Answers from the documentation; checking which model is on duty
Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
Imported from heart-breaker666/FlashCSV (AGENTS.md). Install upstream with npx skills add heart-breaker666/FlashCSV. Copyright stays with the author.
开发约定
项目仅在本目录开发,构建、数据和报告使用项目内的 build/、data/、reports/。
功能与验收以 docs/design.md 为准,按需查阅,不重复加载全部文档。
docs/implementation-plan.md 只记录任务顺序。
Linux、C++17、CMake;核心代码 1,000–2,500 行,测试与脚本另计。
遵循用户当前指令;获得实施授权后,计划内可逆改动无需逐项确认。
功能改动验证相关行为;并发改动验证取消与线程回收。未执行的测试不能写成通过。
不扩展已确认范围,不为凑行数压缩代码,不提交构建产物与大数据。
行为规则变更只更新设计,避免多处重复。
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - a plan picks it for its slotcurl-s-X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
Installed into a catalogue, chosen by a router
Install FlashCSV and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.