- Inicio
- Plugins
- Modelos y proveedores
- dsh-jev-harness
dsh-jev-harness
zrxparley/dsh-jev-harness
One switch decides who does the work in DeepSeek Harness. OFF steps aside and uses the DSH model gateway; ON sends every instruction to a JEV judge first, which routes judgment tasks to Kimi and routine execution to DeepSeek Flash. By default the routed calls run through the DSH model gateway (ctx.llm), so only the JEV judge key is needed here; the strategy and execution models are picked from the providers and model ids this DSH install actually has (ctx.llm.listProviders/listModels), auto-ranked or pinned in the panel; Direct mode calls your own OpenAI-compatible gateway instead. Includes a left-sidebar settings page, a composer switch, a hover decision trace (which model actually answered), a traffic dashboard, and a skill router that asks the same judge which of the 39 mattpocock/skills fits the task. Tools: harness_call/harness_classify/harness_review/harness_probe/harness_skill/harness_dsh. No user-facing tier choice. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
Instalar
dsh plugin --profile web add github:zrxparley/dsh-jev-harnessREADME
JEV Tiered Harness
A self-contained DeepSeek Harness plugin: one switch decides who does the work in a session. While it is ON, every instruction you send is first read by a JEV judge, which picks the tier and routes the work to Kimi (judgment) or DeepSeek Flash (execution). You never choose a tier — and there is no tier UI to choose from.
No provider configuration and no route authorization in DSH are required.
Where it shows up
| Location | What it does |
|---|---|
| Left sidebar entry | "JEV 分级调度" panel: master switch + base URL / API key / model id per gateway + connectivity test |
| Composer switch | One-click ON/OFF, effective immediately |
| Settings → Plugins → global plugin card | The same configuration page |
Master switch
- ON — the harness owns routing: JEV judges each instruction, then Kimi or DeepSeek Flash produces the answer; DSH's own model selector is not part of the path.
- OFF — the harness steps aside completely and everything falls back to DSH's own model gateway.
Execution route (DSH gateway vs direct)
Two real paths once the switch is ON — pick one in the 执行方式 card:
| Mode | Who sends the Kimi / DeepSeek request | Keys needed here |
|---|---|---|
| Via DSH gateway (default) | DSH itself (ctx.llm, using providers/models configured in DSH) | JEV judge key only |
| Direct | the plugin calls its own OpenAI-compatible endpoints | JEV + Kimi + DeepSeek |
In DSH mode the plugin holds and uses no kimi/dsf credentials: the Host already owns provider credentials, so the plugin only decides the tier and hands the work over. Tier provider/model are two dropdowns filled from ctx.llm.listProviders() / listModels() (「刷新模型清单」 re-asks the Host). Leaving them empty means auto: follow the provider you picked in the DSH selector, then rank model names for strongest vs fastest.
「让 DSH 选择器跟随」 is on by default: after JEV hands work to a model, the Host agentDefaultModel is rewritten to that provider/model, so the selector above the composer shows the model that actually did the work. Turn it off if you do not want that rewrite.
Where the models come from: your own DSH gateway
The plugin does not pick providers for you. Both dropdowns are filled from what this machine's DSH actually registered (ctx.llm.listProviders() / listModels()) — you have titigate, somebody else has theirs, and each install lists its own.
- Auto (default): stay inside the provider your DSH model selector points at, then rank by model name — judge-like ids (
kimi / k3 / pro / max / reason) for the decision tier, fast ids (flash / mini / lite / fast) for execution. The resulting pair is printed on the card (现在会用到:titigate/kimi-k3.1-pro). - Pin it: choose an explicit provider + model in the dropdowns.
- 「刷新模型清单」 re-reads the list from DSH at any time.
Traffic dashboard
The top of the settings page is a live per-gateway dashboard:
| Metric | Meaning |
|---|---|
| Requests | one per real HTTP call to a gateway (probes and failures included) |
| Tokens | the gateway's own usage; failed calls count 0 |
| Success rate / latency | accumulated over the selected window, latency averaged |
| Bars | hourly for the last 24h, daily for the last 7d, grouped by gateway; hover for exact values |
Three gateways, three traffic kinds: JEV judge (/systemone), Kimi decision, DSF execution. It refreshes every 10 seconds.
The ledger lives at <DSH_HOME>/jev-harness-usage.json (default ~/.dsh/jev-harness-usage.json), accumulated hourly and daily so it survives restarts; only counts, tokens and latency are stored, never prompt text.
Skill routing · mattpocock/skills
With "auto-mount skill" on, harness_call asks the JEV judge one more question before dispatching: does this task have a skill that would change how it is executed? The judge picks one of the 39 skills in mattpocock/skills (TDD, code-review, diagnosing-bugs, wayfinder, to-spec, to-tickets, triage, wizard, grilling, teach, …) or answers none. The chosen skill's body is prepended as a ## Skill: <name> block, so the routed model follows it instead of improvising.
| Mode | How |
|---|---|
| auto | default; harness_call picks and mounts |
| explicit | harness_call(skill="engineering/tdd") |
| skip | harness_call(skill="off") |
| browse | harness_skill(action="list") |
| dry-run the pick | harness_skill(action="pick", task="…") |
| read a body | harness_skill(action="read", id="engineering/tdd") |
| sync upstream | harness_skill(action="refresh") or the panel's refresh button |
- The catalog ships bundled (routing costs no network).
refreshissues exactly one request (the GitHub source tarball), rewrites~/.dsh/jev-harness-skills/catalog.jsonand caches all 39 bodies, so later reads are local. - Upstream changes need a refresh, not a plugin upgrade. If the JEV gateway is unreachable, a local keyword matcher takes over.
Design boundaries (convention vs guarantee)
Not every behaviour here is equally solid. Some are guaranteed by code (the merged judge fires exactly one request, recursion jev→jev is refused, degradation is always marked in the ledger); others are conventions held by prompts (the "harness owns routing" switch only works if the agent actually calls harness_call). Confusing the two is how this project kept breaking. The component diagram and the full convention-vs-guarantee table live in docs/ARCHITECTURE.md; the reasoning behind each decision is in docs/adr/.
Roadmap
Iteration items live as GitHub issues with现状 evidence, requirements and acceptance criteria. The ordering and the reasoning behind it are in docs/ROADMAP.md, tracked by #12.
Honest status: "switch ON = traffic does not go through the DSH gateway" is a convention today, not a mechanism. The plugin can register tools and a system prompt; which endpoint actually serves a request is decided by the DSH provider layer. Making that guarantee real is #5.
Tools
| Tool | Purpose |
|---|---|
harness_call | The entry point, tier=auto by default: JEV judges, then Kimi / DeepSeek Flash answers |
harness_classify | Ask what tier the judge would pick, without executing (diagnostics) |
harness_review | Second-model quality gate: decision drafts reviewed by Flash, execution drafts by Kimi |
harness_skill | catalog of the 39 skills: list / pick / read / refresh / status |
harness_probe | Probe gateway reachability and discover real model ids via OpenAI-compatible GET /models |
Tier rule: does a human need to judge whether this is right? → decision (Kimi); mechanical execution → execution (Flash). Without a JEV gateway the plugin falls back to a local keyword heuristic, ties going to decision.
- Hover the switch for the decision trace: which tier the judge picked and with what confidence, which model actually answered, tokens, latency and a task excerpt. Falls back honestly to
heuristic (JEV unreachable)when the judge is down.
Install
dsh plugin add @zrxparley/dsh-jev-harness
Or DSH Settings → Plugins → Add plugin → search @zrxparley/dsh-jev-harness.
Client bundle id and release installs
DSH's client module loader keys every bundle factory by its boot-manifest row id, which is
the installed package name. A client half that hardcodes the other name never materializes:
the loader throws no registered factory for "<id>" and the panel silently never mounts.
lib/client.js therefore derives its id at load time from window.__DSH_BOOT__.entries
(the row whose id ends in jev-harness, with a /client suffix stripped), and falls back to
@local/jev-harness when no manifest is present (unit tests, older hosts). Both install modes
work with the same file:
| Install mode | manifest row id | registered id |
|---|---|---|
| local bundle | @local/jev-harness | @local/jev-harness |
| npm / tarball | @zrxparley/dsh-jev-harness | @zrxparley/dsh-jev-harness |
Verified without npm: test/release-pack.test.js builds a tarball from package.json's files
with the system tar, unpacks it, loads the unpacked lib/client.js against a release-shaped
manifest, and asserts that both main and sidebar.panellist register with components.
test/bundle-id.test.js locks the id derivation itself (npm id, local id, /client suffix,
missing manifest, unrelated entries). With npm available, run npm pack and feed the tarball
to the same assertions.
Configure
Fill the in-plugin settings panel (written to ~/.dsh/jev-harness.json, mode 0600 — keys never enter the repo or the config file):
kimiBaseUrl/kimiApiKey/kimiModel— decision tier, e.g.https://your-gateway/v1+kimi-k3.1-prodsfBaseUrl/dsfApiKey/dsfModel— execution tier, e.g.https://your-gateway/v1+deepseek-v4.1-flash-1017jevBaseUrl/jevApiKey/jevModel— the judge, a TypeSafe-compatible/v1/systemone
Use the gateway's real model ids, not marketing names. "Test connectivity" lists the ids the gateway actually serves.
Environment variables work as a fallback: KIMI_API_KEY / DSF_API_KEY / JEV_API_KEY, plus *_BASE_URL / *_MODEL.
Note
deepseek-v4.1-flash-1017 is a reasoning model, so its thinking spends the completion budget. On empty content the result carries reasoningTokens and suggests retrying with maxTokens around 600–1200.
License
MIT
Plugins relacionados
dsh-our-free-model
ebony-vinyl/dsh-our-free-model
dsh-routing-suite
yjh051108/dsh-routing-suite
dsh-connect-workbuddy
dingminhua/dsh-connect-workbuddy
dsh-workbuddy-connect
corrinehu/dsh-workbuddy-connect