From 641991043faa9c9b84db739cd087151131b7876e Mon Sep 17 00:00:00 2001 From: Codex Date: Sun, 25 Oct 2026 00:42:57 -0700 Subject: [PATCH] =?UTF-8?q?=E5=90=8C=E6=AD=A5=E9=A6=99=E6=B8=AF=20LiteLLM?= =?UTF-8?q?=20=E9=95=9C=E5=83=8F=E4=B8=8E=E5=A4=9A=E6=8F=90=E4=BE=9B?= =?UTF-8?q?=E5=95=86=E8=B7=AF=E7=94=B1?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- servers/bwh-hk-cmi/litellm/README.md | 11 ++- servers/bwh-hk-cmi/litellm/compose.yaml | 15 ++- servers/bwh-hk-cmi/litellm/models.yaml | 43 +++++++++ servers/bwh-hk-cmi/litellm/provider_routes.py | 96 +++++++++++++++++++ servers/bwh-hk-cmi/litellm/render_config.py | 41 ++++++++ servers/bwh-hk-cmi/litellm/test_config.py | 36 +++++++ 6 files changed, 237 insertions(+), 5 deletions(-) create mode 100644 servers/bwh-hk-cmi/litellm/models.yaml create mode 100644 servers/bwh-hk-cmi/litellm/provider_routes.py create mode 100644 servers/bwh-hk-cmi/litellm/render_config.py create mode 100644 servers/bwh-hk-cmi/litellm/test_config.py diff --git a/servers/bwh-hk-cmi/litellm/README.md b/servers/bwh-hk-cmi/litellm/README.md index 62ecd17..dcd8d1a 100644 --- a/servers/bwh-hk-cmi/litellm/README.md +++ b/servers/bwh-hk-cmi/litellm/README.md @@ -1,4 +1,4 @@ -# Hong Kong CMI LiteLLM Vertex AI Relay +# 香港 CMI LiteLLM 多提供商代理 - 公网 OpenAI-compatible 入口为 `https://api.opfo.xyz/v1`，由 Caddy 终止 TLS 后通过外部 Docker 网络 `hk-web` 反向代理到 `litellm-api:1049`。 - LiteLLM 不使用 host network，也不向宿主机发布端口；容器内监听 `0.0.0.0:1049` 仅供 `hk-web` 上的 Caddy 访问。 @@ -8,4 +8,11 @@ - 对外模型别名包括 `gemini-3.6-flash`、`gemini-3.5-flash-lite`、 `google/gemini-embedding-2` 和 `google/gemini-3.8-flash`；后两者仍通过 Vertex AI ADC 路由。 -- 后续 Vertex Anthropic 模型在 `config.yaml` 增加独立模型项。 +- 2026-10-25 同步 tools-pve 已验证的 LiteLLM 1.104.2 固定镜像，以及 `models.yaml` 中的提供商映射。`latest` 是维护的别名，不是自动发现所有厂商的新模型。 +- `provider_routes.py` 是同日 tools-pve 的路由生成器快照；更新提供商逻辑时应同步比对两端。HK 的 `render_config.py` 删除数据库管理、OAuth 和个人词库路线，保留现有主密钥认证。 +- Arcane Project 本地变量增加 `ZENMUX_SUBSCRIPTION_API_KEY`、`ZENMUX_PAYG_API_KEY`、`OPENROUTER_API_KEY`、`GOOGLE_AI_STUDIO_API_KEY`。只有相应凭据存在时才生成该组路由；真实值不进入 Git。 +- Claude 使用 ZenMux 原生 Anthropic Messages 路径，订阅与 `-payg` 显式分开；开源模型使用 ZenMux 订阅优先、同模型 OpenRouter 后备。不自动回退至 ZenMux PAYG。 +- Google AI Studio 的 `gemini-transcribe` 是普通转写路线，不含个人热词；个人词库、OAuth 会话和会议处理程序没有复制至 HK。 +- Vertex 继续使用 HK 原有 ADC。旧 `gemini-3.6-flash` 别名保留，但指向当前映射的 `gemini-3.8-flash`；其余旧别名保留。 +- 当前实际配置由启动脚本生成至 `/tmp/litellm.yaml`；旧 `config.yaml` 仅作为历史参考，不再挂载。 +- 升级只重建 LiteLLM，不变更 Caddy、HAProxy、其他项目及 ADC 卷。失败时回退本次 Git 提交并同步，再按需要 Redeploy，禁止删除卷。 diff --git a/servers/bwh-hk-cmi/litellm/compose.yaml b/servers/bwh-hk-cmi/litellm/compose.yaml index 2837f75..3e7364a 100644 --- a/servers/bwh-hk-cmi/litellm/compose.yaml +++ b/servers/bwh-hk-cmi/litellm/compose.yaml @@ -14,7 +14,7 @@ services: printf '%s' "$${GOOGLE_ADC_B64}" | base64 -d > /credentials/application_default_credentials.json litellm: - image: ghcr.io/berriai/litellm:main-stable@sha256:625981c83410a3ea68eb0697590a57ec1d764d634514d54fa5db0591077ee839 + image: ghcr.io/berriai/litellm:main-stable@sha256:3d88bd757134a00e8c00237b85a021ab1f6d54abb9c1df750f411dbe7256a500 restart: unless-stopped depends_on: adc-init: @@ -28,10 +28,19 @@ services: VERTEXAI_PROJECT: ${VERTEXAI_PROJECT} VERTEXAI_LOCATION: ${VERTEXAI_LOCATION:-global} LITELLM_MASTER_KEY: ${LITELLM_MASTER_KEY} + VERTEXAI_ENABLED: "true" + ZENMUX_SUBSCRIPTION_API_KEY: ${ZENMUX_SUBSCRIPTION_API_KEY:-} + ZENMUX_PAYG_API_KEY: ${ZENMUX_PAYG_API_KEY:-} + OPENROUTER_API_KEY: ${OPENROUTER_API_KEY:-} + GOOGLE_AI_STUDIO_API_KEY: ${GOOGLE_AI_STUDIO_API_KEY:-} volumes: - - ./config.yaml:/app/config.yaml:ro + - ./models.yaml:/etc/litellm/models.yaml:ro + - ./provider_routes.py:/etc/litellm/provider_routes.py:ro + - ./render_config.py:/etc/litellm/render_config.py:ro - google-adc:/credentials:ro - command: ["--config", "/app/config.yaml", "--host", "0.0.0.0", "--port", "${LITELLM_PORT:-1049}"] + entrypoint: ["/bin/sh", "-c"] + command: + - python /etc/litellm/render_config.py && exec litellm --config /tmp/litellm.yaml --host 0.0.0.0 --port ${LITELLM_PORT:-1049} --num_workers 1 logging: driver: json-file options: diff --git a/servers/bwh-hk-cmi/litellm/models.yaml b/servers/bwh-hk-cmi/litellm/models.yaml new file mode 100644 index 0000000..f25007b --- /dev/null +++ b/servers/bwh-hk-cmi/litellm/models.yaml @@ -0,0 +1,43 @@ +# 除 Google 自带 latest 别名外，本项目映射不会自行追踪上游发布。 +zenmux: + claude-sonnet-latest: anthropic/claude-sonnet-5.5 + claude-opus-latest: anthropic/claude-opus-5.5 + claude-haiku-latest: anthropic/claude-haiku-5.5 +openrouter: + deepseek-flash-latest: deepseek/deepseek-v4.1-flash + deepseek-pro-latest: deepseek/deepseek-v4-pro + glm-latest: z-ai/glm-5.3-prime + glm-flash-latest: z-ai/glm-5.3-flash + kimi-latest: moonshotai/kimi-k3 + mimo-flash-latest: xiaomi/mimo-v2.6-flash +# These existing public aliases are subscription-first, not load-balanced. +zenmux_open_models: + deepseek-flash-latest: deepseek/deepseek-v4.1-flash + deepseek-pro-latest: deepseek/deepseek-v4-pro + glm-latest: z-ai/glm-5.3-prime + glm-flash-latest: z-ai/glm-5.3-flash + kimi-latest: moonshotai/kimi-k3 + mimo-flash-latest: xiaomi/mimo-v2.6-flash +zenmux_chat: + gemini-flash-zenmux: google/gemini-3.8-flash +google_ai_studio: + gemini-flash-latest: gemini-flash-latest + gemini-flash-lite-latest: gemini-flash-lite-latest + gemini-pro-latest: gemini-pro-latest + gemini-embedding-2-studio: gemini-embedding-2 +google_vertex: + gemini-flash-vertex: gemini-3.8-flash + gemini-flash-lite-vertex: gemini-3.5-flash-lite + gemini-pro-vertex: gemini-3.1-pro-preview + google-rerank-default: semantic-ranker-default@latest + google-rerank-fast: semantic-ranker-fast@latest +# 已有 Hindsight 部署用过的候选模型；本代理仍需独立授权与请求验收。 +# renderer 在实际 token 出现前排除这些路线。 +chatgpt: + gpt-luna-latest: gpt-6-luna + gpt-sol-latest: gpt-6.1-sol + gpt-work-sol: gpt-6-sol + gpt-review-5.5: gpt-5.5 + gpt-astra-latest: gpt-6-astra +xai: + grok-latest: grok-4.7 diff --git a/servers/bwh-hk-cmi/litellm/provider_routes.py b/servers/bwh-hk-cmi/litellm/provider_routes.py new file mode 100644 index 0000000..f20dc69 --- /dev/null +++ b/servers/bwh-hk-cmi/litellm/provider_routes.py @@ -0,0 +1,96 @@ +"""Render only credential-ready routes; credentials remain environment references.""" +import os +import json +from pathlib import Path + +import yaml + + +def oauth_ready(path): + try: + record = json.loads(path.read_text()) + return isinstance(record, dict) and bool(record.get('access_token')) + except (OSError, ValueError): + return False + + +def build_config(catalog, env, exists): + routes = [] + fallbacks = [] + + def add(alias, model, key=None, **params): + if key: + params['api_key'] = 'os.environ/' + key + routes.append({'model_name': alias, 'litellm_params': {'model': model, **params}}) + + for key, suffix in [('ZENMUX_SUBSCRIPTION_API_KEY', ''), ('ZENMUX_PAYG_API_KEY', '-payg')]: + if env.get(key): + for alias, model in catalog['zenmux'].items(): + # Strip only the LiteLLM provider prefix, retaining ZenMux's vendor prefix. + add(alias + suffix, 'anthropic/' + model, key, + api_base='https://zenmux.ai/api/anthropic') + if env.get('ZENMUX_SUBSCRIPTION_API_KEY'): + for alias, model in catalog.get('zenmux_chat', {}).items(): + add(alias, 'openai/' + model, 'ZENMUX_SUBSCRIPTION_API_KEY', + api_base='https://zenmux.ai/api/v1') + if env.get('OPENROUTER_API_KEY'): + for alias, model in catalog['openrouter'].items(): + primary = catalog.get('zenmux_open_models', {}).get(alias) + if primary and env.get('ZENMUX_SUBSCRIPTION_API_KEY'): + if primary != model: + raise ValueError('Cross-provider model mismatch: ' + alias) + add(alias, 'openai/' + primary, 'ZENMUX_SUBSCRIPTION_API_KEY', + api_base='https://zenmux.ai/api/v1', max_retries=0) + routes[-1]['model_info'] = {'cooldown_time': 60, + 'allowed_fails_policy': {'RateLimitErrorAllowedFails': 0, + 'AuthenticationErrorAllowedFails': 0, + 'InternalServerErrorAllowedFails': 0, + 'ServiceUnavailableErrorAllowedFails': 0, + 'TimeoutErrorAllowedFails': 0}} + add(alias + '-openrouter', 'openrouter/' + model, 'OPENROUTER_API_KEY') + fallbacks.append({alias: [alias + '-openrouter']}) + else: + add(alias, 'openrouter/' + model, 'OPENROUTER_API_KEY') + elif env.get('ZENMUX_SUBSCRIPTION_API_KEY'): + for alias, model in catalog.get('zenmux_open_models', {}).items(): + add(alias, 'openai/' + model, 'ZENMUX_SUBSCRIPTION_API_KEY', + api_base='https://zenmux.ai/api/v1', max_retries=0) + if env.get('GOOGLE_AI_STUDIO_API_KEY'): + add('gemini-transcribe-personal', 'gemini/gemini-3.5-transcribe', + 'GOOGLE_AI_STUDIO_API_KEY', personal_vocabulary=True) + for alias, model in catalog['google_ai_studio'].items(): + add(alias, 'gemini/' + model, 'GOOGLE_AI_STUDIO_API_KEY') + if env.get('VERTEXAI_ENABLED', '').lower() == 'true' and env.get('VERTEXAI_PROJECT'): + for alias, model in catalog.get('google_vertex', {}).items(): + add(alias, 'vertex_ai/' + model, + vertex_project='os.environ/VERTEXAI_PROJECT', + vertex_location='os.environ/VERTEXAI_LOCATION') + for provider, token_var, default_dir in [ + ('chatgpt', 'CHATGPT_TOKEN_DIR', '/tokens/chatgpt'), + ('xai', 'XAI_OAUTH_TOKEN_DIR', '/tokens/xai'), + ]: + if exists(Path(env.get(token_var, default_dir)) / 'auth.json'): + for alias, model in catalog[provider].items(): + extra = {'use_xai_oauth': True} if provider == 'xai' else {} + add(alias, provider + '/' + model, **extra) + return { + 'model_list': routes, + 'general_settings': { + 'master_key': 'os.environ/LITELLM_MASTER_KEY', + 'database_url': 'os.environ/DATABASE_URL', + 'store_model_in_db': False, + 'disable_env_credential_login': True, + }, + 'litellm_settings': {'drop_params': False, 'set_verbose': False}, + # Only explicitly approved open-model routes have cross-provider fallbacks. + 'router_settings': {'num_retries': 1, 'timeout': 180, 'fallbacks': fallbacks}, + } + + +if __name__ == '__main__': + catalog = yaml.safe_load(Path('/etc/litellm/models.yaml').read_text()) + config = build_config(catalog, os.environ, oauth_ready) + output = Path('/tmp/litellm.yaml') + output.write_text(yaml.safe_dump(config, allow_unicode=True, sort_keys=False)) + output.chmod(0o600) + print('Configured routes:', ', '.join(route['model_name'] for route in config['model_list'])) diff --git a/servers/bwh-hk-cmi/litellm/render_config.py b/servers/bwh-hk-cmi/litellm/render_config.py new file mode 100644 index 0000000..387a748 --- /dev/null +++ b/servers/bwh-hk-cmi/litellm/render_config.py @@ -0,0 +1,41 @@ +"""HK reuses tools-pve provider routing without OAuth, database, or private vocabulary.""" +import os +from pathlib import Path + +import yaml + +from provider_routes import build_config + + +def build_hk_config(catalog, env): + config = build_config(catalog, env, lambda path: False) + config['general_settings'] = {'master_key': 'os.environ/LITELLM_MASTER_KEY'} + routes = config['model_list'] + routes[:] = [route for route in routes if route['model_name'] != 'gemini-transcribe-personal'] + if env.get('GOOGLE_AI_STUDIO_API_KEY'): + routes.append({'model_name': 'gemini-transcribe', 'litellm_params': { + 'model': 'gemini/gemini-3.5-transcribe', + 'api_key': 'os.environ/GOOGLE_AI_STUDIO_API_KEY'}}) + if env.get('VERTEXAI_ENABLED', '').lower() == 'true' and env.get('VERTEXAI_PROJECT'): + # Keep old client aliases; the old 3.6 alias now follows the verified Flash map. + legacy = { + 'gemini-3.6-flash': catalog['google_vertex']['gemini-flash-vertex'], + 'gemini-3.5-flash-lite': catalog['google_vertex']['gemini-flash-lite-vertex'], + 'google/gemini-embedding-2': 'gemini-embedding-2', + 'google/gemini-3.8-flash': catalog['google_vertex']['gemini-flash-vertex'], + } + for alias, model in legacy.items(): + routes.append({'model_name': alias, 'litellm_params': { + 'model': 'vertex_ai/' + model, + 'vertex_project': 'os.environ/VERTEXAI_PROJECT', + 'vertex_location': 'os.environ/VERTEXAI_LOCATION'}}) + return config + + +if __name__ == '__main__': + catalog = yaml.safe_load(Path('/etc/litellm/models.yaml').read_text()) + config = build_hk_config(catalog, os.environ) + output = Path('/tmp/litellm.yaml') + output.write_text(yaml.safe_dump(config, allow_unicode=True, sort_keys=False)) + output.chmod(0o600) + print('Configured routes:', ', '.join(route['model_name'] for route in config['model_list'])) diff --git a/servers/bwh-hk-cmi/litellm/test_config.py b/servers/bwh-hk-cmi/litellm/test_config.py new file mode 100644 index 0000000..46e9180 --- /dev/null +++ b/servers/bwh-hk-cmi/litellm/test_config.py @@ -0,0 +1,36 @@ +import unittest +from pathlib import Path + +import yaml + +from render_config import build_hk_config + + +class RoutingTests(unittest.TestCase): + def test_all_providers(self): + catalog = yaml.safe_load(Path(__file__).with_name('models.yaml').read_text()) + env = {key: 'synthetic' for key in ['ZENMUX_SUBSCRIPTION_API_KEY', + 'ZENMUX_PAYG_API_KEY', 'OPENROUTER_API_KEY', 'GOOGLE_AI_STUDIO_API_KEY', + 'VERTEXAI_PROJECT']} + env['VERTEXAI_ENABLED'] = 'true' + result = build_hk_config(catalog, env) + routes = {r['model_name']: r['litellm_params'] for r in result['model_list']} + self.assertEqual(len(routes), len(result['model_list'])) + self.assertNotIn('gemini-transcribe-personal', routes) + self.assertNotIn('grok-latest', routes) + self.assertNotIn('gpt-sol-latest', routes) + self.assertEqual(routes['gemini-transcribe']['model'], 'gemini/gemini-3.5-transcribe') + self.assertEqual(routes['gemini-3.6-flash']['model'], 'vertex_ai/gemini-3.8-flash') + self.assertEqual(len(result['router_settings']['fallbacks']), 6) + self.assertEqual(result['general_settings'], {'master_key': 'os.environ/LITELLM_MASTER_KEY'}) + self.assertNotIn('synthetic', yaml.safe_dump(result)) + + def test_missing_credentials(self): + catalog = yaml.safe_load(Path(__file__).with_name('models.yaml').read_text()) + result = build_hk_config(catalog, {}) + self.assertEqual(result['model_list'], []) + self.assertEqual(result['router_settings']['fallbacks'], []) + + +if __name__ == '__main__': + unittest.main()