chore: sync fork with v0.9.29

.cursor-plugin/plugin.json

@@ -0,0 +1,34 @@
+{
+  "name": "agentmemory",
+  "version": "0.9.29-codex.1",
+  "description": "Persistent memory for Cursor: auto-captures sessions, prompts, and tool use via hooks, recalls with hybrid BM25 + vector + graph search, and exposes 54 memory tools over MCP. Keyless by default, runs entirely on your machine.",
+  "author": {
+    "name": "Rohit Ghumare",
+    "email": "ghumare64@gmail.com"
+  },
+  "homepage": "https://agent-memory.dev",
+  "repository": "https://github.com/rohitg00/agentmemory",
+  "license": "Apache-2.0",
+  "keywords": ["memory", "mcp", "hooks", "recall", "knowledge-graph", "agent-memory"],
+  "logo": "assets/logo.svg",
+  "skills": "plugin/skills/",
+  "hooks": "plugin/cursor/hooks.json",
+  "mcpServers": "plugin/cursor/mcp.json",
+  "variables": {
+    "type": "object",
+    "properties": {
+      "AGENTMEMORY_URL": {
+        "type": "string",
+        "title": "agentmemory server URL",
+        "description": "REST base URL of the running agentmemory server",
+        "default": "http://localhost:3111"
+      },
+      "AGENTMEMORY_SECRET": {
+        "type": "string",
+        "title": "agentmemory secret",
+        "description": "Bearer token, required only when the server sets AGENTMEMORY_SECRET",
+        "default": ""
+      }
+    }
+  }
+}

.env.example

@@ -26,22 +26,24 @@
 # 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_API_KEY=sk-...                          # Activates both the OpenAI-compatible LLM provider (DeepSeek, SiliconFlow, vLLM, LM Studio, Ollama via `/v1`) and OpenAI embeddings. Set OPENAI_API_KEY_FOR_LLM=false to scope it to embeddings only.
 # OPENAI_BASE_URL=https://api.openai.com         # Override for OpenAI-compatible providers
+# OPENAI_MODEL=gpt-5.6-luna                      # Default OpenAI-compatible chat model
+# OPENAI_API_KEY_FOR_LLM=false                   # Skip OpenAI auto-detection for LLM; key stays active for embeddings
 
 # ANTHROPIC_API_KEY=sk-ant-...
-# ANTHROPIC_MODEL=claude-sonnet-4-20250514       # Default Anthropic model
+# ANTHROPIC_MODEL=claude-sonnet-5                # 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)
+# GEMINI_MODEL=gemini-3.7-flash                  # Default Gemini model (current stable Flash)
 
 # OPENROUTER_API_KEY=sk-or-...
-# OPENROUTER_MODEL=anthropic/claude-sonnet-4-20250514
+# OPENROUTER_MODEL=anthropic/claude-sonnet-5
 
 # MINIMAX_API_KEY=...
-# MINIMAX_MODEL=MiniMax-M2.7
+# MINIMAX_MODEL=MiniMax-M3
 
 # MAX_TOKENS=4096                                # Cap LLM completion tokens for compression / summarise calls
 
@@ -111,6 +113,13 @@
 # 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
+
+# Local reasoning models only: set to 1 to ask the model to skip its
+# hidden thinking pass during graph extraction. Extraction runs several
+# times faster; relation quality can drop slightly. Leave unset to let
+# the model think (default).
+# AGENTMEMORY_LLM_NOTHINK=1
+
 # 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).
@@ -119,7 +128,7 @@
 # 6. CLI / runtime knobs
 # -----------------------------------------------------------------------------
 
-# AGENTMEMORY_TOOLS=all                          # core (7 tools, default) | all (51 tools) — surface exposed to MCP clients
+# AGENTMEMORY_TOOLS=core                         # all (54 tools, default) | core (8 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)