661,630 packages matching “text-only-model”
@linxin666/dsh-tool-describe-image
v0.2.6 · 3 hours ago
Model-facing describe_image tool for the dsh web GUI: gives a text-only model image understanding by asking a vision-language model at an OpenAI-compatible endpoint to describe one image (local path, http(s) URL, or attachment reference). Hot-pluggable —
No known vulnerabilities
pi-image-fallback
v1.1.1 · 3 days ago
pi extension: let a text-only model see pasted images through a vision sidecar, without ever switching models.
No known vulnerabilities
@bytetrue/pi-vision
v0.2.2 · 2 days ago
Pi extension: let a text-only model read images by asking a vision-capable model from your own models.json.
No known vulnerabilities
picturereader
v3.0.6 · 6 hours ago
Unified image understanding plugin for DeepSeek Harness (DSH). Visual twin adapter for native thumbnails + auto-analysis on any text-only model (incl. pi-ai providers); privacy/smart/strict routing; local tools (scan/OCR×3 engines/crop/palette/compare/bat
No known vulnerabilities
@deepseek-ai/dsh-persona
v0.0.1-rc.1 · 10 days ago
Composition-authored deployment persona section for the DeepSeek Harness
No known vulnerabilities
@deepseek-ai/dsh-client-locale
v0.0.1-rc.1 · 10 days ago
Locale plugin: Host-backed zh/en preference, browser-derived fallback, locale snapshots, and typed namespace dictionaries
No known vulnerabilities
@deepseek-ai/dsh-user-approval
v0.0.1-rc.1 · 10 days ago
User-approval seam (ctx.approval) for the DeepSeek Harness: one-shot permission decisions dispatched to composed answerers over the approval/request waterfall, fail-closed by default
No known vulnerabilities
@deepseek-ai/dsh-command-feedback
v0.0.1-rc.1 · 10 days ago
Log-only session feedback producer and human-facing slash command
No known vulnerabilities
@deepseek-ai/dsh-spill-policy
v0.0.1-rc.1 · 10 days ago
Tool-result spill policy for the DeepSeek Harness — replaces oversized plain-text tool results with a retained preview plus a spill-file path (no service surface)
No known vulnerabilities
@deepseek-ai/dsh-tool-web
v0.0.1-rc.1 · 10 days ago
Model-facing web tools (web_search, web_fetch) over the DeepSeek Harness web capability seam (ctx.web)
No known vulnerabilities
@deepseek-ai/dsh-fs-sandbox
v0.0.1-rc.1 · 10 days ago
Sandbox-enforcing implementation of the DeepSeek Harness filesystem seam: fences write/edit by the per-call sandbox mode (read-only denies mutation, workspace-write contains it to the workspace + temp roots) while reads pass through
No known vulnerabilities
@deepseek-ai/dsh-client-ui-workflow-run
v0.0.1-rc.2 · 9 days ago
Durable workflow-run Conversation Node and nested member disclosure for dsh web
No known vulnerabilities
@deepseek-ai/dsh-session-reference
v0.0.1-rc.1 · 10 days ago
Cross-session snapshot references and durable untrusted model context (ctx.sessionReferences)
No known vulnerabilities
@deepseek-ai/dsh-client-ui-settings-general
v0.0.1-rc.1 · 10 days ago
Settings ownerless-copy and product onboarding plugin: the General section, shell trigger/header chrome content, settings dictionaries, and the versioned welcome notice
No known vulnerabilities
@deepseek-ai/dsh-output-retention
v0.0.1-rc.5 · 8 days ago
Zero-dependency bounded-retention primitive: ItemRetainer/TextRetainer + neutral notice helpers (what did we keep, what did we omit)
No known vulnerabilities
@deepseek-ai/dsh-session-title-llm
v0.0.1-rc.1 · 10 days ago
Shared LLM generation policy for DeepSeek Harness session-title providers
No known vulnerabilities
@deepseek-ai/dsh-headless
v0.0.1-rc.1 · 10 days ago
The dsh one-shot bundle: a direct core Agent/Session runner over dsh-base with no Host, HTTP, or browser layer
No known vulnerabilities
@rails/actiontext
v7.2.302 · 22 days ago
Edit and display rich text in Rails applications
No known vulnerabilities
@ckeditor/ckeditor5-engine
v48.4.0 · 16 days ago
The editing engine of CKEditor 5 – the best browser-based rich text editor.
No known vulnerabilities
@vue/babel-sugar-v-model
v1.4.0 · 3 years ago
Babel syntactic sugar for v-model support in Vue JSX
No known vulnerabilities