Skip to content

[ACTION] OpenAI Responses API #17475

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Conversation

jcortes
Copy link
Collaborator

@jcortes jcortes commented Jul 4, 2025

WHY

Resolves #17031 authored by @jeevikasirwani

Summary by CodeRabbit

  • New Features

    • Introduced a new action to interact with the OpenAI Responses API, supporting advanced chat capabilities with configurable tools and structured output options.
    • Enhanced parsing utilities to support deep, safe parsing of nested JSON strings within arrays or objects.
  • Bug Fixes

    • Improved cycle detection and depth limiting in JSON parsing to prevent errors with complex or cyclic data structures.
  • Chores

    • Updated multiple actions with new version numbers.
    • Updated dependencies, adding a new SDK and removing an outdated library.

@jcortes jcortes self-assigned this Jul 4, 2025
Copy link

vercel bot commented Jul 4, 2025

The latest updates on your projects. Learn more about Vercel for Git ↗︎

3 Skipped Deployments
Name Status Preview Comments Updated (UTC)
docs-v2 ⬜️ Ignored (Inspect) Visit Preview Jul 7, 2025 10:25pm
pipedream-docs ⬜️ Ignored (Inspect) Jul 7, 2025 10:25pm
pipedream-docs-redirect-do-not-edit ⬜️ Ignored (Inspect) Jul 7, 2025 10:25pm

Copy link
Contributor

coderabbitai bot commented Jul 4, 2025

Walkthrough

A new action, "Chat With Responses API," was added to support OpenAI's Responses API with multiple tool integration, including MCP servers. Supporting helpers for deep JSON parsing were implemented. Several existing actions had their version numbers incremented. The OpenAI package updated its dependencies and version.

Changes

File(s) Change Summary
components/openai/actions/chat-with-responses-api/chat-with-responses-api.mjs New action: Implements "Chat With Responses API" with multi-tool support and JSON schema validation.
components/openai/common/helpers.mjs Added deep/cycle-safe JSON parsing utilities: parseJson (internal) and parseArray (exported).
components/openai/package.json Bumped version to 1.1.0; added @pipedream/sdk, removed axios.
components/openai/actions/chat/chat.mjs
components/openai/actions/chat-using-file-search/chat-using-file-search.mjs
components/openai/actions/chat-using-functions/chat-using-functions.mjs
components/openai/actions/chat-using-web-search/chat-using-web-search.mjs
components/openai/actions/classify-items-into-categories/classify-items-into-categories.mjs
components/openai/actions/create-embeddings/create-embeddings.mjs
components/openai/actions/send-prompt/send-prompt.mjs
components/openai/actions/summarize/summarize.mjs
components/openai/actions/translate-text/translate-text.mjs
Incremented version numbers only; no functional changes.

Sequence Diagram(s)

sequenceDiagram
    participant User
    participant Action ("Chat With Responses API")
    participant OpenAI API
    participant MCP Server (optional)

    User->>Action: Provide input, select tools, set options
    Action->>MCP Server: (Optional) Fetch available tools (async)
    Action->>Action: Validate JSON schema if needed
    Action->>OpenAI API: Send chat request with tools, options, and input
    OpenAI API-->>Action: Return response
    Action-->>User: Export summary and chat output, return full response
Loading

Assessment against linked issues

Objective Addressed Explanation
New action for OpenAI Responses API allowing MCP server as a tool (#17031)
Support for multiple tools (web search, code interpreter, multiple MCP servers, etc) (#17031)
JSON schema enforcement and validation for structured output (#17031)
Async request to pull available tools from MCP server (#17031)

Poem

A rabbit hopped with code delight,
New tools for chat now come in sight!
JSON parsed both deep and wide,
MCP servers join the ride.
Version numbers gently climb,
OpenAI’s response—sublime!
🐇✨

Warning

There were issues while running some tools. Please review the errors and either fix the tool's configuration or disable the tool if it's a critical failure.

🔧 ESLint

If the error stems from missing dependencies, add them to the package.json file. For unrecoverable errors (e.g., due to private dependencies), disable the tool in the CodeRabbit configuration.

components/openai/actions/chat-using-file-search/chat-using-file-search.mjs

Oops! Something went wrong! :(

ESLint: 8.57.1

Error [ERR_MODULE_NOT_FOUND]: Cannot find package 'jsonc-eslint-parser' imported from /eslint.config.mjs
at Object.getPackageJSONURL (node:internal/modules/package_json_reader:255:9)
at packageResolve (node:internal/modules/esm/resolve:767:81)
at moduleResolve (node:internal/modules/esm/resolve:853:18)
at defaultResolve (node:internal/modules/esm/resolve:983:11)
at ModuleLoader.defaultResolve (node:internal/modules/esm/loader:801:12)
at #cachedDefaultResolve (node:internal/modules/esm/loader:725:25)
at ModuleLoader.resolve (node:internal/modules/esm/loader:708:38)
at ModuleLoader.getModuleJobForImport (node:internal/modules/esm/loader:309:38)
at #link (node:internal/modules/esm/module_job:202:49)

components/openai/actions/chat-using-functions/chat-using-functions.mjs

Oops! Something went wrong! :(

ESLint: 8.57.1

Error [ERR_MODULE_NOT_FOUND]: Cannot find package 'jsonc-eslint-parser' imported from /eslint.config.mjs
at Object.getPackageJSONURL (node:internal/modules/package_json_reader:255:9)
at packageResolve (node:internal/modules/esm/resolve:767:81)
at moduleResolve (node:internal/modules/esm/resolve:853:18)
at defaultResolve (node:internal/modules/esm/resolve:983:11)
at ModuleLoader.defaultResolve (node:internal/modules/esm/loader:801:12)
at #cachedDefaultResolve (node:internal/modules/esm/loader:725:25)
at ModuleLoader.resolve (node:internal/modules/esm/loader:708:38)
at ModuleLoader.getModuleJobForImport (node:internal/modules/esm/loader:309:38)
at #link (node:internal/modules/esm/module_job:202:49)

components/openai/actions/chat-using-web-search/chat-using-web-search.mjs

Oops! Something went wrong! :(

ESLint: 8.57.1

Error [ERR_MODULE_NOT_FOUND]: Cannot find package 'jsonc-eslint-parser' imported from /eslint.config.mjs
at Object.getPackageJSONURL (node:internal/modules/package_json_reader:255:9)
at packageResolve (node:internal/modules/esm/resolve:767:81)
at moduleResolve (node:internal/modules/esm/resolve:853:18)
at defaultResolve (node:internal/modules/esm/resolve:983:11)
at ModuleLoader.defaultResolve (node:internal/modules/esm/loader:801:12)
at #cachedDefaultResolve (node:internal/modules/esm/loader:725:25)
at ModuleLoader.resolve (node:internal/modules/esm/loader:708:38)
at ModuleLoader.getModuleJobForImport (node:internal/modules/esm/loader:309:38)
at #link (node:internal/modules/esm/module_job:202:49)

  • 8 others
✨ Finishing Touches
  • 📝 Generate Docstrings

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share
🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>, please review it.
    • Explain this complex logic.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    • @coderabbitai explain this code block.
    • @coderabbitai modularize this function.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @coderabbitai read src/utils.ts and explain its main purpose.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
    • @coderabbitai help me debug CodeRabbit configuration file.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai generate docstrings to generate docstrings for this PR.
  • @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Other keywords and placeholders

  • Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

  • You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
  • Please see the configuration documentation for more information.
  • If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

Copy link
Contributor

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 4

📜 Review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 6e90be3 and 5f77461.

⛔ Files ignored due to path filters (1)
  • pnpm-lock.yaml is excluded by !**/pnpm-lock.yaml
📒 Files selected for processing (1)
  • components/openai/actions/chat-with-opeai-responses-api/chat-with-openai-responses-api.mjs (1 hunks)
🧰 Additional context used
🧠 Learnings (1)
components/openai/actions/chat-with-opeai-responses-api/chat-with-openai-responses-api.mjs (3)
Learnt from: GTFalcao
PR: PipedreamHQ/pipedream#12731
File: components/hackerone/actions/get-members/get-members.mjs:3-28
Timestamp: 2024-07-04T18:11:59.822Z
Learning: When exporting a summary message in the `run` method of an action, ensure the message is correctly formatted. For example, in the `hackerone-get-members` action, the correct format is `Successfully retrieved ${response.data.length} members`.
Learnt from: GTFalcao
PR: PipedreamHQ/pipedream#12731
File: components/hackerone/actions/get-members/get-members.mjs:3-28
Timestamp: 2024-10-08T15:33:38.240Z
Learning: When exporting a summary message in the `run` method of an action, ensure the message is correctly formatted. For example, in the `hackerone-get-members` action, the correct format is `Successfully retrieved ${response.data.length} members`.
Learnt from: GTFalcao
PR: PipedreamHQ/pipedream#16954
File: components/salesloft/salesloft.app.mjs:14-23
Timestamp: 2025-06-04T17:52:05.780Z
Learning: In the Salesloft API integration (components/salesloft/salesloft.app.mjs), the _makeRequest method returns response.data which directly contains arrays for list endpoints like listPeople, listCadences, listUsers, and listAccounts. The propDefinitions correctly call .map() directly on these responses without needing to destructure a nested data property.
⏰ Context from checks skipped due to timeout of 90000ms (4)
  • GitHub Check: pnpm publish
  • GitHub Check: Lint Code Base
  • GitHub Check: Publish TypeScript components
  • GitHub Check: Verify TypeScript components

@jcortes jcortes force-pushed the pr/jeevikasirwani/17052 branch 2 times, most recently from cfc66bc to b2ff889 Compare July 7, 2025 22:21
@jcortes jcortes force-pushed the pr/jeevikasirwani/17052 branch from b2ff889 to 478ab4e Compare July 7, 2025 22:25
Copy link
Contributor

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 2

📜 Review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between cfc66bc and 478ab4e.

⛔ Files ignored due to path filters (1)
  • pnpm-lock.yaml is excluded by !**/pnpm-lock.yaml
📒 Files selected for processing (12)
  • components/openai/actions/chat-using-file-search/chat-using-file-search.mjs (1 hunks)
  • components/openai/actions/chat-using-functions/chat-using-functions.mjs (1 hunks)
  • components/openai/actions/chat-using-web-search/chat-using-web-search.mjs (1 hunks)
  • components/openai/actions/chat-with-responses-api/chat-with-responses-api.mjs (1 hunks)
  • components/openai/actions/chat/chat.mjs (1 hunks)
  • components/openai/actions/classify-items-into-categories/classify-items-into-categories.mjs (1 hunks)
  • components/openai/actions/create-embeddings/create-embeddings.mjs (1 hunks)
  • components/openai/actions/send-prompt/send-prompt.mjs (1 hunks)
  • components/openai/actions/summarize/summarize.mjs (1 hunks)
  • components/openai/actions/translate-text/translate-text.mjs (1 hunks)
  • components/openai/common/helpers.mjs (1 hunks)
  • components/openai/package.json (2 hunks)
✅ Files skipped from review due to trivial changes (9)
  • components/openai/actions/create-embeddings/create-embeddings.mjs
  • components/openai/actions/translate-text/translate-text.mjs
  • components/openai/actions/summarize/summarize.mjs
  • components/openai/actions/chat-using-functions/chat-using-functions.mjs
  • components/openai/actions/chat/chat.mjs
  • components/openai/actions/chat-using-web-search/chat-using-web-search.mjs
  • components/openai/actions/chat-using-file-search/chat-using-file-search.mjs
  • components/openai/actions/send-prompt/send-prompt.mjs
  • components/openai/actions/classify-items-into-categories/classify-items-into-categories.mjs
🚧 Files skipped from review as they are similar to previous changes (2)
  • components/openai/package.json
  • components/openai/common/helpers.mjs
🧰 Additional context used
🧠 Learnings (1)
components/openai/actions/chat-with-responses-api/chat-with-responses-api.mjs (2)
Learnt from: GTFalcao
PR: PipedreamHQ/pipedream#12731
File: components/hackerone/actions/get-members/get-members.mjs:3-28
Timestamp: 2024-07-04T18:11:59.822Z
Learning: When exporting a summary message in the `run` method of an action, ensure the message is correctly formatted. For example, in the `hackerone-get-members` action, the correct format is `Successfully retrieved ${response.data.length} members`.
Learnt from: GTFalcao
PR: PipedreamHQ/pipedream#12731
File: components/hackerone/actions/get-members/get-members.mjs:3-28
Timestamp: 2024-10-08T15:33:38.240Z
Learning: When exporting a summary message in the `run` method of an action, ensure the message is correctly formatted. For example, in the `hackerone-get-members` action, the correct format is `Successfully retrieved ${response.data.length} members`.
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (3)
  • GitHub Check: Publish TypeScript components
  • GitHub Check: Lint Code Base
  • GitHub Check: Verify TypeScript components

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

[ACTION] OpenAI Responses API
2 participants