.coderabbit.yaml

# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0

# yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json
# Docs: https://docs.coderabbit.ai/getting-started/configure-coderabbit/
language: "en-US"
tone_instructions: "Prefer concise, actionable review comments. When a fix is concrete and safe, include a GitHub Suggested Change so it can be applied with one click."
early_access: false
reviews:
  profile: "chill"
  request_changes_workflow: false
  high_level_summary: true
  # John likes the poems, no messing
  poem: true
  review_status: true
  review_details: true
  collapse_walkthrough: false
  enable_prompt_for_ai_agents: true
  auto_review:
    enabled: true
    drafts: true
    auto_incremental_review: true
    auto_pause_after_reviewed_commits: 5
  # Include reviewable source areas explicitly so support-matrix CSV diffs are
  # reviewed even though CSV files are normally skipped by default.
  path_filters:
    - ".claude/skills/**"
    - ".claude/**"
    - ".github/**"
    - "collector/**"
    - "docker/**"
    - "docs/**"
    - "aic-core/**"
    - "src/**"
    - "tests/**"
    - "tools/**"
    - ".dockerignore"
    - ".gitattributes"
    - ".gitignore"
    - ".pre-commit-config.yaml"
    - "LICENSE"
    - "*.md"
    - "*.ini"
    - "*.js"
    - "*.json"
    - "*.toml"
    - "*.yaml"
    - "*.yml"
    - ".coderabbit.yaml"
  path_instructions:
    - path: "**/*"
      instructions: |
        - Prefer applicable inline comments. When the correct fix is clear, small, and limited to the commented diff hunk, include it as a GitHub Suggested Change so the author can apply it with one click.
        - Do not use a suggested change when the fix requires broader design choices, multiple files, generated artifacts, unavailable context, or validation that cannot be inferred from the diff.
        - If a comment is not directly applicable, state the smallest concrete next step and why a one-click suggestion is not safe.
    - path: ".claude/skills/**/SKILL.md"
      instructions: |
        - This file is a skill definition. Apply contract consistency rules when `## Inputs` or `## Outputs` sections are present.
        - If the skill references another skill by name, verify expected field names match the callee's declared outputs and required inputs.
        - If the skill declares outputs consumed by another skill, verify callers remain compatible with the updated output fields.
        - Do not flag missing `## Inputs` or `## Outputs` sections by themselves; enforce these checks only when the sections exist.
    - path: "src/aiconfigurator/generator/**"
      instructions: |
        - Enforce the generator development rules from `.claude/rules/generator-development.md`.
        - Trace changes across the pipeline: input parsing, defaults, rule evaluation, parameter mapping, template rendering, and emitted artifacts.
        - For `.j2` templates and `.rule` files, verify `# Guard:` and `# Why:` comments are preserved and followed. Flag removals or bypasses unless the PR explicitly justifies them.
        - Check cross-backend consistency across TRT-LLM, vLLM, and SGLang when a backend-specific rule, template, parameter, or versioned artifact changes.
        - For new user-facing generator parameters, require matching CLI, SDK/profiler bridge, generator validator, docs, and test coverage updates where applicable.
        - For versioned template changes, verify the affected backend versions against `src/aiconfigurator/generator/config/backend_version_matrix.yaml`.
    - path: "collector/**"
      instructions: |
        - Enforce the collector rules from `.claude/rules/collector/layer_permissions.md`, `failure_handling.md`, and `case_authoring.md`.
        - Flag any silent case skip in collector code (a queued case may only execute or raise); the sole sanctioned filter is generation-time memory feasibility with counted drops.
        - Flag invented fallbacks on both ends: generation must raise on unresolvable declarations (never substitute defaults or another model's geometry); collectors must never swap in a different backend/kernel than the framework's own dispatch selects — manual pins require framework source citations.
        - Flag any reintroduction of selector/exception machinery (case_ids/contains/indices/ranges/limit/rules, sm_exceptions-style shape or version predicates) in YAML or code.
        - Capability floors (`cases/capabilities.yaml`) may hold hardware facts only: no shapes, no framework versions, no per-backend nesting. `cases/denylist.yaml` is for hang/node-killers only, dated.
        - Collector changes must stay within `collector/` and `tests/unit/collector/`; flag producer+consumer contract changes (perf row schema, PerfFile names) unless the PR explicitly declares them.
        - Check collector changes for backend/runtime version accuracy, GPU resource assumptions, reproducible command construction, and clear failure evidence.
        - Flag changes that make support-matrix or perf-data results harder to trace back to the command, model, system, quantization, or runtime version that produced them.
    - path: "src/aiconfigurator/cli/**"
      instructions: |
        - Check that CLI argument changes preserve backward compatibility, validation behavior, defaults, and plain-output expectations.
        - For new or changed user-facing options, verify docs updates and generator/SDK wiring.
        - Watch for non-TTY assumptions in tests or output formatting.
    - path: "src/aiconfigurator/sdk/**"
      instructions: |
        - Verify SDK API changes remain compatible with generator inputs, profiler data flow, and documented examples.
        - Flag silent schema or field-name drift between SDK models and generator/module bridge code.
    - path: "aic-core/src/aiconfigurator_core/sdk/**"
      instructions: |
        - Verify core SDK API changes remain compatible with legacy aiconfigurator.sdk imports, generator inputs, profiler data flow, and documented examples.
        - Flag upper-layer dependencies or silent schema drift introduced into the minimal core distribution.
    - path: "aic-core/src/aiconfigurator_core/sdk/operations/**"
      instructions: |
        - Enforce `.claude/rules/rust-core/parity.md` Rule 2 and its executable contract, tests/cross_package/test_single_oracle_contract.py; flag any change those sources prohibit.
    - path: "aic-core/src/aiconfigurator_core/sdk/perf_database.py"
      instructions: |
        - Enforce `.claude/rules/rust-core/parity.md` Rule 2 and tests/cross_package/test_single_oracle_contract.py for the `query_*` surface. Data loading remains in scope for this file and fine to extend.
    - path: "src/aiconfigurator/generator/module_bridge.py"
      instructions: |
        - Treat this as a compatibility bridge between profiler/SDK outputs and generator inputs.
        - Flag field renames, default changes, or type conversions unless corresponding tests and downstream generator expectations are updated.
    - path: "tools/generator_validator/**"
      instructions: |
        - Check that validator changes keep generated artifact coverage aligned across supported backends and versions.
        - For new generator flags or templates, verify the validator inspects the new emitted behavior instead of only command success.
    - path: "tools/support_matrix/**"
      instructions: |
        - Check support-matrix logic for deterministic ordering, duplicate-row handling, runtime/version matching, and clear PASS/FAIL semantics.
        - Verify changes distinguish collector/probe failures from actual model/backend support failures.
    - path: "aic-core/src/aiconfigurator_core/systems/support_matrix/**"
      instructions: |
        - Review support-matrix CSV updates as source-of-truth compatibility data, not generated noise.
        - Check that model, backend, runtime version, GPU system, quantization, tensor/pipeline/expert parallelism, and PASS/FAIL wording are internally consistent.
        - Flag stale or contradictory rows, duplicate keys, or claims that are not supported by linked evidence in the PR.
    - path: "tests/**"
      instructions: |
        - Check that tests cover the changed behavior rather than only the happy path.
        - Watch for fixtures or golden outputs that mask backend drift, support-matrix ordering changes, or CLI output regressions.
    - path: ".github/workflows/**"
      instructions: |
        - Review workflow edits for least-privilege permissions, safe trigger scopes, secret exposure, fork behavior, and release/cherry-pick side effects.
        - Verify matrix jobs, artifact uploads, and scheduled support-matrix workflows still produce debuggable evidence.
    - path: "docs/**"
      instructions: |
        - Check that docs match changed CLI, SDK, generator, backend, and support-matrix behavior.
        - Flag docs that describe unsupported runtimes, stale command names, or behavior not covered by tests or support-matrix evidence.
  suggested_labels: false
  suggested_reviewers: false
  sequence_diagrams: false
  related_issues: false
  related_prs: false
  finishing_touches:
    docstrings:
      enabled: false
    unit_tests:
      enabled: false
  pre_merge_checks:
    docstrings:
      mode: off
  tools:
    ruff:
      enabled: true
    shellcheck:
      enabled: true
    yamllint:
      enabled: true
    markdownlint:
      enabled: true
    github-checks:
      enabled: true
      timeout_ms: 900000
    gitleaks:
      enabled: true
    trufflehog:
      enabled: true
knowledge_base:
  code_guidelines:
    enabled: true
    filePatterns:
      - ".claude/rules/**/*.md"
chat:
  auto_reply: true