session_init
Initialize an AI session by setting the project root and loading the memory index. Call this first to establish project context and check the vector-index status.
Instructions
Single-call session bootstrap. Call this FIRST in every AI session.
Performs:
1. Sets project root (if `project_path` is provided).
2. Warns if the chosen root is the MCP server's own directory.
3. Reads `.ai/memory.md` (only the index/headings — full text on demand).
4. Refreshes the lightweight L0 manifest.
5. Reports vector-index status (without loading it).
6. Starts the self-healing maintenance daemon.
The heavy vector store / embedding model is NEVER loaded here — it is
lazily loaded only when a semantic query needs it. This keeps
`session_init` well under the MCP 30s tool timeout even on multi-GB
repositories.
Args:
project_path: Absolute path to the target project. Leave empty to use
auto-detection (CWD + project markers).
Returns:
Consolidated Markdown brief summarising project root, memory, and index state.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "session_init"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| project_path | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |