dsh-llm-ai
models.dev-cataloged multi-provider LLM adapter for the DeepSeek Harness LLM seam
94 results
models.dev-cataloged multi-provider LLM adapter for the DeepSeek Harness LLM seam
Context occupancy and account balance for the DeepSeek Harness Web Client: a session-header readout, a balance capability seam, and a DeepSeek provider
Synthetic-backed search provider and Settings card for the DeepSeek Harness web capability seam (ctx.web)
Native multi-provider web search for the DeepSeek Harness: Tavily, Exa, Firecrawl, Brave Search, and Serper as keyed providers with an automatic keyless DuckDuckGo fallback, plugged into the harness ctx.web seam so the built-in web_search tool works even without a DeepSeek API key.
Volcengine Ark (火山方舟) web-search provider for the DSH web seam: calls the Ark Responses API with the native web_search tool and maps url_citation annotations to search sources.
Keyless DuckDuckGo web search provider for DeepSeek Harness (ctx.web seam) — zero API keys, zero tokens, zero accounts
Shared zero-runtime-dependency toolkit for PerryLink DSH plugins: a pluggable Provider registry seam, fail-closed approval and adaptive session-event gates, mechanical verify scripts, shared sanitize/pricing/judge modules, and a new-plugin skeleton.
Kimi Coding web search and fetch providers for the DeepSeek Harness — one coding-plan key fills both ctx.web seams, with a dedicated settings GUI card and credential fallbacks down to the Kimi CLI config file
Xiaomi MiMo v2.5 adapter for DeepSeek Harness LLM seam with thinking chain support
Structured git tools for DeepSeek Harness agents: deterministic porcelain parsing (Chinese/UTF-8 paths, Windows) plus a diff-before-commit policy gate that refuses blind commits.
Git status badges for DeepSeek Harness: sidebar workspace rows (via the sidebar.workspaces.row seam) and an input-row chip showing the current conversation's workspace git state. Event-driven freshness over SSE.
Keyless multi-engine web search + page fetch providers for the dsh web seam (no DeepSeek dependency).
Docker-container (WSL2 backend) shell executor for the DeepSeek Harness bash capability seam on Windows: every bash tool call runs in a disposable Linux container with the workspace bind-mounted.
Tavily-backed search provider for the DeepSeek Harness web capability seam (ctx.web): keyless mode, full official search parameters, settings section, and credentials support
Official-basic Codex compaction with an optional account-owned native summarization seam and legacy structured reader; no core patches or duplicate login.
Exa web search provider for the DeepSeek Harness ctx.web seam, with Dynamic Highlights on by default, an /exa command to change highlights, search type and result count at runtime, and an exa_search tool that owns its own result cap.
Fixes malformed tool-call arguments (nested {"arguments":{…}} wrappers, wrapper-key aliases, param-key aliases) at the llm/stream seam — repairs execution, persistence and history replay in one place. 修复模型产出的畸形工具参数。
ChatGPT Web (owned Chromium driving Temporary Chat) adapter for the DeepSeek Harness LLM seam
Six-tier web search provider for the ctx.web seam: free local scraping with a billing-guarded official fallback (allowOfficial, default off), a tier-capable web_search_deep tool a preset cannot shadow, and a settings card.
Layered, approval-gated, auditable cross-session memory for DeepSeek Harness — a capability seam (ctx.memory service + local SQLite provider + memory tool + frozen snapshot injection), not another memory warehouse
Multi-provider LLM configuration for the DeepSeek Harness LLM seam: declare any number of providers, each with its own endpoint, credential and per-model parameters, across the OpenAI Chat, OpenAI Responses, Anthropic Messages and Google Gemini wire formats.
DSH Tavily search and page fetch: a model-visible tavily_search tool backed by a rotating multi-key pool, plus web_fetch through the shell seam.