Compare commits
3 Commits
v1.0.0
...
68f24e6794
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
68f24e6794 | ||
|
|
bed3bc11ca | ||
|
|
0d0f3b611a |
@@ -1,4 +1,21 @@
|
||||
.git
|
||||
__pycache__/
|
||||
*.pyc
|
||||
.pytest_cache/
|
||||
.gitignore
|
||||
.venv
|
||||
venv
|
||||
__pycache__
|
||||
*.py[cod]
|
||||
*$py.class
|
||||
.pytest_cache
|
||||
.mypy_cache
|
||||
reports/*
|
||||
!reports/.gitkeep
|
||||
docs
|
||||
tests
|
||||
scripts
|
||||
config
|
||||
*.md
|
||||
!README.md
|
||||
.env
|
||||
.env.*
|
||||
*.log
|
||||
.DS_Store
|
||||
|
||||
31
.gitignore
vendored
Normal file
31
.gitignore
vendored
Normal file
@@ -0,0 +1,31 @@
|
||||
# Secrets / local env
|
||||
.env
|
||||
.env.*
|
||||
!.env.example
|
||||
config/local.env
|
||||
|
||||
# Python
|
||||
__pycache__/
|
||||
*.py[cod]
|
||||
*$py.class
|
||||
.venv/
|
||||
venv/
|
||||
.pytest_cache/
|
||||
.mypy_cache/
|
||||
*.egg-info/
|
||||
dist/
|
||||
build/
|
||||
|
||||
# Dry-run / local artifacts (keep directory)
|
||||
reports/*
|
||||
!reports/.gitkeep
|
||||
|
||||
# Editor / OS
|
||||
.DS_Store
|
||||
.idea/
|
||||
.vscode/
|
||||
*.swp
|
||||
*~
|
||||
|
||||
# Docker
|
||||
*.tar
|
||||
18
Dockerfile
18
Dockerfile
@@ -1,14 +1,18 @@
|
||||
FROM modelhubxc-4pd.tencentcloudcr.com/xc_agent_platform/python:3.11-slim
|
||||
|
||||
ENV PYTHONUNBUFFERED=1
|
||||
# ModelHub XC adaptation agent — Phase1 skeleton
|
||||
# Default base MUST stay the platform image (do not swap to public mirrors).
|
||||
ARG BASE_IMAGE=modelhubxc-4pd.tencentcloudcr.com/xc_agent_platform/python:3.11-slim
|
||||
FROM ${BASE_IMAGE}
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
COPY requirements.txt .
|
||||
RUN pip install --no-cache-dir -r requirements.txt
|
||||
# Copy only what the runtime needs (see .dockerignore)
|
||||
COPY src/ ./src/
|
||||
|
||||
COPY . .
|
||||
ENV PORT=8080
|
||||
ENV PYTHONUNBUFFERED=1
|
||||
# STRATEGY_ID and tokens are injected by the platform at run time — never bake them in.
|
||||
|
||||
EXPOSE 8080
|
||||
|
||||
CMD ["python", "main.py"]
|
||||
# Start HTTP service only (no register / submit side effects)
|
||||
CMD ["python", "-m", "src.server"]
|
||||
|
||||
44
Makefile
Normal file
44
Makefile
Normal file
@@ -0,0 +1,44 @@
|
||||
# ModelHub XC agent contrib — Phase1
|
||||
# Allowed: test / build / smoke-health / dry-run
|
||||
# FORBIDDEN: register / submit / deploy / push targets
|
||||
|
||||
.PHONY: build-config-dry probe-readonly test build smoke-health dry-run dry-run-pending help
|
||||
|
||||
PYTHON ?= python3
|
||||
IMAGE ?= modelhub-agent-contrib:local
|
||||
PORT ?= 8080
|
||||
|
||||
help:
|
||||
@echo "build-config-dry generate YAML via API (requires token; never creates task)"
|
||||
@echo "probe-readonly authenticated read-only task/page GET"
|
||||
@echo "dry-run-pending read-only adapt pending A→B report"
|
||||
@echo "test stdlib unit tests + local SIGTERM integration (needs sockets)"
|
||||
@echo "build Docker build using platform base (needs Docker + TCR access)"
|
||||
@echo "smoke-health local HTTP smoke (needs sockets; default test STRATEGY_ID)"
|
||||
@echo "dry-run read-only pending report (example fallback)"
|
||||
@echo "No register/submit/deploy/push — default live off."
|
||||
|
||||
test:
|
||||
$(PYTHON) -m unittest discover -s tests -v
|
||||
|
||||
build:
|
||||
@command -v docker >/dev/null 2>&1 || { \
|
||||
echo "ERROR: docker not found. See docs/build-notes.md"; \
|
||||
exit 1; \
|
||||
}
|
||||
docker build -t $(IMAGE) .
|
||||
|
||||
smoke-health:
|
||||
$(PYTHON) scripts/smoke_health.py
|
||||
|
||||
dry-run:
|
||||
$(PYTHON) scripts/dry_run.py
|
||||
|
||||
dry-run-pending:
|
||||
PENDING_SUBMIT_MD=/workspace/modelhub-adapt/pending-submit.md PENDING_SUBMIT_TXT=/workspace/modelhub-adapt/pending-submit.txt $(PYTHON) scripts/dry_run.py
|
||||
|
||||
probe-readonly:
|
||||
$(PYTHON) scripts/probe_readonly.py
|
||||
|
||||
build-config-dry:
|
||||
$(PYTHON) scripts/build_config_dry.py
|
||||
87
README.md
87
README.md
@@ -1,39 +1,76 @@
|
||||
# Strategy Platform Demo Repo
|
||||
# modelhub-agent-contrib
|
||||
|
||||
Minimal strategy repository for testing the platform Kaniko build and deployment flow.
|
||||
ModelHub XC(信创模盒)**适配智能体** Phase1 本地骨架。
|
||||
|
||||
It satisfies the runtime contract from the parent README:
|
||||
> **不代注册、不代提交。** 发布智能体本身 **不得分**。积分来自成功适配,数字一律 **待平台核实**。
|
||||
> 冲突裁决:**适配 W1 优先**;本仓默认 dry-run,不抢验证队列。
|
||||
|
||||
- Root-level `Dockerfile`
|
||||
- Listens on port `8080`
|
||||
- Exposes `GET /health`
|
||||
- Reads `EXTERNAL_SERVICE_TOKEN`
|
||||
- Handles `SIGTERM` for graceful shutdown
|
||||
## 契约要点
|
||||
|
||||
## Local Run
|
||||
| 项 | 值 |
|
||||
|----|-----|
|
||||
| 端口 | 8080 |
|
||||
| 健康检查 | `GET /health` → `{"status":"ok"}` |
|
||||
| 启动 | **必须**有非空 `STRATEGY_ID`,否则 exit ≠0 |
|
||||
| Live | `ALLOW_LIVE_SUBMIT=1` **且** `LIVE_CONFIRM=I_CONFIRM_LIVE_SUBMIT`;Phase1 仍无真实 `task/add` 客户端 |
|
||||
| Base 镜像 | 平台 `xc_agent_platform/python:3.11-slim`(勿擅自改默认 FROM) |
|
||||
|
||||
闸门以 `src/gate.py` 实现为准:仅 `ALLOW_LIVE_SUBMIT=1` 与
|
||||
`LIVE_CONFIRM=I_CONFIRM_LIVE_SUBMIT` 同时满足才开逻辑闸门。PRD 示例
|
||||
`ALLOW_LIVE_SUBMIT=true` / `CONFIRM_LIVE=YES` 不受支持;本仓不读取确认文件。
|
||||
即使开闸,无真实客户端仍返回 blocked;请保持默认关闭。
|
||||
|
||||
## 快速开始
|
||||
|
||||
```bash
|
||||
python main.py
|
||||
curl http://localhost:8080/health
|
||||
curl http://localhost:8080/
|
||||
cd /workspace/modelhub-agent-contrib
|
||||
make test
|
||||
make smoke-health # 自动起本地 server(需 STRATEGY_ID,脚本可注入测试值)
|
||||
make dry-run # 写出 reports/dry-run-*.md
|
||||
make build # 需 Docker + 可达平台 base;失败见 docs/build-notes.md
|
||||
```
|
||||
|
||||
## Build Locally
|
||||
本地起服务:
|
||||
|
||||
```bash
|
||||
docker build -t strategy-demo:v1.0.0 .
|
||||
|
||||
docker run --rm -p 8080:8080 strategy-demo:v1.0.0
|
||||
export STRATEGY_ID=local-dev
|
||||
python3 -m src.server
|
||||
# → http://127.0.0.1:8080/health
|
||||
```
|
||||
|
||||
## Platform Test
|
||||
## 目录
|
||||
|
||||
Push this directory to Gitea and keep the `v1.0.0` tag. Then create a strategy with:
|
||||
|
||||
```json
|
||||
{
|
||||
"name": "strategy-demo",
|
||||
"repo_url": "https://<your-gitea-host>/<user>/strategy-demo",
|
||||
"tag": "v1.0.0"
|
||||
}
|
||||
```text
|
||||
Dockerfile Makefile README.md
|
||||
src/ # server / health / strategy / gate
|
||||
config/ # example.env, candidates.example.json
|
||||
scripts/ # smoke_health.py, dry_run.py, tag_release.py
|
||||
reports/ # dry-run 输出(gitignore)
|
||||
docs/ # 契约 / runbook / kickoff / issues
|
||||
tests/ # stdlib unittest
|
||||
```
|
||||
|
||||
## Makefile 目标
|
||||
|
||||
- `test` / `build` / `smoke-health` / `dry-run`
|
||||
- **没有** `register` / `submit` / `deploy` / `push`
|
||||
|
||||
## 文档
|
||||
|
||||
- [`docs/kickoff-for-victor.md`](docs/kickoff-for-victor.md) — 一页开工 + 验收勾选
|
||||
- [`docs/platform-contract-agent.md`](docs/platform-contract-agent.md) — 契约表
|
||||
- [`docs/register-runbook.md`](docs/register-runbook.md) — 仅人工注册
|
||||
- [`docs/api-probe-design.md`](docs/api-probe-design.md) — 写接口禁止代调
|
||||
- [`docs/diff-vs-demo.md`](docs/diff-vs-demo.md) — 对照官方 demo
|
||||
- [`docs/issues.md`](docs/issues.md) — M0–M4 / Phase 清单
|
||||
- [`docs/build-notes.md`](docs/build-notes.md) — 镜像构建说明
|
||||
|
||||
## 资源声明
|
||||
|
||||
按平台量级设计:约 **100m–1 CPU / 256–512Mi**。
|
||||
|
||||
## 许可与边界
|
||||
|
||||
本仓库用于 Victor 本地/Gitea 交付骨架;任何 ModelHub 写操作须 Victor 本人在控制台或显式批准后执行。
|
||||
|
||||
Phase2:`make dry-run-pending` 只读生成 A→B 草稿,名称硬门与禁提过滤已接入;需 Victor 人工提交/确认。task/add 客户端默认不调用,必须显式注入并通过双闸门、队列及单次预算;测试仅 mock HTTP。
|
||||
|
||||
21
config/candidates.example.json
Normal file
21
config/candidates.example.json
Normal file
@@ -0,0 +1,21 @@
|
||||
{
|
||||
"candidates": [
|
||||
{
|
||||
"model_id": "example-org/example-model",
|
||||
"modelAddress": "example-org/example-model",
|
||||
"taskType": "text-generation",
|
||||
"targetGpu": "Iluvatar_bi-100",
|
||||
"framework": "vllm",
|
||||
"notes": "Phase1 example only — not a real submit payload"
|
||||
},
|
||||
{
|
||||
"model_id": "example-org/another-model",
|
||||
"taskType": "text-generation",
|
||||
"notes": "Minimal fields: model_id required; others optional"
|
||||
}
|
||||
],
|
||||
"_meta": {
|
||||
"description": "Minimal dry-run input schema for Phase1",
|
||||
"pending_align": "Future Phase2 may read /workspace/modelhub-adapt/pending-submit.md A→B order"
|
||||
}
|
||||
}
|
||||
20
config/example.env
Normal file
20
config/example.env
Normal file
@@ -0,0 +1,20 @@
|
||||
# Copy to config/local.env (gitignored) for local runs. Never commit real tokens.
|
||||
|
||||
# Required for process start (Phase1): non-empty STRATEGY_ID
|
||||
STRATEGY_ID=local-dev-strategy-placeholder
|
||||
|
||||
# Optional listen port (default 8080)
|
||||
PORT=8080
|
||||
|
||||
# Implementation is authoritative: ALLOW_LIVE_SUBMIT=1 AND
|
||||
# LIVE_CONFIRM=I_CONFIRM_LIVE_SUBMIT. No confirmation file is read.
|
||||
# PRD examples ALLOW_LIVE_SUBMIT=true / CONFIRM_LIVE=YES are unsupported.
|
||||
# Even with both set, no real client exists: still blocked. Keep defaults below.
|
||||
# Dual live gate — BOTH required for live; default is dry-run / blocked
|
||||
ALLOW_LIVE_SUBMIT=0
|
||||
LIVE_CONFIRM=
|
||||
|
||||
# Platform injects EXTERNAL_SERVICE_TOKEN at runtime.
|
||||
# Community aliases (presence only; never log values):
|
||||
# XC_TOKEN_FILE / XC_TOKEN / MODELHUB_XC_TOKEN / EXTERNAL_SERVICE_TOKEN
|
||||
# EXTERNAL_SERVICE_TOKEN=
|
||||
43
docs/api-probe-design.md
Normal file
43
docs/api-probe-design.md
Normal file
@@ -0,0 +1,43 @@
|
||||
# API 探针设计(只读意图 · 禁止代调写接口)
|
||||
|
||||
- 日期:2026-10-16 Asia/Shanghai
|
||||
- Phase2:客户端已实现但默认不调用;本轮禁止真实 task/add
|
||||
|
||||
## 管理 API `/agent_platform/strategies*`
|
||||
|
||||
| 方法 | 路径 | 本仓态度 |
|
||||
|------|------|----------|
|
||||
| POST | `/agent_platform/strategies` | **禁止代调**(注册) |
|
||||
| POST | `.../{id}/deploy` | **禁止代调** |
|
||||
| POST | `.../{id}/stop` | **禁止代调** |
|
||||
| DELETE | `.../{id}` | **禁止代调** |
|
||||
| GET | `.../{id}` | 未来只读探针可选(Phase3+,需 Victor 授权) |
|
||||
| GET | `.../{id}/logs` | 未来只读探针可选 |
|
||||
|
||||
鉴权(浏览器):`Authorization: Bearer <login token>`(等级 A)。
|
||||
|
||||
## 适配任务 API
|
||||
|
||||
| 方法 | 路径 | 本仓态度 |
|
||||
|------|------|----------|
|
||||
| GET | `/api/adapt/task/page` | 未来只读鉴权探针(对齐 huni-probe,`ALLOW_SUBMIT=0`) |
|
||||
| POST | `/api/adapt/task/build-config` | 设计可引用;Phase1 不实现 |
|
||||
| POST | `/api/adapt/task/add` | 显式注入客户端 + 双闸门;本轮只做 mock 测试 |
|
||||
| GET | `/api/adapt/task/calculate-credit` | 只读索引;勿写死 KPI |
|
||||
|
||||
容器内社区鉴权(C):`Xc-Token` + body `strategyId` — **待 Victor 账号核实**;60014 仍为 **D(unverified)**。
|
||||
|
||||
## Phase2 落地边界
|
||||
|
||||
- `src/gate.py`:闸门逻辑 + `attempt_live_submit(..., client=Fake)` ;真实客户端只能显式注入,测试必须 mock HTTP
|
||||
- `src/task_add_client.py` 使用 urllib;import 和 dry-run 无网络调用,无自动重试
|
||||
- token 优先级:XC_TOKEN_FILE → XC_TOKEN → MODELHUB_XC_TOKEN → EXTERNAL_SERVICE_TOKEN;禁止输出 token
|
||||
- build_payload 中 GPU/framework/strategyId/configParams 占位须人工替换;真实调用要求 STRATEGY_ID 与 payload 一致
|
||||
- 队列 ≥95 阻断;无效队列提示也阻断;每进程一次调用预算在调用前保留,异常也不重试(防止响应丢失造成重复创建)
|
||||
- 名称/族硬门不能证明元数据 PASS;未跳过的 pending 行均标 needs_human
|
||||
- 仍禁止所有 agent_platform 写接口
|
||||
- Makefile **无** register / submit / deploy / push
|
||||
|
||||
## 冲突裁决提醒
|
||||
|
||||
适配 W1:队列 ≥95 → 禁 live;智能体不抢验证空位。
|
||||
25
docs/autoconfig-probe-plan.md
Normal file
25
docs/autoconfig-probe-plan.md
Normal file
@@ -0,0 +1,25 @@
|
||||
# configParams 配置来源与容器验证
|
||||
|
||||
日期:2026-10-16 Asia/Shanghai。
|
||||
|
||||
结论:**API**。配置来自服务端,前端将响应 `data` 写入 `configParams`。
|
||||
依据:[autoconfig-capture-2026-10-16.md](/workspace/modelhub-adapt/logs/autoconfig-capture-2026-10-16.md)。原「公开面无 build-config」缺口关闭:**未公开文档但已抓包证实**。
|
||||
|
||||
## 已证实契约
|
||||
|
||||
- `POST /api/adapt/task/build-config`
|
||||
- Query:`gpuType=Sunrise_pt-200-x1&framework=vllm&taskType=text-generation`
|
||||
- 空 body,无 JSON;模型地址不进入 query/body,也无需传 strategyId。
|
||||
- HTTP 2xx,JSON `code == 0`,非空字符串 `data` 为 YAML。
|
||||
- 当前 UI 无「自动配置」标签。新建适配弹层选择模型、GPU、文本生成后,选择框架触发 effect 并填入配置。
|
||||
- 抓包观察到 `Authorization` 头,值未记录。容器默认按社区实践发送 `Xc-Token`;`BUILD_CONFIG_USE_AUTHORIZATION=1` 改用同一 resolve_token 值作为 Authorization,不自动加 Bearer。
|
||||
|
||||
## 客户端与验证
|
||||
|
||||
`src/build_config_client.py` 的 `build_config()` 成功返回 YAML,失败抛出 `BuildConfigError`,包含安全归因、HTTP 状态和平台数字码;不返回服务端消息或传输异常细节。缺失/无效凭证不联网,40100、40101、其他平台码、传输失败和无效 data 均可区分。导入无 I/O。
|
||||
|
||||
默认 dry-run 使用 `templates/config_params.sample.yaml`,无网络。`CONFIG_PARAMS_SOURCE=build-config` 强制 API;或 `ALLOW_BUILD_CONFIG=1` 且可解析 token 时使用 API。调用失败直接报错,不回退 sample。调用方须传真实 GPU enum。`make build-config-dry` 仅生成配置,缺 token 非零退出,不输出 YAML 或凭证。
|
||||
|
||||
## 剩余 GAP 与边界
|
||||
|
||||
尚无容器 token 鉴权实证;需运行时 token + API 调用并与只读探针对照,不能宣称鉴权就绪。sample 本身不是 production-ready。队列 ≥95 禁 live。本轮仅 mock 测试,不进行真实 API 调用,不调用 task/add,不保存秘密,不提交任务或推送 tag。
|
||||
59
docs/build-notes.md
Normal file
59
docs/build-notes.md
Normal file
@@ -0,0 +1,59 @@
|
||||
# Build notes
|
||||
|
||||
- 日期:2026-10-16 Asia/Shanghai
|
||||
- 默认 `FROM`:`modelhubxc-4pd.tencentcloudcr.com/xc_agent_platform/python:3.11-slim`
|
||||
- **禁止**因本地拉不下而改默认 FROM 为公网镜像
|
||||
|
||||
## 本机(box)首次尝试
|
||||
|
||||
| 项 | 结果 |
|
||||
|----|------|
|
||||
| `docker` CLI | **未安装 / 不可用**(`which docker` 空) |
|
||||
| `make build` | 预期失败:`docker not found`(Makefile 显式报错) |
|
||||
| 默认 FROM | **未修改** |
|
||||
|
||||
### 后续建议(Victor)
|
||||
|
||||
1. 在有 Docker 且能访问腾讯云 TCR 平台镜像的环境执行 `make build`
|
||||
2. 若 `docker pull` 平台 base 失败:把完整错误贴本文件「拉取失败记录」,仍保持默认 FROM
|
||||
3. 无镜像时用本地验收:`STRATEGY_ID=test make smoke-health` / `make test`
|
||||
|
||||
## 拉取失败记录
|
||||
|
||||
(尚无 Docker,无 pull 日志。有 Docker 后在此追加。)
|
||||
|
||||
## 2026-10-16 13:46 Asia/Shanghai — `make build` 实测
|
||||
|
||||
```text
|
||||
ERROR: docker not found. See docs/build-notes.md
|
||||
make: *** [Makefile:19: build] Error 1
|
||||
```
|
||||
|
||||
- 原因:box 无 Docker 引擎/CLI,**未发生**平台 base `docker pull`(因此无 TCR 拉取错误日志)
|
||||
- 默认 `FROM modelhubxc-4pd.tencentcloudcr.com/xc_agent_platform/python:3.11-slim` **未改**
|
||||
- 替代验收:`make test` 绿;`STRATEGY_ID=test make smoke-health` 绿(本地 `python -m src.server`)
|
||||
|
||||
## 2026-10-16 Asia/Shanghai — Victor Mac `make build`
|
||||
|
||||
- Docker Desktop:已连接
|
||||
- 结果:失败 — `modelhubxc-4pd.tencentcloudcr.com/xc_agent_platform/python:3.11-slim` pull access denied / insufficient_scope
|
||||
- 默认 FROM:未修改
|
||||
|
||||
## 2026-10-16 Asia/Shanghai — Codex 沙箱复测
|
||||
|
||||
- `make build` 实际退出 2:`ERROR: docker not found. See docs/build-notes.md`。
|
||||
- 无 Docker,未尝试拉取 TCR;本机结果不能证明 TCR 可达或不可达。上文 Mac 的拒绝记录为已有人工证据,未在本轮复现。
|
||||
- `STRATEGY_ID=test make smoke-health` 实际退出 2:沙箱创建 socket 被拒,`PermissionError: [Errno 1] Operation not permitted`。
|
||||
- `make test`:优化后 19 项中 18 项通过,SIGTERM 集成项在监听前同样被 socket 权限阻塞;未跳过或标绿。
|
||||
- 默认平台 base / FROM 保持原样;须在允许本地 socket、具备 Docker 与 TCR 权限的环境复验完整 DoD。
|
||||
|
||||
## 2026-10-16 ~15:20 Asia/Shanghai — tcr-then-build 探测(Mac)
|
||||
|
||||
- Docker Desktop:已连接;`docker` CLI 可用
|
||||
- `~/.docker/config.json`:`auths` 空,`credsStore=desktop` → **未登录** TCR
|
||||
- `docker pull modelhubxc-4pd.tencentcloudcr.com/xc_agent_platform/python:3.11-slim`:
|
||||
`Error response from daemon: pull access denied ... may require 'docker login'`
|
||||
- 默认 FROM:**未修改**
|
||||
- 既有 `agent-contrib:local`(sha256:95a4d01e2b55…):**不算**本轮 DoD(CMD=`src.main`,基底公网 python:3.11-slim)
|
||||
- 验收标准:`/Users/vc/modelhub-adapt-logs/agent-image-dod-2026-10-16.md`(box 同源 `/workspace/modelhub-adapt/logs/agent-image-dod-2026-10-16.md`)
|
||||
- 阻塞:需 Victor 提供 TCR 账号并对 `xc_agent_platform/python` 有 pull,执行 `docker login modelhubxc-4pd.tencentcloudcr.com` 后重试 pull + `make build`
|
||||
40
docs/diff-vs-demo.md
Normal file
40
docs/diff-vs-demo.md
Normal file
@@ -0,0 +1,40 @@
|
||||
# 对照官方演示仓 `luopingyi/xc_agent_platform_demo`
|
||||
|
||||
- 日期:2026-10-16 Asia/Shanghai
|
||||
- 官方演示:https://dev.modelhub.org.cn/luopingyi/xc_agent_platform_demo
|
||||
- 安全探针参照:`huni/huni-probe-agent`(只读)
|
||||
- **不要照搬**:`huni/huni-adapt-agent` 默认真提交循环
|
||||
|
||||
## 对齐项(保留)
|
||||
|
||||
| 项 | demo / 规划 | 本仓 |
|
||||
|----|-------------|------|
|
||||
| 根目录 Dockerfile | 是 | 是 |
|
||||
| 默认 base 镜像 | 平台 `python:3.11-slim` | 同(`BASE_IMAGE` 仅 build-arg,默认不改公网) |
|
||||
| `EXPOSE 8080` | 是 | 是 |
|
||||
| `GET /health` → 200 `{"status":"ok"}` | 是 | 是 |
|
||||
| 读 `EXTERNAL_SERVICE_TOKEN` 是否存在 | demo | `/status` 布尔;永不打值 |
|
||||
| stdlib / 轻依赖 | demo 极简 | Phase1 仅 stdlib |
|
||||
|
||||
## 本仓相对 demo 的补强
|
||||
|
||||
| 项 | 说明 |
|
||||
|----|------|
|
||||
| `STRATEGY_ID` 启动校验 | Phase1:**缺失则 exit ≠0**(产品规划;相对「仅读 token 保活」的社区变体) |
|
||||
| 双重 live 闸门 | `ALLOW_LIVE_SUBMIT` + `LIVE_CONFIRM=I_CONFIRM_LIVE_SUBMIT` |
|
||||
| `GET /status` | 仅布尔字段 |
|
||||
| dry-run 报告 | `scripts/dry_run.py` → `reports/dry-run-*.md` |
|
||||
| 单测 | health / 缺 STRATEGY_ID / 闸门默认拒绝 / SIGTERM |
|
||||
| 无默认真提交 | live 仅闸门 + **注入假客户端**单测;仓库无默认真打 `/api/adapt/task/add` 的 HTTP 客户端 |
|
||||
|
||||
## 明确不照搬
|
||||
|
||||
| 来源 | 行为 | 本仓 |
|
||||
|------|------|------|
|
||||
| huni-adapt-agent | 默认真提交循环 | **禁止** |
|
||||
| CoolBoy / 社区刷分脚本 | 绕队列 / 无闸门 | **禁止** |
|
||||
| 旧对话口径「缺 STRATEGY_ID 保活 + /health 仍 200」 | 与产品规划 Phase1 冲突 | **以产品规划为准:启动失败** |
|
||||
|
||||
## 资源声明
|
||||
|
||||
文档按约 **100m–1 CPU / 256–512Mi** 设计;Phase1 不做 k8s manifests。
|
||||
51
docs/gpu-perf-order.md
Normal file
51
docs/gpu-perf-order.md
Normal file
@@ -0,0 +1,51 @@
|
||||
# GPU 缺卡序(契约)
|
||||
|
||||
- 日期:2026-10-16 Asia/Shanghai
|
||||
- 对齐:模盒产品经理 + 模盒积分
|
||||
- 正式性能表:**无** → 报告字段 `perf_order=unset`(勿写成官方 TPS 排名)
|
||||
- 缺卡补齐所用序:**经验序 / 待平台核实**(下表)— 产品要求排序器按此序;非站内正式性能榜
|
||||
|
||||
## A. 正式性能序
|
||||
|
||||
| 优先级 | 展示名 | targetGpu | 依据 |
|
||||
|--------|--------|-----------|------|
|
||||
| — | — | — | 模盒积分定稿:无正式卡间性能表 → `perf_order=unset` |
|
||||
|
||||
## B. 缺卡经验序(排序器用 · 待平台核实)
|
||||
|
||||
跨卡总策略优先于本序:已验证/已下载落点 → 只打**未适配卡**;跳过正在验证 / 已验证成功 / 唯一性失败 / 同卡已知失败禁重试;队列 ≥95 停交(live)。
|
||||
|
||||
| 优先级(高→低) | 平台展示名 | targetGpu(已观察,待再核) | 备注 |
|
||||
|-----------------|------------|------------------------------|------|
|
||||
| 1(一梯队并列) | 壁砺166M | `Biren_166m` | ≈ 曦望 S2;社区成功量壁砺更高 |
|
||||
| 1(一梯队并列) | 曦望 S2 | `Sunrise_pt-200-x1`(抓包证实) | 与壁砺并列,勿臆造先后「性能」 |
|
||||
| 2 | 天垓150 | Iluvatar 天垓族(字符串待核) | 条件回退;饱和+唯一性碰撞多 |
|
||||
| 3 | 天垓100 | (待核) | 一般不扇出 |
|
||||
| 4 | 智铠 mrv-100 | `Iluvatar_mrv-100` | 我方唯一成功样本族;不当最快卡宣传 |
|
||||
|
||||
并列一梯队时:若 pending `try-next` 已给出相对顺序则保留;否则可按「壁砺 / 曦望」与池内缺口并列候选,报告标 `order_source=experience`。
|
||||
|
||||
## C. 映射备忘(非排名)
|
||||
|
||||
| 展示名 | 提交字段 | 备注 |
|
||||
|--------|----------|------|
|
||||
| 曦望 S2 | `Sunrise_pt-200-x1` | 2026-10-16 build-config query 抓包证实;非性能排名 |
|
||||
| (docs sample) | `MetaX_c-500` | 与中文悬赏卡无已核实映射 |
|
||||
|
||||
## D. 依据文件(工作流/观察,非官方性能榜)
|
||||
|
||||
- `/workspace/modelhub-adapt/pending-submit.md`
|
||||
- `/workspace/modelhub-adapt/submit-plan-2026-10-15-v2.md`
|
||||
- `/workspace/modelhub-adapt/uniqueness-collision-notes-2026-10-15-eve.md`
|
||||
- `/workspace/modelhub-adapt/gpu-skip-patterns-xiwang-vs-bili-2026-10-15-eve2.md`
|
||||
|
||||
## E. configParams 缺口(产品补充)
|
||||
|
||||
- 结论:**API**,未公开文档但已抓包证实,依据 [autoconfig-capture-2026-10-16.md](/workspace/modelhub-adapt/logs/autoconfig-capture-2026-10-16.md)。
|
||||
- `POST /api/adapt/task/build-config`,query 为 `gpuType` / `framework` / `taskType`,空 body;成功 JSON `code=0`,`data` 为 YAML。
|
||||
- UI 无「自动配置」标签;选择框架触发 effect 填入 configParams。模型地址不进入该请求。
|
||||
- 抓包观察 Authorization(值未记录);容器默认 Xc-Token 社区实践,可显式切换 Authorization,尚无 token 鉴权实证。
|
||||
- 默认 dry-run:`resolve_token()` 成功时优先 build-config;失败回退 sample,逐条报告 configParams_source、GAP 和 fallback reason。无 token → sample。CONFIG_PARAMS_SOURCE=sample 强制离线;=build-config 强制 API 路径(dry-run with_meta 仍可回退)。make build-config-dry 保持失败非零退出。
|
||||
- API gpuType 仅映射壁砺/壁砺166M/Biren_166m 与曦望/曦望 S2/Sunrise_pt-200-x1;未知卡不请求 API,报告 GAP: gpu enum unmapped。
|
||||
- 选策优化后仍为 experience_order,perf_order=unset;order_source=experience;无正式性能表。Section A 仅按 foothold 文本将 verified_reuse 提前,其余 A 保持文件序,再接 B。API foothold evidence: GAP (not wired)。
|
||||
- **live 前必须有 token + API 调用实证**;sample 单独不是 production-ready。队列 ≥95 继续禁 live,本轮无 live。
|
||||
47
docs/issues.md
Normal file
47
docs/issues.md
Normal file
@@ -0,0 +1,47 @@
|
||||
# Issue / Phase 清单
|
||||
|
||||
对齐 PRD M0–M4 与产品规划 Phase 0–5。
|
||||
|
||||
## Phase / Milestone 映射
|
||||
|
||||
| Phase(产品规划) | PRD | 状态(本仓) |
|
||||
|-------------------|-----|--------------|
|
||||
| Phase 0 调研冻结 | M0 | 文档已落 `docs/` |
|
||||
| Phase 1 本地可部署样例 | M1 | **本轮交付** |
|
||||
| Phase 2 Dry-run 闭环 | M2 | 已实现 pending A→B 解析、名称硬门/禁提过滤与 dry-run;元数据 PASS 仍需人工核实 |
|
||||
| Phase 3 人工注册 + 只读探针 | M3 | 仅 runbook / api-probe-design;**不代注册** |
|
||||
| Phase 4 一次 live 验证 | M4 | 闸门已备;客户端已实现;默认关闭,必须显式注入 |
|
||||
| Phase 5 规模化 | — | 未开 |
|
||||
|
||||
## P0 Issues
|
||||
|
||||
- [x] docs: 冻结智能体平台契约(health/STRATEGY_ID/SIGTERM/资源)
|
||||
- [x] docs: 对照 xc_agent_platform_demo 写 diff-vs-demo
|
||||
- [x] chore: 初始化 Dockerfile / Makefile / example.env
|
||||
- [x] feat: GET /health 200 + STRATEGY_ID 校验(缺则启动失败)
|
||||
- [x] feat: SIGTERM 优雅退出(≤30s;测试 <5s)
|
||||
- [x] feat: dry-run 报告生成器(默认模式)
|
||||
- [x] feat: live 人工确认闸门 + 单测(默认拒绝)
|
||||
- [x] docs: 注册智能体 runbook — 仅人工
|
||||
- [x] chore: tag_release(只打本地 tag,不 push / 不注册)
|
||||
- [x] docs: api-probe-design(禁止代调写接口)
|
||||
|
||||
Phase1 构建与运行验收须独立记录;环境阻塞不等于通过。
|
||||
|
||||
## P1
|
||||
|
||||
- [x] 对接 `/workspace/modelhub-adapt/pending-submit.md` A→B 只读
|
||||
- [ ] 结构化 JSON 日志(禁密钥)
|
||||
- [ ] evidence-agent 模板填写
|
||||
|
||||
## P2(未做)
|
||||
|
||||
- [ ] 贡献台账 CSV
|
||||
- [ ] 多 Tag 矩阵
|
||||
|
||||
## 硬边界(持续)
|
||||
|
||||
- 无 register / submit / deploy / push Makefile 目标
|
||||
- 无 `/agent_platform/strategies*` 写调用
|
||||
- `/api/adapt/task/add` 客户端默认不调用;双闸门、队列≥95 阻断、每进程最多一次;本轮未授权真网
|
||||
- 适配 W1 优先;不抢队列
|
||||
43
docs/kickoff-for-victor.md
Normal file
43
docs/kickoff-for-victor.md
Normal file
@@ -0,0 +1,43 @@
|
||||
# 开工包(一页)— Victor
|
||||
|
||||
**仓路径(本地)**:`/workspace/modelhub-agent-contrib/`
|
||||
**远程**:Gitea 命名空间/仓名 **未定** → Phase1 以本地验收为主
|
||||
**模式**:默认 dry-run;**不代注册、不代提交**
|
||||
|
||||
## 闸门
|
||||
|
||||
| 条件 | 值 |
|
||||
|------|-----|
|
||||
| `ALLOW_LIVE_SUBMIT` | 默认 `0` |
|
||||
| `LIVE_CONFIRM` | 空;live 须 `I_CONFIRM_LIVE_SUBMIT` |
|
||||
| `STRATEGY_ID` | **启动必需**;缺失 → exit ≠0 |
|
||||
| 真实 `task/add` | Phase1 **未实现**(仅假客户端单测) |
|
||||
|
||||
## 本地命令
|
||||
|
||||
```bash
|
||||
cd /workspace/modelhub-agent-contrib
|
||||
make test
|
||||
make build # 需 Docker + 可达平台 base;失败见 docs/build-notes.md
|
||||
make smoke-health # 无镜像时脚本会拉起本地 server
|
||||
make dry-run # 生成 reports/dry-run-*.md
|
||||
```
|
||||
|
||||
入口:`python -m src.server`(Dockerfile `CMD` 同)
|
||||
|
||||
## 验收勾选(Phase1)
|
||||
|
||||
- [ ] `make test` 绿(health / 缺 STRATEGY_ID / 闸门拒绝 / SIGTERM)
|
||||
- [ ] `make build` 绿 **或** `docs/build-notes.md` 记录平台镜像拉取失败且 **未改默认 FROM**
|
||||
- [ ] `make smoke-health` 绿(镜像或本地 server)
|
||||
- [ ] 根目录 Dockerfile + `EXPOSE 8080`
|
||||
- [ ] README 写清:发布 = 0 分;积分待核实;不代注册/提交
|
||||
- [ ] Makefile **无** register/submit/deploy/push
|
||||
- [ ] dry-run 报告含「需 Victor 人工提交」「积分:待平台核实」
|
||||
- [ ] 未调用任何 ModelHub 写接口
|
||||
|
||||
## 人工下一步(非本 Phase 自动化)
|
||||
|
||||
1. 定 Gitea `<namespace>/<repo>`
|
||||
2. push + tag(`scripts/tag_release.py` 仅本地 tag)
|
||||
3. 控制台新增智能体(见 `docs/register-runbook.md`)
|
||||
62
docs/platform-contract-agent.md
Normal file
62
docs/platform-contract-agent.md
Normal file
@@ -0,0 +1,62 @@
|
||||
# 平台契约 — 适配智能体(Phase1)
|
||||
|
||||
- 日期:2026-10-16 Asia/Shanghai
|
||||
- 依据:产品规划 `agent-product-plan-2026-10-16.md` §1 + PRD `02-agent-contribution-prd.md`
|
||||
- **冲突裁决:适配 W1 优先**(队列 ≥95 禁 live;本骨架默认 dry-run)
|
||||
|
||||
## 核实等级
|
||||
|
||||
| 等级 | 含义 |
|
||||
|------|------|
|
||||
| **A** | 官方演示仓 / 主站前端明文 |
|
||||
| **B** | PRD 已核实(docs/6 + 控制台,基线 2026-10-12) |
|
||||
| **C** | 社区样例,非平台承诺 |
|
||||
| **D** | 待核实 |
|
||||
|
||||
## 运行契约
|
||||
|
||||
| 项 | 内容 | 等级 |
|
||||
|----|------|------|
|
||||
| 代码托管 | `dev.modelhub.org.cn` 用户仓 | B |
|
||||
| 注册 UI | 名称、仓库地址、**Git Tag**(不可用分支名) | B |
|
||||
| 构建 | 平台 Kaniko,`refs/tags/<tag>` | B |
|
||||
| Dockerfile | **仓库根目录**;base `modelhubxc-4pd.tencentcloudcr.com/xc_agent_platform/python:3.11-slim` | A |
|
||||
| 端口 | **8080**,`EXPOSE 8080` | A |
|
||||
| 健康检查 | `GET /health` → 200 `{"status":"ok"}` | A |
|
||||
| 可选状态 | `GET /status` → 布尔 `strategy_id_present` / `external_service_token_present`(**不回传值**) | 本仓 Phase1 |
|
||||
| 优雅退出 | `SIGTERM`,约 **≤30s** 平台窗口;本实现目标 ~1s 退出主循环 | B |
|
||||
| 平台注入 | `STRATEGY_ID`;`EXTERNAL_SERVICE_TOKEN`(及社区别名) | A/B |
|
||||
| **STRATEGY_ID 缺失** | **Phase1:进程启动失败(exit ≠0)** | 产品规划 Phase1 + PRD |
|
||||
| 资源 | 约 100m–1 CPU / 256–512Mi | B |
|
||||
| **发布智能体得分** | **0 分**(发布 ≠ 得分) | B |
|
||||
| Live 默认 | **关**;双重闸门 `ALLOW_LIVE_SUBMIT=1` + `LIVE_CONFIRM=I_CONFIRM_LIVE_SUBMIT` | 本仓 |
|
||||
| 积分 | 来自**成功适配**;智能体代提成功计同一成功分;公式/周报 **待平台核实** | B / D |
|
||||
|
||||
## 鉴权双轨(文档索引,Phase1 不代调)
|
||||
|
||||
| 场景 | 头 | 等级 |
|
||||
|------|----|------|
|
||||
| 浏览器 / `agent_platform` | `Authorization: Bearer <login token>` | A |
|
||||
| 容器内社区实践 | `Xc-Token: <token>`;body 带 `strategyId` | C |
|
||||
|
||||
## 禁止
|
||||
|
||||
- 代注册、代 live 提交、Makefile 含 register/submit/deploy/push
|
||||
- 日志/响应/镜像层写入 token 或 STRATEGY_ID **值**
|
||||
- 把「智能体已发布」写入千分进度
|
||||
|
||||
## 冲突裁决(强制)
|
||||
|
||||
| 资源 | 裁决 |
|
||||
|------|------|
|
||||
| 异步验证队列 | 适配 W1 优先;≥95 全体停交(含智能体 live) |
|
||||
| Codex | hold 期扩池/归因 > 智能体脚手架 |
|
||||
| 本骨架 | 默认 dry-run;本轮无真实 `task/add` HTTP 客户端 |
|
||||
|
||||
## 闸门配置以实现为准
|
||||
|
||||
`src/gate.py` 只接受 `ALLOW_LIVE_SUBMIT=1` 与
|
||||
`LIVE_CONFIRM=I_CONFIRM_LIVE_SUBMIT`(去除首尾空白后精确匹配)。
|
||||
PRD 的 `ALLOW_LIVE_SUBMIT=true` / `CONFIRM_LIVE=YES` 仅为需求示例,
|
||||
本仓不支持这些值/别名,也不读取确认文件。开闸无客户端仍 blocked。
|
||||
这只是本地逻辑闸门,不代表已获 live 授权或已校验队列与候选硬门。
|
||||
39
docs/register-runbook.md
Normal file
39
docs/register-runbook.md
Normal file
@@ -0,0 +1,39 @@
|
||||
# 注册智能体 Runbook(仅人工 · Victor)
|
||||
|
||||
> Agent / Bot **不代填、不代点、不代调写接口**。
|
||||
|
||||
## 流程
|
||||
|
||||
1. **本地绿**:`make test`(及有 Docker 时 `make build` + `make smoke-health`)
|
||||
2. **Gitea 建仓**(Victor):`dev.modelhub.org.cn/<namespace>/<repo>`
|
||||
- 命名空间/仓名 **未定**时:仅本地验收,不阻塞 Phase1
|
||||
3. **推送代码**(Victor 本人):本 Makefile **无 push 目标**
|
||||
4. **打 Git Tag**(可用本仓 `scripts/tag_release.py` **仅本地 tag**;push tag 由 Victor 执行)
|
||||
5. **控制台新增**:个人主页 → 我的适配智能体 → 新增
|
||||
- 名称
|
||||
- 仓库地址(远程 Git URL)
|
||||
- **Git Tag**(须先出现在远程;`GET .../tags` 下拉可选后再填)
|
||||
6. **Kaniko 构建**:等待状态;证据同时记中文文案与枚举(`building` / `ready` / `failed` / `running` / `stopped`)
|
||||
7. **部署后**:确认容器 `GET /health` → 200;积分应 **无变化**(发布 = 0 分)
|
||||
|
||||
## POST `/agent_platform/strategies`(文档说明 · 禁止代调)
|
||||
|
||||
| 字段 | 说明 |
|
||||
|------|------|
|
||||
| `name` | 策略显示名 |
|
||||
| `repo_url` | Gitea 仓库 URL |
|
||||
| `tag` | Git Tag(非分支) |
|
||||
|
||||
成功响应含 `.id`(等级 A:前端 bundle)。
|
||||
**本仓与 Agent 禁止代调该写接口。**
|
||||
|
||||
相关写接口(同样禁止代调):`/{id}/deploy`、`/{id}/stop`、`DELETE /{id}`。
|
||||
|
||||
## 环境变量(平台注入 / 控制台)
|
||||
|
||||
| 变量 | 说明 |
|
||||
|------|------|
|
||||
| `STRATEGY_ID` | 策略 id;本仓启动必需 |
|
||||
| `EXTERNAL_SERVICE_TOKEN` | 服务凭证;只检存在,不记值 |
|
||||
| `ALLOW_LIVE_SUBMIT` | 默认 `0` |
|
||||
| `LIVE_CONFIRM` | live 时须为 `I_CONFIRM_LIVE_SUBMIT` |
|
||||
14
docs/tag-dryrun-notes-draft.md
Normal file
14
docs/tag-dryrun-notes-draft.md
Normal file
@@ -0,0 +1,14 @@
|
||||
# Tag 文案草稿(仍默认 dry-run)
|
||||
|
||||
- 建议 Tag:`v0.2.0-phase2-dryrun`
|
||||
- 基线:控制台当前 `v0.1.0-phase1` @ `0d0f3b6`
|
||||
- 相对 Phase1:pending **Section A** + 经验序;只读 `task/page` 探针;`build-config` 客户端(默认离线 sample,opt-in 才调 API);`task/add` 双重闸门默认关
|
||||
- **不含**:live 开闸、默认真实提交
|
||||
- 推送:仅 Victor 本人;Agent 不代 push
|
||||
- 队列≥95 / 无书面批准:**不开闸**
|
||||
|
||||
检查清单:
|
||||
1. `make test` 42/42
|
||||
2. `ALLOW_LIVE_SUBMIT` 默认非 1
|
||||
3. 重建后 `/health` 200;`/status` token/strategy 布尔
|
||||
4. 不代注册、不代 live
|
||||
70
main.py
70
main.py
@@ -1,70 +0,0 @@
|
||||
import json
|
||||
import os
|
||||
import signal
|
||||
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
|
||||
|
||||
|
||||
HOST = "0.0.0.0"
|
||||
PORT = 8080
|
||||
shutdown_requested = False
|
||||
|
||||
|
||||
def _config() -> dict:
|
||||
token = os.getenv("EXTERNAL_SERVICE_TOKEN", "")
|
||||
return {
|
||||
"external_service_token_present": bool(token),
|
||||
}
|
||||
|
||||
|
||||
class Handler(BaseHTTPRequestHandler):
|
||||
def do_GET(self) -> None:
|
||||
if self.path == "/health":
|
||||
self._send_json({"status": "ok"})
|
||||
return
|
||||
|
||||
if self.path == "/":
|
||||
self._send_json(
|
||||
{
|
||||
"name": "strategy-demo",
|
||||
"status": "running",
|
||||
"config": _config(),
|
||||
}
|
||||
)
|
||||
return
|
||||
|
||||
self._send_json({"error": "not found"}, status=404)
|
||||
|
||||
def log_message(self, fmt: str, *args: object) -> None:
|
||||
print(f"{self.address_string()} - {fmt % args}", flush=True)
|
||||
|
||||
def _send_json(self, body: dict, status: int = 200) -> None:
|
||||
payload = json.dumps(body).encode()
|
||||
self.send_response(status)
|
||||
self.send_header("Content-Type", "application/json")
|
||||
self.send_header("Content-Length", str(len(payload)))
|
||||
self.end_headers()
|
||||
self.wfile.write(payload)
|
||||
|
||||
|
||||
def _handle_signal(signum: int, _frame: object) -> None:
|
||||
global shutdown_requested
|
||||
shutdown_requested = True
|
||||
print(f"received signal {signum}, shutting down", flush=True)
|
||||
|
||||
|
||||
def main() -> None:
|
||||
signal.signal(signal.SIGTERM, _handle_signal)
|
||||
signal.signal(signal.SIGINT, _handle_signal)
|
||||
|
||||
server = ThreadingHTTPServer((HOST, PORT), Handler)
|
||||
server.timeout = 1
|
||||
print(f"strategy-demo listening on {HOST}:{PORT}", flush=True)
|
||||
|
||||
while not shutdown_requested:
|
||||
server.handle_request()
|
||||
|
||||
server.server_close()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
0
reports/.gitkeep
Normal file
0
reports/.gitkeep
Normal file
@@ -1 +0,0 @@
|
||||
|
||||
26
scripts/build_config_dry.py
Normal file
26
scripts/build_config_dry.py
Normal file
@@ -0,0 +1,26 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Generate config only; never creates a task or prints returned YAML/secrets."""
|
||||
import argparse
|
||||
import sys
|
||||
from pathlib import Path
|
||||
sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
|
||||
from src.build_config_client import build_config, BuildConfigError
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(description=__doc__)
|
||||
parser.add_argument('--gpu-type', default='Sunrise_pt-200-x1')
|
||||
parser.add_argument('--framework', default='vllm')
|
||||
parser.add_argument('--task-type', default='text-generation')
|
||||
args = parser.parse_args()
|
||||
try:
|
||||
yaml = build_config(args.gpu_type, args.framework, args.task_type)
|
||||
except BuildConfigError as error:
|
||||
print(str(error), file=sys.stderr)
|
||||
return 1
|
||||
print(f'configParams_source=build-config; generated YAML characters={len(yaml)}; no task submitted')
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
sys.exit(main())
|
||||
88
scripts/dry_run.py
Executable file
88
scripts/dry_run.py
Executable file
@@ -0,0 +1,88 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Read-only Phase2 pending draft report. Token-resolvable build-config first; explicit sample fallback."""
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
from zoneinfo import ZoneInfo
|
||||
|
||||
ROOT = Path(__file__).resolve().parents[1]
|
||||
sys.path.insert(0, str(ROOT))
|
||||
from src.pending_pool import build_ordered_candidates, input_path, experience_order
|
||||
from src.config_params import build_config_params_with_meta, SOURCE, GAP
|
||||
from src.queue_depth import queue_depth
|
||||
from src.task_add_client import build_payload
|
||||
|
||||
TZ = ZoneInfo('Asia/Shanghai')
|
||||
|
||||
|
||||
def _load_candidates(path):
|
||||
data = json.loads(path.read_text())
|
||||
return data if isinstance(data, list) else list(data['candidates'])
|
||||
|
||||
|
||||
def _render(candidates, ts, src):
|
||||
candidates = [c for c in candidates if not os.environ.get('PENDING_SECTION') or
|
||||
c.get('section', 'B') == os.environ['PENDING_SECTION'].strip().upper()]
|
||||
depth = queue_depth()
|
||||
lines = [f'# 代提候选 / 需 Victor 确认 — Dry-run — {ts} (Asia/Shanghai)', '',
|
||||
'> 模式:dry-run;仅配置生成 API;无任务提交;需 Victor 人工提交/确认',
|
||||
'> 积分:待平台核实', '> perf_order=unset;order_source=experience(经验序 / 待平台核实)',
|
||||
f'> configParams source: {SOURCE}', '> API foothold evidence: GAP (not wired)', f'> {GAP}', '',
|
||||
'## A→B 顺序草稿', '', f'输入:{src};候选条数:{len(candidates)}',
|
||||
f'队列深度:{depth if depth is not None else "未知,需人工确认"}',
|
||||
'队列≥95:禁 live;适配 W1 优先,不抢空位。', '']
|
||||
if depth is not None and depth >= 95:
|
||||
lines.extend(['> **禁 live / 队列≥95**', ''])
|
||||
for i, c in enumerate(candidates, 1):
|
||||
model = c.get('model_address') or c.get('modelAddress') or c.get('model_id') or '<MODEL>'
|
||||
gpus = experience_order(c.get('try_next_gpus', []))
|
||||
target = gpus[0] if gpus else c.get('targetGpu', '<TARGET_GPU:需人工确认>')
|
||||
status = c.get('status', 'needs_human')
|
||||
lines.extend([f'### {i}. Section {c.get("section", "B")} — `{model}`', '',
|
||||
f'状态:{status};needs_human={c.get("needs_human", True)}',
|
||||
f'过滤:{c.get("skip_reason") or "名称硬门未命中;元数据/唯一性待人工核实"}', ''])
|
||||
lines.extend([f'未适配卡(仅 pending 缺口):{", ".join(gpus) or "未提供,需确认"}',
|
||||
'perf_order=unset;order_source=experience;天垓100 一般不扇出', ''])
|
||||
yaml, meta = build_config_params_with_meta(target)
|
||||
lines.extend([f'foothold_class={c.get("foothold_class", "unknown")}; evidence_source={c.get("evidence_source", "GAP")}; no_download={c.get("no_download", False)}',
|
||||
'; '.join(f'{key}={value}' for key, value in meta.items()), ''])
|
||||
draft = build_payload(model, target, 'vllm', strategy_id='<STRATEGY_ID>',
|
||||
config_params=yaml)
|
||||
# Display only; this truncated draft must never be submitted.
|
||||
draft['configParams'] = draft['configParams'][:400] + '\n… [truncated; dry-run only]'
|
||||
lines.extend(['build-config query: gpuType=<targetGpu>&framework=vllm&taskType=text-generation; POST empty body', 'POST 字段草稿(skipped 行禁止提交):', '```json', json.dumps(draft, ensure_ascii=False, indent=2), '```',
|
||||
'需 Victor 人工提交/确认;积分:待平台核实', ''])
|
||||
report = '\n'.join(lines)
|
||||
# Defensive redaction even if an input happens to contain an injected credential.
|
||||
secrets = [os.environ.get(k, '') for k in ('XC_TOKEN', 'MODELHUB_XC_TOKEN', 'EXTERNAL_SERVICE_TOKEN', 'Xc-Token')]
|
||||
if os.environ.get('XC_TOKEN_FILE'):
|
||||
try:
|
||||
secrets.append(Path(os.environ['XC_TOKEN_FILE']).read_text().strip())
|
||||
except OSError:
|
||||
pass
|
||||
for secret in secrets:
|
||||
if secret:
|
||||
report = report.replace(secret, '[REDACTED]')
|
||||
return report
|
||||
|
||||
|
||||
def main():
|
||||
md = input_path('PENDING_SUBMIT_MD', 'pending-submit.md')
|
||||
txt = input_path('PENDING_SUBMIT_TXT', 'pending-submit.txt')
|
||||
if md.is_file() or txt.is_file():
|
||||
src = md if md.is_file() else txt
|
||||
candidates = build_ordered_candidates(md, txt)
|
||||
else:
|
||||
src = Path(os.environ.get('DRY_RUN_CANDIDATES', ROOT / 'config/candidates.example.json'))
|
||||
candidates = _load_candidates(src)
|
||||
now = datetime.now(TZ)
|
||||
out = ROOT / 'reports' / f'dry-run-{now:%Y%m%d-%H%M%S}.md'
|
||||
out.parent.mkdir(exist_ok=True)
|
||||
out.write_text(_render(candidates, now.strftime('%Y-%m-%d %H:%M:%S'), src), encoding='utf-8')
|
||||
print(f'Wrote {out}')
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
17
scripts/probe_readonly.py
Normal file
17
scripts/probe_readonly.py
Normal file
@@ -0,0 +1,17 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Run only the task/page GET; print credential-free summary."""
|
||||
import json
|
||||
import sys
|
||||
from pathlib import Path
|
||||
sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
|
||||
from src.readonly_probe import probe_readonly
|
||||
|
||||
|
||||
def main():
|
||||
result = probe_readonly()
|
||||
print(json.dumps(result, ensure_ascii=False))
|
||||
return 0 if result['auth_ok'] else 1
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
sys.exit(main())
|
||||
100
scripts/smoke_health.py
Executable file
100
scripts/smoke_health.py
Executable file
@@ -0,0 +1,100 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Smoke: GET /health must return 200 {"status":"ok"}.
|
||||
|
||||
Usage:
|
||||
# Against already-running server:
|
||||
SMOKE_BASE_URL=http://127.0.0.1:8080 python3 scripts/smoke_health.py
|
||||
|
||||
# Or let this script start a local server (needs STRATEGY_ID):
|
||||
STRATEGY_ID=test python3 scripts/smoke_health.py
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import os
|
||||
import signal
|
||||
import subprocess
|
||||
import sys
|
||||
import time
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
from pathlib import Path
|
||||
|
||||
ROOT = Path(__file__).resolve().parents[1]
|
||||
|
||||
|
||||
def _get(url: str, timeout: float = 2.0) -> tuple[int, dict]:
|
||||
req = urllib.request.Request(url, method="GET")
|
||||
with urllib.request.urlopen(req, timeout=timeout) as resp:
|
||||
body = resp.read().decode("utf-8")
|
||||
return resp.status, json.loads(body)
|
||||
|
||||
|
||||
def _wait_health(base: str, attempts: int = 30) -> None:
|
||||
url = base.rstrip("/") + "/health"
|
||||
last_err: Exception | None = None
|
||||
for _ in range(attempts):
|
||||
try:
|
||||
code, data = _get(url)
|
||||
if code == 200 and data.get("status") == "ok":
|
||||
print(f"OK: GET {url} -> {code} {data}")
|
||||
return
|
||||
raise AssertionError(f"unexpected response: {code} {data}")
|
||||
except (urllib.error.URLError, ConnectionError, AssertionError, TimeoutError) as exc:
|
||||
last_err = exc
|
||||
time.sleep(0.2)
|
||||
raise SystemExit(f"smoke-health failed: {last_err}")
|
||||
|
||||
|
||||
def main() -> None:
|
||||
external = os.environ.get("SMOKE_BASE_URL", "").strip()
|
||||
if external:
|
||||
_wait_health(external)
|
||||
# optional status check
|
||||
try:
|
||||
code, data = _get(external.rstrip("/") + "/status")
|
||||
print(f"OK: GET /status -> {code} {data}")
|
||||
except Exception as exc: # noqa: BLE001
|
||||
print(f"WARN: /status check skipped: {exc}", file=sys.stderr)
|
||||
return
|
||||
|
||||
if not os.environ.get("STRATEGY_ID", "").strip():
|
||||
os.environ["STRATEGY_ID"] = "smoke-test-strategy"
|
||||
|
||||
port = os.environ.get("SMOKE_PORT", "18080")
|
||||
env = os.environ.copy()
|
||||
env["PORT"] = port
|
||||
env["HOST"] = "127.0.0.1"
|
||||
env["STRATEGY_ID"] = env.get("STRATEGY_ID") or "smoke-test-strategy"
|
||||
|
||||
proc = subprocess.Popen(
|
||||
[sys.executable, "-m", "src.server"],
|
||||
cwd=str(ROOT),
|
||||
env=env,
|
||||
stdout=subprocess.DEVNULL,
|
||||
stderr=subprocess.PIPE,
|
||||
)
|
||||
try:
|
||||
_wait_health(f"http://127.0.0.1:{port}")
|
||||
code, data = _get(f"http://127.0.0.1:{port}/status")
|
||||
print(f"OK: GET /status -> {code} {data}")
|
||||
assert "strategy_id_present" in data
|
||||
assert data["strategy_id_present"] is True
|
||||
# never assert on secret values — only booleans
|
||||
finally:
|
||||
proc.send_signal(signal.SIGTERM)
|
||||
try:
|
||||
proc.wait(timeout=5)
|
||||
except subprocess.TimeoutExpired:
|
||||
proc.kill()
|
||||
proc.wait(timeout=2)
|
||||
if proc.returncode not in (0, -signal.SIGTERM, signal.SIGTERM):
|
||||
# 0 or terminated by SIGTERM is fine
|
||||
err = (proc.stderr.read() or b"").decode("utf-8", errors="replace")
|
||||
if proc.returncode is not None and proc.returncode > 0:
|
||||
print(f"WARN: server exit code {proc.returncode}: {err}", file=sys.stderr)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
43
scripts/tag_release.py
Executable file
43
scripts/tag_release.py
Executable file
@@ -0,0 +1,43 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Create a local git tag only. Does NOT push. Does NOT register on ModelHub.
|
||||
|
||||
Usage:
|
||||
python3 scripts/tag_release.py v0.1.0
|
||||
python3 scripts/tag_release.py v0.1.0 --message "Phase1 skeleton"
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import subprocess
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
ROOT = Path(__file__).resolve().parents[1]
|
||||
|
||||
|
||||
def main() -> None:
|
||||
parser = argparse.ArgumentParser(description="Local git tag only (no push, no register)")
|
||||
parser.add_argument("tag", help="Tag name, e.g. v0.1.0")
|
||||
parser.add_argument("--message", "-m", default="", help="Annotated tag message")
|
||||
args = parser.parse_args()
|
||||
|
||||
if not (ROOT / ".git").exists():
|
||||
print(
|
||||
"WARN: not a git repository yet. Init locally if needed; "
|
||||
"this script will not push or register.",
|
||||
file=sys.stderr,
|
||||
)
|
||||
# Still attempt so the failure is clear
|
||||
msg = args.message or f"Release {args.tag} (local tag only — no push / no ModelHub register)"
|
||||
cmd = ["git", "tag", "-a", args.tag, "-m", msg]
|
||||
print(f"Running (cwd={ROOT}): {' '.join(cmd)}")
|
||||
print("NOTE: This does NOT git push and does NOT call ModelHub APIs.")
|
||||
result = subprocess.run(cmd, cwd=str(ROOT))
|
||||
if result.returncode != 0:
|
||||
raise SystemExit(result.returncode)
|
||||
print(f"OK: local tag {args.tag!r} created. Push tag yourself when ready for Kaniko.")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
3
src/__init__.py
Normal file
3
src/__init__.py
Normal file
@@ -0,0 +1,3 @@
|
||||
"""ModelHub XC adaptation agent — Phase1 local skeleton."""
|
||||
|
||||
__version__ = "0.1.0"
|
||||
60
src/build_config_client.py
Normal file
60
src/build_config_client.py
Normal file
@@ -0,0 +1,60 @@
|
||||
"""Explicit configuration generation; import performs no I/O.
|
||||
|
||||
Returns YAML on success, otherwise raises BuildConfigError with safe attribution
|
||||
and HTTP/platform status. Server messages and transport details are never exposed.
|
||||
"""
|
||||
import json
|
||||
import os
|
||||
import urllib.error
|
||||
import urllib.parse
|
||||
import urllib.request
|
||||
from src.task_add_client import resolve_token
|
||||
|
||||
|
||||
class BuildConfigError(RuntimeError):
|
||||
def __init__(self, reason, http_status=None, platform_code=None):
|
||||
self.error_attribution = reason
|
||||
self.http_status = http_status
|
||||
self.platform_code = platform_code
|
||||
super().__init__('build-config: ' + reason)
|
||||
|
||||
|
||||
def build_config(gpu_type, framework='vllm', task_type='text-generation'):
|
||||
try:
|
||||
token = resolve_token()
|
||||
except (ValueError, OSError):
|
||||
raise BuildConfigError('missing/invalid credential') from None
|
||||
if not isinstance(gpu_type, str) or not gpu_type.strip() or '<' in gpu_type:
|
||||
raise BuildConfigError('gpu_type required (platform enum)')
|
||||
query = urllib.parse.urlencode(dict(gpuType=gpu_type, framework=framework, taskType=task_type))
|
||||
header = 'Authorization' if os.environ.get('BUILD_CONFIG_USE_AUTHORIZATION') == '1' else 'Xc-Token'
|
||||
try:
|
||||
request = urllib.request.Request(
|
||||
os.environ.get('MODELHUB_API_BASE', 'https://www.modelhub.org.cn').rstrip('/')
|
||||
+ '/api/adapt/task/build-config?' + query,
|
||||
headers={header: token, 'Accept': 'application/json'}, method='POST')
|
||||
with urllib.request.urlopen(request, timeout=30) as response:
|
||||
status, raw = response.status, response.read()
|
||||
except urllib.error.HTTPError as error:
|
||||
status, raw = error.code, error.read()
|
||||
except (OSError, urllib.error.URLError, ValueError):
|
||||
raise BuildConfigError('transport/timeout') from None
|
||||
try:
|
||||
body = json.loads(raw)
|
||||
except (ValueError, UnicodeError):
|
||||
raise BuildConfigError('invalid JSON response', status) from None
|
||||
if not isinstance(body, dict):
|
||||
raise BuildConfigError('invalid response object', status)
|
||||
code = body.get('code')
|
||||
# Only numeric codes are retained; arbitrary server strings may echo secrets.
|
||||
code = code if type(code) is int else None
|
||||
if code in (40100, 40101):
|
||||
raise BuildConfigError({40100: '40100 NOT_LOGIN_ERROR', 40101: '40101 NO_AUTH_ERROR'}[code], status, code)
|
||||
if not 200 <= status < 300 or code != 0:
|
||||
raise BuildConfigError('other HTTP/platform code', status, code)
|
||||
data = body.get('data')
|
||||
if not isinstance(data, str) or not data.strip():
|
||||
raise BuildConfigError('empty/non-str data', status, code)
|
||||
if token in data:
|
||||
raise BuildConfigError('credential echoed in data', status, code)
|
||||
return data
|
||||
66
src/config_params.py
Normal file
66
src/config_params.py
Normal file
@@ -0,0 +1,66 @@
|
||||
"""Dry-run configuration: token-resolvable build-config first; failures fall back to sample with GAP."""
|
||||
import os
|
||||
from pathlib import Path
|
||||
from src.build_config_client import build_config, BuildConfigError
|
||||
from src.task_add_client import resolve_token
|
||||
|
||||
SOURCE = 'POST /api/adapt/task/build-config (discovered via capture); fallback templates/config_params.sample.yaml'
|
||||
GAP = 'GAP: build-config API discovered via capture; sample is dry-run draft only, NOT production-ready. API foothold evidence: GAP (not wired).'
|
||||
GPU_ENUMS = {
|
||||
'壁砺': 'Biren_166m', '壁砺166M': 'Biren_166m', 'Biren_166m': 'Biren_166m',
|
||||
'曦望': 'Sunrise_pt-200-x1', '曦望 S2': 'Sunrise_pt-200-x1',
|
||||
'Sunrise_pt-200-x1': 'Sunrise_pt-200-x1',
|
||||
}
|
||||
|
||||
|
||||
def config_params_source():
|
||||
"""Requested source preference for dry-run.
|
||||
|
||||
- CONFIG_PARAMS_SOURCE=sample → force offline sample
|
||||
- CONFIG_PARAMS_SOURCE=build-config → force API path (with soft fallback in with_meta)
|
||||
- default (empty): prefer build-config when resolve_token() succeeds; else sample
|
||||
- ALLOW_BUILD_CONFIG=1 remains a legacy opt-in synonym when source empty and token ok
|
||||
"""
|
||||
source = os.environ.get('CONFIG_PARAMS_SOURCE', '').strip()
|
||||
if source not in ('', 'sample', 'build-config'):
|
||||
raise BuildConfigError('unsupported CONFIG_PARAMS_SOURCE')
|
||||
if source:
|
||||
return source
|
||||
try:
|
||||
resolve_token()
|
||||
except (ValueError, OSError):
|
||||
return 'sample'
|
||||
# Token resolvable → prefer build-config (kickoff select-opt default).
|
||||
return 'build-config'
|
||||
|
||||
|
||||
def build_config_params_with_meta(gpu_type=None, framework='vllm', task_type='text-generation'):
|
||||
"""Return (YAML, metadata); API failures explicitly fall back for dry-run.
|
||||
|
||||
scripts/build_config_dry.py calls build_config directly and remains strict.
|
||||
"""
|
||||
source = config_params_source()
|
||||
meta = {'configParams_source': 'sample'}
|
||||
try:
|
||||
resolve_token()
|
||||
except (ValueError, OSError):
|
||||
meta['auth'] = 'missing'
|
||||
else:
|
||||
meta['auth'] = 'ok'
|
||||
gpu_enum = GPU_ENUMS.get(gpu_type)
|
||||
if source == 'build-config' and gpu_enum is None:
|
||||
meta['configParams_fallback_reason'] = 'GAP: gpu enum unmapped'
|
||||
elif source == 'build-config':
|
||||
try:
|
||||
yaml = build_config(gpu_enum, framework, task_type)
|
||||
except BuildConfigError as error:
|
||||
meta['configParams_fallback_reason'] = 'GAP: ' + error.error_attribution
|
||||
else:
|
||||
meta['configParams_source'] = 'build-config'
|
||||
return yaml, meta
|
||||
return (Path(__file__).resolve().parents[1] / 'templates/config_params.sample.yaml').read_text(), meta
|
||||
|
||||
|
||||
def build_config_params(gpu_type=None, framework='vllm', task_type='text-generation'):
|
||||
"""Compatible YAML-only dry-run wrapper, including explicit fallback."""
|
||||
return build_config_params_with_meta(gpu_type, framework, task_type)[0]
|
||||
123
src/gate.py
Normal file
123
src/gate.py
Normal file
@@ -0,0 +1,123 @@
|
||||
"""Dual live-submit gate. Default: dry-run / blocked.
|
||||
|
||||
Live is allowed only when ALL of:
|
||||
- ALLOW_LIVE_SUBMIT=1
|
||||
- LIVE_CONFIRM=I_CONFIRM_LIVE_SUBMIT
|
||||
- STRATEGY_ID present
|
||||
|
||||
Phase2 client exists but requires explicit injection. No automatic wiring.
|
||||
Queue ≥95 blocks; at most one injected submit per process.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import threading
|
||||
from .queue_depth import queue_depth
|
||||
from dataclasses import dataclass
|
||||
from typing import Any, Callable, Dict, Optional, Protocol
|
||||
|
||||
from .strategy import strategy_id_present
|
||||
|
||||
_submit_count = 0
|
||||
_submit_lock = threading.Lock()
|
||||
|
||||
LIVE_CONFIRM_VALUE = "I_CONFIRM_LIVE_SUBMIT"
|
||||
|
||||
|
||||
class SubmitClient(Protocol):
|
||||
"""Minimal interface for a submit client (injected fake in tests)."""
|
||||
|
||||
def submit(self, payload: Dict[str, Any]) -> Dict[str, Any]:
|
||||
...
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class GateDecision:
|
||||
mode: str # "dry-run" | "live" | "blocked"
|
||||
allowed: bool
|
||||
reason: str
|
||||
|
||||
|
||||
def _allow_live_flag() -> bool:
|
||||
return os.environ.get("ALLOW_LIVE_SUBMIT", "0").strip() == "1"
|
||||
|
||||
|
||||
def _live_confirm_ok() -> bool:
|
||||
return os.environ.get("LIVE_CONFIRM", "").strip() == LIVE_CONFIRM_VALUE
|
||||
|
||||
|
||||
def evaluate_gate() -> GateDecision:
|
||||
"""Evaluate whether live submit is permitted."""
|
||||
if not strategy_id_present():
|
||||
return GateDecision(
|
||||
mode="blocked",
|
||||
allowed=False,
|
||||
reason="STRATEGY_ID missing or empty",
|
||||
)
|
||||
if not _allow_live_flag():
|
||||
return GateDecision(
|
||||
mode="dry-run",
|
||||
allowed=False,
|
||||
reason="ALLOW_LIVE_SUBMIT is not 1 (default dry-run)",
|
||||
)
|
||||
if not _live_confirm_ok():
|
||||
return GateDecision(
|
||||
mode="blocked",
|
||||
allowed=False,
|
||||
reason=f"LIVE_CONFIRM must be exactly {LIVE_CONFIRM_VALUE!r}",
|
||||
)
|
||||
depth = queue_depth()
|
||||
if depth is None and ("ASYNC_QUEUE_DEPTH" in os.environ or "QUEUE_SNAPSHOT_JSON" in os.environ):
|
||||
return GateDecision("blocked", False, "queue depth invalid/unknown; human confirmation required")
|
||||
if depth is not None and depth >= 95:
|
||||
return GateDecision("blocked", False, "queue ≥95: 禁 live")
|
||||
return GateDecision(
|
||||
mode="live",
|
||||
allowed=True,
|
||||
reason="dual gate open (ALLOW_LIVE_SUBMIT=1 and LIVE_CONFIRM set)",
|
||||
)
|
||||
|
||||
|
||||
def attempt_live_submit(
|
||||
payload: Dict[str, Any],
|
||||
client: Optional[SubmitClient] = None,
|
||||
) -> Dict[str, Any]:
|
||||
"""Attempt a live submit only if the gate opens and a client is injected.
|
||||
|
||||
Phase2 TaskAddClient must be explicitly injected and dual-gated.
|
||||
Tests must use fake clients or mock HTTP only.
|
||||
"""
|
||||
global _submit_count
|
||||
decision = evaluate_gate()
|
||||
if not decision.allowed:
|
||||
return {
|
||||
"ok": False,
|
||||
"mode": decision.mode,
|
||||
"reason": decision.reason,
|
||||
"submitted": False,
|
||||
}
|
||||
if client is None:
|
||||
return {
|
||||
"ok": False,
|
||||
"mode": "blocked",
|
||||
"reason": (
|
||||
"Phase2 task/add client exists; explicit client injection required; "
|
||||
"no real request without injection and dual gate"
|
||||
),
|
||||
"submitted": False,
|
||||
}
|
||||
with _submit_lock:
|
||||
if _submit_count >= 1:
|
||||
return dict(ok=False, mode="blocked", submitted=False,
|
||||
reason="process limit: at most 1 real add")
|
||||
# Reserve before invocation: a transport failure may still have created a task.
|
||||
_submit_count += 1
|
||||
result = client.submit(payload)
|
||||
return {
|
||||
"ok": True,
|
||||
"mode": "live",
|
||||
"reason": decision.reason,
|
||||
"submitted": True,
|
||||
"result": result,
|
||||
}
|
||||
33
src/health.py
Normal file
33
src/health.py
Normal file
@@ -0,0 +1,33 @@
|
||||
"""Health and status HTTP handlers. Never echo secrets."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from typing import Any, Dict, Tuple
|
||||
|
||||
from .strategy import external_service_token_present, strategy_id_present
|
||||
|
||||
|
||||
def health_payload() -> Dict[str, str]:
|
||||
return {"status": "ok"}
|
||||
|
||||
|
||||
def status_payload() -> Dict[str, Any]:
|
||||
"""Booleans only — never include STRATEGY_ID or token values."""
|
||||
return {
|
||||
"strategy_id_present": strategy_id_present(),
|
||||
"external_service_token_present": external_service_token_present(),
|
||||
}
|
||||
|
||||
|
||||
def handle_get(path: str) -> Tuple[int, Dict[str, str], bytes]:
|
||||
"""Return (status_code, headers, body) for GET paths."""
|
||||
headers = {"Content-Type": "application/json; charset=utf-8"}
|
||||
if path == "/health" or path.startswith("/health?"):
|
||||
body = json.dumps(health_payload(), ensure_ascii=False).encode("utf-8")
|
||||
return 200, headers, body
|
||||
if path == "/status" or path.startswith("/status?"):
|
||||
body = json.dumps(status_payload(), ensure_ascii=False).encode("utf-8")
|
||||
return 200, headers, body
|
||||
body = json.dumps({"error": "not_found"}, ensure_ascii=False).encode("utf-8")
|
||||
return 404, headers, body
|
||||
129
src/pending_pool.py
Normal file
129
src/pending_pool.py
Normal file
@@ -0,0 +1,129 @@
|
||||
"""Read-only pending pool. Name checks cannot establish metadata/uniqueness PASS."""
|
||||
import os
|
||||
import re
|
||||
from pathlib import Path
|
||||
|
||||
BASE = Path('/workspace/modelhub-adapt')
|
||||
GPUS = r'曦望(?: S2)?|壁砺(?:166M)?|天垓150|天垓100|智铠(?: mrv-100)?|Iluvatar_mrv-100|Biren_166m|Sunrise_pt-200-x1'
|
||||
FAMILIES = ('lfm2', 'olmo-2', 'olmo2', 'spark-x2.5', 'spark2_5', 'nemotron-h')
|
||||
|
||||
|
||||
def input_path(env, filename):
|
||||
return Path(os.environ.get(env) or BASE / filename)
|
||||
|
||||
|
||||
def load_do_not_resubmit(path):
|
||||
# Exact ids only; includes collision bullets and overnight tables.
|
||||
return {s for s in re.findall(r'`([^`]+)`', Path(path).read_text())
|
||||
if re.fullmatch(r'[\w.-]+/[\w.\-/]+', s)}
|
||||
|
||||
|
||||
def load_banned_name_tokens(path):
|
||||
text = Path(path).read_text().lower()
|
||||
return {s for s in ('abliterated', 'heretic', 'uncensored', 'unsensored') if s in text}
|
||||
|
||||
|
||||
def experience_order(gpus):
|
||||
"""Stable tier sort of missing chips only; tier-one pending order wins.
|
||||
|
||||
docs/gpu-perf-order.md Section B is experience, never official performance.
|
||||
Unknown names retain their relative order after known tiers; no chips added.
|
||||
"""
|
||||
def tier(gpu):
|
||||
if any(name in gpu for name in ('壁砺', '曦望', 'Biren_166m', 'Sunrise_pt-200-x1')):
|
||||
return 1
|
||||
if '天垓150' in gpu:
|
||||
return 2
|
||||
if '天垓100' in gpu:
|
||||
return 3
|
||||
if '智铠' in gpu or 'mrv-100' in gpu:
|
||||
return 4
|
||||
return 5
|
||||
return sorted(dict.fromkeys(gpus), key=tier)
|
||||
|
||||
|
||||
def classify_foothold(text):
|
||||
"""Classify literal pending evidence; mixed markers prefer verified."""
|
||||
for label, markers in (
|
||||
('verified_reuse', ('已验证成功', '验证通过')),
|
||||
('in_flight', ('正在验证', '验证排队中', '验证进行中')),
|
||||
('failed_foothold', ('验证失败',)),
|
||||
):
|
||||
if any(marker in text for marker in markers):
|
||||
return label
|
||||
return 'unknown'
|
||||
|
||||
|
||||
def has_no_download_marker(text):
|
||||
"""True only for explicit 免下载/已下载; never inferred from verified alone."""
|
||||
return any(marker in text for marker in ('免下载', '已下载'))
|
||||
|
||||
|
||||
def _candidate(model, section, gpu_text, notes, foothold_text=''):
|
||||
evidence_text = foothold_text if section == 'A' else ''
|
||||
foothold_class = classify_foothold(evidence_text) if section == 'A' else 'unknown'
|
||||
no_download = has_no_download_marker(evidence_text + ' ' + notes)
|
||||
evidence = 'pending-foothold' if (foothold_class != 'unknown' or no_download) else 'GAP'
|
||||
return dict(model_address=model, section=section,
|
||||
foothold_text=foothold_text, foothold_class=foothold_class,
|
||||
evidence_source=evidence, no_download=no_download,
|
||||
try_next_gpus=experience_order(re.findall(GPUS, gpu_text)),
|
||||
perf_order="unset", order_source="experience",
|
||||
notes=notes, comment=notes, skip_reason=None,
|
||||
needs_human=False, status='candidate')
|
||||
|
||||
|
||||
def parse_pending_md(path):
|
||||
rows, section = [], None
|
||||
for line in Path(path).read_text().splitlines():
|
||||
heading = re.match(r'##\s+Section\s+([AB])\b', line)
|
||||
if heading:
|
||||
section = heading[1]
|
||||
elif line.startswith('## '):
|
||||
section = None
|
||||
if section and re.match(r'\|\s*\d+\s*\|', line):
|
||||
cols = [s.strip() for s in line.strip('|').split('|')]
|
||||
model = re.search(r'`([^`]+)`', cols[1])
|
||||
if model:
|
||||
rows.append(_candidate(model[1], section, cols[3] if section == 'A' else cols[-1], cols[-1], cols[2] if section == 'A' else ''))
|
||||
return rows
|
||||
|
||||
|
||||
def parse_pending_txt(path):
|
||||
rows = []
|
||||
for line in Path(path).read_text().splitlines():
|
||||
if not line.strip() or line.startswith('#'):
|
||||
continue
|
||||
parts = re.split(r'\t|\\t', line, maxsplit=1)
|
||||
comment = parts[1] if len(parts) == 2 else ''
|
||||
match = re.match(r'#([AB])', comment)
|
||||
section = match[1] if match else 'B'
|
||||
gpu_text = re.split(r'(?:still\s+)?try\s*:', comment, maxsplit=1)[-1] if 'try:' in comment else (comment if section == 'B' else '')
|
||||
row = _candidate(parts[0].strip(), section, gpu_text, comment, comment if section == 'A' else '')
|
||||
if not match:
|
||||
row.update(needs_human=True, status='needs_human')
|
||||
rows.append(row)
|
||||
return rows
|
||||
|
||||
|
||||
def build_ordered_candidates(md_path=None, txt_path=None, dnr_path=None, banned_path=None):
|
||||
md = Path(md_path) if md_path is not None else input_path('PENDING_SUBMIT_MD', 'pending-submit.md')
|
||||
txt = Path(txt_path) if txt_path is not None else input_path('PENDING_SUBMIT_TXT', 'pending-submit.txt')
|
||||
rows = parse_pending_md(md) if md.is_file() else parse_pending_txt(txt) if txt.is_file() else []
|
||||
dnr = Path(dnr_path) if dnr_path is not None else input_path('DO_NOT_RESUBMIT_MD', 'do-not-resubmit.md')
|
||||
banned = Path(banned_path) if banned_path is not None else input_path('BANNED_PATTERNS_MD', 'banned-patterns.md')
|
||||
excluded = load_do_not_resubmit(dnr) if dnr.is_file() else set()
|
||||
tokens = load_banned_name_tokens(banned) if banned.is_file() else set()
|
||||
section = os.environ.get('PENDING_SECTION', '').strip().upper()
|
||||
if section:
|
||||
rows = [row for row in rows if row['section'] == section]
|
||||
for row in rows:
|
||||
name = row['model_address']
|
||||
reason = ('do-not-resubmit' if name in excluded else
|
||||
'hard-gate: banned name token' if any(t in name.lower() for t in tokens) else
|
||||
'hard-gate: banned family' if any(t in name.lower() for t in FAMILIES) else None)
|
||||
row['skip_reason'] = reason
|
||||
# Metadata gates (weights, context, riskTag, uniqueness) remain unverified.
|
||||
row['needs_human'] = not bool(reason)
|
||||
row['status'] = 'skipped' if reason else 'needs_human'
|
||||
return sorted(rows, key=lambda r: (r['section'] != 'A', not (r['foothold_class'] == 'verified_reuse' or r.get('no_download'))))
|
||||
22
src/queue_depth.py
Normal file
22
src/queue_depth.py
Normal file
@@ -0,0 +1,22 @@
|
||||
"""Read queue hints without contacting the platform; unknown is conservative."""
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
def queue_depth():
|
||||
value = os.environ.get('ASYNC_QUEUE_DEPTH')
|
||||
if value is None and os.environ.get('QUEUE_SNAPSHOT_JSON'):
|
||||
try:
|
||||
data = json.loads(Path(os.environ['QUEUE_SNAPSHOT_JSON']).read_text())
|
||||
if isinstance(data, dict):
|
||||
value = next((data[k] for k in ('depth', 'queue_depth', 'async_queue_depth', 'ASYNC_QUEUE_DEPTH') if k in data), None)
|
||||
except (OSError, ValueError):
|
||||
return None
|
||||
try:
|
||||
if isinstance(value, bool):
|
||||
return None
|
||||
depth = int(str(value))
|
||||
return depth if depth >= 0 else None
|
||||
except (TypeError, ValueError):
|
||||
return None
|
||||
44
src/readonly_probe.py
Normal file
44
src/readonly_probe.py
Normal file
@@ -0,0 +1,44 @@
|
||||
"""Explicit read-only auth probe. Import performs no I/O; never calls task/add."""
|
||||
import json
|
||||
import os
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
from src.task_add_client import resolve_token
|
||||
|
||||
|
||||
def probe_readonly():
|
||||
try:
|
||||
token = resolve_token()
|
||||
except (ValueError, OSError):
|
||||
return dict(http_status=None, platform_code=None, auth_ok=False,
|
||||
record_summary={'count': 0}, error_attribution='missing/invalid credential')
|
||||
request = urllib.request.Request(
|
||||
os.environ.get('MODELHUB_API_BASE', 'https://modelhub.org.cn').rstrip('/')
|
||||
+ '/api/adapt/task/page?onlyMine=true&pageSize=5¤t=1',
|
||||
headers={'Xc-Token': token, 'Accept': 'application/json'}, method='GET')
|
||||
try:
|
||||
with urllib.request.urlopen(request, timeout=30) as response:
|
||||
status, raw = response.status, response.read()
|
||||
except urllib.error.HTTPError as error:
|
||||
status, raw = error.code, error.read()
|
||||
except (OSError, urllib.error.URLError, ValueError):
|
||||
return dict(http_status=None, platform_code=None, auth_ok=False,
|
||||
record_summary={'count': 0}, error_attribution='transport/timeout')
|
||||
# Never expose response strings: servers can echo credentials in any field.
|
||||
try:
|
||||
body = json.loads(raw)
|
||||
except (ValueError, UnicodeError):
|
||||
body = {}
|
||||
body = body if isinstance(body, dict) else {}
|
||||
code = body.get('code')
|
||||
code = code if type(code) is int else int(code) if isinstance(code, str) and code in ('0', '40100', '40101') else None
|
||||
ok = 200 <= status < 300 and code == 0
|
||||
data = body.get('data')
|
||||
records = data.get('records') if isinstance(data, dict) else None
|
||||
summary = {'count': len(records) if isinstance(records, list) else 0}
|
||||
if isinstance(data, dict) and type(data.get('total')) is int:
|
||||
summary['total'] = data['total']
|
||||
attribution = {40100: '40100 NOT_LOGIN_ERROR', 40101: '40101 NO_AUTH_ERROR'}.get(
|
||||
code, 'success' if ok else 'other HTTP/platform/invalid response')
|
||||
return dict(http_status=status, platform_code=code, auth_ok=ok,
|
||||
record_summary=summary, error_attribution=attribution)
|
||||
83
src/server.py
Normal file
83
src/server.py
Normal file
@@ -0,0 +1,83 @@
|
||||
"""Minimal HTTP server for the adaptation agent (stdlib only).
|
||||
|
||||
Listens on PORT (default 8080). Handles SIGTERM and exits the main loop
|
||||
within ~1s (platform window documented as ≤30s).
|
||||
|
||||
Startup: require STRATEGY_ID (Phase1 product plan — fail if missing).
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import signal
|
||||
import sys
|
||||
import threading
|
||||
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
|
||||
from typing import Optional
|
||||
|
||||
from .health import handle_get
|
||||
from .strategy import require_strategy_id
|
||||
|
||||
_shutdown = threading.Event()
|
||||
_httpd: Optional[ThreadingHTTPServer] = None
|
||||
|
||||
|
||||
class AgentHandler(BaseHTTPRequestHandler):
|
||||
protocol_version = "HTTP/1.1"
|
||||
|
||||
def log_message(self, fmt: str, *args) -> None: # noqa: A003
|
||||
# Avoid noisy default logging; never log env secrets.
|
||||
sys.stderr.write("[http] request handled (details omitted)\n")
|
||||
|
||||
def do_GET(self) -> None: # noqa: N802
|
||||
code, headers, body = handle_get(self.path)
|
||||
self.send_response(code)
|
||||
for k, v in headers.items():
|
||||
self.send_header(k, v)
|
||||
self.send_header("Content-Length", str(len(body)))
|
||||
self.end_headers()
|
||||
self.wfile.write(body)
|
||||
|
||||
def do_POST(self) -> None: # noqa: N802
|
||||
body = b'{"error":"method_not_allowed"}'
|
||||
self.send_response(405)
|
||||
self.send_header("Content-Type", "application/json; charset=utf-8")
|
||||
self.send_header("Content-Length", str(len(body)))
|
||||
self.end_headers()
|
||||
self.wfile.write(body)
|
||||
|
||||
|
||||
def _on_sigterm(signum: int, frame) -> None: # noqa: ARG001
|
||||
sys.stderr.write(f"Received signal {signum}; shutting down...\n")
|
||||
_shutdown.set()
|
||||
httpd = _httpd
|
||||
if httpd is not None:
|
||||
# wake serve_forever
|
||||
threading.Thread(target=httpd.shutdown, daemon=True).start()
|
||||
|
||||
|
||||
def main() -> None:
|
||||
global _httpd
|
||||
|
||||
require_strategy_id() # exit 1 if missing
|
||||
|
||||
port = int(os.environ.get("PORT", "8080"))
|
||||
host = os.environ.get("HOST", "0.0.0.0")
|
||||
|
||||
signal.signal(signal.SIGTERM, _on_sigterm)
|
||||
signal.signal(signal.SIGINT, _on_sigterm)
|
||||
|
||||
httpd = ThreadingHTTPServer((host, port), AgentHandler)
|
||||
httpd.daemon_threads = True
|
||||
_httpd = httpd
|
||||
|
||||
sys.stderr.write(f"Listening on {host}:{port} (GET /health, GET /status)\n")
|
||||
try:
|
||||
httpd.serve_forever(poll_interval=0.5)
|
||||
finally:
|
||||
httpd.server_close()
|
||||
sys.stderr.write("Server stopped.\n")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
81
src/strategy.py
Normal file
81
src/strategy.py
Normal file
@@ -0,0 +1,81 @@
|
||||
"""STRATEGY_ID and external-token presence helpers.
|
||||
|
||||
Phase1 (product plan): missing STRATEGY_ID → process must fail to start
|
||||
(exit non-zero). Values are never logged or returned in responses.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import sys
|
||||
from typing import Optional
|
||||
|
||||
# Community alias order (level C); we only check presence, never echo values.
|
||||
_TOKEN_ENV_KEYS = (
|
||||
"XC_TOKEN_FILE",
|
||||
"XC_TOKEN",
|
||||
"MODELHUB_XC_TOKEN",
|
||||
"EXTERNAL_SERVICE_TOKEN",
|
||||
)
|
||||
|
||||
|
||||
def get_strategy_id() -> Optional[str]:
|
||||
"""Return STRATEGY_ID if set and non-empty after strip; else None."""
|
||||
raw = os.environ.get("STRATEGY_ID")
|
||||
if raw is None:
|
||||
return None
|
||||
value = raw.strip()
|
||||
return value if value else None
|
||||
|
||||
|
||||
def require_strategy_id() -> str:
|
||||
"""Return STRATEGY_ID or exit the process with a non-zero status.
|
||||
|
||||
Does not print the value. Safe for startup path.
|
||||
"""
|
||||
sid = get_strategy_id()
|
||||
if sid is None:
|
||||
print(
|
||||
"ERROR: STRATEGY_ID is required and must be non-empty. "
|
||||
"Refusing to start (Phase1 contract).",
|
||||
file=sys.stderr,
|
||||
)
|
||||
sys.exit(1)
|
||||
return sid
|
||||
|
||||
|
||||
def strategy_id_present() -> bool:
|
||||
return get_strategy_id() is not None
|
||||
|
||||
|
||||
def _token_from_file(path: str) -> bool:
|
||||
"""True if path exists and has non-empty content (value never read into logs)."""
|
||||
try:
|
||||
if not path or not os.path.isfile(path):
|
||||
return False
|
||||
with open(path, "r", encoding="utf-8") as fh:
|
||||
content = fh.read().strip()
|
||||
return bool(content)
|
||||
except OSError:
|
||||
return False
|
||||
|
||||
|
||||
def external_service_token_present() -> bool:
|
||||
"""Whether any known token env / file alias is present (boolean only)."""
|
||||
for key in _TOKEN_ENV_KEYS:
|
||||
raw = os.environ.get(key)
|
||||
if raw is None:
|
||||
continue
|
||||
value = raw.strip()
|
||||
if not value:
|
||||
continue
|
||||
if key == "XC_TOKEN_FILE":
|
||||
if _token_from_file(value):
|
||||
return True
|
||||
continue
|
||||
# Reject obvious placeholders (community practice, level C)
|
||||
lowered = value.lower()
|
||||
if lowered in ("tmp", "placeholder", "changeme", "xxx"):
|
||||
continue
|
||||
return True
|
||||
return False
|
||||
58
src/task_add_client.py
Normal file
58
src/task_add_client.py
Normal file
@@ -0,0 +1,58 @@
|
||||
"""Explicit task/add client; import never sends requests. No retries.
|
||||
|
||||
Community Xc-Token authentication is C; platform code 60014 is D (unverified).
|
||||
GPU enums/framework/configParams require human verification. Draft placeholders
|
||||
must be replaced before a real call. Use through the dual gate with injection.
|
||||
"""
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import urllib.request
|
||||
import urllib.error
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
def build_payload(model_address, target_gpu='<TARGET_GPU>', framework='<FRAMEWORK>',
|
||||
strategy_id=None, config_params='<CONFIG_PARAMS>'):
|
||||
return dict(modelAddress=model_address, taskType='text-generation', targetGpu=target_gpu,
|
||||
framework=framework, strategyId=strategy_id or os.environ.get('STRATEGY_ID') or '<STRATEGY_ID>',
|
||||
configParams=config_params)
|
||||
|
||||
|
||||
def resolve_token():
|
||||
file = os.environ.get('XC_TOKEN_FILE')
|
||||
token = Path(file).read_text().strip() if file else next(
|
||||
(os.environ[k].strip() for k in ('XC_TOKEN', 'MODELHUB_XC_TOKEN', 'EXTERNAL_SERVICE_TOKEN') if os.environ.get(k)), '')
|
||||
if not token or re.search(r'(?i)(?:^|[^a-z0-9])(placeholder|changeme|tmp)(?:$|[^a-z0-9])', token):
|
||||
raise ValueError('Missing or invalid service credential')
|
||||
return token
|
||||
|
||||
|
||||
class TaskAddClient:
|
||||
def submit(self, payload):
|
||||
if not os.environ.get('STRATEGY_ID', '').strip():
|
||||
raise ValueError('STRATEGY_ID required')
|
||||
required = ('modelAddress', 'taskType', 'targetGpu', 'framework', 'strategyId', 'configParams')
|
||||
if any(k not in payload or not payload[k] or '<' in str(payload[k]) for k in required):
|
||||
raise ValueError('Replace all required payload placeholders')
|
||||
if payload['strategyId'] != os.environ['STRATEGY_ID'].strip():
|
||||
raise ValueError('strategyId must match STRATEGY_ID')
|
||||
token = resolve_token()
|
||||
request = urllib.request.Request(os.environ.get('MODELHUB_API_BASE', 'https://www.modelhub.org.cn').rstrip('/') + '/api/adapt/task/add',
|
||||
data=json.dumps(payload).encode(), headers={'Xc-Token': token, 'Content-Type': 'application/json'}, method='POST')
|
||||
try:
|
||||
with urllib.request.urlopen(request, timeout=30) as response:
|
||||
status, raw = response.status, response.read()
|
||||
except urllib.error.HTTPError as error:
|
||||
status, raw = error.code, error.read()
|
||||
except (OSError, urllib.error.URLError):
|
||||
return dict(http_status=None, body=None, platform_code=None, error_attribution='transport/timeout')
|
||||
# A server may echo credentials; redact before parsing or returning anything.
|
||||
text = raw.decode('utf-8', errors='replace').replace(token, '[REDACTED]')
|
||||
try:
|
||||
body = json.loads(text)
|
||||
except ValueError:
|
||||
body = text
|
||||
code = body.get('code') if isinstance(body, dict) else None
|
||||
attribution = '60014: D (unverified)' if str(code) == '60014' else 'HTTP error' if status >= 400 else 'platform response (unverified)'
|
||||
return dict(http_status=status, body=body, platform_code=code, error_attribution=attribution)
|
||||
44
templates/config_params.sample.yaml
Normal file
44
templates/config_params.sample.yaml
Normal file
@@ -0,0 +1,44 @@
|
||||
framework: vllm
|
||||
api: completion
|
||||
lang: en
|
||||
max_model_len: 4096
|
||||
max_tokens: 1024
|
||||
temperature: 0.7
|
||||
repetition_penalty: 1.1
|
||||
top_p: 0.9
|
||||
sut_config:
|
||||
gpu_num: 1
|
||||
values:
|
||||
command:
|
||||
- /opt/conda/bin/vllm
|
||||
- serve
|
||||
- /model
|
||||
- --port
|
||||
- '20644'
|
||||
- --served-model-name
|
||||
- llm
|
||||
- --max-model-len
|
||||
- '4096'
|
||||
- --gpu-memory-utilization
|
||||
- '0.9'
|
||||
- -tp
|
||||
- '1'
|
||||
- --enforce-eager
|
||||
- --trust-remote-code
|
||||
ref_config:
|
||||
gpu_num: 1
|
||||
values:
|
||||
command:
|
||||
- vllm
|
||||
- serve
|
||||
- /model
|
||||
- --port
|
||||
- '80'
|
||||
- --served-model-name
|
||||
- llm
|
||||
- --max-model-len
|
||||
- '4096'
|
||||
- -tp
|
||||
- '1'
|
||||
- --enforce-eager
|
||||
- --trust-remote-code
|
||||
0
tests/__init__.py
Normal file
0
tests/__init__.py
Normal file
73
tests/test_build_config_client.py
Normal file
73
tests/test_build_config_client.py
Normal file
@@ -0,0 +1,73 @@
|
||||
import runpy
|
||||
import io
|
||||
import json
|
||||
import os
|
||||
import unittest
|
||||
import urllib.error
|
||||
from unittest.mock import MagicMock, patch
|
||||
from urllib.parse import urlparse, parse_qs
|
||||
from src.build_config_client import build_config, BuildConfigError
|
||||
from scripts.build_config_dry import main
|
||||
|
||||
|
||||
class TestBuildConfigClient(unittest.TestCase):
|
||||
def response(self, body, status=200):
|
||||
response = MagicMock()
|
||||
response.__enter__.return_value = response
|
||||
response.status = status
|
||||
response.read.return_value = json.dumps(body).encode()
|
||||
return response
|
||||
|
||||
def test_success_request_and_auth(self):
|
||||
for authorization in ('0', '1'):
|
||||
with patch.dict(os.environ, {'XC_TOKEN': 'test-secret', 'BUILD_CONFIG_USE_AUTHORIZATION': authorization}, clear=True), patch('urllib.request.urlopen', return_value=self.response({'code': 0, 'data': 'framework: vllm\n'})) as call:
|
||||
self.assertEqual(build_config('Sunrise_pt-200-x1'), 'framework: vllm\n')
|
||||
request = call.call_args.args[0]
|
||||
self.assertEqual(request.get_method(), 'POST')
|
||||
self.assertIsNone(request.data)
|
||||
parsed = urlparse(request.full_url)
|
||||
self.assertEqual(parsed.path, '/api/adapt/task/build-config')
|
||||
self.assertNotIn('/task/add', request.full_url)
|
||||
self.assertEqual(parse_qs(parsed.query), {'gpuType': ['Sunrise_pt-200-x1'], 'framework': ['vllm'], 'taskType': ['text-generation']})
|
||||
self.assertEqual(request.get_header('Authorization' if authorization == '1' else 'Xc-token'), 'test-secret')
|
||||
self.assertIsNone(request.get_header('Xc-token' if authorization == '1' else 'Authorization'))
|
||||
|
||||
def test_missing_invalid_no_network(self):
|
||||
for env in ({}, {'XC_TOKEN': 'placeholder'}, {'XC_TOKEN_FILE': '/nonexistent/token'}):
|
||||
with patch.dict(os.environ, env, clear=True), patch('urllib.request.urlopen') as call:
|
||||
with self.assertRaisesRegex(BuildConfigError, 'missing/invalid credential'):
|
||||
build_config('gpu')
|
||||
with patch('sys.argv', ['build_config_dry']), patch('sys.stderr', io.StringIO()):
|
||||
self.assertEqual(main(), 1)
|
||||
call.assert_not_called()
|
||||
|
||||
def test_platform_and_data_errors(self):
|
||||
for body, reason in [({'code': 40100}, '40100'), ({'code': 40101}, '40101'), ({'code': 9}, 'other HTTP/platform'), ({'code': 0, 'data': ''}, 'empty/non-str'), ({'code': 0, 'data': []}, 'empty/non-str'), ({'code': 0, 'data': 'test-secret'}, 'credential echoed')]:
|
||||
with patch.dict(os.environ, {'XC_TOKEN': 'test-secret'}, clear=True), patch('urllib.request.urlopen', return_value=self.response(body)):
|
||||
with self.assertRaisesRegex(BuildConfigError, reason):
|
||||
build_config('gpu')
|
||||
|
||||
def test_http_transport_invalid_response(self):
|
||||
for code in (40100, 40101):
|
||||
error = urllib.error.HTTPError('https://example.test', 403, '', {}, io.BytesIO(json.dumps({'code': code}).encode()))
|
||||
with patch.dict(os.environ, {'XC_TOKEN': 'test-secret'}, clear=True), patch('urllib.request.urlopen', side_effect=error):
|
||||
with self.assertRaisesRegex(BuildConfigError, str(code)):
|
||||
build_config('gpu')
|
||||
with patch.dict(os.environ, {'XC_TOKEN': 'test-secret'}, clear=True):
|
||||
for error in (TimeoutError('secret'), urllib.error.URLError('secret')):
|
||||
with patch('urllib.request.urlopen', side_effect=error), self.assertRaisesRegex(BuildConfigError, 'transport/timeout'):
|
||||
build_config('gpu')
|
||||
for response in (self.response([], 200), self.response({'code': 0, 'data': 'yaml'}, 500)):
|
||||
with patch('urllib.request.urlopen', return_value=response), self.assertRaises(BuildConfigError):
|
||||
build_config('gpu')
|
||||
response = self.response({})
|
||||
response.read.return_value = b'not-json'
|
||||
with patch('urllib.request.urlopen', return_value=response), self.assertRaisesRegex(BuildConfigError, 'invalid JSON'):
|
||||
build_config('gpu')
|
||||
|
||||
def test_import_no_io(self):
|
||||
import src.build_config_client
|
||||
with patch('urllib.request.urlopen') as call, patch('pathlib.Path.read_text') as read:
|
||||
runpy.run_path('src/build_config_client.py')
|
||||
call.assert_not_called()
|
||||
read.assert_not_called()
|
||||
83
tests/test_config_params.py
Normal file
83
tests/test_config_params.py
Normal file
@@ -0,0 +1,83 @@
|
||||
import json
|
||||
import re
|
||||
import unittest
|
||||
import os
|
||||
from unittest.mock import patch
|
||||
from pathlib import Path
|
||||
from src.config_params import build_config_params, config_params_source, build_config_params_with_meta, GAP
|
||||
from src.build_config_client import BuildConfigError
|
||||
from scripts.dry_run import _render
|
||||
|
||||
|
||||
class TestConfigParams(unittest.TestCase):
|
||||
def setUp(self):
|
||||
env = patch.dict(os.environ, {}, clear=True)
|
||||
env.start()
|
||||
self.addCleanup(env.stop)
|
||||
|
||||
def test_source_selection_and_failure(self):
|
||||
# No token → sample, no network
|
||||
with patch('src.config_params.resolve_token', side_effect=ValueError), patch('src.config_params.build_config') as client:
|
||||
self.assertEqual(config_params_source(), 'sample')
|
||||
yaml, meta = build_config_params_with_meta('壁砺')
|
||||
self.assertEqual(meta['auth'], 'missing')
|
||||
self.assertEqual(meta['configParams_source'], 'sample')
|
||||
client.assert_not_called()
|
||||
# Token alone → prefer build-config (kickoff default)
|
||||
for gpu, enum in [('壁砺', 'Biren_166m'), ('壁砺166M', 'Biren_166m'),
|
||||
('Biren_166m', 'Biren_166m'), ('曦望', 'Sunrise_pt-200-x1'),
|
||||
('曦望 S2', 'Sunrise_pt-200-x1'), ('Sunrise_pt-200-x1', 'Sunrise_pt-200-x1')]:
|
||||
with self.subTest(gpu=gpu), patch('src.config_params.resolve_token', return_value='synthetic'), patch('src.config_params.build_config', return_value='api: yaml') as client:
|
||||
self.assertEqual(config_params_source(), 'build-config')
|
||||
yaml, meta = build_config_params_with_meta(gpu)
|
||||
self.assertEqual(yaml, 'api: yaml')
|
||||
self.assertEqual(meta['configParams_source'], 'build-config')
|
||||
self.assertEqual(meta['auth'], 'ok')
|
||||
client.assert_called_once_with(enum, 'vllm', 'text-generation')
|
||||
# Failure → sample + GAP reason
|
||||
with patch('src.config_params.resolve_token', return_value='synthetic'), patch('src.config_params.build_config', side_effect=BuildConfigError('transport/timeout')):
|
||||
yaml, meta = build_config_params_with_meta('壁砺')
|
||||
self.assertEqual(meta['configParams_source'], 'sample')
|
||||
self.assertEqual(meta['configParams_fallback_reason'], 'GAP: transport/timeout')
|
||||
self.assertIn('max_model_len: 4096', yaml)
|
||||
# Forced build-config also soft-falls back in with_meta
|
||||
with patch.dict(os.environ, {'CONFIG_PARAMS_SOURCE': 'build-config'}), patch('src.config_params.resolve_token', return_value='synthetic'), patch('src.config_params.build_config', side_effect=BuildConfigError('transport/timeout')):
|
||||
yaml, meta = build_config_params_with_meta('壁砺')
|
||||
self.assertEqual(meta['configParams_fallback_reason'], 'GAP: transport/timeout')
|
||||
# Unmapped GPU → no API call
|
||||
for gpu in ('天垓150', '智铠 mrv-100', 'MetaX_c-500', '<GPU>', None):
|
||||
with patch('src.config_params.resolve_token', return_value='synthetic'), patch('src.config_params.build_config') as client:
|
||||
_, meta = build_config_params_with_meta(gpu)
|
||||
self.assertIn('GAP: gpu enum unmapped', meta['configParams_fallback_reason'])
|
||||
client.assert_not_called()
|
||||
# Force sample even with token
|
||||
with patch.dict(os.environ, {'CONFIG_PARAMS_SOURCE': 'sample'}), patch('src.config_params.resolve_token', return_value='synthetic'), patch('src.config_params.build_config') as client:
|
||||
self.assertEqual(config_params_source(), 'sample')
|
||||
build_config_params('壁砺')
|
||||
client.assert_not_called()
|
||||
|
||||
def test_report_api_failure_metadata(self):
|
||||
with patch('src.config_params.resolve_token', return_value='synthetic'), patch('src.config_params.build_config', side_effect=BuildConfigError('transport/timeout')):
|
||||
report = _render([{'model_address': 'org/a', 'try_next_gpus': ['壁砺'],
|
||||
'foothold_class': 'verified_reuse', 'evidence_source': 'pending-foothold',
|
||||
'no_download': False}], 'test', 'fixture')
|
||||
for value in ('foothold_class=verified_reuse', 'evidence_source=pending-foothold', 'no_download=False',
|
||||
'configParams_source=sample', 'configParams_fallback_reason=GAP: transport/timeout'):
|
||||
self.assertIn(value, report)
|
||||
|
||||
def test_official_sample_exact(self):
|
||||
scrape = Path('/workspace/modelhub-adapt/logs/api-docs-scrape-2026-10-16.md')
|
||||
if scrape.is_file():
|
||||
body = json.loads(re.search(r'```json\n(.*?)\n```', scrape.read_text(), re.S)[1])
|
||||
with patch('src.config_params.resolve_token', side_effect=ValueError):
|
||||
self.assertEqual(build_config_params(), body['configParams'])
|
||||
with patch('src.config_params.resolve_token', side_effect=ValueError):
|
||||
self.assertIn('max_model_len: 4096', build_config_params())
|
||||
self.assertIn('framework: vllm', build_config_params())
|
||||
self.assertIn('NOT production-ready', GAP)
|
||||
|
||||
def test_report_draft_and_gap(self):
|
||||
with patch('src.config_params.resolve_token', side_effect=ValueError):
|
||||
report = _render([{'model_address': 'org/a', 'try_next_gpus': ['壁砺']}], 'test', 'fixture')
|
||||
for value in ('代提候选 / 需 Victor 确认', 'configParams source', 'configParams_source=sample', 'foothold_class=unknown', 'evidence_source=GAP', 'no_download=False', 'GAP:', 'truncated', 'max_model_len: 4096', 'perf_order=unset', 'order_source=experience'):
|
||||
self.assertIn(value, report)
|
||||
159
tests/test_gate.py
Normal file
159
tests/test_gate.py
Normal file
@@ -0,0 +1,159 @@
|
||||
"""Gate defaults to dry-run / blocked; live only with dual confirm + STRATEGY_ID."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import unittest
|
||||
from unittest import mock
|
||||
|
||||
from src.gate import LIVE_CONFIRM_VALUE, attempt_live_submit, evaluate_gate
|
||||
|
||||
|
||||
class FakeClient:
|
||||
def __init__(self) -> None:
|
||||
self.calls = []
|
||||
|
||||
def submit(self, payload):
|
||||
self.calls.append(payload)
|
||||
return {"task_id": "fake-1"}
|
||||
|
||||
|
||||
class TestGate(unittest.TestCase):
|
||||
def setUp(self):
|
||||
self.counter = mock.patch('src.gate._submit_count', 0)
|
||||
self.counter.start()
|
||||
self.addCleanup(self.counter.stop)
|
||||
self.env = mock.patch.dict(os.environ, {}, clear=True)
|
||||
self.env.start()
|
||||
self.addCleanup(self.env.stop)
|
||||
|
||||
def test_queue_and_process_limit(self):
|
||||
client = FakeClient()
|
||||
with mock.patch.dict(os.environ, {
|
||||
'STRATEGY_ID': 'sid', 'ALLOW_LIVE_SUBMIT': '1',
|
||||
'LIVE_CONFIRM': LIVE_CONFIRM_VALUE, 'ASYNC_QUEUE_DEPTH': '95'
|
||||
}):
|
||||
self.assertIn('≥95', attempt_live_submit({}, client)['reason'])
|
||||
self.assertEqual(client.calls, [])
|
||||
os.environ['ASYNC_QUEUE_DEPTH'] = '94'
|
||||
self.assertTrue(attempt_live_submit({}, client)['submitted'])
|
||||
self.assertFalse(attempt_live_submit({}, client)['submitted'])
|
||||
self.assertEqual(len(client.calls), 1)
|
||||
|
||||
def _clear_gate_env(self):
|
||||
return mock.patch.dict(
|
||||
os.environ,
|
||||
{
|
||||
"STRATEGY_ID": "sid-1",
|
||||
"ALLOW_LIVE_SUBMIT": "0",
|
||||
"LIVE_CONFIRM": "",
|
||||
},
|
||||
clear=False,
|
||||
)
|
||||
|
||||
def test_default_dry_run(self) -> None:
|
||||
with self._clear_gate_env():
|
||||
d = evaluate_gate()
|
||||
self.assertFalse(d.allowed)
|
||||
self.assertEqual(d.mode, "dry-run")
|
||||
|
||||
def test_missing_strategy_blocked(self) -> None:
|
||||
env = {
|
||||
"ALLOW_LIVE_SUBMIT": "1",
|
||||
"LIVE_CONFIRM": LIVE_CONFIRM_VALUE,
|
||||
}
|
||||
# Remove STRATEGY_ID
|
||||
base = {k: v for k, v in os.environ.items() if k != "STRATEGY_ID"}
|
||||
base.update(env)
|
||||
with mock.patch.dict(os.environ, base, clear=True):
|
||||
d = evaluate_gate()
|
||||
self.assertFalse(d.allowed)
|
||||
self.assertEqual(d.mode, "blocked")
|
||||
|
||||
def test_allow_without_confirm_blocked(self) -> None:
|
||||
with mock.patch.dict(
|
||||
os.environ,
|
||||
{
|
||||
"STRATEGY_ID": "sid-1",
|
||||
"ALLOW_LIVE_SUBMIT": "1",
|
||||
"LIVE_CONFIRM": "YES",
|
||||
},
|
||||
clear=False,
|
||||
):
|
||||
d = evaluate_gate()
|
||||
self.assertFalse(d.allowed)
|
||||
self.assertEqual(d.mode, "blocked")
|
||||
|
||||
def test_dual_gate_opens(self) -> None:
|
||||
with mock.patch.dict(
|
||||
os.environ,
|
||||
{
|
||||
"STRATEGY_ID": "sid-1",
|
||||
"ALLOW_LIVE_SUBMIT": "1",
|
||||
"LIVE_CONFIRM": LIVE_CONFIRM_VALUE,
|
||||
},
|
||||
clear=False,
|
||||
):
|
||||
d = evaluate_gate()
|
||||
self.assertTrue(d.allowed)
|
||||
self.assertEqual(d.mode, "live")
|
||||
|
||||
def test_open_gate_without_client_still_blocked(self) -> None:
|
||||
"""Phase2: an open gate never constructs a network client."""
|
||||
with mock.patch.dict(
|
||||
os.environ,
|
||||
{
|
||||
"STRATEGY_ID": "sid-1",
|
||||
"ALLOW_LIVE_SUBMIT": "1",
|
||||
"LIVE_CONFIRM": LIVE_CONFIRM_VALUE,
|
||||
},
|
||||
clear=False,
|
||||
):
|
||||
result = attempt_live_submit({"modelAddress": "x/y"})
|
||||
self.assertFalse(result["submitted"])
|
||||
self.assertIn("no real", result["reason"].lower())
|
||||
self.assertEqual(result["mode"], "blocked")
|
||||
self.assertFalse(result["ok"])
|
||||
|
||||
def test_prd_example_and_whitespace_id_never_submit(self) -> None:
|
||||
cases = [
|
||||
{"ALLOW_LIVE_SUBMIT": "true", "LIVE_CONFIRM": LIVE_CONFIRM_VALUE},
|
||||
{"ALLOW_LIVE_SUBMIT": "1", "LIVE_CONFIRM": "", "CONFIRM_LIVE": "YES"},
|
||||
{"ALLOW_LIVE_SUBMIT": "1", "LIVE_CONFIRM": LIVE_CONFIRM_VALUE, "STRATEGY_ID": " "},
|
||||
]
|
||||
for overrides in cases:
|
||||
with self.subTest(overrides=overrides):
|
||||
client = FakeClient()
|
||||
env = {"STRATEGY_ID": "sid-test", **overrides}
|
||||
with mock.patch.dict(os.environ, env, clear=True):
|
||||
result = attempt_live_submit({}, client=client)
|
||||
self.assertFalse(result["submitted"])
|
||||
self.assertFalse(result["ok"])
|
||||
self.assertEqual(client.calls, [])
|
||||
self.assertTrue(result["reason"])
|
||||
|
||||
def test_injected_fake_client(self) -> None:
|
||||
client = FakeClient()
|
||||
with mock.patch.dict(
|
||||
os.environ,
|
||||
{
|
||||
"STRATEGY_ID": "sid-1",
|
||||
"ALLOW_LIVE_SUBMIT": "1",
|
||||
"LIVE_CONFIRM": LIVE_CONFIRM_VALUE,
|
||||
},
|
||||
clear=False,
|
||||
):
|
||||
result = attempt_live_submit({"modelAddress": "x/y"}, client=client)
|
||||
self.assertTrue(result["submitted"])
|
||||
self.assertEqual(len(client.calls), 1)
|
||||
|
||||
def test_default_attempt_rejects(self) -> None:
|
||||
client = FakeClient()
|
||||
with self._clear_gate_env():
|
||||
result = attempt_live_submit({"modelAddress": "x/y"}, client=client)
|
||||
self.assertFalse(result["submitted"])
|
||||
self.assertEqual(len(client.calls), 0)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
60
tests/test_health.py
Normal file
60
tests/test_health.py
Normal file
@@ -0,0 +1,60 @@
|
||||
"""Tests for /health and /status handlers."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import os
|
||||
import unittest
|
||||
from unittest import mock
|
||||
|
||||
from src.health import handle_get, health_payload, status_payload
|
||||
|
||||
|
||||
class TestHealth(unittest.TestCase):
|
||||
def test_health_payload(self) -> None:
|
||||
self.assertEqual(health_payload(), {"status": "ok"})
|
||||
|
||||
def test_handle_get_health(self) -> None:
|
||||
code, headers, body = handle_get("/health")
|
||||
self.assertEqual(code, 200)
|
||||
self.assertIn("application/json", headers["Content-Type"])
|
||||
data = json.loads(body.decode("utf-8"))
|
||||
self.assertEqual(data, {"status": "ok"})
|
||||
|
||||
def test_handle_get_unknown(self) -> None:
|
||||
code, _, body = handle_get("/nope")
|
||||
self.assertEqual(code, 404)
|
||||
self.assertIn("not_found", body.decode("utf-8"))
|
||||
|
||||
def test_status_booleans_only_no_secret_values(self) -> None:
|
||||
with mock.patch.dict(
|
||||
os.environ,
|
||||
{
|
||||
"STRATEGY_ID": "secret-strategy-id-xyz",
|
||||
"EXTERNAL_SERVICE_TOKEN": "secret-token-abc",
|
||||
},
|
||||
clear=False,
|
||||
):
|
||||
payload = status_payload()
|
||||
self.assertTrue(payload["strategy_id_present"])
|
||||
self.assertTrue(payload["external_service_token_present"])
|
||||
blob = json.dumps(payload)
|
||||
self.assertNotIn("secret-strategy-id-xyz", blob)
|
||||
self.assertNotIn("secret-token-abc", blob)
|
||||
|
||||
def test_status_absent(self) -> None:
|
||||
env = {k: v for k, v in os.environ.items() if k not in (
|
||||
"STRATEGY_ID",
|
||||
"EXTERNAL_SERVICE_TOKEN",
|
||||
"XC_TOKEN",
|
||||
"XC_TOKEN_FILE",
|
||||
"MODELHUB_XC_TOKEN",
|
||||
)}
|
||||
with mock.patch.dict(os.environ, env, clear=True):
|
||||
payload = status_payload()
|
||||
self.assertFalse(payload["strategy_id_present"])
|
||||
self.assertFalse(payload["external_service_token_present"])
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
86
tests/test_pending_pool.py
Normal file
86
tests/test_pending_pool.py
Normal file
@@ -0,0 +1,86 @@
|
||||
import tempfile
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
from src.pending_pool import build_ordered_candidates, parse_pending_txt
|
||||
|
||||
|
||||
class TestPendingPool(unittest.TestCase):
|
||||
def test_order_filters_and_first_gpu(self):
|
||||
with tempfile.TemporaryDirectory() as directory:
|
||||
root = Path(directory)
|
||||
md, txt, dnr, banned = [root / n for n in ('pending.md', 'pending.txt', 'dnr.md', 'banned.md')]
|
||||
md.write_text('''## Section B
|
||||
| 1 | `org/cold` | 50 | | |
|
||||
## Section A
|
||||
| 1 | `org/good` | 曦望 | 壁砺, 天垓150 | — |
|
||||
| 2 | `org/exact` | 曦望 | 壁砺 | — |
|
||||
| 3 | `org/Heretic-model` | 曦望 | 壁砺 | — |
|
||||
| 4 | `org/OLMo-2-model` | 曦望 | 壁砺 | — |
|
||||
''')
|
||||
dnr.write_text('| 1 | `org/exact` | fail |\n## Uniqueness collisions\n- `org/collision`\n## Overnight\n- `org/overnight`')
|
||||
banned.write_text('`abliterated` `heretic` `uncensored` `unsensored`')
|
||||
rows = build_ordered_candidates(md, txt, dnr, banned)
|
||||
self.assertEqual([r['section'] for r in rows], ['A'] * 4 + ['B'])
|
||||
self.assertEqual(rows[0]['try_next_gpus'][0], '壁砺')
|
||||
self.assertEqual(rows[1]['skip_reason'], 'do-not-resubmit')
|
||||
self.assertEqual(rows[2]['status'], 'skipped')
|
||||
self.assertIn('family', rows[3]['skip_reason'])
|
||||
self.assertTrue(rows[-1]['needs_human'])
|
||||
txt.write_text('org/b\t#B cold\norg/a\t#A done:曦望; still try:壁砺+天垓150\norg/c\\t#A try:天垓150\n')
|
||||
self.assertEqual(parse_pending_txt(txt)[1]['try_next_gpus'], ['壁砺', '天垓150'])
|
||||
fallback = build_ordered_candidates(root/'absent', txt, dnr, banned)
|
||||
self.assertEqual([r['model_address'] for r in fallback], ['org/a', 'org/c', 'org/b'])
|
||||
self.assertEqual(len(build_ordered_candidates(md, txt, dnr, banned)), 5)
|
||||
|
||||
def test_experience_order_missing_only_and_ties(self):
|
||||
from src.pending_pool import experience_order, parse_pending_md
|
||||
self.assertEqual(experience_order(['智铠 mrv-100', '天垓100', '曦望', '天垓150', '壁砺']),
|
||||
['曦望', '壁砺', '天垓150', '天垓100', '智铠 mrv-100'])
|
||||
self.assertEqual(experience_order(['天垓150']), ['天垓150'])
|
||||
with tempfile.TemporaryDirectory() as directory:
|
||||
path = Path(directory) / 'pending.md'
|
||||
path.write_text('## Section A\n| 1 | `org/a` | 壁砺:验证失败; 曦望:正在验证 | 天垓150 | no 壁砺 retry |\n## Section B\n| 1 | `org/b` | 0 | 壁砺 |\n')
|
||||
from unittest.mock import patch
|
||||
import os
|
||||
with patch.dict(os.environ, {'PENDING_SECTION': 'A'}):
|
||||
rows = build_ordered_candidates(path, dnr_path=Path(directory)/'none', banned_path=Path(directory)/'none')
|
||||
self.assertEqual(len(rows), 1)
|
||||
self.assertEqual(rows[0]['try_next_gpus'], ['天垓150'])
|
||||
self.assertEqual(rows[0]['perf_order'], 'unset')
|
||||
|
||||
def test_foothold_evidence_and_stable_verified_priority(self):
|
||||
with tempfile.TemporaryDirectory() as directory:
|
||||
root = Path(directory)
|
||||
md = root / 'pending.md'
|
||||
md.write_text('## Section B\n| 1 | `org/b` | 0 | 壁砺 |\n## Section A\n| 1 | `org/unknown` | 曦望 | 壁砺 | 已验证成功 |\n| 2 | `org/flight` | 验证失败; 正在验证 | 壁砺 | — |\n| 3 | `org/verified` | 他人:已验证成功; 正在验证 | 壁砺 | — |\n| 4 | `org/fail` | 验证失败 | 曦望 | — |\n| 5 | `org/pass` | 既有:验证通过 | 曦望 | — |\n| 6 | `org/queue` | 验证排队中 | 壁砺 | — |\n| 7 | `org/progress` | 验证进行中 | 壁砺 | — |\n')
|
||||
rows = build_ordered_candidates(md, dnr_path=root/'none', banned_path=root/'none')
|
||||
self.assertEqual([r['model_address'] for r in rows],
|
||||
['org/verified', 'org/pass', 'org/unknown', 'org/flight',
|
||||
'org/fail', 'org/queue', 'org/progress', 'org/b'])
|
||||
self.assertEqual([r['foothold_class'] for r in rows],
|
||||
['verified_reuse', 'verified_reuse', 'unknown', 'in_flight',
|
||||
'failed_foothold', 'in_flight', 'in_flight', 'unknown'])
|
||||
for row in rows:
|
||||
self.assertEqual(row['evidence_source'], 'GAP' if row['foothold_class'] == 'unknown' else 'pending-foothold')
|
||||
self.assertEqual(rows[0]['foothold_text'], '他人:已验证成功; 正在验证')
|
||||
txt = root / 'pending.txt'
|
||||
txt.write_text('org/a\t#A done:曦望; try:壁砺\norg/v\t#A 验证通过; try:壁砺\n')
|
||||
parsed = parse_pending_txt(txt)
|
||||
self.assertEqual(parsed[0]['foothold_class'], 'unknown')
|
||||
self.assertEqual(parsed[0]['evidence_source'], 'GAP')
|
||||
self.assertEqual(parsed[1]['foothold_class'], 'verified_reuse')
|
||||
|
||||
def test_no_download_marker_without_inventing(self):
|
||||
with tempfile.TemporaryDirectory() as directory:
|
||||
root = Path(directory)
|
||||
md = root / 'pending.md'
|
||||
md.write_text('## Section A\n| 1 | `org/plain` | 曦望:验证排队中 | 壁砺 | — |\n| 2 | `org/cached` | 壁砺:已下载; 曦望:免下载 | 天垓150 | — |\n| 3 | `org/verified` | 壁砺:已验证成功 | 天垓150 | — |\n')
|
||||
rows = build_ordered_candidates(md, dnr_path=root/'none', banned_path=root/'none')
|
||||
by = {r['model_address']: r for r in rows}
|
||||
self.assertFalse(by['org/plain']['no_download'])
|
||||
self.assertEqual(by['org/plain']['evidence_source'], 'pending-foothold')
|
||||
self.assertTrue(by['org/cached']['no_download'])
|
||||
self.assertEqual(by['org/cached']['evidence_source'], 'pending-foothold')
|
||||
self.assertFalse(by['org/verified']['no_download']) # verified alone does not invent no_download
|
||||
self.assertEqual([r['model_address'] for r in rows],
|
||||
['org/cached', 'org/verified', 'org/plain'])
|
||||
61
tests/test_readonly_probe.py
Normal file
61
tests/test_readonly_probe.py
Normal file
@@ -0,0 +1,61 @@
|
||||
import io
|
||||
import json
|
||||
import os
|
||||
import unittest
|
||||
import urllib.error
|
||||
from unittest.mock import patch, MagicMock
|
||||
from src.readonly_probe import probe_readonly
|
||||
from scripts.probe_readonly import main
|
||||
|
||||
|
||||
class TestReadonlyProbe(unittest.TestCase):
|
||||
def test_missing_token_no_network(self):
|
||||
with patch.dict(os.environ, {}, clear=True), patch('urllib.request.urlopen') as call:
|
||||
self.assertFalse(probe_readonly()['auth_ok'])
|
||||
with patch('sys.stdout', io.StringIO()):
|
||||
self.assertEqual(main(), 1)
|
||||
call.assert_not_called()
|
||||
|
||||
def test_success_and_exact_request(self):
|
||||
response = MagicMock()
|
||||
response.__enter__.return_value = response
|
||||
response.status = 200
|
||||
response.read.return_value = json.dumps({'code': 0, 'data': {
|
||||
'records': [{'modelId': 'secret-value'}], 'total': 10}}).encode()
|
||||
with patch.dict(os.environ, {'EXTERNAL_SERVICE_TOKEN': 'secret-value'}, clear=True), patch('urllib.request.urlopen', return_value=response) as call:
|
||||
result = probe_readonly()
|
||||
request = call.call_args.args[0]
|
||||
self.assertEqual(request.get_method(), 'GET')
|
||||
self.assertEqual(request.full_url, 'https://modelhub.org.cn/api/adapt/task/page?onlyMine=true&pageSize=5¤t=1')
|
||||
self.assertEqual(request.get_header('Xc-token'), 'secret-value')
|
||||
self.assertTrue(result['auth_ok'])
|
||||
self.assertEqual(result['record_summary'], {'count': 1, 'total': 10})
|
||||
self.assertNotIn('secret-value', json.dumps(result))
|
||||
|
||||
def test_errors_no_fallback_or_echo(self):
|
||||
for code in (40100, 40101, 50000):
|
||||
error = urllib.error.HTTPError('https://example.test', 403, '', {}, io.BytesIO(json.dumps({'code': code, 'message': 'secret-value'}).encode()))
|
||||
with patch.dict(os.environ, {'XC_TOKEN': 'secret-value'}, clear=True), patch('urllib.request.urlopen', side_effect=error) as call:
|
||||
result = probe_readonly()
|
||||
self.assertEqual(call.call_count, 1)
|
||||
self.assertFalse(result['auth_ok'])
|
||||
self.assertEqual(result['platform_code'], code)
|
||||
self.assertIn(str(code) if code != 50000 else 'other', result['error_attribution'])
|
||||
self.assertNotIn('secret-value', json.dumps(result))
|
||||
|
||||
def test_transport_and_invalid_json(self):
|
||||
for error in (OSError('secret-value'), urllib.error.URLError('secret-value')):
|
||||
with patch.dict(os.environ, {'XC_TOKEN': 'secret-value'}, clear=True), patch('urllib.request.urlopen', side_effect=error):
|
||||
self.assertEqual(probe_readonly()['error_attribution'], 'transport/timeout')
|
||||
response = MagicMock()
|
||||
response.__enter__.return_value = response
|
||||
response.status, response.read.return_value = 200, b'invalid secret-value'
|
||||
with patch.dict(os.environ, {'XC_TOKEN': 'secret-value'}, clear=True), patch('urllib.request.urlopen', return_value=response):
|
||||
self.assertFalse(probe_readonly()['auth_ok'])
|
||||
|
||||
def test_import_no_network(self):
|
||||
import importlib
|
||||
import src.readonly_probe
|
||||
with patch('urllib.request.urlopen') as call:
|
||||
importlib.reload(src.readonly_probe)
|
||||
call.assert_not_called()
|
||||
46
tests/test_report_safety.py
Normal file
46
tests/test_report_safety.py
Normal file
@@ -0,0 +1,46 @@
|
||||
"""Local report and HTTP log regression checks; no network requests."""
|
||||
import contextlib
|
||||
import io
|
||||
import os
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
from unittest import mock
|
||||
|
||||
from scripts.dry_run import _render
|
||||
from src.server import AgentHandler
|
||||
|
||||
|
||||
class TestReportSafety(unittest.TestCase):
|
||||
def test_report_marks_pending_and_does_not_echo_gate_values(self):
|
||||
sentinel = "synthetic-sensitive-value"
|
||||
with mock.patch.dict(os.environ, {
|
||||
"ALLOW_LIVE_SUBMIT": sentinel,
|
||||
"LIVE_CONFIRM": sentinel,
|
||||
"STRATEGY_ID": sentinel,
|
||||
"EXTERNAL_SERVICE_TOKEN": sentinel,
|
||||
}, clear=True):
|
||||
report = _render([], "test-time", Path("example.json"))
|
||||
self.assertNotIn(sentinel, report)
|
||||
for required in ("A→B", "需 Victor 人工提交", "积分:待平台核实", "≥95"):
|
||||
self.assertIn(required, report)
|
||||
|
||||
def test_pending_draft_queue_banner_and_skips(self):
|
||||
rows = [dict(model_address='org/a', section='A', try_next_gpus=['壁砺', '天垓150'],
|
||||
status='skipped', skip_reason='do-not-resubmit', needs_human=False),
|
||||
dict(model_address='org/b', section='B', try_next_gpus=[],
|
||||
status='needs_human', needs_human=True)]
|
||||
with mock.patch.dict(os.environ, {'ASYNC_QUEUE_DEPTH': '95'}, clear=True):
|
||||
report = _render(rows, 'test', Path('pending.md'))
|
||||
self.assertIn('禁 live / 队列≥95', report)
|
||||
self.assertIn('do-not-resubmit', report)
|
||||
self.assertIn('needs_human', report)
|
||||
self.assertIn('"targetGpu": "壁砺"', report)
|
||||
self.assertNotIn('"targetGpu": "天垓150"', report)
|
||||
self.assertLess(report.index('Section A'), report.index('Section B'))
|
||||
|
||||
def test_http_log_omits_request_details(self):
|
||||
output = io.StringIO()
|
||||
with contextlib.redirect_stderr(output):
|
||||
AgentHandler.log_message(None, '"%s" %s', '/health?token=synthetic-sensitive-value', 200)
|
||||
self.assertNotIn("synthetic-sensitive-value", output.getvalue())
|
||||
self.assertIn("request handled", output.getvalue())
|
||||
69
tests/test_sigterm.py
Normal file
69
tests/test_sigterm.py
Normal file
@@ -0,0 +1,69 @@
|
||||
"""SIGTERM should stop the server subprocess promptly (<< 30s platform window)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import os
|
||||
import signal
|
||||
import subprocess
|
||||
import sys
|
||||
import time
|
||||
import unittest
|
||||
import urllib.request
|
||||
from pathlib import Path
|
||||
|
||||
ROOT = Path(__file__).resolve().parents[1]
|
||||
|
||||
|
||||
class TestSigterm(unittest.TestCase):
|
||||
def test_sigterm_exits_quickly(self) -> None:
|
||||
port = "19090"
|
||||
env = os.environ.copy()
|
||||
env["STRATEGY_ID"] = "sigterm-test"
|
||||
env["PORT"] = port
|
||||
env["HOST"] = "127.0.0.1"
|
||||
|
||||
proc = subprocess.Popen(
|
||||
[sys.executable, "-m", "src.server"],
|
||||
cwd=str(ROOT),
|
||||
env=env,
|
||||
stdout=subprocess.DEVNULL,
|
||||
stderr=subprocess.PIPE,
|
||||
)
|
||||
try:
|
||||
# wait until health is up
|
||||
url = f"http://127.0.0.1:{port}/health"
|
||||
deadline = time.time() + 5
|
||||
while time.time() < deadline:
|
||||
try:
|
||||
with urllib.request.urlopen(url, timeout=0.5) as resp:
|
||||
data = json.loads(resp.read().decode("utf-8"))
|
||||
if resp.status == 200 and data.get("status") == "ok":
|
||||
break
|
||||
except Exception:
|
||||
time.sleep(0.1)
|
||||
else:
|
||||
if proc.poll() is not None:
|
||||
self.fail(f"server exited before health check: {proc.stderr.read().decode(errors='replace')}")
|
||||
self.fail("server did not become healthy in time")
|
||||
|
||||
t0 = time.time()
|
||||
proc.send_signal(signal.SIGTERM)
|
||||
try:
|
||||
proc.wait(timeout=5)
|
||||
except subprocess.TimeoutExpired:
|
||||
proc.kill()
|
||||
self.fail("server did not exit within 5s after SIGTERM (platform allows ≤30s)")
|
||||
elapsed = time.time() - t0
|
||||
self.assertLess(elapsed, 5.0, f"exit took {elapsed:.2f}s")
|
||||
self.assertEqual(proc.returncode, 0, "SIGTERM must exit cleanly, not kill the process")
|
||||
finally:
|
||||
if proc.poll() is None:
|
||||
proc.kill()
|
||||
proc.wait(timeout=2)
|
||||
if proc.stderr:
|
||||
proc.stderr.close()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
57
tests/test_strategy_startup.py
Normal file
57
tests/test_strategy_startup.py
Normal file
@@ -0,0 +1,57 @@
|
||||
"""Missing STRATEGY_ID must cause startup failure (exit non-zero)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import subprocess
|
||||
import sys
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
from unittest import mock
|
||||
|
||||
ROOT = Path(__file__).resolve().parents[1]
|
||||
|
||||
|
||||
class TestStrategyStartup(unittest.TestCase):
|
||||
def test_missing_strategy_id_exits_nonzero(self) -> None:
|
||||
env = os.environ.copy()
|
||||
env["STRATEGY_ID"] = ""
|
||||
env["PORT"] = "19081"
|
||||
env["HOST"] = "127.0.0.1"
|
||||
proc = subprocess.run(
|
||||
[sys.executable, "-m", "src.server"],
|
||||
cwd=str(ROOT),
|
||||
env=env,
|
||||
capture_output=True,
|
||||
text=True,
|
||||
timeout=10,
|
||||
)
|
||||
self.assertNotEqual(proc.returncode, 0)
|
||||
self.assertIn("STRATEGY_ID", proc.stderr)
|
||||
|
||||
def test_whitespace_strategy_id_exits_nonzero(self) -> None:
|
||||
env = os.environ.copy()
|
||||
env["STRATEGY_ID"] = " "
|
||||
env["PORT"] = "19082"
|
||||
env["HOST"] = "127.0.0.1"
|
||||
proc = subprocess.run(
|
||||
[sys.executable, "-m", "src.server"],
|
||||
cwd=str(ROOT),
|
||||
env=env,
|
||||
capture_output=True,
|
||||
text=True,
|
||||
timeout=10,
|
||||
)
|
||||
self.assertNotEqual(proc.returncode, 0)
|
||||
|
||||
def test_require_strategy_id_helper(self) -> None:
|
||||
from src.strategy import require_strategy_id
|
||||
|
||||
with self.assertRaises(SystemExit) as ctx:
|
||||
with mock.patch.dict(os.environ, {"STRATEGY_ID": ""}, clear=False):
|
||||
require_strategy_id()
|
||||
self.assertNotEqual(ctx.exception.code, 0)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
69
tests/test_task_add_client.py
Normal file
69
tests/test_task_add_client.py
Normal file
@@ -0,0 +1,69 @@
|
||||
import importlib
|
||||
import io
|
||||
import os
|
||||
import tempfile
|
||||
import unittest
|
||||
import urllib.error
|
||||
from pathlib import Path
|
||||
from unittest import mock
|
||||
from src import task_add_client as module
|
||||
|
||||
|
||||
class TestTaskAddClient(unittest.TestCase):
|
||||
def setUp(self):
|
||||
patch = mock.patch.dict(os.environ, {'STRATEGY_ID': 'sid', 'XC_TOKEN': 'test-secret-credential'}, clear=True)
|
||||
patch.start()
|
||||
self.addCleanup(patch.stop)
|
||||
self.payload = module.build_payload('org/model', '壁砺', 'vllm', config_params={ 'max_model_len': 4096 })
|
||||
|
||||
def test_import_no_network(self):
|
||||
with mock.patch('urllib.request.urlopen') as urlopen:
|
||||
importlib.reload(module)
|
||||
urlopen.assert_not_called()
|
||||
|
||||
def test_success(self):
|
||||
response = mock.MagicMock()
|
||||
response.__enter__.return_value = response
|
||||
response.status = 200
|
||||
response.read.return_value = b'{"code":0,"message":"test-secret-credential"}'
|
||||
with mock.patch('urllib.request.urlopen', return_value=response) as urlopen:
|
||||
result = module.TaskAddClient().submit(self.payload)
|
||||
self.assertEqual(result['http_status'], 200)
|
||||
self.assertNotIn(os.environ['XC_TOKEN'], str(result))
|
||||
request = urlopen.call_args.args[0]
|
||||
self.assertEqual(request.get_header('Xc-token'), os.environ['XC_TOKEN'])
|
||||
self.assertEqual(request.method, 'POST')
|
||||
urlopen.assert_called_once()
|
||||
|
||||
def test_http_4xx_60014(self):
|
||||
error = urllib.error.HTTPError('https://example.invalid', 403, 'forbidden', {}, io.BytesIO(b'{"code":60014}'))
|
||||
with mock.patch('urllib.request.urlopen', side_effect=error) as urlopen:
|
||||
result = module.TaskAddClient().submit(self.payload)
|
||||
self.assertEqual(result['http_status'], 403)
|
||||
self.assertEqual(result['platform_code'], 60014)
|
||||
self.assertIn('D (unverified)', result['error_attribution'])
|
||||
urlopen.assert_called_once()
|
||||
|
||||
def test_transport_no_retry(self):
|
||||
with mock.patch('urllib.request.urlopen', side_effect=TimeoutError('test-secret-credential')) as urlopen:
|
||||
result = module.TaskAddClient().submit(self.payload)
|
||||
self.assertNotIn(os.environ['XC_TOKEN'], str(result))
|
||||
self.assertEqual(result['error_attribution'], 'transport/timeout')
|
||||
urlopen.assert_called_once()
|
||||
|
||||
def test_token_precedence_and_rejections(self):
|
||||
with tempfile.TemporaryDirectory() as directory:
|
||||
path = Path(directory)/'credential'
|
||||
path.write_text(' file-credential \n')
|
||||
with mock.patch.dict(os.environ, {'XC_TOKEN_FILE': str(path)}):
|
||||
self.assertEqual(module.resolve_token(), 'file-credential')
|
||||
for token in ('', 'tmp', 'PLACEHOLDER', 'changeme', 'tmp-token'):
|
||||
with self.subTest(token=token), mock.patch.dict(os.environ, {'XC_TOKEN': token}):
|
||||
with self.assertRaises(ValueError):
|
||||
module.resolve_token()
|
||||
|
||||
def test_placeholder_never_requests(self):
|
||||
with mock.patch('urllib.request.urlopen') as urlopen:
|
||||
with self.assertRaises(ValueError):
|
||||
module.TaskAddClient().submit(module.build_payload('org/model'))
|
||||
urlopen.assert_not_called()
|
||||
Reference in New Issue
Block a user