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

feat(xai): upgrade to Responses API, add TTS provider

Browse Source 
Cherry-picked and trimmed from PR #10600 by Jaaneek.

- Switch xAI transport from openai_chat to codex_responses (Responses API)
- Add codex_responses detection for xAI in all runtime_provider resolution paths
- Add xAI api_mode detection in AIAgent.__init__ (provider name + URL auto-detect)
- Add extra_headers passthrough for codex_responses requests
- Add x-grok-conv-id session header for xAI prompt caching
- Add xAI reasoning support (encrypted_content include, no effort param)
- Move x-grok-conv-id from chat_completions path to codex_responses path
- Add xAI TTS provider (dedicated /v1/tts endpoint with Opus conversion)
- Add xAI provider aliases (grok, x-ai, x.ai) across auth, models, providers, auxiliary
- Trim xAI model list to agentic models (grok-4.20-reasoning, grok-4-1-fast-reasoning)
- Add XAI_API_KEY/XAI_BASE_URL to OPTIONAL_ENV_VARS
- Add xAI TTS config section, setup wizard entry, tools_config provider option
- Add shared xai_http.py helper for User-Agent string

Co-authored-by: Jaaneek <Jaaneek@users.noreply.github.com>
This commit is contained in:
Teknium
2026-04-15 22:27:26 -07:00
committed by Teknium
parent 330ed12fb1
commit 0c1217d01e
14 changed files with 189 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
hermes_cli/auth.py
View File

@@ -928,6 +928,7 @@ def resolve_provider(
_PROVIDER_ALIASES = {
"glm": "zai", "z-ai": "zai", "z.ai": "zai", "zhipu": "zai",
"google": "gemini", "google-gemini": "gemini", "google-ai-studio": "gemini",
"x-ai": "xai", "x.ai": "xai", "grok": "xai",
"kimi": "kimi-coding", "kimi-for-coding": "kimi-coding", "moonshot": "kimi-coding",
"kimi-cn": "kimi-coding-cn", "moonshot-cn": "kimi-coding-cn",
"arcee-ai": "arcee", "arceeai": "arcee",

24
hermes_cli/config.py
View File

@@ -566,7 +566,7 @@ DEFAULT_CONFIG = {
# Text-to-speech configuration
"tts": {
"provider": "edge", # "edge" (free) | "elevenlabs" (premium) | "openai" | "minimax" | "mistral" | "neutts" (local)
"provider": "edge", # "edge" (free) | "elevenlabs" (premium) | "openai" | "xai" | "minimax" | "mistral" | "neutts" (local)
"edge": {
"voice": "en-US-AriaNeural",
# Popular: AriaNeural, JennyNeural, AndrewNeural, BrianNeural, SoniaNeural
@@ -580,6 +580,12 @@ DEFAULT_CONFIG = {
"voice": "alloy",
# Voices: alloy, echo, fable, onyx, nova, shimmer
},
"xai": {
"voice_id": "eve",
"language": "en",
"sample_rate": 24000,
"bit_rate": 128000,
},
"mistral": {
"model": "voxtral-mini-tts-2603",
"voice_id": "c69964a6-ab8b-4f8a-9465-ec0925096ec8", # Paul - Neutral
@@ -836,6 +842,22 @@ OPTIONAL_ENV_VARS = {
"category": "provider",
"advanced": True,
},
"XAI_API_KEY": {
"description": "xAI API key",
"prompt": "xAI API key",
"url": "https://console.x.ai/",
"password": True,
"category": "provider",
"advanced": True,
},
"XAI_BASE_URL": {
"description": "xAI base URL override",
"prompt": "xAI base URL (leave empty for default)",
"url": None,
"password": False,
"category": "provider",
"advanced": True,
},
"GLM_API_KEY": {
"description": "Z.AI / GLM API key (also recognized as ZAI_API_KEY / Z_AI_API_KEY)",
"prompt": "Z.AI / GLM API key",

2
hermes_cli/main.py
View File

@@ -4890,7 +4890,7 @@ For more help on a command:
)
chat_parser.add_argument(
"--provider",
choices=["auto", "openrouter", "nous", "openai-codex", "copilot-acp", "copilot", "anthropic", "gemini", "ollama-cloud", "huggingface", "zai", "kimi-coding", "kimi-coding-cn", "minimax", "minimax-cn", "kilocode", "xiaomi", "arcee"],
choices=["auto", "openrouter", "nous", "openai-codex", "copilot-acp", "copilot", "anthropic", "gemini", "xai", "ollama-cloud", "huggingface", "zai", "kimi-coding", "kimi-coding-cn", "minimax", "minimax-cn", "kilocode", "xiaomi", "arcee"],
default=None,
help="Inference provider (default: auto)"
)

11
hermes_cli/models.py
View File

@@ -145,17 +145,8 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
"glm-4.5-flash",
],
"xai": [
"grok-4.20-0309-reasoning",
"grok-4.20-0309-non-reasoning",
"grok-4.20-multi-agent-0309",
"grok-4.20-reasoning",
"grok-4-1-fast-reasoning",
"grok-4-1-fast-non-reasoning",
"grok-4-fast-reasoning",
"grok-4-fast-non-reasoning",
"grok-4-0709",
"grok-code-fast-1",
"grok-3",
"grok-3-mini",
],
"kimi-coding": [
"kimi-for-coding",

1
hermes_cli/nous_subscription.py
View File

@@ -143,6 +143,7 @@ def _tts_label(current_provider: str) -> str:
"openai": "OpenAI TTS",
"elevenlabs": "ElevenLabs",
"edge": "Edge TTS",
"xai": "xAI TTS",
"mistral": "Mistral Voxtral TTS",
"neutts": "NeuTTS",
}

3
hermes_cli/providers.py
View File

@@ -128,7 +128,7 @@ HERMES_OVERLAYS: Dict[str, HermesOverlay] = {
base_url_env_var="HF_BASE_URL",
),
"xai": HermesOverlay(
transport="openai_chat",
transport="codex_responses",
base_url_override="https://api.x.ai/v1",
base_url_env_var="XAI_BASE_URL",
),
@@ -184,6 +184,7 @@ ALIASES: Dict[str, str] = {
# xai
"x-ai": "xai",
"x.ai": "xai",
"grok": "xai",
# kimi-for-coding (models.dev ID)
"kimi": "kimi-for-coding",

8
hermes_cli/runtime_provider.py
View File

@@ -41,6 +41,8 @@ def _detect_api_mode_for_url(base_url: str) -> Optional[str]:
tool calls with reasoning (chat/completions returns 400).
"""
normalized = (base_url or "").strip().lower().rstrip("/")
if "api.x.ai" in normalized:
return "codex_responses"
if "api.openai.com" in normalized and "openrouter" not in normalized:
return "codex_responses"
return None
@@ -163,6 +165,8 @@ def _resolve_runtime_from_pool_entry(
base_url = cfg_base_url or base_url or "https://api.anthropic.com"
elif provider == "openrouter":
base_url = base_url or OPENROUTER_BASE_URL
elif provider == "xai":
api_mode = "codex_responses"
elif provider == "nous":
api_mode = "chat_completions"
elif provider == "copilot":
@@ -628,6 +632,8 @@ def _resolve_explicit_runtime(
api_mode = "chat_completions"
if provider == "copilot":
api_mode = _copilot_runtime_api_mode(model_cfg, api_key)
elif provider == "xai":
api_mode = "codex_responses"
else:
configured_mode = _parse_api_mode(model_cfg.get("api_mode"))
if configured_mode:
@@ -924,6 +930,8 @@ def resolve_runtime_provider(
api_mode = "chat_completions"
if provider == "copilot":
api_mode = _copilot_runtime_api_mode(model_cfg, creds.get("api_key", ""))
elif provider == "xai":
api_mode = "codex_responses"
else:
configured_provider = str(model_cfg.get("provider") or "").strip().lower()
# Only honor persisted api_mode when it belongs to the same provider family.

21
hermes_cli/setup.py
View File

@@ -920,6 +920,7 @@ def _setup_tts_provider(config: dict):
"edge": "Edge TTS",
"elevenlabs": "ElevenLabs",
"openai": "OpenAI TTS",
"xai": "xAI TTS",
"minimax": "MiniMax TTS",
"mistral": "Mistral Voxtral TTS",
"neutts": "NeuTTS",
@@ -941,12 +942,13 @@ def _setup_tts_provider(config: dict):
"Edge TTS (free, cloud-based, no setup needed)",
"ElevenLabs (premium quality, needs API key)",
"OpenAI TTS (good quality, needs API key)",
"xAI TTS (Grok voices, needs API key)",
"MiniMax TTS (high quality with voice cloning, needs API key)",
"Mistral Voxtral TTS (multilingual, native Opus, needs API key)",
"NeuTTS (local on-device, free, ~300MB model download)",
]
)
providers.extend(["edge", "elevenlabs", "openai", "minimax", "mistral", "neutts"])
providers.extend(["edge", "elevenlabs", "openai", "xai", "minimax", "mistral", "neutts"])
choices.append(f"Keep current ({current_label})")
keep_current_idx = len(choices) - 1
idx = prompt_choice("Select TTS provider:", choices, keep_current_idx)
@@ -1012,6 +1014,23 @@ def _setup_tts_provider(config: dict):
print_warning("No API key provided. Falling back to Edge TTS.")
selected = "edge"
elif selected == "xai":
existing = get_env_value("XAI_API_KEY")
if not existing:
print()
api_key = prompt("xAI API key for TTS", password=True)
if api_key:
save_env_value("XAI_API_KEY", api_key)
print_success("xAI TTS API key saved")
else:
from hermes_constants import display_hermes_home as _dhh
print_warning(
"No xAI API key provided for TTS. Configure XAI_API_KEY via "
f"hermes setup model or {_dhh()}/.env to use xAI TTS. "
"Falling back to Edge TTS."
)
selected = "edge"
elif selected == "minimax":
existing = get_env_value("MINIMAX_API_KEY")
if not existing:

8
hermes_cli/tools_config.py
View File

@@ -146,6 +146,14 @@ TOOL_CATEGORIES = {
],
"tts_provider": "openai",
},
{
"name": "xAI TTS",
"tag": "Grok voices - requires xAI API key",
"env_vars": [
{"key": "XAI_API_KEY", "prompt": "xAI API key", "url": "https://console.x.ai/"},
],
"tts_provider": "xai",
},
{
"name": "ElevenLabs",
"badge": "paid",