node-red-contrib-ollama 0.6.1 → 0.6.2

package/.github/workflows/deploy-site.yml

@@ -0,0 +1,38 @@
+name: Deploy site
+
+on:
+  push:
+    branches: [main]
+    paths:
+      - "site/**"
+      - ".github/workflows/deploy-site.yml"
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  pages: write
+  id-token: write
+
+concurrency:
+  group: pages
+  cancel-in-progress: false
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: withastro/action@v3
+        with:
+          path: site
+          node-version: 22
+  deploy:
+    needs: build
+    runs-on: ubuntu-latest
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    steps:
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4

package/CHANGELOG.md

@@ -4,6 +4,12 @@ All notable changes to this project will be documented in this file.
 
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
+## [0.6.2] - 2026-09-15
+
+### Fixed
+
+- Added `ollama-ps` and `ollama-abort` to the bundled example flow (`examples/Example.json`) — they were the only two action nodes not demonstrated in any example, which the Node-RED flow library scorecard flags as missing example coverage.
+
 ## [0.6.1] - 2026-09-13
 
 ### Fixed

package/CLAUDE.md

@@ -0,0 +1,18 @@
+# Code notes for this repo
+
+Node-RED plugin wrapping the `ollama` JS client library as configurable nodes. Each node type is declared in `package.json` (`node-red.nodes`) as an `.html` + `.js` pair under `nodes/`.
+
+## Node categories
+
+- **Config nodes** (no direct output, referenced by action nodes via `config.server`/etc.): `ollama-config-server` (host/port, or Ollama Cloud + API key credential), `ollama-config-options`, `ollama-config-format`, `ollama-config-tools`.
+- **Action nodes** (12): `ollama-chat`, `ollama-generate`, `ollama-embed`, `ollama-list`, `ollama-show`, `ollama-ps`, `ollama-pull`, `ollama-push`, `ollama-create`, `ollama-copy`, `ollama-delete`, `ollama-abort` — each wraps one `ollama.js` client method.
+
+## Shared patterns (present in every action node — keep them in sync when touching one)
+
+- **Host resolution**: with a local server configured, `msg.payload.host` may override the configured host. With Ollama Cloud (`server.useCloud`), the configured host is always used and `msg.payload.host` is **never** allowed to override it — an override would let the configured API key leak to an arbitrary host. See `ollama-chat.js` for the canonical implementation.
+- **Param resolution**: `model` and other per-call params read from `msg.payload.<field>` first, falling back to the node's own config value — respecting the field's configured type (`str` literal vs `msg` property lookup).
+- **Streaming** (`stream: true`): the node consumes the response with `for await` and emits one cloned `msg` per chunk on `payload` — never pass a raw `AbortableAsyncIterator` out to `msg.payload`.
+
+## Style
+
+- 4-space indentation, a space inside parens in declarations/conditions (`function( RED )`, `if( config.model )`) — match this in new code, even though it's an unusual style choice.

package/examples/Example.json

@@ -403,5 +403,81 @@
                 "c74ec4ac9b76d0f4"
             ]
         ]
+    },
+    {
+        "id": "f1a2b3c4d5e6f708",
+        "type": "ollama-ps",
+        "z": "3bccaf6e46d3dbf5",
+        "name": "Running models",
+        "x": 450,
+        "y": 700,
+        "wires": [
+            [
+                "03ee0eeb510c4079"
+            ]
+        ]
+    },
+    {
+        "id": "a1b2c3d4e5f60718",
+        "type": "inject",
+        "z": "3bccaf6e46d3dbf5",
+        "name": "Trigger",
+        "props": [
+            {
+                "p": "payload"
+            }
+        ],
+        "repeat": "",
+        "crontab": "",
+        "once": false,
+        "onceDelay": 0.1,
+        "topic": "",
+        "payload": "",
+        "payloadType": "date",
+        "x": 270,
+        "y": 700,
+        "wires": [
+            [
+                "f1a2b3c4d5e6f708"
+            ]
+        ]
+    },
+    {
+        "id": "b2c3d4e5f6071829",
+        "type": "ollama-abort",
+        "z": "3bccaf6e46d3dbf5",
+        "name": "Abort",
+        "x": 430,
+        "y": 760,
+        "wires": [
+            [
+                "03ee0eeb510c4079"
+            ]
+        ]
+    },
+    {
+        "id": "c3d4e5f607182930",
+        "type": "inject",
+        "z": "3bccaf6e46d3dbf5",
+        "name": "Trigger",
+        "props": [
+            {
+                "p": "payload"
+            }
+        ],
+        "repeat": "",
+        "crontab": "",
+        "once": false,
+        "onceDelay": 0.1,
+        "topic": "",
+        "payload": "",
+        "payloadType": "date",
+        "x": 270,
+        "y": 760,
+        "wires": [
+            [
+                "b2c3d4e5f6071829"
+            ]
+        ]
     }
 ]

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "node-red-contrib-ollama",
-  "version": "0.6.1",
+  "version": "0.6.2",
   "description": "Add AI functionality to your flows! This module includes a set of nodes that enable easy communication with Ollama, enriching your projects with intelligent solutions.",
   "keywords": [
     "ai",