Use Claude Code, Codex, VSCode, Pi, and OpenCode (and 6 other harnesses) for free (1.3B+ free tokens) from your terminal, app, IDE, or phone, and now from the browser with native browser sessions (multi-harness + multi-model) like OpenClaw (voice supported + ToS friendly)
Python
feat(opencode): integrate OpenCode Zen provider and API key support (#426)
Rizki Kotet32e2e4d7557c
diff --git a/.env.example b/.env.exampleindex 7f710722..88dca390 100644--- a/.env.example+++ b/.env.example@@ -18,6 +18,10 @@ KIMI_API_KEY=""WAFER_API_KEY=""+# OpenCode Zen Config (OpenAI-compatible Chat Completions at opencode.ai/zen/v1)+OPENCODE_API_KEY=""++# LM Studio Config (local provider, no API key required)LM_STUDIO_BASE_URL="http://localhost:1234/v1"@@ -32,7 +36,7 @@ OLLAMA_BASE_URL="http://localhost:11434"# All Claude model requests are mapped to these models, plain model is fallback# Format: provider_type/model/name-# Valid providers: "nvidia_nim" | "open_router" | "deepseek" | "lmstudio" | "llamacpp" | "ollama" | "kimi" | "wafer"+# Valid providers: "nvidia_nim" | "open_router" | "deepseek" | "lmstudio" | "llamacpp" | "ollama" | "kimi" | "wafer" | "opencode"MODEL_OPUS=MODEL_SONNET=MODEL_HAIKU=@@ -49,6 +53,7 @@ FCC_SMOKE_MODEL_LLAMACPP=FCC_SMOKE_MODEL_OLLAMA=FCC_SMOKE_MODEL_KIMI=FCC_SMOKE_MODEL_WAFER=+FCC_SMOKE_MODEL_OPENCODE=FCC_SMOKE_NIM_MODELS=FCC_SMOKE_NIM_EXTRA_MODELS=FCC_SMOKE_OPENROUTER_FREE_MODELS=@@ -72,6 +77,7 @@ LMSTUDIO_PROXY=""LLAMACPP_PROXY=""KIMI_PROXY=""WAFER_PROXY=""+OPENCODE_PROXY=""PROVIDER_RATE_LIMIT=1PROVIDER_RATE_WINDOW=3diff --git a/README.md b/README.mdindex ee0cc022..a5826285 100644--- a/README.md+++ b/README.md@@ -37,7 +37,7 @@ Free Claude Code routes Anthropic Messages API traffic from Claude Code to NVIDI## What You Get- Drop-in proxy for Claude Code's Anthropic API calls.-- Eight provider backends: NVIDIA NIM, Kimi, Wafer, OpenRouter, DeepSeek, LM Studio, llama.cpp, and Ollama.+- Nine provider backends: NVIDIA NIM, Kimi, Wafer, OpenRouter, DeepSeek, LM Studio, llama.cpp, Ollama, and OpenCode Zen.- Per-model routing: send Opus, Sonnet, Haiku, and fallback traffic to different providers.- Native Claude Code `/model` picker support through the proxy's `/v1/models` endpoint (Claude Code must opt in to Gateway model discovery; see [Model Picker](#model-picker)).- Streaming, tool use, reasoning/thinking block handling, and local request optimizations.@@ -208,11 +208,30 @@ In the Admin UI, keep or update `OLLAMA_BASE_URL`, then set `MODEL` to the same`OLLAMA_BASE_URL` is the Ollama server root; do not append `/v1`. Example model slugs include `ollama/llama3.1` and `ollama/llama3.1:8b`.-### 9. Mix Providers By Model Tier+### 9. [OpenCode Zen](https://opencode.ai/)++Get an API key at [opencode.ai/auth](https://opencode.ai/auth).++In the Admin UI, paste it into `OPENCODE_API_KEY`, then set `MODEL` to an OpenCode Zen model slug such as `opencode/gpt-5.3-codex`.++OpenCode Zen is a curated model gateway that provides access to models from Anthropic, OpenAI, Google, DeepSeek, and more through a single API key and OpenAI-compatible endpoint at `https://opencode.ai/zen/v1`.++Popular examples:++- `opencode/gpt-5.3-codex`+- `opencode/claude-sonnet-4`+- `opencode/deepseek-v4-flash-free` (free)+- `opencode/gemini-3-flash`+- `opencode/big-pickle` (free)+- `opencode/glm-5.1`++Browse available models at [opencode.ai](https://opencode.ai).++### 10. Mix Providers By Model TierEach model tier can use a different provider by setting `MODEL_OPUS`, `MODEL_SONNET`, and `MODEL_HAIKU` in the Admin UI. Leave a tier blank to inherit `MODEL`.-For example, you can route Opus to `nvidia_nim/moonshotai/kimi-k2.5`, Sonnet to `open_router/deepseek/deepseek-r1-0528:free`, Haiku to `lmstudio/unsloth/GLM-4.7-Flash-GGUF`, and keep the fallback `MODEL` on `wafer/DeepSeek-V4-Pro`.+For example, you can route Opus to `nvidia_nim/moonshotai/kimi-k2.5`, Sonnet to `open_router/deepseek/deepseek-r1-0528:free`, Haiku to `lmstudio/unsloth/GLM-4.7-Flash-GGUF`, and keep the fallback `MODEL` on `opencode/gpt-5.3-codex`.## Connect Claude Code@@ -364,6 +383,7 @@ NVIDIA_NIM_API_KEY=""OPENROUTER_API_KEY=""DEEPSEEK_API_KEY=""WAFER_API_KEY=""+OPENCODE_API_KEY=""LM_STUDIO_BASE_URL="http://localhost:1234/v1"LLAMACPP_BASE_URL="http://localhost:8080/v1"OLLAMA_BASE_URL="http://localhost:11434"@@ -377,6 +397,7 @@ OPENROUTER_PROXY=""LMSTUDIO_PROXY=""LLAMACPP_PROXY=""WAFER_PROXY=""+OPENCODE_PROXY=""```### 4. Rate Limits And Timeouts@@ -430,7 +451,7 @@ Important pieces:- FastAPI exposes Anthropic-compatible routes such as `/v1/messages`, `/v1/messages/count_tokens`, and `/v1/models`.- Model routing resolves the Claude model name to `MODEL_OPUS`, `MODEL_SONNET`, `MODEL_HAIKU`, or `MODEL`.-- NIM uses OpenAI chat streaming translated into Anthropic SSE.+- NIM, OpenCode Zen use OpenAI chat streaming translated into Anthropic SSE.- Wafer, OpenRouter, DeepSeek, LM Studio, llama.cpp, and Ollama use Anthropic Messages style transports.- The proxy normalizes thinking blocks, tool calls, token usage metadata, and provider errors into the shape Claude Code expects.- Request optimizations answer trivial Claude Code probes locally to save latency and quota.diff --git a/api/admin_config.py b/api/admin_config.pyindex 9a37e7fe..c13d22d8 100644--- a/api/admin_config.py+++ b/api/admin_config.py@@ -158,6 +158,15 @@ FIELDS: tuple[ConfigFieldSpec, ...] = (settings_attr="wafer_api_key",secret=True,),+ ConfigFieldSpec(+ "OPENCODE_API_KEY",+ "OpenCode Zen API Key",+ "providers",+ "secret",+ settings_attr="opencode_api_key",+ secret=True,+ description="OpenCode Zen curated model gateway at opencode.ai.",+ ),ConfigFieldSpec("LM_STUDIO_BASE_URL","LM Studio Base URL",@@ -233,6 +242,15 @@ FIELDS: tuple[ConfigFieldSpec, ...] = (secret=True,advanced=True,),+ ConfigFieldSpec(+ "OPENCODE_PROXY",+ "OpenCode Zen Proxy",+ "providers",+ "secret",+ settings_attr="opencode_proxy",+ secret=True,+ advanced=True,+ ),ConfigFieldSpec("MODEL","Default Model",@@ -693,6 +711,12 @@ FIELDS: tuple[ConfigFieldSpec, ...] = ("smoke",advanced=True,),+ ConfigFieldSpec(+ "FCC_SMOKE_MODEL_OPENCODE",+ "Smoke OpenCode Zen Model",+ "smoke",+ advanced=True,+ ),ConfigFieldSpec("FCC_SMOKE_NIM_MODELS","Smoke NIM Models",diff --git a/api/admin_static/admin.js b/api/admin_static/admin.jsindex 0f3d69a1..6603db40 100644--- a/api/admin_static/admin.js+++ b/api/admin_static/admin.js@@ -32,6 +32,7 @@ function providerName(providerId) {ollama: "Ollama",kimi: "Kimi",wafer: "Wafer",+ opencode: "OpenCode Zen",};if (names[providerId]) return names[providerId];return providerIddiff --git a/api/services.py b/api/services.pyindex 9611e516..711bc277 100644--- a/api/services.py+++ b/api/services.py@@ -34,7 +34,7 @@ TokenCounter = Callable[[list[Any], str | list[Any] | None, list[Any] | None], iProviderGetter = Callable[[str], BaseProvider]# Providers that use ``/chat/completions`` + Anthropic-to-OpenAI conversion (not native Messages).-_OPENAI_CHAT_UPSTREAM_IDS = frozenset({"nvidia_nim"})+_OPENAI_CHAT_UPSTREAM_IDS = frozenset({"nvidia_nim", "opencode"})def anthropic_sse_streaming_response(diff --git a/config/provider_catalog.py b/config/provider_catalog.pyindex 62eff7ee..f10194d9 100644--- a/config/provider_catalog.py+++ b/config/provider_catalog.py@@ -23,6 +23,7 @@ OPENROUTER_DEFAULT_BASE = "https://openrouter.ai/api/v1"LMSTUDIO_DEFAULT_BASE = "http://localhost:1234/v1"LLAMACPP_DEFAULT_BASE = "http://localhost:8080/v1"OLLAMA_DEFAULT_BASE = "http://localhost:11434"+OPENCODE_DEFAULT_BASE = "https://opencode.ai/zen/v1"@dataclass(frozen=True, slots=True)@@ -124,6 +125,16 @@ PROVIDER_CATALOG: dict[str, ProviderDescriptor] = {proxy_attr="wafer_proxy",capabilities=("chat", "streaming", "tools", "thinking", "native_anthropic"),),+ "opencode": ProviderDescriptor(+ provider_id="opencode",+ transport_type="openai_chat",+ credential_env="OPENCODE_API_KEY",+ credential_url="https://opencode.ai/auth",+ credential_attr="opencode_api_key",+ default_base_url=OPENCODE_DEFAULT_BASE,+ proxy_attr="opencode_proxy",+ capabilities=("chat", "streaming", "tools", "thinking", "rate_limit"),+ ),}# Order matches docs / historical error text; must match PROVIDER_CATALOG keys.diff --git a/config/settings.py b/config/settings.pyindex d08804f0..f2016008 100644--- a/config/settings.py+++ b/config/settings.py@@ -118,6 +118,9 @@ class Settings(BaseSettings):# ==================== Wafer Config ====================wafer_api_key: str = Field(default="", validation_alias="WAFER_API_KEY")+ # ==================== OpenCode Zen Config ====================+ opencode_api_key: str = Field(default="", validation_alias="OPENCODE_API_KEY")+# ==================== Messaging Platform Selection ====================# Valid: "telegram" | "discord" | "none"messaging_platform: str = Field(@@ -169,6 +172,7 @@ class Settings(BaseSettings):llamacpp_proxy: str = Field(default="", validation_alias="LLAMACPP_PROXY")kimi_proxy: str = Field(default="", validation_alias="KIMI_PROXY")wafer_proxy: str = Field(default="", validation_alias="WAFER_PROXY")+ opencode_proxy: str = Field(default="", validation_alias="OPENCODE_PROXY")# ==================== Provider Rate Limiting ====================provider_rate_limit: int = Field(default=40, validation_alias="PROVIDER_RATE_LIMIT")diff --git a/providers/defaults.py b/providers/defaults.pyindex 2d4d6507..d411f1e2 100644--- a/providers/defaults.py+++ b/providers/defaults.py@@ -8,6 +8,7 @@ from config.provider_catalog import (LMSTUDIO_DEFAULT_BASE,NVIDIA_NIM_DEFAULT_BASE,OLLAMA_DEFAULT_BASE,+ OPENCODE_DEFAULT_BASE,OPENROUTER_DEFAULT_BASE,WAFER_DEFAULT_BASE,)@@ -20,6 +21,7 @@ __all__ = ("LMSTUDIO_DEFAULT_BASE","NVIDIA_NIM_DEFAULT_BASE","OLLAMA_DEFAULT_BASE",+ "OPENCODE_DEFAULT_BASE","OPENROUTER_DEFAULT_BASE","WAFER_DEFAULT_BASE",)diff --git a/providers/opencode/__init__.py b/providers/opencode/__init__.pynew file mode 100644index 00000000..19e3c479--- /dev/null+++ b/providers/opencode/__init__.py@@ -0,0 +1,10 @@+"""OpenCode Zen provider exports."""++from providers.defaults import OPENCODE_DEFAULT_BASE++from .client import OpenCodeProvider++__all__ = [+ "OPENCODE_DEFAULT_BASE",+ "OpenCodeProvider",+]diff --git a/providers/opencode/client.py b/providers/opencode/client.pynew file mode 100644index 00000000..bf15a0b3--- /dev/null+++ b/providers/opencode/client.py@@ -0,0 +1,31 @@+"""OpenCode Zen provider implementation (OpenAI-compatible Chat Completions)."""++from __future__ import annotations++from typing import Any++from providers.base import ProviderConfig+from providers.defaults import OPENCODE_DEFAULT_BASE+from providers.openai_compat import OpenAIChatTransport++from .request import build_request_body+++class OpenCodeProvider(OpenAIChatTransport):+ """OpenCode Zen provider using ``https://opencode.ai/zen/v1/chat/completions``."""++ def __init__(self, config: ProviderConfig):+ super().__init__(+ config,+ provider_name="OPENCODE",+ base_url=config.base_url or OPENCODE_DEFAULT_BASE,+ api_key=config.api_key,+ )++ def _build_request_body(+ self, request: Any, thinking_enabled: bool | None = None+ ) -> dict:+ return build_request_body(+ request,+ thinking_enabled=self._is_thinking_enabled(request, thinking_enabled),+ )diff --git a/providers/opencode/request.py b/providers/opencode/request.pynew file mode 100644index 00000000..243b945c--- /dev/null+++ b/providers/opencode/request.py@@ -0,0 +1,35 @@+"""Request builder for OpenCode Zen provider."""++from typing import Any++from loguru import logger++from core.anthropic import ReasoningReplayMode, build_base_request_body+from core.anthropic.conversion import OpenAIConversionError+from providers.exceptions import InvalidRequestError+++def build_request_body(request_data: Any, *, thinking_enabled: bool) -> dict:+ """Build OpenAI-format request body from Anthropic request for OpenCode Zen."""+ logger.debug(+ "OPENCODE_REQUEST: conversion start model={} msgs={}",+ getattr(request_data, "model", "?"),+ len(getattr(request_data, "messages", [])),+ )+ try:+ body = build_base_request_body(+ request_data,+ reasoning_replay=ReasoningReplayMode.REASONING_CONTENT+ if thinking_enabled+ else ReasoningReplayMode.DISABLED,+ )+ except OpenAIConversionError as exc:+ raise InvalidRequestError(str(exc)) from exc++ logger.debug(+ "OPENCODE_REQUEST: conversion done model={} msgs={} tools={}",+ body.get("model"),+ len(body.get("messages", [])),+ len(body.get("tools", [])),+ )+ return bodydiff --git a/providers/registry.py b/providers/registry.pyindex 7375048c..dab8260a 100644--- a/providers/registry.py+++ b/providers/registry.py@@ -80,6 +80,12 @@ def _create_wafer(config: ProviderConfig, _settings: Settings) -> BaseProvider:return WaferProvider(config)+def _create_opencode(config: ProviderConfig, _settings: Settings) -> BaseProvider:+ from providers.opencode import OpenCodeProvider++ return OpenCodeProvider(config)++PROVIDER_FACTORIES: dict[str, ProviderFactory] = {"nvidia_nim": _create_nvidia_nim,"open_router": _create_open_router,@@ -89,6 +95,7 @@ PROVIDER_FACTORIES: dict[str, ProviderFactory] = {"ollama": _create_ollama,"kimi": _create_kimi,"wafer": _create_wafer,+ "opencode": _create_opencode,}if set(PROVIDER_DESCRIPTORS) != set(SUPPORTED_PROVIDER_IDS) or set(diff --git a/smoke/lib/config.py b/smoke/lib/config.pyindex f23f28c0..b12d5e87 100644--- a/smoke/lib/config.py+++ b/smoke/lib/config.py@@ -49,6 +49,7 @@ PROVIDER_SMOKE_DEFAULT_MODELS: dict[str, str] = {"llamacpp": "llamacpp/local-model","ollama": "ollama/llama3.1","wafer": "wafer/DeepSeek-V4-Pro",+ "opencode": "opencode/gpt-5.3-codex",}NVIDIA_NIM_CLI_DEFAULT_MODELS: tuple[str, ...] = (@@ -231,6 +232,8 @@ class SmokeConfig:return bool(self.settings.ollama_base_url.strip())if provider == "wafer":return bool(self.settings.wafer_api_key.strip())+ if provider == "opencode":+ return bool(self.settings.opencode_api_key.strip())return Falsediff --git a/tests/api/test_dependencies.py b/tests/api/test_dependencies.pyindex b2e068d2..1a64d4be 100644--- a/tests/api/test_dependencies.py+++ b/tests/api/test_dependencies.py@@ -37,12 +37,14 @@ def _make_mock_settings(**overrides):mock.open_router_api_key = "test_openrouter_key"mock.deepseek_api_key = "test_deepseek_key"mock.wafer_api_key = "test_wafer_key"+ mock.opencode_api_key = "test_opencode_key"mock.lm_studio_base_url = "http://localhost:1234/v1"mock.ollama_base_url = "http://localhost:11434"mock.lmstudio_proxy = ""mock.llamacpp_proxy = ""mock.kimi_proxy = ""mock.wafer_proxy = ""+ mock.opencode_proxy = ""mock.nim = NimSettings()mock.http_read_timeout = 300.0mock.http_write_timeout = 10.0diff --git a/tests/contracts/test_feature_manifest.py b/tests/contracts/test_feature_manifest.pyindex a514de53..51cf944b 100644--- a/tests/contracts/test_feature_manifest.py+++ b/tests/contracts/test_feature_manifest.py@@ -11,6 +11,7 @@ from providers.lmstudio import LMStudioProviderfrom providers.nvidia_nim import NvidiaNimProviderfrom providers.ollama import OllamaProviderfrom providers.open_router import OpenRouterProvider+from providers.opencode import OpenCodeProviderfrom providers.wafer import WaferProviderfrom smoke.features import FEATURE_INVENTORY, README_FEATURES, feature_ids@@ -75,6 +76,7 @@ def test_provider_and_platform_registries_include_advertised_builtins() -> None:"llamacpp": LlamaCppProvider,"ollama": OllamaProvider,"wafer": WaferProvider,+ "opencode": OpenCodeProvider,}for provider_class in provider_classes.values():assert issubclass(provider_class, BaseProvider)diff --git a/tests/contracts/test_smoke_config.py b/tests/contracts/test_smoke_config.pyindex 3b368aa3..d82ee56a 100644--- a/tests/contracts/test_smoke_config.py+++ b/tests/contracts/test_smoke_config.py@@ -27,6 +27,7 @@ def _settings(**overrides):"open_router_api_key": "","deepseek_api_key": "","wafer_api_key": "",+ "opencode_api_key": "","lm_studio_base_url": "","llamacpp_base_url": "","ollama_base_url": "http://localhost:11434",diff --git a/tests/providers/test_model_validation.py b/tests/providers/test_model_validation.pyindex d54b9816..ae64100b 100644--- a/tests/providers/test_model_validation.py+++ b/tests/providers/test_model_validation.py@@ -33,6 +33,7 @@ def _settings(open_router_api_key: str = "",deepseek_api_key: str = "",wafer_api_key: str = "",+ opencode_api_key: str = "",) -> Settings:return Settings.model_construct(model=model,@@ -43,6 +44,7 @@ def _settings(open_router_api_key=open_router_api_key,deepseek_api_key=deepseek_api_key,wafer_api_key=wafer_api_key,+ opencode_api_key=opencode_api_key,log_api_error_tracebacks=False,)diff --git a/tests/providers/test_registry.py b/tests/providers/test_registry.pyindex 0b02d59b..e4da84bd 100644--- a/tests/providers/test_registry.py+++ b/tests/providers/test_registry.py@@ -13,6 +13,7 @@ from providers.lmstudio import LMStudioProviderfrom providers.nvidia_nim import NvidiaNimProviderfrom providers.ollama import OllamaProviderfrom providers.open_router import OpenRouterProvider+from providers.opencode import OpenCodeProviderfrom providers.registry import (PROVIDER_DESCRIPTORS,ProviderRegistry,@@ -29,6 +30,7 @@ def _make_settings(**overrides):mock.open_router_api_key = "test_openrouter_key"mock.deepseek_api_key = "test_deepseek_key"mock.wafer_api_key = "test_wafer_key"+ mock.opencode_api_key = "test_opencode_key"mock.lm_studio_base_url = "http://localhost:1234/v1"mock.llamacpp_base_url = "http://localhost:8080/v1"mock.ollama_base_url = "http://localhost:11434"@@ -38,6 +40,7 @@ def _make_settings(**overrides):mock.llamacpp_proxy = ""mock.kimi_proxy = ""mock.wafer_proxy = ""+ mock.opencode_proxy = ""mock.provider_rate_limit = 40mock.provider_rate_window = 60mock.provider_max_concurrency = 5@@ -99,6 +102,7 @@ def test_create_provider_instantiates_each_builtin():"llamacpp": LlamaCppProvider,"ollama": OllamaProvider,"wafer": WaferProvider,+ "opencode": OpenCodeProvider,}with (