reported_tool - hermes_cli/providers.py: Removed dead @property decorator on module-level function (decorator has no effect outside a class) - gateway/run.py: Removed unused MCP config load before reconnect - gateway/platforms/slack.py: Removed dead SessionSource construction Undefined name bugs fixed (would cause NameError at runtime): - batch_runner.py: Added missing logger = logging.getLogger(__name__) - tools/environments/daytona.py: Added missing Dict and Path imports Unnecessary global statements removed (14): - tools/terminal_tool.py: 5 functions declared global for dicts they only mutated via .pop()/[key]=value (no rebinding) - tools/browser_tool.py: cleanup thread loop only reads flag - tools/rl_training_tool.py: 4 functions only do dict mutations - tools/mcp_oauth.py: only reads the global - hermes_time.py: only reads cached values Inefficient patterns fixed: - startswith/endswith tuple form: 15 instances of x.startswith('a') or x.startswith('b') consolidated to x.startswith(('a', 'b')) - len(x)==0 / len(x)>0: 13 instances replaced with pythonic truthiness checks (not x / bool(x)) - in dict.keys(): 5 instances simplified to in dict - Redefined unused name: removed duplicate _strip_mdv2 import in send_message_tool.py Other fixes: - hermes_cli/doctor.py: Replaced undefined logger.debug() with pass - hermes_cli/config.py: Consolidated chained .endswith() calls Test results: 3934 passed, 17 failed (all pre-existing on main), 19 skipped. Zero regressions.
2026-04-07 10:25:31 -07:00
if key.upper() in api_keys or key.upper().endswith(('_API_KEY', '_TOKEN')) or key.upper().startswith('TERMINAL_SSH'):
save_env_value(key.upper(), value)
print(f"✓ Set {key} in {get_env_path()}")
return
# Otherwise it goes to config.yaml
# Read the raw user config (not merged with defaults) to avoid
# dumping all default values back to the file
config_path = get_config_path()
user_config = {}
if config_path.exists():
try:
with open(config_path, encoding="utf-8") as f:
user_config = yaml.safe_load(f) or {}
except Exception:
user_config = {}
# Handle nested keys (e.g., "tts.provider")
parts = key.split('.')
current = user_config
for part in parts[:-1]:
if part not in current or not isinstance(current.get(part), dict):
current[part] = {}
current = current[part]
# Convert value to appropriate type
if value.lower() in ('true', 'yes', 'on'):
value = True
elif value.lower() in ('false', 'no', 'off'):
value = False
elif value.isdigit():
value = int(value)
elif value.replace('.', '', 1).isdigit():
value = float(value)
current[parts[-1]] = value
# Write only user config back (not the full merged defaults)
ensure_hermes_home()
refactor: extract shared helpers to deduplicate repeated code patterns (#7917) * refactor: add shared helper modules for code deduplication New modules: - gateway/platforms/helpers.py: MessageDeduplicator, TextBatchAggregator, strip_markdown, ThreadParticipationTracker, redact_phone - hermes_cli/cli_output.py: print_info/success/warning/error, prompt helpers - tools/path_security.py: validate_within_dir, has_traversal_component - utils.py additions: safe_json_loads, read_json_file, read_jsonl, append_jsonl, env_str/lower/int/bool helpers - hermes_constants.py additions: get_config_path, get_skills_dir, get_logs_dir, get_env_path * refactor: migrate gateway adapters to shared helpers - MessageDeduplicator: discord, slack, dingtalk, wecom, weixin, mattermost - strip_markdown: bluebubbles, feishu, sms - redact_phone: sms, signal - ThreadParticipationTracker: discord, matrix - _acquire/_release_platform_lock: telegram, discord, slack, whatsapp, signal, weixin Net -316 lines across 19 files. * refactor: migrate CLI modules to shared helpers - tools_config.py: use cli_output print/prompt + curses_radiolist (-117 lines) - setup.py: use cli_output print helpers + curses_radiolist (-101 lines) - mcp_config.py: use cli_output prompt (-15 lines) - memory_setup.py: use curses_radiolist (-86 lines) Net -263 lines across 5 files. * refactor: migrate to shared utility helpers - safe_json_loads: agent/display.py (4 sites) - get_config_path: skill_utils.py, hermes_logging.py, hermes_time.py - get_skills_dir: skill_utils.py, prompt_builder.py - Token estimation dedup: skills_tool.py imports from model_metadata - Path security: skills_tool, cronjob_tools, skill_manager_tool, credential_files - Non-atomic YAML writes: doctor.py, config.py now use atomic_yaml_write - Platform dict: new platforms.py, skills_config + tools_config derive from it - Anthropic key: new get_anthropic_key() in auth.py, used by doctor/status/config/main * test: update tests for shared helper migrations - test_dingtalk: use _dedup.is_duplicate() instead of _is_duplicate() - test_mattermost: use _dedup instead of _seen_posts/_prune_seen - test_signal: import redact_phone from helpers instead of signal - test_discord_connect: _platform_lock_identity instead of _token_lock_identity - test_telegram_conflict: updated lock error message format - test_skill_manager_tool: 'escapes' instead of 'boundary' in error msgs
2026-04-11 13:59:52 -07:00
from utils import atomic_yaml_write
atomic_yaml_write(config_path, user_config, sort_keys=False)
# Keep .env in sync for keys that terminal_tool reads directly from env vars.
# config.yaml is authoritative, but terminal_tool only reads TERMINAL_ENV etc.
_config_to_env_sync = {
"terminal.backend": "TERMINAL_ENV",
"terminal.modal_mode": "TERMINAL_MODAL_MODE",
"terminal.docker_image": "TERMINAL_DOCKER_IMAGE",
"terminal.singularity_image": "TERMINAL_SINGULARITY_IMAGE",
"terminal.modal_image": "TERMINAL_MODAL_IMAGE",
"terminal.daytona_image": "TERMINAL_DAYTONA_IMAGE",
"terminal.docker_mount_cwd_to_workspace": "TERMINAL_DOCKER_MOUNT_CWD_TO_WORKSPACE",
"terminal.cwd": "TERMINAL_CWD",
"terminal.timeout": "TERMINAL_TIMEOUT",
"terminal.sandbox_dir": "TERMINAL_SANDBOX_DIR",
"terminal.persistent_shell": "TERMINAL_PERSISTENT_SHELL",
"terminal.container_cpu": "TERMINAL_CONTAINER_CPU",
"terminal.container_memory": "TERMINAL_CONTAINER_MEMORY",
"terminal.container_disk": "TERMINAL_CONTAINER_DISK",
"terminal.container_persistent": "TERMINAL_CONTAINER_PERSISTENT",
}
if key in _config_to_env_sync:
save_env_value(_config_to_env_sync[key], str(value))
print(f"✓ Set {key} = {value} in {config_path}")
# =============================================================================
# Command handler
# =============================================================================
def config_command(args):
"""Handle config subcommands."""
subcmd = getattr(args, 'config_command', None)
if subcmd is None or subcmd == "show":
show_config()
elif subcmd == "edit":
edit_config()
elif subcmd == "set":
key = getattr(args, 'key', None)
value = getattr(args, 'value', None)
if not key or value is None:
print("Usage: hermes config set <key> <value>")
print()
print("Examples:")
print(" hermes config set model anthropic/claude-sonnet-4")
print(" hermes config set terminal.backend docker")
print(" hermes config set OPENROUTER_API_KEY sk-or-...")
sys.exit(1)
set_config_value(key, value)
elif subcmd == "path":
print(get_config_path())
elif subcmd == "env-path":
print(get_env_path())
elif subcmd == "migrate":
print()
print(color("🔄 Checking configuration for updates...", Colors.CYAN, Colors.BOLD))
print()
# Check what's missing
missing_env = get_missing_env_vars(required_only=False)
missing_config = get_missing_config_fields()
current_ver, latest_ver = check_config_version()
if not missing_env and not missing_config and current_ver >= latest_ver:
print(color("✓ Configuration is up to date!", Colors.GREEN))
print()
return
# Show what needs to be updated
if current_ver < latest_ver:
print(f" Config version: {current_ver}{latest_ver}")
if missing_config:
print(f"\n {len(missing_config)} new config option(s) will be added with defaults")
required_missing = [v for v in missing_env if v.get("is_required")]
optional_missing = [
v for v in missing_env
if not v.get("is_required") and not v.get("advanced")
]
if required_missing:
print(f"\n ⚠️ {len(required_missing)} required API key(s) missing:")
for var in required_missing:
print(f"{var['name']}")
if optional_missing:
print(f"\n {len(optional_missing)} optional API key(s) not configured:")
for var in optional_missing:
tools = var.get("tools", [])
tools_str = f" (enables: {', '.join(tools[:2])})" if tools else ""
print(f"{var['name']}{tools_str}")
print()
# Run migration
results = migrate_config(interactive=True, quiet=False)
print()
if results["env_added"] or results["config_added"]:
print(color("✓ Configuration updated!", Colors.GREEN))
if results["warnings"]:
print()
for warning in results["warnings"]:
print(color(f" ⚠️ {warning}", Colors.YELLOW))
print()
elif subcmd == "check":
# Non-interactive check for what's missing
print()
print(color("📋 Configuration Status", Colors.CYAN, Colors.BOLD))
print()
current_ver, latest_ver = check_config_version()
if current_ver >= latest_ver:
print(f" Config version: {current_ver}")
else:
print(color(f" Config version: {current_ver}{latest_ver} (update available)", Colors.YELLOW))
print()
print(color(" Required:", Colors.BOLD))
for var_name in REQUIRED_ENV_VARS:
if get_env_value(var_name):
print(f"{var_name}")
else:
print(color(f"{var_name} (missing)", Colors.RED))
print()
print(color(" Optional:", Colors.BOLD))
for var_name, info in OPTIONAL_ENV_VARS.items():
if get_env_value(var_name):
print(f"{var_name}")
else:
tools = info.get("tools", [])
tools_str = f"{', '.join(tools[:2])}" if tools else ""
print(color(f"{var_name}{tools_str}", Colors.DIM))
missing_config = get_missing_config_fields()
if missing_config:
print()
print(color(f" {len(missing_config)} new config option(s) available", Colors.YELLOW))
print(" Run 'hermes config migrate' to add them")
print()
else:
print(f"Unknown config command: {subcmd}")
print()
print("Available commands:")
print(" hermes config Show current configuration")
print(" hermes config edit Open config in editor")
print(" hermes config set <key> <value> Set a config value")
print(" hermes config check Check for missing/outdated config")
print(" hermes config migrate Update config with new options")
print(" hermes config path Show config file path")
print(" hermes config env-path Show .env file path")
sys.exit(1)