dsh-flash-godmode
Manifest valid★ 1V4 Flash God Mode v0.2 (opencode-go Adapted Version) — w7 persona (classification/review/anti-divergence anchor) + first-round tool anchoring + depth/speed guided dispatch based on task complexity (agent/inbox/spliced capture, headless first-round available).
dsh-flash-godmode
V4 Flash "god mode" for DeepSeek Harness: w7 persona anchoring + first-turn tool anchoring + complexity-dispatched guidance — turn Flash's unstable thinking into reproducible capability.
简体中文版见 README.zh.md
V4 Flash on reasoning: max is powerful but unstable: it over-thinks simple tasks, under-thinks complex ones, and drifts mid-session. This plugin turns that instability into a routed capability, using the measured persona bands from dsh-router-standard:
- w7 persona (author-measured Flash optimum) — neutral identity + classify-then-act instruction + recall/anti-runaway anchors. No deep-thinking sentence baked in (author's correction: per-message guidance is negative on related-task chains, P21).
- Complexity-dispatched guidance — complex tasks get the decision-closure deep guide, simple tasks get the fast-convergence guide. Dispatched on the very first request, thanks to a capture path that works on headless (see below).
- First-turn tool anchoring — the first request sees only the core tool set (read/write/edit + shell); after the first durable tool call the full catalog is exposed.
Dependencies: DSH 0.1.x (headless profile) + any openai-completions provider (built and tested with the opencode-go channel, deepseek-v4-flash, reasoning: max).
Why the capture path matters
The author's own router reads the first user message via user/message events. On headless, that event lands after the first prompt assembly — too late for the path-committing first request. This plugin listens for agent/inbox/spliced instead, which carries the task text before the first assembly (verified on rc.6 headless). Result: the guidance decision is present on request #1, where it counts.
Quick start
# bundle install (recommended)
dsh plugin --profile headless add github:Cavan-Ou/dsh-flash-godmode
# verify: run any task; stderr shows the dispatch decision
dsh --profile headless "简单任务:运行 python3 -c 'print(1+1)' 并报告输出" 2>&1 | grep godmode
# → [godmode] taskLen=NN complex=false guide=fast mode=weak
Flash models are routed to weak mode automatically (model-id detection). Non-Flash models fall back to keyword task classification (react/spec/weak).
What's inside
lib/
├── router-core.mjs # pure routing logic: personas, bands, complexity heuristic, task classification (zero deps)
└── router-bootstrap.mjs # Cordis plugin: task-text capture, guidance dispatch, tool anchoring
tests/
└── router.test.mjs # node:test unit tests (11 cases)
Observed results
| Result | Evidence |
|---|---|
| Complexity dispatch works end-to-end on headless | 2026-08-18, three real runs: simple task → guide=fast (1-step convergence); refactor/architecture task → guide=deep (decision-closure guide, deep analysis proceeded); multi-turn write+run task → completed correctly with tool anchoring intact. 3/3 passed |
| Environment-check rumination suppressed | 2026-08-15 five-anchor experiment: echo/whoami/uname/node --version/date calls recognized as wasted turns and suppressed via the anti-runaway anchor (now also a global rule in the workspace's ~/.dsh/AGENTS.md) |
| Zero tool failures across real sessions | Observation journal, 2026-08-15/16: 8 sessions, 129 tool calls, 0 failures |
| w7 persona is the measured Flash optimum (author-published) | dsh-router-standard: discrimination +5.67 (P11), single-task completion 100% (P23), decision-closure deep guide: depth +12% with faster convergence 8.0 vs 8.3 steps (P30) |
Known edges
- The complexity heuristic (
text.length > 120or architecture keywords) is the author's original — a filename likeanalyze.pycounts as complex. False positives lean toward the safe direction (deep guide, not no guide). - If the
agent/inbox/splicedcapture fails on a future DSH version, the plugin falls back to the bare w7 persona (no guidance) — safe per P23, and the task still runs. - All author-measured numbers above come from the official DeepSeek API; this plugin was verified on the opencode-go channel (same weights, different serving) — see the local runs in the table.
Relationship to dsh-routing-suite
dsh-routing-suite is the author's full kit (runtime injector + router presets) aimed at the web profile (PowerShell installer, preset selection per session). This plugin is the headless-native single-plugin form: installable via dsh plugin add, no installer script, first-request guidance on headless (which the suite's own issue tracker flags as not taking effect on rc.6).
Contributing
This plugin grows from real use. Hit an edge not listed here? Open an issue with the incident (symptom → root cause → fix). PRs welcome in Chinese or English.
License
MIT — with attribution to dsh-router-standard (MIT), whose measured persona bands and guidance texts this plugin builds on.
Built by running real tasks on headless, not by reading docs.
Comments
Loading…
From the same category
by tt-a1i
Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.
★ 71.9k
↓ 3.5k/wk
MIT
JavaScript
Sep 25, 2026
dsh plugin --profile agent add @tt-a1i/archify-dshDeepSeek Harness plugin for Reactive Resume: bridges your resumes and job applications into a Harness session over MCP.
★ 41.7k
↓ 236/wk
MIT
Aug 24, 2026
dsh plugin --profile web add dsh-plugin-reactive-resumeby Tencent
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
★ 30.2k
↓ 838/wk
NOASSERTION
Go
Sep 26, 2026
dsh plugin --profile web add @wxg-prc-cpg/dsh-weknoraby anywhere-labs
为 DeepSeek Harness (DSH) 插件生态打造的现代化桌面端解决方案。万物皆「插件」,桌面本身也是「插件」。
★ 29k
↓ 167/wk
MIT
TypeScript
Sep 25, 2026
dsh plugin --profile web add dsh-plugin-desktopdeepseek-harness-desktop is a interface plugin for DeepSeek Harness. See the repository documentation for its documented capabilities.
★ 28.6k
MIT
by titanwings
Distilly — Distill how they think into reusable Skills for any Agent or Bot. Formerly Colleague Skill(原同事 Skill).
★ 25k
MIT
TypeScript
Sep 22, 2026