mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-05-15 04:12:25 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 9

Merge branch 'main' into compaction-secrets-preservation

Browse source
This commit is contained in:
Mariano Nicolini 2026-04-14 11:18:20 -03:00
commit ef32968408
247 changed files with 13395 additions and 2874 deletions
Download patch file Download diff file Expand all files Collapse all files

15
agent/anthropic_adapter.py
View file

@ -1230,9 +1230,10 @@ def build_anthropic_kwargs(
When *base_url* points to a third-party Anthropic-compatible endpoint,
thinking block signatures are stripped (they are Anthropic-proprietary).
When *fast_mode* is True, adds ``speed: "fast"`` and the fast-mode beta
header for ~2.5x faster output throughput on Opus 4.6. Currently only
supported on native Anthropic endpoints (not third-party compatible ones).
When *fast_mode* is True, adds ``extra_body["speed"] = "fast"`` and the
fast-mode beta header for ~2.5x faster output throughput on Opus 4.6.
Currently only supported on native Anthropic endpoints (not third-party
compatible ones).
"""
system, anthropic_messages = convert_messages_to_anthropic(messages, base_url=base_url)
anthropic_tools = convert_tools_to_anthropic(tools) if tools else []
@ -1333,11 +1334,11 @@ def build_anthropic_kwargs(
kwargs["max_tokens"] = max(effective_max_tokens, budget + 4096)
# ── Fast mode (Opus 4.6 only) ────────────────────────────────────
# Adds speed:"fast" + the fast-mode beta header for ~2.5x output speed.
# Only for native Anthropic endpoints — third-party providers would
# reject the unknown beta header and speed parameter.
# Adds extra_body.speed="fast" + the fast-mode beta header for ~2.5x
# output speed. Only for native Anthropic endpoints — third-party
# providers would reject the unknown beta header and speed parameter.
if fast_mode and not _is_third_party_anthropic_endpoint(base_url):
kwargs["speed"] = "fast"
kwargs.setdefault("extra_body", {})["speed"] = "fast"
# Build extra_headers with ALL applicable betas (the per-request
# extra_headers override the client-level anthropic-beta header).
betas = list(_common_betas_for_base_url(base_url))

58
agent/auxiliary_client.py
View file

@ -64,6 +64,8 @@ _PROVIDER_ALIASES = {
"zhipu": "zai",
"kimi": "kimi-coding",
"moonshot": "kimi-coding",
"kimi-cn": "kimi-coding-cn",
"moonshot-cn": "kimi-coding-cn",
"minimax-china": "minimax-cn",
"minimax_cn": "minimax-cn",
"claude": "anthropic",
@ -94,6 +96,7 @@ _API_KEY_PROVIDER_AUX_MODELS: Dict[str, str] = {
"gemini": "gemini-3-flash-preview",
"zai": "glm-4.5-flash",
"kimi-coding": "kimi-k2-turbo-preview",
"kimi-coding-cn": "kimi-k2-turbo-preview",
"minimax": "MiniMax-M2.7",
"minimax-cn": "MiniMax-M2.7",
"anthropic": "claude-haiku-4-5-20251001",
@ -1220,6 +1223,12 @@ def _to_async_client(sync_client, model: str):
return AsyncCodexAuxiliaryClient(sync_client), model
if isinstance(sync_client, AnthropicAuxiliaryClient):
return AsyncAnthropicAuxiliaryClient(sync_client), model
try:
from agent.copilot_acp_client import CopilotACPClient
if isinstance(sync_client, CopilotACPClient):
return sync_client, model
except ImportError:
pass
async_kwargs = {
"api_key": sync_client.api_key,
@ -1438,10 +1447,14 @@ def resolve_provider_client(
custom_entry = _get_named_custom_provider(provider)
if custom_entry:
custom_base = custom_entry.get("base_url", "").strip()
custom_key = custom_entry.get("api_key", "").strip() or "no-key-required"
custom_key = custom_entry.get("api_key", "").strip()
custom_key_env = custom_entry.get("key_env", "").strip()
if not custom_key and custom_key_env:
custom_key = os.getenv(custom_key_env, "").strip()
custom_key = custom_key or "no-key-required"
if custom_base:
final_model = _normalize_resolved_model(
model or _read_main_model() or "gpt-4o-mini",
model or custom_entry.get("model") or _read_main_model() or "gpt-4o-mini",
provider,
)
client = OpenAI(api_key=custom_key, base_url=custom_base)
@ -1460,7 +1473,11 @@ def resolve_provider_client(
# ── API-key providers from PROVIDER_REGISTRY ─────────────────────
try:
from hermes_cli.auth import PROVIDER_REGISTRY, resolve_api_key_provider_credentials
from hermes_cli.auth import (
PROVIDER_REGISTRY,
resolve_api_key_provider_credentials,
resolve_external_process_provider_credentials,
)
except ImportError:
logger.debug("hermes_cli.auth not available for provider %s", provider)
return None, None
@ -1534,6 +1551,41 @@ def resolve_provider_client(
return (_to_async_client(client, final_model) if async_mode
else (client, final_model))
if pconfig.auth_type == "external_process":
creds = resolve_external_process_provider_credentials(provider)
final_model = _normalize_resolved_model(model or _read_main_model(), provider)
if provider == "copilot-acp":
api_key = str(creds.get("api_key", "")).strip()
base_url = str(creds.get("base_url", "")).strip()
command = str(creds.get("command", "")).strip() or None
args = list(creds.get("args") or [])
if not final_model:
logger.warning(
"resolve_provider_client: copilot-acp requested but no model "
"was provided or configured"
)
return None, None
if not api_key or not base_url:
logger.warning(
"resolve_provider_client: copilot-acp requested but external "
"process credentials are incomplete"
)
return None, None
from agent.copilot_acp_client import CopilotACPClient
client = CopilotACPClient(
api_key=api_key,
base_url=base_url,
command=command,
args=args,
)
logger.debug("resolve_provider_client: %s (%s)", provider, final_model)
return (_to_async_client(client, final_model) if async_mode
else (client, final_model))
logger.warning("resolve_provider_client: external-process provider %s not "
"directly supported", provider)
return None, None
elif pconfig.auth_type in ("oauth_device_code", "oauth_external"):
# OAuth providers — route through their specific try functions
if provider == "nous":

2
agent/context_engine.py
View file

@ -26,7 +26,7 @@ Lifecycle:
"""
from abc import ABC, abstractmethod
from typing import Any, Dict, List, Optional
from typing import Any, Dict, List
class ContextEngine(ABC):

9
agent/credential_pool.py
View file

@ -18,7 +18,6 @@ import hermes_cli.auth as auth_mod
from hermes_cli.auth import (
CODEX_ACCESS_TOKEN_REFRESH_SKEW_SECONDS,
DEFAULT_AGENT_KEY_MIN_TTL_SECONDS,
KIMI_CODE_BASE_URL,
PROVIDER_REGISTRY,
_auth_store_lock,
_codex_access_token_is_expiring,
@ -289,6 +288,14 @@ def _iter_custom_providers(config: Optional[dict] = None):
return
custom_providers = config.get("custom_providers")
if not isinstance(custom_providers, list):
# Fall back to the v12+ providers dict via the compatibility layer
try:
from hermes_cli.config import get_compatible_custom_providers
custom_providers = get_compatible_custom_providers(config)
except Exception:
return
if not custom_providers:
return
for entry in custom_providers:
if not isinstance(entry, dict):

6
agent/display.py
View file

@ -77,12 +77,6 @@ def _diff_ansi() -> dict[str, str]:
return _diff_colors_cached
def reset_diff_colors() -> None:
"""Reset cached diff colors (call after /skin switch)."""
global _diff_colors_cached
_diff_colors_cached = None
# Module-level helpers — each call resolves from the active skin lazily.
def _diff_dim(): return _diff_ansi()["dim"]
def _diff_file(): return _diff_ansi()["file"]

13
agent/error_classifier.py
View file

@ -13,7 +13,6 @@ from __future__ import annotations
import enum
import logging
import re
from dataclasses import dataclass, field
from typing import Any, Dict, Optional
@ -157,6 +156,18 @@ _CONTEXT_OVERFLOW_PATTERNS = [
"prompt exceeds max length",
"max_tokens",
"maximum number of tokens",
# vLLM / local inference server patterns
"exceeds the max_model_len",
"max_model_len",
"prompt length", # "engine prompt length X exceeds"
"input is too long",
"maximum model length",
# Ollama patterns
"context length exceeded",
"truncating input",
# llama.cpp / llama-server patterns
"slot context", # "slot context: N tokens, prompt N tokens"
"n_ctx_slot",
# Chinese error messages (some providers return these)
"超过最大长度",
"上下文长度",

1
agent/insights.py
View file

@ -27,7 +27,6 @@ from agent.usage_pricing import (
DEFAULT_PRICING,
estimate_usage_cost,
format_duration_compact,
get_pricing,
has_known_pricing,
)

1
agent/memory_manager.py
View file

@ -28,7 +28,6 @@ Usage in run_agent.py:
from __future__ import annotations
import json
import logging
import re
from typing import Any, Dict, List, Optional

21
agent/model_metadata.py
View file

@ -5,7 +5,6 @@ and run_agent.py for pre-flight context checks.
"""
import logging
import os
import re
import time
from pathlib import Path
@ -24,17 +23,19 @@ logger = logging.getLogger(__name__)
# are preserved so the full model name reaches cache lookups and server queries.
_PROVIDER_PREFIXES: frozenset[str] = frozenset({
"openrouter", "nous", "openai-codex", "copilot", "copilot-acp",
"gemini", "zai", "kimi-coding", "minimax", "minimax-cn", "anthropic", "deepseek",
"gemini", "zai", "kimi-coding", "kimi-coding-cn", "minimax", "minimax-cn", "anthropic", "deepseek",
"opencode-zen", "opencode-go", "ai-gateway", "kilocode", "alibaba",
"qwen-oauth",
"xiaomi",
"arcee",
"custom", "local",
# Common aliases
"google", "google-gemini", "google-ai-studio",
"glm", "z-ai", "z.ai", "zhipu", "github", "github-copilot",
"github-models", "kimi", "moonshot", "claude", "deep-seek",
"github-models", "kimi", "moonshot", "kimi-cn", "moonshot-cn", "claude", "deep-seek",
"opencode", "zen", "go", "vercel", "kilo", "dashscope", "aliyun", "qwen",
"mimo", "xiaomi-mimo",
"arcee-ai", "arceeai",
"qwen-portal",
})
@ -105,9 +106,15 @@ DEFAULT_CONTEXT_LENGTHS = {
"claude-sonnet-4.6": 1000000,
# Catch-all for older Claude models (must sort after specific entries)
"claude": 200000,
# OpenAI
# OpenAI — GPT-5 family (most have 400k; specific overrides first)
# Source: https://developers.openai.com/api/docs/models
"gpt-5.4-nano": 400000, # 400k (not 1.05M like full 5.4)
"gpt-5.4-mini": 400000, # 400k (not 1.05M like full 5.4)
"gpt-5.4": 1050000, # GPT-5.4, GPT-5.4 Pro (1.05M context)
"gpt-5.3-codex-spark": 128000, # Spark variant has reduced 128k context
"gpt-5.1-chat": 128000, # Chat variant has 128k context
"gpt-5": 400000, # GPT-5.x base, mini, codex variants (400k)
"gpt-4.1": 1047576,
"gpt-5": 128000,
"gpt-4": 128000,
# Google
"gemini": 1048576,
@ -149,6 +156,8 @@ DEFAULT_CONTEXT_LENGTHS = {
"kimi": 262144,
# Arcee
"trinity": 262144,
# OpenRouter
"elephant": 262144,
# Hugging Face Inference Providers — model IDs use org/name format
"Qwen/Qwen3.5-397B-A17B": 131072,
"Qwen/Qwen3.5-35B-A3B": 131072,
@ -211,7 +220,9 @@ _URL_TO_PROVIDER: Dict[str, str] = {
"api.anthropic.com": "anthropic",
"api.z.ai": "zai",
"api.moonshot.ai": "kimi-coding",
"api.moonshot.cn": "kimi-coding-cn",
"api.kimi.com": "kimi-coding",
"api.arcee.ai": "arcee",
"api.minimax": "minimax",
"dashscope.aliyuncs.com": "alibaba",
"dashscope-intl.aliyuncs.com": "alibaba",

97
agent/models_dev.py
View file

@ -18,10 +18,8 @@ Other modules should import the dataclasses and query functions from here
rather than parsing the raw JSON themselves.
"""
import difflib
import json
import logging
import os
import time
from dataclasses import dataclass
from pathlib import Path
@ -148,6 +146,7 @@ PROVIDER_TO_MODELS_DEV: Dict[str, str] = {
"openai-codex": "openai",
"zai": "zai",
"kimi-coding": "kimi-for-coding",
"kimi-coding-cn": "kimi-for-coding",
"minimax": "minimax",
"minimax-cn": "minimax-cn",
"deepseek": "deepseek",
@ -176,13 +175,6 @@ PROVIDER_TO_MODELS_DEV: Dict[str, str] = {
_MODELS_DEV_TO_PROVIDER: Optional[Dict[str, str]] = None
def _get_reverse_mapping() -> Dict[str, str]:
"""Return models.dev ID → Hermes provider ID mapping."""
global _MODELS_DEV_TO_PROVIDER
if _MODELS_DEV_TO_PROVIDER is None:
_MODELS_DEV_TO_PROVIDER = {v: k for k, v in PROVIDER_TO_MODELS_DEV.items()}
return _MODELS_DEV_TO_PROVIDER
def _get_cache_path() -> Path:
"""Return path to disk cache file."""
@ -463,93 +455,6 @@ def list_agentic_models(provider: str) -> List[str]:
return result
def search_models_dev(
query: str, provider: str = None, limit: int = 5
) -> List[Dict[str, Any]]:
"""Fuzzy search across models.dev catalog. Returns matching model entries.
Args:
query: Search string to match against model IDs.
provider: Optional Hermes provider ID to restrict search scope.
If None, searches across all providers in PROVIDER_TO_MODELS_DEV.
limit: Maximum number of results to return.
Returns:
List of dicts, each containing 'provider', 'model_id', and the full
model 'entry' from models.dev.
"""
data = fetch_models_dev()
if not data:
return []
# Build list of (provider_id, model_id, entry) candidates
candidates: List[tuple] = []
if provider is not None:
# Search only the specified provider
mdev_provider_id = PROVIDER_TO_MODELS_DEV.get(provider)
if not mdev_provider_id:
return []
provider_data = data.get(mdev_provider_id, {})
if isinstance(provider_data, dict):
models = provider_data.get("models", {})
if isinstance(models, dict):
for mid, mdata in models.items():
candidates.append((provider, mid, mdata))
else:
# Search across all mapped providers
for hermes_prov, mdev_prov in PROVIDER_TO_MODELS_DEV.items():
provider_data = data.get(mdev_prov, {})
if isinstance(provider_data, dict):
models = provider_data.get("models", {})
if isinstance(models, dict):
for mid, mdata in models.items():
candidates.append((hermes_prov, mid, mdata))
if not candidates:
return []
# Use difflib for fuzzy matching — case-insensitive comparison
model_ids_lower = [c[1].lower() for c in candidates]
query_lower = query.lower()
# First try exact substring matches (more intuitive than pure edit-distance)
substring_matches = []
for prov, mid, mdata in candidates:
if query_lower in mid.lower():
substring_matches.append({"provider": prov, "model_id": mid, "entry": mdata})
# Then add difflib fuzzy matches for any remaining slots
fuzzy_ids = difflib.get_close_matches(
query_lower, model_ids_lower, n=limit * 2, cutoff=0.4
)
seen_ids: set = set()
results: List[Dict[str, Any]] = []
# Prioritize substring matches
for match in substring_matches:
key = (match["provider"], match["model_id"])
if key not in seen_ids:
seen_ids.add(key)
results.append(match)
if len(results) >= limit:
return results
# Add fuzzy matches
for fid in fuzzy_ids:
# Find original-case candidates matching this lowered ID
for prov, mid, mdata in candidates:
if mid.lower() == fid:
key = (prov, mid)
if key not in seen_ids:
seen_ids.add(key)
results.append({"provider": prov, "model_id": mid, "entry": mdata})
if len(results) >= limit:
return results
return results
# ---------------------------------------------------------------------------
# Rich dataclass constructors — parse raw models.dev JSON into dataclasses

6
agent/prompt_builder.py
View file

@ -376,6 +376,12 @@ PLATFORM_HINTS = {
"downloaded and sent as native photos. Do NOT tell the user you lack file-sending "
"capability — use MEDIA: syntax whenever a file delivery is appropriate."
),
"qqbot": (
"You are on QQ, a popular Chinese messaging platform. QQ supports markdown formatting "
"and emoji. You can send media files natively: include MEDIA:/absolute/path/to/file in "
"your response. Images are sent as native photos, and other files arrive as downloadable "
"documents."
),
}
# ---------------------------------------------------------------------------

2
agent/rate_limit_tracker.py
View file

@ -24,7 +24,7 @@ from __future__ import annotations
import time
from dataclasses import dataclass, field
from typing import Any, Dict, Mapping, Optional
from typing import Any, Mapping, Optional
@dataclass

19
agent/usage_pricing.py
View file

@ -575,25 +575,6 @@ def has_known_pricing(
return entry is not None
def get_pricing(
model_name: str,
provider: Optional[str] = None,
base_url: Optional[str] = None,
api_key: Optional[str] = None,
) -> Dict[str, float]:
"""Backward-compatible thin wrapper for legacy callers.
Returns only non-cache input/output fields when a pricing entry exists.
Unknown routes return zeroes.
"""
entry = get_pricing_entry(model_name, provider=provider, base_url=base_url, api_key=api_key)
if not entry:
return {"input": 0.0, "output": 0.0}
return {
"input": float(entry.input_cost_per_million or _ZERO),
"output": float(entry.output_cost_per_million or _ZERO),
}
def format_duration_compact(seconds: float) -> str:
if seconds < 60: