feat: v0.2.0-beta - History UI, resume/cache, native tool calls (开发预览版) #13
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.

功能更新与使用说明(v0.2.0-beta 开发预览版)
你会看到的主要变化
/history,按 Project → Simulation → Report 的嵌套关系浏览历史,并可一键跳转到 Step2/Step3/Report/Chat。Continue会在同一个report_id上从未完成章节继续生成(不重复生成已完成章节)。Regenerate会为同一个simulation_id创建新的report_id(旧报告保留在历史中)。interview_agents需要模拟进入 waiting/alive 模式;后端支持"只重连,不原地重启",避免破坏历史数据。Activate (safe):自动创建新的 simulation branch(新simulation_id),在新分支上运行 Step3 来恢复 Interview 环境,原分支目录不被修改。run_parallel_simulation.py脚本的代码版本(MD5),当检测到代码更新时,会自动终止旧进程并提示重启,确保使用最新代码。tool_calls(不依赖模型输出<tool_call>文本),减少"未注册工具"类干扰。/settings),支持查看可用模型列表、切换默认模型。scripts/smoke.mjs(quick/full),用于本地端到端验证。如何正确“继续生成/重新生成”(避免污染)
1) 先确认 Interview 环境是否 Alive
Interview Env状态卡:env_alive=true:可以安全继续/重新生成报告(会调用原模拟环境,不会重启模拟目录)。env_alive=false:无法采访;需要 先恢复环境(见下一节)。2) 当
env_alive=false时如何恢复Activate (safe):simulation_id(分支)alive本地配置(MiroFish-config + Clash Verge)
配置加载优先级
后端会按以下优先级读取环境变量:
MIROFISH_ENV_FILE(显式指定).envMiroFish-config/.envHTTP(S) Proxy(可选)
在
.env或MiroFish-config/.env中设置:LLM Base URL
LLM_BASE_URL支持配置为你自己的 OpenAI-compatible endpoint(例如https://your-endpoint或https://your-endpoint/v1;系统会归一化为包含/v1的形式)。LLM_BASE_URL(并设置OPENAI_BASE_URL等兼容变量)。运行与验证
npm run devcd backend && .venv/bin/python -m pytest -qnpm run buildnpm run smokenpm run smoke:fullnpm run smoke:full:cleanup排障(最常见)
interview_agents返回(可能需要几分钟)。backend/uploads/reports/<report_id>/console_log.txtbackend/uploads/reports/<report_id>/agent_log.jsonlInterview Env是否aliveActivate (safe)创建分支恢复环境