278 results
Settings UI for DeepSeek Harness (DSH) to edit each model provider's request retryPolicy — mode (normal/always), maxRetries, retryableCodes and exponential-backoff parameters — written to settings.yaml and applied by dsh-llm-retry. 模型重试策略设置：在设置面板中可视化编辑各模型提供方的 API 请求失败重试策略。
Official-grade GitHub CI for DeepSeek Harness: composite action (review PRs / fix CI / report), polling PR review bot with idempotent inline comments, a status-check gate, and approval-gated PR/issue/repo/file tools
DeepSeek Harness plugin: per-event task-completion and attention sounds for turn-end / approval / question / plan-review / goal-blocked / task-failure, each with its own sound (built-in synth, local audio file) and volume (Web UI)
DeepSeek Harness plugin: per-event task-completion and attention sounds for turn-end / approval / question / plan-review / goal-blocked / task-failure, each with its own sound (built-in synth, local audio file) and volume, with a separate subagent channel (Web UI)
Route DeepSeek Harness agent requests by role: planner model in plan mode, default model otherwise, subagent model for subagents.
Provider-independent DSH document parsing powered by MinerU, with native background jobs, immutable results, and safe request coalescing.
Display images read by the read_image tool inside the DeepSeek Harness Web GUI: a dedicated Read image row with a default-expanded message-style image card (PS-style transparency checkerboard), merged read-N-images rows with side-by-side frames for multi-image requests, and an in-page full-resolution lightbox (zoom buttons, mouse wheel, 1:1 original size). 在 Web GUI 对话流中展示 read_image 读到的图片：默认展开的消息图片卡（透明棋盘格）+ 多图合并并排行（读取了 N 张图片）+ 页面内全精度放大层。
把开发变成 RPG：回合/工具/todo 积累 XP、成就徽章、等级与赛季。事件流驱动，纯函数计分。
DeepSeek Harness vision enhancer: raises image limits to the official DeepSeek values, raises the per-model request image budget for DeepSeek-V4.1-Flash, and provides high-resolution tiled image reading via a dedicated tool.
Model-based permission approval (approve-for-me) for DeepSeek Harness: an approval/request answerer backed by a separate reviewer model
CC Switch-style token consumption statistics for the DeepSeek Harness Web GUI: per-request usage log, real-consumption hero, request-time-bucketed trend chart, per-model peak/off-peak list pricing, per-project and per-model stats, and account balance.
Question-Driven Discovery CLI
DeepSeek Harness QoL plugin for the local Qwen3.8 line (27B, Flash-Next): per-request thinking budgets on both llama.cpp and NInfer dialects, vision + tools, and a compaction backend whose summaries stop burning the output cap on thinking.
Codex-style conversation outline for DeepSeek Harness: a floating panel listing every user question in the current conversation with search, load-older and click-to-jump (scroll + highlight). Bilingual zh-CN / en.
WebUI-managed encrypted credentials for DeepSeek Harness: one file, plaintext until a password is set, then AES-256-GCM ciphertext under an Argon2id-derived key with SHA3-256 fingerprints; per-request decryption, unlock lockout, leak-guard output redaction, and shipped-code integrity self-checks.
On-demand vision for text-only DSH sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model
Whitelist / blacklist / any-error retry policy for DeepSeek Harness, driving DSH's built-in LLM request retry mechanism.
Inject an x-session-id HTTP header onto every DeepSeek Harness LLM provider request, carrying the harness session id of that exact call; also covers whitelisted gateway fetches during tool execution.
Persistent long-term persona memory for DeepSeek Harness: MEMORY.md/USER.md storage, memory + memory_search tools, per-request context injection, secret scanning, and a WebUI memory-management settings page. Ported in spirit from pi-hermes-memory. TypeScript sources, built with tsc + esbuild.
DeepSeek Harness plugin: real-time DeepSeek API balance and usage timeline (cost / tokens / request count), rendered in a settings page.
Global proxy for DeepSeek Harness: route agent tools, model requests and web fetches through the Windows system proxy or a custom proxy with one persistent toggle, an editable settings card, agent-visible status and a bypass-aware prompt section
Claude Code integration plugin for DeepSeek Harness, providing native Claude conversations powered by the Claude Agent SDK, with model selection, approvals, questions, tools, and session continuation.
Persistent global fetch proxy for DeepSeek Harness LLM requests (undici setGlobalDispatcher + EnvHttpProxyAgent), configured via the llm-proxy settings namespace
Desktop notifications for DeepSeek Harness (dsh): run completion, model questions, and approval requests. Zero runtime dependencies — all peers provided by the dsh CLI.