common/hermes
2
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

refactor: extract shared helpers to deduplicate repeated code patterns (#7917)

Browse Source 
* 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
This commit is contained in:
Teknium
2026-04-11 13:59:52 -07:00
committed by GitHub
parent cf53e2676b
commit 04c1c5d53f
49 changed files with 887 additions and 949 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
tools/credential_files.py
View File

@@ -80,20 +80,18 @@ def register_credential_file(
# Resolve symlinks and normalise ``..`` before the containment check so
# that traversal like ``../. ssh/id_rsa`` cannot escape HERMES_HOME.
try:
resolved = host_path.resolve()
hermes_home_resolved = hermes_home.resolve()
resolved.relative_to(hermes_home_resolved) # raises ValueError if outside
except ValueError:
from tools.path_security import validate_within_dir
containment_error = validate_within_dir(host_path, hermes_home)
if containment_error:
logger.warning(
"credential_files: rejected path traversal %r "
"(resolves to %s, outside HERMES_HOME %s)",
"credential_files: rejected path traversal %r (%s)",
relative_path,
resolved,
hermes_home_resolved,
containment_error,
)
return False
resolved = host_path.resolve()
if not resolved.is_file():
logger.debug("credential_files: skipping %s (not found)", resolved)
return False
@@ -142,7 +140,8 @@ def _load_config_files() -> List[Dict[str, str]]:
cfg = read_raw_config()
cred_files = cfg.get("terminal", {}).get("credential_files")
if isinstance(cred_files, list):
hermes_home_resolved = hermes_home.resolve()
from tools.path_security import validate_within_dir
for item in cred_files:
if isinstance(item, str) and item.strip():
rel = item.strip()
@@ -151,20 +150,19 @@ def _load_config_files() -> List[Dict[str, str]]:
"credential_files: rejected absolute config path %r", rel,
)
continue
host_path = (hermes_home / rel).resolve()
try:
host_path.relative_to(hermes_home_resolved)
except ValueError:
host_path = hermes_home / rel
containment_error = validate_within_dir(host_path, hermes_home)
if containment_error:
logger.warning(
"credential_files: rejected config path traversal %r "
"(resolves to %s, outside HERMES_HOME %s)",
rel, host_path, hermes_home_resolved,
"credential_files: rejected config path traversal %r (%s)",
rel, containment_error,
)
continue
if host_path.is_file():
resolved_path = host_path.resolve()
if resolved_path.is_file():
container_path = f"/root/.hermes/{rel}"
result.append({
"host_path": str(host_path),
"host_path": str(resolved_path),
"container_path": container_path,
})
except Exception as e:

8
tools/cronjob_tools.py
View File

@@ -165,12 +165,12 @@ def _validate_cron_script_path(script: Optional[str]) -> Optional[str]:
)
# Validate containment after resolution
from tools.path_security import validate_within_dir
scripts_dir = get_hermes_home() / "scripts"
scripts_dir.mkdir(parents=True, exist_ok=True)
resolved = (scripts_dir / raw).resolve()
try:
resolved.relative_to(scripts_dir.resolve())
except ValueError:
containment_error = validate_within_dir(scripts_dir / raw, scripts_dir)
if containment_error:
return (
f"Script path escapes the scripts directory via traversal: {raw!r}"
)

43
tools/path_security.py Normal file
View File

@@ -0,0 +1,43 @@
"""Shared path validation helpers for tool implementations.
Extracts the ``resolve() + relative_to()`` and ``..`` traversal check
patterns previously duplicated across skill_manager_tool, skills_tool,
skills_hub, cronjob_tools, and credential_files.
"""
import logging
from pathlib import Path
from typing import Optional
logger = logging.getLogger(__name__)
def validate_within_dir(path: Path, root: Path) -> Optional[str]:
"""Ensure *path* resolves to a location within *root*.
Returns an error message string if validation fails, or ``None`` if the
path is safe. Uses ``Path.resolve()`` to follow symlinks and normalize
``..`` components.
Usage::
error = validate_within_dir(user_path, allowed_root)
if error:
return json.dumps({"error": error})
"""
try:
resolved = path.resolve()
root_resolved = root.resolve()
resolved.relative_to(root_resolved)
except (ValueError, OSError) as exc:
return f"Path escapes allowed directory: {exc}"
return None
def has_traversal_component(path_str: str) -> bool:
"""Return True if *path_str* contains ``..`` traversal components.
Quick check for obvious traversal attempts before doing full resolution.
"""
parts = Path(path_str).parts
return ".." in parts

17
tools/skill_manager_tool.py
View File

@@ -219,13 +219,15 @@ def _validate_file_path(file_path: str) -> Optional[str]:
Validate a file path for write_file/remove_file.
Must be under an allowed subdirectory and not escape the skill dir.
"""
from tools.path_security import has_traversal_component
if not file_path:
return "file_path is required."
normalized = Path(file_path)
# Prevent path traversal
if ".." in normalized.parts:
if has_traversal_component(file_path):
return "Path traversal ('..') is not allowed."
# Must be under an allowed subdirectory
@@ -242,15 +244,12 @@ def _validate_file_path(file_path: str) -> Optional[str]:
def _resolve_skill_target(skill_dir: Path, file_path: str) -> Tuple[Optional[Path], Optional[str]]:
"""Resolve a supporting-file path and ensure it stays within the skill directory."""
from tools.path_security import validate_within_dir
target = skill_dir / file_path
try:
resolved = target.resolve(strict=False)
skill_dir_resolved = skill_dir.resolve()
resolved.relative_to(skill_dir_resolved)
except ValueError:
return None, "Path escapes skill directory boundary."
except OSError as e:
return None, f"Invalid file path '{file_path}': {e}"
error = validate_within_dir(target, skill_dir)
if error:
return None, error
return target, None

37
tools/skills_tool.py
View File

@@ -447,17 +447,8 @@ def _get_category_from_path(skill_path: Path) -> Optional[str]:
return None
def _estimate_tokens(content: str) -> int:
"""
Rough token estimate (4 chars per token average).
Args:
content: Text content
Returns:
Estimated token count
"""
return len(content) // 4
# Token estimation — use the shared implementation from model_metadata.
from agent.model_metadata import estimate_tokens_rough as _estimate_tokens
def _parse_tags(tags_value) -> List[str]:
@@ -947,9 +938,10 @@ def skill_view(name: str, file_path: str = None, task_id: str = None) -> str:
# If a specific file path is requested, read that instead
if file_path and skill_dir:
from tools.path_security import validate_within_dir, has_traversal_component
# Security: Prevent path traversal attacks
normalized_path = Path(file_path)
if ".." in normalized_path.parts:
if has_traversal_component(file_path):
return json.dumps(
{
"success": False,
@@ -962,24 +954,13 @@ def skill_view(name: str, file_path: str = None, task_id: str = None) -> str:
target_file = skill_dir / file_path
# Security: Verify resolved path is still within skill directory
try:
resolved = target_file.resolve()
skill_dir_resolved = skill_dir.resolve()
if not resolved.is_relative_to(skill_dir_resolved):
return json.dumps(
{
"success": False,
"error": "Path escapes skill directory boundary.",
"hint": "Use a relative path within the skill directory",
},
ensure_ascii=False,
)
except (OSError, ValueError):
traversal_error = validate_within_dir(target_file, skill_dir)
if traversal_error:
return json.dumps(
{
"success": False,
"error": f"Invalid file path: '{file_path}'",
"hint": "Use a valid relative path within the skill directory",
"error": traversal_error,
"hint": "Use a relative path within the skill directory",
},
ensure_ascii=False,
)