mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-25 00:51:20 +00:00
Merge branch 'main' of github.com:NousResearch/hermes-agent into feat/ink-refactor
This commit is contained in:
Brooklyn Nicholson
commit
cb2a737bc8
49 changed files with 1055 additions and 229 deletions
|
|
@ -28,19 +28,45 @@ except ImportError:
|
|||
logger = logging.getLogger(__name__)
|
||||
|
||||
THINKING_BUDGET = {"xhigh": 32000, "high": 16000, "medium": 8000, "low": 4000}
|
||||
# Hermes effort → Anthropic adaptive-thinking effort (output_config.effort).
|
||||
# Anthropic exposes 5 levels on 4.7+: low, medium, high, xhigh, max.
|
||||
# Opus/Sonnet 4.6 only expose 4 levels: low, medium, high, max — no xhigh.
|
||||
# We preserve xhigh as xhigh on 4.7+ (the recommended default for coding/
|
||||
# agentic work) and downgrade it to max on pre-4.7 adaptive models (which
|
||||
# is the strongest level they accept). "minimal" is a legacy alias that
|
||||
# maps to low on every model. See:
|
||||
# https://platform.claude.com/docs/en/about-claude/models/migration-guide
|
||||
ADAPTIVE_EFFORT_MAP = {
|
||||
"xhigh": "max",
|
||||
"high": "high",
|
||||
"medium": "medium",
|
||||
"low": "low",
|
||||
"max": "max",
|
||||
"xhigh": "xhigh",
|
||||
"high": "high",
|
||||
"medium": "medium",
|
||||
"low": "low",
|
||||
"minimal": "low",
|
||||
}
|
||||
|
||||
# Models that accept the "xhigh" output_config.effort level. Opus 4.7 added
|
||||
# xhigh as a distinct level between high and max; older adaptive-thinking
|
||||
# models (4.6) reject it with a 400. Keep this substring list in sync with
|
||||
# the Anthropic migration guide as new model families ship.
|
||||
_XHIGH_EFFORT_SUBSTRINGS = ("4-7", "4.7")
|
||||
|
||||
# Models where extended thinking is deprecated/removed (4.6+ behavior: adaptive
|
||||
# is the only supported mode; 4.7 additionally forbids manual thinking entirely
|
||||
# and drops temperature/top_p/top_k).
|
||||
_ADAPTIVE_THINKING_SUBSTRINGS = ("4-6", "4.6", "4-7", "4.7")
|
||||
|
||||
# Models where temperature/top_p/top_k return 400 if set to non-default values.
|
||||
# This is the Opus 4.7 contract; future 4.x+ models are expected to follow it.
|
||||
_NO_SAMPLING_PARAMS_SUBSTRINGS = ("4-7", "4.7")
|
||||
|
||||
# ── Max output token limits per Anthropic model ───────────────────────
|
||||
# Source: Anthropic docs + Cline model catalog. Anthropic's API requires
|
||||
# max_tokens as a mandatory field. Previously we hardcoded 16384, which
|
||||
# starves thinking-enabled models (thinking tokens count toward the limit).
|
||||
_ANTHROPIC_OUTPUT_LIMITS = {
|
||||
# Claude 4.7
|
||||
"claude-opus-4-7": 128_000,
|
||||
# Claude 4.6
|
||||
"claude-opus-4-6": 128_000,
|
||||
"claude-sonnet-4-6": 64_000,
|
||||
|
|
@ -91,11 +117,37 @@ def _get_anthropic_max_output(model: str) -> int:
|
|||
|
||||
|
||||
def _supports_adaptive_thinking(model: str) -> bool:
|
||||
"""Return True for Claude 4.6 models that support adaptive thinking."""
|
||||
return any(v in model for v in ("4-6", "4.6"))
|
||||
"""Return True for Claude 4.6+ models that support adaptive thinking."""
|
||||
return any(v in model for v in _ADAPTIVE_THINKING_SUBSTRINGS)
|
||||
|
||||
|
||||
# Beta headers for enhanced features (sent with ALL auth types)
|
||||
def _supports_xhigh_effort(model: str) -> bool:
|
||||
"""Return True for models that accept the 'xhigh' adaptive effort level.
|
||||
|
||||
Opus 4.7 introduced xhigh as a distinct level between high and max.
|
||||
Pre-4.7 adaptive models (Opus/Sonnet 4.6) only accept low/medium/high/max
|
||||
and reject xhigh with an HTTP 400. Callers should downgrade xhigh→max
|
||||
when this returns False.
|
||||
"""
|
||||
return any(v in model for v in _XHIGH_EFFORT_SUBSTRINGS)
|
||||
|
||||
|
||||
def _forbids_sampling_params(model: str) -> bool:
|
||||
"""Return True for models that 400 on any non-default temperature/top_p/top_k.
|
||||
|
||||
Opus 4.7 explicitly rejects sampling parameters; later Claude releases are
|
||||
expected to follow suit. Callers should omit these fields entirely rather
|
||||
than passing zero/default values (the API rejects anything non-null).
|
||||
"""
|
||||
return any(v in model for v in _NO_SAMPLING_PARAMS_SUBSTRINGS)
|
||||
|
||||
|
||||
# Beta headers for enhanced features (sent with ALL auth types).
|
||||
# As of Opus 4.7 (2026-04-16), both of these are GA on Claude 4.6+ — the
|
||||
# beta headers are still accepted (harmless no-op) but not required. Kept
|
||||
# here so older Claude (4.5, 4.1) + third-party Anthropic-compat endpoints
|
||||
# that still gate on the headers continue to get the enhanced features.
|
||||
# Migration guide: remove these if you no longer support ≤4.5 models.
|
||||
_COMMON_BETAS = [
|
||||
"interleaved-thinking-2025-05-14",
|
||||
"fine-grained-tool-streaming-2025-05-14",
|
||||
|
|
@ -1341,18 +1393,31 @@ def build_anthropic_kwargs(
|
|||
kwargs["tool_choice"] = {"type": "tool", "name": tool_choice}
|
||||
|
||||
# Map reasoning_config to Anthropic's thinking parameter.
|
||||
# Claude 4.6 models use adaptive thinking + output_config.effort.
|
||||
# Claude 4.6+ models use adaptive thinking + output_config.effort.
|
||||
# Older models use manual thinking with budget_tokens.
|
||||
# MiniMax Anthropic-compat endpoints support thinking (manual mode only,
|
||||
# not adaptive). Haiku does NOT support extended thinking — skip entirely.
|
||||
#
|
||||
# On 4.7+ the `thinking.display` field defaults to "omitted", which
|
||||
# silently hides reasoning text that Hermes surfaces in its CLI. We
|
||||
# request "summarized" so the reasoning blocks stay populated — matching
|
||||
# 4.6 behavior and preserving the activity-feed UX during long tool runs.
|
||||
if reasoning_config and isinstance(reasoning_config, dict):
|
||||
if reasoning_config.get("enabled") is not False and "haiku" not in model.lower():
|
||||
effort = str(reasoning_config.get("effort", "medium")).lower()
|
||||
budget = THINKING_BUDGET.get(effort, 8000)
|
||||
if _supports_adaptive_thinking(model):
|
||||
kwargs["thinking"] = {"type": "adaptive"}
|
||||
kwargs["thinking"] = {
|
||||
"type": "adaptive",
|
||||
"display": "summarized",
|
||||
}
|
||||
adaptive_effort = ADAPTIVE_EFFORT_MAP.get(effort, "medium")
|
||||
# Downgrade xhigh→max on models that don't list xhigh as a
|
||||
# supported level (Opus/Sonnet 4.6). Opus 4.7+ keeps xhigh.
|
||||
if adaptive_effort == "xhigh" and not _supports_xhigh_effort(model):
|
||||
adaptive_effort = "max"
|
||||
kwargs["output_config"] = {
|
||||
"effort": ADAPTIVE_EFFORT_MAP.get(effort, "medium")
|
||||
"effort": adaptive_effort,
|
||||
}
|
||||
else:
|
||||
kwargs["thinking"] = {"type": "enabled", "budget_tokens": budget}
|
||||
|
|
@ -1360,6 +1425,15 @@ def build_anthropic_kwargs(
|
|||
kwargs["temperature"] = 1
|
||||
kwargs["max_tokens"] = max(effective_max_tokens, budget + 4096)
|
||||
|
||||
# ── Strip sampling params on 4.7+ ─────────────────────────────────
|
||||
# Opus 4.7 rejects any non-default temperature/top_p/top_k with a 400.
|
||||
# Callers (auxiliary_client, flush_memories, etc.) may set these for
|
||||
# older models; drop them here as a safety net so upstream 4.6 → 4.7
|
||||
# migrations don't require coordinated edits everywhere.
|
||||
if _forbids_sampling_params(model):
|
||||
for _sampling_key in ("temperature", "top_p", "top_k"):
|
||||
kwargs.pop(_sampling_key, None)
|
||||
|
||||
# ── Fast mode (Opus 4.6 only) ────────────────────────────────────
|
||||
# Adds extra_body.speed="fast" + the fast-mode beta header for ~2.5x
|
||||
# output speed. Only for native Anthropic endpoints — third-party
|
||||
|
|
@ -1417,12 +1491,20 @@ def normalize_anthropic_response(
|
|||
)
|
||||
)
|
||||
|
||||
# Map Anthropic stop_reason to OpenAI finish_reason
|
||||
# Map Anthropic stop_reason to OpenAI finish_reason.
|
||||
# Newer stop reasons added in Claude 4.5+ / 4.7:
|
||||
# - refusal: the model declined to answer (cyber safeguards, CSAM, etc.)
|
||||
# - model_context_window_exceeded: hit context limit (not max_tokens)
|
||||
# Both need distinct handling upstream — a refusal should surface to the
|
||||
# user with a clear message, and a context-window overflow should trigger
|
||||
# compression/truncation rather than be treated as normal end-of-turn.
|
||||
stop_reason_map = {
|
||||
"end_turn": "stop",
|
||||
"tool_use": "tool_calls",
|
||||
"max_tokens": "length",
|
||||
"stop_sequence": "stop",
|
||||
"refusal": "content_filter",
|
||||
"model_context_window_exceeded": "length",
|
||||
}
|
||||
finish_reason = stop_reason_map.get(response.stop_reason, "stop")
|
||||
|
||||
|
|
|
|||
|
|
@ -518,8 +518,13 @@ class _AnthropicCompletionsAdapter:
|
|||
tool_choice=normalized_tool_choice,
|
||||
is_oauth=self._is_oauth,
|
||||
)
|
||||
# Opus 4.7+ rejects any non-default temperature/top_p/top_k; only set
|
||||
# temperature for models that still accept it. build_anthropic_kwargs
|
||||
# additionally strips these keys as a safety net — keep both layers.
|
||||
if temperature is not None:
|
||||
anthropic_kwargs["temperature"] = temperature
|
||||
from agent.anthropic_adapter import _forbids_sampling_params
|
||||
if not _forbids_sampling_params(model):
|
||||
anthropic_kwargs["temperature"] = temperature
|
||||
|
||||
response = self._client.messages.create(**anthropic_kwargs)
|
||||
assistant_message, finish_reason = normalize_anthropic_response(response)
|
||||
|
|
@ -2288,6 +2293,15 @@ def _build_call_kwargs(
|
|||
"timeout": timeout,
|
||||
}
|
||||
|
||||
# Opus 4.7+ rejects any non-default temperature/top_p/top_k — silently
|
||||
# drop here so auxiliary callers that hardcode temperature (e.g. 0.3 on
|
||||
# flush_memories, 0 on structured-JSON extraction) don't 400 the moment
|
||||
# the aux model is flipped to 4.7.
|
||||
if temperature is not None:
|
||||
from agent.anthropic_adapter import _forbids_sampling_params
|
||||
if _forbids_sampling_params(model):
|
||||
temperature = None
|
||||
|
||||
if temperature is not None:
|
||||
kwargs["temperature"] = temperature
|
||||
|
||||
|
|
|
|||
|
|
@ -313,9 +313,25 @@ class CopilotACPClient:
|
|||
tools=tools,
|
||||
tool_choice=tool_choice,
|
||||
)
|
||||
# Normalise timeout: run_agent.py may pass an httpx.Timeout object
|
||||
# (used natively by the OpenAI SDK) rather than a plain float.
|
||||
if timeout is None:
|
||||
_effective_timeout = _DEFAULT_TIMEOUT_SECONDS
|
||||
elif isinstance(timeout, (int, float)):
|
||||
_effective_timeout = float(timeout)
|
||||
else:
|
||||
# httpx.Timeout or similar — pick the largest component so the
|
||||
# subprocess has enough wall-clock time for the full response.
|
||||
_candidates = [
|
||||
getattr(timeout, attr, None)
|
||||
for attr in ("read", "write", "connect", "pool", "timeout")
|
||||
]
|
||||
_numeric = [float(v) for v in _candidates if isinstance(v, (int, float))]
|
||||
_effective_timeout = max(_numeric) if _numeric else _DEFAULT_TIMEOUT_SECONDS
|
||||
|
||||
response_text, reasoning_text = self._run_prompt(
|
||||
prompt_text,
|
||||
timeout_seconds=float(timeout or _DEFAULT_TIMEOUT_SECONDS),
|
||||
timeout_seconds=_effective_timeout,
|
||||
)
|
||||
|
||||
tool_calls, cleaned_text = _extract_tool_calls_from_text(response_text)
|
||||
|
|
|
|||
|
|
@ -102,6 +102,8 @@ DEFAULT_CONTEXT_LENGTHS = {
|
|||
# fuzzy-match collisions (e.g. "anthropic/claude-sonnet-4" is a
|
||||
# substring of "anthropic/claude-sonnet-4.6").
|
||||
# OpenRouter-prefixed models resolve via OpenRouter live API or models.dev.
|
||||
"claude-opus-4-7": 1000000,
|
||||
"claude-opus-4.7": 1000000,
|
||||
"claude-opus-4-6": 1000000,
|
||||
"claude-sonnet-4-6": 1000000,
|
||||
"claude-opus-4.6": 1000000,
|
||||
|
|
|
|||
|
|
@ -561,7 +561,10 @@ class BatchRunner:
|
|||
provider_sort (str): Sort providers by price/throughput/latency (optional)
|
||||
max_tokens (int): Maximum tokens for model responses (optional, uses model default if not set)
|
||||
reasoning_config (Dict): OpenRouter reasoning config override (e.g. {"effort": "none"} to disable thinking)
|
||||
prefill_messages (List[Dict]): Messages to prepend as prefilled conversation context (few-shot priming)
|
||||
prefill_messages (List[Dict]): Messages to prepend as prefilled conversation context (few-shot priming).
|
||||
NOTE: Anthropic Sonnet 4.6+ and Opus 4.6+ reject a trailing assistant-role prefill
|
||||
(400 error). For those models use output_config.format or structured-output
|
||||
schemas instead. Safe here for user-role priming and for older Claude / non-Claude models.
|
||||
max_samples (int): Only process the first N samples from the dataset (optional, processes all if not set)
|
||||
"""
|
||||
self.dataset_file = Path(dataset_file)
|
||||
|
|
|
|||
12
cli.py
12
cli.py
|
|
@ -6328,13 +6328,21 @@ class HermesCLI:
|
|||
def _toggle_yolo(self):
|
||||
"""Toggle YOLO mode — skip all dangerous command approval prompts."""
|
||||
import os
|
||||
from hermes_cli.colors import Colors as _Colors
|
||||
|
||||
current = bool(os.environ.get("HERMES_YOLO_MODE"))
|
||||
if current:
|
||||
os.environ.pop("HERMES_YOLO_MODE", None)
|
||||
self.console.print(" ⚠ YOLO mode [bold red]OFF[/] — dangerous commands will require approval.")
|
||||
_cprint(
|
||||
f" ⚠ YOLO mode {_Colors.BOLD}{_Colors.RED}OFF{_Colors.RESET}"
|
||||
" — dangerous commands will require approval."
|
||||
)
|
||||
else:
|
||||
os.environ["HERMES_YOLO_MODE"] = "1"
|
||||
self.console.print(" ⚡ YOLO mode [bold green]ON[/] — all commands auto-approved. Use with caution.")
|
||||
_cprint(
|
||||
f" ⚡ YOLO mode {_Colors.BOLD}{_Colors.GREEN}ON{_Colors.RESET}"
|
||||
" — all commands auto-approved. Use with caution."
|
||||
)
|
||||
|
||||
def _handle_reasoning_command(self, cmd: str):
|
||||
"""Handle /reasoning — manage effort level and display toggle.
|
||||
|
|
|
|||
|
|
@ -23,7 +23,6 @@ from dataclasses import dataclass
|
|||
from pathlib import Path
|
||||
from typing import Dict, Any, Optional, List, Tuple
|
||||
|
||||
from tools.tool_backend_helpers import managed_nous_tools_enabled as _managed_nous_tools_enabled
|
||||
|
||||
_IS_WINDOWS = platform.system() == "Windows"
|
||||
_ENV_VAR_NAME_RE = re.compile(r"^[A-Za-z_][A-Za-z0-9_]*$")
|
||||
|
|
@ -1646,14 +1645,8 @@ OPTIONAL_ENV_VARS = {
|
|||
},
|
||||
}
|
||||
|
||||
if not _managed_nous_tools_enabled():
|
||||
for _hidden_var in (
|
||||
"FIRECRAWL_GATEWAY_URL",
|
||||
"TOOL_GATEWAY_DOMAIN",
|
||||
"TOOL_GATEWAY_SCHEME",
|
||||
"TOOL_GATEWAY_USER_TOKEN",
|
||||
):
|
||||
OPTIONAL_ENV_VARS.pop(_hidden_var, None)
|
||||
# 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]]:
|
||||
|
|
|
|||
|
|
@ -166,6 +166,7 @@ def curses_radiolist(
|
|||
selected: int = 0,
|
||||
*,
|
||||
cancel_returns: int | None = None,
|
||||
description: str | None = None,
|
||||
) -> int:
|
||||
"""Curses single-select radio list. Returns the selected index.
|
||||
|
||||
|
|
@ -174,6 +175,9 @@ def curses_radiolist(
|
|||
items: Display labels for each row.
|
||||
selected: Index that starts selected (pre-selected).
|
||||
cancel_returns: Returned on ESC/q. Defaults to the original *selected*.
|
||||
description: Optional multi-line text shown between the title and
|
||||
the item list. Useful for context that should survive the
|
||||
curses screen clear.
|
||||
"""
|
||||
if cancel_returns is None:
|
||||
cancel_returns = selected
|
||||
|
|
@ -181,6 +185,10 @@ def curses_radiolist(
|
|||
if not sys.stdin.isatty():
|
||||
return cancel_returns
|
||||
|
||||
desc_lines: list[str] = []
|
||||
if description:
|
||||
desc_lines = description.splitlines()
|
||||
|
||||
try:
|
||||
import curses
|
||||
result_holder: list = [None]
|
||||
|
|
@ -199,22 +207,35 @@ def curses_radiolist(
|
|||
stdscr.clear()
|
||||
max_y, max_x = stdscr.getmaxyx()
|
||||
|
||||
row = 0
|
||||
|
||||
# Header
|
||||
try:
|
||||
hattr = curses.A_BOLD
|
||||
if curses.has_colors():
|
||||
hattr |= curses.color_pair(2)
|
||||
stdscr.addnstr(0, 0, title, max_x - 1, hattr)
|
||||
stdscr.addnstr(row, 0, title, max_x - 1, hattr)
|
||||
row += 1
|
||||
|
||||
# Description lines
|
||||
for dline in desc_lines:
|
||||
if row >= max_y - 1:
|
||||
break
|
||||
stdscr.addnstr(row, 0, dline, max_x - 1, curses.A_NORMAL)
|
||||
row += 1
|
||||
|
||||
stdscr.addnstr(
|
||||
1, 0,
|
||||
row, 0,
|
||||
" \u2191\u2193 navigate ENTER/SPACE select ESC cancel",
|
||||
max_x - 1, curses.A_DIM,
|
||||
)
|
||||
row += 1
|
||||
except curses.error:
|
||||
pass
|
||||
|
||||
# Scrollable item list
|
||||
visible_rows = max_y - 4
|
||||
items_start = row + 1
|
||||
visible_rows = max_y - items_start - 1
|
||||
if cursor < scroll_offset:
|
||||
scroll_offset = cursor
|
||||
elif cursor >= scroll_offset + visible_rows:
|
||||
|
|
@ -223,7 +244,7 @@ def curses_radiolist(
|
|||
for draw_i, i in enumerate(
|
||||
range(scroll_offset, min(len(items), scroll_offset + visible_rows))
|
||||
):
|
||||
y = draw_i + 3
|
||||
y = draw_i + items_start
|
||||
if y >= max_y - 1:
|
||||
break
|
||||
radio = "\u25cf" if i == selected else "\u25cb"
|
||||
|
|
|
|||
|
|
@ -1564,11 +1564,8 @@ def _model_flow_nous(config, current_model="", args=None):
|
|||
AuthError, format_auth_error,
|
||||
_login_nous, PROVIDER_REGISTRY,
|
||||
)
|
||||
from hermes_cli.config import get_env_value, save_config, save_env_value
|
||||
from hermes_cli.nous_subscription import (
|
||||
apply_nous_provider_defaults,
|
||||
get_nous_subscription_explainer_lines,
|
||||
)
|
||||
from hermes_cli.config import get_env_value, load_config, save_config, save_env_value
|
||||
from hermes_cli.nous_subscription import prompt_enable_tool_gateway
|
||||
import argparse
|
||||
|
||||
state = get_provider_auth_state("nous")
|
||||
|
|
@ -1587,9 +1584,12 @@ def _model_flow_nous(config, current_model="", args=None):
|
|||
insecure=bool(getattr(args, "insecure", False)),
|
||||
)
|
||||
_login_nous(mock_args, PROVIDER_REGISTRY["nous"])
|
||||
print()
|
||||
for line in get_nous_subscription_explainer_lines():
|
||||
print(line)
|
||||
# Offer Tool Gateway enablement for paid subscribers
|
||||
try:
|
||||
_refreshed = load_config() or {}
|
||||
prompt_enable_tool_gateway(_refreshed)
|
||||
except Exception:
|
||||
pass
|
||||
except SystemExit:
|
||||
print("Login cancelled or failed.")
|
||||
return
|
||||
|
|
@ -1697,18 +1697,10 @@ def _model_flow_nous(config, current_model="", args=None):
|
|||
if get_env_value("OPENAI_BASE_URL"):
|
||||
save_env_value("OPENAI_BASE_URL", "")
|
||||
save_env_value("OPENAI_API_KEY", "")
|
||||
changed_defaults = apply_nous_provider_defaults(config)
|
||||
save_config(config)
|
||||
print(f"Default model set to: {selected} (via Nous Portal)")
|
||||
if "tts" in changed_defaults:
|
||||
print("TTS provider set to: OpenAI TTS via your Nous subscription")
|
||||
else:
|
||||
current_tts = str(config.get("tts", {}).get("provider") or "edge")
|
||||
if current_tts.lower() not in {"", "edge"}:
|
||||
print(f"Keeping your existing TTS provider: {current_tts}")
|
||||
print()
|
||||
for line in get_nous_subscription_explainer_lines():
|
||||
print(line)
|
||||
# Offer Tool Gateway enablement for paid subscribers
|
||||
prompt_enable_tool_gateway(config)
|
||||
else:
|
||||
print("No change.")
|
||||
|
||||
|
|
|
|||
|
|
@ -26,7 +26,8 @@ COPILOT_REASONING_EFFORTS_O_SERIES = ["low", "medium", "high"]
|
|||
# Fallback OpenRouter snapshot used when the live catalog is unavailable.
|
||||
# (model_id, display description shown in menus)
|
||||
OPENROUTER_MODELS: list[tuple[str, str]] = [
|
||||
("anthropic/claude-opus-4.6", "recommended"),
|
||||
("anthropic/claude-opus-4.7", "recommended"),
|
||||
("anthropic/claude-opus-4.6", ""),
|
||||
("anthropic/claude-sonnet-4.6", ""),
|
||||
("qwen/qwen3.6-plus", ""),
|
||||
("anthropic/claude-sonnet-4.5", ""),
|
||||
|
|
@ -181,6 +182,7 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
|
|||
"MiniMax-M2",
|
||||
],
|
||||
"anthropic": [
|
||||
"claude-opus-4-7",
|
||||
"claude-opus-4-6",
|
||||
"claude-sonnet-4-6",
|
||||
"claude-opus-4-5-20251101",
|
||||
|
|
|
|||
|
|
@ -258,6 +258,15 @@ def get_nous_subscription_features(
|
|||
terminal_cfg.get("modal_mode")
|
||||
)
|
||||
|
||||
# use_gateway flags — when True, the user explicitly opted into the
|
||||
# Tool Gateway via `hermes model`, so direct credentials should NOT
|
||||
# prevent gateway routing.
|
||||
web_use_gateway = bool(web_cfg.get("use_gateway"))
|
||||
tts_use_gateway = bool(tts_cfg.get("use_gateway"))
|
||||
browser_use_gateway = bool(browser_cfg.get("use_gateway"))
|
||||
image_gen_cfg = config.get("image_gen") if isinstance(config.get("image_gen"), dict) else {}
|
||||
image_use_gateway = bool(image_gen_cfg.get("use_gateway"))
|
||||
|
||||
direct_exa = bool(get_env_value("EXA_API_KEY"))
|
||||
direct_firecrawl = bool(get_env_value("FIRECRAWL_API_KEY") or get_env_value("FIRECRAWL_API_URL"))
|
||||
direct_parallel = bool(get_env_value("PARALLEL_API_KEY"))
|
||||
|
|
@ -270,6 +279,21 @@ def get_nous_subscription_features(
|
|||
direct_browser_use = bool(get_env_value("BROWSER_USE_API_KEY"))
|
||||
direct_modal = has_direct_modal_credentials()
|
||||
|
||||
# When use_gateway is set, suppress direct credentials for managed detection
|
||||
if web_use_gateway:
|
||||
direct_firecrawl = False
|
||||
direct_exa = False
|
||||
direct_parallel = False
|
||||
direct_tavily = False
|
||||
if image_use_gateway:
|
||||
direct_fal = False
|
||||
if tts_use_gateway:
|
||||
direct_openai_tts = False
|
||||
direct_elevenlabs = False
|
||||
if browser_use_gateway:
|
||||
direct_browser_use = False
|
||||
direct_browserbase = False
|
||||
|
||||
managed_web_available = managed_tools_flag and nous_auth_present and is_managed_tool_gateway_ready("firecrawl")
|
||||
managed_image_available = managed_tools_flag and nous_auth_present and is_managed_tool_gateway_ready("fal-queue")
|
||||
managed_tts_available = managed_tools_flag and nous_auth_present and is_managed_tool_gateway_ready("openai-audio")
|
||||
|
|
@ -440,37 +464,7 @@ def get_nous_subscription_features(
|
|||
)
|
||||
|
||||
|
||||
def get_nous_subscription_explainer_lines() -> list[str]:
|
||||
if not managed_nous_tools_enabled():
|
||||
return []
|
||||
|
||||
return [
|
||||
"Nous subscription enables managed web tools, image generation, OpenAI TTS, and browser automation by default.",
|
||||
"Those managed tools bill to your Nous subscription. Modal execution is optional and can bill to your subscription too.",
|
||||
"Change these later with: hermes setup tools, hermes setup terminal, or hermes status.",
|
||||
]
|
||||
|
||||
|
||||
def apply_nous_provider_defaults(config: Dict[str, object]) -> set[str]:
|
||||
"""Apply provider-level Nous defaults shared by `hermes setup` and `hermes model`."""
|
||||
if not managed_nous_tools_enabled():
|
||||
return set()
|
||||
|
||||
features = get_nous_subscription_features(config)
|
||||
if not features.provider_is_nous:
|
||||
return set()
|
||||
|
||||
tts_cfg = config.get("tts")
|
||||
if not isinstance(tts_cfg, dict):
|
||||
tts_cfg = {}
|
||||
config["tts"] = tts_cfg
|
||||
|
||||
current_tts = str(tts_cfg.get("provider") or "edge").strip().lower()
|
||||
if current_tts not in {"", "edge"}:
|
||||
return set()
|
||||
|
||||
tts_cfg["provider"] = "openai"
|
||||
return {"tts"}
|
||||
|
||||
|
||||
def apply_nous_managed_defaults(
|
||||
|
|
@ -530,3 +524,255 @@ def apply_nous_managed_defaults(
|
|||
changed.add("image_gen")
|
||||
|
||||
return changed
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Tool Gateway offer — single Y/n prompt after model selection
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
_GATEWAY_TOOL_LABELS = {
|
||||
"web": "Web search & extract (Firecrawl)",
|
||||
"image_gen": "Image generation (FAL)",
|
||||
"tts": "Text-to-speech (OpenAI TTS)",
|
||||
"browser": "Browser automation (Browser Use)",
|
||||
}
|
||||
|
||||
|
||||
def _get_gateway_direct_credentials() -> Dict[str, bool]:
|
||||
"""Return a dict of tool_key -> has_direct_credentials."""
|
||||
return {
|
||||
"web": bool(
|
||||
get_env_value("FIRECRAWL_API_KEY")
|
||||
or get_env_value("FIRECRAWL_API_URL")
|
||||
or get_env_value("PARALLEL_API_KEY")
|
||||
or get_env_value("TAVILY_API_KEY")
|
||||
or get_env_value("EXA_API_KEY")
|
||||
),
|
||||
"image_gen": bool(get_env_value("FAL_KEY")),
|
||||
"tts": bool(
|
||||
resolve_openai_audio_api_key()
|
||||
or get_env_value("ELEVENLABS_API_KEY")
|
||||
),
|
||||
"browser": bool(
|
||||
get_env_value("BROWSER_USE_API_KEY")
|
||||
or (get_env_value("BROWSERBASE_API_KEY") and get_env_value("BROWSERBASE_PROJECT_ID"))
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
_GATEWAY_DIRECT_LABELS = {
|
||||
"web": "Firecrawl/Exa/Parallel/Tavily key",
|
||||
"image_gen": "FAL key",
|
||||
"tts": "OpenAI/ElevenLabs key",
|
||||
"browser": "Browser Use/Browserbase key",
|
||||
}
|
||||
|
||||
_ALL_GATEWAY_KEYS = ("web", "image_gen", "tts", "browser")
|
||||
|
||||
|
||||
def get_gateway_eligible_tools(
|
||||
config: Optional[Dict[str, object]] = None,
|
||||
) -> tuple[list[str], list[str], list[str]]:
|
||||
"""Return (unconfigured, has_direct, already_managed) tool key lists.
|
||||
|
||||
- unconfigured: tools with no direct credentials (easy switch)
|
||||
- has_direct: tools where the user has their own API keys
|
||||
- already_managed: tools already routed through the gateway
|
||||
|
||||
All lists are empty when the user is not a paid Nous subscriber or
|
||||
is not using Nous as their provider.
|
||||
"""
|
||||
if not managed_nous_tools_enabled():
|
||||
return [], [], []
|
||||
|
||||
if config is None:
|
||||
from hermes_cli.config import load_config
|
||||
config = load_config() or {}
|
||||
|
||||
# Quick provider check without the heavy get_nous_subscription_features call
|
||||
model_cfg = config.get("model")
|
||||
if not isinstance(model_cfg, dict) or str(model_cfg.get("provider") or "").strip().lower() != "nous":
|
||||
return [], [], []
|
||||
|
||||
direct = _get_gateway_direct_credentials()
|
||||
|
||||
# Check which tools the user has explicitly opted into the gateway for.
|
||||
# This is distinct from managed_by_nous which fires implicitly when
|
||||
# no direct keys exist — we only skip the prompt for tools where
|
||||
# use_gateway was explicitly set.
|
||||
opted_in = {
|
||||
"web": bool((config.get("web") if isinstance(config.get("web"), dict) else {}).get("use_gateway")),
|
||||
"image_gen": bool((config.get("image_gen") if isinstance(config.get("image_gen"), dict) else {}).get("use_gateway")),
|
||||
"tts": bool((config.get("tts") if isinstance(config.get("tts"), dict) else {}).get("use_gateway")),
|
||||
"browser": bool((config.get("browser") if isinstance(config.get("browser"), dict) else {}).get("use_gateway")),
|
||||
}
|
||||
|
||||
unconfigured: list[str] = []
|
||||
has_direct: list[str] = []
|
||||
already_managed: list[str] = []
|
||||
for key in _ALL_GATEWAY_KEYS:
|
||||
if opted_in.get(key):
|
||||
already_managed.append(key)
|
||||
elif direct.get(key):
|
||||
has_direct.append(key)
|
||||
else:
|
||||
unconfigured.append(key)
|
||||
return unconfigured, has_direct, already_managed
|
||||
|
||||
|
||||
def apply_gateway_defaults(
|
||||
config: Dict[str, object],
|
||||
tool_keys: list[str],
|
||||
) -> set[str]:
|
||||
"""Apply Tool Gateway config for the given tool keys.
|
||||
|
||||
Sets ``use_gateway: true`` in each tool's config section so the
|
||||
runtime prefers the gateway even when direct API keys are present.
|
||||
|
||||
Returns the set of tools that were actually changed.
|
||||
"""
|
||||
changed: set[str] = set()
|
||||
|
||||
web_cfg = config.get("web")
|
||||
if not isinstance(web_cfg, dict):
|
||||
web_cfg = {}
|
||||
config["web"] = web_cfg
|
||||
|
||||
tts_cfg = config.get("tts")
|
||||
if not isinstance(tts_cfg, dict):
|
||||
tts_cfg = {}
|
||||
config["tts"] = tts_cfg
|
||||
|
||||
browser_cfg = config.get("browser")
|
||||
if not isinstance(browser_cfg, dict):
|
||||
browser_cfg = {}
|
||||
config["browser"] = browser_cfg
|
||||
|
||||
if "web" in tool_keys:
|
||||
web_cfg["backend"] = "firecrawl"
|
||||
web_cfg["use_gateway"] = True
|
||||
changed.add("web")
|
||||
|
||||
if "tts" in tool_keys:
|
||||
tts_cfg["provider"] = "openai"
|
||||
tts_cfg["use_gateway"] = True
|
||||
changed.add("tts")
|
||||
|
||||
if "browser" in tool_keys:
|
||||
browser_cfg["cloud_provider"] = "browser-use"
|
||||
browser_cfg["use_gateway"] = True
|
||||
changed.add("browser")
|
||||
|
||||
if "image_gen" in tool_keys:
|
||||
image_cfg = config.get("image_gen")
|
||||
if not isinstance(image_cfg, dict):
|
||||
image_cfg = {}
|
||||
config["image_gen"] = image_cfg
|
||||
image_cfg["use_gateway"] = True
|
||||
changed.add("image_gen")
|
||||
|
||||
return changed
|
||||
|
||||
|
||||
def prompt_enable_tool_gateway(config: Dict[str, object]) -> set[str]:
|
||||
"""If eligible tools exist, prompt the user to enable the Tool Gateway.
|
||||
|
||||
Uses prompt_choice() with a description parameter so the curses TUI
|
||||
shows the tool context alongside the choices.
|
||||
|
||||
Returns the set of tools that were enabled, or empty set if the user
|
||||
declined or no tools were eligible.
|
||||
"""
|
||||
unconfigured, has_direct, already_managed = get_gateway_eligible_tools(config)
|
||||
if not unconfigured and not has_direct:
|
||||
return set()
|
||||
|
||||
try:
|
||||
from hermes_cli.setup import prompt_choice
|
||||
except Exception:
|
||||
return set()
|
||||
|
||||
# Build description lines showing full status of all gateway tools
|
||||
desc_parts: list[str] = [
|
||||
"",
|
||||
" The Tool Gateway gives you access to web search, image generation,",
|
||||
" text-to-speech, and browser automation through your Nous subscription.",
|
||||
" No need to sign up for separate API keys — just pick the tools you want.",
|
||||
"",
|
||||
]
|
||||
if already_managed:
|
||||
for k in already_managed:
|
||||
desc_parts.append(f" ✓ {_GATEWAY_TOOL_LABELS[k]} — using Tool Gateway")
|
||||
if unconfigured:
|
||||
for k in unconfigured:
|
||||
desc_parts.append(f" ○ {_GATEWAY_TOOL_LABELS[k]} — not configured")
|
||||
if has_direct:
|
||||
for k in has_direct:
|
||||
desc_parts.append(f" ○ {_GATEWAY_TOOL_LABELS[k]} — using {_GATEWAY_DIRECT_LABELS[k]}")
|
||||
|
||||
# Build short choice labels — detail is in the description above
|
||||
choices: list[str] = []
|
||||
choice_keys: list[str] = [] # maps choice index -> action
|
||||
|
||||
if unconfigured and has_direct:
|
||||
choices.append("Enable for all tools (existing keys kept, not used)")
|
||||
choice_keys.append("all")
|
||||
|
||||
choices.append("Enable only for tools without existing keys")
|
||||
choice_keys.append("unconfigured")
|
||||
|
||||
choices.append("Skip")
|
||||
choice_keys.append("skip")
|
||||
|
||||
elif unconfigured:
|
||||
choices.append("Enable Tool Gateway")
|
||||
choice_keys.append("unconfigured")
|
||||
|
||||
choices.append("Skip")
|
||||
choice_keys.append("skip")
|
||||
|
||||
else:
|
||||
choices.append("Enable Tool Gateway (existing keys kept, not used)")
|
||||
choice_keys.append("all")
|
||||
|
||||
choices.append("Skip")
|
||||
choice_keys.append("skip")
|
||||
|
||||
description = "\n".join(desc_parts) if desc_parts else None
|
||||
# Default to "Enable" when user has no direct keys (new user),
|
||||
# default to "Skip" when they have existing keys to preserve.
|
||||
default_idx = 0 if not has_direct else len(choices) - 1
|
||||
|
||||
try:
|
||||
idx = prompt_choice(
|
||||
"Your Nous subscription includes the Tool Gateway.",
|
||||
choices,
|
||||
default_idx,
|
||||
description=description,
|
||||
)
|
||||
except (KeyboardInterrupt, EOFError, OSError, SystemExit):
|
||||
return set()
|
||||
|
||||
action = choice_keys[idx]
|
||||
if action == "skip":
|
||||
return set()
|
||||
|
||||
if action == "all":
|
||||
# Apply to switchable tools + ensure already-managed tools also
|
||||
# have use_gateway persisted in config for consistency.
|
||||
to_apply = list(_ALL_GATEWAY_KEYS)
|
||||
else:
|
||||
to_apply = unconfigured
|
||||
|
||||
changed = apply_gateway_defaults(config, to_apply)
|
||||
if changed:
|
||||
from hermes_cli.config import save_config
|
||||
save_config(config)
|
||||
# Only report the tools that actually switched (not already-managed ones)
|
||||
newly_switched = changed - set(already_managed)
|
||||
for key in sorted(newly_switched):
|
||||
label = _GATEWAY_TOOL_LABELS.get(key, key)
|
||||
print(f" ✓ {label}: enabled via Nous subscription")
|
||||
if already_managed and not newly_switched:
|
||||
print(" (all tools already using Tool Gateway)")
|
||||
return changed
|
||||
|
|
|
|||
|
|
@ -20,10 +20,7 @@ import copy
|
|||
from pathlib import Path
|
||||
from typing import Optional, Dict, Any
|
||||
|
||||
from hermes_cli.nous_subscription import (
|
||||
apply_nous_provider_defaults,
|
||||
get_nous_subscription_features,
|
||||
)
|
||||
from hermes_cli.nous_subscription import get_nous_subscription_features
|
||||
from tools.tool_backend_helpers import managed_nous_tools_enabled
|
||||
from hermes_constants import get_optional_skills_dir
|
||||
|
||||
|
|
@ -213,20 +210,20 @@ def prompt(question: str, default: str = None, password: bool = False) -> str:
|
|||
sys.exit(1)
|
||||
|
||||
|
||||
def _curses_prompt_choice(question: str, choices: list, default: int = 0) -> int:
|
||||
def _curses_prompt_choice(question: str, choices: list, default: int = 0, description: str | None = None) -> int:
|
||||
"""Single-select menu using curses. Delegates to curses_radiolist."""
|
||||
from hermes_cli.curses_ui import curses_radiolist
|
||||
return curses_radiolist(question, choices, selected=default, cancel_returns=-1)
|
||||
return curses_radiolist(question, choices, selected=default, cancel_returns=-1, description=description)
|
||||
|
||||
|
||||
|
||||
def prompt_choice(question: str, choices: list, default: int = 0) -> int:
|
||||
def prompt_choice(question: str, choices: list, default: int = 0, description: str | None = None) -> int:
|
||||
"""Prompt for a choice from a list with arrow key navigation.
|
||||
|
||||
Escape keeps the current default (skips the question).
|
||||
Ctrl+C exits the wizard.
|
||||
"""
|
||||
idx = _curses_prompt_choice(question, choices, default)
|
||||
idx = _curses_prompt_choice(question, choices, default, description=description)
|
||||
if idx >= 0:
|
||||
if idx == default:
|
||||
print_info(" Skipped (keeping current)")
|
||||
|
|
@ -835,14 +832,7 @@ def setup_model_provider(config: dict, *, quick: bool = False):
|
|||
print_info("Skipped — add later with 'hermes setup' or configure AUXILIARY_VISION_* settings")
|
||||
|
||||
|
||||
if selected_provider == "nous" and nous_subscription_selected:
|
||||
changed_defaults = apply_nous_provider_defaults(config)
|
||||
current_tts = str(config.get("tts", {}).get("provider") or "edge")
|
||||
if "tts" in changed_defaults:
|
||||
print_success("TTS provider set to: OpenAI TTS via your Nous subscription")
|
||||
else:
|
||||
print_info(f"Keeping your existing TTS provider: {current_tts}")
|
||||
|
||||
# Tool Gateway prompt is already shown by _model_flow_nous() above.
|
||||
save_config(config)
|
||||
|
||||
if not quick and selected_provider != "nous":
|
||||
|
|
|
|||
|
|
@ -212,7 +212,7 @@ def show_status(args):
|
|||
if managed_nous_tools_enabled():
|
||||
features = get_nous_subscription_features(config)
|
||||
print()
|
||||
print(color("◆ Nous Subscription Features", Colors.CYAN, Colors.BOLD))
|
||||
print(color("◆ Nous Tool Gateway", Colors.CYAN, Colors.BOLD))
|
||||
if not features.nous_auth_present:
|
||||
print(" Nous Portal ✗ not logged in")
|
||||
else:
|
||||
|
|
@ -230,6 +230,18 @@ def show_status(args):
|
|||
else:
|
||||
state = "not configured"
|
||||
print(f" {feature.label:<15} {check_mark(feature.available or feature.active or feature.managed_by_nous)} {state}")
|
||||
elif nous_logged_in:
|
||||
# Logged into Nous but on the free tier — show upgrade nudge
|
||||
print()
|
||||
print(color("◆ Nous Tool Gateway", Colors.CYAN, Colors.BOLD))
|
||||
print(" Your free-tier Nous account does not include Tool Gateway access.")
|
||||
print(" Upgrade your subscription to unlock managed web, image, TTS, and browser tools.")
|
||||
try:
|
||||
portal_url = nous_status.get("portal_base_url", "").rstrip("/")
|
||||
if portal_url:
|
||||
print(f" Upgrade: {portal_url}")
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
# =========================================================================
|
||||
# API-Key Providers
|
||||
|
|
|
|||
|
|
@ -954,34 +954,49 @@ def _configure_provider(provider: dict, config: dict):
|
|||
|
||||
# Set TTS provider in config if applicable
|
||||
if provider.get("tts_provider"):
|
||||
config.setdefault("tts", {})["provider"] = provider["tts_provider"]
|
||||
tts_cfg = config.setdefault("tts", {})
|
||||
tts_cfg["provider"] = provider["tts_provider"]
|
||||
tts_cfg["use_gateway"] = bool(managed_feature)
|
||||
|
||||
# Set browser cloud provider in config if applicable
|
||||
if "browser_provider" in provider:
|
||||
bp = provider["browser_provider"]
|
||||
browser_cfg = config.setdefault("browser", {})
|
||||
if bp == "local":
|
||||
config.setdefault("browser", {})["cloud_provider"] = "local"
|
||||
browser_cfg["cloud_provider"] = "local"
|
||||
_print_success(" Browser set to local mode")
|
||||
elif bp:
|
||||
config.setdefault("browser", {})["cloud_provider"] = bp
|
||||
browser_cfg["cloud_provider"] = bp
|
||||
_print_success(f" Browser cloud provider set to: {bp}")
|
||||
browser_cfg["use_gateway"] = bool(managed_feature)
|
||||
|
||||
# Set web search backend in config if applicable
|
||||
if provider.get("web_backend"):
|
||||
config.setdefault("web", {})["backend"] = provider["web_backend"]
|
||||
web_cfg = config.setdefault("web", {})
|
||||
web_cfg["backend"] = provider["web_backend"]
|
||||
web_cfg["use_gateway"] = bool(managed_feature)
|
||||
_print_success(f" Web backend set to: {provider['web_backend']}")
|
||||
|
||||
# For tools without a specific config key (e.g. image_gen), still
|
||||
# track use_gateway so the runtime knows the user's intent.
|
||||
if managed_feature and managed_feature not in ("web", "tts", "browser"):
|
||||
config.setdefault(managed_feature, {})["use_gateway"] = True
|
||||
elif not managed_feature:
|
||||
# User picked a non-gateway provider — find which category this
|
||||
# belongs to and clear use_gateway if it was previously set.
|
||||
for cat_key, cat in TOOL_CATEGORIES.items():
|
||||
if provider in cat.get("providers", []):
|
||||
section = config.get(cat_key)
|
||||
if isinstance(section, dict) and section.get("use_gateway"):
|
||||
section["use_gateway"] = False
|
||||
break
|
||||
|
||||
if not env_vars:
|
||||
if provider.get("post_setup"):
|
||||
_run_post_setup(provider["post_setup"])
|
||||
_print_success(f" {provider['name']} - no configuration needed!")
|
||||
if managed_feature:
|
||||
_print_info(" Requests for this tool will be billed to your Nous subscription.")
|
||||
override_envs = provider.get("override_env_vars", [])
|
||||
if any(get_env_value(env_var) for env_var in override_envs):
|
||||
_print_warning(
|
||||
" Direct credentials are still configured and may take precedence until you remove them from ~/.hermes/.env."
|
||||
)
|
||||
return
|
||||
|
||||
# Prompt for each required env var
|
||||
|
|
@ -1187,11 +1202,6 @@ def _reconfigure_provider(provider: dict, config: dict):
|
|||
_print_success(f" {provider['name']} - no configuration needed!")
|
||||
if managed_feature:
|
||||
_print_info(" Requests for this tool will be billed to your Nous subscription.")
|
||||
override_envs = provider.get("override_env_vars", [])
|
||||
if any(get_env_value(env_var) for env_var in override_envs):
|
||||
_print_warning(
|
||||
" Direct credentials are still configured and may take precedence until you remove them from ~/.hermes/.env."
|
||||
)
|
||||
return
|
||||
|
||||
for var in env_vars:
|
||||
|
|
|
|||
|
|
@ -160,11 +160,11 @@ CONCLUDE_SCHEMA = {
|
|||
"properties": {
|
||||
"conclusion": {
|
||||
"type": "string",
|
||||
"description": "A factual statement to persist. Required when not using delete_id.",
|
||||
"description": "A factual statement to persist. Provide this when creating a conclusion. Do not send it together with delete_id.",
|
||||
},
|
||||
"delete_id": {
|
||||
"type": "string",
|
||||
"description": "Conclusion ID to delete (for PII removal). Required when not using conclusion.",
|
||||
"description": "Conclusion ID to delete for PII removal. Provide this when deleting a conclusion. Do not send it together with conclusion.",
|
||||
},
|
||||
"peer": {
|
||||
"type": "string",
|
||||
|
|
@ -1008,16 +1008,20 @@ class HonchoMemoryProvider(MemoryProvider):
|
|||
return json.dumps({"result": "\n\n".join(parts) or "No context available."})
|
||||
|
||||
elif tool_name == "honcho_conclude":
|
||||
delete_id = args.get("delete_id")
|
||||
delete_id = (args.get("delete_id") or "").strip()
|
||||
conclusion = args.get("conclusion", "").strip()
|
||||
peer = args.get("peer", "user")
|
||||
if delete_id:
|
||||
|
||||
has_delete_id = bool(delete_id)
|
||||
has_conclusion = bool(conclusion)
|
||||
if has_delete_id == has_conclusion:
|
||||
return tool_error("Exactly one of conclusion or delete_id must be provided.")
|
||||
|
||||
if has_delete_id:
|
||||
ok = self._manager.delete_conclusion(self._session_key, delete_id, peer=peer)
|
||||
if ok:
|
||||
return json.dumps({"result": f"Conclusion {delete_id} deleted."})
|
||||
return tool_error(f"Failed to delete conclusion {delete_id}.")
|
||||
conclusion = args.get("conclusion", "")
|
||||
if not conclusion:
|
||||
return tool_error("Missing required parameter: conclusion or delete_id")
|
||||
ok = self._manager.create_conclusion(self._session_key, conclusion, peer=peer)
|
||||
if ok:
|
||||
return json.dumps({"result": f"Conclusion saved for {peer}: {conclusion}"})
|
||||
|
|
|
|||
|
|
@ -641,6 +641,9 @@ class AIAgent:
|
|||
prefill_messages (List[Dict]): Messages to prepend to conversation history as prefilled context.
|
||||
Useful for injecting a few-shot example or priming the model's response style.
|
||||
Example: [{"role": "user", "content": "Hi!"}, {"role": "assistant", "content": "Hello!"}]
|
||||
NOTE: Anthropic Sonnet 4.6+ and Opus 4.6+ reject a conversation that ends on an
|
||||
assistant-role message (400 error). For those models use structured outputs or
|
||||
output_config.format instead of a trailing-assistant prefill.
|
||||
platform (str): The interface platform the user is on (e.g. "cli", "telegram", "discord", "whatsapp").
|
||||
Used to inject platform-specific formatting hints into the system prompt.
|
||||
skip_context_files (bool): If True, skip auto-injection of SOUL.md, AGENTS.md, and .cursorrules
|
||||
|
|
|
|||
|
|
@ -46,6 +46,7 @@ AUTHOR_MAP = {
|
|||
# contributors (from noreply pattern)
|
||||
"35742124+0xbyt4@users.noreply.github.com": "0xbyt4",
|
||||
"82637225+kshitijk4poor@users.noreply.github.com": "kshitijk4poor",
|
||||
"kshitijk4poor@users.noreply.github.com": "kshitijk4poor",
|
||||
"16443023+stablegenius49@users.noreply.github.com": "stablegenius49",
|
||||
"185121704+stablegenius49@users.noreply.github.com": "stablegenius49",
|
||||
"101283333+batuhankocyigit@users.noreply.github.com": "batuhankocyigit",
|
||||
|
|
@ -190,6 +191,9 @@ AUTHOR_MAP = {
|
|||
"cola-runner@users.noreply.github.com": "cola-runner",
|
||||
"ygd58@users.noreply.github.com": "ygd58",
|
||||
"vominh1919@users.noreply.github.com": "vominh1919",
|
||||
"trevmanthony@gmail.com": "trevthefoolish",
|
||||
"ziliangpeng@users.noreply.github.com": "ziliangpeng",
|
||||
"centripetal-star@users.noreply.github.com": "centripetal-star",
|
||||
"LeonSGP43@users.noreply.github.com": "LeonSGP43",
|
||||
"Lubrsy706@users.noreply.github.com": "Lubrsy706",
|
||||
"niyant@spicefi.xyz": "spniyant",
|
||||
|
|
|
|||
|
|
@ -951,13 +951,21 @@ class TestBuildAnthropicKwargs:
|
|||
max_tokens=4096,
|
||||
reasoning_config={"enabled": True, "effort": "high"},
|
||||
)
|
||||
assert kwargs["thinking"] == {"type": "adaptive"}
|
||||
# Adaptive thinking + display="summarized" keeps reasoning text
|
||||
# populated in the response stream (Opus 4.7 default is "omitted").
|
||||
assert kwargs["thinking"] == {"type": "adaptive", "display": "summarized"}
|
||||
assert kwargs["output_config"] == {"effort": "high"}
|
||||
assert "budget_tokens" not in kwargs["thinking"]
|
||||
assert "temperature" not in kwargs
|
||||
assert kwargs["max_tokens"] == 4096
|
||||
|
||||
def test_reasoning_config_maps_xhigh_to_max_effort_for_4_6_models(self):
|
||||
def test_reasoning_config_downgrades_xhigh_to_max_for_4_6_models(self):
|
||||
# Opus 4.7 added "xhigh" as a distinct effort level (low/medium/high/
|
||||
# xhigh/max). Opus 4.6 only supports low/medium/high/max — sending
|
||||
# "xhigh" there returns an API 400. Preserve the pre-migration
|
||||
# behavior of aliasing xhigh→max on pre-4.7 adaptive models so users
|
||||
# who prefer xhigh as their default don't 400 every request when
|
||||
# switching back to 4.6.
|
||||
kwargs = build_anthropic_kwargs(
|
||||
model="claude-sonnet-4-6",
|
||||
messages=[{"role": "user", "content": "think harder"}],
|
||||
|
|
@ -965,9 +973,53 @@ class TestBuildAnthropicKwargs:
|
|||
max_tokens=4096,
|
||||
reasoning_config={"enabled": True, "effort": "xhigh"},
|
||||
)
|
||||
assert kwargs["thinking"] == {"type": "adaptive"}
|
||||
assert kwargs["thinking"] == {"type": "adaptive", "display": "summarized"}
|
||||
assert kwargs["output_config"] == {"effort": "max"}
|
||||
|
||||
def test_reasoning_config_preserves_xhigh_for_4_7_models(self):
|
||||
# On 4.7+ xhigh is a real level and the recommended default for
|
||||
# coding/agentic work — keep it distinct from max.
|
||||
kwargs = build_anthropic_kwargs(
|
||||
model="claude-opus-4-7",
|
||||
messages=[{"role": "user", "content": "think harder"}],
|
||||
tools=None,
|
||||
max_tokens=4096,
|
||||
reasoning_config={"enabled": True, "effort": "xhigh"},
|
||||
)
|
||||
assert kwargs["thinking"] == {"type": "adaptive", "display": "summarized"}
|
||||
assert kwargs["output_config"] == {"effort": "xhigh"}
|
||||
|
||||
def test_reasoning_config_maps_max_effort_for_4_7_models(self):
|
||||
kwargs = build_anthropic_kwargs(
|
||||
model="claude-opus-4-7",
|
||||
messages=[{"role": "user", "content": "maximum reasoning please"}],
|
||||
tools=None,
|
||||
max_tokens=4096,
|
||||
reasoning_config={"enabled": True, "effort": "max"},
|
||||
)
|
||||
assert kwargs["thinking"] == {"type": "adaptive", "display": "summarized"}
|
||||
assert kwargs["output_config"] == {"effort": "max"}
|
||||
|
||||
def test_opus_4_7_strips_sampling_params(self):
|
||||
# Opus 4.7 returns 400 on non-default temperature/top_p/top_k.
|
||||
# build_anthropic_kwargs must strip them as a safety net even if an
|
||||
# upstream caller injects them for older-model compatibility.
|
||||
kwargs = build_anthropic_kwargs(
|
||||
model="claude-opus-4-7",
|
||||
messages=[{"role": "user", "content": "hi"}],
|
||||
tools=None,
|
||||
max_tokens=1024,
|
||||
reasoning_config=None,
|
||||
)
|
||||
# Manually inject sampling params then re-run through the guard.
|
||||
# Because build_anthropic_kwargs doesn't currently accept sampling
|
||||
# params through its signature, we exercise the strip behavior by
|
||||
# calling the internal predicate directly.
|
||||
from agent.anthropic_adapter import _forbids_sampling_params
|
||||
assert _forbids_sampling_params("claude-opus-4-7") is True
|
||||
assert _forbids_sampling_params("claude-opus-4-6") is False
|
||||
assert _forbids_sampling_params("claude-sonnet-4-5") is False
|
||||
|
||||
def test_reasoning_disabled(self):
|
||||
kwargs = build_anthropic_kwargs(
|
||||
model="claude-sonnet-4-20250514",
|
||||
|
|
@ -1248,6 +1300,21 @@ class TestNormalizeResponse:
|
|||
assert r2 == "tool_calls"
|
||||
assert r3 == "length"
|
||||
|
||||
def test_stop_reason_refusal_and_context_exceeded(self):
|
||||
# Claude 4.5+ introduced two new stop_reason values the Messages API
|
||||
# returns. We map both to OpenAI-style finish_reasons upstream
|
||||
# handlers already understand, instead of silently collapsing to
|
||||
# "stop" (old behavior).
|
||||
block = SimpleNamespace(type="text", text="")
|
||||
_, refusal_reason = normalize_anthropic_response(
|
||||
self._make_response([block], "refusal")
|
||||
)
|
||||
_, overflow_reason = normalize_anthropic_response(
|
||||
self._make_response([block], "model_context_window_exceeded")
|
||||
)
|
||||
assert refusal_reason == "content_filter"
|
||||
assert overflow_reason == "length"
|
||||
|
||||
def test_no_text_content(self):
|
||||
block = SimpleNamespace(
|
||||
type="tool_use", id="tc_1", name="search", input={"q": "hi"}
|
||||
|
|
|
|||
|
|
@ -113,8 +113,10 @@ class TestDefaultContextLengths:
|
|||
for key, value in DEFAULT_CONTEXT_LENGTHS.items():
|
||||
if "claude" not in key:
|
||||
continue
|
||||
# Claude 4.6 models have 1M context
|
||||
if "4.6" in key or "4-6" in key:
|
||||
# Claude 4.6+ models (4.6 and 4.7) have 1M context at standard
|
||||
# API pricing (no long-context premium). Older Claude 4.x and
|
||||
# 3.x models cap at 200k.
|
||||
if any(tag in key for tag in ("4.6", "4-6", "4.7", "4-7")):
|
||||
assert value == 1000000, f"{key} should be 1000000"
|
||||
else:
|
||||
assert value == 200000, f"{key} should be 200000"
|
||||
|
|
|
|||
|
|
@ -413,7 +413,7 @@ class TestBuildSkillsSystemPrompt:
|
|||
|
||||
class TestBuildNousSubscriptionPrompt:
|
||||
def test_includes_active_subscription_features(self, monkeypatch):
|
||||
monkeypatch.setenv("HERMES_ENABLE_NOUS_MANAGED_TOOLS", "1")
|
||||
monkeypatch.setattr("tools.tool_backend_helpers.managed_nous_tools_enabled", lambda: True)
|
||||
monkeypatch.setattr(
|
||||
"hermes_cli.nous_subscription.get_nous_subscription_features",
|
||||
lambda config=None: NousSubscriptionFeatures(
|
||||
|
|
@ -437,7 +437,7 @@ class TestBuildNousSubscriptionPrompt:
|
|||
assert "do not ask the user for Firecrawl, FAL, OpenAI TTS, or Browser-Use API keys" in prompt
|
||||
|
||||
def test_non_subscriber_prompt_includes_relevant_upgrade_guidance(self, monkeypatch):
|
||||
monkeypatch.setenv("HERMES_ENABLE_NOUS_MANAGED_TOOLS", "1")
|
||||
monkeypatch.setattr("tools.tool_backend_helpers.managed_nous_tools_enabled", lambda: True)
|
||||
monkeypatch.setattr(
|
||||
"hermes_cli.nous_subscription.get_nous_subscription_features",
|
||||
lambda config=None: NousSubscriptionFeatures(
|
||||
|
|
@ -460,7 +460,7 @@ class TestBuildNousSubscriptionPrompt:
|
|||
assert "Do not mention subscription unless" in prompt
|
||||
|
||||
def test_feature_flag_off_returns_empty_prompt(self, monkeypatch):
|
||||
monkeypatch.delenv("HERMES_ENABLE_NOUS_MANAGED_TOOLS", raising=False)
|
||||
monkeypatch.setattr("tools.tool_backend_helpers.managed_nous_tools_enabled", lambda: False)
|
||||
|
||||
prompt = build_nous_subscription_prompt({"web_search"})
|
||||
|
||||
|
|
|
|||
|
|
@ -308,7 +308,7 @@ def test_codex_provider_replaces_incompatible_default_model(monkeypatch):
|
|||
|
||||
|
||||
def test_model_flow_nous_prints_subscription_guidance_without_mutating_explicit_tts(monkeypatch, capsys):
|
||||
monkeypatch.setenv("HERMES_ENABLE_NOUS_MANAGED_TOOLS", "1")
|
||||
monkeypatch.setattr("hermes_cli.nous_subscription.managed_nous_tools_enabled", lambda: True)
|
||||
config = {
|
||||
"model": {"provider": "nous", "default": "claude-opus-4-6"},
|
||||
"tts": {"provider": "elevenlabs"},
|
||||
|
|
@ -333,21 +333,17 @@ def test_model_flow_nous_prints_subscription_guidance_without_mutating_explicit_
|
|||
monkeypatch.setattr("hermes_cli.auth._prompt_model_selection", lambda model_ids, current_model="", pricing=None, **kw: "claude-opus-4-6")
|
||||
monkeypatch.setattr("hermes_cli.auth._save_model_choice", lambda model: None)
|
||||
monkeypatch.setattr("hermes_cli.auth._update_config_for_provider", lambda provider, url: None)
|
||||
monkeypatch.setattr(
|
||||
"hermes_cli.nous_subscription.get_nous_subscription_explainer_lines",
|
||||
lambda: ["Nous subscription enables managed web tools."],
|
||||
)
|
||||
|
||||
hermes_main._model_flow_nous(config, current_model="claude-opus-4-6")
|
||||
|
||||
out = capsys.readouterr().out
|
||||
assert "Nous subscription enables managed web tools." in out
|
||||
assert "Default model set to:" in out
|
||||
assert config["tts"]["provider"] == "elevenlabs"
|
||||
assert config["browser"]["cloud_provider"] == "browser-use"
|
||||
|
||||
|
||||
def test_model_flow_nous_applies_managed_tts_default_when_unconfigured(monkeypatch, capsys):
|
||||
monkeypatch.setenv("HERMES_ENABLE_NOUS_MANAGED_TOOLS", "1")
|
||||
def test_model_flow_nous_offers_tool_gateway_prompt_when_unconfigured(monkeypatch, capsys):
|
||||
monkeypatch.setattr("hermes_cli.nous_subscription.managed_nous_tools_enabled", lambda: True)
|
||||
config = {
|
||||
"model": {"provider": "nous", "default": "claude-opus-4-6"},
|
||||
"tts": {"provider": "edge"},
|
||||
|
|
@ -355,13 +351,13 @@ def test_model_flow_nous_applies_managed_tts_default_when_unconfigured(monkeypat
|
|||
|
||||
monkeypatch.setattr(
|
||||
"hermes_cli.auth.get_provider_auth_state",
|
||||
lambda provider: {"access_token": "nous-token"},
|
||||
lambda provider: {"access_token": "***"},
|
||||
)
|
||||
monkeypatch.setattr(
|
||||
"hermes_cli.auth.resolve_nous_runtime_credentials",
|
||||
lambda *args, **kwargs: {
|
||||
"base_url": "https://inference.example.com/v1",
|
||||
"api_key": "nous-key",
|
||||
"api_key": "***",
|
||||
},
|
||||
)
|
||||
monkeypatch.setattr(
|
||||
|
|
@ -371,17 +367,12 @@ def test_model_flow_nous_applies_managed_tts_default_when_unconfigured(monkeypat
|
|||
monkeypatch.setattr("hermes_cli.auth._prompt_model_selection", lambda model_ids, current_model="", pricing=None, **kw: "claude-opus-4-6")
|
||||
monkeypatch.setattr("hermes_cli.auth._save_model_choice", lambda model: None)
|
||||
monkeypatch.setattr("hermes_cli.auth._update_config_for_provider", lambda provider, url: None)
|
||||
monkeypatch.setattr(
|
||||
"hermes_cli.nous_subscription.get_nous_subscription_explainer_lines",
|
||||
lambda: ["Nous subscription enables managed web tools."],
|
||||
)
|
||||
|
||||
hermes_main._model_flow_nous(config, current_model="claude-opus-4-6")
|
||||
|
||||
out = capsys.readouterr().out
|
||||
assert "Nous subscription enables managed web tools." in out
|
||||
assert "OpenAI TTS via your Nous subscription" in out
|
||||
assert config["tts"]["provider"] == "openai"
|
||||
# Tool Gateway prompt should be shown (input() raises OSError in pytest
|
||||
# which is caught, so the prompt text appears but nothing is applied)
|
||||
assert "Tool Gateway" in out
|
||||
|
||||
|
||||
def test_codex_provider_uses_config_model(monkeypatch):
|
||||
|
|
|
|||
|
|
@ -24,7 +24,7 @@ def test_get_nous_subscription_features_recognizes_direct_exa_backend(monkeypatc
|
|||
|
||||
|
||||
def test_get_nous_subscription_features_prefers_managed_modal_in_auto_mode(monkeypatch):
|
||||
monkeypatch.setenv("HERMES_ENABLE_NOUS_MANAGED_TOOLS", "1")
|
||||
monkeypatch.setattr("tools.tool_backend_helpers.managed_nous_tools_enabled", lambda: True)
|
||||
monkeypatch.setattr(ns, "get_env_value", lambda name: "")
|
||||
monkeypatch.setattr(ns, "get_nous_auth_status", lambda: {"logged_in": True})
|
||||
monkeypatch.setattr(ns, "managed_nous_tools_enabled", lambda: True)
|
||||
|
|
|
|||
|
|
@ -363,7 +363,7 @@ def test_codex_setup_uses_runtime_access_token_for_live_model_list(tmp_path, mon
|
|||
|
||||
|
||||
def test_modal_setup_can_use_nous_subscription_without_modal_creds(tmp_path, monkeypatch, capsys):
|
||||
monkeypatch.setenv("HERMES_ENABLE_NOUS_MANAGED_TOOLS", "1")
|
||||
monkeypatch.setattr("hermes_cli.setup.managed_nous_tools_enabled", lambda: True)
|
||||
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
|
||||
config = load_config()
|
||||
|
||||
|
|
@ -405,7 +405,7 @@ def test_modal_setup_can_use_nous_subscription_without_modal_creds(tmp_path, mon
|
|||
|
||||
|
||||
def test_modal_setup_persists_direct_mode_when_user_chooses_their_own_account(tmp_path, monkeypatch):
|
||||
monkeypatch.setenv("HERMES_ENABLE_NOUS_MANAGED_TOOLS", "1")
|
||||
monkeypatch.setattr("hermes_cli.setup.managed_nous_tools_enabled", lambda: True)
|
||||
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
|
||||
monkeypatch.delenv("MODAL_TOKEN_ID", raising=False)
|
||||
monkeypatch.delenv("MODAL_TOKEN_SECRET", raising=False)
|
||||
|
|
|
|||
|
|
@ -64,7 +64,7 @@ def test_show_status_displays_legacy_string_model_and_custom_endpoint(monkeypatc
|
|||
|
||||
|
||||
def test_show_status_reports_managed_nous_features(monkeypatch, capsys, tmp_path):
|
||||
monkeypatch.setenv("HERMES_ENABLE_NOUS_MANAGED_TOOLS", "1")
|
||||
monkeypatch.setattr("hermes_cli.status.managed_nous_tools_enabled", lambda: True)
|
||||
from hermes_cli import status as status_mod
|
||||
|
||||
_patch_common_status_deps(monkeypatch, status_mod, tmp_path)
|
||||
|
|
@ -98,13 +98,13 @@ def test_show_status_reports_managed_nous_features(monkeypatch, capsys, tmp_path
|
|||
status_mod.show_status(SimpleNamespace(all=False, deep=False))
|
||||
|
||||
out = capsys.readouterr().out
|
||||
assert "Nous Subscription Features" in out
|
||||
assert "Nous Tool Gateway" in out
|
||||
assert "Browser automation" in out
|
||||
assert "active via Nous subscription" in out
|
||||
|
||||
|
||||
def test_show_status_hides_nous_subscription_section_when_feature_flag_is_off(monkeypatch, capsys, tmp_path):
|
||||
monkeypatch.delenv("HERMES_ENABLE_NOUS_MANAGED_TOOLS", raising=False)
|
||||
monkeypatch.setattr("hermes_cli.status.managed_nous_tools_enabled", lambda: False)
|
||||
from hermes_cli import status as status_mod
|
||||
|
||||
_patch_common_status_deps(monkeypatch, status_mod, tmp_path)
|
||||
|
|
@ -121,4 +121,4 @@ def test_show_status_hides_nous_subscription_section_when_feature_flag_is_off(mo
|
|||
status_mod.show_status(SimpleNamespace(all=False, deep=False))
|
||||
|
||||
out = capsys.readouterr().out
|
||||
assert "Nous Subscription Features" not in out
|
||||
assert "Nous Tool Gateway" not in out
|
||||
|
|
|
|||
|
|
@ -296,7 +296,7 @@ def test_save_platform_tools_still_preserves_mcp_with_platform_default_present()
|
|||
|
||||
|
||||
def test_visible_providers_include_nous_subscription_when_logged_in(monkeypatch):
|
||||
monkeypatch.setenv("HERMES_ENABLE_NOUS_MANAGED_TOOLS", "1")
|
||||
monkeypatch.setattr("hermes_cli.tools_config.managed_nous_tools_enabled", lambda: True)
|
||||
config = {"model": {"provider": "nous"}}
|
||||
|
||||
monkeypatch.setattr(
|
||||
|
|
@ -310,7 +310,7 @@ def test_visible_providers_include_nous_subscription_when_logged_in(monkeypatch)
|
|||
|
||||
|
||||
def test_visible_providers_hide_nous_subscription_when_feature_flag_is_off(monkeypatch):
|
||||
monkeypatch.delenv("HERMES_ENABLE_NOUS_MANAGED_TOOLS", raising=False)
|
||||
monkeypatch.setattr("hermes_cli.tools_config.managed_nous_tools_enabled", lambda: False)
|
||||
config = {"model": {"provider": "nous"}}
|
||||
|
||||
monkeypatch.setattr(
|
||||
|
|
@ -338,7 +338,8 @@ def test_local_browser_provider_is_saved_explicitly(monkeypatch):
|
|||
|
||||
|
||||
def test_first_install_nous_auto_configures_managed_defaults(monkeypatch):
|
||||
monkeypatch.setenv("HERMES_ENABLE_NOUS_MANAGED_TOOLS", "1")
|
||||
monkeypatch.setattr("hermes_cli.tools_config.managed_nous_tools_enabled", lambda: True)
|
||||
monkeypatch.setattr("hermes_cli.nous_subscription.managed_nous_tools_enabled", lambda: True)
|
||||
config = {
|
||||
"model": {"provider": "nous"},
|
||||
"platform_toolsets": {"cli": []},
|
||||
|
|
|
|||
|
|
@ -366,6 +366,17 @@ class TestPeerLookupHelpers:
|
|||
|
||||
|
||||
class TestConcludeToolDispatch:
|
||||
def test_conclude_schema_has_no_anyof(self):
|
||||
"""anyOf/oneOf/allOf breaks Anthropic and Fireworks APIs — schema must be plain object."""
|
||||
from plugins.memory.honcho import CONCLUDE_SCHEMA
|
||||
params = CONCLUDE_SCHEMA["parameters"]
|
||||
assert params["type"] == "object"
|
||||
assert "conclusion" in params["properties"]
|
||||
assert "delete_id" in params["properties"]
|
||||
assert "anyOf" not in params
|
||||
assert "oneOf" not in params
|
||||
assert "allOf" not in params
|
||||
|
||||
def test_honcho_conclude_defaults_to_user_peer(self):
|
||||
provider = HonchoMemoryProvider()
|
||||
provider._session_initialized = True
|
||||
|
|
@ -470,10 +481,50 @@ class TestConcludeToolDispatch:
|
|||
result = provider.handle_tool_call("honcho_conclude", {})
|
||||
|
||||
parsed = json.loads(result)
|
||||
assert "error" in parsed or "Missing required" in parsed.get("result", "")
|
||||
assert parsed == {"error": "Exactly one of conclusion or delete_id must be provided."}
|
||||
provider._manager.create_conclusion.assert_not_called()
|
||||
provider._manager.delete_conclusion.assert_not_called()
|
||||
|
||||
def test_honcho_conclude_rejects_both_params_at_once(self):
|
||||
"""Sending both conclusion and delete_id should be rejected."""
|
||||
import json
|
||||
provider = HonchoMemoryProvider()
|
||||
provider._session_initialized = True
|
||||
provider._session_key = "telegram:123"
|
||||
provider._manager = MagicMock()
|
||||
result = provider.handle_tool_call(
|
||||
"honcho_conclude",
|
||||
{"conclusion": "User prefers dark mode", "delete_id": "conc-123"},
|
||||
)
|
||||
parsed = json.loads(result)
|
||||
assert parsed == {"error": "Exactly one of conclusion or delete_id must be provided."}
|
||||
provider._manager.create_conclusion.assert_not_called()
|
||||
provider._manager.delete_conclusion.assert_not_called()
|
||||
|
||||
def test_honcho_conclude_rejects_whitespace_only_conclusion(self):
|
||||
"""Whitespace-only conclusion should be treated as empty."""
|
||||
import json
|
||||
provider = HonchoMemoryProvider()
|
||||
provider._session_initialized = True
|
||||
provider._session_key = "telegram:123"
|
||||
provider._manager = MagicMock()
|
||||
result = provider.handle_tool_call("honcho_conclude", {"conclusion": " "})
|
||||
parsed = json.loads(result)
|
||||
assert parsed == {"error": "Exactly one of conclusion or delete_id must be provided."}
|
||||
provider._manager.create_conclusion.assert_not_called()
|
||||
|
||||
def test_honcho_conclude_rejects_whitespace_only_delete_id(self):
|
||||
"""Whitespace-only delete_id should be treated as empty."""
|
||||
import json
|
||||
provider = HonchoMemoryProvider()
|
||||
provider._session_initialized = True
|
||||
provider._session_key = "telegram:123"
|
||||
provider._manager = MagicMock()
|
||||
result = provider.handle_tool_call("honcho_conclude", {"delete_id": " "})
|
||||
parsed = json.loads(result)
|
||||
assert parsed == {"error": "Exactly one of conclusion or delete_id must be provided."}
|
||||
provider._manager.delete_conclusion.assert_not_called()
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Message chunking
|
||||
|
|
|
|||
|
|
@ -47,7 +47,15 @@ def _restore_tool_and_agent_modules():
|
|||
|
||||
@pytest.fixture(autouse=True)
|
||||
def _enable_managed_nous_tools(monkeypatch):
|
||||
monkeypatch.setenv("HERMES_ENABLE_NOUS_MANAGED_TOOLS", "1")
|
||||
"""Ensure managed_nous_tools_enabled() returns True even after module reloads.
|
||||
|
||||
The _install_fake_tools_package() helper resets and reimports tool modules,
|
||||
so a simple monkeypatch on tool_backend_helpers doesn't survive. We patch
|
||||
the *source* modules that the reimported modules will import from — both
|
||||
hermes_cli.auth and hermes_cli.models — so the function body returns True.
|
||||
"""
|
||||
monkeypatch.setattr("hermes_cli.auth.get_nous_auth_status", lambda: {"logged_in": True})
|
||||
monkeypatch.setattr("hermes_cli.models.check_nous_free_tier", lambda: False)
|
||||
|
||||
|
||||
def _install_fake_tools_package():
|
||||
|
|
|
|||
|
|
@ -46,7 +46,10 @@ def _restore_tool_and_agent_modules():
|
|||
|
||||
@pytest.fixture(autouse=True)
|
||||
def _enable_managed_nous_tools(monkeypatch):
|
||||
monkeypatch.setenv("HERMES_ENABLE_NOUS_MANAGED_TOOLS", "1")
|
||||
"""Patch the source modules so managed_nous_tools_enabled() returns True
|
||||
even after tool modules are dynamically reloaded."""
|
||||
monkeypatch.setattr("hermes_cli.auth.get_nous_auth_status", lambda: {"logged_in": True})
|
||||
monkeypatch.setattr("hermes_cli.models.check_nous_free_tier", lambda: False)
|
||||
|
||||
|
||||
def _install_fake_tools_package():
|
||||
|
|
|
|||
|
|
@ -19,11 +19,10 @@ def test_resolve_managed_tool_gateway_derives_vendor_origin_from_shared_domain()
|
|||
with patch.dict(
|
||||
os.environ,
|
||||
{
|
||||
"HERMES_ENABLE_NOUS_MANAGED_TOOLS": "1",
|
||||
"TOOL_GATEWAY_DOMAIN": "nousresearch.com",
|
||||
},
|
||||
clear=False,
|
||||
):
|
||||
), patch.object(managed_tool_gateway, "managed_nous_tools_enabled", return_value=True):
|
||||
result = resolve_managed_tool_gateway(
|
||||
"firecrawl",
|
||||
token_reader=lambda: "nous-token",
|
||||
|
|
@ -39,11 +38,10 @@ def test_resolve_managed_tool_gateway_uses_vendor_specific_override():
|
|||
with patch.dict(
|
||||
os.environ,
|
||||
{
|
||||
"HERMES_ENABLE_NOUS_MANAGED_TOOLS": "1",
|
||||
"BROWSER_USE_GATEWAY_URL": "http://browser-use-gateway.localhost:3009/",
|
||||
},
|
||||
clear=False,
|
||||
):
|
||||
), patch.object(managed_tool_gateway, "managed_nous_tools_enabled", return_value=True):
|
||||
result = resolve_managed_tool_gateway(
|
||||
"browser-use",
|
||||
token_reader=lambda: "nous-token",
|
||||
|
|
@ -57,11 +55,10 @@ def test_resolve_managed_tool_gateway_is_inactive_without_nous_token():
|
|||
with patch.dict(
|
||||
os.environ,
|
||||
{
|
||||
"HERMES_ENABLE_NOUS_MANAGED_TOOLS": "1",
|
||||
"TOOL_GATEWAY_DOMAIN": "nousresearch.com",
|
||||
},
|
||||
clear=False,
|
||||
):
|
||||
), patch.object(managed_tool_gateway, "managed_nous_tools_enabled", return_value=True):
|
||||
result = resolve_managed_tool_gateway(
|
||||
"firecrawl",
|
||||
token_reader=lambda: None,
|
||||
|
|
@ -70,8 +67,9 @@ def test_resolve_managed_tool_gateway_is_inactive_without_nous_token():
|
|||
assert result is None
|
||||
|
||||
|
||||
def test_resolve_managed_tool_gateway_is_disabled_without_feature_flag():
|
||||
with patch.dict(os.environ, {"TOOL_GATEWAY_DOMAIN": "nousresearch.com"}, clear=False):
|
||||
def test_resolve_managed_tool_gateway_is_disabled_without_subscription():
|
||||
with patch.dict(os.environ, {"TOOL_GATEWAY_DOMAIN": "nousresearch.com"}, clear=False), \
|
||||
patch.object(managed_tool_gateway, "managed_nous_tools_enabled", return_value=False):
|
||||
result = resolve_managed_tool_gateway(
|
||||
"firecrawl",
|
||||
token_reader=lambda: "nous-token",
|
||||
|
|
|
|||
|
|
@ -7,7 +7,6 @@ terminal_tool_module = importlib.import_module("tools.terminal_tool")
|
|||
def _clear_terminal_env(monkeypatch):
|
||||
"""Remove terminal env vars that could affect requirements checks."""
|
||||
keys = [
|
||||
"HERMES_ENABLE_NOUS_MANAGED_TOOLS",
|
||||
"TERMINAL_ENV",
|
||||
"TERMINAL_MODAL_MODE",
|
||||
"TERMINAL_SSH_HOST",
|
||||
|
|
@ -19,6 +18,11 @@ def _clear_terminal_env(monkeypatch):
|
|||
]
|
||||
for key in keys:
|
||||
monkeypatch.delenv(key, raising=False)
|
||||
# Default: no Nous subscription — patch both the terminal_tool local
|
||||
# binding and tool_backend_helpers (used by resolve_modal_backend_state).
|
||||
monkeypatch.setattr(terminal_tool_module, "managed_nous_tools_enabled", lambda: False)
|
||||
import tools.tool_backend_helpers as _tbh
|
||||
monkeypatch.setattr(_tbh, "managed_nous_tools_enabled", lambda: False)
|
||||
|
||||
|
||||
def test_local_terminal_requirements(monkeypatch, caplog):
|
||||
|
|
@ -81,7 +85,9 @@ def test_modal_backend_without_token_or_config_logs_specific_error(monkeypatch,
|
|||
|
||||
def test_modal_backend_with_managed_gateway_does_not_require_direct_creds_or_minisweagent(monkeypatch, tmp_path):
|
||||
_clear_terminal_env(monkeypatch)
|
||||
monkeypatch.setenv("HERMES_ENABLE_NOUS_MANAGED_TOOLS", "1")
|
||||
monkeypatch.setattr(terminal_tool_module, "managed_nous_tools_enabled", lambda: True)
|
||||
import tools.tool_backend_helpers as _tbh
|
||||
monkeypatch.setattr(_tbh, "managed_nous_tools_enabled", lambda: True)
|
||||
monkeypatch.setenv("TERMINAL_ENV", "modal")
|
||||
monkeypatch.setenv("HOME", str(tmp_path))
|
||||
monkeypatch.setenv("USERPROFILE", str(tmp_path))
|
||||
|
|
@ -98,7 +104,9 @@ def test_modal_backend_with_managed_gateway_does_not_require_direct_creds_or_min
|
|||
|
||||
def test_modal_backend_auto_mode_prefers_managed_gateway_over_direct_creds(monkeypatch, tmp_path):
|
||||
_clear_terminal_env(monkeypatch)
|
||||
monkeypatch.setenv("HERMES_ENABLE_NOUS_MANAGED_TOOLS", "1")
|
||||
monkeypatch.setattr(terminal_tool_module, "managed_nous_tools_enabled", lambda: True)
|
||||
import tools.tool_backend_helpers as _tbh
|
||||
monkeypatch.setattr(_tbh, "managed_nous_tools_enabled", lambda: True)
|
||||
monkeypatch.setenv("TERMINAL_ENV", "modal")
|
||||
monkeypatch.setenv("MODAL_TOKEN_ID", "tok-id")
|
||||
monkeypatch.setenv("MODAL_TOKEN_SECRET", "tok-secret")
|
||||
|
|
@ -147,7 +155,7 @@ def test_modal_backend_managed_mode_does_not_fall_back_to_direct(monkeypatch, ca
|
|||
|
||||
assert ok is False
|
||||
assert any(
|
||||
"HERMES_ENABLE_NOUS_MANAGED_TOOLS is not enabled" in record.getMessage()
|
||||
"paid Nous subscription is required" in record.getMessage()
|
||||
for record in caplog.records
|
||||
)
|
||||
|
||||
|
|
@ -165,6 +173,6 @@ def test_modal_backend_managed_mode_without_feature_flag_logs_clear_error(monkey
|
|||
|
||||
assert ok is False
|
||||
assert any(
|
||||
"HERMES_ENABLE_NOUS_MANAGED_TOOLS is not enabled" in record.getMessage()
|
||||
"paid Nous subscription is required" in record.getMessage()
|
||||
for record in caplog.records
|
||||
)
|
||||
|
|
|
|||
|
|
@ -28,7 +28,8 @@ class TestTerminalRequirements:
|
|||
assert {"read_file", "write_file", "patch", "search_files"}.issubset(names)
|
||||
|
||||
def test_terminal_and_execute_code_tools_resolve_for_managed_modal(self, monkeypatch, tmp_path):
|
||||
monkeypatch.setenv("HERMES_ENABLE_NOUS_MANAGED_TOOLS", "1")
|
||||
monkeypatch.setattr("tools.tool_backend_helpers.managed_nous_tools_enabled", lambda: True)
|
||||
monkeypatch.setattr(terminal_tool_module, "managed_nous_tools_enabled", lambda: True)
|
||||
monkeypatch.setenv("HOME", str(tmp_path))
|
||||
monkeypatch.setenv("USERPROFILE", str(tmp_path))
|
||||
monkeypatch.delenv("MODAL_TOKEN_ID", raising=False)
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
"""Unit tests for tools/tool_backend_helpers.py.
|
||||
|
||||
Tests cover:
|
||||
- managed_nous_tools_enabled() feature flag
|
||||
- managed_nous_tools_enabled() subscription-based gate
|
||||
- normalize_browser_cloud_provider() coercion
|
||||
- coerce_modal_mode() / normalize_modal_mode() validation
|
||||
- has_direct_modal_credentials() detection
|
||||
|
|
@ -27,24 +27,51 @@ from tools.tool_backend_helpers import (
|
|||
)
|
||||
|
||||
|
||||
def _raise_import():
|
||||
raise ImportError("simulated missing module")
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# managed_nous_tools_enabled
|
||||
# ---------------------------------------------------------------------------
|
||||
class TestManagedNousToolsEnabled:
|
||||
"""Feature flag driven by HERMES_ENABLE_NOUS_MANAGED_TOOLS."""
|
||||
"""Subscription-based gate: True for paid Nous subscribers."""
|
||||
|
||||
def test_disabled_by_default(self, monkeypatch):
|
||||
monkeypatch.delenv("HERMES_ENABLE_NOUS_MANAGED_TOOLS", raising=False)
|
||||
def test_disabled_when_not_logged_in(self, monkeypatch):
|
||||
monkeypatch.setattr(
|
||||
"hermes_cli.auth.get_nous_auth_status",
|
||||
lambda: {},
|
||||
)
|
||||
assert managed_nous_tools_enabled() is False
|
||||
|
||||
@pytest.mark.parametrize("val", ["1", "true", "True", "yes"])
|
||||
def test_enabled_when_truthy(self, monkeypatch, val):
|
||||
monkeypatch.setenv("HERMES_ENABLE_NOUS_MANAGED_TOOLS", val)
|
||||
def test_disabled_for_free_tier(self, monkeypatch):
|
||||
monkeypatch.setattr(
|
||||
"hermes_cli.auth.get_nous_auth_status",
|
||||
lambda: {"logged_in": True},
|
||||
)
|
||||
monkeypatch.setattr(
|
||||
"hermes_cli.models.check_nous_free_tier",
|
||||
lambda: True,
|
||||
)
|
||||
assert managed_nous_tools_enabled() is False
|
||||
|
||||
def test_enabled_for_paid_subscriber(self, monkeypatch):
|
||||
monkeypatch.setattr(
|
||||
"hermes_cli.auth.get_nous_auth_status",
|
||||
lambda: {"logged_in": True},
|
||||
)
|
||||
monkeypatch.setattr(
|
||||
"hermes_cli.models.check_nous_free_tier",
|
||||
lambda: False,
|
||||
)
|
||||
assert managed_nous_tools_enabled() is True
|
||||
|
||||
@pytest.mark.parametrize("val", ["0", "false", "no", ""])
|
||||
def test_disabled_when_falsy(self, monkeypatch, val):
|
||||
monkeypatch.setenv("HERMES_ENABLE_NOUS_MANAGED_TOOLS", val)
|
||||
def test_returns_false_on_exception(self, monkeypatch):
|
||||
"""Should never crash — returns False on any exception."""
|
||||
monkeypatch.setattr(
|
||||
"hermes_cli.auth.get_nous_auth_status",
|
||||
_raise_import,
|
||||
)
|
||||
assert managed_nous_tools_enabled() is False
|
||||
|
||||
|
||||
|
|
@ -171,10 +198,10 @@ class TestResolveModalBackendState:
|
|||
@staticmethod
|
||||
def _resolve(monkeypatch, mode, *, has_direct, managed_ready, nous_enabled=False):
|
||||
"""Helper to call resolve_modal_backend_state with feature flag control."""
|
||||
if nous_enabled:
|
||||
monkeypatch.setenv("HERMES_ENABLE_NOUS_MANAGED_TOOLS", "1")
|
||||
else:
|
||||
monkeypatch.setenv("HERMES_ENABLE_NOUS_MANAGED_TOOLS", "")
|
||||
monkeypatch.setattr(
|
||||
"tools.tool_backend_helpers.managed_nous_tools_enabled",
|
||||
lambda: nous_enabled,
|
||||
)
|
||||
return resolve_modal_backend_state(
|
||||
mode, has_direct=has_direct, managed_ready=managed_ready
|
||||
)
|
||||
|
|
|
|||
|
|
@ -26,7 +26,6 @@ class TestFirecrawlClientConfig:
|
|||
tools.web_tools._firecrawl_client = None
|
||||
tools.web_tools._firecrawl_client_config = None
|
||||
for key in (
|
||||
"HERMES_ENABLE_NOUS_MANAGED_TOOLS",
|
||||
"FIRECRAWL_API_KEY",
|
||||
"FIRECRAWL_API_URL",
|
||||
"FIRECRAWL_GATEWAY_URL",
|
||||
|
|
@ -35,7 +34,15 @@ class TestFirecrawlClientConfig:
|
|||
"TOOL_GATEWAY_USER_TOKEN",
|
||||
):
|
||||
os.environ.pop(key, None)
|
||||
os.environ["HERMES_ENABLE_NOUS_MANAGED_TOOLS"] = "1"
|
||||
# Enable managed tools by default for these tests — patch both the
|
||||
# local web_tools import and the managed_tool_gateway import so the
|
||||
# full firecrawl client init path sees True.
|
||||
self._managed_patchers = [
|
||||
patch("tools.web_tools.managed_nous_tools_enabled", return_value=True),
|
||||
patch("tools.managed_tool_gateway.managed_nous_tools_enabled", return_value=True),
|
||||
]
|
||||
for p in self._managed_patchers:
|
||||
p.start()
|
||||
|
||||
def teardown_method(self):
|
||||
"""Reset client after each test."""
|
||||
|
|
@ -43,7 +50,6 @@ class TestFirecrawlClientConfig:
|
|||
tools.web_tools._firecrawl_client = None
|
||||
tools.web_tools._firecrawl_client_config = None
|
||||
for key in (
|
||||
"HERMES_ENABLE_NOUS_MANAGED_TOOLS",
|
||||
"FIRECRAWL_API_KEY",
|
||||
"FIRECRAWL_API_URL",
|
||||
"FIRECRAWL_GATEWAY_URL",
|
||||
|
|
@ -52,6 +58,8 @@ class TestFirecrawlClientConfig:
|
|||
"TOOL_GATEWAY_USER_TOKEN",
|
||||
):
|
||||
os.environ.pop(key, None)
|
||||
for p in self._managed_patchers:
|
||||
p.stop()
|
||||
|
||||
# ── Configuration matrix ─────────────────────────────────────────
|
||||
|
||||
|
|
@ -298,7 +306,6 @@ class TestBackendSelection:
|
|||
"""
|
||||
|
||||
_ENV_KEYS = (
|
||||
"HERMES_ENABLE_NOUS_MANAGED_TOOLS",
|
||||
"EXA_API_KEY",
|
||||
"PARALLEL_API_KEY",
|
||||
"FIRECRAWL_API_KEY",
|
||||
|
|
@ -311,14 +318,20 @@ class TestBackendSelection:
|
|||
)
|
||||
|
||||
def setup_method(self):
|
||||
os.environ["HERMES_ENABLE_NOUS_MANAGED_TOOLS"] = "1"
|
||||
for key in self._ENV_KEYS:
|
||||
if key != "HERMES_ENABLE_NOUS_MANAGED_TOOLS":
|
||||
os.environ.pop(key, None)
|
||||
os.environ.pop(key, None)
|
||||
self._managed_patchers = [
|
||||
patch("tools.web_tools.managed_nous_tools_enabled", return_value=True),
|
||||
patch("tools.managed_tool_gateway.managed_nous_tools_enabled", return_value=True),
|
||||
]
|
||||
for p in self._managed_patchers:
|
||||
p.start()
|
||||
|
||||
def teardown_method(self):
|
||||
for key in self._ENV_KEYS:
|
||||
os.environ.pop(key, None)
|
||||
for p in self._managed_patchers:
|
||||
p.stop()
|
||||
|
||||
# ── Config-based selection (web.backend in config.yaml) ───────────
|
||||
|
||||
|
|
@ -523,7 +536,6 @@ class TestCheckWebApiKey:
|
|||
"""Test suite for check_web_api_key() unified availability check."""
|
||||
|
||||
_ENV_KEYS = (
|
||||
"HERMES_ENABLE_NOUS_MANAGED_TOOLS",
|
||||
"EXA_API_KEY",
|
||||
"PARALLEL_API_KEY",
|
||||
"FIRECRAWL_API_KEY",
|
||||
|
|
@ -536,14 +548,20 @@ class TestCheckWebApiKey:
|
|||
)
|
||||
|
||||
def setup_method(self):
|
||||
os.environ["HERMES_ENABLE_NOUS_MANAGED_TOOLS"] = "1"
|
||||
for key in self._ENV_KEYS:
|
||||
if key != "HERMES_ENABLE_NOUS_MANAGED_TOOLS":
|
||||
os.environ.pop(key, None)
|
||||
os.environ.pop(key, None)
|
||||
self._managed_patchers = [
|
||||
patch("tools.web_tools.managed_nous_tools_enabled", return_value=True),
|
||||
patch("tools.managed_tool_gateway.managed_nous_tools_enabled", return_value=True),
|
||||
]
|
||||
for p in self._managed_patchers:
|
||||
p.start()
|
||||
|
||||
def teardown_method(self):
|
||||
for key in self._ENV_KEYS:
|
||||
os.environ.pop(key, None)
|
||||
for p in self._managed_patchers:
|
||||
p.stop()
|
||||
|
||||
def test_parallel_key_only(self):
|
||||
with patch.dict(os.environ, {"PARALLEL_API_KEY": "test-key"}):
|
||||
|
|
|
|||
|
|
@ -10,7 +10,7 @@ import requests
|
|||
|
||||
from tools.browser_providers.base import CloudBrowserProvider
|
||||
from tools.managed_tool_gateway import resolve_managed_tool_gateway
|
||||
from tools.tool_backend_helpers import managed_nous_tools_enabled
|
||||
from tools.tool_backend_helpers import managed_nous_tools_enabled, prefers_gateway
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
_pending_create_keys: Dict[str, str] = {}
|
||||
|
|
@ -75,7 +75,7 @@ class BrowserUseProvider(CloudBrowserProvider):
|
|||
|
||||
def _get_config_or_none(self) -> Optional[Dict[str, Any]]:
|
||||
api_key = os.environ.get("BROWSER_USE_API_KEY")
|
||||
if api_key:
|
||||
if api_key and not prefers_gateway("browser"):
|
||||
return {
|
||||
"api_key": api_key,
|
||||
"base_url": _BASE_URL,
|
||||
|
|
|
|||
|
|
@ -39,7 +39,7 @@ from urllib.parse import urlencode
|
|||
import fal_client
|
||||
from tools.debug_helpers import DebugSession
|
||||
from tools.managed_tool_gateway import resolve_managed_tool_gateway
|
||||
from tools.tool_backend_helpers import managed_nous_tools_enabled
|
||||
from tools.tool_backend_helpers import managed_nous_tools_enabled, prefers_gateway
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
|
@ -87,8 +87,9 @@ _managed_fal_client_lock = threading.Lock()
|
|||
|
||||
|
||||
def _resolve_managed_fal_gateway():
|
||||
"""Return managed fal-queue gateway config when direct FAL credentials are absent."""
|
||||
if os.getenv("FAL_KEY"):
|
||||
"""Return managed fal-queue gateway config when the user prefers the gateway
|
||||
or direct FAL credentials are absent."""
|
||||
if os.getenv("FAL_KEY") and not prefers_gateway("image_gen"):
|
||||
return None
|
||||
return resolve_managed_tool_gateway("fal-queue")
|
||||
|
||||
|
|
|
|||
|
|
@ -762,8 +762,8 @@ def _create_environment(env_type: str, image: str, cwd: str, timeout: int,
|
|||
if modal_state["managed_mode_blocked"]:
|
||||
raise ValueError(
|
||||
"Modal backend is configured for managed mode, but "
|
||||
"HERMES_ENABLE_NOUS_MANAGED_TOOLS is not enabled and no direct "
|
||||
"Modal credentials/config were found. Enable the feature flag or "
|
||||
"a paid Nous subscription is required for the Tool Gateway and no direct "
|
||||
"Modal credentials/config were found. Log in with `hermes model` or "
|
||||
"choose TERMINAL_MODAL_MODE=direct/auto."
|
||||
)
|
||||
if modal_state["mode"] == "managed":
|
||||
|
|
@ -1577,8 +1577,8 @@ def check_terminal_requirements() -> bool:
|
|||
if modal_state["managed_mode_blocked"]:
|
||||
logger.error(
|
||||
"Modal backend selected with TERMINAL_MODAL_MODE=managed, but "
|
||||
"HERMES_ENABLE_NOUS_MANAGED_TOOLS is not enabled and no direct "
|
||||
"Modal credentials/config were found. Enable the feature flag "
|
||||
"a paid Nous subscription is required for the Tool Gateway and no direct "
|
||||
"Modal credentials/config were found. Log in with `hermes model` "
|
||||
"or choose TERMINAL_MODAL_MODE=direct/auto."
|
||||
)
|
||||
return False
|
||||
|
|
|
|||
|
|
@ -6,7 +6,6 @@ import os
|
|||
from pathlib import Path
|
||||
from typing import Any, Dict
|
||||
|
||||
from utils import env_var_enabled
|
||||
|
||||
_DEFAULT_BROWSER_PROVIDER = "local"
|
||||
_DEFAULT_MODAL_MODE = "auto"
|
||||
|
|
@ -14,8 +13,26 @@ _VALID_MODAL_MODES = {"auto", "direct", "managed"}
|
|||
|
||||
|
||||
def managed_nous_tools_enabled() -> bool:
|
||||
"""Return True when the hidden Nous-managed tools feature flag is enabled."""
|
||||
return env_var_enabled("HERMES_ENABLE_NOUS_MANAGED_TOOLS")
|
||||
"""Return True when the user has an active paid Nous subscription.
|
||||
|
||||
The Tool Gateway is available to any Nous subscriber who is NOT on
|
||||
the free tier. We intentionally catch all exceptions and return
|
||||
False — never block the agent startup path.
|
||||
"""
|
||||
try:
|
||||
from hermes_cli.auth import get_nous_auth_status
|
||||
|
||||
status = get_nous_auth_status()
|
||||
if not status.get("logged_in"):
|
||||
return False
|
||||
|
||||
from hermes_cli.models import check_nous_free_tier
|
||||
|
||||
if check_nous_free_tier():
|
||||
return False # free-tier users don't get gateway access
|
||||
return True
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
|
||||
def normalize_browser_cloud_provider(value: object | None) -> str:
|
||||
|
|
@ -87,3 +104,18 @@ def resolve_openai_audio_api_key() -> str:
|
|||
os.getenv("VOICE_TOOLS_OPENAI_KEY", "")
|
||||
or os.getenv("OPENAI_API_KEY", "")
|
||||
).strip()
|
||||
|
||||
|
||||
def prefers_gateway(config_section: str) -> bool:
|
||||
"""Return True when the user opted into the Tool Gateway for this tool.
|
||||
|
||||
Reads ``<section>.use_gateway`` from config.yaml. Never raises.
|
||||
"""
|
||||
try:
|
||||
from hermes_cli.config import load_config
|
||||
section = (load_config() or {}).get(config_section)
|
||||
if isinstance(section, dict):
|
||||
return bool(section.get("use_gateway"))
|
||||
except Exception:
|
||||
pass
|
||||
return False
|
||||
|
|
|
|||
|
|
@ -44,7 +44,7 @@ from hermes_constants import display_hermes_home
|
|||
|
||||
logger = logging.getLogger(__name__)
|
||||
from tools.managed_tool_gateway import resolve_managed_tool_gateway
|
||||
from tools.tool_backend_helpers import managed_nous_tools_enabled, resolve_openai_audio_api_key
|
||||
from tools.tool_backend_helpers import managed_nous_tools_enabled, prefers_gateway, resolve_openai_audio_api_key
|
||||
from tools.xai_http import hermes_xai_user_agent
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
|
|
@ -823,9 +823,13 @@ def check_tts_requirements() -> bool:
|
|||
|
||||
|
||||
def _resolve_openai_audio_client_config() -> tuple[str, str]:
|
||||
"""Return direct OpenAI audio config or a managed gateway fallback."""
|
||||
"""Return direct OpenAI audio config or a managed gateway fallback.
|
||||
|
||||
When ``tts.use_gateway`` is set in config, the Tool Gateway is preferred
|
||||
even if direct OpenAI credentials are present.
|
||||
"""
|
||||
direct_api_key = resolve_openai_audio_api_key()
|
||||
if direct_api_key:
|
||||
if direct_api_key and not prefers_gateway("tts"):
|
||||
return direct_api_key, DEFAULT_OPENAI_BASE_URL
|
||||
|
||||
managed_gateway = resolve_managed_tool_gateway("openai-audio")
|
||||
|
|
|
|||
|
|
@ -59,7 +59,7 @@ from tools.managed_tool_gateway import (
|
|||
read_nous_access_token as _read_nous_access_token,
|
||||
resolve_managed_tool_gateway,
|
||||
)
|
||||
from tools.tool_backend_helpers import managed_nous_tools_enabled
|
||||
from tools.tool_backend_helpers import managed_nous_tools_enabled, prefers_gateway
|
||||
from tools.url_safety import is_safe_url
|
||||
from tools.website_policy import check_website_access
|
||||
|
||||
|
|
@ -165,8 +165,8 @@ def _raise_web_backend_configuration_error() -> None:
|
|||
)
|
||||
if managed_nous_tools_enabled():
|
||||
message += (
|
||||
" If you have the hidden Nous-managed tools flag enabled, you can also login to Nous "
|
||||
"(`hermes model`) and provide FIRECRAWL_GATEWAY_URL or TOOL_GATEWAY_DOMAIN."
|
||||
" With your Nous subscription you can also use the Tool Gateway — "
|
||||
"run `hermes tools` and select Nous Subscription as the web provider."
|
||||
)
|
||||
raise ValueError(message)
|
||||
|
||||
|
|
@ -176,8 +176,8 @@ def _firecrawl_backend_help_suffix() -> str:
|
|||
if not managed_nous_tools_enabled():
|
||||
return ""
|
||||
return (
|
||||
", or, if you have the hidden Nous-managed tools flag enabled, login to Nous and use "
|
||||
"FIRECRAWL_GATEWAY_URL or TOOL_GATEWAY_DOMAIN"
|
||||
", or use the Nous Tool Gateway via your subscription "
|
||||
"(FIRECRAWL_GATEWAY_URL or TOOL_GATEWAY_DOMAIN)"
|
||||
)
|
||||
|
||||
|
||||
|
|
@ -205,13 +205,14 @@ def _web_requires_env() -> list[str]:
|
|||
def _get_firecrawl_client():
|
||||
"""Get or create Firecrawl client.
|
||||
|
||||
Direct Firecrawl takes precedence when explicitly configured. Otherwise
|
||||
Hermes falls back to the Firecrawl tool-gateway for logged-in Nous Subscribers.
|
||||
When ``web.use_gateway`` is set in config, the Tool Gateway is preferred
|
||||
even if direct Firecrawl credentials are present. Otherwise direct
|
||||
Firecrawl takes precedence when explicitly configured.
|
||||
"""
|
||||
global _firecrawl_client, _firecrawl_client_config
|
||||
|
||||
direct_config = _get_direct_firecrawl_config()
|
||||
if direct_config is not None:
|
||||
if direct_config is not None and not prefers_gateway("web"):
|
||||
kwargs, client_config = direct_config
|
||||
else:
|
||||
managed_gateway = resolve_managed_tool_gateway(
|
||||
|
|
|
|||
|
|
@ -267,7 +267,6 @@ Run `nix build .#configKeys && cat result` to see every leaf config key extracte
|
|||
|
||||
# ── Documents ──────────────────────────────────────────────────────
|
||||
documents = {
|
||||
"SOUL.md" = builtins.readFile /home/user/.hermes/SOUL.md;
|
||||
"USER.md" = ./documents/USER.md;
|
||||
};
|
||||
|
||||
|
|
@ -316,7 +315,7 @@ Quick reference for the most common things Nix users want to customize:
|
|||
| Change the LLM model | `settings.model.default` | `"anthropic/claude-sonnet-4"` |
|
||||
| Use a different provider endpoint | `settings.model.base_url` | `"https://openrouter.ai/api/v1"` |
|
||||
| Add API keys | `environmentFiles` | `[ config.sops.secrets."hermes-env".path ]` |
|
||||
| Give the agent a personality | `documents."SOUL.md"` | `builtins.readFile ./my-soul.md` |
|
||||
| Give the agent a personality | `${services.hermes-agent.stateDir}/.hermes/SOUL.md` | manage the file directly |
|
||||
| Add MCP tool servers | `mcpServers.<name>` | See [MCP Servers](#mcp-servers) |
|
||||
| Mount host directories into container | `container.extraVolumes` | `[ "/data:/data:rw" ]` |
|
||||
| Pass GPU access to container | `container.extraOptions` | `[ "--gpus" "all" ]` |
|
||||
|
|
@ -397,17 +396,14 @@ The file is only copied if `auth.json` doesn't already exist (unless `authFileFo
|
|||
|
||||
The `documents` option installs files into the agent's working directory (the `workingDirectory`, which the agent reads as its workspace). Hermes looks for specific filenames by convention:
|
||||
|
||||
- **`SOUL.md`** — the agent's system prompt / personality. Hermes reads this on startup and uses it as persistent instructions that shape its behavior across all conversations.
|
||||
- **`USER.md`** — context about the user the agent is interacting with.
|
||||
- Any other files you place here are visible to the agent as workspace files.
|
||||
|
||||
The agent identity file is separate: Hermes loads its primary `SOUL.md` from `$HERMES_HOME/SOUL.md`, which in the NixOS module is `${services.hermes-agent.stateDir}/.hermes/SOUL.md`. Putting `SOUL.md` in `documents` only creates a workspace file and will not replace the main persona file.
|
||||
|
||||
```nix
|
||||
{
|
||||
services.hermes-agent.documents = {
|
||||
"SOUL.md" = ''
|
||||
You are a helpful research assistant specializing in NixOS packaging.
|
||||
Always cite sources and prefer reproducible solutions.
|
||||
'';
|
||||
"USER.md" = ./documents/USER.md; # path reference, copied from Nix store
|
||||
};
|
||||
}
|
||||
|
|
|
|||
|
|
@ -65,11 +65,7 @@ If `git status --short` shows unexpected changes after `hermes update`, stop and
|
|||
hermes version
|
||||
```
|
||||
|
||||
Compare against the latest release at the [GitHub releases page](https://github.com/NousResearch/hermes-agent/releases) or check for available updates:
|
||||
|
||||
```bash
|
||||
hermes update --check
|
||||
```
|
||||
Compare against the latest release at the [GitHub releases page](https://github.com/NousResearch/hermes-agent/releases).
|
||||
|
||||
### Updating from Messaging Platforms
|
||||
|
||||
|
|
|
|||
|
|
@ -49,6 +49,10 @@ The OpenAI Codex provider authenticates via device code (open a URL, enter a cod
|
|||
Even when using Nous Portal, Codex, or a custom endpoint, some tools (vision, web summarization, MoA) use a separate "auxiliary" model — by default Gemini Flash via OpenRouter. An `OPENROUTER_API_KEY` enables these tools automatically. You can also configure which model and provider these tools use — see [Auxiliary Models](/docs/user-guide/configuration#auxiliary-models).
|
||||
:::
|
||||
|
||||
:::tip Nous Tool Gateway
|
||||
Paid Nous Portal subscribers also get access to the **[Tool Gateway](/docs/user-guide/features/tool-gateway)** — web search, image generation, TTS, and browser automation routed through your subscription. No extra API keys needed. It's offered automatically during `hermes model` setup, or enable it later with `hermes tools`.
|
||||
:::
|
||||
|
||||
### Two Commands for Model Management
|
||||
|
||||
Hermes has **two** model commands that serve different purposes:
|
||||
|
|
|
|||
|
|
@ -110,6 +110,17 @@ For native Anthropic auth, Hermes prefers Claude Code's own credential files whe
|
|||
| `WANDB_API_KEY` | RL training metrics ([wandb.ai](https://wandb.ai/)) |
|
||||
| `DAYTONA_API_KEY` | Daytona cloud sandboxes ([daytona.io](https://daytona.io/)) |
|
||||
|
||||
### Nous Tool Gateway
|
||||
|
||||
These variables configure the [Tool Gateway](/docs/user-guide/features/tool-gateway) for paid Nous subscribers or self-hosted gateway deployments. Most users don't need to set these — the gateway is configured automatically via `hermes model` or `hermes tools`.
|
||||
|
||||
| Variable | Description |
|
||||
|----------|-------------|
|
||||
| `TOOL_GATEWAY_DOMAIN` | Base domain for Tool Gateway routing (default: `nousresearch.com`) |
|
||||
| `TOOL_GATEWAY_SCHEME` | HTTP or HTTPS scheme for gateway URLs (default: `https`) |
|
||||
| `TOOL_GATEWAY_USER_TOKEN` | Auth token for the Tool Gateway (normally auto-populated from Nous auth) |
|
||||
| `FIRECRAWL_GATEWAY_URL` | Override URL for the Firecrawl gateway endpoint specifically |
|
||||
|
||||
## Terminal Backend
|
||||
|
||||
| Variable | Description |
|
||||
|
|
|
|||
|
|
@ -33,6 +33,10 @@ Key capabilities:
|
|||
|
||||
## Setup
|
||||
|
||||
:::tip Nous Subscribers
|
||||
If you have a paid [Nous Portal](https://portal.nousresearch.com) subscription, you can use browser automation through the **[Tool Gateway](tool-gateway.md)** without any separate API keys. Run `hermes model` or `hermes tools` to enable it.
|
||||
:::
|
||||
|
||||
### Browserbase cloud mode
|
||||
|
||||
To use Browserbase-managed cloud browsers, add:
|
||||
|
|
|
|||
|
|
@ -11,6 +11,10 @@ Hermes Agent can generate images from text prompts using FAL.ai's **FLUX 2 Pro**
|
|||
|
||||
## Setup
|
||||
|
||||
:::tip Nous Subscribers
|
||||
If you have a paid [Nous Portal](https://portal.nousresearch.com) subscription, you can use image generation through the **[Tool Gateway](tool-gateway.md)** without a FAL API key. Run `hermes model` or `hermes tools` to enable it.
|
||||
:::
|
||||
|
||||
### Get a FAL API Key
|
||||
|
||||
1. Sign up at [fal.ai](https://fal.ai/)
|
||||
|
|
|
|||
187
website/docs/user-guide/features/tool-gateway.md
Normal file
187
website/docs/user-guide/features/tool-gateway.md
Normal file
|
|
@ -0,0 +1,187 @@
|
|||
---
|
||||
title: "Nous Tool Gateway"
|
||||
description: "Route web search, image generation, text-to-speech, and browser automation through your Nous subscription — no extra API keys needed"
|
||||
sidebar_label: "Tool Gateway"
|
||||
sidebar_position: 2
|
||||
---
|
||||
|
||||
# Nous Tool Gateway
|
||||
|
||||
:::tip Get Started
|
||||
The Tool Gateway is included with paid Nous Portal subscriptions. **[Manage your subscription →](https://portal.nousresearch.com/manage-subscription)**
|
||||
:::
|
||||
|
||||
The **Tool Gateway** lets paid [Nous Portal](https://portal.nousresearch.com) subscribers use web search, image generation, text-to-speech, and browser automation through their existing subscription — no need to sign up for separate API keys from Firecrawl, FAL, OpenAI, or Browser Use.
|
||||
|
||||
## What's Included
|
||||
|
||||
| Tool | What It Does | Direct Alternative |
|
||||
|------|--------------|--------------------|
|
||||
| **Web search & extract** | Search the web and extract page content via Firecrawl | `FIRECRAWL_API_KEY`, `EXA_API_KEY`, `PARALLEL_API_KEY`, `TAVILY_API_KEY` |
|
||||
| **Image generation** | Generate images via FAL (FLUX 2 Pro + upscaling) | `FAL_KEY` |
|
||||
| **Text-to-speech** | Convert text to speech via OpenAI TTS | `VOICE_TOOLS_OPENAI_KEY`, `ELEVENLABS_API_KEY` |
|
||||
| **Browser automation** | Control cloud browsers via Browser Use | `BROWSER_USE_API_KEY`, `BROWSERBASE_API_KEY` |
|
||||
|
||||
All four tools bill to your Nous subscription. You can enable any combination — for example, use the gateway for web and image generation while keeping your own ElevenLabs key for TTS.
|
||||
|
||||
## Eligibility
|
||||
|
||||
The Tool Gateway is available to **paid** [Nous Portal](https://portal.nousresearch.com/manage-subscription) subscribers. Free-tier accounts do not have access — [upgrade your subscription](https://portal.nousresearch.com/manage-subscription) to unlock it.
|
||||
|
||||
To check your status:
|
||||
|
||||
```bash
|
||||
hermes status
|
||||
```
|
||||
|
||||
Look for the **Nous Tool Gateway** section. It shows which tools are active via the gateway, which use direct keys, and which aren't configured.
|
||||
|
||||
## Enabling the Tool Gateway
|
||||
|
||||
### During model setup
|
||||
|
||||
When you run `hermes model` and select Nous Portal as your provider, Hermes automatically offers to enable the Tool Gateway:
|
||||
|
||||
```
|
||||
Your Nous subscription includes the Tool Gateway.
|
||||
|
||||
The Tool Gateway gives you access to web search, image generation,
|
||||
text-to-speech, and browser automation through your Nous subscription.
|
||||
No need to sign up for separate API keys — just pick the tools you want.
|
||||
|
||||
○ Web search & extract (Firecrawl) — not configured
|
||||
○ Image generation (FAL) — not configured
|
||||
○ Text-to-speech (OpenAI TTS) — not configured
|
||||
○ Browser automation (Browser Use) — not configured
|
||||
|
||||
● Enable Tool Gateway
|
||||
○ Skip
|
||||
```
|
||||
|
||||
Select **Enable Tool Gateway** and you're done.
|
||||
|
||||
If you already have direct API keys for some tools, the prompt adapts — you can enable the gateway for all tools (your existing keys are kept in `.env` but not used at runtime), enable only for unconfigured tools, or skip entirely.
|
||||
|
||||
### Via `hermes tools`
|
||||
|
||||
You can also enable the gateway tool-by-tool through the interactive tool configuration:
|
||||
|
||||
```bash
|
||||
hermes tools
|
||||
```
|
||||
|
||||
Select a tool category (Web, Browser, Image Generation, or TTS), then choose **Nous Subscription** as the provider. This sets `use_gateway: true` for that tool in your config.
|
||||
|
||||
### Manual configuration
|
||||
|
||||
Set the `use_gateway` flag directly in `~/.hermes/config.yaml`:
|
||||
|
||||
```yaml
|
||||
web:
|
||||
backend: firecrawl
|
||||
use_gateway: true
|
||||
|
||||
image_gen:
|
||||
use_gateway: true
|
||||
|
||||
tts:
|
||||
provider: openai
|
||||
use_gateway: true
|
||||
|
||||
browser:
|
||||
cloud_provider: browser-use
|
||||
use_gateway: true
|
||||
```
|
||||
|
||||
## How It Works
|
||||
|
||||
When `use_gateway: true` is set for a tool, the runtime routes API calls through the Nous Tool Gateway instead of using direct API keys:
|
||||
|
||||
1. **Web tools** — `web_search` and `web_extract` use the gateway's Firecrawl endpoint
|
||||
2. **Image generation** — `image_generate` uses the gateway's FAL endpoint
|
||||
3. **TTS** — `text_to_speech` uses the gateway's OpenAI Audio endpoint
|
||||
4. **Browser** — `browser_navigate` and other browser tools use the gateway's Browser Use endpoint
|
||||
|
||||
The gateway authenticates using your Nous Portal credentials (stored in `~/.hermes/auth.json` after `hermes model`).
|
||||
|
||||
### Precedence
|
||||
|
||||
Each tool checks `use_gateway` first:
|
||||
|
||||
- **`use_gateway: true`** → route through the gateway, even if direct API keys exist in `.env`
|
||||
- **`use_gateway: false`** (or absent) → use direct API keys if available, fall back to gateway only when no direct keys exist
|
||||
|
||||
This means you can switch between gateway and direct keys at any time without deleting your `.env` credentials.
|
||||
|
||||
## Switching Back to Direct Keys
|
||||
|
||||
To stop using the gateway for a specific tool:
|
||||
|
||||
```bash
|
||||
hermes tools # Select the tool → choose a direct provider
|
||||
```
|
||||
|
||||
Or set `use_gateway: false` in config:
|
||||
|
||||
```yaml
|
||||
web:
|
||||
backend: firecrawl
|
||||
use_gateway: false # Now uses FIRECRAWL_API_KEY from .env
|
||||
```
|
||||
|
||||
When you select a non-gateway provider in `hermes tools`, the `use_gateway` flag is automatically set to `false` to prevent contradictory config.
|
||||
|
||||
## Checking Status
|
||||
|
||||
```bash
|
||||
hermes status
|
||||
```
|
||||
|
||||
The **Nous Tool Gateway** section shows:
|
||||
|
||||
```
|
||||
◆ Nous Tool Gateway
|
||||
Nous Portal ✓ managed tools available
|
||||
Web tools ✓ active via Nous subscription
|
||||
Image gen ✓ active via Nous subscription
|
||||
TTS ✓ active via Nous subscription
|
||||
Browser ○ active via Browser Use key
|
||||
Modal ○ available via subscription (optional)
|
||||
```
|
||||
|
||||
Tools marked "active via Nous subscription" are routed through the gateway. Tools with their own keys show which provider is active.
|
||||
|
||||
## Advanced: Self-Hosted Gateway
|
||||
|
||||
For self-hosted or custom gateway deployments, you can override the gateway endpoints via environment variables in `~/.hermes/.env`:
|
||||
|
||||
```bash
|
||||
TOOL_GATEWAY_DOMAIN=nousresearch.com # Base domain for gateway routing
|
||||
TOOL_GATEWAY_SCHEME=https # HTTP or HTTPS (default: https)
|
||||
TOOL_GATEWAY_USER_TOKEN=your-token # Auth token (normally auto-populated)
|
||||
FIRECRAWL_GATEWAY_URL=https://... # Override for the Firecrawl endpoint specifically
|
||||
```
|
||||
|
||||
These env vars are always visible in the configuration regardless of subscription status — they're useful for custom infrastructure setups.
|
||||
|
||||
## FAQ
|
||||
|
||||
### Do I need to delete my existing API keys?
|
||||
|
||||
No. When `use_gateway: true` is set, the runtime skips direct API keys and routes through the gateway. Your keys stay in `.env` untouched. If you later disable the gateway, they'll be used again automatically.
|
||||
|
||||
### Can I use the gateway for some tools and direct keys for others?
|
||||
|
||||
Yes. The `use_gateway` flag is per-tool. You can mix and match — for example, gateway for web and image generation, your own ElevenLabs key for TTS, and Browserbase for browser automation.
|
||||
|
||||
### What if my subscription expires?
|
||||
|
||||
Tools that were routed through the gateway will stop working until you [renew your subscription](https://portal.nousresearch.com/manage-subscription) or switch to direct API keys via `hermes tools`.
|
||||
|
||||
### Does the gateway work with the messaging gateway?
|
||||
|
||||
Yes. The Tool Gateway routes tool API calls regardless of whether you're using the CLI, Telegram, Discord, or any other messaging platform. It operates at the tool runtime level, not the entry point level.
|
||||
|
||||
### Is Modal included?
|
||||
|
||||
Modal (serverless terminal backend) is available as an optional add-on through the Nous subscription. It's not enabled by the Tool Gateway prompt — configure it separately via `hermes setup terminal` or in `config.yaml`.
|
||||
|
|
@ -31,6 +31,10 @@ High-level categories:
|
|||
|
||||
For the authoritative code-derived registry, see [Built-in Tools Reference](/docs/reference/tools-reference) and [Toolsets Reference](/docs/reference/toolsets-reference).
|
||||
|
||||
:::tip Nous Tool Gateway
|
||||
Paid [Nous Portal](https://portal.nousresearch.com) subscribers can use web search, image generation, TTS, and browser automation through the **[Tool Gateway](tool-gateway.md)** — no separate API keys needed. Run `hermes model` to enable it, or configure individual tools with `hermes tools`.
|
||||
:::
|
||||
|
||||
## Using Toolsets
|
||||
|
||||
```bash
|
||||
|
|
|
|||
|
|
@ -8,6 +8,10 @@ description: "Text-to-speech and voice message transcription across all platform
|
|||
|
||||
Hermes Agent supports both text-to-speech output and voice message transcription across all messaging platforms.
|
||||
|
||||
:::tip Nous Subscribers
|
||||
If you have a paid [Nous Portal](https://portal.nousresearch.com) subscription, OpenAI TTS is available through the **[Tool Gateway](tool-gateway.md)** without a separate OpenAI API key. Run `hermes model` or `hermes tools` to enable it.
|
||||
:::
|
||||
|
||||
## Text-to-Speech
|
||||
|
||||
Convert text to speech with six providers:
|
||||
|
|
|
|||
|
|
@ -36,6 +36,7 @@ const sidebars: SidebarsConfig = {
|
|||
collapsed: true,
|
||||
items: [
|
||||
'user-guide/features/overview',
|
||||
'user-guide/features/tool-gateway',
|
||||
{
|
||||
type: 'category',
|
||||
label: 'Core',
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue