76 results
DSH harness bundle/plugin: tolerate OpenAI-compatible providers whose streaming responses omit finish_reason (e.g. the Snowflake Cortex gateway) so turns complete instead of failing with a TRANSPORT error.
dsh plugin: live USD cost badge (whole-session + per-turn) from provider token usage and a configurable pricing table.
One-command installer for the dsh-anchored-standard experimental presets (Anchored / Zero-Anchored / Whoami Standard)
Network diagnostics toolbox for DeepSeek Harness (dsh): DNS lookup (A/AAAA/CNAME/MX/TXT/NS/SOA/SRV/PTR/CAA), ICMP ping, TCP port check, TLS certificate check, traceroute, WHOIS registry lookup, and public IP info — zero runtime dependencies
Detach the DeepSeek Harness Web GUI into a Document Picture-in-Picture window: a floating button moves the whole app into an always-on-top window and back
Token usage analytics tab for the dsh web GUI: whole-log projections plus a per-turn/per-step breakdown
DSH plugin: right-side whole-disk file browser panel with name/size/mtime sorting and drag-into-chat
DeepSeek Harness (DSH) plugin that delegates coding tasks to the Claude Code and Codex agent CLIs and streams the whole run live — autonomous control, multi-account, automatic install, git worktrees, and any Anthropic-compatible endpoint.
Personalization plugin for the DeepSeek Harness (dsh): teach your assistant who you are, who it is, and how it should behave. Adds a Personalization page to dsh settings (custom instructions, nicknames, persona) and injects the content into every agent turn's system prompt.
Attach local files to the conversation context: a composer chip adds files whose content is injected into the model context (agent/pre-step), with a removable ✕ chips strip above the input.
Whole-disk ctx.fileReferences provider for DeepSeek Harness: Everything-backed instant search with a bounded cross-platform fallback index, fuzzy matching, and regex queries
Keeps long coding-agent sessions lean: wrap work in named tasks and, when one is done, fold its whole span into a short titled summary. The conversation stays readable, context costs stay low, and every fold's original content can be read back on demand. For DeepSeek Harness.
Don't hand over the whole machine, just the decision blocking it: unattended DeepSeek Harness approvals and ask_user_question prompts reach your phone as Feishu cards, desktop first, outbound only.
Automatically manage dsh session titles in a date｜type｜topic format: a model summarizes the type and topic of the whole conversation.
Pure-incremental directive-driven compaction for DeepSeek Harness: /compact-directive <requirement> summarizes the session middle per your requirement, /trim-directive <requirement> trims the whole conversation per your requirement
Say the secret handshake: DSH subagents start on the Minimal two-tool condition to unlock DeepSeek's full RL-trained strength, then get the whole toolbox.
Code mode for the DeepSeek Harness web GUI: a third segment beside Chat and Work whose column is the harness's own terminal, running in the conversation's workspace
DSH host plugin: OS-level desktop control tools (screen OCR with coordinates, mouse click/drag, Unicode typing, key combos) so the model can operate the whole browser including the address bar, and any other window.
Codex-style in-place conversation rollback and edit-and-resend for the DeepSeek Harness web GUI, plus a right-edge outline rail (session table of contents, switchable from Settings) whose search pages backwards through history until it matches
DSH profile bundle: load OpenClaw-style persona files (SOUL.md, IDENTITY.md, USER.md, TOOLS.md, MEMORY.md, AGENTS.md, HEARTBEAT.md, memory/*.md) into every DSH session whose workspace contains an openclaw/ subdirectory.
Everything-class whole-disk file lookup for DeepSeek Harness, backed by the goz engine (MFT filename index). Lets the agent answer "where is that file" across projects in milliseconds.
Codex-style code and file selection for DeepSeek Harness Web: workspace file tree + file viewer; selecting code or a whole file adds it to the message as context automatically
DeepSeek Harness (dsh) plugin: route one request to a modality-capable fallback model instead of forcing the whole session onto a single model.
Context compression for small-context models on the DeepSeek Harness Web GUI: one click condenses the whole conversation into a few sentences, opens a fresh session in the same workspace, and re-injects the summary as the first message so a small model keeps working with a clean, compact context.