Fixes #17048: GitHub actions for retrieving commits

.github/workflows/retrieve-commits.yml

@@ -0,0 +1,39 @@
+name: Retrieve Commits
+
+
+on:
+  workflow_dispatch:
+
+jobs:
+  fetch-commits:
+    runs-on: ubuntu-latest
+    steps:
+
+      - name: Checkout repository
+        uses: actions/checkout@v3
+
+
+      - name: List commits
+        run: |
+          gh api \
+            -H "Accept: application/vnd.github+json" \
+            -H "X-GitHub-Api-Version: 2022-11-28" \
+            /repos/${{ github.repository_owner }}/${{ github.event.repository.name }}/commits?per_page=30 \
+            > commits.json
+
+      - name: Get specific commit
+        run: |
+          gh api \
+            -H "Accept: application/vnd.github+json" \
+            -H "X-GitHub-Api-Version: 2022-11-28" \
+            /repos/${{ github.repository_owner }}/${{ github.event.repository.name }}/commits/${{ github.sha }} \
+            > commit.json
+
+
+      - name: Upload commit data
+        uses: actions/upload-artifact@v3
+        with:
+          name: commit-data
+          path: |
+            commits.json
+            commit.json 

components/openai/actions/chat-with-opeai-responses-api/chat-with-openai-responses-api.mjs

@@ -0,0 +1,196 @@
+import openai from "../../openai.app.mjs";
+import common from "../common/common.mjs";
+import constants from "../../common/constants.mjs";
+import axios from "axios";
+
+export default {
+  ...common,
+  key: "openai-chat-using-responses-api",
+  name: "Chat with OpenAI Responses API",
+  version: "0.0.1",
+  description:
+    "Send a chat via the Responses API, mixing built-in tools and MCP servers.",
+  type: "action",
+  props: {
+    openai,
+    modelId: {
+      type: "string",
+      label: "Model",
+      description: "Model used to generate the response",
+      default: "gpt-4o",
+      options: [
+        "gpt-4o",
+        "gpt-4o-mini",
+      ],
+    },
+    input: {
+      type: "string",
+      label: "Chat Input",
+      description: "Text input to the model used to generate a response",
+    },
+    instructions: {
+      type: "string",
+      label: "Instructions",
+      description:
+        "Inserts a system (or developer) message as the first item in the model's context",
+      optional: true,
+    },
+    previousResponseId: {
+      type: "string",
+      label: "Previous Response ID",
+      description:
+        "The unique ID of the previous response to the model. Use this to create multi-turn conversations",
+      optional: true,
+    },
+    truncation: {
+      type: "string",
+      label: "Truncation",
+      description:
+        "Specifies the truncation mode for the response if it exceeds the context window",
+      default: "auto",
+      options: [
+        "auto",
+        "disabled",
+      ],
+      optional: true,
+    },
+    responseFormat: {
+      type: "string",
+      label: "Response Format",
+      description:
+        "- **text**: Returns unstructured text output.\n- **json_schema**: Enforces a specific structure using a JSON schema.",
+      options: [
+        "text",
+        "json_schema",
+      ],
+      default: "text",
+      optional: true,
+      reloadProps: true,
+    },
+    skipThisStep: {
+      type: "boolean",
+      label: "Skip This Step",
+      description:
+        "Pass in a boolean custom expression to skip execution at runtime",
+      default: false,
+      optional: true,
+    },
+    builtInTools: {
+      type: "string[]",
+      label: "Built-In Tools",
+      description:
+        "Which of OpenAI’s first-party tools to enable (web search, file search, code interpreter).",
+      options: [
+        {
+          label: "Web Search",
+          value: "web_search_preview",
+        },
+        {
+          label: "File Search",
+          value: "file_search",
+        },
+        {
+          label: "Code Interpreter",
+          value: "code_interpreter",
+        },
+      ],
+      default: [],
+    },
+    mcpServers: {
+      type: "string[]",
+      label: "MCP Server URLs",
+      description:
+        "Enter your MCP server base URLs. To set one up, visit https://mcp.pipedream.com/ and click “Create new server.",
+      optional: true,
+    },
+    mcpTools: {
+      type: "string[]",
+      label: "MCP Tools to Enable",
+      description:
+        "Select which tools from your MCP servers to include in the chat.",
+      optional: true,
+      async options({ mcpServers }) {
+        if (!mcpServers?.length) return [];
+        const all = [];
+        for (let url of mcpServers) {
+          url = url.replace(/\/$/, "");
+          const { data } = await axios.get(`${url}/tools`);
+          for (const t of data.tools) {
+            all.push({
+              label: t.name,
+              value: t.id,
+            });
+          }
+        }
+        return all;
+      },
+    },
+  },
+  additionalProps() {
+    const props = {};
+    if (
+      this.responseFormat ===
+      constants.CHAT_RESPONSE_FORMAT.JSON_SCHEMA.value
+    ) {
+      props.jsonSchema = {
+        type: "string",
+        label: "JSON Schema",
+        description:
+          "Define the schema that the model's output must adhere to.",
+      };
+    }
+    return props;
+  },
+  methods: {
+    ...common.methods,
+  },
+  async run({ $ }) {
+    if (this.skipThisStep) {
+      $.export("$summary", "Step execution skipped");
+      return;
+    }
+    const tools = [];
+    for (const id of this.builtInTools) {
+      tools.push({
+        type: id,
+      });
+    }
+    for (const id of this.mcpTools || []) {
+      tools.push({
+        type: id,
+      });
+    }
+    const data = {
+      model: this.modelId,
+      input: this.input,
+      instructions: this.instructions,
+      previous_response_id: this.previousResponseId,
+      truncation: this.truncation,
+      tools,
+    };
+    if (
+      this.responseFormat ===
+      constants.CHAT_RESPONSE_FORMAT.JSON_SCHEMA.value
+    ) {
+      try {
+        data.text = {
+          format: {
+            type: this.responseFormat,
+            ...JSON.parse(this.jsonSchema),
+          },
+        };
+      } catch {
+        throw new Error("Invalid JSON format in the provided JSON Schema");
+      }
+    }
+    const response = await this.openai.responses({
+      $,
+      data,
+    });
+    if (response) {
+      $.export("$summary", `Chat sent (id: ${response.id})`);
+      $.export("chat_responses", response.output);
+    }
+    return response;
+  },
+};