Bundle builder tool-call payload (#42)

[leynos]

Summary

This branch finishes the issue #42 argument-count refactor in the builder core loop by grouping the remaining tool-call response fields behind a private parameter object.

Closes #42.

Review walkthrough

• Start with src/tools/builder/core/build_loop.rs to review the new ToolCallPayload parameter object and the updated handle_tool_calls signature.
• Then review the RespondResult::ToolCalls branch in the same file to confirm the call site now constructs the payload without changing control flow.

Validation

• cargo fmt --all: passed
• cargo fmt --manifest-path tools-src/github/Cargo.toml --all: passed
• make all: passed
• Local argument-count check: handle_tool_calls is 4 explicit parameters, build_success_result is 3, fail_planning_stuck is 2, fail_max_iterations is 2, and the module average is 2.31.

Notes

• CodeRabbit review was attempted with coderabbit review --agent, but the service returned a usage-credit rate-limit error before producing review findings.
• This is a code-only internal refactor; no documentation label is needed because there are no documentation-only changes.

Summary by Sourcery

Refactor the builder core loop to bundle tool-call response data into a dedicated payload object passed to the tool-call handler.

Enhancements:

• Introduce a ToolCallPayload struct to group tool_calls and content for tool-call handling in the builder loop.
• Update the handle_tool_calls method and its call site to accept the new payload object without changing control flow.

[coderabbitai]

Important

Review skipped

Draft detected.

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

⚙️ Run configuration

Configuration used: Organization UI

Review profile: ASSERTIVE

Plan: Pro Plus

Run ID: 513b326c-874d-45d8-b38d-ee1a67facad2

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

• 🔍 Trigger review

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch issue-42-argument-count-in-builder-core-loop-helpers

---

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[sourcery-ai]

Reviewer's guide (collapsed on small PRs)

Reviewer's Guide

Refactors the builder core loop to bundle tool-call related arguments into a new ToolCallPayload struct, simplifying the handle_tool_calls signature while preserving existing control flow and behavior.

File-Level Changes

Change	Details	Files
Introduce ToolCallPayload struct to group tool-call response fields and update handle_tool_calls to use it.	Add ToolCallPayload struct encapsulating tool_calls and content fields. Change handle_tool_calls signature to accept a ToolCallPayload instead of separate tool_calls and content parameters. Update assistant_with_tool_calls invocation to read from the ToolCallPayload instance. Adjust iteration over tool calls to consume payload.tool_calls.	src/tools/builder/core/build_loop.rs
Update the ToolCalls response handling branch to construct and pass ToolCallPayload without altering logic.	In the RespondResult::ToolCalls match arm, mark tools_executed and construct a ToolCallPayload from tool_calls and content. Pass the constructed ToolCallPayload into handle_tool_calls, maintaining the previous control flow and async behavior.	src/tools/builder/core/build_loop.rs

Assessment against linked issues

Issue	Objective	Addressed	Explanation
#42	Refactor the four helper functions (handle_tool_calls, build_success_result, fail_planning_stuck, fail_max_iterations) in src/tools/builder/core/build_loop.rs to reduce their parameter counts to 4 or fewer by introducing parameter objects, without changing behaviour or the public API.	✅
#42	Reduce the module’s average function-argument count below 4.00 while keeping control flow, log/error strings, and result shapes (user-visible messages/JSON) identical and ensuring all tests pass.	✅
#42	Keep the refactor scoped to src/tools/builder/core/build_loop.rs and any strictly necessary internal helpers only.	✅

Possibly linked issues

• Excess Number of Function Arguments: reduce argument count in builder core loop helpers #42: PR completes the issue’s builder core loop argument-count refactor by bundling tool-call response fields into ToolCallPayload.

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[codescene-delta-analysis]

Gates Failed
Enforce advisory code health rules (1 file with Large Method)

Gates Passed
5 Quality Gates Passed

See analysis details in CodeScene

Reason for failure

Enforce advisory code health rules	Violations	Code Health Impact
build_loop.rs	1 advisory rule	8.96 → 8.58	Suppress

Quality Gate Profile: Pay Down Tech Debt
Install CodeScene MCP: safeguard and uplift AI-generated code. Catch issues early with our IDE extension and CLI tool.

[codescene-delta-analysis]

❌ New issue: Large Method
LlmSoftwareBuilder.execute_build_loop has 76 lines, threshold = 70

_Suppress