mirror of https://github.com/lobehub/lobe-chat.git synced 2026-06-14 03:30:19 +00:00

Files

T

History

Rylan Cai 99023811d8 📝 fix: clarify local system shell result wording (#15745 )

* 🔥 remove local system listFiles exposure

* 📝 clarify local system shell result wording

* 📝 refine local system shell manifest copy

* 📝 simplify local system shell prompt semantics

* 🐛 fix command wait-window result wording

* 📝 limit transient device retry guidance

* ✨ show command output duration

* 🏷️ narrow command duration result type

* 🐛 propagate operation id for device tool calls

* 🐛 update project skill discovery hint

* 📝 clarify project skill file access

* 📝 align project skill discovery comment

2026-06-13 16:34:10 +08:00

src

📝 fix: clarify local system shell result wording (#15745 )

2026-06-13 16:34:10 +08:00

.gitignore

♻️ refactor: remove promptfoo configs and dependencies (#13665 )

2026-04-08 17:50:55 +08:00

package.json

🐛 fix(desktop): relocate visual-ref helpers to @lobechat/const to fix renderer crash (#15369 )

2026-06-01 11:46:03 +08:00

README.md

♻️ refactor: remove promptfoo configs and dependencies (#13665 )

2026-04-08 17:50:55 +08:00

vitest.config.mts

✅ test: add unit tests for @lobechat/prompts (#8967 )

2025-08-28 20:44:28 +08:00

README.md

@lobechat/prompts

This package contains prompt chains and templates for the LobeHub application.

Features

Prompt Chains: Reusable prompt templates for various AI tasks
Multi-language Support: Prompts for multiple languages
Type Safety: Full TypeScript support with proper type definitions

Available Prompt Chains

chainSummaryTitle - Generate conversation titles
chainLangDetect - Detect language of input text
chainTranslate - Translate content between languages
chainPickEmoji - Select appropriate emojis for content
chainAnswerWithContext - Answer questions using knowledge base context
chainAbstractChunkText - Summarize text chunks

Testing

Prompt evaluation tests are located in devtools/agent-evals/scenarios/prompt-chain/ (cloud repo) and run via the agent-evals CLI.

# Run from cloud repo root
bun run agent-evals run prompt-chain/translate
bun run agent-evals run prompt-chain/emoji-picker
bun run agent-evals list # See all available scenarios

Development

# Run unit tests
pnpm test

Architecture

src/
├── chains/           # Prompt chain implementations
├── prompts/          # Prompt templates and utilities
└── index.ts          # Main exports