mirror of
https://github.com/tinyhumansai/openhuman.git
synced 2026-07-28 05:12:33 +00:00
YellowSnnowmannandGitHub
1acc916244
* feat: implement user working memory extraction from skill sync payloads - Added functionality to enable the extraction of user working memory from successful skill syncs, allowing for persistent storage of user preferences, goals, constraints, and entities. - Introduced a new configuration option in to toggle working memory extraction. - Created comprehensive documentation on the working memory extraction process, detailing its implementation and privacy considerations. - Updated memory loading logic to include working memory entries in the context provided to agents, enhancing personalization capabilities. - Enhanced logging for memory extraction processes to improve observability and debugging. This feature enhances the user experience by allowing skills to maintain context across interactions, improving the overall effectiveness of the OpenHuman platform. * docs: update architecture documentation to include user working memory integration * refactor: centralize working memory constants and enhance extraction logic - Moved `WORKING_MEMORY_KEY_PREFIX` and `WORKING_MEMORY_LIMIT` constants to `memory_context.rs` for better organization and accessibility. - Updated `MemoryLoader` to utilize these constants, improving code clarity. - Enhanced working memory extraction logic in `MemoryWriteJob` to conditionally persist user working-memory documents based on the job type. - Improved logging for memory extraction processes to provide clearer insights during execution. - Adjusted tests to ensure consistent behavior with the new working memory extraction logic. * chore: update OpenHuman version to 0.51.8 and refactor JSON-RPC test for clarity - Bumped the OpenHuman version in Cargo.lock from 0.51.6 to 0.51.8. - Refactored the JSON-RPC end-to-end test to improve readability by encapsulating the result assertion logic within a block, enhancing clarity in the flow of data handling.
170 lines
7.2 KiB
Bash
170 lines
7.2 KiB
Bash
# Root environment variables — Rust core, Tauri shell, and shared settings.
|
|
# Copy to .env and fill in values as needed.
|
|
# Loaded via: source scripts/load-dotenv.sh
|
|
#
|
|
# Tags: [required] must be set, [optional] has a sensible default or can be blank
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Backend API
|
|
# ---------------------------------------------------------------------------
|
|
# [required] Primary backend URL (read by Rust core and QuickJS skills sandbox)
|
|
BACKEND_URL=https://staging-api.alphahuman.xyz
|
|
# [required] Also read by Vite frontend (VITE_ prefix required for browser exposure)
|
|
VITE_BACKEND_URL=https://staging-api.alphahuman.xyz
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Authentication (for skills OAuth proxy and debug scripts)
|
|
# ---------------------------------------------------------------------------
|
|
# [optional] Session JWT — used by QuickJS skills sandbox for oauth.fetch proxy calls.
|
|
# Also used by debug scripts (scripts/debug-skill.sh, scripts/debug-notion-live.sh).
|
|
# Get from login flow or browser devtools.
|
|
JWT_TOKEN=
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Core process
|
|
# ---------------------------------------------------------------------------
|
|
# [optional] Default: 127.0.0.1 (use 0.0.0.0 for Docker / cloud).
|
|
# Leave unset to keep the default; the Docker image sets 0.0.0.0 automatically.
|
|
# OPENHUMAN_CORE_HOST=
|
|
# [optional] Default: 7788
|
|
OPENHUMAN_CORE_PORT=7788
|
|
# [optional] Default: http://127.0.0.1:7788/rpc
|
|
OPENHUMAN_CORE_RPC_URL=http://127.0.0.1:7788/rpc
|
|
# [optional] Run mode: child (default, spawns sidecar) | inprocess
|
|
OPENHUMAN_CORE_RUN_MODE=child
|
|
# [optional] Override path to openhuman core binary (leave blank for auto-detection)
|
|
OPENHUMAN_CORE_BIN=
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Config overrides (override config.toml values at runtime)
|
|
# ---------------------------------------------------------------------------
|
|
# [required] API key for the LLM provider
|
|
OPENHUMAN_API_KEY=
|
|
# [optional] Default model to use
|
|
OPENHUMAN_MODEL=
|
|
# [optional] Workspace directory (default: ~/.openhuman)
|
|
OPENHUMAN_WORKSPACE=
|
|
# [optional] Default: 0.7
|
|
OPENHUMAN_TEMPERATURE=0.7
|
|
# [optional] Skill + agent tool execution timeout in seconds (default 120, max 3600)
|
|
# OPENHUMAN_TOOL_TIMEOUT_SECS=
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Runtime flags
|
|
# ---------------------------------------------------------------------------
|
|
# [optional] Default: 0
|
|
OPENHUMAN_BROWSER_ALLOW_ALL=0
|
|
# [optional] Default: 0
|
|
OPENHUMAN_LOG_PROMPTS=0
|
|
# [optional] Enable reasoning mode
|
|
OPENHUMAN_REASONING_ENABLED=
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Web search
|
|
# ---------------------------------------------------------------------------
|
|
# [optional] Default: false
|
|
OPENHUMAN_WEB_SEARCH_ENABLED=false
|
|
# [optional] Search provider name
|
|
OPENHUMAN_WEB_SEARCH_PROVIDER=
|
|
# [optional] Required if web search provider is Brave
|
|
OPENHUMAN_BRAVE_API_KEY=
|
|
# [optional] Default: 5
|
|
OPENHUMAN_WEB_SEARCH_MAX_RESULTS=5
|
|
# [optional] Default: 10
|
|
OPENHUMAN_WEB_SEARCH_TIMEOUT_SECS=10
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Storage
|
|
# ---------------------------------------------------------------------------
|
|
# [optional] Storage backend (default: SQLite)
|
|
OPENHUMAN_STORAGE_PROVIDER=
|
|
# [optional] Database connection URL
|
|
OPENHUMAN_STORAGE_DB_URL=
|
|
# [optional] Connection timeout in seconds
|
|
OPENHUMAN_STORAGE_CONNECT_TIMEOUT_SECS=
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Proxy
|
|
# ---------------------------------------------------------------------------
|
|
# [optional] Default: false
|
|
OPENHUMAN_PROXY_ENABLED=false
|
|
# [optional] HTTP proxy URL
|
|
OPENHUMAN_HTTP_PROXY=
|
|
# [optional] HTTPS proxy URL
|
|
OPENHUMAN_HTTPS_PROXY=
|
|
# [optional] Catch-all proxy URL
|
|
OPENHUMAN_ALL_PROXY=
|
|
# [optional] Comma-separated hosts to bypass proxy
|
|
OPENHUMAN_NO_PROXY=
|
|
# [optional] Proxy scope
|
|
OPENHUMAN_PROXY_SCOPE=
|
|
# [optional] Comma-separated services to proxy
|
|
OPENHUMAN_PROXY_SERVICES=
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Local AI model tier
|
|
# ---------------------------------------------------------------------------
|
|
# [optional] Override selected model tier: low, medium, high
|
|
# Applies the corresponding preset at config load time (overrides config.toml).
|
|
OPENHUMAN_LOCAL_AI_TIER=
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Local AI binary overrides
|
|
# ---------------------------------------------------------------------------
|
|
# [optional] Override path to whisper binary
|
|
WHISPER_BIN=
|
|
# [optional] Override path to piper binary
|
|
PIPER_BIN=
|
|
# [optional] Override path to ollama binary
|
|
OLLAMA_BIN=
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Telegram managed login
|
|
# ---------------------------------------------------------------------------
|
|
# [optional] Bot username for managed Telegram DM linking (default: openhuman_bot)
|
|
OPENHUMAN_TELEGRAM_BOT_USERNAME=openhuman_bot
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Skills
|
|
# ---------------------------------------------------------------------------
|
|
# [optional] Override skills registry URL.
|
|
# Supports remote HTTP URLs and local file paths for development:
|
|
# SKILLS_REGISTRY_URL=https://example.com/registry.json (remote)
|
|
# SKILLS_REGISTRY_URL=/path/to/openhuman-skills/skills/registry.json (local)
|
|
# When set to a local path, the registry is read directly from disk on every
|
|
# call (no caching), so changes are picked up immediately.
|
|
SKILLS_REGISTRY_URL=
|
|
# [optional] Local skills source directory for development.
|
|
# Points to the built skills directory (the folder containing per-skill subdirs
|
|
# with manifest.json + index.js). When set, this takes highest priority for
|
|
# skill discovery and install will copy from this directory instead of downloading.
|
|
# Example: SKILLS_LOCAL_DIR=/Users/you/work/openhuman-skills/skills
|
|
SKILLS_LOCAL_DIR=
|
|
# [optional] Enable sync-derived user working memory extraction (default: true).
|
|
# Set to false to disable persisting `working.user.*` docs from skill sync payloads.
|
|
OPENHUMAN_SKILLS_WORKING_MEMORY_ENABLED=true
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Error Reporting (Sentry)
|
|
# ---------------------------------------------------------------------------
|
|
# [optional] Sentry DSN for Rust core error reporting (no PII is sent)
|
|
OPENHUMAN_SENTRY_DSN=
|
|
# [optional] Default: true — set to false to disable anonymized analytics & crash reports
|
|
OPENHUMAN_ANALYTICS_ENABLED=true
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Logging
|
|
# ---------------------------------------------------------------------------
|
|
# [optional] Default: info
|
|
RUST_LOG=info
|
|
# [optional] Default: 0 (set to 1 for full backtraces)
|
|
RUST_BACKTRACE=1
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Testing (do not set in production)
|
|
# ---------------------------------------------------------------------------
|
|
# [optional] Enable mock service mode
|
|
# OPENHUMAN_SERVICE_MOCK=0
|
|
# [optional] Path to mock state file
|
|
# OPENHUMAN_SERVICE_MOCK_STATE_FILE=
|