Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs(preset): let the preset directory be the roster

Browse Source 
The README and the note each restated which presets ship. `code` was added a
layer later and neither followed, so both said three where the directory holds
four — the drift the review predicted, arriving on schedule. They point at
`apps/cli/config/agent-presets/` now: one directory per preset, and the
listing is the answer. The real-composition test still pins the exact set,
which is where a roster change should be felt.
This commit is contained in:
Yichen Jiang
2026-08-06 20:03:05 +08:00
parent ef089ed6ec
commit 1123a128d9
6 changed files with 8 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
.agents/notes/implemented/architecture/2026-08-03-per-session-agent-presets.i18n.yaml
View File

@@ -2,5 +2,5 @@
# side as of the last confirmed-consistent state. Both languages carry equal authority;
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-03-per-session-agent-presets.md
2026-08-03-per-session-agent-presets.md: b0f0de131b6f5051bb5a17a38636826ebd5771fd
2026-08-03-per-session-agent-presets.zh.md: 9ca1374d1b4b43fda24fea81adf741d474dc0084
2026-08-03-per-session-agent-presets.md: ba8476690f6b4b71e571ef7a19b61a2b31d00724
2026-08-03-per-session-agent-presets.zh.md: fcca281068055d24475e3bbfdc959f9930815a30

2
.agents/notes/implemented/architecture/2026-08-03-per-session-agent-presets.md
View File

@@ -23,7 +23,7 @@ Composition splits into two planes, decided by what must be shared rather than b
Model routing stays out of presets. `installAgentLlmTarget` is already the per-agent seam for provider, model, and reasoning effort, and an LLM adapter mounted inside a preset would never be resolved by `agent-loop`, which lives in the host plane.
The deployment ships three presets — `standard` (the full coding agent), `minimal` (a two-tool benchmark surface), and `cordis` (the standard agent plus the self-referential toolset and a composition-authoring skill).
The presets the deployment ships are the directories under `apps/cli/config/agent-presets/`; the roster is that listing, not a list restated here.
Mounting is per-session by default. Measured cost for a twelve-row composition is ~3ms and ~600KB per session, so isolation is the cheaper default than any sharing scheme, and a preset authored by a user or by an agent then has the smallest possible blast radius. A preset that genuinely owns an expensive singleton opts into sharing with Cordis's own `isolate` vocabulary: a named realm label is process-global, so two subtrees naming the same label resolve one instance.

2
.agents/notes/implemented/architecture/2026-08-03-per-session-agent-presets.zh.md
View File

@@ -23,7 +23,7 @@ Status: implemented
模型路由不进 preset。`installAgentLlmTarget` 已经是 provider、model 与 reasoning effort 的按 agent 可替换点；而挂在 preset 内部的 LLM 适配器永远不会被 `agent-loop` 解析到，因为后者位于宿主平面。
部署随附三个 preset —— `standard`（完整编码 agent）、`minimal`（两个工具的 benchmark 表层）与 `cordis`（标准 agent 加上自指工具集与一份组装创作 skill）。
部署交付哪些 preset，取决于 `apps/cli/config/agent-presets/` 下有哪些目录；清单是那份目录列表，而不是在此另抄一份。
挂载默认按会话进行。实测一份十二行组装每会话约 3ms、约 600KB，因此隔离比任何共享方案都更划算；而由用户或 agent 写出的 preset 也因此拥有尽可能小的影响面。确实自带昂贵单例的 preset，可以用 Cordis 自身的 `isolate` 词汇显式选择共享：命名 realm 的 label 是进程级全局的，因此两棵子树只要写同一个 label 就解析到同一个实例。