Fix: align tensormap orchestration tensor handling

[jvjhfhg]

• Move make_tensor helpers into pto_orchestration_api.h so orchestration code depends on the public header boundary
• Treat batch paged attention accumulator tensors as INOUT and track real heap allocation separately for TensorMap insertion
• Remove redundant PTO2TaskId wrapper helpers and switch runtime code and docs to direct PTO2TaskId accessors

[gemini-code-assist]

Summary of Changes

Hello, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request refactors tensor handling within the orchestration and runtime components, primarily by relocating tensor factory helpers to a more appropriate header, correcting the parameter type for batch paged attention accumulator tensors to ensure proper memory management, and streamlining the PTO2TaskId API by removing redundant wrapper functions in favor of direct member access. These changes improve code organization, correctness, and API clarity.

Highlights

• Header Reorganization: Moved make_tensor and make_tensor_external helper functions from tensor.h to pto_orchestration_api.h to ensure proper header dependency boundaries for orchestration code.
• Tensor Handling Correction: Modified the batch paged attention orchestration to treat accumulator tensors (oi_batch) as INOUT instead of OUTPUT, and introduced a mechanism to track real heap allocation for TensorMap insertion. This ensures correct memory management and dependency tracking for these tensors.
• API Simplification: Removed redundant wrapper functions (pto2_task_id_ring, pto2_task_id_local, pto2_task_id_raw) for PTO2TaskId and updated runtime code and documentation to use direct member accessors (.ring(), .local(), .raw). This simplifies the API and reduces overhead.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request introduces several valuable improvements to the tensormap orchestration handling. The changes correctly reclassify accumulator tensors as INOUT and refine the heap allocation tracking logic for TensorMap insertion, which enhances correctness. The codebase is also made more maintainable and readable by refactoring PTO2TaskId usage to direct accessors and moving make_tensor helpers to a more appropriate public API header. The accompanying documentation updates are accurate and helpful. Overall, the changes are well-executed and improve the system's architecture and correctness.