Amr Gharbeia
c86d079418
Some checks failed
Deploy (Gitea) / deploy (push) Failing after 2s
File Reorganization: - Extracted core-context → symbolic-awareness (skill) - Extracted heartbeat → symbolic-events (skill) - Relocated 6 utility fragments, renamed 23 files, deleted system-model.lisp - Renamed gateway-* → channel-*, split gateway-messaging → 4 channel-* files - Renamed defskill/defpackage names to match new file prefixes - Deleted gateway-messaging.org/.lisp, removed core-context filter - Documented self-repair criterion, added AGENTS.md core boundary rule Token Economics (v0.5.0, skills not core): - tokenizer.lisp: count-tokens, model-token-ratio, token-cost, provider-token-cost (11 tests) - cost-tracker.lisp: cost-track-call, cost-session-total, cost-by-provider (6 tests) - token-economics.lisp: prompt-prefix-cached, context-assemble-cached, enforce-token-budget with CONTEXT_MAX_TOKENS env var (9 tests) Bug Fixes: - Fixed DeepSeek 400 (removed malformed tools from cascade) - Fixed UNDEFINED-FUNCTION crash (fboundp guards in think()) - Fixed gate-trace duplication (setf replaces list* in cognitive-verify) - Tightened dexador connect-timeout 10s→5s Test suite: 116/116 (100%)
113 lines
4.7 KiB
Plaintext
113 lines
4.7 KiB
Plaintext
# passepartout: Environment Configuration Template
|
|
# Copy this to .env and fill in your values
|
|
|
|
# =============================================================================
|
|
# IDENTITY
|
|
# =============================================================================
|
|
MEMEX_USER="YourName"
|
|
MEMEX_ASSISTANT="AgentName"
|
|
|
|
# =============================================================================
|
|
# LLM PROVIDERS (OpenRouter recommended as primary)
|
|
# =============================================================================
|
|
OPENROUTER_API_KEY="your_openrouter_key_here"
|
|
OPENAI_API_KEY="your_openai_key_here"
|
|
ANTHROPIC_API_KEY="your_anthropic_key_here"
|
|
GROQ_API_KEY="your_groq_api_key_here"
|
|
GEMINI_API_KEY="your_gemini_key_here"
|
|
DEEPSEEK_API_KEY="your_deepseek_key_here"
|
|
NVIDIA_API_KEY="your_nvidia_nim_key_here"
|
|
|
|
# Cascade order (first available provider wins)
|
|
# Default (if unset): openrouter,openai,anthropic,groq,gemini-api,deepseek,nvidia
|
|
PROVIDER_CASCADE=deepseek,openrouter,openai,anthropic,groq,gemini,nvidia
|
|
|
|
# =============================================================================
|
|
# LOCAL LLM (generic OpenAI-compatible endpoint)
|
|
# =============================================================================
|
|
# Set this to the base URL of any local OpenAI-compatible server
|
|
# (llama.cpp, Ollama, vLLM, LM Studio, etc.)
|
|
LOCAL_BASE_URL="localhost:8080"
|
|
|
|
# Ollama host (legacy: falls back to LOCAL_BASE_URL if not set)
|
|
OLLAMA_HOST="localhost:11434"
|
|
|
|
# =============================================================================
|
|
# VECTOR EMBEDDINGS (semantic search)
|
|
# =============================================================================
|
|
EMBEDDING_PROVIDER="hashing" # "hashing" (local, no deps), "local", or "openai"
|
|
EMBEDDING_MODEL="nomic-embed-text" # model name for embeddings
|
|
EMBEDDING_BASE_URL="https://api.openai.com/v1" # for :openai provider
|
|
|
|
# =============================================================================
|
|
# MESSAGING GATEWAYS (optional)
|
|
# =============================================================================
|
|
TELEGRAM_BOT_TOKEN="your_telegram_bot_token_here"
|
|
SIGNAL_ACCOUNT_NUMBER="+1..."
|
|
|
|
# =============================================================================
|
|
# DAEMON CONFIGURATION
|
|
# =============================================================================
|
|
ORG_AGENT_DAEMON_PORT=9105
|
|
DAEMON_HOST="0.0.0.0"
|
|
HEARTBEAT_INTERVAL=60
|
|
DAEMON_SLEEP_INTERVAL=3600
|
|
DEFAULT_ACTUATOR="cli"
|
|
SILENT_ACTUATORS="cli,system-message,emacs"
|
|
|
|
# =============================================================================
|
|
# SECURITY
|
|
# =============================================================================
|
|
PROTOCOL_ENFORCE_HMAC=false
|
|
PROTOCOL_HMAC_SECRET="change-this-to-a-secure-random-string"
|
|
|
|
# Privacy filter tags: comma-separated list of tags that mark content as private.
|
|
# Files/headings tagged with any of these will be filtered from LLM context.
|
|
# Default: @personal
|
|
PRIVACY_FILTER_TAGS="@personal,@health,@finance"
|
|
|
|
# =============================================================================
|
|
# DISPATCHER RULE LEARNING
|
|
# =============================================================================
|
|
# Number of HITL approvals before a pattern becomes a permanent rule
|
|
DISPATCHER_RULE_THRESHOLD=3
|
|
|
|
# Where learned rules are persisted
|
|
RULES_FILE="$HOME/memex/system/rules.org"
|
|
|
|
# =============================================================================
|
|
# BOOTSTRAP
|
|
# =============================================================================
|
|
MANDATORY_SKILLS="security-policy,security-dispatcher"
|
|
|
|
# =============================================================================
|
|
# CONTEXT / MEMORY
|
|
# =============================================================================
|
|
CONTEXT_SEMANTIC_THRESHOLD=0.75
|
|
CONTEXT_LOG_LIMIT=20
|
|
|
|
# =============================================================================
|
|
# MEMEX STRUCTURE
|
|
# =============================================================================
|
|
MEMEX_DIR="$HOME/memex"
|
|
ZETTELKASTEN_DIR="$HOME/memex/notes"
|
|
INBOX_DIR="$HOME/memex/inbox"
|
|
DAILY_DIR="$HOME/memex/daily"
|
|
PROJECTS_DIR="$HOME/memex/projects"
|
|
AREAS_DIR="$HOME/memex/areas"
|
|
RESOURCES_DIR="$HOME/memex/resources"
|
|
ARCHIVES_DIR="$HOME/memex/archives"
|
|
SYSTEM_DIR="$HOME/memex/system"
|
|
LLM_REQUEST_TIMEOUT=30
|
|
|
|
# =============================================================================
|
|
# TOKEN ECONOMICS (v0.5.0)
|
|
# =============================================================================
|
|
# Max tokens for the combined system prompt + context + user prompt.
|
|
# Default: 16384 (half of a 32K context window, leaves room for model response).
|
|
CONTEXT_MAX_TOKENS=16384
|
|
|
|
# Soft daily cost cap in USD. Warning injected into system prompt when
|
|
# approaching budget.
|
|
COST_BUDGET_DAILY=1.00
|