xiaobright /dsh-anchored-standard
Two-phase DeepSeek Harness preset: Minimal-aligned bootstrap, then full Standard tools (Project2 98/99)
★ 3,715⑂ 121👁 4⑃ 43● 48▤ 0
+0
Daily
-5
Weekly
-46
Monthly
3,715
stars
121
forks
4
watchers
43
prs
48
issues
0
releases
README
dsh-anchored-standard 中文说明 Experimental DeepSeek Harness agent presets — a base mode, two live-anchor variants, and one seeded prefab mode — that anchor a session's model trajectory on the Minimal condition (real Minimal tool schema, no auto-injected context), then promote to a small resident catalog once the session is durable, unlocking heavier Standard tools on demand. This is a community project. It is not an official DeepSeek preset and is not affiliated with or endorsed by DeepSeek. The project is frozen — new issues and pull requests are no longer accepted (see Project status). For ideas for new plugins or useful findings, please submit them under the repository. Project status (frozen 2026-09-10) This project is frozen. On 2026-09-10 DeepSeek released V4.1 Flash and announced that V4 Pro — the model these presets were measured on and tuned for — is retired on 2026-09-14 12:00, with its traffic routed to V4.1 Flash. The presets exist to re-anchor a trajectory that the successor does not appear to need patched: the flash family anchored under every condition in our first-round dose-response probes (32/32), which is why the project never tuned for it. V4.1 Flash's own first-round trajectory has NOT been measured (no API budget in maintenance mode), so treat that as an inference from the earlier flash data, not a result. The model the work was built around is going away, so the maintenance period ends here. New issues and pull requests are no longer accepted or handled. The repository stays online with its history, data and acknowledgement record intact. This is the ending FAREWELL.md asked for: "let the next model eat more diverse harness environments during training, so that patch engineering like this is no longer necessary." That file now ends with a closing note written by the successor model itself, V4.1 Flash. What stays valid is the model-agnostic part — the context-gate unified injection control, the prefab pipeline, the discovery-tool dose-response data, and the general observation that the API-visible surface conditions the trajectory. Research material remains open in DeepseekCotexplorations. Earlier status (2026-08-17, kept for the record): following the price increases on both the DeepSeek official API and the opencode go subscription, active development had already stopped — the evaluation loops these presets depend on (Project2-class runs and multi-trial roll/probe experiments) were no longer affordable, leaving the repository in maintenance only mode (bug fixes and harness-compatibility updates when feasible). A personal note from the maintainer: FAREWELL.md (Chinese). Contributors and collaborators are listed in ACKNOWLEDGEMENTS.md. Community projects that users report perform better in some scenarios, plus ecosystem tooling built around these presets: - dsh-routing-suite — a runtime injector plus task-aware thinking-mode routing presets (the router-standard family). - J-Space Cognition Suite — a model-agnosti
Top issues
#61每次bash工具调用会延迟3.5s返回5 comments · 2026-08-16#49instruction-hint 的命令式措辞会把锚定轨迹打回 "let me";中性/建议式措辞能保住 "we"——且 AGENTS.md 知识可通过按需读取(skill_load/read)保留,不降智5 comments · 2026-08-15#85反馈:both 模式晋升 + 完整 SDK,以及两个有害旋钮(首轮输出帽 / 锚定门)3 comments · 2026-08-31#32dev_tool_search 在 0.1.0-rc.6 上搜索不到任何工具,解锁链路失效3 comments · 2026-08-15#81[Behavior] Identity drift: model claims I am Claude under the bare Minimal persona(附一行修复与验证数据)2 comments · 2026-08-26#65Independent replication (n=3 per preset): trajectory anchoring reproduces strongly, the ability gap does not2 comments · 2026-08-16#51Multi-env test report: V4 Pro x anchored-standard (modeltest Project2) — Ability 85–90, 98/99 not reproduced2 comments · 2026-08-16#40[Issue] .agent-presets 下无 preset.yml 的目录仍被注册为空名预设2 comments · 2026-08-15
相关报道 (9)
blog.csdnGitHub每日热评|dsh-anchored-standard:用 Minimal 的第一跳稳定 Agent 工具轨迹2026-09-06bilibili末影龙桌宠(dsh anchored-standard插件 )2026-08-29blog.csdnGitHub 开源热榜项目-周榜(2026-08-17)2026-08-17QQ News从毛坯到精装,DeepSeek Harness的入门教程来了2026-08-24风闻DeepSeek V4 Pro正式版:同一模型能力差距为何断档?2026-08-18虎嗅网一个Skill让DeepSeek V4 Pro超越Fable 5?热门插件被锤了2026-08-18SohuDSH插件生态爆发!首日100+次日破千,先装开智插件提模型表现2026-08-17搜狐网DeepSeev-V4-Pro被冤枉了?性能时好时坏,真相可能藏在「极简模式」里?2026-08-16QQ NewsDeepSeek Harness 最新邪修曝光!极简模式能让性能暴增?但是几乎没有人会用2026-08-15