liqiang
b119135836
Build latest book artifacts / build (push) Canceled after 0s
dependency resolution / resolve (3.11) (push) Canceled after 0s
dependency resolution / resolve (3.13) (push) Canceled after 0s
deploy-pages / build (push) Canceled after 0s
deploy-pages / deploy (push) Canceled after 0s
i18n consistency check / check (push) Canceled after 0s
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
web-search-agent tests / test (push) Canceled after 0s
web-search-agent tests / agentbook (push) Canceled after 0s
25 lines
1.0 KiB
Plaintext
25 lines
1.0 KiB
Plaintext
# Provider: openai (default), dashscope/qwen/bailian, or openrouter
|
||
LLM_PROVIDER=openai
|
||
|
||
# OpenAI 配置
|
||
OPENAI_API_KEY=your_openai_api_key_here
|
||
|
||
# Alibaba Cloud Model Studio / Bailian (Qwen)
|
||
# DASHSCOPE_API_KEY=your_dashscope_api_key_here
|
||
# DASHSCOPE_BASE_URL=https://dashscope-intl.aliyuncs.com/compatible-mode/v1
|
||
|
||
# 模型（默认 gpt-4o-mini）：本实验特意用这个较弱、"故意可被攻破"的基线，
|
||
# 才能展示"防御逐层加强 -> 注入成功率下降"的对照曲线；换更强的模型（如 gpt-5.6-luna）
|
||
# 会在 D1 无防御下就抗住全部注入，抹平教学对比。
|
||
OPENAI_MODEL=gpt-4o-mini
|
||
|
||
# 可选：自定义 API base_url（默认官方；请勿指向已失效的第三方网关）
|
||
# OPENAI_BASE_URL=
|
||
|
||
# 通用回退：未设置 OPENAI_API_KEY 时，若配置了 OPENROUTER_API_KEY，则自动改走
|
||
# OpenRouter（gpt-* 会映射为 openai/…）。
|
||
# OPENROUTER_API_KEY=your-openrouter-api-key
|
||
|
||
# 可选：每个 攻击x防御 组合的试验次数（建议 3-5，控制成本）
|
||
TRIALS=4
|