{"_id":"@buckeyestudio/toh-session-title-all-prompts-llm","name":"@buckeyestudio/toh-session-title-all-prompts-llm","dist-tags":{"next":"0.1.1-rc.2","latest":"0.1.1-rc.2"},"versions":{"0.1.1-rc.2":{"name":"@buckeyestudio/toh-session-title-all-prompts-llm","description":"All-user-messages LLM provider plugin for TheOpen Harness session titles","version":"0.1.1-rc.2","publishConfig":{"access":"public"},"repository":{"type":"git","url":"git+https://github.com/dustinwloring1988/theopen-harness.git","directory":"packages/session/session-title-all-prompts-llm"},"type":"module","main":"lib/index.js","types":"lib/types/index.d.ts","exports":{".":{"types":"./lib/types/index.d.ts","default":"./lib/index.js"},"./invariant":{"types":"./lib/types/invariant.d.ts","default":"./lib/invariant.js"},"./package.json":"./package.json"},"license":"MIT","author":{"name":"buckeyestudio"},"peerDependencies":{"@buckeyestudio/toh-llm":"^0.1.1-rc.2","@buckeyestudio/toh-invariants":"^0.1.1-rc.2","@buckeyestudio/toh-session":"^0.1.1-rc.2","@buckeyestudio/toh-session-title-llm":"^0.1.1-rc.2","@buckeyestudio/cordis":"^4.0.1","@buckeyestudio/toh-session-title":"^0.1.1-rc.2"},"dependencies":{"@buckeyestudio/schemastery":"^3.18.1"},"devDependencies":{"@buckeyestudio/toh-invariants":"^0.1.1-rc.2","@buckeyestudio/toh-llm":"^0.1.1-rc.2","@buckeyestudio/toh-session":"^0.1.1-rc.2","@buckeyestudio/toh-session-title":"^0.1.1-rc.2","@buckeyestudio/toh-session-title-llm":"^0.1.1-rc.2","@buckeyestudio/cordis":"^4.0.1"},"_id":"@buckeyestudio/toh-session-title-all-prompts-llm@0.1.1-rc.2","bugs":{"url":"https://github.com/dustinwloring1988/theopen-harness/issues"},"homepage":"https://github.com/dustinwloring1988/theopen-harness#readme","_integrity":"sha512-HHniD4k6esw2czwC1ar4kI7n7IU6dKbwkPcVKoViG6gUlfGv9XhHldnRyB0IM7KetFIZb8Heqo8lGQhWAuqTpA==","_resolved":"/home/runner/work/theopen-harness/theopen-harness/dist/npm/buckeyestudio-toh-session-title-all-prompts-llm-0.1.1-rc.2.tgz","_from":"file:/home/runner/work/theopen-harness/theopen-harness/dist/npm/buckeyestudio-toh-session-title-all-prompts-llm-0.1.1-rc.2.tgz","_nodeVersion":"24.19.0","_npmVersion":"11.17.0","dist":{"integrity":"sha512-HHniD4k6esw2czwC1ar4kI7n7IU6dKbwkPcVKoViG6gUlfGv9XhHldnRyB0IM7KetFIZb8Heqo8lGQhWAuqTpA==","shasum":"7ff0a3e1d810cd857123f90e03354d1615e9c6b4","tarball":"https://registry.npmjs.org/@buckeyestudio/toh-session-title-all-prompts-llm/-/toh-session-title-all-prompts-llm-0.1.1-rc.2.tgz","fileCount":9,"unpackedSize":10645,"signatures":[{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEUCIFH6dyPgfDIed70yzsQIJENJgCsrxQKJuQfH3Dsjz7HjAiEAn+WIX/UvaorkmDIDgEjjsI9+KYzz9RqVgD2IUptRWzU="}]},"_npmUser":{"name":"buckeyestudio","email":"dustinwloring1988@gmail.com"},"directories":{},"maintainers":[{"name":"buckeyestudio","email":"dustinwloring1988@gmail.com"}],"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/toh-session-title-all-prompts-llm_0.1.1-rc.2_1787489843838_0.4499174558000303"},"_hasShrinkwrap":false}},"time":{"created":"2026-08-23T12:57:23.708Z","0.1.1-rc.2":"2026-08-23T12:57:23.955Z","modified":"2026-08-23T12:57:24.121Z"},"maintainers":[{"name":"buckeyestudio","email":"dustinwloring1988@gmail.com"}],"description":"All-user-messages LLM provider plugin for TheOpen Harness session titles","homepage":"https://github.com/dustinwloring1988/theopen-harness#readme","repository":{"type":"git","url":"git+https://github.com/dustinwloring1988/theopen-harness.git","directory":"packages/session/session-title-all-prompts-llm"},"author":{"name":"buckeyestudio"},"bugs":{"url":"https://github.com/dustinwloring1988/theopen-harness/issues"},"license":"MIT","readme":"# @buckeyestudio/toh-session-title-all-prompts-llm\n\n[English](README.md) | 中文\n\n可选的 `ctx.sessionTitle` 提供方，通过 `ctx.llm` 总结所有符合条件的用户消息。它注册 `all-prompts` 节奏，并在每条新用户提示词后启动新 revision，同时使用预置历史与子会话提示词。较新的 revision 会中止并取代旧工作；即使提供方忽略取消，也无法提交陈旧输出。\n\n该插件使用完整且必填的[共享 LLM（大语言模型）配置](../session-title-llm/README.zh.md#configuration)。同时省略 `provider` 与 `model` 时，会继承每个当前已记录主请求的确切路由；也可以同时设置二者，使标题生成使用独立路由。如果最终封装的聚合提示词超过 `maxInputBytes`，请求会失败而不是截断历史；自动使用时会发出警告并保留先前标题。\n\n## 模型体验\n\n### 全消息标题请求\n\n#### 模型看到的内容\n\n标题模型会收到共享标题指令，以及一个 JSON 数组，其中按日志顺序包含截至当前 revision 的所有符合条件用户消息和确切 seq。预置历史也包含在内。\n\n#### Token 影响\n\n每条符合条件的新提示词之后都可能发送一次辅助请求，每次请求受 `maxInputBytes` 和 `maxOutputTokens` 约束；显式刷新可能增加调用。主 agent（智能体）请求不会增加 token。\n\n#### KV Cache 影响\n\n不会使主请求的 KV Cache 失效。每条提示词后，辅助输入都会增长或变化，因此提供方专用缓存复用会在第一个变化的 JSON token 处结束。\n\n## 已知限制与暂缓事项\n\n- 输入溢出时保留先前标题；对于很长的会话，此提供方没有基于摘要继续生成摘要的机制或保留策略。\n- 它平等对待所有符合条件的用户消息，不提供权重、过滤或手动标题优先级。\n","readmeFilename":"README.zh.md","_rev":"1-4a60b04bf09e3b6575647a67df1ab677"}