From 660ad21365e2084891c8dea9033a6f6eaa73f788 Mon Sep 17 00:00:00 2001 From: yumoqing Date: Tue, 1 Sep 2026 17:27:17 +0800 Subject: [PATCH] =?UTF-8?q?feat(pipeline-llm):=20=E6=A8=A1=E5=9E=8B?= =?UTF-8?q?=E6=B2=BB=E7=90=86=E6=A8=A1=E5=9D=97v1.0.0=20=E2=80=94=20?= =?UTF-8?q?=E4=BE=9B=E5=BA=94=E5=95=86/=E7=AB=AF=E7=82=B9=E7=9B=AE?= =?UTF-8?q?=E5=BD=95/=E8=B4=A6=E5=8F=B7=E9=92=B1=E5=8C=85/=E6=A8=A1?= =?UTF-8?q?=E5=9E=8B=E6=B3=A8=E5=86=8C/=E7=BB=84=E7=BB=87=E5=AE=B9?= =?UTF-8?q?=E9=94=99=E7=AD=96=E7=95=A5/=E9=99=90=E9=A2=9D=E9=99=90?= =?UTF-8?q?=E6=B5=81/=E5=8F=8C=E7=BB=B4=E5=BA=A6=E8=AE=B0=E8=B4=A6?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - 8张llm_前缀表(手写幂等DDL): vendor/account/model/api_profile/org_policy/org_quota/user_quota/usage - gateway.py 门禁链: 限流→限额→策略选模型(主备容错)→账号×端点轮转(偏好过滤+余额加权+冷却避让)→预授权-结算 - api_key AES单层加密(非RC4,盐不对称不可解); 限流Redis分钟窗口(db4) fail-open - 双维度记账: 一次调用同行记cost(账号侧)+charge(组织池侧); 充值=recharge行 - CRUD+index.ui 8卡片导航+总览; appcodes字典5组; 设计规范+30测试用例 - 策略即开关: 机构无策略→__LEGACY__走旧llm表(向后兼容零改动) --- .gitignore | 20 + README.md | 74 ++ docs/design-spec.md | 259 +++++++ docs/test-cases.md | 66 ++ init/data.json | 39 ++ json/llm_account_list.json | 43 ++ json/llm_api_profile_list.json | 45 ++ json/llm_model_list.json | 54 ++ json/llm_org_policy_list.json | 42 ++ json/llm_org_quota_list.json | 32 + json/llm_usage_list.json | 43 ++ json/llm_user_quota_list.json | 31 + json/llm_vendor_list.json | 36 + models/llm_account.json | 113 +++ models/llm_api_profile.json | 100 +++ models/llm_model.json | 200 ++++++ models/llm_org_policy.json | 97 +++ models/llm_org_quota.json | 87 +++ models/llm_usage.json | 149 ++++ models/llm_user_quota.json | 95 +++ models/llm_vendor.json | 98 +++ mysql.ddl.sql | 133 ++++ pipeline_llm/__init__.py | 1 + pipeline_llm/gateway.py | 653 ++++++++++++++++++ pipeline_llm/init.py | 455 ++++++++++++ pyproject.toml | 17 + scripts/load_path.py | 36 + wwwroot/api/get_llm_account_options.dspy | 10 + wwwroot/api/get_llm_capability_options.dspy | 11 + .../api/get_llm_endpoint_pref_options.dspy | 11 + wwwroot/api/get_llm_model_options.dspy | 10 + wwwroot/api/get_llm_ppid_options.dspy | 10 + wwwroot/api/get_llm_protocol_options.dspy | 11 + wwwroot/api/get_llm_status_options.dspy | 11 + wwwroot/api/get_llm_vendor_options.dspy | 10 + wwwroot/api/llm_account_recharge.dspy | 11 + wwwroot/api/llm_dashboard.dspy | 5 + wwwroot/api/llm_dashboard_widget.dspy | 48 ++ wwwroot/api/llm_org_recharge.dspy | 11 + wwwroot/api/llm_usage_query.dspy | 6 + wwwroot/index.ui | 271 ++++++++ 41 files changed, 3454 insertions(+) create mode 100644 .gitignore create mode 100644 README.md create mode 100644 docs/design-spec.md create mode 100644 docs/test-cases.md create mode 100644 init/data.json create mode 100644 json/llm_account_list.json create mode 100644 json/llm_api_profile_list.json create mode 100644 json/llm_model_list.json create mode 100644 json/llm_org_policy_list.json create mode 100644 json/llm_org_quota_list.json create mode 100644 json/llm_usage_list.json create mode 100644 json/llm_user_quota_list.json create mode 100644 json/llm_vendor_list.json create mode 100644 models/llm_account.json create mode 100644 models/llm_api_profile.json create mode 100644 models/llm_model.json create mode 100644 models/llm_org_policy.json create mode 100644 models/llm_org_quota.json create mode 100644 models/llm_usage.json create mode 100644 models/llm_user_quota.json create mode 100644 models/llm_vendor.json create mode 100644 mysql.ddl.sql create mode 100644 pipeline_llm/__init__.py create mode 100644 pipeline_llm/gateway.py create mode 100644 pipeline_llm/init.py create mode 100644 pyproject.toml create mode 100644 scripts/load_path.py create mode 100644 wwwroot/api/get_llm_account_options.dspy create mode 100644 wwwroot/api/get_llm_capability_options.dspy create mode 100644 wwwroot/api/get_llm_endpoint_pref_options.dspy create mode 100644 wwwroot/api/get_llm_model_options.dspy create mode 100644 wwwroot/api/get_llm_ppid_options.dspy create mode 100644 wwwroot/api/get_llm_protocol_options.dspy create mode 100644 wwwroot/api/get_llm_status_options.dspy create mode 100644 wwwroot/api/get_llm_vendor_options.dspy create mode 100644 wwwroot/api/llm_account_recharge.dspy create mode 100644 wwwroot/api/llm_dashboard.dspy create mode 100644 wwwroot/api/llm_dashboard_widget.dspy create mode 100644 wwwroot/api/llm_org_recharge.dspy create mode 100644 wwwroot/api/llm_usage_query.dspy create mode 100644 wwwroot/index.ui diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..3c7cc48 --- /dev/null +++ b/.gitignore @@ -0,0 +1,20 @@ +# build artifacts +build/ +*.egg-info/ +__pycache__/ +*.pyc +dist/ + +# CRUD generated directories (auto-generated by xls2ui at build time, NOT in repo) +wwwroot/llm_vendor/ +wwwroot/llm_account/ +wwwroot/llm_model/ +wwwroot/llm_api_profile/ +wwwroot/llm_org_policy/ +wwwroot/llm_org_quota/ +wwwroot/llm_user_quota/ +wwwroot/llm_usage/ + +# venv +py3/ +venv/ diff --git a/README.md b/README.md new file mode 100644 index 0000000..931b12b --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +# pipeline-llm — 产线平台模型治理模块 + +产线平台的模型层：供应商/账号/模型治理 + 组织容错策略 + 限额限流 + 双维度记账。 +所有表 `llm_` 前缀，建在宿主应用库（pipeline）。 + +## 模块定位 + +解决五类问题： +1. **供给侧治理**：供应商协议+全球端点目录、账号（钱包）、模型注册、适配模板 +2. **容量治理**：供应商限流 → 多账号轮转；多供应商 → 主备模型容错 +3. **需求侧治理**：组织级模型容错策略、组织限额限流、个人限额限流 +4. **计费**：双维度记账（成本侧记账号、消费侧记组织/个人），模型挂定价 `pricing_program.ppid` +5. **端点选择**：端点目录配在供应商下（全球配置一次），账号选用端点，客户按区域偏好（prefer/must） + +## 数据表（8 张） + +| 表 | 说明 | +|---|---| +| `llm_vendor` | 供应商（协议 + 端点目录 JSON） | +| `llm_account` | 供应商账号（钱包：余额/充值/选端点，api_key AES 加密） | +| `llm_model` | 模型注册（能力分类/挂定价 ppid/成本售价，name 唯一） | +| `llm_api_profile` | 适配模板（协议×能力形态去重） | +| `llm_org_policy` | 组织容错策略（主备模型 + 端点偏好） | +| `llm_org_quota` | 组织限额限流（池余额 + QPM） | +| `llm_user_quota` | 个人限额限流（额度上限 + QPM） | +| `llm_usage` | 用量流水（双维度记账事实表） | + +## 调用门禁链 + +``` +① 个人限流 → ② 组织限流 → ③ 个人额度 → ④ 组织池(预授权) +→ ⑤ 组织策略选模型(主→备) → ⑥ 账号×端点候选池(偏好过滤+余额加权+冷却避让) +→ ⑦ 调用 → ⑧ 结算(实际用量，多退少补，双维度记账) +``` +任何一级不过：快速失败 + 明确中文原因（不挂起、不静默）。 + +## 集成方式（复用不改建） + +模块只提供治理引擎与配置管理；实际 LLM 转发仍由宿主已有的 +`pipeline_service.llm_bridge` / `llm_proxy` 承担，在两处挂钩子： +- `llm_bridge._get_model_config`：治理启用时前置解析（主备容错+端点选择） +- `llm_proxy.proxy_chat_completion`：调用前后接门禁与结算（运行环境 token 路径） + +机构未配置治理（无策略、无新模型）→ 返回 `__LEGACY__`，调用方回退旧 `llm` 表，向后兼容。 + +## 宿主接入清单 + +1. `app/pipeline_app.py` init() 加 `load_llm()`（try/except ImportError 兜底） +2. `build.sh`：clone 枚举 + pip install 枚举 + CRUD 生成枚举 + wwwroot 符号链接枚举 +3. `scripts/create_tables.py`：IDE 幂等建表枚举加 `pipeline-llm`（或执行本模块 `mysql.ddl.sql`） +4. `scripts/import_init.py`：INIT_MODULES 加本模块 `init/data.json`（appcodes 字典） +5. `conf/rp.json`：`/pipeline-llm/**` 注册到 `logined`；运行 `scripts/load_path.py` +6. `wwwroot/index.ui` 主菜单加「模型治理」项（URL `/pipeline-llm`） +7. `restart-pipeline.sh` 重启（.py 变更必须重启；`api_key` 有缓存，改 key 也须重启） + +## 关键约定 + +- **api_key 用 AES 单层加密**（`appPublic.aes.aes_encode_b64`，password_key 做密钥）。 + ⚠️ 不用 RC4：`password()/unpassword()` 盐不对称，加密后永久不可解。 +- **限流用 Redis 分钟窗口原子计数**（db4，与会话 db3 隔离）；Redis 故障时限流放行（fail-open）， + 余额仍由 DB 条件 UPDATE 守住。 +- **429 → (账号,端点)对冷却 60s**；账号级冷却用 `*` 通配键。 +- **双维度记账**：一次调用同行记 `cost`（成本侧，账号余额扣）+ `charge`（消费侧，组织池扣）； + 充值是 `status=recharge` 行（对账用）。 +- **预授权-结算**：调用前按预估冻结，调用后按实际 token 多退少补。 + +## 文档 + +- `docs/design-spec.md` — 完整设计规范（架构/表/机制/功能点/分期） +- `docs/test-cases.md` — 测试用例（30 例，部署后全部执行） + +## 开发日志 + +见 `docs/work-log-2026-09-01.md`。 diff --git a/docs/design-spec.md b/docs/design-spec.md new file mode 100644 index 0000000..231dabb --- /dev/null +++ b/docs/design-spec.md @@ -0,0 +1,259 @@ +# pipeline-llm 模块设计规范 + +> 版本：1.0 | 日期：2026-09-01 | 状态：待实施 +> 宿主：产线平台（pipeline-app，共享 `pipeline` 库） | 表前缀：`llm_` + +## 1. 背景与目标 + +产线平台现有模型层是 `llm` 单表（name/provider/model_id/api_base/api_key/capabilities）， +内嵌接入信息、单一 OpenAI-chat 调用形态、能力是标签不是契约。随着模型增多（非 t2t 能力、 +多供应商、多账号），需要独立的模型治理模块。本模块解决五类问题： + +1. **供给侧治理**：供应商协议/端点目录、账号（钱包）、模型注册、适配模板 +2. **容量治理**：供应商限流 → 多账号轮转；多供应商 → 主备模型容错 +3. **需求侧治理**：组织级模型容错策略、组织限额限流、个人限额限流 +4. **计费**：双维度记账（成本侧记账号、消费侧记组织/个人），挂定价平台 `pricing_program.ppid` +5. **端点选择**：供应商全球端点配置一次，账号选用端点，客户按区域偏好（prefer/must） + +## 2. 架构总览 + +``` +供给侧（容量） 需求侧（治理） +───────────── ───────────── +llm_vendor (协议+端点目录) llm_org_policy (组织容错策略) + └─ llm_account (钱包+选端点) llm_org_quota (组织限额限流) + └─ llm_model (模型注册) llm_user_quota (个人限额限流) + └─ llm_api_profile (适配) + ↓ + llm_usage (用量流水，双维度) +``` + +**调用门禁链**（所有 LLM 调用收敛点 `llm_call`）： + +``` +① 个人限流窗口 → ② 组织限流窗口 +→ ③ 个人额度余额 → ④ 组织池余额 +→ ⑤ 组织容错策略选模型（主→备） +→ ⑥ 账号×端点候选池：区域偏好过滤 → 剩余额度加权轮转 + 冷却避让 +→ ⑦ 预授权（冻结预估用量）→ 调用 → ⑧ 结算（实际用量，双维度记账） +任何一级不过：快速失败 + 明确原因（不挂起、不静默） +``` + +## 3. 数据表（8 张，全部 `llm_` 前缀，建在 `pipeline` 库） + +### 3.1 llm_vendor — 供应商 +| 字段 | 类型 | 说明 | +|---|---|---| +| id | str(32) PK | | +| name | str(100) | 供应商名（如 阿里云百炼） | +| protocol | str(20) | openai_compat / dashscope_async / custom | +| endpoints | text(JSON) | 端点目录 `[{region, base_url, proxy, timeout, note}]` | +| description | text | | +| status | str(20) | active / disabled，默认 active | +| org_id | str(32) | 0=系统级 | +| created_at/updated_at | str(30) | | + +端点目录挂在 vendor 下（全球端点配置一次），账号选用。`endpoints` JSON 元素： +`region`（domestic/international/europe/...）、`base_url`、`proxy`（可选，国外端点走 SOCKS）、 +`timeout`（秒，默认 60）、`note`。 + +### 3.2 llm_account — 供应商账号（钱包） +| 字段 | 类型 | 说明 | +|---|---|---| +| id | str(32) PK | | +| vendor_id | str(32) | → llm_vendor.id | +| name | str(100) | 账号名 | +| api_key | str(500) | **AES 单层加密**（appPublic.aes.aes_encode_b64，password_key 做密钥，对称可解密）。⚠️ 不能用 RC4：rc4.password()/unpassword() 盐不对称，加密后永久不可解（2026-08 实测坑）。改 key 须重启进程（有缓存） | +| endpoint_ids | text(JSON) | 选用的端点索引列表（对应 vendor.endpoints 下标），有序；空=不启用 | +| balance | decimal(14,4) | 余额（充值-消耗），单位与定价币种一致 | +| total_recharge | decimal(14,4) | 累计充值 | +| status | str(20) | active / suspended / exhausted，默认 active | +| org_id | str(32) | | +| created_at/updated_at | str(30) | | + +独立充值、独立记账。轮转限流时余额不足的账号直接跳过（不消耗）。 + +### 3.3 llm_model — 模型注册（旧 `llm` 表的替代） +| 字段 | 类型 | 说明 | +|---|---|---| +| id | str(32) PK | | +| vendor_id | str(32) | → llm_vendor.id | +| account_id | str(32) | 默认账号（可空，运行时轮转选） | +| name | str(100) UNIQUE | 模型注册名（平台内唯一，调用方用此名） | +| vendor_model_id | str(100) | 供应商侧模型名（各家命名不一） | +| capability | str(20) | 能力类型，默认 t2t（见 §6 能力标准） | +| sync_mode | str(10) | sync / async_task，默认 sync | +| profile_id | str(32) | → llm_api_profile.id（适配模板） | +| ppid | str(32) | → 定价平台 `pricing_program.id`（挂定价） | +| default_params | text(JSON) | 默认参数（temperature/max_tokens 等） | +| status | str(20) | active / disabled | +| description | text | | +| org_id | str(32) | | +| created_at/updated_at | str(30) | | + +### 3.4 llm_api_profile — 适配模板（协议×能力形态去重） +| 字段 | 类型 | 说明 | +|---|---|---| +| id | str(32) PK | | +| name | str(100) | 如 openai-chat、dashscope-image-async | +| protocol | str(20) | 同 vendor.protocol | +| capability | str(20) | 能力类型 | +| request_template | text | Jinja2：参数 → 供应商请求体 | +| response_template | text | Jinja2：供应商响应 → 统一结果（含 usage） | +| param_schema | text(JSON) | bricks input_fields 格式（参数表单定义） | +| status | str(20) | active / disabled | +| created_at/updated_at | str(30) | | + +模板按「协议×能力形态」开，不按模型开——同一端点 N 个模型共用一条，杜绝重复记录。 +一期只内置 `openai-chat`（sync），非 chat 形态模型进来时再加对应 profile。 + +### 3.5 llm_org_policy — 组织模型容错策略 +| 字段 | 类型 | 说明 | +|---|---|---| +| id | str(32) PK | | +| org_id | str(32) UNIQUE | 一组织一策略 | +| primary_model_id | str(32) | → llm_model.id 主模型 | +| backup_model_ids | text(JSON) | 备模型 id 列表（有序） | +| endpoint_pref | str(20) | prefer_domestic / prefer_intl / must_domestic / must_intl / any，默认 any | +| status | str(20) | active / disabled | +| created_at/updated_at | str(30) | | + +生效优先级：会话/项目选择 > 组织策略 > 平台默认（与现有 +`sd_projects.default_model > pipeline_agent_settings.default_llm_id` 链兼容，组织策略插中间）。 +must 模式：候选端点耗尽宁可报错冒泡，绝不跨端点。 + +### 3.6 llm_org_quota — 组织限额限流 +| 字段 | 类型 | 说明 | +|---|---|---| +| id | str(32) PK | | +| org_id | str(32) UNIQUE | | +| balance | decimal(14,4) | 组织池余额（充值-消耗） | +| total_recharge | decimal(14,4) | 累计充值 | +| rate_limit | int | 组织 QPM 上限（0=不限） | +| status | str(20) | active / disabled | +| created_at/updated_at | str(30) | | + +### 3.7 llm_user_quota — 个人限额限流 +| 字段 | 类型 | 说明 | +|---|---|---| +| id | str(32) PK | | +| user_id | str(32) | | +| org_id | str(32) | 所属组织（额度挂组织池） | +| quota_limit | decimal(14,4) | 个人额度上限（0=不限） | +| quota_used | decimal(14,4) | 个人已用 | +| rate_limit | int | 个人 QPM 上限（0=不限） | +| status | str(20) | active / disabled | +| created_at/updated_at | str(30) | | + +关系默认「共享池 + 个人上限」：组织充值一个池，个人上限防单人打爆池子。 +个人额度耗尽不影响他人；组织池耗尽全员不可用（冒泡提醒充值）。 + +### 3.8 llm_usage — 用量流水（双维度记账事实表） +| 字段 | 类型 | 说明 | +|---|---|---| +| id | str(32) PK | | +| org_id / user_id | str(32) | 消费侧维度 | +| model_id / account_id | str(32) | 供给侧维度（model_id 空+source=recharge 时为充值记录） | +| endpoint_region | str(20) | 实际走的端点区域 | +| req_tokens / resp_tokens | int | 实际用量 | +| cost | decimal(12,6) | 成本侧金额（账号扣减，按定价） | +| charge | decimal(12,6) | 消费侧金额（组织池扣减，按产品定价） | +| ppid | str(32) | 定价项目（冗余自模型，便于对账） | +| task_ref | str(100) | 调用来源（任务/会话标识） | +| status | str(20) | ok / failed / recharge（充值记录） | +| note | str(200) | 失败原因/充值备注 | +| created_at | str(30) | | + +一次调用两条线：**成本侧** cost 记账号（供应商对账），**消费侧** charge 记组织池+个人 +（客户计费）。充值是 balance 变动事件，记 `source=recharge` 行（model_id/account_id 空）。 + +## 4. 核心机制 + +### 4.1 选择链与轮转（gateway.py `llm_call`） + +```python +async def llm_call(prompt, model=None, org_id=None, user_id=None, task_ref='', **kw) +``` + +1. 解析模型：调用方指定 model → 直接用；否则查组织策略主备链 +2. 候选对构建：模型的账号池（account.status=active）× 账号选用端点 +3. 区域偏好过滤：must_* 只留对应区域端点对；prefer_* 排序（匹配区域优先） +4. 加权轮转：按账号余额 + 端点窗口剩余配额加权；限流冷却中的对跳过 +5. 调用 → 429 标记该(账号,端点)对冷却 → 换下一对；账号池耗尽 → 降备模型； + 备模型也耗尽 → must 模式冒泡报错 / prefer 模式跨端点重试 +6. 401/403 标记账号失效（不轮转）；5xx 短暂重试（最多 2 次） + +### 4.2 预授权-结算（防并发击穿余额） + +- 调用前：按 max_tokens 预估（默认 2000 token × 单价）Redis 原子冻结组织池+个人额度 +- 调用后：按实际 token 多退少补，写双维度流水 +- GeneratorExit/超时：结算兜底（按预估释放，写 failed 流水） + +### 4.3 限流（Redis 滑动窗口） + +- key：`llm_rl:{user|org}:{id}:{minute}`，原子 INCR + EXPIRE +- 超窗拒绝：返回明确错误（个人限流/组织限流），下窗口自动恢复，不涉及钱 +- 供应商侧 429：(账号,端点)对冷却 60s，窗口内不再选它 + +### 4.4 定价对接（ppid） + +- 模型挂 `pricing_program.id`（定价平台的定价项目） +- 消费侧单价从定价平台读取（跨库：定价模块库），一期支持手动设置 `price_per_1k` + 兜底（组织策略页配置），二期接定价平台实时价 +- 成本侧单价：账号维度配置（供应商结算价），一期也走手动配置 + +## 5. 功能点清单（共 18 项） + +| # | 功能点 | 表/文件 | 优先级 | +|---|---|---|---| +| F01 | 供应商管理（含端点目录配置） | llm_vendor + CRUD | P0 | +| F02 | 账号管理（充值、余额、选端点） | llm_account + CRUD | P0 | +| F03 | 模型注册（挂能力、挂定价、挂适配） | llm_model + CRUD | P0 | +| F04 | 适配模板管理 | llm_api_profile + CRUD | P1（一期内置 openai-chat） | +| F05 | 组织容错策略（主备模型+端点偏好） | llm_org_policy + CRUD | P0 | +| F06 | 组织限额限流（充值、QPM） | llm_org_quota + CRUD | P0 | +| F07 | 个人限额限流 | llm_user_quota + CRUD | P0 | +| F08 | 调用门禁（①-④ 限流限额检查） | gateway.py | P0 | +| F09 | 主备容错（策略选模型→备链） | gateway.py | P0 | +| F10 | 账号×端点轮转（加权+冷却） | gateway.py | P0 | +| F11 | 区域偏好过滤（prefer/must） | gateway.py | P0 | +| F12 | 预授权-结算 | gateway.py | P0 | +| F13 | 双维度记账流水 | llm_usage | P0 | +| F14 | 充值操作（账号/组织池） | recharge dspy | P0 | +| F15 | 用量查询（按组织/模型/账号/时间） | usage 列表页 | P1 | +| F16 | 模型管理入口（主菜单） | index.ui 菜单项 | P0 | +| F17 | 与现有调用链兼容（llm_bridge 切换） | llm_bridge.py 适配 | P0 | +| F18 | 机构未配置冒泡提示 | gateway 错误路径 | P0 | + +## 6. 能力类型标准（capabilities 取值，先行收敛） + +| 值 | 含义 | 同步性 | +|---|---|---| +| t2t | 文本对话/生成 | sync | +| t2i | 文生图 | async_task | +| i2t | 图生文（多模态理解） | sync | +| t2v | 文生视频 | async_task | +| embedding | 文本向量化 | sync | +| mm-embedding | 多模态向量化 | sync | +| rerank | 重排序 | sync | +| mm-rerank | 多模态重排序 | sync | +| tts | 语音合成 | sync | +| asr | 语音识别 | sync | + +新增能力类型走评审（改本文档 + init/data.json appcodes），禁止野生标签。 + +## 7. 集成点 + +1. **宿主加载**：`pipeline_app.py` init() 加 `load_llm()`（try/except ImportError 兜底） +2. **菜单**：`wwwroot/index.ui` 主菜单加「模型管理」项 → `/llm`（TabPanel） +3. **RBAC**：`/llm/**` 注册到 superuser；静态资源 any；load_path.py 注册各路径 +4. **i18n**：zh/en 双语文案（模块内文案走 appcodes + i18n msg.txt） +5. **建表**：mysql.ddl.sql（json2ddl 生成 + 手写补齐），存量库 ALTER 幂等 +6. **兼容**：旧 `llm` 表保留，`llm_bridge.py` 优先查新表（按 name），无则回退旧表—— + 现有调用零改动，迁移平滑 + +## 8. 分期 + +- **一期（本次交付）**：全部 10 张表 + F01-F03/F05-F14/F16-F18 + F04 内置 openai-chat + F15 +- **二期（触发：第一个非 t2t 模型）**：异步任务形态适配模板、任务轮询端点 +- **三期（触发：定价平台实时价接入）**：成本/消费侧单价自动读取 diff --git a/docs/test-cases.md b/docs/test-cases.md new file mode 100644 index 0000000..2a06f57 --- /dev/null +++ b/docs/test-cases.md @@ -0,0 +1,66 @@ +# pipeline-llm 测试用例（部署到测试环境后全部执行） + +> 测试环境：pipeline@pipeline.opencomputing.cn /d/pipeline/pipeline-app +> 验收标准：浏览器真实执行（curl 不算通过）+ 数据库事实核验 + +## A. 部署与集成（5 例） + +| # | 用例 | 步骤 | 预期 | +|---|---|---|---| +| A1 | 服务启动 | 重启 pipeline_app | 9090 返回 200，日志有 `[pipeline_llm] loaded` | +| A2 | 建表完整 | SHOW TABLES LIKE 'llm\_%' | 8 张表齐全 | +| A3 | 菜单入口 | 浏览器登录→主菜单 | 「模型管理」项存在，点击打开 /llm 页面（非空白） | +| A4 | RBAC | 未登录访问 /llm/index.ui | 401/跳转登录；登录后 200 | +| A5 | 兼容回退 | 现有驾驶舱对话（走旧 llm 表模型） | 正常回复，不因新模块中断 | + +## B. 供给侧配置（6 例） + +| # | 用例 | 步骤 | 预期 | +|---|---|---|---| +| B1 | 供应商+端点目录 | 建供应商，endpoints 配国内+国外两端点 | 保存成功，列表可见两端点 | +| B2 | 账号+充值 | 建账号绑定 B1 供应商，选国内端点，充值 100 | balance=100，total_recharge=100，流水有 recharge 行 | +| B3 | api_key 加密 | 查库 B2 账号 api_key | 密文（非明文），调用时能解密使用 | +| B4 | 模型注册+挂定价 | 建模型挂 vendor+ppid+capability=t2t | 保存成功，ppid 关联可见 | +| B5 | 适配模板 | 内置 openai-chat profile 存在 | request/response 模板非空，参数 schema 合法 | +| B6 | 端点探测 | 账号选用不存在的端点下标 | 保存时校验拒绝（防死配置） | + +## C. 需求侧治理（5 例） + +| # | 用例 | 步骤 | 预期 | +|---|---|---|---| +| C1 | 组织策略 | 建组织策略：主模型=B4，备模型空，端点 any | 保存成功 | +| C2 | 组织充值 | 组织池充值 50 | balance=50，流水有记录 | +| C3 | 个人限额 | 建个人配额：额度 10、QPM 5 | 保存成功 | +| C4 | 组织限流 | 同组织 1 分钟内发起 >QPM 次调用 | 超限请求返回「组织限流」明确错误 | +| C5 | 个人限额耗尽 | 个人连续调用至额度用完 | 后续请求返回「个人额度不足」，不影响同组织他人 | + +## D. 调用门禁链（7 例） + +| # | 用例 | 步骤 | 预期 | +|---|---|---|---| +| D1 | 正常调用 | 配置齐全后发起一次对话调用 | 成功返回，usage 流水 1 条（双维度金额>0） | +| D2 | 预授权结算 | D1 调用前后查组织池余额 | 冻结→释放，最终扣减=实际 charge | +| D3 | 账号余额不足跳过 | 账号 A 余额 0、账号 B 有余额 | 调用自动走 B，A 不消耗 | +| D4 | 429 轮转 | mock 账号 A 端点返回 429 | 自动切同账号另一端点或账号 B，调用成功 | +| D5 | 主备容错 | 主模型全部账号不可用 | 自动降备模型，调用成功，日志记录降级 | +| D6 | must 端点 | 策略 must_domestic，仅国际端点可用 | 报错冒泡（绝不跨端点），错误信息明确 | +| D7 | 机构未配置 | 无策略无余额的机构调用 | 冒泡提示「未配置模型/余额」，不静默失败 | + +## E. 记账与用量（4 例） + +| # | 用例 | 步骤 | 预期 | +|---|---|---|---| +| E1 | 双维度流水 | D1 后查 llm_usage | 同行含成本侧 cost + 消费侧 charge，ppid 冗余正确 | +| E2 | 账号对账 | 账号余额 = 充值 - Σcost | 数值吻合 | +| E3 | 组织对账 | 组织池余额 = 充值 - Σcharge | 数值吻合 | +| E4 | 用量查询页 | 用量列表按组织/模型/时间筛选 | 筛选结果正确，金额汇总与流水一致 | + +## F. 回归（3 例） + +| # | 用例 | 步骤 | 预期 | +|---|---|---|---| +| F1 | 待办动态表单 | 触发冒泡→待办内提交 | 既有功能不受影响 | +| F2 | 工作空间 | 开发产线打开工作空间 | 仓库树正常（本模块改动不波及） | +| F3 | 驾驶舱对话 | 完整一轮开发产线对话 | 正常，模型解析走新链路 | + +**共计 30 例**。执行报告逐条记录：实际命令/截图路径 + 数据库核验结果 + 结论（通过/失败/跳过及原因）。 diff --git a/init/data.json b/init/data.json new file mode 100644 index 0000000..a303661 --- /dev/null +++ b/init/data.json @@ -0,0 +1,39 @@ +{ + "appcodes": [ + {"parentid": "llm_protocol", "parentname": "供应商协议", "items": [ + {"k": "openai_compat", "v": "OpenAI兼容"}, + {"k": "dashscope_async", "v": "DashScope异步任务"}, + {"k": "custom", "v": "自定义"} + ]}, + {"parentid": "llm_status", "parentname": "状态", "items": [ + {"k": "active", "v": "启用"}, + {"k": "disabled", "v": "停用"}, + {"k": "suspended", "v": "暂停"}, + {"k": "exhausted", "v": "余额耗尽"} + ]}, + {"parentid": "llm_capability", "parentname": "模型能力类型", "items": [ + {"k": "t2t", "v": "文本对话/生成"}, + {"k": "t2i", "v": "文生图"}, + {"k": "i2t", "v": "图生文"}, + {"k": "t2v", "v": "文生视频"}, + {"k": "embedding", "v": "文本向量化"}, + {"k": "mm-embedding", "v": "多模态向量化"}, + {"k": "rerank", "v": "重排序"}, + {"k": "mm-rerank", "v": "多模态重排序"}, + {"k": "tts", "v": "语音合成"}, + {"k": "asr", "v": "语音识别"} + ]}, + {"parentid": "llm_endpoint_pref", "parentname": "端点偏好", "items": [ + {"k": "any", "v": "不限"}, + {"k": "prefer_domestic", "v": "优先国内"}, + {"k": "prefer_intl", "v": "优先国际"}, + {"k": "must_domestic", "v": "仅国内(合规)"}, + {"k": "must_intl", "v": "仅国际(合规)"} + ]}, + {"parentid": "llm_usage_status", "parentname": "用量状态", "items": [ + {"k": "ok", "v": "成功"}, + {"k": "failed", "v": "失败"}, + {"k": "recharge", "v": "充值"} + ]} + ] +} diff --git a/json/llm_account_list.json b/json/llm_account_list.json new file mode 100644 index 0000000..d99cdbc --- /dev/null +++ b/json/llm_account_list.json @@ -0,0 +1,43 @@ +{ + "tblname": "llm_account", + "title": "供应商账号", + "params": { + "sortby": "name", + "browserfields": { + "exclouded": [ + "id", + "api_key" + ], + "alters": { + "vendor_id": { + "uitype": "code", + "dataurl": "{{entire_url('../api/get_llm_vendor_options.dspy')}}", + "valueField": "value", + "textField": "text" + }, + "status": { + "uitype": "code", + "dataurl": "{{entire_url('../api/get_llm_status_options.dspy')}}", + "valueField": "value", + "textField": "text" + } + } + }, + "editexclouded": [ + "id", + "api_key", + "balance", + "total_recharge", + "created_at", + "updated_at" + ], + "editable": { + "new_data_url": "{{entire_url('./add_llm_account.dspy')}}", + "update_data_url": "{{entire_url('./update_llm_account.dspy')}}", + "delete_data_url": "{{entire_url('./delete_llm_account.dspy')}}" + }, + "confidential_fields": [ + "api_key" + ] + } +} diff --git a/json/llm_api_profile_list.json b/json/llm_api_profile_list.json new file mode 100644 index 0000000..069135b --- /dev/null +++ b/json/llm_api_profile_list.json @@ -0,0 +1,45 @@ +{ + "tblname": "llm_api_profile", + "title": "适配模板", + "params": { + "sortby": "name", + "browserfields": { + "exclouded": [ + "id", + "request_template", + "response_template", + "param_schema" + ], + "alters": { + "protocol": { + "uitype": "code", + "dataurl": "{{entire_url('../api/get_llm_protocol_options.dspy')}}", + "valueField": "value", + "textField": "text" + }, + "capability": { + "uitype": "code", + "dataurl": "{{entire_url('../api/get_llm_capability_options.dspy')}}", + "valueField": "value", + "textField": "text" + }, + "status": { + "uitype": "code", + "dataurl": "{{entire_url('../api/get_llm_status_options.dspy')}}", + "valueField": "value", + "textField": "text" + } + } + }, + "editexclouded": [ + "id", + "created_at", + "updated_at" + ], + "editable": { + "new_data_url": "{{entire_url('./add_llm_api_profile.dspy')}}", + "update_data_url": "{{entire_url('./update_llm_api_profile.dspy')}}", + "delete_data_url": "{{entire_url('./delete_llm_api_profile.dspy')}}" + } + } +} diff --git a/json/llm_model_list.json b/json/llm_model_list.json new file mode 100644 index 0000000..62fda2f --- /dev/null +++ b/json/llm_model_list.json @@ -0,0 +1,54 @@ +{ + "tblname": "llm_model", + "title": "模型注册", + "params": { + "sortby": "name", + "browserfields": { + "exclouded": [ + "id" + ], + "alters": { + "vendor_id": { + "uitype": "code", + "dataurl": "{{entire_url('../api/get_llm_vendor_options.dspy')}}", + "valueField": "value", + "textField": "text" + }, + "account_id": { + "uitype": "code", + "dataurl": "{{entire_url('../api/get_llm_account_options.dspy')}}", + "valueField": "value", + "textField": "text" + }, + "capability": { + "uitype": "code", + "dataurl": "{{entire_url('../api/get_llm_capability_options.dspy')}}", + "valueField": "value", + "textField": "text" + }, + "status": { + "uitype": "code", + "dataurl": "{{entire_url('../api/get_llm_status_options.dspy')}}", + "valueField": "value", + "textField": "text" + }, + "ppid": { + "uitype": "code", + "dataurl": "{{entire_url('../api/get_llm_ppid_options.dspy')}}", + "valueField": "value", + "textField": "text" + } + } + }, + "editexclouded": [ + "id", + "created_at", + "updated_at" + ], + "editable": { + "new_data_url": "{{entire_url('./add_llm_model.dspy')}}", + "update_data_url": "{{entire_url('./update_llm_model.dspy')}}", + "delete_data_url": "{{entire_url('./delete_llm_model.dspy')}}" + } + } +} diff --git a/json/llm_org_policy_list.json b/json/llm_org_policy_list.json new file mode 100644 index 0000000..adaf0a7 --- /dev/null +++ b/json/llm_org_policy_list.json @@ -0,0 +1,42 @@ +{ + "tblname": "llm_org_policy", + "title": "组织容错策略", + "params": { + "sortby": "created_at", + "browserfields": { + "exclouded": [ + "id" + ], + "alters": { + "primary_model_id": { + "uitype": "code", + "dataurl": "{{entire_url('../api/get_llm_model_options.dspy')}}", + "valueField": "value", + "textField": "text" + }, + "endpoint_pref": { + "uitype": "code", + "dataurl": "{{entire_url('../api/get_llm_endpoint_pref_options.dspy')}}", + "valueField": "value", + "textField": "text" + }, + "status": { + "uitype": "code", + "dataurl": "{{entire_url('../api/get_llm_status_options.dspy')}}", + "valueField": "value", + "textField": "text" + } + } + }, + "editexclouded": [ + "id", + "created_at", + "updated_at" + ], + "editable": { + "new_data_url": "{{entire_url('./add_llm_org_policy.dspy')}}", + "update_data_url": "{{entire_url('./update_llm_org_policy.dspy')}}", + "delete_data_url": "{{entire_url('./delete_llm_org_policy.dspy')}}" + } + } +} diff --git a/json/llm_org_quota_list.json b/json/llm_org_quota_list.json new file mode 100644 index 0000000..d963526 --- /dev/null +++ b/json/llm_org_quota_list.json @@ -0,0 +1,32 @@ +{ + "tblname": "llm_org_quota", + "title": "组织限额限流", + "params": { + "sortby": "created_at", + "browserfields": { + "exclouded": [ + "id" + ], + "alters": { + "status": { + "uitype": "code", + "dataurl": "{{entire_url('../api/get_llm_status_options.dspy')}}", + "valueField": "value", + "textField": "text" + } + } + }, + "editexclouded": [ + "id", + "balance", + "total_recharge", + "created_at", + "updated_at" + ], + "editable": { + "new_data_url": "{{entire_url('./add_llm_org_quota.dspy')}}", + "update_data_url": "{{entire_url('./update_llm_org_quota.dspy')}}", + "delete_data_url": "{{entire_url('./delete_llm_org_quota.dspy')}}" + } + } +} diff --git a/json/llm_usage_list.json b/json/llm_usage_list.json new file mode 100644 index 0000000..91d72ec --- /dev/null +++ b/json/llm_usage_list.json @@ -0,0 +1,43 @@ +{ + "tblname": "llm_usage", + "title": "用量流水", + "params": { + "sortby": [ + "created_at" + ], + "browserfields": { + "exclouded": [ + "id" + ] + }, + "editexclouded": [ + "id", + "org_id", + "user_id", + "model_id", + "account_id", + "endpoint_region", + "req_tokens", + "resp_tokens", + "cost", + "charge", + "ppid", + "task_ref", + "status", + "note", + "created_at" + ], + "record_toolbar": [ + { + "label": "查询统计", + "actiontype": "dspy", + "url": "{{entire_url('../api/llm_usage_query.dspy')}}", + "options": { + "icon": "search", + "cwidth": 20, + "cheight": 12 + } + } + ] + } +} diff --git a/json/llm_user_quota_list.json b/json/llm_user_quota_list.json new file mode 100644 index 0000000..40fd76a --- /dev/null +++ b/json/llm_user_quota_list.json @@ -0,0 +1,31 @@ +{ + "tblname": "llm_user_quota", + "title": "个人限额限流", + "params": { + "sortby": "created_at", + "browserfields": { + "exclouded": [ + "id" + ], + "alters": { + "status": { + "uitype": "code", + "dataurl": "{{entire_url('../api/get_llm_status_options.dspy')}}", + "valueField": "value", + "textField": "text" + } + } + }, + "editexclouded": [ + "id", + "quota_used", + "created_at", + "updated_at" + ], + "editable": { + "new_data_url": "{{entire_url('./add_llm_user_quota.dspy')}}", + "update_data_url": "{{entire_url('./update_llm_user_quota.dspy')}}", + "delete_data_url": "{{entire_url('./delete_llm_user_quota.dspy')}}" + } + } +} diff --git a/json/llm_vendor_list.json b/json/llm_vendor_list.json new file mode 100644 index 0000000..9e30a76 --- /dev/null +++ b/json/llm_vendor_list.json @@ -0,0 +1,36 @@ +{ + "tblname": "llm_vendor", + "title": "模型供应商", + "params": { + "sortby": "name", + "browserfields": { + "exclouded": [ + "id" + ], + "alters": { + "protocol": { + "uitype": "code", + "dataurl": "{{entire_url('../api/get_llm_protocol_options.dspy')}}", + "valueField": "value", + "textField": "text" + }, + "status": { + "uitype": "code", + "dataurl": "{{entire_url('../api/get_llm_status_options.dspy')}}", + "valueField": "value", + "textField": "text" + } + } + }, + "editexclouded": [ + "id", + "created_at", + "updated_at" + ], + "editable": { + "new_data_url": "{{entire_url('./add_llm_vendor.dspy')}}", + "update_data_url": "{{entire_url('./update_llm_vendor.dspy')}}", + "delete_data_url": "{{entire_url('./delete_llm_vendor.dspy')}}" + } + } +} diff --git a/models/llm_account.json b/models/llm_account.json new file mode 100644 index 0000000..9c1d207 --- /dev/null +++ b/models/llm_account.json @@ -0,0 +1,113 @@ +{ + "summary": [ + { + "name": "llm_account", + "title": "供应商账号(钱包)", + "primary": [ + "id" + ], + "catelog": "entity" + } + ], + "fields": [ + { + "name": "id", + "title": "主键ID", + "type": "str", + "length": 32, + "nullable": "no" + }, + { + "name": "vendor_id", + "title": "供应商ID", + "type": "str", + "length": 32, + "nullable": "no" + }, + { + "name": "name", + "title": "账号名称", + "type": "str", + "length": 100, + "nullable": "no" + }, + { + "name": "api_key", + "title": "API密钥(加密)", + "type": "str", + "length": 500 + }, + { + "name": "endpoint_ids", + "title": "选用端点索引(JSON)", + "type": "text" + }, + { + "name": "balance", + "title": "余额", + "type": "float", + "length": 14, + "dec": 4, + "default": "0" + }, + { + "name": "total_recharge", + "title": "累计充值", + "type": "float", + "length": 14, + "dec": 4, + "default": "0" + }, + { + "name": "status", + "title": "状态", + "type": "str", + "length": 20, + "nullable": "no", + "default": "'active'" + }, + { + "name": "org_id", + "title": "所属机构", + "type": "str", + "length": 32, + "nullable": "no", + "default": "'0'" + }, + { + "name": "created_at", + "title": "创建时间", + "type": "timestamp", + "nullable": "no" + }, + { + "name": "updated_at", + "title": "更新时间", + "type": "timestamp" + } + ], + "indexes": [ + { + "name": "idx_llm_account_vendor", + "idxtype": "index", + "idxfields": [ + "vendor_id" + ] + } + ], + "codes": [ + { + "field": "vendor_id", + "table": "llm_vendor", + "valuefield": "id", + "textfield": "name" + }, + { + "field": "status", + "table": "appcodes_kv", + "valuefield": "k", + "textfield": "v", + "cond": "parentid='llm_status'" + } + ] +} diff --git a/models/llm_api_profile.json b/models/llm_api_profile.json new file mode 100644 index 0000000..3b1742a --- /dev/null +++ b/models/llm_api_profile.json @@ -0,0 +1,100 @@ +{ + "summary": [ + { + "name": "llm_api_profile", + "title": "适配模板", + "primary": [ + "id" + ], + "catelog": "entity" + } + ], + "fields": [ + { + "name": "id", + "title": "主键ID", + "type": "str", + "length": 32, + "nullable": "no" + }, + { + "name": "name", + "title": "模板名称", + "type": "str", + "length": 100, + "nullable": "no" + }, + { + "name": "protocol", + "title": "协议类型", + "type": "str", + "length": 20, + "nullable": "no" + }, + { + "name": "capability", + "title": "能力类型", + "type": "str", + "length": 20, + "nullable": "no", + "default": "'t2t'" + }, + { + "name": "request_template", + "title": "请求模板(Jinja2)", + "type": "text" + }, + { + "name": "response_template", + "title": "响应模板(Jinja2)", + "type": "text" + }, + { + "name": "param_schema", + "title": "参数Schema(bricks)", + "type": "text" + }, + { + "name": "status", + "title": "状态", + "type": "str", + "length": 20, + "nullable": "no", + "default": "'active'" + }, + { + "name": "created_at", + "title": "创建时间", + "type": "timestamp", + "nullable": "no" + }, + { + "name": "updated_at", + "title": "更新时间", + "type": "timestamp" + } + ], + "codes": [ + { + "field": "protocol", + "table": "appcodes_kv", + "valuefield": "k", + "textfield": "v", + "cond": "parentid='llm_protocol'" + }, + { + "field": "capability", + "table": "appcodes_kv", + "valuefield": "k", + "textfield": "v", + "cond": "parentid='llm_capability'" + }, + { + "field": "status", + "table": "appcodes_kv", + "valuefield": "k", + "textfield": "v", + "cond": "parentid='llm_status'" + } + ] +} diff --git a/models/llm_model.json b/models/llm_model.json new file mode 100644 index 0000000..54072a2 --- /dev/null +++ b/models/llm_model.json @@ -0,0 +1,200 @@ +{ + "summary": [ + { + "name": "llm_model", + "title": "模型注册", + "primary": [ + "id" + ], + "catelog": "entity" + } + ], + "fields": [ + { + "name": "id", + "title": "主键ID", + "type": "str", + "length": 32, + "nullable": "no" + }, + { + "name": "vendor_id", + "title": "供应商ID", + "type": "str", + "length": 32, + "nullable": "no" + }, + { + "name": "account_id", + "title": "默认账号ID", + "type": "str", + "length": 32 + }, + { + "name": "name", + "title": "模型注册名", + "type": "str", + "length": 100, + "nullable": "no" + }, + { + "name": "vendor_model_id", + "title": "供应商侧模型名", + "type": "str", + "length": 100 + }, + { + "name": "capability", + "title": "能力类型", + "type": "str", + "length": 20, + "nullable": "no", + "default": "'t2t'" + }, + { + "name": "sync_mode", + "title": "同步性", + "type": "str", + "length": 10, + "nullable": "no", + "default": "'sync'" + }, + { + "name": "profile_id", + "title": "适配模板ID", + "type": "str", + "length": 32 + }, + { + "name": "ppid", + "title": "定价项目ID", + "type": "str", + "length": 32 + }, + { + "name": "price_input", + "title": "输入单价(元/千token)", + "type": "float", + "length": 12, + "dec": 6, + "default": "0" + }, + { + "name": "price_output", + "title": "输出单价(元/千token)", + "type": "float", + "length": 12, + "dec": 6, + "default": "0" + }, + { + "name": "cost_input", + "title": "输入成本(元/千token)", + "type": "float", + "length": 12, + "dec": 6, + "default": "0" + }, + { + "name": "cost_output", + "title": "输出成本(元/千token)", + "type": "float", + "length": 12, + "dec": 6, + "default": "0" + }, + { + "name": "default_params", + "title": "默认参数(JSON)", + "type": "text" + }, + { + "name": "status", + "title": "状态", + "type": "str", + "length": 20, + "nullable": "no", + "default": "'active'" + }, + { + "name": "description", + "title": "描述", + "type": "text" + }, + { + "name": "org_id", + "title": "所属机构", + "type": "str", + "length": 32, + "nullable": "no", + "default": "'0'" + }, + { + "name": "created_at", + "title": "创建时间", + "type": "timestamp", + "nullable": "no" + }, + { + "name": "updated_at", + "title": "更新时间", + "type": "timestamp" + } + ], + "indexes": [ + { + "name": "uk_llm_model_name", + "idxtype": "unique", + "idxfields": [ + "name" + ] + }, + { + "name": "idx_llm_model_vendor", + "idxtype": "index", + "idxfields": [ + "vendor_id" + ] + } + ], + "codes": [ + { + "field": "vendor_id", + "table": "llm_vendor", + "valuefield": "id", + "textfield": "name" + }, + { + "field": "account_id", + "table": "llm_account", + "valuefield": "id", + "textfield": "name" + }, + { + "field": "profile_id", + "table": "llm_api_profile", + "valuefield": "id", + "textfield": "name" + }, + { + "field": "capability", + "table": "appcodes_kv", + "valuefield": "k", + "textfield": "v", + "cond": "parentid='llm_capability'" + }, + { + "field": "status", + "table": "appcodes_kv", + "valuefield": "k", + "textfield": "v", + "cond": "parentid='llm_status'" + }, + { + "field": "ppid", + "table": "pricing_program", + "valuefield": "id", + "textfield": "name" + } + ] +} diff --git a/models/llm_org_policy.json b/models/llm_org_policy.json new file mode 100644 index 0000000..cf3c43c --- /dev/null +++ b/models/llm_org_policy.json @@ -0,0 +1,97 @@ +{ + "summary": [ + { + "name": "llm_org_policy", + "title": "组织模型容错策略", + "primary": [ + "id" + ], + "catelog": "entity" + } + ], + "fields": [ + { + "name": "id", + "title": "主键ID", + "type": "str", + "length": 32, + "nullable": "no" + }, + { + "name": "org_id", + "title": "机构ID", + "type": "str", + "length": 32, + "nullable": "no" + }, + { + "name": "primary_model_id", + "title": "主模型ID", + "type": "str", + "length": 32 + }, + { + "name": "backup_model_ids", + "title": "备模型ID列表(JSON)", + "type": "text" + }, + { + "name": "endpoint_pref", + "title": "端点偏好", + "type": "str", + "length": 20, + "nullable": "no", + "default": "'any'" + }, + { + "name": "status", + "title": "状态", + "type": "str", + "length": 20, + "nullable": "no", + "default": "'active'" + }, + { + "name": "created_at", + "title": "创建时间", + "type": "timestamp", + "nullable": "no" + }, + { + "name": "updated_at", + "title": "更新时间", + "type": "timestamp" + } + ], + "indexes": [ + { + "name": "uk_llm_org_policy_org", + "idxtype": "unique", + "idxfields": [ + "org_id" + ] + } + ], + "codes": [ + { + "field": "primary_model_id", + "table": "llm_model", + "valuefield": "id", + "textfield": "name" + }, + { + "field": "endpoint_pref", + "table": "appcodes_kv", + "valuefield": "k", + "textfield": "v", + "cond": "parentid='llm_endpoint_pref'" + }, + { + "field": "status", + "table": "appcodes_kv", + "valuefield": "k", + "textfield": "v", + "cond": "parentid='llm_status'" + } + ] +} diff --git a/models/llm_org_quota.json b/models/llm_org_quota.json new file mode 100644 index 0000000..60b1e8c --- /dev/null +++ b/models/llm_org_quota.json @@ -0,0 +1,87 @@ +{ + "summary": [ + { + "name": "llm_org_quota", + "title": "组织限额限流", + "primary": [ + "id" + ], + "catelog": "entity" + } + ], + "fields": [ + { + "name": "id", + "title": "主键ID", + "type": "str", + "length": 32, + "nullable": "no" + }, + { + "name": "org_id", + "title": "机构ID", + "type": "str", + "length": 32, + "nullable": "no" + }, + { + "name": "balance", + "title": "组织池余额", + "type": "float", + "length": 14, + "dec": 4, + "default": "0" + }, + { + "name": "total_recharge", + "title": "累计充值", + "type": "float", + "length": 14, + "dec": 4, + "default": "0" + }, + { + "name": "rate_limit", + "title": "组织QPM上限", + "type": "int", + "default": "0" + }, + { + "name": "status", + "title": "状态", + "type": "str", + "length": 20, + "nullable": "no", + "default": "'active'" + }, + { + "name": "created_at", + "title": "创建时间", + "type": "timestamp", + "nullable": "no" + }, + { + "name": "updated_at", + "title": "更新时间", + "type": "timestamp" + } + ], + "indexes": [ + { + "name": "uk_llm_org_quota_org", + "idxtype": "unique", + "idxfields": [ + "org_id" + ] + } + ], + "codes": [ + { + "field": "status", + "table": "appcodes_kv", + "valuefield": "k", + "textfield": "v", + "cond": "parentid='llm_status'" + } + ] +} diff --git a/models/llm_usage.json b/models/llm_usage.json new file mode 100644 index 0000000..51fa6ce --- /dev/null +++ b/models/llm_usage.json @@ -0,0 +1,149 @@ +{ + "summary": [ + { + "name": "llm_usage", + "title": "用量流水(双维度记账)", + "primary": [ + "id" + ], + "catelog": "entity" + } + ], + "fields": [ + { + "name": "id", + "title": "主键ID", + "type": "str", + "length": 32, + "nullable": "no" + }, + { + "name": "org_id", + "title": "机构ID", + "type": "str", + "length": 32 + }, + { + "name": "user_id", + "title": "用户ID", + "type": "str", + "length": 32 + }, + { + "name": "model_id", + "title": "模型ID", + "type": "str", + "length": 32 + }, + { + "name": "account_id", + "title": "账号ID", + "type": "str", + "length": 32 + }, + { + "name": "endpoint_region", + "title": "端点区域", + "type": "str", + "length": 20 + }, + { + "name": "req_tokens", + "title": "请求token", + "type": "int", + "default": "0" + }, + { + "name": "resp_tokens", + "title": "响应token", + "type": "int", + "default": "0" + }, + { + "name": "cost", + "title": "成本金额(账号)", + "type": "float", + "length": 12, + "dec": 6, + "default": "0" + }, + { + "name": "charge", + "title": "消费金额(组织池)", + "type": "float", + "length": 12, + "dec": 6, + "default": "0" + }, + { + "name": "ppid", + "title": "定价项目ID", + "type": "str", + "length": 32 + }, + { + "name": "task_ref", + "title": "调用来源", + "type": "str", + "length": 100 + }, + { + "name": "status", + "title": "状态", + "type": "str", + "length": 20, + "nullable": "no", + "default": "'ok'" + }, + { + "name": "note", + "title": "备注/原因", + "type": "str", + "length": 200 + }, + { + "name": "created_at", + "title": "创建时间", + "type": "timestamp", + "nullable": "no" + } + ], + "indexes": [ + { + "name": "idx_llm_usage_org", + "idxtype": "index", + "idxfields": [ + "org_id", + "created_at" + ] + }, + { + "name": "idx_llm_usage_model", + "idxtype": "index", + "idxfields": [ + "model_id" + ] + } + ], + "codes": [ + { + "field": "model_id", + "table": "llm_model", + "valuefield": "id", + "textfield": "name" + }, + { + "field": "account_id", + "table": "llm_account", + "valuefield": "id", + "textfield": "name" + }, + { + "field": "status", + "table": "appcodes_kv", + "valuefield": "k", + "textfield": "v", + "cond": "parentid='llm_usage_status'" + } + ] +} diff --git a/models/llm_user_quota.json b/models/llm_user_quota.json new file mode 100644 index 0000000..53f64bf --- /dev/null +++ b/models/llm_user_quota.json @@ -0,0 +1,95 @@ +{ + "summary": [ + { + "name": "llm_user_quota", + "title": "个人限额限流", + "primary": [ + "id" + ], + "catelog": "entity" + } + ], + "fields": [ + { + "name": "id", + "title": "主键ID", + "type": "str", + "length": 32, + "nullable": "no" + }, + { + "name": "user_id", + "title": "用户ID", + "type": "str", + "length": 32, + "nullable": "no" + }, + { + "name": "org_id", + "title": "所属机构", + "type": "str", + "length": 32, + "nullable": "no" + }, + { + "name": "quota_limit", + "title": "个人额度上限", + "type": "float", + "length": 14, + "dec": 4, + "default": "0" + }, + { + "name": "quota_used", + "title": "个人已用", + "type": "float", + "length": 14, + "dec": 4, + "default": "0" + }, + { + "name": "rate_limit", + "title": "个人QPM上限", + "type": "int", + "default": "0" + }, + { + "name": "status", + "title": "状态", + "type": "str", + "length": 20, + "nullable": "no", + "default": "'active'" + }, + { + "name": "created_at", + "title": "创建时间", + "type": "timestamp", + "nullable": "no" + }, + { + "name": "updated_at", + "title": "更新时间", + "type": "timestamp" + } + ], + "indexes": [ + { + "name": "idx_llm_user_quota_user", + "idxtype": "index", + "idxfields": [ + "user_id", + "org_id" + ] + } + ], + "codes": [ + { + "field": "status", + "table": "appcodes_kv", + "valuefield": "k", + "textfield": "v", + "cond": "parentid='llm_status'" + } + ] +} diff --git a/models/llm_vendor.json b/models/llm_vendor.json new file mode 100644 index 0000000..52e4181 --- /dev/null +++ b/models/llm_vendor.json @@ -0,0 +1,98 @@ +{ + "summary": [ + { + "name": "llm_vendor", + "title": "模型供应商", + "primary": [ + "id" + ], + "catelog": "entity" + } + ], + "fields": [ + { + "name": "id", + "title": "主键ID", + "type": "str", + "length": 32, + "nullable": "no" + }, + { + "name": "name", + "title": "供应商名称", + "type": "str", + "length": 100, + "nullable": "no" + }, + { + "name": "protocol", + "title": "协议类型", + "type": "str", + "length": 20, + "nullable": "no", + "default": "'openai_compat'" + }, + { + "name": "endpoints", + "title": "端点目录(JSON)", + "type": "text" + }, + { + "name": "description", + "title": "描述", + "type": "text" + }, + { + "name": "status", + "title": "状态", + "type": "str", + "length": 20, + "nullable": "no", + "default": "'active'" + }, + { + "name": "org_id", + "title": "所属机构", + "type": "str", + "length": 32, + "nullable": "no", + "default": "'0'" + }, + { + "name": "created_at", + "title": "创建时间", + "type": "timestamp", + "nullable": "no" + }, + { + "name": "updated_at", + "title": "更新时间", + "type": "timestamp" + } + ], + "indexes": [ + { + "name": "idx_llm_vendor_status", + "idxtype": "index", + "idxfields": [ + "status" + ] + } + ], + "codes": [ + { + "field": "protocol", + "table": "appcodes_kv", + "valuefield": "k", + "textfield": "v", + "cond": "parentid='llm_protocol'" + }, + { + "field": "status", + "table": "appcodes_kv", + "valuefield": "k", + "textfield": "v", + "cond": "parentid='llm_status'" + } + ] +} diff --git a/mysql.ddl.sql b/mysql.ddl.sql new file mode 100644 index 0000000..a602a19 --- /dev/null +++ b/mysql.ddl.sql @@ -0,0 +1,133 @@ +-- pipeline-llm 模块数据表（8 张，全部 llm_ 前缀，pipeline 库） +-- 手写幂等 DDL（IF NOT EXISTS + 内联索引），由宿主 scripts/create_tables.py 执行 +-- 金额用 DECIMAL（对账精度），时间用 datetime + +CREATE TABLE IF NOT EXISTS llm_vendor ( + `id` varchar(32) NOT NULL comment '主键ID', + `name` varchar(100) NOT NULL comment '供应商名称', + `protocol` varchar(20) NOT NULL DEFAULT 'openai_compat' comment '协议类型', + `endpoints` text comment '端点目录(JSON): [{region,base_url,proxy,timeout,note}]', + `description` text comment '描述', + `status` varchar(20) NOT NULL DEFAULT 'active' comment '状态', + `org_id` varchar(32) NOT NULL DEFAULT '0' comment '所属机构', + `created_at` datetime NOT NULL DEFAULT current_timestamp() comment '创建时间', + `updated_at` datetime DEFAULT current_timestamp() ON UPDATE current_timestamp() comment '更新时间', + PRIMARY KEY (`id`), + KEY `idx_llm_vendor_status` (`status`) +) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 COLLATE=utf8mb4_unicode_ci comment='模型供应商'; + +CREATE TABLE IF NOT EXISTS llm_account ( + `id` varchar(32) NOT NULL comment '主键ID', + `vendor_id` varchar(32) NOT NULL comment '供应商ID', + `name` varchar(100) NOT NULL comment '账号名称', + `api_key` varchar(500) comment 'API密钥(AES加密)', + `endpoint_ids` text comment '选用端点索引列表(JSON)', + `balance` decimal(14,4) NOT NULL DEFAULT 0 comment '余额', + `total_recharge` decimal(14,4) NOT NULL DEFAULT 0 comment '累计充值', + `status` varchar(20) NOT NULL DEFAULT 'active' comment '状态', + `org_id` varchar(32) NOT NULL DEFAULT '0' comment '所属机构', + `created_at` datetime NOT NULL DEFAULT current_timestamp() comment '创建时间', + `updated_at` datetime DEFAULT current_timestamp() ON UPDATE current_timestamp() comment '更新时间', + PRIMARY KEY (`id`), + KEY `idx_llm_account_vendor` (`vendor_id`) +) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 COLLATE=utf8mb4_unicode_ci comment='供应商账号(钱包)'; + +CREATE TABLE IF NOT EXISTS llm_model ( + `id` varchar(32) NOT NULL comment '主键ID', + `vendor_id` varchar(32) NOT NULL comment '供应商ID', + `account_id` varchar(32) comment '默认账号ID', + `name` varchar(100) NOT NULL comment '模型注册名(平台唯一)', + `vendor_model_id` varchar(100) comment '供应商侧模型名', + `capability` varchar(20) NOT NULL DEFAULT 't2t' comment '能力类型', + `sync_mode` varchar(10) NOT NULL DEFAULT 'sync' comment '同步性', + `profile_id` varchar(32) comment '适配模板ID', + `ppid` varchar(32) comment '定价项目ID(pricing_program)', + `price_input` decimal(12,6) NOT NULL DEFAULT 0 comment '输入单价(元/千token)', + `price_output` decimal(12,6) NOT NULL DEFAULT 0 comment '输出单价(元/千token)', + `cost_input` decimal(12,6) NOT NULL DEFAULT 0 comment '输入成本(元/千token)', + `cost_output` decimal(12,6) NOT NULL DEFAULT 0 comment '输出成本(元/千token)', + `default_params` text comment '默认参数(JSON)', + `status` varchar(20) NOT NULL DEFAULT 'active' comment '状态', + `description` text comment '描述', + `org_id` varchar(32) NOT NULL DEFAULT '0' comment '所属机构', + `created_at` datetime NOT NULL DEFAULT current_timestamp() comment '创建时间', + `updated_at` datetime DEFAULT current_timestamp() ON UPDATE current_timestamp() comment '更新时间', + PRIMARY KEY (`id`), + UNIQUE KEY `uk_llm_model_name` (`name`), + KEY `idx_llm_model_vendor` (`vendor_id`) +) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 COLLATE=utf8mb4_unicode_ci comment='模型注册'; + +CREATE TABLE IF NOT EXISTS llm_api_profile ( + `id` varchar(32) NOT NULL comment '主键ID', + `name` varchar(100) NOT NULL comment '模板名称', + `protocol` varchar(20) NOT NULL comment '协议类型', + `capability` varchar(20) NOT NULL DEFAULT 't2t' comment '能力类型', + `request_template` text comment '请求模板(Jinja2)', + `response_template` text comment '响应模板(Jinja2)', + `param_schema` text comment '参数Schema(bricks input_fields)', + `status` varchar(20) NOT NULL DEFAULT 'active' comment '状态', + `created_at` datetime NOT NULL DEFAULT current_timestamp() comment '创建时间', + `updated_at` datetime DEFAULT current_timestamp() ON UPDATE current_timestamp() comment '更新时间', + PRIMARY KEY (`id`) +) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 COLLATE=utf8mb4_unicode_ci comment='适配模板(协议x能力形态去重)'; + +CREATE TABLE IF NOT EXISTS llm_org_policy ( + `id` varchar(32) NOT NULL comment '主键ID', + `org_id` varchar(32) NOT NULL comment '机构ID', + `primary_model_id` varchar(32) comment '主模型ID', + `backup_model_ids` text comment '备模型ID列表(JSON)', + `endpoint_pref` varchar(20) NOT NULL DEFAULT 'any' comment '端点偏好', + `status` varchar(20) NOT NULL DEFAULT 'active' comment '状态', + `created_at` datetime NOT NULL DEFAULT current_timestamp() comment '创建时间', + `updated_at` datetime DEFAULT current_timestamp() ON UPDATE current_timestamp() comment '更新时间', + PRIMARY KEY (`id`), + UNIQUE KEY `uk_llm_org_policy_org` (`org_id`) +) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 COLLATE=utf8mb4_unicode_ci comment='组织模型容错策略'; + +CREATE TABLE IF NOT EXISTS llm_org_quota ( + `id` varchar(32) NOT NULL comment '主键ID', + `org_id` varchar(32) NOT NULL comment '机构ID', + `balance` decimal(14,4) NOT NULL DEFAULT 0 comment '组织池余额', + `total_recharge` decimal(14,4) NOT NULL DEFAULT 0 comment '累计充值', + `rate_limit` int NOT NULL DEFAULT 0 comment '组织QPM上限(0=不限)', + `status` varchar(20) NOT NULL DEFAULT 'active' comment '状态', + `created_at` datetime NOT NULL DEFAULT current_timestamp() comment '创建时间', + `updated_at` datetime DEFAULT current_timestamp() ON UPDATE current_timestamp() comment '更新时间', + PRIMARY KEY (`id`), + UNIQUE KEY `uk_llm_org_quota_org` (`org_id`) +) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 COLLATE=utf8mb4_unicode_ci comment='组织限额限流'; + +CREATE TABLE IF NOT EXISTS llm_user_quota ( + `id` varchar(32) NOT NULL comment '主键ID', + `user_id` varchar(32) NOT NULL comment '用户ID', + `org_id` varchar(32) NOT NULL comment '所属机构', + `quota_limit` decimal(14,4) NOT NULL DEFAULT 0 comment '个人额度上限(0=不限)', + `quota_used` decimal(14,4) NOT NULL DEFAULT 0 comment '个人已用', + `rate_limit` int NOT NULL DEFAULT 0 comment '个人QPM上限(0=不限)', + `status` varchar(20) NOT NULL DEFAULT 'active' comment '状态', + `created_at` datetime NOT NULL DEFAULT current_timestamp() comment '创建时间', + `updated_at` datetime DEFAULT current_timestamp() ON UPDATE current_timestamp() comment '更新时间', + PRIMARY KEY (`id`), + KEY `idx_llm_user_quota_user` (`user_id`,`org_id`) +) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 COLLATE=utf8mb4_unicode_ci comment='个人限额限流'; + +CREATE TABLE IF NOT EXISTS llm_usage ( + `id` varchar(32) NOT NULL comment '主键ID', + `org_id` varchar(32) comment '机构ID', + `user_id` varchar(32) comment '用户ID', + `model_id` varchar(32) comment '模型ID', + `account_id` varchar(32) comment '账号ID', + `endpoint_region` varchar(20) comment '端点区域', + `req_tokens` int NOT NULL DEFAULT 0 comment '请求token', + `resp_tokens` int NOT NULL DEFAULT 0 comment '响应token', + `cost` decimal(12,6) NOT NULL DEFAULT 0 comment '成本金额(账号侧)', + `charge` decimal(12,6) NOT NULL DEFAULT 0 comment '消费金额(组织池侧)', + `ppid` varchar(32) comment '定价项目ID', + `task_ref` varchar(100) comment '调用来源', + `status` varchar(20) NOT NULL DEFAULT 'ok' comment '状态(ok/failed/recharge)', + `note` varchar(200) comment '备注/原因', + `created_at` datetime NOT NULL DEFAULT current_timestamp() comment '创建时间', + PRIMARY KEY (`id`), + KEY `idx_llm_usage_org` (`org_id`,`created_at`), + KEY `idx_llm_usage_model` (`model_id`) +) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 COLLATE=utf8mb4_unicode_ci comment='用量流水(双维度记账)'; diff --git a/pipeline_llm/__init__.py b/pipeline_llm/__init__.py new file mode 100644 index 0000000..ce6bb69 --- /dev/null +++ b/pipeline_llm/__init__.py @@ -0,0 +1 @@ +from .init import load_llm diff --git a/pipeline_llm/gateway.py b/pipeline_llm/gateway.py new file mode 100644 index 0000000..d85f81b --- /dev/null +++ b/pipeline_llm/gateway.py @@ -0,0 +1,653 @@ +"""pipeline_llm.gateway — 模型治理引擎：门禁链 + 主备容错 + 账号端点轮转 + 双维度记账。 + +调用链（与设计规范 §2 一致）： + ① 个人限流窗口 → ② 组织限流窗口 + → ③ 个人额度余额 → ④ 组织池余额（预授权冻结） + → ⑤ 组织容错策略选模型（主→备） + → ⑥ 账号×端点候选池：区域偏好过滤 → 余额加权轮转 + 限流冷却避让 + → ⑦ 调用（调用方执行）→ ⑧ govern_settle 结算（实际用量，双维度记账） + +集成方式（复用不改建）： + - llm_bridge._get_model_config 前置调 govern_resolve：机构配了策略/新模型表才走治理， + 否则返回 None 由旧 llm 表逻辑兜底（向后兼容）。 + - proxy_chat_completion（运行环境 token 路径）拿到真实 usage 后调 govern_settle 精算。 + - llm_bridge 内部路径按 prompt/response 长度估算 token 调 govern_settle（note='est'）。 + +限流：Redis 分钟窗口原子计数（db4，与会话 db3 隔离）。Redis 不可用时限流放行（fail-open， +记 warning）——限流失效不应阻断业务，余额检查仍在 DB 侧守住。 +余额：读-校验-条件 UPDATE（WHERE balance>=amount），并发竞态由 Redis 预授权计数托底。 + +错误必须真实可行动（用户铁律）：每一级失败返回明确的中文原因，前端原样展示。 +""" + +import json +import logging +import time + +logger = logging.getLogger("pipeline_llm.gateway") + +DBNAME = "pipeline" +GOVERN_REDIS_DB = 4 # 治理计数器命名空间（会话用 db3，互不干扰） +_COOLDOWN_SEC = 60 # 429 冷却窗口 +_EST_TOKENS_PER_CALL = 800 # 无法估算时的单次调用预估（预授权用） + +# 治理开关缓存：机构是否启用治理（有策略记录或有 llm_model 记录） +_govern_cache: dict = {} +_cfg_cache: dict = {} # (account_id) -> {api_key 解密, base_url...} + + +# ────────────────────────── 基础设施 ────────────────────────── + +def _get_db(): + from sqlor.dbpools import DBPools + db = DBPools() + if not db.databases: + from appPublic.jsonConfig import getConfig + config = getConfig() + if config.databases: + db.databases = config.databases + return db, DBNAME + + +def _password_key(): + from appPublic.jsonConfig import getConfig + try: + return getConfig().password_key or 'QRIVSRHrthhwyjy176556332' + except Exception: + return 'QRIVSRHrthhwyjy176556332' + + +def encrypt_api_key(plain: str) -> str: + """AES 单层加密（对称可解密）。⚠️ 不用 RC4：password/unpassword 盐不对称，加密后不可解。""" + if not plain: + return '' + from appPublic.aes import aes_encode_b64 + return aes_encode_b64(_password_key(), plain) + + +def decrypt_api_key(enc: str) -> str: + """解密 api_key。非密文（历史明文/环境差异）原样返回。""" + if not enc: + return '' + try: + from appPublic.aes import aes_decode_b64 + return aes_decode_b64(_password_key(), enc) + except Exception: + return enc + + +def _redis(): + """治理用 Redis 连接（db4）。从 session_redis 配置推导地址，不可用返回 None。""" + try: + import redis as _r + from appPublic.jsonConfig import getConfig + url = '' + try: + url = (getConfig().website or {}).get('session_redis', {}).get('url', '') + except Exception: + url = '' + if not url: + url = 'redis://127.0.0.1:6379/3' + # 替换库号：会话用配置的库，治理固定 GOVERN_REDIS_DB + base = url.rsplit('/', 1)[0] + return _r.Redis.from_url(base + '/' + str(GOVERN_REDIS_DB), socket_timeout=2) + except Exception as e: + logger.warning("pipeline_llm: redis 不可用（限流降级放行）: %s", e) + return None + + +def _row_to_dict(r): + try: + return {k: v for k, v in vars(r).items() if not callable(v)} + except TypeError: + return dict(r) + + +def _parse_json(s, default): + if not s: + return default + try: + v = json.loads(s) + return v if v is not None else default + except Exception: + return default + + +def _fnum(v): + try: + return float(v or 0) + except (TypeError, ValueError): + return 0.0 + + +# ────────────────────────── 门禁 ①②：限流 ────────────────────────── + +async def _rate_check(scope: str, scope_id: str, limit: int): + """分钟窗口限流。返回 (ok, msg)。limit<=0 不限；Redis 故障放行。""" + if not limit or limit <= 0 or not scope_id: + return True, '' + r = _redis() + if r is None: + return True, '' + minute = int(time.time() // 60) + key = 'llm_rl:%s:%s:%d' % (scope, scope_id, minute) + try: + cnt = r.incr(key) + r.expire(key, 70) + except Exception as e: + logger.warning("pipeline_llm: 限流计数失败（放行）: %s", e) + return True, '' + if cnt > limit: + label = '个人' if scope == 'user' else '组织' + return False, '%s限流：本分钟已调用 %d 次（上限 %d），请下一分钟再试' % (label, cnt, limit) + return True, '' + + +# ────────────────────────── 门禁 ③④：额度检查 + 预授权 ────────────────────────── + +async def _reserve_quota(sor, org_id: str, user_id: str, amount: float): + """预授权：组织池 + 个人额度扣减。返回 (ok, msg, 实际冻结金额)。 + + 条件 UPDATE 防超扣；个人不足先回滚组织侧。0 元调用（未定价模型）不冻结。 + """ + if amount <= 0: + return True, '', 0.0 + # 组织池 + recs = await sor.sqlExe( + "SELECT id, balance FROM llm_org_quota WHERE org_id=${o}$ AND status='active' LIMIT 1", + {"o": org_id}) + await sor.sqlExe("COMMIT", {}) + org_quota_id = '' + if recs: + if _fnum(getattr(recs[0], 'balance', 0)) < amount: + return False, '组织余额不足：当前余额 %.4f，本次预扣 %.4f。请充值组织池（模型治理→组织限额限流）' % ( + _fnum(getattr(recs[0], 'balance', 0)), amount), 0.0 + org_quota_id = getattr(recs[0], 'id', '') + await sor.sqlExe( + "UPDATE llm_org_quota SET balance=balance-${a}$ WHERE id=${i}$ AND balance>=${a}$", + {"a": amount, "i": org_quota_id}) + await sor.sqlExe("COMMIT", {}) + # 个人额度（有记录才校验；共享池+个人上限模式） + if user_id: + recs = await sor.sqlExe( + "SELECT id, quota_limit, quota_used FROM llm_user_quota " + "WHERE user_id=${u}$ AND org_id=${o}$ AND status='active' LIMIT 1", + {"u": user_id, "o": org_id}) + await sor.sqlExe("COMMIT", {}) + if recs: + lim = _fnum(getattr(recs[0], 'quota_limit', 0)) + used = _fnum(getattr(recs[0], 'quota_used', 0)) + if lim > 0 and used + amount > lim: + if org_quota_id: # 回滚组织侧 + await sor.sqlExe( + "UPDATE llm_org_quota SET balance=balance+${a}$ WHERE id=${i}$", + {"a": amount, "i": org_quota_id}) + await sor.sqlExe("COMMIT", {}) + return False, '个人额度不足：已用 %.4f / 上限 %.4f，本次需 %.4f。请联系管理员调高个人额度' % ( + used, lim, amount), 0.0 + await sor.sqlExe( + "UPDATE llm_user_quota SET quota_used=quota_used+${a}$ WHERE id=${i}$", + {"a": amount, "i": getattr(recs[0], 'id', '')}) + await sor.sqlExe("COMMIT", {}) + return True, '', amount + + +async def _release_quota(sor, org_id: str, user_id: str, amount: float): + """释放预授权（调用失败时）。""" + if amount <= 0: + return + await sor.sqlExe( + "UPDATE llm_org_quota SET balance=balance+${a}$ WHERE org_id=${o}$ AND status='active'", + {"a": amount, "o": org_id}) + if user_id: + await sor.sqlExe( + "UPDATE llm_user_quota SET quota_used=GREATEST(quota_used-${a}$,0) " + "WHERE user_id=${u}$ AND org_id=${o}$", + {"a": amount, "u": user_id, "o": org_id}) + await sor.sqlExe("COMMIT", {}) + + +# ────────────────────────── 门禁 ⑤⑥：策略选模型 + 候选轮转 ────────────────────────── + +async def _org_policy(sor, org_id: str): + """组织容错策略。无记录返回 (主模型空, 备链空, 端点偏好 any)。""" + if not org_id: + return '', [], 'any' + recs = await sor.sqlExe( + "SELECT primary_model_id, backup_model_ids, endpoint_pref FROM llm_org_policy " + "WHERE org_id=${o}$ AND status='active' LIMIT 1", {"o": org_id}) + await sor.sqlExe("COMMIT", {}) + if not recs: + return '', [], 'any' + r = recs[0] + return (getattr(r, 'primary_model_id', '') or '', + _parse_json(getattr(r, 'backup_model_ids', ''), []), + getattr(r, 'endpoint_pref', '') or 'any') + + +async def _model_chain(sor, org_id: str, model_name: str): + """解析模型链 [主, 备...]，返回 llm_model 记录 dict 列表。 + + - 调用方指定 model_name：在 llm_model 找到 → [它] + 策略备链补充；找不到 → 空（走旧表兜底） + - 未指定：策略主模型 + 备链；无策略 → 空 + """ + chain_ids = [] + primary, backups, pref = await _org_policy(sor, org_id) + if model_name: + recs = await sor.sqlExe( + "SELECT id FROM llm_model WHERE status='active' AND (name=${n}$ OR vendor_model_id=${n}$) LIMIT 1", + {"n": model_name}) + await sor.sqlExe("COMMIT", {}) + if not recs: + return [], pref + chain_ids.append(getattr(recs[0], 'id', '')) + chain_ids.extend([b for b in backups if b not in chain_ids]) + else: + if primary: + chain_ids.append(primary) + chain_ids.extend([b for b in backups if b not in chain_ids]) + if not chain_ids: + return [], pref + models = [] + for mid in chain_ids: + recs = await sor.sqlExe( + "SELECT id, name, vendor_id, vendor_model_id, capability, default_params, " + "price_input, price_output, cost_input, cost_output, ppid, org_id " + "FROM llm_model WHERE id=${i}$ AND status='active' LIMIT 1", {"i": mid}) + await sor.sqlExe("COMMIT", {}) + if recs: + models.append(_row_to_dict(recs[0])) + return models, pref + + +async def _vendor_endpoints(sor, vendor_id: str): + """供应商端点目录。返回 (protocol, [endpoint dict])。""" + recs = await sor.sqlExe( + "SELECT protocol, endpoints FROM llm_vendor WHERE id=${i}$ AND status='active' LIMIT 1", + {"i": vendor_id}) + await sor.sqlExe("COMMIT", {}) + if not recs: + return '', [] + r = recs[0] + return getattr(r, 'protocol', '') or '', _parse_json(getattr(r, 'endpoints', ''), []) + + +async def _account_candidates(sor, model: dict): + """模型的候选账号池：同供应商、启用中。""" + recs = await sor.sqlExe( + "SELECT id, name, api_key, endpoint_ids, balance, status FROM llm_account " + "WHERE vendor_id=${v}$ AND status='active'", {"v": model.get('vendor_id', '')}) + await sor.sqlExe("COMMIT", {}) + return [_row_to_dict(r) for r in (recs or [])] + + +def _filter_by_pref(candidates_with_ep, pref: str): + """按端点偏好过滤/排序候选 (account, endpoint, idx) 列表。 + + must_*：只保留匹配区域，空则返回空（宁可冒泡不跨端点）。 + prefer_*：匹配区域排前。any：原序。 + """ + if pref in ('must_domestic', 'prefer_domestic'): + want = 'domestic' + elif pref in ('must_intl', 'prefer_intl'): + want = 'international' + else: + return candidates_with_ep + matched = [c for c in candidates_with_ep if (c[1].get('region') or '') == want] + if pref.startswith('must'): + return matched + rest = [c for c in candidates_with_ep if (c[1].get('region') or '') != want] + return matched + rest + + +async def _pick_candidate(sor, model: dict, pref: str): + """构建候选并选一个：区域偏好过滤 → 冷却避让 → 余额加权。 + + 返回 (ok, result)：ok 时 result=(account_dict, endpoint_dict)；否则 result=错误信息。 + """ + vendor_id = model.get('vendor_id', '') + if not vendor_id: + return False, '模型「%s」未绑定供应商，无法选择账号' % model.get('name', '') + protocol, endpoints = await _vendor_endpoints(sor, vendor_id) + if not endpoints: + return False, '供应商端点目录为空（模型治理→供应商→端点目录），请配置端点' + accounts = await _account_candidates(sor, model) + if not accounts: + return False, '模型「%s」的供应商下无启用账号（或账号余额状态异常）' % model.get('name', '') + # 展开 (账号, 端点) 对：账号选用的端点下标 + pairs = [] + for acc in accounts: + idxs = _parse_json(acc.get('endpoint_ids'), []) + if not idxs: + continue + for i in idxs: + try: + i = int(i) + except (TypeError, ValueError): + continue + if 0 <= i < len(endpoints): + pairs.append((acc, endpoints[i], i)) + if not pairs: + return False, '所有账号都未选用端点（模型治理→供应商账号→选用端点），请配置' + pairs = _filter_by_pref(pairs, pref) + if not pairs: + return False, ('端点偏好为「仅 %s」，但没有可用的该区域端点。按合规要求不跨端点降级——' + '请配置该区域端点或调整组织策略的端点偏好' % + ('国内' if 'domestic' in pref else '国际')) + # 冷却避让 + 余额加权选择 + r = _redis() + best, best_score = None, -1.0 + for acc, ep, i in pairs: + cool_key = 'llm_cool:%s:%d' % (acc.get('id', ''), i) + acct_key = 'llm_cool:%s:*' % (acc.get('id', ''),) + try: + if r is not None and (r.get(cool_key) or r.get(acct_key)): + continue # 限流冷却中（端点级或账号级） + except Exception: + pass + score = _fnum(acc.get('balance')) + if score > best_score: + best, best_score = (acc, ep, i), score + if best is None: + return False, '模型「%s」的全部候选（账号×端点）都在限流冷却中，请稍后重试' % model.get('name', '') + acc, ep, i = best + if _fnum(acc.get('balance')) <= 0: + return False, '模型「%s」的候选账号余额均不足，请为账号充值' % model.get('name', '') + return True, (acc, ep) + + +def _mark_cooldown(account_id: str, ep_index): + """429 后把该账号（或账号×端点对）放进冷却。ep_index='*' 表示账号级。""" + r = _redis() + if r is None: + return + try: + r.set('llm_cool:%s:%s' % (account_id, ep_index), '1', ex=_COOLDOWN_SEC) + except Exception: + pass + + +def mark_cooldown_by_pair(account_id: str, base_url: str): + """供代理层 429 回调：按 base_url 找到端点下标进冷却（找不到则全部下标冷却）。""" + try: + # 代理层只拿得到 base_url；冷却键按下标，这里无法反查下标—— + # 退化为账号级冷却（该账号所有端点），宁可保守 + _mark_cooldown(account_id, '*') + except Exception: + pass + + +# ────────────────────────── 对外主入口 ────────────────────────── + +class GovernError(ValueError): + """治理失败：消息真实可行动，前端原样展示。""" + + +async def governance_enabled(sor, org_id: str) -> bool: + """机构是否启用治理：**策略即开关**——该机构有 active 的容错策略才启用。 + + ⚠️ 不能用"新模型表有记录"判断（2026-09-01 修正）：系统级（org_id=0）模型 + 注册后会让所有未配策略的机构被误判为启用，调用直接报错，断掉旧 llm 表链路。 + 机构显式建策略才是接入治理的动作；无策略 → 一切照旧（__LEGACY__）。 + 带缓存（改配置需重启，与 key 缓存一致）。 + """ + if not org_id: + return False + if org_id in _govern_cache: + return _govern_cache[org_id] + enabled = False + try: + recs = await sor.sqlExe( + "SELECT COUNT(*) AS c FROM llm_org_policy WHERE org_id=${o}$ AND status='active'", + {"o": org_id}) + await sor.sqlExe("COMMIT", {}) + enabled = (int(getattr(recs[0], 'c', 0)) if recs else 0) > 0 + except Exception as e: + logger.warning("pipeline_llm: governance_enabled 检查失败（按未启用）: %s", e) + enabled = False + _govern_cache[org_id] = enabled + return enabled + + +async def govern_resolve(org_id: str, user_id: str = '', model_name: str = '', + est_tokens: int = 0, task_ref: str = ''): + """门禁链 ①-⑥ + 预授权。 + + 返回 (ok, result)： + ok=True → result = {api_base, api_key(明文,仅进程内), model_id, name, + account_id, endpoint_region, reserved(冻结金额), + model_row(定价信息), user_id, org_id, task_ref} + ok=False → result = 错误信息（真实可行动） + 机构未启用治理 → (False, '__LEGACY__') 特殊标记：调用方走旧 llm 表逻辑 + """ + db, dbname = _get_db() + async with db.sqlorContext(dbname) as sor: + if not await governance_enabled(sor, org_id or ''): + return False, '__LEGACY__' + # ① 个人限流 + if user_id: + recs = await sor.sqlExe( + "SELECT rate_limit FROM llm_user_quota WHERE user_id=${u}$ AND org_id=${o}$ " + "AND status='active' LIMIT 1", {"u": user_id, "o": org_id}) + await sor.sqlExe("COMMIT", {}) + ulimit = int(_fnum(getattr(recs[0], 'rate_limit', 0))) if recs else 0 + ok, msg = await _rate_check('user', user_id, ulimit) + if not ok: + return False, msg + # ② 组织限流 + recs = await sor.sqlExe( + "SELECT rate_limit FROM llm_org_quota WHERE org_id=${o}$ AND status='active' LIMIT 1", + {"o": org_id}) + await sor.sqlExe("COMMIT", {}) + olimit = int(_fnum(getattr(recs[0], 'rate_limit', 0))) if recs else 0 + ok, msg = await _rate_check('org', org_id, olimit) + if not ok: + return False, msg + # ⑤ 模型链（含 ⑥ 偏好） + models, pref = await _model_chain(sor, org_id or '', model_name or '') + if not models: + if model_name: + return False, '__LEGACY__' # 指定模型不在新表 → 旧表兜底 + return False, ('机构未配置模型容错策略且未指定模型：请在模型治理→组织容错策略配置主/备模型，' + '或在调用时指定模型名') + # ⑥ 逐模型尝试（主 → 备容错） + last_err = '' + chosen = None + for m in models: + ok, cand = await _pick_candidate(sor, m, pref) + if ok and isinstance(cand, tuple): + chosen = (m, cand) + break + last_err = cand if isinstance(cand, str) else last_err + logger.info("pipeline_llm: 模型 %s 候选不可用（%s），尝试备模型", m.get('name'), cand) + if chosen is None: + return False, '主/备模型全部不可用。最后原因：%s' % last_err + model, chosen_pair = chosen + acc, ep = chosen_pair + # ③④ 预授权（按预估用量冻结组织池+个人额度） + price_in = _fnum(model.get('price_input')) + price_out = _fnum(model.get('price_output')) + est = int(est_tokens or 0) or _EST_TOKENS_PER_CALL + est_charge = est / 1000.0 * (price_in + price_out) / 2.0 + ok, msg, reserved = await _reserve_quota(sor, org_id or '', user_id or '', est_charge) + if not ok: + return False, msg + # 组装结果（api_key 解密，只在本进程内存） + return True, { + 'api_base': (ep.get('base_url') or '').rstrip('/'), + 'api_key': decrypt_api_key(acc.get('api_key') or ''), + 'model_id': model.get('vendor_model_id') or model.get('name', ''), + 'name': model.get('name', ''), + 'account_id': acc.get('id', ''), + 'endpoint_region': ep.get('region') or '', + 'endpoint_proxy': ep.get('proxy') or '', + 'timeout': int(_fnum(ep.get('timeout')) or 60), + 'reserved': reserved, + 'model_row': model, + 'user_id': user_id or '', + 'org_id': org_id or '', + 'task_ref': task_ref or '', + } + + +async def govern_settle(ctx: dict, ok_call: bool, req_tokens: int = 0, resp_tokens: int = 0, + note: str = ''): + """结算 ⑧：按实际用量修正预授权 + 双维度记账。 + + ctx govern_resolve 成功时返回的 dict + ok_call 上游调用是否成功（失败也记账：释放预授权，写 failed 流水） + """ + if not ctx or not isinstance(ctx, dict): + return + db, dbname = _get_db() + try: + model = ctx.get('model_row') or {} + price_in = _fnum(model.get('price_input')) + price_out = _fnum(model.get('price_output')) + cost_in = _fnum(model.get('cost_input')) + cost_out = _fnum(model.get('cost_output')) + charge = req_tokens / 1000.0 * price_in + resp_tokens / 1000.0 * price_out + cost = req_tokens / 1000.0 * cost_in + resp_tokens / 1000.0 * cost_out + reserved = _fnum(ctx.get('reserved')) + async with db.sqlorContext(dbname) as sor: + if not ok_call: + # 上游限流(429)失败 → 账号级冷却，轮转避让下一轮不再选它 + if '429' in str(note or ''): + _mark_cooldown(ctx.get('account_id', ''), '*') + await _release_quota(sor, ctx.get('org_id', ''), ctx.get('user_id', ''), reserved) + else: + # 多退少补：实际消费 vs 预授权 + diff = charge - reserved + if diff > 0: + await sor.sqlExe( + "UPDATE llm_org_quota SET balance=balance-${d}$ " + "WHERE org_id=${o}$ AND status='active'", + {"d": diff, "o": ctx.get('org_id', '')}) + elif diff < 0: + await sor.sqlExe( + "UPDATE llm_org_quota SET balance=balance+${d}$ " + "WHERE org_id=${o}$ AND status='active'", + {"d": -diff, "o": ctx.get('org_id', '')}) + # 个人额度按实际修正（预授权按估算扣了，退还差额） + if ctx.get('user_id') and diff < 0: + await sor.sqlExe( + "UPDATE llm_user_quota SET quota_used=GREATEST(quota_used-${d}$,0) " + "WHERE user_id=${u}$ AND org_id=${o}$", + {"d": -diff, "u": ctx.get('user_id', ''), "o": ctx.get('org_id', '')}) + await sor.sqlExe("COMMIT", {}) + # 成本侧：账号余额扣减 + if ctx.get('account_id') and cost > 0: + await sor.sqlExe( + "UPDATE llm_account SET balance=balance-${c}$ WHERE id=${i}$", + {"c": cost, "i": ctx.get('account_id', '')}) + await sor.sqlExe("COMMIT", {}) + # 双维度流水 + from appPublic.uniqueID import getID + await sor.C('llm_usage', { + 'id': getID(), + 'org_id': ctx.get('org_id', ''), + 'user_id': ctx.get('user_id', ''), + 'model_id': model.get('id', ''), + 'account_id': ctx.get('account_id', ''), + 'endpoint_region': ctx.get('endpoint_region', ''), + 'req_tokens': int(req_tokens or 0), + 'resp_tokens': int(resp_tokens or 0), + 'cost': round(cost, 6), + 'charge': round(charge, 6), + 'ppid': model.get('ppid', '') or '', + 'task_ref': ctx.get('task_ref', ''), + 'status': 'ok' if ok_call else 'failed', + 'note': (note or '')[:200], + }) + await sor.sqlExe("COMMIT", {}) + except Exception as e: + logger.warning("pipeline_llm: 结算失败（不阻断调用方）: %s", e) + + +# ────────────────────────── 充值 ────────────────────────── + +async def recharge_account(account_id: str, amount, note: str = '', operator: str = ''): + """供应商账号充值（成本侧钱包）。返回 (ok, msg)。""" + try: + amount = float(amount) + except (TypeError, ValueError): + return False, '充值金额必须是数字' + if amount <= 0: + return False, '充值金额必须大于 0' + db, dbname = _get_db() + async with db.sqlorContext(dbname) as sor: + recs = await sor.sqlExe("SELECT id FROM llm_account WHERE id=${i}$", {"i": account_id}) + await sor.sqlExe("COMMIT", {}) + if not recs: + return False, '账号不存在' + await sor.sqlExe( + "UPDATE llm_account SET balance=balance+${a}$, total_recharge=total_recharge+${a}$ " + "WHERE id=${i}$", {"a": amount, "i": account_id}) + await sor.sqlExe("COMMIT", {}) + await _write_recharge_usage(sor, '', '', account_id, amount, note, operator) + _govern_cache.clear() + return True, '账号充值 %.4f 成功' % amount + + +async def recharge_org(org_id: str, amount, note: str = '', operator: str = ''): + """组织池充值（消费侧钱包）。无记录自动创建。返回 (ok, msg)。""" + try: + amount = float(amount) + except (TypeError, ValueError): + return False, '充值金额必须是数字' + if amount <= 0: + return False, '充值金额必须大于 0' + if not org_id: + return False, '缺少机构 ID' + db, dbname = _get_db() + async with db.sqlorContext(dbname) as sor: + recs = await sor.sqlExe("SELECT id FROM llm_org_quota WHERE org_id=${o}$", {"o": org_id}) + await sor.sqlExe("COMMIT", {}) + if recs: + await sor.sqlExe( + "UPDATE llm_org_quota SET balance=balance+${a}$, total_recharge=total_recharge+${a}$ " + "WHERE org_id=${o}$", {"a": amount, "o": org_id}) + else: + from appPublic.uniqueID import getID + await sor.C('llm_org_quota', { + 'id': getID(), 'org_id': org_id, + 'balance': amount, 'total_recharge': amount, + 'rate_limit': 0, 'status': 'active'}) + await sor.sqlExe("COMMIT", {}) + await _write_recharge_usage(sor, org_id, '', '', amount, note, operator) + _govern_cache.clear() + return True, '组织池充值 %.4f 成功' % amount + + +async def _write_recharge_usage(sor, org_id, user_id, account_id, amount, note, operator): + """充值流水（llm_usage 里 status=recharge 的行，对账用）。""" + from appPublic.uniqueID import getID + await sor.C('llm_usage', { + 'id': getID(), + 'org_id': org_id or '', + 'user_id': user_id or '', + 'model_id': '', + 'account_id': account_id or '', + 'endpoint_region': '', + 'req_tokens': 0, + 'resp_tokens': 0, + 'cost': round(float(amount), 6) if account_id else 0, + 'charge': round(float(amount), 6) if org_id else 0, + 'ppid': '', + 'task_ref': 'recharge', + 'status': 'recharge', + 'note': ((note or '') + (' | 操作人:%s' % operator if operator else ''))[:200], + }) + await sor.sqlExe("COMMIT", {}) + + +def load_gateway(): + """注册治理函数到 ServerEnv（供 dspy/其他模块调用）。""" + from ahserver.serverenv import ServerEnv + env = ServerEnv() + env.llm_govern_resolve = govern_resolve + env.llm_govern_settle = govern_settle + env.llm_recharge_account = recharge_account + env.llm_recharge_org = recharge_org + env.llm_encrypt_api_key = encrypt_api_key + logger.info("[pipeline_llm] gateway loaded") diff --git a/pipeline_llm/init.py b/pipeline_llm/init.py new file mode 100644 index 0000000..4ea8b25 --- /dev/null +++ b/pipeline_llm/init.py @@ -0,0 +1,455 @@ +"""pipeline_llm 模块入口 — 模型治理（供应商/账号/模型/组织策略/限额限流/记账）。 + +宿主集成：应用入口调用 load_llm()（try/except ImportError 兜底）。 +所有表共享宿主应用的库（get_module_dbname('pipeline_llm')），表名统一 llm_ 前缀。 + +模块只提供治理引擎与配置管理；实际 LLM 转发仍由宿主已有的 +pipeline_service.llm_bridge / llm_proxy 承担——本模块在两个调用链上挂钩子： + - llm_bridge._get_model_config：治理启用时前置解析（主备容错+端点选择） + - llm_proxy.proxy_chat_completion：调用前后接门禁与结算（运行环境路径） +""" + +import json +import logging + +from sqlor.dbpools import DBPools +from ahserver.serverenv import ServerEnv +from appPublic.uniqueID import getID + +from .gateway import ( + govern_resolve, govern_settle, governance_enabled, + recharge_account, recharge_org, + encrypt_api_key, decrypt_api_key, load_gateway, GovernError, +) + +logger = logging.getLogger("pipeline_llm") + +MODULE_NAME = 'pipeline_llm' + + +def _dbname(): + """动态取宿主库名（禁硬编码）。未注册 get_module_dbname 时回落 pipeline。""" + env = ServerEnv() + fn = getattr(env, 'get_module_dbname', None) + if callable(fn): + try: + return fn(MODULE_NAME) or 'pipeline' + except Exception: + pass + return 'pipeline' + + +def _get_sor(): + return DBPools(), _dbname() + + +# ────────────────────── CRUD（供生成的 CRUD 页面调用） ────────────────────── + +def _clean(params_kw): + data = dict(params_kw or {}) + for k in ('page', 'rows', 'data_filter', 'sortby'): + data.pop(k, None) + return data + + +async def create_llm_vendor(params_kw): + result = {'success': False, 'message': ''} + try: + data = _clean(params_kw) + endpoints = data.get('endpoints', '') or '' + if isinstance(endpoints, (list, dict)): + endpoints = json.dumps(endpoints, ensure_ascii=False) + if endpoints.strip(): + eps = json.loads(endpoints) + if not isinstance(eps, list): + raise ValueError('endpoints 必须是 JSON 数组') + for i, ep in enumerate(eps): + if not isinstance(ep, dict) or not (ep.get('base_url') or '').strip(): + raise ValueError('端点 #%d 缺少 base_url' % (i + 1)) + data['endpoints'] = endpoints + data['id'] = getID() + db, dbname = _get_sor() + async with db.sqlorContext(dbname) as sor: + await sor.C('llm_vendor', data) + result['success'] = True + result['message'] = '创建成功' + except Exception as e: + result['message'] = str(e) + return json.dumps(result, ensure_ascii=False, default=str) + + +async def update_llm_vendor(params_kw): + result = {'success': False, 'message': ''} + try: + data = _clean(params_kw) + if 'endpoints' in data: + endpoints = data.get('endpoints', '') or '' + if isinstance(endpoints, (list, dict)): + endpoints = json.dumps(endpoints, ensure_ascii=False) + if endpoints.strip(): + eps = json.loads(endpoints) + if not isinstance(eps, list): + raise ValueError('endpoints 必须是 JSON 数组') + for i, ep in enumerate(eps): + if not isinstance(ep, dict) or not (ep.get('base_url') or '').strip(): + raise ValueError('端点 #%d 缺少 base_url' % (i + 1)) + data['endpoints'] = endpoints + db, dbname = _get_sor() + async with db.sqlorContext(dbname) as sor: + await sor.U('llm_vendor', data) + result['success'] = True + result['message'] = '更新成功' + except Exception as e: + result['message'] = str(e) + return json.dumps(result, ensure_ascii=False, default=str) + + +async def delete_llm_vendor(params_kw): + """供应商删除前置检查：有账号/模型引用时禁止（防孤儿）。""" + result = {'success': False, 'message': ''} + try: + vid = (params_kw or {}).get('id', '') + if not vid: + raise ValueError('缺少 id') + db, dbname = _get_sor() + async with db.sqlorContext(dbname) as sor: + recs = await sor.sqlExe( + "SELECT (SELECT COUNT(*) FROM llm_account WHERE vendor_id=${v}$) + " + "(SELECT COUNT(*) FROM llm_model WHERE vendor_id=${v}$) AS c", {"v": vid}) + await sor.sqlExe("COMMIT", {}) + cnt = int(getattr(recs[0], 'c', 0)) if recs else 0 + if cnt > 0: + raise ValueError('该供应商下还有 %d 个账号/模型，请先移除后再删除' % cnt) + await sor.sqlExe("DELETE FROM llm_vendor WHERE id=${v}$", {"v": vid}) + await sor.sqlExe("COMMIT", {}) + result['success'] = True + result['message'] = '删除成功' + except Exception as e: + result['message'] = str(e) + return json.dumps(result, ensure_ascii=False, default=str) + + +async def create_llm_account(params_kw): + """账号创建：api_key 自动 AES 加密；校验端点下标合法。""" + result = {'success': False, 'message': ''} + try: + data = _clean(params_kw) + vid = data.get('vendor_id', '') + if not vid: + raise ValueError('必须选择供应商') + # api_key 加密存储 + if data.get('api_key'): + data['api_key'] = encrypt_api_key(data['api_key']) + # 端点下标校验 + idxs_raw = data.get('endpoint_ids', '') or '' + if isinstance(idxs_raw, (list, dict)): + idxs_raw = json.dumps(idxs_raw, ensure_ascii=False) + idxs = [] + if idxs_raw.strip(): + idxs = json.loads(idxs_raw) + if not isinstance(idxs, list): + raise ValueError('endpoint_ids 必须是 JSON 数组') + db, dbname = _get_sor() + async with db.sqlorContext(dbname) as sor: + recs = await sor.sqlExe("SELECT endpoints FROM llm_vendor WHERE id=${v}$", {"v": vid}) + await sor.sqlExe("COMMIT", {}) + if not recs: + raise ValueError('供应商不存在') + eps = [] + try: + eps = json.loads(getattr(recs[0], 'endpoints', '') or '') or [] + except Exception: + eps = [] + for i in idxs: + if not isinstance(i, int) and not (isinstance(i, str) and i.isdigit()): + raise ValueError('endpoint_ids 元素必须是端点下标（数字）') + if int(i) < 0 or int(i) >= len(eps): + raise ValueError('端点下标 %s 超出供应商端点目录（共 %d 个端点）' % (i, len(eps))) + data['endpoint_ids'] = json.dumps([int(i) for i in idxs], ensure_ascii=False) if idxs else '' + data['id'] = getID() + async with db.sqlorContext(dbname) as sor: + await sor.C('llm_account', data) + result['success'] = True + result['message'] = '创建成功' + except Exception as e: + result['message'] = str(e) + return json.dumps(result, ensure_ascii=False, default=str) + + +async def update_llm_account(params_kw): + """账号更新：api_key 非空才重新加密（空=不改）。""" + result = {'success': False, 'message': ''} + try: + data = _clean(params_kw) + if data.get('api_key'): + data['api_key'] = encrypt_api_key(data['api_key']) + else: + data.pop('api_key', None) + if 'endpoint_ids' in data: + idxs_raw = data.get('endpoint_ids', '') or '' + if isinstance(idxs_raw, (list, dict)): + idxs_raw = json.dumps(idxs_raw, ensure_ascii=False) + idxs = [] + if idxs_raw.strip(): + idxs = json.loads(idxs_raw) + if not isinstance(idxs, list): + raise ValueError('endpoint_ids 必须是 JSON 数组') + data['endpoint_ids'] = json.dumps([int(i) for i in idxs], ensure_ascii=False) if idxs else '' + db, dbname = _get_sor() + async with db.sqlorContext(dbname) as sor: + await sor.U('llm_account', data) + result['success'] = True + result['message'] = '更新成功' + except Exception as e: + result['message'] = str(e) + return json.dumps(result, ensure_ascii=False, default=str) + + +async def delete_llm_account(params_kw): + result = {'success': False, 'message': ''} + try: + aid = (params_kw or {}).get('id', '') + if not aid: + raise ValueError('缺少 id') + db, dbname = _get_sor() + async with db.sqlorContext(dbname) as sor: + recs = await sor.sqlExe( + "SELECT COUNT(*) AS c FROM llm_model WHERE account_id=${a}$", {"a": aid}) + await sor.sqlExe("COMMIT", {}) + cnt = int(getattr(recs[0], 'c', 0)) if recs else 0 + if cnt > 0: + raise ValueError('该账号被 %d 个模型设为默认账号，请先解除后再删除' % cnt) + await sor.sqlExe("DELETE FROM llm_account WHERE id=${a}$", {"a": aid}) + await sor.sqlExe("COMMIT", {}) + result['success'] = True + result['message'] = '删除成功' + except Exception as e: + result['message'] = str(e) + return json.dumps(result, ensure_ascii=False, default=str) + + +async def create_llm_model(params_kw): + result = {'success': False, 'message': ''} + try: + data = _clean(params_kw) + name = (data.get('name', '') or '').strip() + if not name: + raise ValueError('模型注册名不能为空') + if not data.get('vendor_id'): + raise ValueError('必须选择供应商') + dp = data.get('default_params', '') or '' + if isinstance(dp, (list, dict)): + dp = json.dumps(dp, ensure_ascii=False) + if dp.strip(): + json.loads(dp) # 校验合法 + data['default_params'] = dp + data['id'] = getID() + db, dbname = _get_sor() + async with db.sqlorContext(dbname) as sor: + recs = await sor.sqlExe("SELECT id FROM llm_model WHERE name=${n}$", {"n": name}) + await sor.sqlExe("COMMIT", {}) + if recs: + raise ValueError('模型注册名「%s」已存在（平台内唯一）' % name) + await sor.C('llm_model', data) + result['success'] = True + result['message'] = '创建成功' + except Exception as e: + result['message'] = str(e) + return json.dumps(result, ensure_ascii=False, default=str) + + +async def update_llm_model(params_kw): + result = {'success': False, 'message': ''} + try: + data = _clean(params_kw) + if 'default_params' in data: + dp = data.get('default_params', '') or '' + if isinstance(dp, (list, dict)): + dp = json.dumps(dp, ensure_ascii=False) + if dp.strip(): + json.loads(dp) + data['default_params'] = dp + db, dbname = _get_sor() + async with db.sqlorContext(dbname) as sor: + await sor.U('llm_model', data) + result['success'] = True + result['message'] = '更新成功' + except Exception as e: + result['message'] = str(e) + return json.dumps(result, ensure_ascii=False, default=str) + + +async def delete_llm_model(params_kw): + """模型删除前置检查：被策略引用时禁止。""" + result = {'success': False, 'message': ''} + try: + mid = (params_kw or {}).get('id', '') + if not mid: + raise ValueError('缺少 id') + db, dbname = _get_sor() + async with db.sqlorContext(dbname) as sor: + recs = await sor.sqlExe( + "SELECT COUNT(*) AS c FROM llm_org_policy WHERE primary_model_id=${m}$", {"m": mid}) + await sor.sqlExe("COMMIT", {}) + cnt = int(getattr(recs[0], 'c', 0)) if recs else 0 + if cnt > 0: + raise ValueError('该模型被 %d 个组织策略设为主模型，请先调整策略' % cnt) + await sor.sqlExe("DELETE FROM llm_model WHERE id=${m}$", {"m": mid}) + await sor.sqlExe("COMMIT", {}) + result['success'] = True + result['message'] = '删除成功' + except Exception as e: + result['message'] = str(e) + return json.dumps(result, ensure_ascii=False, default=str) + + +async def update_llm_org_policy(params_kw): + """组织策略保存：校验模型存在、备链去重。""" + result = {'success': False, 'message': ''} + try: + data = _clean(params_kw) + backups = data.get('backup_model_ids', '') or '' + if isinstance(backups, (list, dict)): + backups = json.dumps(backups, ensure_ascii=False) + bl = [] + if backups.strip(): + bl = json.loads(backups) + if not isinstance(bl, list): + raise ValueError('backup_model_ids 必须是 JSON 数组') + seen = [] + for b in bl: + if b and b not in seen: + seen.append(b) + bl = seen + data['backup_model_ids'] = json.dumps(bl, ensure_ascii=False) if bl else '' + primary = data.get('primary_model_id', '') or '' + if primary and primary in bl: + raise ValueError('主模型不能同时出现在备模型链中') + db, dbname = _get_sor() + async with db.sqlorContext(dbname) as sor: + if primary: + recs = await sor.sqlExe("SELECT id FROM llm_model WHERE id=${m}$", {"m": primary}) + await sor.sqlExe("COMMIT", {}) + if not recs: + raise ValueError('主模型不存在或已停用') + org_id = data.get('org_id', '') + if org_id: + recs = await sor.sqlExe("SELECT id FROM llm_org_policy WHERE org_id=${o}$", {"o": org_id}) + await sor.sqlExe("COMMIT", {}) + if recs: + data['id'] = getattr(recs[0], 'id', '') + await sor.U('llm_org_policy', data) + else: + data['id'] = getID() + await sor.C('llm_org_policy', data) + else: + await sor.U('llm_org_policy', data) + result['success'] = True + result['message'] = '保存成功' + except Exception as e: + result['message'] = str(e) + return json.dumps(result, ensure_ascii=False, default=str) + + +async def llm_usage_query(params_kw): + """用量查询（列表页工具栏）：按机构/模型/账号/状态/时间范围过滤，返回汇总+明细。""" + result = {'success': False, 'message': ''} + try: + pk = params_kw or {} + conds = ["1=1"] + params = {} + if pk.get('org_id'): + conds.append("org_id=${o}$"); params['o'] = pk['org_id'] + if pk.get('model_id'): + conds.append("model_id=${m}$"); params['m'] = pk['model_id'] + if pk.get('account_id'): + conds.append("account_id=${a}$"); params['a'] = pk['account_id'] + if pk.get('status'): + conds.append("status=${s}$"); params['s'] = pk['status'] + if pk.get('date_from'): + conds.append("created_at>=${df}$"); params['df'] = pk['date_from'] + if pk.get('date_to'): + conds.append("created_at<=${dt}$"); params['dt'] = pk['date_to'] + ' 23:59:59' + where = " AND ".join(conds) + db, dbname = _get_sor() + async with db.sqlorContext(dbname) as sor: + recs = await sor.sqlExe( + "SELECT u.id, u.org_id, u.user_id, u.model_id, m.name AS model_name, " + "u.account_id, a.name AS account_name, u.endpoint_region, " + "u.req_tokens, u.resp_tokens, u.cost, u.charge, u.ppid, u.task_ref, " + "u.status, u.note, u.created_at " + "FROM llm_usage u " + "LEFT JOIN llm_model m ON m.id=u.model_id " + "LEFT JOIN llm_account a ON a.id=u.account_id " + "WHERE %s ORDER BY u.created_at DESC LIMIT 200" % where, params) + sums = await sor.sqlExe( + "SELECT COUNT(*) AS cnt, COALESCE(SUM(req_tokens),0) AS req_t, " + "COALESCE(SUM(resp_tokens),0) AS resp_t, COALESCE(SUM(cost),0) AS cost_s, " + "COALESCE(SUM(charge),0) AS charge_s FROM llm_usage WHERE %s" % where, params) + await sor.sqlExe("COMMIT", {}) + rows = [] + for r in (recs or []): + d = {} + for k, v in vars(r).items(): + if not callable(v): + d[k] = v + rows.append(d) + s = sums[0] if sums else None + result['success'] = True + result['rows'] = rows + result['summary'] = { + 'count': int(getattr(s, 'cnt', 0)) if s else 0, + 'req_tokens': int(getattr(s, 'req_t', 0)) if s else 0, + 'resp_tokens': int(getattr(s, 'resp_t', 0)) if s else 0, + 'cost': round(float(getattr(s, 'cost_s', 0)), 6) if s else 0, + 'charge': round(float(getattr(s, 'charge_s', 0)), 6) if s else 0, + } + except Exception as e: + result['message'] = str(e) + return json.dumps(result, ensure_ascii=False, default=str) + + +async def llm_dashboard(params_kw): + """治理总览（首页卡片数据源）：各机构策略/余额/近期用量。""" + result = {'success': True} + try: + db, dbname = _get_sor() + async with db.sqlorContext(dbname) as sor: + vendors = await sor.sqlExe("SELECT COUNT(*) AS c FROM llm_vendor WHERE status='active'", {}) + accounts = await sor.sqlExe( + "SELECT COUNT(*) AS c, COALESCE(SUM(balance),0) AS b FROM llm_account WHERE status='active'", {}) + models = await sor.sqlExe("SELECT COUNT(*) AS c FROM llm_model WHERE status='active'", {}) + orgs = await sor.sqlExe("SELECT COUNT(*) AS c FROM llm_org_policy WHERE status='active'", {}) + usage = await sor.sqlExe( + "SELECT COUNT(*) AS c, COALESCE(SUM(charge),0) AS ch FROM llm_usage WHERE status='ok'", {}) + await sor.sqlExe("COMMIT", {}) + result['vendors'] = int(getattr(vendors[0], 'c', 0)) if vendors else 0 + result['accounts'] = int(getattr(accounts[0], 'c', 0)) if accounts else 0 + result['account_balance'] = round(float(getattr(accounts[0], 'b', 0)), 4) if accounts else 0 + result['models'] = int(getattr(models[0], 'c', 0)) if models else 0 + result['org_policies'] = int(getattr(orgs[0], 'c', 0)) if orgs else 0 + result['usage_calls'] = int(getattr(usage[0], 'c', 0)) if usage else 0 + result['usage_charge'] = round(float(getattr(usage[0], 'ch', 0)), 4) if usage else 0 + except Exception as e: + result['success'] = False + result['message'] = str(e) + return json.dumps(result, ensure_ascii=False, default=str) + + +def load_llm(): + """模块加载：注册全部函数到 ServerEnv。""" + load_gateway() + env = ServerEnv() + env.create_llm_vendor = create_llm_vendor + env.update_llm_vendor = update_llm_vendor + env.delete_llm_vendor = delete_llm_vendor + env.create_llm_account = create_llm_account + env.update_llm_account = update_llm_account + env.delete_llm_account = delete_llm_account + env.create_llm_model = create_llm_model + env.update_llm_model = update_llm_model + env.delete_llm_model = delete_llm_model + env.update_llm_org_policy = update_llm_org_policy + env.llm_usage_query = llm_usage_query + env.llm_dashboard = llm_dashboard + logger.info("[pipeline_llm] v1.0.0 loaded — 模型治理模块就绪") diff --git a/pyproject.toml b/pyproject.toml new file mode 100644 index 0000000..1a73ee1 --- /dev/null +++ b/pyproject.toml @@ -0,0 +1,17 @@ +[build-system] +requires = ["setuptools>=45", "wheel"] +build-backend = "setuptools.build_meta" + +[project] +name = "pipeline_llm" +version = "1.0.0" +description = "Pipeline platform model governance module — vendors/accounts/endpoints, org policies, quotas, failover rotation, dual-dimension accounting" +requires-python = ">=3.8" +dependencies = [ + "aiohttp", + "redis", +] + +[tool.setuptools.packages.find] +where = ["."] +include = ["pipeline_llm*"] diff --git a/scripts/load_path.py b/scripts/load_path.py new file mode 100644 index 0000000..94fbb34 --- /dev/null +++ b/scripts/load_path.py @@ -0,0 +1,36 @@ +#!/usr/bin/env python3 +"""pipeline_llm module RBAC permission registration. + +Run from app root: py3/bin/python pkgs/pipeline-llm/scripts/load_path.py +Requires app-root wrapper set_role_perm.py. +""" +import subprocess + +MOD = "pipeline-llm" + +PATHS_ANY = [] # 本模块无免登录资源（全部需登录） + +PATHS_LOGINED = [ + f"/{MOD}/", + f"/{MOD}/index.ui", +] + +# api/ 与生成的 CRUD 目录用通配符一次覆盖 +PATHS_WILDCARD_LOGINED = [ + f"/{MOD}/**", +] + + +def register_paths(): + for path in PATHS_ANY: + subprocess.run(["py3/bin/python", "set_role_perm.py", "any", path]) + print(f" any: {path}") + for path in PATHS_LOGINED + PATHS_WILDCARD_LOGINED: + subprocess.run(["py3/bin/python", "set_role_perm.py", "logined", path]) + print(f" logined: {path}") + + +if __name__ == "__main__": + print(f"=== {MOD} (pipeline_llm) RBAC registration ===") + register_paths() + print("Done.") diff --git a/wwwroot/api/get_llm_account_options.dspy b/wwwroot/api/get_llm_account_options.dspy new file mode 100644 index 0000000..deda2f6 --- /dev/null +++ b/wwwroot/api/get_llm_account_options.dspy @@ -0,0 +1,10 @@ +# get_llm_account_options.dspy — 供应商账号下拉（active） +dbname = get_module_dbname('pipeline_llm') +try: + async with get_sor_context(request._run_ns, dbname) as sor: + recs = await sor.sqlExe( + "SELECT id, name FROM llm_account WHERE status='active' ORDER BY name", {}) + await sor.sqlExe("COMMIT", {}) +except Exception as e: + return {"success": False, "message": str(e), "data": []} +return [{"value": getattr(r, "id", ""), "text": getattr(r, "name", "")} for r in (recs or [])] diff --git a/wwwroot/api/get_llm_capability_options.dspy b/wwwroot/api/get_llm_capability_options.dspy new file mode 100644 index 0000000..41438a3 --- /dev/null +++ b/wwwroot/api/get_llm_capability_options.dspy @@ -0,0 +1,11 @@ +# get_llm_capability_options.dspy — appcodes_kv 下拉选项（parentid=llm_capability） +dbname = get_module_dbname('pipeline_llm') +try: + async with get_sor_context(request._run_ns, dbname) as sor: + recs = await sor.sqlExe( + "SELECT k, v FROM appcodes_kv WHERE parentid=${p}$ ORDER BY k", + {"p": "llm_capability"}) + await sor.sqlExe("COMMIT", {}) +except Exception as e: + return {"success": False, "message": str(e), "data": []} +return [{"value": getattr(r, "k", ""), "text": getattr(r, "v", "") or getattr(r, "k", "")} for r in (recs or [])] diff --git a/wwwroot/api/get_llm_endpoint_pref_options.dspy b/wwwroot/api/get_llm_endpoint_pref_options.dspy new file mode 100644 index 0000000..8e67b13 --- /dev/null +++ b/wwwroot/api/get_llm_endpoint_pref_options.dspy @@ -0,0 +1,11 @@ +# get_llm_endpoint_pref_options.dspy — appcodes_kv 下拉选项（parentid=llm_endpoint_pref） +dbname = get_module_dbname('pipeline_llm') +try: + async with get_sor_context(request._run_ns, dbname) as sor: + recs = await sor.sqlExe( + "SELECT k, v FROM appcodes_kv WHERE parentid=${p}$ ORDER BY k", + {"p": "llm_endpoint_pref"}) + await sor.sqlExe("COMMIT", {}) +except Exception as e: + return {"success": False, "message": str(e), "data": []} +return [{"value": getattr(r, "k", ""), "text": getattr(r, "v", "") or getattr(r, "k", "")} for r in (recs or [])] diff --git a/wwwroot/api/get_llm_model_options.dspy b/wwwroot/api/get_llm_model_options.dspy new file mode 100644 index 0000000..149e5da --- /dev/null +++ b/wwwroot/api/get_llm_model_options.dspy @@ -0,0 +1,10 @@ +# get_llm_model_options.dspy — 模型下拉（active，策略主备模型用） +dbname = get_module_dbname('pipeline_llm') +try: + async with get_sor_context(request._run_ns, dbname) as sor: + recs = await sor.sqlExe( + "SELECT id, name FROM llm_model WHERE status='active' ORDER BY name", {}) + await sor.sqlExe("COMMIT", {}) +except Exception as e: + return {"success": False, "message": str(e), "data": []} +return [{"value": getattr(r, "id", ""), "text": getattr(r, "name", "")} for r in (recs or [])] diff --git a/wwwroot/api/get_llm_ppid_options.dspy b/wwwroot/api/get_llm_ppid_options.dspy new file mode 100644 index 0000000..861cef4 --- /dev/null +++ b/wwwroot/api/get_llm_ppid_options.dspy @@ -0,0 +1,10 @@ +# get_llm_ppid_options.dspy — 定价项目下拉（pricing_program，挂定价用） +dbname = get_module_dbname('pipeline_llm') +try: + async with get_sor_context(request._run_ns, dbname) as sor: + recs = await sor.sqlExe( + "SELECT id, name FROM pricing_program ORDER BY name", {}) + await sor.sqlExe("COMMIT", {}) +except Exception as e: + return {"success": False, "message": str(e), "data": []} +return [{"value": getattr(r, "id", ""), "text": getattr(r, "name", "")} for r in (recs or [])] diff --git a/wwwroot/api/get_llm_protocol_options.dspy b/wwwroot/api/get_llm_protocol_options.dspy new file mode 100644 index 0000000..e4026f8 --- /dev/null +++ b/wwwroot/api/get_llm_protocol_options.dspy @@ -0,0 +1,11 @@ +# get_llm_protocol_options.dspy — appcodes_kv 下拉选项（parentid=llm_protocol） +dbname = get_module_dbname('pipeline_llm') +try: + async with get_sor_context(request._run_ns, dbname) as sor: + recs = await sor.sqlExe( + "SELECT k, v FROM appcodes_kv WHERE parentid=${p}$ ORDER BY k", + {"p": "llm_protocol"}) + await sor.sqlExe("COMMIT", {}) +except Exception as e: + return {"success": False, "message": str(e), "data": []} +return [{"value": getattr(r, "k", ""), "text": getattr(r, "v", "") or getattr(r, "k", "")} for r in (recs or [])] diff --git a/wwwroot/api/get_llm_status_options.dspy b/wwwroot/api/get_llm_status_options.dspy new file mode 100644 index 0000000..a7ba750 --- /dev/null +++ b/wwwroot/api/get_llm_status_options.dspy @@ -0,0 +1,11 @@ +# get_llm_status_options.dspy — appcodes_kv 下拉选项（parentid=llm_status） +dbname = get_module_dbname('pipeline_llm') +try: + async with get_sor_context(request._run_ns, dbname) as sor: + recs = await sor.sqlExe( + "SELECT k, v FROM appcodes_kv WHERE parentid=${p}$ ORDER BY k", + {"p": "llm_status"}) + await sor.sqlExe("COMMIT", {}) +except Exception as e: + return {"success": False, "message": str(e), "data": []} +return [{"value": getattr(r, "k", ""), "text": getattr(r, "v", "") or getattr(r, "k", "")} for r in (recs or [])] diff --git a/wwwroot/api/get_llm_vendor_options.dspy b/wwwroot/api/get_llm_vendor_options.dspy new file mode 100644 index 0000000..0a825ce --- /dev/null +++ b/wwwroot/api/get_llm_vendor_options.dspy @@ -0,0 +1,10 @@ +# get_llm_vendor_options.dspy — 供应商下拉（active） +dbname = get_module_dbname('pipeline_llm') +try: + async with get_sor_context(request._run_ns, dbname) as sor: + recs = await sor.sqlExe( + "SELECT id, name FROM llm_vendor WHERE status='active' ORDER BY name", {}) + await sor.sqlExe("COMMIT", {}) +except Exception as e: + return {"success": False, "message": str(e), "data": []} +return [{"value": getattr(r, "id", ""), "text": getattr(r, "name", "")} for r in (recs or [])] diff --git a/wwwroot/api/llm_account_recharge.dspy b/wwwroot/api/llm_account_recharge.dspy new file mode 100644 index 0000000..237b19f --- /dev/null +++ b/wwwroot/api/llm_account_recharge.dspy @@ -0,0 +1,11 @@ +# llm_account_recharge.dspy — 供应商账号充值（成本侧钱包） +uid = await get_user() +if not uid: + return {"success": False, "message": "未登录"} +account_id = (params_kw or {}).get('account_id', '') or (params_kw or {}).get('id', '') +amount = (params_kw or {}).get('amount', 0) +note = (params_kw or {}).get('note', '') or '' +if not account_id: + return {"success": False, "message": "缺少账号"} +ok, msg = await llm_recharge_account(account_id, amount, note, uid) +return {"success": ok, "message": msg} diff --git a/wwwroot/api/llm_dashboard.dspy b/wwwroot/api/llm_dashboard.dspy new file mode 100644 index 0000000..4c3cc41 --- /dev/null +++ b/wwwroot/api/llm_dashboard.dspy @@ -0,0 +1,5 @@ +# llm_dashboard.dspy — 模型治理总览数据 +uid = await get_user() +if not uid: + return {"success": False, "message": "未登录"} +return json.loads(await llm_dashboard({})) diff --git a/wwwroot/api/llm_dashboard_widget.dspy b/wwwroot/api/llm_dashboard_widget.dspy new file mode 100644 index 0000000..4a674de --- /dev/null +++ b/wwwroot/api/llm_dashboard_widget.dspy @@ -0,0 +1,48 @@ +# llm_dashboard_widget.dspy — 模型治理总览（顶部统计条，返回 Bricks widget） +dbname = get_module_dbname('pipeline_llm') +data = {"vendors": 0, "accounts": 0, "account_balance": 0, "models": 0, + "org_policies": 0, "usage_calls": 0, "usage_charge": 0} +try: + async with get_sor_context(request._run_ns, dbname) as sor: + vendors = await sor.sqlExe("SELECT COUNT(*) AS c FROM llm_vendor WHERE status='active'", {}) + accounts = await sor.sqlExe( + "SELECT COUNT(*) AS c, COALESCE(SUM(balance),0) AS b FROM llm_account WHERE status='active'", {}) + models = await sor.sqlExe("SELECT COUNT(*) AS c FROM llm_model WHERE status='active'", {}) + orgs = await sor.sqlExe("SELECT COUNT(*) AS c FROM llm_org_policy WHERE status='active'", {}) + usage = await sor.sqlExe( + "SELECT COUNT(*) AS c, COALESCE(SUM(charge),0) AS ch FROM llm_usage WHERE status='ok'", {}) + await sor.sqlExe("COMMIT", {}) + data['vendors'] = int(getattr(vendors[0], 'c', 0)) if vendors else 0 + data['accounts'] = int(getattr(accounts[0], 'c', 0)) if accounts else 0 + data['account_balance'] = round(float(getattr(accounts[0], 'b', 0)), 4) if accounts else 0 + data['models'] = int(getattr(models[0], 'c', 0)) if models else 0 + data['org_policies'] = int(getattr(orgs[0], 'c', 0)) if orgs else 0 + data['usage_calls'] = int(getattr(usage[0], 'c', 0)) if usage else 0 + data['usage_charge'] = round(float(getattr(usage[0], 'ch', 0)), 4) if usage else 0 +except Exception: + pass + +stats = [ + ('供应商', str(data['vendors'])), + ('账号', str(data['accounts'])), + ('账号总余额', str(data['account_balance'])), + ('模型', str(data['models'])), + ('组织策略', str(data['org_policies'])), + ('调用次数', str(data['usage_calls'])), + ('累计消费', str(data['usage_charge'])), +] +boxes = [] +for label, val in stats: + boxes.append({ + "widgettype": "VBox", + "options": {"css": "card", "padding": "12px 20px", "minWidth": "110px"}, + "subwidgets": [ + {"widgettype": "Text", "options": {"text": val, "cfontsize": 1.6, "color": "#1e293b", "halign": "middle"}}, + {"widgettype": "Text", "options": {"text": label, "cfontsize": 0.9, "color": "#64748b", "halign": "middle"}}, + ] + }) +return { + "widgettype": "HBox", + "options": {"gap": "12px", "padding": "0 0 16px 0", "wrap": "wrap"}, + "subwidgets": boxes +} diff --git a/wwwroot/api/llm_org_recharge.dspy b/wwwroot/api/llm_org_recharge.dspy new file mode 100644 index 0000000..76b4ed1 --- /dev/null +++ b/wwwroot/api/llm_org_recharge.dspy @@ -0,0 +1,11 @@ +# llm_org_recharge.dspy — 组织池充值（消费侧钱包） +uid = await get_user() +if not uid: + return {"success": False, "message": "未登录"} +org_id = (params_kw or {}).get('org_id', '') or '' +amount = (params_kw or {}).get('amount', 0) +note = (params_kw or {}).get('note', '') or '' +if not org_id: + return {"success": False, "message": "缺少机构"} +ok, msg = await llm_recharge_org(org_id, amount, note, uid) +return {"success": ok, "message": msg} diff --git a/wwwroot/api/llm_usage_query.dspy b/wwwroot/api/llm_usage_query.dspy new file mode 100644 index 0000000..0c05ba7 --- /dev/null +++ b/wwwroot/api/llm_usage_query.dspy @@ -0,0 +1,6 @@ +# llm_usage_query.dspy — 用量查询统计（工具栏入口，透传过滤条件） +uid = await get_user() +if not uid: + return {"success": False, "message": "未登录"} +pk = dict(params_kw or {}) +return json.loads(await llm_usage_query(pk)) diff --git a/wwwroot/index.ui b/wwwroot/index.ui new file mode 100644 index 0000000..bc1c5fd --- /dev/null +++ b/wwwroot/index.ui @@ -0,0 +1,271 @@ +{ + "widgettype": "VBox", + "options": { + "width": "100%", + "height": "100%", + "padding": "0" + }, + "subwidgets": [ + { + "widgettype": "HBox", + "options": { + "width": "100%", + "alignItems": "center", + "marginBottom": "24px" + }, + "subwidgets": [ + { + "widgettype": "Title2", + "options": { + "text": "模型治理" + } + }, + { + "widgettype": "Filler" + }, + { + "widgettype": "Text", + "options": { + "text": "供应商/账号/模型 · 容错策略 · 限额限流 · 双维度记账", + "cfontsize": 1.2 + } + } + ] + }, + { + "widgettype": "urlwidget", + "options": { + "url": "{{entire_url('/pipeline-llm/api/llm_dashboard_widget.dspy')}}" + } + }, + { + "widgettype": "VScrollPanel", + "options": { + "css": "filler" + }, + "subwidgets": [ + { + "widgettype": "VBox", + "options": { + "spacing": 24 + }, + "subwidgets": [ + { + "widgettype": "ResponsableBox", + "options": { + "gap": "16px", + "minWidth": "300px" + }, + "subwidgets": [ + { + "widgettype": "VBox", + "options": { + "css": "card", + "cwidth": 25, + "padding": "16px", + "cursor": "pointer" + }, + "binds": [ + { + "wid": "self", + "event": "click", + "actiontype": "urlwidget", + "target": "app.llm_content", + "options": { + "url": "{{entire_url('/pipeline-llm/llm_vendor')}}" + }, + "mode": "replace" + } + ], + "subwidgets": [ + {"widgettype": "Title4", "options": {"text": "供应商与端点", "marginBottom": "8px"}}, + {"widgettype": "Text", "options": {"text": "供应商协议 + 全球端点目录（国内/国际，配置一次全账号共用）", "cfontsize": 1.2}} + ] + }, + { + "widgettype": "VBox", + "options": { + "css": "card", + "cwidth": 25, + "padding": "16px", + "cursor": "pointer" + }, + "binds": [ + { + "wid": "self", + "event": "click", + "actiontype": "urlwidget", + "target": "app.llm_content", + "options": { + "url": "{{entire_url('/pipeline-llm/llm_account')}}" + }, + "mode": "replace" + } + ], + "subwidgets": [ + {"widgettype": "Title4", "options": {"text": "供应商账号（钱包）", "marginBottom": "8px"}}, + {"widgettype": "Text", "options": {"text": "多账号独立充值记账、选用端点；轮转突破供应商限流", "cfontsize": 1.2}} + ] + }, + { + "widgettype": "VBox", + "options": { + "css": "card", + "cwidth": 25, + "padding": "16px", + "cursor": "pointer" + }, + "binds": [ + { + "wid": "self", + "event": "click", + "actiontype": "urlwidget", + "target": "app.llm_content", + "options": { + "url": "{{entire_url('/pipeline-llm/llm_model')}}" + }, + "mode": "replace" + } + ], + "subwidgets": [ + {"widgettype": "Title4", "options": {"text": "模型注册", "marginBottom": "8px"}}, + {"widgettype": "Text", "options": {"text": "能力分类（t2t/…）、挂定价项目（ppid）、成本/售价", "cfontsize": 1.2}} + ] + }, + { + "widgettype": "VBox", + "options": { + "css": "card", + "cwidth": 25, + "padding": "16px", + "cursor": "pointer" + }, + "binds": [ + { + "wid": "self", + "event": "click", + "actiontype": "urlwidget", + "target": "app.llm_content", + "options": { + "url": "{{entire_url('/pipeline-llm/llm_api_profile')}}" + }, + "mode": "replace" + } + ], + "subwidgets": [ + {"widgettype": "Title4", "options": {"text": "适配模板", "marginBottom": "8px"}}, + {"widgettype": "Text", "options": {"text": "协议×能力形态的请求/响应模板（按形态去重，不按模型开）", "cfontsize": 1.2}} + ] + }, + { + "widgettype": "VBox", + "options": { + "css": "card", + "cwidth": 25, + "padding": "16px", + "cursor": "pointer" + }, + "binds": [ + { + "wid": "self", + "event": "click", + "actiontype": "urlwidget", + "target": "app.llm_content", + "options": { + "url": "{{entire_url('/pipeline-llm/llm_org_policy')}}" + }, + "mode": "replace" + } + ], + "subwidgets": [ + {"widgettype": "Title4", "options": {"text": "组织容错策略", "marginBottom": "8px"}}, + {"widgettype": "Text", "options": {"text": "组织级主模型 + 备模型链 + 端点偏好（prefer/must）", "cfontsize": 1.2}} + ] + }, + { + "widgettype": "VBox", + "options": { + "css": "card", + "cwidth": 25, + "padding": "16px", + "cursor": "pointer" + }, + "binds": [ + { + "wid": "self", + "event": "click", + "actiontype": "urlwidget", + "target": "app.llm_content", + "options": { + "url": "{{entire_url('/pipeline-llm/llm_org_quota')}}" + }, + "mode": "replace" + } + ], + "subwidgets": [ + {"widgettype": "Title4", "options": {"text": "组织限额限流", "marginBottom": "8px"}}, + {"widgettype": "Text", "options": {"text": "组织池充值/余额 + 组织 QPM 上限", "cfontsize": 1.2}} + ] + }, + { + "widgettype": "VBox", + "options": { + "css": "card", + "cwidth": 25, + "padding": "16px", + "cursor": "pointer" + }, + "binds": [ + { + "wid": "self", + "event": "click", + "actiontype": "urlwidget", + "target": "app.llm_content", + "options": { + "url": "{{entire_url('/pipeline-llm/llm_user_quota')}}" + }, + "mode": "replace" + } + ], + "subwidgets": [ + {"widgettype": "Title4", "options": {"text": "个人限额限流", "marginBottom": "8px"}}, + {"widgettype": "Text", "options": {"text": "个人额度上限 + 个人 QPM（共享组织池模式）", "cfontsize": 1.2}} + ] + }, + { + "widgettype": "VBox", + "options": { + "css": "card", + "cwidth": 25, + "padding": "16px", + "cursor": "pointer" + }, + "binds": [ + { + "wid": "self", + "event": "click", + "actiontype": "urlwidget", + "target": "app.llm_content", + "options": { + "url": "{{entire_url('/pipeline-llm/llm_usage')}}" + }, + "mode": "replace" + } + ], + "subwidgets": [ + {"widgettype": "Title4", "options": {"text": "用量流水", "marginBottom": "8px"}}, + {"widgettype": "Text", "options": {"text": "双维度记账：成本侧（账号）+ 消费侧（组织/个人）", "cfontsize": 1.2}} + ] + } + ] + } + ] + }, + { + "widgettype": "VBox", + "id": "llm_content" + } + ] + } + ] +}