Merge branch 'main' of github.com:NousResearch/hermes-agent into bb/gui

This commit is contained in:
Brooklyn Nicholson
2026-05-21 13:53:53 -05:00
105 changed files with 5022 additions and 1714 deletions
+7 -13
View File
@@ -48,7 +48,7 @@ import httpx
import yaml
from hermes_cli.config import get_hermes_home, get_config_path, read_raw_config
from hermes_constants import OPENROUTER_BASE_URL
from hermes_constants import OPENROUTER_BASE_URL, secure_parent_dir
from utils import atomic_replace, atomic_yaml_write, is_truthy_value
logger = logging.getLogger(__name__)
@@ -1030,10 +1030,8 @@ def _save_auth_store(auth_store: Dict[str, Any]) -> Path:
auth_file.parent.mkdir(parents=True, exist_ok=True)
# Tighten parent dir to 0o700 so siblings can't traverse to creds.
# No-op on Windows (POSIX mode bits not enforced); ignore failures.
try:
os.chmod(auth_file.parent, 0o700)
except OSError:
pass
# secure_parent_dir refuses to chmod / or top-level dirs (#25821).
secure_parent_dir(auth_file)
auth_store["version"] = AUTH_STORE_VERSION
auth_store["updated_at"] = datetime.now(timezone.utc).isoformat()
payload = json.dumps(auth_store, indent=2) + "\n"
@@ -1863,10 +1861,8 @@ def _read_qwen_cli_tokens() -> Dict[str, Any]:
def _save_qwen_cli_tokens(tokens: Dict[str, Any]) -> Path:
auth_path = _qwen_cli_auth_path()
auth_path.parent.mkdir(parents=True, exist_ok=True)
try:
os.chmod(auth_path.parent, 0o700)
except OSError:
pass
# secure_parent_dir refuses to chmod / or top-level dirs (#25821).
secure_parent_dir(auth_path)
# Per-process random temp suffix avoids collisions between concurrent
# writers and stale leftovers from a crashed prior write.
tmp_path = auth_path.with_name(f"{auth_path.name}.tmp.{os.getpid()}.{uuid.uuid4().hex}")
@@ -4168,10 +4164,8 @@ def _write_shared_nous_state(state: Dict[str, Any]) -> None:
with _nous_shared_store_lock():
path = _nous_shared_store_path()
path.parent.mkdir(parents=True, exist_ok=True)
try:
os.chmod(path.parent, 0o700)
except OSError:
pass
# secure_parent_dir refuses to chmod / or top-level dirs (#25821).
secure_parent_dir(path)
tmp = path.with_name(f"{path.name}.tmp.{os.getpid()}.{uuid.uuid4().hex}")
# Create with 0o600 atomically via os.open(O_EXCL) — closes the TOCTOU
# window where write_text() + post-write chmod briefly exposed Nous
+66 -3
View File
@@ -508,6 +508,68 @@ def telegram_bot_commands() -> list[tuple[str, str]]:
return result
_TELEGRAM_MENU_PRIORITY = (
# Most-typed everyday commands first.
"help",
"new",
"stop",
"status",
"resume",
"sessions",
"model",
# Maintenance / diagnostics — the ones that prompted this priority list.
"debug",
"restart",
"update",
"verbose",
"commands",
# Mid-turn session control.
"approve",
"deny",
"queue",
"steer",
"background",
# Lower-priority but still useful operational built-ins.
"reasoning",
"usage",
"platforms",
"platform",
"profile",
"whoami",
)
"""Built-in commands that should stay visible in Telegram's capped menu.
Telegram only displays a small BotCommand menu in practice. The full Hermes
registry is still dispatchable when typed manually, but operational commands
need to survive the visible menu cap ahead of lower-priority built-ins.
"""
def _prioritize_telegram_menu_commands(
commands: list[tuple[str, str]],
) -> list[tuple[str, str]]:
priority = {
_sanitize_telegram_name(name): index
for index, name in enumerate(_TELEGRAM_MENU_PRIORITY)
}
return [
command
for _index, command in sorted(
enumerate(commands),
key=lambda item: (
0,
priority[item[1][0]],
item[0],
)
if item[1][0] in priority
else (
1,
item[0],
),
)
]
_CMD_NAME_LIMIT = 32
"""Max command name length shared by Telegram and Discord."""
@@ -721,11 +783,12 @@ def telegram_menu_commands(max_commands: int = 100) -> tuple[list[tuple[str, str
Returns:
(menu_commands, hidden_count) where hidden_count is the number of
skill commands omitted due to the cap.
commands omitted due to the cap.
"""
core_commands = list(telegram_bot_commands())
core_commands = _prioritize_telegram_menu_commands(list(telegram_bot_commands()))
reserved_names = {n for n, _ in core_commands}
all_commands = list(core_commands)
hidden_core_count = max(0, len(all_commands) - max_commands)
remaining_slots = max(0, max_commands - len(all_commands))
entries, hidden_count = _collect_gateway_skill_entries(
@@ -737,7 +800,7 @@ def telegram_menu_commands(max_commands: int = 100) -> tuple[list[tuple[str, str
)
# Drop the cmd_key — Telegram only needs (name, desc) pairs.
all_commands.extend((n, d) for n, d, _k in entries)
return all_commands[:max_commands], hidden_count
return all_commands[:max_commands], hidden_count + hidden_core_count
def discord_skill_commands(
+6 -2
View File
@@ -3016,7 +3016,7 @@ def _normalize_custom_provider_entry(
"api_mode", "transport", "model", "default_model", "models",
"context_length", "rate_limit_delay",
"request_timeout_seconds", "stale_timeout_seconds",
"discover_models",
"discover_models", "extra_body",
}
for camel, snake in _CAMEL_ALIASES.items():
if camel in entry and snake not in entry:
@@ -3111,6 +3111,10 @@ def _normalize_custom_provider_entry(
if isinstance(discover_models, bool):
normalized["discover_models"] = discover_models
extra_body = entry.get("extra_body")
if isinstance(extra_body, dict):
normalized["extra_body"] = dict(extra_body)
return normalized
@@ -3271,7 +3275,7 @@ _KNOWN_ROOT_KEYS = {
# 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",
"context_length", "rate_limit_delay", "extra_body",
# key_env is read at runtime by runtime_provider.py and auxiliary_client.py
# — include it here so the set accurately describes the supported schema.
"key_env",
+53
View File
@@ -951,6 +951,58 @@ CREATE INDEX IF NOT EXISTS idx_notify_task ON kanban_notify_subs(task_
_INITIALIZED_PATHS: set[str] = set()
_INIT_LOCK = threading.RLock()
_SQLITE_HEADER = b"SQLite format 3\x00"
def _looks_like_tls_record_at(data: bytes, offset: int) -> bool:
"""Return True for a TLS record header at ``data[offset:]``."""
if len(data) < offset + 5:
return False
content_type = data[offset]
major = data[offset + 1]
minor = data[offset + 2]
length = int.from_bytes(data[offset + 3:offset + 5], "big")
return (
content_type in {0x14, 0x15, 0x16, 0x17}
and major == 0x03
and minor in {0x00, 0x01, 0x02, 0x03, 0x04}
and 0 < length <= 18432
)
def _validate_sqlite_header(path: Path) -> None:
"""Fail early with an actionable error for non-SQLite Kanban DB files.
``sqlite3.connect()`` creates missing and zero-byte files, so those are
allowed. Existing non-empty files must have the SQLite header before we
hand them to SQLite/WAL setup. This keeps corrupted page-0 failures from
being collapsed into a generic PRAGMA error and lets the gateway's corrupt
board handling identify the board by fingerprint.
"""
try:
stat = path.stat()
except FileNotFoundError:
return
except OSError:
return
if stat.st_size == 0:
return
try:
with path.open("rb") as handle:
head = handle.read(64)
except OSError:
return
if head.startswith(_SQLITE_HEADER):
return
signature = ""
if head.startswith(b"SQLit") and _looks_like_tls_record_at(head, 5):
signature = " (TLS record header detected at byte offset 5)"
elif _looks_like_tls_record_at(head, 0):
signature = " (TLS record header detected at byte offset 0)"
raise sqlite3.DatabaseError(
"file is not a database: invalid SQLite header for "
f"{path}{signature}; first_32={head[:32].hex(' ')}"
)
def connect(
@@ -981,6 +1033,7 @@ def connect(
else:
path = kanban_db_path(board=board)
path.parent.mkdir(parents=True, exist_ok=True)
_validate_sqlite_header(path)
resolved = str(path.resolve())
conn = sqlite3.connect(str(path), isolation_level=None, timeout=30)
try:
+24 -12
View File
@@ -6112,24 +6112,36 @@ def _validate_critical_files_syntax(root) -> tuple[bool, str | None, str | None]
them after a successful ``git pull`` so we can auto-roll-back instead of
leaving the user with a bricked install.
The compiled ``.pyc`` is written to a temp directory rather than the
source tree's ``__pycache__/`` so we don't race with concurrent test
workers that walk the same dir, and so we don't leave a stale pyc
behind in production if the next interpreter run picks a different
Python version. The pyc is discarded on function return either way
we only care about the compile-or-not signal.
Returns ``(ok, failing_path, error_message)``. ``ok=True`` means every
file parsed cleanly.
"""
import py_compile
import tempfile
root = Path(root)
for relpath in _UPDATE_CRITICAL_FILES:
path = root / relpath
if not path.exists():
# Missing file is suspicious but not necessarily fatal — a future
# refactor may legitimately remove one of these. Skip and move on.
continue
try:
py_compile.compile(str(path), doraise=True)
except py_compile.PyCompileError as exc:
return False, str(path), str(exc)
except OSError as exc:
return False, str(path), f"could not read: {exc}"
with tempfile.TemporaryDirectory(prefix="hermes-syntax-check-") as tmpdir:
for relpath in _UPDATE_CRITICAL_FILES:
path = root / relpath
if not path.exists():
# Missing file is suspicious but not necessarily fatal — a future
# refactor may legitimately remove one of these. Skip and move on.
continue
# Mirror the relative path under the tmpdir so two different
# files with the same basename don't collide on the cfile name.
cfile = Path(tmpdir) / (relpath.replace("/", "__") + "c")
try:
py_compile.compile(str(path), cfile=str(cfile), doraise=True)
except py_compile.PyCompileError as exc:
return False, str(path), str(exc)
except OSError as exc:
return False, str(path), f"could not read: {exc}"
return True, None, None
+43 -1
View File
@@ -902,7 +902,49 @@ def delete_profile(name: str, yes: bool = False) -> Path:
# 4. Remove profile directory
try:
shutil.rmtree(profile_dir)
def _make_writable(func, path, exc):
"""onexc/onerror handler: add +w on PermissionError so rmtree can proceed.
Handles two cases on NixOS (and other systems with read-only
copies from immutable stores):
1. The path itself isn't writable (e.g. a file with mode 0444)
2. The *parent* directory isn't writable (e.g. mode 0555)
Compatible with both the ``onexc`` API (3.12+, receives an
exception instance) and the ``onerror`` API (3.11-, receives
``sys.exc_info()`` tuple).
"""
import stat as _stat
import sys as _sys
# Normalise the two callback signatures:
# onexc(func, path, exc_instance) — 3.12+
# onerror(func, path, exc_info_tuple) — 3.11
if isinstance(exc, tuple):
exc = exc[1] # exc_info → actual exception object
if isinstance(exc, PermissionError):
# Make the path writable
try:
os.chmod(path, os.stat(path).st_mode | _stat.S_IWUSR)
except OSError:
pass
# Also make the parent writable (needed for unlink/rmdir)
parent = os.path.dirname(path)
if parent:
try:
os.chmod(parent, os.stat(parent).st_mode | _stat.S_IWUSR)
except OSError:
pass
func(path)
else:
raise
# ``onexc`` was added in 3.12; fall back to ``onerror`` on 3.11.
try:
shutil.rmtree(profile_dir, onexc=_make_writable)
except TypeError:
shutil.rmtree(profile_dir, onerror=_make_writable)
print(f"✓ Removed {profile_dir}")
except Exception as e:
print(f"⚠ Could not remove {profile_dir}: {e}")
+124 -9
View File
@@ -100,6 +100,63 @@ def _detect_api_mode_for_url(base_url: str) -> Optional[str]:
return None
def _host_derived_api_key(base_url: str) -> str:
"""Look up `<VENDOR>_API_KEY` in the env, derived from the base URL host.
Examples:
https://api.deepseek.com/v1 DEEPSEEK_API_KEY
https://api.groq.com/openai/v1 GROQ_API_KEY
https://api.mistral.ai/v1 MISTRAL_API_KEY
https://generativelanguage.googleapis.com/v1beta/openai/ GOOGLEAPIS_API_KEY
Returns the env value (stripped) or "". Never returns env vars whose names
are already explicitly checked elsewhere those are handled by their own
host-gated paths (OPENAI/OPENROUTER/OLLAMA).
The vendor label is the *registrable* portion of the hostname: strip
``api.`` / ``www.`` prefixes, then take the second-to-last label
(``api.deepseek.com`` ``deepseek``). Falls back to "" for hostnames
that don't yield a usable vendor label (IPs, loopback, single-label
hosts).
"""
hostname = base_url_hostname(base_url)
if not hostname:
return ""
# Reject IPv4 / IPv6 / loopback — no meaningful vendor label.
if any(ch.isdigit() for ch in hostname.split(".")[-1]):
# Last label starts with a digit → likely IP. (TLDs are never numeric.)
return ""
if hostname in ("localhost",) or ":" in hostname:
return ""
labels = [lbl for lbl in hostname.split(".") if lbl]
# Strip common API/CDN prefixes.
while labels and labels[0] in ("api", "www"):
labels.pop(0)
if len(labels) < 2:
return ""
# Take the *registrable* label (second-to-last). For typical provider
# hosts this is what users intuitively call "the vendor":
# deepseek.com → labels[-2] = "deepseek" ✓
# api.groq.com → groq.com → labels[-2] = "groq" ✓
# api.mistral.ai → labels[-2] = "mistral" ✓
# Crucially, lookalike hosts pick the ATTACKER's label, not the spoofed
# vendor:
# api.deepseek.com.attacker.test → labels[-2] = "attacker"
# so DEEPSEEK_API_KEY stays put and the chain falls through to
# no-key-required. This mirrors how `base_url_host_matches` resists the
# same lookalike attack for explicit hosts.
vendor = labels[-2]
# Sanitize to env var charset: A-Z, 0-9, underscore.
sanitized = "".join(ch if ch.isalnum() else "_" for ch in vendor).upper()
if not sanitized or not sanitized[0].isalpha():
return ""
# Don't re-derive env vars already handled by explicit host-gated paths.
if sanitized in ("OPENAI", "OPENROUTER", "OLLAMA"):
return ""
env_name = f"{sanitized}_API_KEY"
return (os.getenv(env_name, "") or "").strip()
def _auto_detect_local_model(base_url: str) -> str:
"""Query a local server for its model name when only one model is loaded."""
if not base_url:
@@ -471,6 +528,9 @@ def _get_named_custom_provider(requested_provider: str) -> Optional[Dict[str, An
"api_key": resolved_api_key,
"model": entry.get("default_model", ""),
}
extra_body = entry.get("extra_body")
if isinstance(extra_body, dict):
result["extra_body"] = dict(extra_body)
# The v11→v12 migration writes the API mode under the new
# ``transport`` field, but hand-edited configs may still
# use the legacy ``api_mode`` spelling. Accept both —
@@ -496,6 +556,9 @@ def _get_named_custom_provider(requested_provider: str) -> Optional[Dict[str, An
"api_key": resolved_api_key,
"model": entry.get("default_model", ""),
}
extra_body = entry.get("extra_body")
if isinstance(extra_body, dict):
result["extra_body"] = dict(extra_body)
api_mode = _parse_api_mode(entry.get("api_mode") or entry.get("transport"))
if api_mode:
result["api_mode"] = api_mode
@@ -539,6 +602,9 @@ def _get_named_custom_provider(requested_provider: str) -> Optional[Dict[str, An
result["key_env"] = key_env
if provider_key:
result["provider_key"] = provider_key
extra_body = entry.get("extra_body")
if isinstance(extra_body, dict):
result["extra_body"] = dict(extra_body)
api_mode = _parse_api_mode(entry.get("api_mode"))
if api_mode:
result["api_mode"] = api_mode
@@ -550,6 +616,13 @@ def _get_named_custom_provider(requested_provider: str) -> Optional[Dict[str, An
return None
def _custom_provider_request_overrides(custom_provider: Dict[str, Any]) -> Dict[str, Any]:
extra_body = custom_provider.get("extra_body")
if not isinstance(extra_body, dict) or not extra_body:
return {}
return {"extra_body": dict(extra_body)}
def _resolve_named_custom_runtime(
*,
requested_provider: str,
@@ -582,10 +655,17 @@ def _resolve_named_custom_runtime(
if pool_result:
pool_result["source"] = "direct-alias"
return pool_result
_da_is_openai_url = base_url_host_matches(base_url, "openai.com") or base_url_host_matches(base_url, "openai.azure.com")
_da_is_openrouter = base_url_host_matches(base_url, "openrouter.ai")
api_key_candidates = [
(explicit_api_key or "").strip(),
os.getenv("OPENAI_API_KEY", "").strip(),
os.getenv("OPENROUTER_API_KEY", "").strip(),
# Gate env key fallbacks on authoritative hosts (#28660)
(os.getenv("OPENAI_API_KEY", "").strip() if _da_is_openai_url else ""),
(os.getenv("OPENROUTER_API_KEY", "").strip() if _da_is_openrouter else ""),
# Bonus (#28660): derive `<VENDOR>_API_KEY` from the host so users
# who set DEEPSEEK_API_KEY / GROQ_API_KEY / MISTRAL_API_KEY get the
# intuitive match without configuring `custom_providers` first.
_host_derived_api_key(base_url),
]
api_key = next(
(c for c in api_key_candidates if has_usable_secret(c)),
@@ -619,14 +699,27 @@ def _resolve_named_custom_runtime(
model_name = custom_provider.get("model")
if model_name:
pool_result["model"] = model_name
request_overrides = _custom_provider_request_overrides(custom_provider)
if request_overrides:
pool_result["request_overrides"] = {
**dict(pool_result.get("request_overrides") or {}),
**request_overrides,
}
return pool_result
_cp_is_openai_url = base_url_host_matches(base_url, "openai.com") or base_url_host_matches(base_url, "openai.azure.com")
_cp_is_openrouter = base_url_host_matches(base_url, "openrouter.ai")
api_key_candidates = [
(explicit_api_key or "").strip(),
str(custom_provider.get("api_key", "") or "").strip(),
os.getenv(str(custom_provider.get("key_env", "") or "").strip(), "").strip(),
os.getenv("OPENAI_API_KEY", "").strip(),
os.getenv("OPENROUTER_API_KEY", "").strip(),
# Gate provider env keys on their authoritative hosts — sending
# OPENAI_API_KEY to a local-llm endpoint leaks credentials (#28660).
(os.getenv("OPENAI_API_KEY", "").strip() if _cp_is_openai_url else ""),
(os.getenv("OPENROUTER_API_KEY", "").strip() if _cp_is_openrouter else ""),
# Bonus (#28660): derive `<VENDOR>_API_KEY` from the host as a final
# fallback when key_env wasn't set explicitly.
_host_derived_api_key(base_url),
]
api_key = next((candidate for candidate in api_key_candidates if has_usable_secret(candidate)), "")
@@ -643,6 +736,9 @@ def _resolve_named_custom_runtime(
# provider name differs from the actual model string the API expects.
if custom_provider.get("model"):
result["model"] = custom_provider["model"]
request_overrides = _custom_provider_request_overrides(custom_provider)
if request_overrides:
result["request_overrides"] = request_overrides
return result
@@ -707,7 +803,15 @@ def _resolve_openrouter_runtime(
# OPENAI_API_KEY so the OpenRouter key doesn't leak to an unrelated
# provider (issues #420, #560).
_is_openrouter_url = base_url_host_matches(base_url, "openrouter.ai")
if _is_openrouter_url:
# Also treat explicitly-configured OpenRouter mirrors/proxies as OpenRouter
# for key selection — if the user set OPENROUTER_BASE_URL or requested
# provider=openrouter explicitly, OPENROUTER_API_KEY should still be used.
_is_openrouter_context = _is_openrouter_url or (
requested_norm == "openrouter"
and (env_openrouter_base_url or base_url == env_openrouter_base_url)
and base_url == (env_openrouter_base_url or "").rstrip("/")
)
if _is_openrouter_context:
api_key_candidates = [
explicit_api_key,
os.getenv("OPENROUTER_API_KEY"),
@@ -721,13 +825,24 @@ def _resolve_openrouter_runtime(
# "ollama.com" (e.g. http://127.0.0.1/ollama.com/v1) or whose
# hostname is a look-alike (ollama.com.attacker.test) must not
# receive the Ollama credential. See GHSA-76xc-57q6-vm5m.
_is_ollama_url = base_url_host_matches(base_url, "ollama.com")
_is_ollama_url = base_url_host_matches(base_url, "ollama.com")
_is_openai_url = base_url_host_matches(base_url, "openai.com")
_is_openai_azure = base_url_host_matches(base_url, "openai.azure.com")
# Gate each provider key on its own host — sending OPENAI_API_KEY or
# OPENROUTER_API_KEY to an unrelated custom endpoint (DeepSeek, Groq,
# Mistral, …) leaks credentials and causes 401s (issue #28660).
# Mirrors the OLLAMA_API_KEY host-gate added in GHSA-76xc-57q6-vm5m.
api_key_candidates = [
explicit_api_key,
(cfg_api_key if use_config_base_url else ""),
(os.getenv("OLLAMA_API_KEY") if _is_ollama_url else ""),
os.getenv("OPENAI_API_KEY"),
os.getenv("OPENROUTER_API_KEY"),
(os.getenv("OLLAMA_API_KEY") if _is_ollama_url else ""),
(os.getenv("OPENAI_API_KEY") if (_is_openai_url or _is_openai_azure) else ""),
(os.getenv("OPENROUTER_API_KEY") if _is_openrouter_url else ""),
# Bonus (#28660): derive `<VENDOR>_API_KEY` from the host so users
# who set DEEPSEEK_API_KEY / GROQ_API_KEY / MISTRAL_API_KEY get the
# intuitive match. Helper returns "" for IPs/loopback and for env
# vars already handled by the explicit host-gated paths above.
_host_derived_api_key(base_url),
]
api_key = next(
(str(candidate or "").strip() for candidate in api_key_candidates if has_usable_secret(candidate)),
+7 -5
View File
@@ -319,12 +319,14 @@ def do_browse(page: int = 1, page_size: int = 20, source: str = "all",
c.print("[dim]No skills found in the Skills Hub.[/]\n")
return
# Deduplicate by name, preferring higher trust
# Deduplicate by identifier, preferring higher trust.
# identifier is always unique per skill; name is not (browse-sh skills from different
# sites can share the same task name, e.g. "search-listings" on Airbnb and Booking.com).
seen: dict = {}
for r in all_results:
rank = _TRUST_RANK.get(r.trust_level, 0)
if r.name not in seen or rank > _TRUST_RANK.get(seen[r.name].trust_level, 0):
seen[r.name] = r
if r.identifier not in seen or rank > _TRUST_RANK.get(seen[r.identifier].trust_level, 0):
seen[r.identifier] = r
deduped = list(seen.values())
# Sort: official first, then by trust level (desc), then alphabetically
@@ -702,8 +704,8 @@ def browse_skills(page: int = 1, page_size: int = 20, source: str = "all") -> di
seen: dict = {}
for r in all_results:
rank = _TRUST_RANK.get(r.trust_level, 0)
if r.name not in seen or rank > _TRUST_RANK.get(seen[r.name].trust_level, 0):
seen[r.name] = r
if r.identifier not in seen or rank > _TRUST_RANK.get(seen[r.identifier].trust_level, 0):
seen[r.identifier] = r
deduped = list(seen.values())
deduped.sort(key=lambda r: (-_TRUST_RANK.get(r.trust_level, 0), r.source != "official", r.name.lower()))
total = len(deduped)