Highlights of the week
The configuration data from this week reveals significant infrastructure testing, most notably a potential shift in the payment processing backend away from Stripe toward an internal system. The hidden plugins list has been updated with highly suggestive identifiers pointing toward advanced agentic capabilities, including computer use and deep research. Additionally, the recently updated GPT-6 Luna model is now explicitly referenced as the underlying engine for specific classification tasks within the platform.
Focus by theme
Search
The list of hidden plugins, which dictates the tools available to the model in the background, has seen major additions. New identifiers such as computer-use@openai-bundled and deep-research-work@openai-curated-remote have appeared. This suggests that OpenAI is testing advanced execution capabilities, potentially allowing the model to perform complex, multi-step research or interact more deeply with system environments. Other notable additions to this hidden list include chatgpt-meetings, findata, and botmail, indicating a broadening of native integrations for productivity and financial data retrieval.
In the realm of local search and mapping, a parameter enabling 3D maps has been activated. For product searches, flags related to a virtual try-on experiment have been toggled to true, suggesting upcoming multimodal shopping features where users might visualize products directly within the interface.
Web run
A major infrastructural change is visible in the checkout and monetization configurations. The primary checkout provider parameter has been changed from Stripe to an internal identifier labeled as open_ai. While it is uncertain if this represents a complete replacement or a routing test, it indicates a significant evolution in how OpenAI handles transactions. Concurrently, new promotional checkout options involving PayPal and multi-currency support have been enabled.
For code execution and repository scanning tasks, the parameters governing commit analysis have been adjusted. The lookback period options have been expanded to include intervals ranging from 7 to 90 days, while the minimum commit threshold for scanning has been drastically reduced from 1000 to 10. This suggests an optimization of the scanning tool to accommodate smaller repositories or more recent, targeted code reviews.
Retrieval and grounding
Following the public deployment of the October update for GPT-6 Luna, the model's identifier is now explicitly visible in the configuration for the homework helper feature. The classifier model for this educational tool has been set to chat-luna-ev3-gpt6-v1, demonstrating how OpenAI routes specific, sensitive, or domain-restricted queries to specialized versions of its latest models.
A new configuration block named delayed generation allowance has been introduced. This setup includes a Kafka queue strategy, a four-hour window duration, and parameters for background synchronization. This strongly suggests that OpenAI is preparing an infrastructure for asynchronous tasks, where the model can process long-running prompts or deep research requests offline and notify the user upon completion.
Financial data retrieval capabilities are also expanding. The permissions governing financial data access have been updated to include new categories for news and private company metrics, adding to the existing public filings and earnings calls data sources.
Ads
The advertising configurations show the introduction of new dual call-to-action agents for specific commercial partners, notably Wayfair and Shopify SMB. These agents are designed to offer multiple interaction paths within a single sponsored placement.
Additionally, the blocklist for connector applications has been significantly reduced, and a new hard limit of 20 links per connector has been established. This indicates an effort to standardize the data flow and limit the payload size when external ad networks or commercial partners interface with the platform.
To monitor
Several interface and engagement tests observed last week have been reversed. The soft rate limit trigger for unauthenticated users, which was increased to 15 messages last week, has been reset to zero. Similarly, the right-to-left language interface adjustments featuring a large orb on the landing page have been disabled, and the dedicated image generation sidebar that appeared after starting a new chat has been deactivated.
New interface elements are currently in testing, including a flashcard widget with pronunciation features, which appears to be aimed at language learning or educational use cases. Finally, new rate limit parameters have surfaced, specifically defining a 5-hour limit and a weekly limit set at 101 interactions, which will need to be monitored to understand which specific feature or user tier they apply to.
