插件目录 / Developer / dsh-code-lens
dsh-code-lens
已验证 · 实测可装 lisycotana
✓ 持续维护
0Stars
0Forks
0未关闭 issue
JavaScript语言
2026-08-15最近推送
跨平台平台
功能简介
DSH代码模式可观测性:工具调用run_code。
我们的评价
可用 — 实测通过,早期项目
可用 — 实测通过,早期项目
DSH代码模式可观测性:工具调用run_code。 实测能干净安装、正常启动。早期项目,但功能可用。
「已验证」表示我们的自动化 CI 在干净 profile 里实际执行了 dsh plugin add 并启动成功——仅此而已。功能描述与版本兼容性均为作者声明。这不是安全审计,也不代表对第三方代码的背书。
README
dsh-code-lens
Observability for DeepSeek Harness **code-mode sub-dispatches** — the tool calls arun_code program makes that the model never sees.
The gap this fills
In code mode the model writes a TypeScript program that orchestrates tool calls. The program receives every result in full. The model receives none of them — only whatever the program finally returns. Both dispatch boundaries are still recorded on the session log. That produces a three-way split with no equivalent outside code mode: | | program | model | session log | |---|---|---|---| | sub-call arguments | ✅ | ❌ | ✅ | | sub-call results | ✅ | ❌ | ✅ | dsh is the only harness that draws this distinction, because it is the only one where a tool call can happen *inside a program the model wrote*. The data is recorded and nothing surfaces it. This plugin does.What it gives you
**AcodeLens session projection** — whole-session totals, readable from the UI
without touching the log:
``json
{ "programs": 1, "dispatches": 2, "settled": 2, "errors": 1, "dispatchMs": 340, "hiddenBytes": 1027 }
`
hiddenBytes is the payload the program consumed and the log preserved while the
model saw none of it.
**A code_lens tool** — lets the model audit its own program after the fact:
`
run_code call_abc: 2 sub-calls, 1 errors, 340ms, 1027B hidden from context
call_abc:code:1 bash ok 140ms 3B
call_abc:code:2 read error 190ms 1024B
`
Install
`sh
dsh plugin --profile web add dsh-code-lens
dsh --profile web
`
Development, without packaging — note the file:// URL (a bare G:/... path is
parsed as a URL scheme on Windows):
`yaml
scratch/cordis.yml
- insert:
- id: code-lens
name: 'file:///G:/dsh-plugins/dsh-code-lens/index.js'
`
`sh
dsh --profile web --patch ./scratch/cordis.yml
`
Design notes
- **Zero dependencies.** The projection registry's runtime contract is
structural — it calls schema.parse(value) and nothing else — so the view
validator is hand-written rather than pinning a zod copy that could drift from
the host's.
- **Never appends from the observer.** session/event listeners run inside the
publication window of the append that produced the event, and Session.append()
throws on reentry. This plugin only reads there.
- **Both registries are optional.** sessionProjections and tools are acquired
through ctx.inject, so the plugin stays loadable in headless assemblies that
compose neither.
- **Holes in sub-call numbering are normal.** A sub-call queued but abandoned by
run settlement logs *neither* event, so a start without a settle is a valid
terminal state, not a leak. turn/end drops the leftovers so persisted state
cannot grow forever.
- **Pairing is by subCallId; timing comes from the event envelope time** —
neither event carries a duration.
Verified against
@deepseek-ai/[email protected], Node 24, DeepSeek-V4 via the headless profile.
Real session output — one run_code program reading eight files:
`
run_code call_00_lMDLou1XAHEXiQYgKbUR9330: 9 sub-calls, 0 errors, 23ms, 1312B hidden from context
call_00_lMDLou1XAHEXiQYgKbUR9330:code:1 read ok 6ms 164B
...
call_00_lMDLou1XAHEXiQYgKbUR9330:code:8 read ok 2ms 164B
call_00_lMDLou1XAHEXiQYgKbUR9330:code:9 code_lens unsettled — 0B
`
The model reported only "24 lines" — those 1312 bytes never entered its context.
The trailing unsettled row is code_lens observing its own in-flight call,
which is the documented terminal state for a start whose settle has not landed.
To reproduce, code mode must be on. The headless bundle already wires the tools
row to an environment variable, so no patch is needed:
`sh
DSH_TOOLS_MODE=code dsh --profile headless --patch ./scratch/cordis.yml "…"
`
Unit-level checks: verify-integration.mjs (projection fold through the real
SessionStore/SessionProjections) and verify-tool.mjs (tool registration and
execution).
Note for plugin authors
ctx.tools.register() takes the **wire** schema — a complete JSON Schema object.
defineTool accepts the author-facing shorthand (a bare property map) and
compiles it. Passing the shorthand straight to register() reaches the provider
as type: null and the request is rejected:
`
INVALID_REQUEST: Invalid schema for function 'x':
schema must be a JSON Schema of 'type: "object"', got 'type: null'.
`
This plugin writes the object root explicitly, and validates its own argument,
because defineTool's compiled validator is what it gives up in exchange for
staying dependency-free. (A plain-JS plugin installed outside the harness tree
cannot resolve @deepseek-ai/dsh-tools` as a bare specifier.)
License
MIT安装
🧩 让 Agent 自动装(推荐)
装一次目录插件,之后本站所有插件都能让 DeepSeek Harness 自动找、自动装:
dsh plugin add dshbase-catalog 然后对 agent 说「帮我装 dsh-code-lens」,它会在目录里找到并自动安装。文档:dshbase-catalog · 已验证场景包。
该插件是 GitHub 源码(未发 npm)——直接从仓库装:
Web profile:
dsh plugin --profile web add github:lisycotana/dsh-code-lens Headless(CLI)profile:
dsh plugin --profile headless add github:lisycotana/dsh-code-lens 实测报告
验证通过:从 GitHub 源码完成 L1 安装 + L2 加载 + L3 运行(dsh 0.1.0-rc.6)。
使用场景
扩展 agent 的编码能力面——给它一个新工具、工作流或集成,让它接手以前做不了的开发任务。
适合谁
想让 dsh 在真实代码库上像队友一样干活的开发者——能改、能跑、能验证,而不只是回答问题。
二次开发建议
工具/命令面就是缝:暴露更多 SDK 能力、加更聪明的上下文接线,或收紧改代码与验证之间的循环。