feat(tool): expose prompt-guided call protocol

[senamakel]

Summary

• move the prompt-guided tool protocol from the OpenAI adapter into harness::tool
• expose provider-neutral instruction, parsing, and response-projection helpers
• keep the OpenAI adapter on the same implementation with no wire behavior change

Why

Non-OpenAI ChatModel implementations also need the crate-owned text-mode tool protocol. Keeping it private to the OpenAI transport forces host adapters to duplicate framework logic and blocks direct model implementations.

Validation

• cargo fmt --all -- --check
• cargo test harness::tool::prompt::test (10 passed)
• cargo clippy --all-targets --all-features -- -D warnings

[coderabbitai]

Warning

Review limit reached

You’ve reached a temporary PR review limit under our Fair Usage Limits Policy.

Your recent review volume is higher than typical usage, so adaptive limits are currently applied.

Next review available in: 6 minutes

Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available.
You're only billed for reviews past your plan's rate limits ($0.25/file).

How can I continue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews.

How do review limits work?

CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability.

For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window.

Please refer docs for additional details.

Review details

⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Pro

Run ID: ab7753e7-fe7b-49be-9248-813ec44ee7be

📥 Commits

Reviewing files that changed from the base of the PR and between 2583fcc and 1c3c204.

📒 Files selected for processing (6)

• src/harness/providers/openai/mod.rs
• src/harness/providers/openai/test.rs
• src/harness/providers/openai/transport.rs
• src/harness/tool/mod.rs
• src/harness/tool/prompt.rs
• src/harness/tool/prompt_test.rs

---

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

[chatgpt-codex-connector]

💡 Codex Review

tinyagents/src/harness/tool/prompt.rs

Lines 139 to 140 in ba7481d

	#[cfg(test)]
	mod test {

Move prompt tests into the dedicated test file

This new unit test module lives inside prompt.rs, but the repo guidance for module directories says module-local unit tests belong in a dedicated test.rs; since src/harness/tool already has test.rs, keeping the prompt protocol tests inline makes the new public helper area inconsistent with the module layout. Please move these tests into the dedicated test file (or wire a scoped test module from there) so future tool-layer tests stay discoverable.

AGENTS.md reference: AGENTS.md:L15-L17

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[senamakel]

Addressed the Codex review in 53ea866: prompt-protocol tests now live in the dedicated src/harness/tool/prompt_test.rs module, wired from tool/mod.rs. Revalidated with cargo test harness::tool::prompt_test (12 passed) and cargo clippy --all-targets --all-features -- -D warnings.

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 53ea866790

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: d8129ae3f7

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".