vault-cortex 0.6.2 → 0.6.4
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +2 -1
- package/dist/env.js +20 -0
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -9,7 +9,8 @@ npx vault-cortex@latest init
|
|
|
9
9
|
|
|
10
10
|
Vault Cortex is a standalone, remote-capable MCP server that gives any AI
|
|
11
11
|
agent hybrid search, task management, structured memory, and read/write
|
|
12
|
-
access to your Obsidian vault —
|
|
12
|
+
access to your Obsidian vault — plus read-only access to its images,
|
|
13
|
+
canvases, and data files — see the
|
|
13
14
|
[full feature overview](https://github.com/aliasunder/vault-cortex#what-you-get).
|
|
14
15
|
The server runs as a Docker container; this CLI scaffolds the config and
|
|
15
16
|
manages the container so you don't have to.
|
package/dist/env.js
CHANGED
|
@@ -18,6 +18,16 @@ const LOCAL_OPTIONAL_BLOCK = `# Optional ─────────────
|
|
|
18
18
|
# Override if you expose the server on a different URL (e.g. via a reverse proxy).
|
|
19
19
|
PUBLIC_URL=http://localhost:8000
|
|
20
20
|
|
|
21
|
+
# Largest asset file vault_read_asset will read, in bytes (default: 52428800 = 50 MiB).
|
|
22
|
+
# Reading a larger file returns an error instead of content.
|
|
23
|
+
MAX_ASSET_BYTES=52428800
|
|
24
|
+
|
|
25
|
+
# Byte budget for images returned by vault_read_asset, in binary bytes before
|
|
26
|
+
# base64 encoding (default: 49152 = 48 KiB, sized for Claude Code's response cap).
|
|
27
|
+
# Images exceeding the budget are downscaled/recompressed to fit. Raise it for clients
|
|
28
|
+
# that accept larger tool responses.
|
|
29
|
+
MAX_IMAGE_OUTPUT_BYTES=49152
|
|
30
|
+
|
|
21
31
|
# Your IANA timezone — affects daily note resolution and memory timestamps.
|
|
22
32
|
# TZ=America/New_York
|
|
23
33
|
|
|
@@ -110,6 +120,16 @@ RERANK_MODE=blended
|
|
|
110
120
|
# the Docker Desktop/WSL2 bridge.
|
|
111
121
|
WINDOWS_MODE=false
|
|
112
122
|
|
|
123
|
+
# Largest asset file vault_read_asset will read, in bytes (default: 52428800 = 50 MiB).
|
|
124
|
+
# Reading a larger file returns an error instead of content.
|
|
125
|
+
MAX_ASSET_BYTES=52428800
|
|
126
|
+
|
|
127
|
+
# Byte budget for images returned by vault_read_asset, in binary bytes before
|
|
128
|
+
# base64 encoding (default: 49152 = 48 KiB, sized for Claude Code's response cap).
|
|
129
|
+
# Images exceeding the budget are downscaled/recompressed to fit. Raise it for clients
|
|
130
|
+
# that accept larger tool responses.
|
|
131
|
+
MAX_IMAGE_OUTPUT_BYTES=49152
|
|
132
|
+
|
|
113
133
|
# Enable or disable the memory layer (default: true).
|
|
114
134
|
# Set to false to hide memory tools and skip About Me/ creation.
|
|
115
135
|
MEMORY_ENABLED=true
|