chore: add CodeRabbit configuration tuned to project guidelines

[lemon07r]

Tunes CodeRabbit to this repo instead of running it with generic defaults.

• Assertive profile + request-changes workflow: it should catch things, not rubber-stamp.
• Path instructions encoding repo rules: benchmark-integrity requirements for retrieval/** (mechanism rationale + Semble verification for ranking changes), minimal-LOC/no-duplication Rust conventions for crates/**, docs tone/freshness rules for *.md, Blacksmith runner awareness for workflows, benchmark-harness integrity for eval/**.
• Integrated linters: actionlint, shellcheck, markdownlint, ruff run inside reviews.
• Noise off: no poems, no sequence diagrams, collapsed walkthroughs; docstring/unit-test generation explicitly disabled (churn, against minimal-LOC).
• Free-tier safe: Pro-gated fields (profile, tools, finishing_touches, chat auto-reply) are marked with a comment; CodeRabbit ignores them post-trial and the rest keeps working.

Validated against the published v2 JSON schema (keys + types) and yaml.safe_load.

---

^{Need help on this PR? Tag @codesmith-bot with what you need. Autofix is disabled.}

---

Summary by cubic

Adds a project-specific .coderabbit.yaml so CodeRabbit enforces our repo rules instead of generic defaults. Reviews switch to an assertive, request-changes workflow with integrated linters; auto-generation of docstrings and unit tests is disabled to avoid churn.

• Review focus:
  • Check path globs and intent:
    • crates/vera-core/src/retrieval/**: require mechanism-level rationale for ranking changes and Semble benchmark verification.
    • crates/**: Rust conventions (edition 2024, MSRV 1.85, anyhow::Result for CLI, thiserror in core, tracing, tests in #[cfg(test)] at file end).
    • **/*.md: docs tone/freshness rules and single-source-of-truth.
    • .github/workflows/**: allow Blacksmith runner labels and preserve release targets and vera-<target>.(tar.gz|zip) archives.
    • eval/**: keep benchmark harness integrity; metrics consistent with benchmarks/scripts/bench_common.py.
  • Confirm tool enablement matches expectations: actionlint, shellcheck, markdownlint, ruff.
  • Note: Pro-tier fields (profile/tools finishing touches, chat auto-reply) are included but ignored on free tier; remaining settings still apply.

^{Written for commit 83fff87. Summary will update on new commits.}

[coderabbitai]

Warning

Review limit reached

@lemon07r, you've reached your PR review limit, so we couldn't start this review.

Next review available in: 51 minutes

Limit details: You’ve used all 3 included reviews currently available.

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 within each organization.

For paid Pro and Pro+ reviews, CodeRabbit uses a developer's included PR review attempts over the past 7 days to set the current hourly allowance. At typical activity levels, the full plan allowance applies. Higher sustained activity can lower the allowance until earlier attempts leave the 7-day window.

Please refer docs for additional details.

Review details

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: ASSERTIVE

Plan: Pro Plus

Run ID: 12169715-be96-4f41-b6f4-92f82b2c55d1

📥 Commits

Reviewing files that changed from the base of the PR and between 8c6239a and 83fff87.

📒 Files selected for processing (1)

• .coderabbit.yaml

---

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

[Copilot]

Pull request overview

Adds a repository-specific CodeRabbit configuration so automated reviews follow this project’s conventions (Rust/MSRV, benchmark integrity, docs tone, and workflow expectations) instead of generic defaults.

Changes:

• Adds .coderabbit.yaml with an assertive review profile and request-changes workflow.
• Configures path-specific instructions (retrieval, crates, docs, workflows, eval) and enables integrated linters (actionlint/shellcheck/markdownlint/ruff).
• Disables docstring and unit-test generation to reduce churn and align with minimal-LOC guidance.

---

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.