initial commit

README.md

@@ -0,0 +1,50 @@
+# Issue Embedder Action
+
+Sends issue comment text to an embeddings API so issue discussions can be stored in a vector lake. Intended to run from an `issue_comment` workflow and pick up the latest comment text for embedding.
+
+## How it works
+
+- Reads issue comments via the GitHub API.
+- Builds a request payload using the first comment for `embed_text` and the latest comment for `store_text`.
+- POSTs the payload to the configured API URL with optional token auth.
+
+## Inputs
+
+- `api_url` (optional): API endpoint. Default: `http://agents-api.servc-agents:3000`
+- `api_token` (optional): API token for authentication.
+- `route` (optional): API route. Default: `agent-lake`
+- `method` (optional): API method. Default: `embeddings_insert`
+- `debug` (optional): Enable debug logging. Default: `false`
+
+## Example workflow
+
+```yaml
+name: Send Tasks to Agent
+on:
+  issue_comment:
+    types:
+      - created
+      - edited
+
+jobs:
+  agent-embed-issue:
+    if: contains(github.event.comment.body, 'solution:')
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      issues: read
+    steps:
+      - name: Send task to embedding agent
+        uses: https://git.yusufali.ca/actions/embed-issues@main
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          api_token: ${{ secrets.AGENT_TOKEN }}
+          api_url: ${{ secrets.AGENT_API_URL }}
+          debug: false
+```
+
+## Notes
+
+- `GITHUB_TOKEN` is used to read issue comments.
+- `AGENT_API_URL` and `AGENT_TOKEN` are expected to be configured as repository secrets.