diff --git a/docs/codacy-ai/codacy-ai.md b/docs/codacy-ai/codacy-ai.md index 95505a14b8..d93e0a898c 100644 --- a/docs/codacy-ai/codacy-ai.md +++ b/docs/codacy-ai/codacy-ai.md @@ -4,17 +4,19 @@ Codacy AI is a set of optional features integrated into the Software designed to optimise development workflows and elevate code quality standards through automated issue descriptions, actionable recommendations and false-positive detection, is available for the Customer. -Codacy AI utilizes only enterprise-grade instances of OpenAI's services with enhanced security, privacy, and data protection features. Customer Code processed through Codacy AI will not be used by Codacy, OpenAI, or any third-party AI provider for training, improving, or developing artificial intelligence models, machine learning algorithms, or any other automated systems. +Codacy AI utilizes only enterprise-grade instances of OpenAI and Google Gemini services with enhanced security, privacy, and data protection features. Customer Code processed through Codacy AI will not be used by Codacy, OpenAI, or any third-party AI provider for training, improving, or developing artificial intelligence models, machine learning algorithms, or any other automated systems. ## AI Features ### AI-enhanced comments +_This feature leverages OpenAI models, and is strictly opt-in: it will only run on repositories or projects where a repository admin has enabled it._ + AI-enhanced comments are optional, machine-generated suggestions that appear directly in pull requests and review threads. They use Codacy's AI to provide concise issue summaries, remediation suggestions, and links to relevant documentation — helping reviewers and authors quickly understand and fix problems. -This feature is strictly opt-in: it will only run on repositories or projects where a repository admin has enabled it. +More details about [AI-enhanced comments here](../repositories-configure/integrations/github-integration.md#ai-enhanced-comments). -How to turn it on +**How to turn it on** 1. Go to your organization or repository settings in Codacy. 2. Navigate to the "Integrations" or "AI features" section (depending on your Codacy plan and UI version). @@ -22,26 +24,62 @@ How to turn it on 4. Optionally configure which repositories, branches, or severity levels should receive AI comments to reduce noise. 5. Save your changes. Once enabled, Codacy will start adding AI-enhanced comments to new pull requests and code reviews according to the configured scope. -Notes +**Notes** - Administrators can enable or disable the feature at organization or repository level. - Enabling the feature may be subject to plan limitations and governance controls; check your Codacy subscription and admin permissions. - Users can still ignore or dismiss individual AI comments during code review. -- Data usage and privacy +**Data usage and privacy** - To generate an AI-enhanced comment, Codacy only processes the specific issue context: the issue line plus up to ten lines before and ten lines after that line. No additional repository data is sent or used. - Codacy does not use your code, repository contents, or comments to train external AI models. No customer code or review text is incorporated into model training. ### Smart False Positive Triage +{% + include-markdown "../assets/includes/paid.md" + start="" + end="" +%} + +_This feature leverages OpenAI models, and is strictly opt-in: you need to get in touch with us in order to enable it._ + +Codacy False Positive triage analyzes results on a commit basis to give you visibility into issues that may be false positives (based on their context). During triage, each issue is given a confidence score along with an explanation. When the confidence level falls below a defined threshold, the issue is then flagged as an AI false positive and surfaced for manual review. You can evaluate potential false positives during a pull request in app or on any Codacy page where issues appear. These issues can be ignored or marked as Not a false positive. -How to turn it on +More details about [False Positives here](../repositories/commits.md#false-positive-issues). + +**How to turn it on** 1. Get in touch with your Customer Success Manager or with -Notes +**Notes** - Codacy does not use your code, repository contents, or comments to train external AI models. No customer code or review text is incorporated into model training. - To detect a Possible False Positive, Codacy only processes the specific issue context: one request per file with issues. No additional repository data is sent or used. - Prompts are neither stored nor visible by anyone + +### AI Reviewer + +!!! note + AI Reviewer is currently only available on GitHub, for all Team and Business plans. + +_This feature leverages Google Gemini models, and is strictly opt-in: it will only run on repositories or projects where a repository admin has enabled it._ + +The AI Reviewer combines the reliability of deterministic, rule-based static code analysis with the power of AI. It draws in the necessary context from source code and PR metadata to ensure the business intent matches the technical outcome, and can catch logic gaps that conventional scanners (and human reviewers) often miss. + +More details about [Ai Reviewer here](../repositories-configure/integrations/github-integration.md#ai-reviewer). + +**How to turn it on** + +1. Go to your organization or repository settings in Codacy. +2. Navigate to the "Integrations" or "AI features" section (depending on your Codacy plan and UI version). +3. Find "AI Reviewer", under "Status checks", and toggle the feature to "On" for the repository or organization scope you want to enable. +4. Save your changes. Once enabled, Codacy will start adding a Summary to your pull requests with of the information used to provide the AI-enriched reviews. +5. To request a PR Review from codacy, add a **`codacy-review`** label to your Pull Request. Codacy listens to the event and will publish the review as soon as it's ready. + +**Notes** + +- Codacy does not use your code, repository contents, or comments to train external AI models. No customer code or review text is incorporated into model training. +- To enrich the review, the git diff of the Pull Request as well as some related files' contents can be sent as context. No data is stored on our side, or used to train any models. +- Prompts are neither stored nor visible by anyone diff --git a/docs/organizations/integrations/images/default-git-provider-settings-apply-all.png b/docs/organizations/integrations/images/default-git-provider-settings-apply-all.png index a52c1741f5..ffe618ba2d 100644 Binary files a/docs/organizations/integrations/images/default-git-provider-settings-apply-all.png and b/docs/organizations/integrations/images/default-git-provider-settings-apply-all.png differ diff --git a/docs/organizations/integrations/images/default-git-provider-settings.png b/docs/organizations/integrations/images/default-git-provider-settings.png index 1af719ef38..f7588494fe 100644 Binary files a/docs/organizations/integrations/images/default-git-provider-settings.png and b/docs/organizations/integrations/images/default-git-provider-settings.png differ diff --git a/docs/repositories-configure/integrations/github-integration.md b/docs/repositories-configure/integrations/github-integration.md index 1a76085a96..0b3a35aac4 100644 --- a/docs/repositories-configure/integrations/github-integration.md +++ b/docs/repositories-configure/integrations/github-integration.md @@ -30,6 +30,17 @@ Adds a report to your pull requests showing whether your pull requests and cover ![Pull request status check on GitHub](images/github-integration-pr-status.png) +### AI Reviewer + +The AI Reviewer combines the reliability of deterministic, rule-based static code analysis with the power of AI. It draws in the necessary context from source code and PR metadata to ensure the business intent matches the technical outcome, and can catch logic gaps that conventional scanners (and human reviewers) often miss. + +It provides feedback on missing or weak tests, complex or duplicated code, and keeps security concerns up to date. Beyond that, it adds contextual insights about whether the changes follow the requirements, business rules, and logic used in the project. + +![AI Reviewer on Github](images/github-integration-ai-reviewer.png) + +!!! note + This feature is only supported on GitHub. + ### Issue annotations Adds annotations on the lines of the pull request where Codacy finds new issues. Codacy maps the severity of the issues reported by the tools to the severity levels of the annotations. To enable this option, you must enable **Status checks** first. diff --git a/docs/repositories-configure/integrations/images/github-integration-ai-reviewer.png b/docs/repositories-configure/integrations/images/github-integration-ai-reviewer.png new file mode 100644 index 0000000000..4d65c1628e Binary files /dev/null and b/docs/repositories-configure/integrations/images/github-integration-ai-reviewer.png differ diff --git a/submodules/chart b/submodules/chart index 6b68419f18..c6e7e25a06 160000 --- a/submodules/chart +++ b/submodules/chart @@ -1 +1 @@ -Subproject commit 6b68419f18e99128420ec030786465b1c71c9e1f +Subproject commit c6e7e25a0645d3d145f19e6457e18e54d8fe1e0c