# =============================================================================
# agentmemory configuration
# =============================================================================
#
# Copy this file to `~/.agentmemory/.env` (or to your project root if you
# prefer scoped config) and uncomment the lines you want to override.
#
# Every line is OFF by default — `agentmemory` runs out of the box with no
# LLM key, no embedding key, and no API auth. Set keys here only when you
# want to enable the corresponding feature.
#
# Run `npx @agentmemory/agentmemory init` to copy this file into place
# automatically. Run `npx @agentmemory/agentmemory doctor` to verify that
# the daemon reads the env you expect.
#
# Defaults shown in comments. Listed in priority order — the first key
# present wins on the LLM detection path (see src/config.ts::detectProvider).

# -----------------------------------------------------------------------------
# 1. LLM provider — pick ONE
# -----------------------------------------------------------------------------
#
# Without a provider key, agentmemory runs in noop mode: observations are
# indexed via zero-LLM synthetic compression, hybrid search still works,
# but LLM-backed summarisation / reflection / consolidation are disabled.
# The detection order is OPENAI_API_KEY → MINIMAX_API_KEY → ANTHROPIC_API_KEY
# → GEMINI_API_KEY → OPENROUTER_API_KEY → noop.

# OPENAI_API_KEY=sk-...                          # Used for OpenAI-compatible embeddings today. PR #307 will extend this to chat completions (DeepSeek, SiliconFlow, vLLM, LM Studio, Ollama via `/v1`).
# OPENAI_BASE_URL=https://api.openai.com         # Override for OpenAI-compatible providers

# ANTHROPIC_API_KEY=sk-ant-...
# ANTHROPIC_MODEL=claude-sonnet-4-20250514       # Default Anthropic model
# ANTHROPIC_BASE_URL=https://api.anthropic.com   # Override for Anthropic-compatible proxies / Azure AI Foundry

# GEMINI_API_KEY=...                             # Either env name works; GEMINI_API_KEY takes precedence
# GOOGLE_API_KEY=...                             # Alias for GEMINI_API_KEY when set alone (emits a one-time stderr hint)
# GEMINI_MODEL=gemini-2.5-flash                  # Default Gemini model (auto-detected GA model)

# OPENROUTER_API_KEY=sk-or-...
# OPENROUTER_MODEL=anthropic/claude-sonnet-4-20250514

# MINIMAX_API_KEY=...
# MINIMAX_MODEL=MiniMax-M2.7

# MAX_TOKENS=4096                                # Cap LLM completion tokens for compression / summarise calls

# Outbound LLM / embedding timeout — shared across every raw-fetch provider
# (Gemini, OpenRouter, MiniMax, OpenAI LLM, and OpenAI/Cohere/Voyage/OpenRouter
# embedding). The OpenAI LLM path also honours the OpenAI-scoped
# OPENAI_TIMEOUT_MS alias for back-compat with v0.9.17 (precedence).
# AGENTMEMORY_LLM_TIMEOUT_MS=60000                # Default: 60 000 ms (60 s)

# Opt-in Claude-subscription fallback (spawns @anthropic-ai/claude-agent-sdk
# child sessions). Off by default — the agent-sdk fallback can trigger
# Stop-hook recursion (#149 follow-up) when invoked from inside Claude Code.
# AGENTMEMORY_ALLOW_AGENT_SDK=true

# FALLBACK_PROVIDERS=anthropic,gemini            # Comma-separated chain tried after the primary provider returns an error (e.g. rate limit)

# -----------------------------------------------------------------------------
# 2. Embedding provider — auto-detected, override via EMBEDDING_PROVIDER
# -----------------------------------------------------------------------------
#
# Without an embedding key, agentmemory runs in BM25-only mode for hybrid
# search. Detection order: EMBEDDING_PROVIDER override → GEMINI_API_KEY →
# OPENAI_API_KEY → VOYAGE_API_KEY → COHERE_API_KEY → OPENROUTER_API_KEY →
# local (Xenova/all-MiniLM-L6-v2, 384-dim).

# EMBEDDING_PROVIDER=local                       # local | openai | voyage | cohere | gemini | openrouter

# VOYAGE_API_KEY=pa-...                          # Optimised for code embeddings

# COHERE_API_KEY=...                             # General-purpose embeddings

# Reuses OPENAI_API_KEY / OPENAI_BASE_URL above when EMBEDDING_PROVIDER=openai.
# OPENAI_EMBEDDING_MODEL=text-embedding-3-small  # Embedding model when EMBEDDING_PROVIDER=openai
# OPENAI_EMBEDDING_DIMENSIONS=1536               # Required when the model is not in the known-models table

# OPENROUTER_EMBEDDING_MODEL=openai/text-embedding-3-small  # When EMBEDDING_PROVIDER=openrouter

# -----------------------------------------------------------------------------
# 3. Auth & security
# -----------------------------------------------------------------------------
#
# Bearer-token auth for the REST API + viewer + all integration plugins.
# Without a secret, REST endpoints are open on loopback. Set this when
# you expose the daemon beyond loopback or run behind a reverse proxy.

# AGENTMEMORY_SECRET=your-secret-here

# -----------------------------------------------------------------------------
# 4. Search tuning
# -----------------------------------------------------------------------------

# BM25_WEIGHT=0.4                                # Hybrid search weight for BM25 leg
# VECTOR_WEIGHT=0.6                              # Hybrid search weight for vector leg
# AGENTMEMORY_GRAPH_WEIGHT=0.2                   # Graph traversal bonus on smart-search ranking
# TOKEN_BUDGET=2000                              # Max tokens injected via mem::context per session
# MAX_OBS_PER_SESSION=500                        # Per-session observation cap before consolidation kicks in
# SUMMARIZE_CHUNK_SIZE=400                       # When mem::summarize sees a session larger than this, it chunks observations and map-reduces (chunk-summarize → reduce-merge) to stay within the LLM's context window. Default 400 ≈ 50k tokens per chunk at ~110 tok/obs. Native sessions are capped by MAX_OBS_PER_SESSION; chunking primarily matters for bulk-imported jsonl sessions, which bypass that cap.
# SUMMARIZE_CHUNK_CONCURRENCY=6                  # Parallel chunk LLM calls during chunked summarize. Default 6 fits ~100-chunk sessions under iii's 180s function-invocation timeout at typical ~8s/call. High-throughput providers (Novita, DeepInfra, DeepSeek) commonly allow 100+ concurrent — bump this for very large imported sessions.

# -----------------------------------------------------------------------------
# 5. Behaviour flags
# -----------------------------------------------------------------------------

# AGENTMEMORY_AUTO_COMPRESS=true                 # Run LLM compression on every observation batch (requires a provider key). Default off — synthetic compression handles most cases.
# AGENTMEMORY_INJECT_CONTEXT=true                # Inject recalled memories back into agent prompts (#143). Default off — hooks capture observations but do not modify conversation.
# CONSOLIDATION_ENABLED=true                     # Run the 4-tier consolidation pipeline (memories → semantic → procedural). Default off — opt in once you've measured the LLM cost.
# CONSOLIDATION_DECAY_DAYS=30                    # Age (days) after which non-reinforced memories decay during consolidation
# GRAPH_EXTRACTION_ENABLED=true                  # Extract concept-graph edges on remember; powers the graph-traversal recall path
# GRAPH_EXTRACTION_BATCH_SIZE=8                  # Memories per graph-extraction batch
# AGENTMEMORY_REFLECT=true                       # Periodically auto-synthesize lessons from memories
# AGENTMEMORY_DROP_STALE_INDEX=true              # Drop on-disk BM25 / vector index on startup if dim guard fires (#248). Recovery toggle for stuck-state debugging.
# AGENTMEMORY_IMAGE_EMBEDDINGS=true              # Enable image embeddings when an image provider is present (experimental).

# -----------------------------------------------------------------------------
# 6. CLI / runtime knobs
# -----------------------------------------------------------------------------

# AGENTMEMORY_TOOLS=all                          # core (7 tools, default) | all (51 tools) — surface exposed to MCP clients
# AGENTMEMORY_SLOTS=memory                       # Comma-separated plugin slot names the CLI should claim
# AGENTMEMORY_DEBUG=1                            # Trace MCP shim probe + standalone fallback decisions to stderr
# AGENTMEMORY_FORCE_PROXY=1                      # Skip the MCP shim livez probe and trust AGENTMEMORY_URL (for sandboxed MCP clients that can't reach localhost)
# AGENTMEMORY_PROBE_TIMEOUT_MS=2000              # MCP shim livez probe timeout
# AGENTMEMORY_URL=http://localhost:3111          # REST base URL — honored by status, doctor, MCP shim
# AGENTMEMORY_VIEWER_URL=http://localhost:3113   # Override the viewer URL printed by `agentmemory status`
# AGENTMEMORY_EXPORT_ROOT=~/agentmemory-backup   # Default destination for `agentmemory export`

# STANDALONE_MCP=1                               # MCP shim only — bypass the worker and run @agentmemory/mcp in-process
# STANDALONE_PERSIST_PATH=~/.agentmemory/local.db  # Path used by the standalone MCP shim's local fallback store

# Snapshot exporter — periodic snapshots of state_store + stream_store.
# SNAPSHOT_ENABLED=true
# SNAPSHOT_DIR=~/.agentmemory/snapshots
# SNAPSHOT_INTERVAL=3600                         # Seconds between snapshots

# Team sharing — when set, memories are scoped to (TEAM_ID, USER_ID) tuples.
# TEAM_MODE=shared
# TEAM_ID=acme
# USER_ID=rohit

# -----------------------------------------------------------------------------
# 7. Ports
# -----------------------------------------------------------------------------

# III_REST_PORT=3111                             # REST API port (also affects viewer at +2)
# III_STREAMS_PORT=3112                          # Streams API port
# III_ENGINE_URL=ws://localhost:49134            # iii-engine WebSocket URL (used by the worker)

# -----------------------------------------------------------------------------
# 8. iii engine pin
# -----------------------------------------------------------------------------
#
# agentmemory currently pins iii-engine to v0.11.2 — v0.11.6 introduces a
# new sandbox-everything-via-`iii worker add` model that agentmemory
# hasn't been refactored for yet. Override with AGENTMEMORY_III_VERSION
# only after migrating to the sandbox model manually.

# AGENTMEMORY_III_VERSION=0.11.2

# -----------------------------------------------------------------------------
# 9. Claude Code bridge (opt-in)
# -----------------------------------------------------------------------------

# CLAUDE_MEMORY_BRIDGE=true                      # Mirror compressed memories into Claude Code's CLAUDE.md
# CLAUDE_PROJECT_PATH=/path/to/your/project      # Required when CLAUDE_MEMORY_BRIDGE=true
# CLAUDE_MEMORY_LINE_BUDGET=200                  # Lines of memory CLAUDE.md should hold

# -----------------------------------------------------------------------------
# 10. Obsidian export (opt-in)
# -----------------------------------------------------------------------------

# OBSIDIAN_AUTO_EXPORT=true                      # Auto-export memories to an Obsidian vault on every consolidation