promptfoo 0.103.0 → 0.103.2

package/README.md

@@ -1,4 +1,4 @@
-# promptfoo: test your LLM app locally
+# Promptfoo: LLM evals & red teaming
 
 [![npm](https://img.shields.io/npm/v/promptfoo)](https://npmjs.com/package/promptfoo)
 [![npm](https://img.shields.io/npm/dm/promptfoo)](https://npmjs.com/package/promptfoo)
@@ -6,451 +6,60 @@
 ![MIT license](https://img.shields.io/github/license/promptfoo/promptfoo)
 [![Discord](https://github.com/user-attachments/assets/2092591a-ccc5-42a7-aeb6-24a2808950fd)](https://discord.gg/gHPS9jjfbs)
 
-`promptfoo` is a tool for testing, evaluating, and red-teaming LLM apps.
+`promptfoo` is a developer-friendly local tool for testing LLM applications. Stop the trial-and-error approach - start shipping secure, reliable AI apps.
 
-With promptfoo, you can:
-
-- **Build reliable prompts, models, and RAGs** with benchmarks specific to your use-case
-- **Secure your apps** with automated [red teaming](https://www.promptfoo.dev/docs/red-team/) and pentesting
-- **Speed up evaluations** with caching, concurrency, and live reloading
-- **Score outputs automatically** by defining [metrics](https://www.promptfoo.dev/docs/configuration/expected-outputs)
-- Use as a [CLI](https://www.promptfoo.dev/docs/usage/command-line), [library](https://www.promptfoo.dev/docs/usage/node-package), or in [CI/CD](https://www.promptfoo.dev/docs/integrations/github-action)
-- Use OpenAI, Anthropic, Azure, Google, HuggingFace, open-source models like Llama, or integrate custom API providers for [any LLM API](https://www.promptfoo.dev/docs/providers)
-
-The goal: **test-driven LLM development** instead of trial-and-error.
+## Quick Start
 
 ```sh
+# Install and initialize project
 npx promptfoo@latest init
-```
-
-# [» View full documentation «](https://www.promptfoo.dev/docs/intro)
-
-promptfoo produces matrix views that let you quickly evaluate outputs across many prompts and inputs:
-
-![prompt evaluation matrix - web viewer](https://github.com/promptfoo/promptfoo/assets/310310/ce5a7817-da82-4484-b26d-32474f1cabc5)
-
-It works on the command line too:
-
-![Prompt evaluation](https://github.com/promptfoo/promptfoo/assets/310310/480e1114-d049-40b9-bd5f-f81c15060284)
-
-It also produces high-level vulnerability and risk reports:
-
-![gen ai red team](https://www.promptfoo.dev/img/riskreport-1@2x.png)
-
-## Why choose promptfoo?
-
-There are many different ways to evaluate prompts. Here are some reasons to consider promptfoo:
-
-- **Developer friendly**: promptfoo is fast, with quality-of-life features like live reloads and caching.
-- **Battle-tested**: Originally built for LLM apps serving over 10 million users in production. Our tooling is flexible and can be adapted to many setups.
-- **Simple, declarative test cases**: Define evals without writing code or working with heavy notebooks.
-- **Language agnostic**: Use Python, Javascript, or any other language.
-- **Share & collaborate**: Built-in share functionality & web viewer for working with teammates.
-- **Open-source**: LLM evals are a commodity and should be served by 100% open-source projects with no strings attached.
-- **Private**: This software runs completely locally. The evals run on your machine and talk directly with the LLM.
-
-## Workflow
-
-Start by establishing a handful of test cases - core use cases and failure cases that you want to ensure your prompt can handle.
-
-As you explore modifications to the prompt, use `promptfoo eval` to rate all outputs. This ensures the prompt is actually improving overall.
-
-As you collect more examples and establish a user feedback loop, continue to build the pool of test cases.
-
-<img width="772" alt="LLM ops" src="https://github.com/promptfoo/promptfoo/assets/310310/cf0461a7-2832-4362-9fbb-4ebd911d06ff">
-
-## Usage - evals
-
-To get started, run this command:
-
-```sh
-npx promptfoo@latest init
-```
-
-This will create a `promptfooconfig.yaml` placeholder in your current directory.
-
-After editing the prompts and variables to your liking, run the eval command to kick off an evaluation:
-
-```
-npx promptfoo@latest eval
-```
-
-## Usage - red teaming/pentesting
-
-Run this command:
-
-```sh
-npx promptfoo@latest redteam init
-```
-
-This will ask you questions about what types of vulnerabilities you want to find and walk you through running your first scan.
 
-### Configuration
-
-The YAML configuration format runs each prompt through a series of example inputs (aka "test case") and checks if they meet requirements (aka "assert").
-
-See the [Configuration docs](https://www.promptfoo.dev/docs/configuration/guide) for a detailed guide.
-
-```yaml
-prompts:
-  - file://prompt1.txt
-  - file://prompt2.txt
-providers:
-  - openai:gpt-4o-mini
-  - ollama:llama3.1:70b
-tests:
-  - description: 'Test translation to French'
-    vars:
-      language: French
-      input: Hello world
-    assert:
-      - type: contains-json
-      - type: javascript
-        value: output.length < 100
-
-  - description: 'Test translation to German'
-    vars:
-      language: German
-      input: How's it going?
-    assert:
-      - type: llm-rubric
-        value: does not describe self as an AI, model, or chatbot
-      - type: similar
-        value: was geht
-        threshold: 0.6 # cosine similarity
+# Run your first evaluation
+npx promptfoo eval
 ```
 
-### Supported assertion types
-
-See [Test assertions](https://www.promptfoo.dev/docs/configuration/expected-outputs) for full details.
-
-Deterministic eval metrics
-
-| Assertion Type                  | Returns true if...                                                |
-| ------------------------------- | ----------------------------------------------------------------- |
-| `equals`                        | output matches exactly                                            |
-| `contains`                      | output contains substring                                         |
-| `icontains`                     | output contains substring, case insensitive                       |
-| `regex`                         | output matches regex                                              |
-| `starts-with`                   | output starts with string                                         |
-| `contains-any`                  | output contains any of the listed substrings                      |
-| `contains-all`                  | output contains all list of substrings                            |
-| `icontains-any`                 | output contains any of the listed substrings, case insensitive    |
-| `icontains-all`                 | output contains all list of substrings, case insensitive          |
-| `is-json`                       | output is valid json (optional json schema validation)            |
-| `contains-json`                 | output contains valid json (optional json schema validation)      |
-| `is-sql`                        | output is valid sql                                               |
-| `contains-sql`                  | output contains valid sql                                         |
-| `is-xml`                        | output is valid xml                                               |
-| `contains-xml`                  | output contains valid xml                                         |
-| `is-refusal`                    | output indicates the model refused to perform the task            |
-| `javascript`                    | provided Javascript function validates the output                 |
-| `python`                        | provided Python function validates the output                     |
-| `webhook`                       | provided webhook returns `{pass: true}`                           |
-| `rouge-n`                       | Rouge-N score is above a given threshold (default 0.75)           |
-| `bleu`                          | BLEU score is above a given threshold (default 0.5)               |
-| `levenshtein`                   | Levenshtein distance is below a threshold                         |
-| `latency`                       | Latency is below a threshold (milliseconds)                       |
-| `perplexity`                    | Perplexity is below a threshold                                   |
-| `perplexity-score`              | Normalized perplexity                                             |
-| `cost`                          | Cost is below a threshold (for models with cost info such as GPT) |
-| `is-valid-openai-function-call` | Ensure that the function call matches the function's JSON schema  |
-| `is-valid-openai-tools-call`    | Ensure that all tool calls match the tools JSON schema            |
-| `assert-set`                    | Group assertions together with optional threshold                 |
-
-Model-assisted eval metrics
-
-| Assertion Type                                                                                      | Method                                                                          |
-| --------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------- |
-| [similar](https://www.promptfoo.dev/docs/configuration/expected-outputs/similar)                    | Embeddings and cosine similarity are above a threshold                          |
-| [classifier](https://www.promptfoo.dev/docs/configuration/expected-outputs/classifier)              | Run LLM output through a classifier                                             |
-| [llm-rubric](https://www.promptfoo.dev/docs/configuration/expected-outputs/model-graded)            | LLM output matches a given rubric, using a Language Model to grade output       |
-| [answer-relevance](https://www.promptfoo.dev/docs/configuration/expected-outputs/model-graded)      | Ensure that LLM output is related to original query                             |
-| [context-faithfulness](https://www.promptfoo.dev/docs/configuration/expected-outputs/model-graded)  | Ensure that LLM output uses the context                                         |
-| [context-recall](https://www.promptfoo.dev/docs/configuration/expected-outputs/model-graded)        | Ensure that ground truth appears in context                                     |
-| [context-relevance](https://www.promptfoo.dev/docs/configuration/expected-outputs/model-graded)     | Ensure that context is relevant to original query                               |
-| [factuality](https://www.promptfoo.dev/docs/configuration/expected-outputs/model-graded)            | LLM output adheres to the given facts, using Factuality method from OpenAI eval |
-| [model-graded-closedqa](https://www.promptfoo.dev/docs/configuration/expected-outputs/model-graded) | LLM output adheres to given criteria, using Closed QA method from OpenAI eval   |
-| [moderation](https://www.promptfoo.dev/docs/configuration/expected-outputs/moderation)              | Make sure outputs are safe                                                      |
-| [select-best](https://www.promptfoo.dev/docs/configuration/expected-outputs/model-graded)           | Compare multiple outputs for a test case and pick the best one                  |
-
-Every test type can be negated by prepending `not-`. For example, `not-equals` or `not-regex`.
-
-### Tests from spreadsheet
-
-Some people prefer to configure their LLM tests in a CSV. In that case, the config is pretty simple:
-
-```yaml
-prompts:
-  - file://prompts.txt
-providers:
-  - openai:gpt-4o-mini
-tests: file://tests.csv
-```
-
-See [example CSV](https://github.com/promptfoo/promptfoo/blob/main/examples/simple-test/tests.csv).
-
-### Command-line
-
-If you're looking to customize your usage, you have a wide set of parameters at your disposal.
-
-| Option                              | Description                                                                                                                                                                            |
-| ----------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `-p, --prompts <paths...>`          | Paths to [prompt files](https://www.promptfoo.dev/docs/configuration/parameters#prompts), directory, or glob                                                                           |
-| `-r, --providers <name or path...>` | One of: openai:chat, openai:completion, openai:model-name, localai:chat:model-name, localai:completion:model-name. See [API providers][providers-docs]                                 |
-| `-o, --output <path>`               | Path to [output file](https://www.promptfoo.dev/docs/configuration/parameters#output-file) (csv, json, yaml, html)                                                                     |
-| `--tests <path>`                    | Path to [external test file](https://www.promptfoo.dev/docs/configuration/expected-outputs/#load-assertions-from-external-file)                                                        |
-| `-c, --config <paths>`              | Path to one or more [configuration files](https://www.promptfoo.dev/docs/configuration/guide). `promptfooconfig.yaml` is automatically loaded if present                               |
-| `-j, --max-concurrency <number>`    | Maximum number of concurrent API calls                                                                                                                                                 |
-| `--table-cell-max-length <number>`  | Truncate console table cells to this length                                                                                                                                            |
-| `--prompt-prefix <path>`            | This prefix is prepended to every prompt                                                                                                                                               |
-| `--prompt-suffix <path>`            | This suffix is append to every prompt                                                                                                                                                  |
-| `--grader`                          | [Provider][providers-docs] that will conduct the evaluation, if you are [using LLM to grade your output](https://www.promptfoo.dev/docs/configuration/expected-outputs#llm-evaluation) |
-
-After running an eval, you may optionally use the `view` command to open the web viewer:
+See [Getting Started](https://www.promptfoo.dev/docs/getting-started/) (evals) or [Red Teaming](https://www.promptfoo.dev/docs/red-team/) (vulnerability scanning) for more.
 
-```sh
-npx promptfoo view
-```
-
-### Examples
-
-#### Prompt quality
-
-In [this example](https://github.com/promptfoo/promptfoo/tree/main/examples/assistant-cli), we evaluate whether adding adjectives to the personality of an assistant bot affects the responses:
-
-```
-npx promptfoo eval -p prompts.txt -r openai:gpt-4o-mini -t tests.csv
-```
-
-<!--
-<img width="1362" alt="Side-by-side evaluation of LLM prompt quality, terminal output" src="https://user-images.githubusercontent.com/310310/235329207-e8c22459-5f51-4fee-9714-1b602ac3d7ca.png">
-
-![Side-by-side evaluation of LLM prompt quality, html output](https://user-images.githubusercontent.com/310310/235483444-4ddb832d-e103-4b9c-a862-b0d6cc11cdc0.png)
--->
-
-This command will evaluate the prompts in `prompts.txt`, substituting the variable values from `vars.csv`, and output results in your terminal.
-
-You can also output a nice [spreadsheet](https://docs.google.com/spreadsheets/d/1nanoj3_TniWrDl1Sj-qYqIMD6jwm5FBy15xPFdUTsmI/edit?usp=sharing), [JSON](https://github.com/promptfoo/promptfoo/blob/main/examples/simple-cli/output.json), YAML, or an HTML file:
-
-![Table output](https://user-images.githubusercontent.com/310310/235483444-4ddb832d-e103-4b9c-a862-b0d6cc11cdc0.png)
-
-#### Model quality
-
-In the [next example](https://github.com/promptfoo/promptfoo/tree/main/examples/gpt-4o-vs-4o-mini), we evaluate the difference between GPT 3 and GPT 4 outputs for a given prompt:
-
-```
-npx promptfoo eval -p prompts.txt -r openai:gpt-4o openai:gpt-4o-mini -o output.html
-```
+## What can you do with Promptfoo?
 
-Produces this HTML table:
+- **Test your prompts and models** with [automated evaluations](https://www.promptfoo.dev/docs/getting-started/)
+- **Secure your LLM apps** with [red teaming](https://www.promptfoo.dev/docs/red-team/) and vulnerability scanning
+- **Compare models** side-by-side (OpenAI, Anthropic, Azure, Bedrock, Ollama, and [more](https://www.promptfoo.dev/docs/providers/))
+- **Automate checks** in [CI/CD](https://www.promptfoo.dev/docs/integrations/ci-cd/)
+- **Share results** with your team
 
-![Side-by-side evaluation of LLM model quality, gpt-4o vs gpt-4o-mini, html output](https://user-images.githubusercontent.com/310310/235490527-e0c31f40-00a0-493a-8afc-8ed6322bb5ca.png)
+Here's what it looks like in action:
 
-## Usage (node package)
+![prompt evaluation matrix - web viewer](https://www.promptfoo.dev/img/claude-vs-gpt-example@2x.png)
 
-You can also use `promptfoo` as a library in your project by importing the `evaluate` function. The function takes the following parameters:
-
-- `testSuite`: the Javascript equivalent of the promptfooconfig.yaml
-
-  ```typescript
-  interface EvaluateTestSuite {
-    providers: string[]; // Valid provider name (e.g. openai:gpt-4o-mini)
-    prompts: string[]; // List of prompts
-    tests: string | TestCase[]; // Path to a CSV file, or list of test cases
-
-    defaultTest?: Omit<TestCase, 'description'>; // Optional: add default vars and assertions on test case
-    outputPath?: string | string[]; // Optional: write results to file
-  }
-
-  interface TestCase {
-    // Optional description of what you're testing
-    description?: string;
-
-    // Key-value pairs to substitute in the prompt
-    vars?: Record<string, string | string[] | object>;
-
-    // Optional list of automatic checks to run on the LLM output
-    assert?: Assertion[];
-
-    // Additional configuration settings for the prompt
-    options?: PromptConfig & OutputConfig & GradingConfig;
-
-    // The required score for this test case.  If not provided, the test case is graded pass/fail.
-    threshold?: number;
-
-    // Override the provider for this test
-    provider?: string | ProviderOptions | ApiProvider;
-  }
-
-  interface Assertion {
-    type: string;
-    value?: string;
-    threshold?: number; // Required score for pass
-    weight?: number; // The weight of this assertion compared to other assertions in the test case. Defaults to 1.
-    provider?: ApiProvider; // For assertions that require an LLM provider
-  }
-  ```
-
-- `options`: misc options related to how the tests are run
-
-  ```typescript
-  interface EvaluateOptions {
-    maxConcurrency?: number;
-    showProgressBar?: boolean;
-    generateSuggestions?: boolean;
-  }
-  ```
-
-### Example
-
-`promptfoo` exports an `evaluate` function that you can use to run prompt evaluations.
-
-```js
-import promptfoo from 'promptfoo';
-
-const results = await promptfoo.evaluate({
-  prompts: ['Rephrase this in French: {{body}}', 'Rephrase this like a pirate: {{body}}'],
-  providers: ['openai:gpt-4o-mini'],
-  tests: [
-    {
-      vars: {
-        body: 'Hello world',
-      },
-    },
-    {
-      vars: {
-        body: "I'm hungry",
-      },
-    },
-  ],
-});
-```
-
-This code imports the `promptfoo` library, defines the evaluation options, and then calls the `evaluate` function with these options.
-
-See the full example [here](https://github.com/promptfoo/promptfoo/tree/main/examples/simple-import), which includes an example results object.
-
-## Configuration
-
-- **[Main guide](https://www.promptfoo.dev/docs/configuration/guide)**: Learn about how to configure your YAML file, setup prompt files, etc.
-- **[Configuring test cases](https://www.promptfoo.dev/docs/configuration/expected-outputs)**: Learn more about how to configure assertions and metrics.
-
-## Installation
-
-Requires Node.js 18 or newer.
-
-You can install promptfoo using npm, npx, Homebrew, or by cloning the repository.
-
-### npm (recommended)
-
-Install `promptfoo` globally:
-
-```sh
-npm install -g promptfoo
-```
-
-Or install it locally in your project:
-
-```sh
-npm install promptfoo
-```
-
-### npx
-
-Run promptfoo without installing it:
-
-```sh
-npx promptfoo@latest init
-```
-
-This will create a `promptfooconfig.yaml` placeholder in your current directory.
-
-### Homebrew
-
-If you prefer using Homebrew, you can install promptfoo with:
-
-```sh
-brew install promptfoo
-```
-
-### From source
-
-For the latest development version:
-
-```sh
-git clone https://github.com/promptfoo/promptfoo.git
-cd promptfoo
-npm install
-npm run build
-npm link
-```
-
-### Verify installation
-
-To verify that promptfoo is installed correctly, run:
-
-```sh
-promptfoo --version
-```
-
-This should display the version number of promptfoo.
-
-For more detailed installation instructions, including system requirements and troubleshooting, please visit our [installation guide](https://www.promptfoo.dev/docs/installation).
-
-## API Providers
-
-We support OpenAI's API as well as a number of open-source models. It's also to set up your own custom API provider. **[See Provider documentation][providers-docs]** for more details.
-
-## Development
-
-Here's how to build and run locally:
-
-```sh
-git clone https://github.com/promptfoo/promptfoo.git
-cd promptfoo
-
-# Optionally use the Node.js version specified in the .nvmrc file - make sure you are on node >= 18
-nvm use
-
-npm i
-cd path/to/experiment-with-promptfoo   # contains your promptfooconfig.yaml
-npx path/to/promptfoo-source eval
-```
-
-The web UI is located in `src/app`. To run it in dev mode, run `npm run local:app`. This will host the web UI at http://localhost:3000. The web UI expects `promptfoo view` to be running separately.
-
-Then run:
-
-```sh
-npm run build
-```
+It works on the command line too:
 
-The build has some side effects such as e.g. copying HTML templates, migrations, etc.
+![prompt evaluation matrix - command line](https://github.com/promptfoo/promptfoo/assets/310310/480e1114-d049-40b9-bd5f-f81c15060284)
 
-Contributions are welcome! Please feel free to submit a pull request or open an issue.
+It also can generate [security vulnerability reports](https://www.promptfoo.dev/docs/red-team/):
 
-`promptfoo` includes several npm scripts to make development easier and more efficient. To use these scripts, run `npm run <script_name>` in the project directory.
+![gen ai red team](https://www.promptfoo.dev/img/riskreport-1@2x.png)
 
-Here are some of the available scripts:
+## Why promptfoo?
 
-- `build`: Transpile TypeScript files to JavaScript
-- `build:watch`: Continuously watch and transpile TypeScript files on changes
-- `test`: Run test suite
-- `test:watch`: Continuously run test suite on changes
-- `db:generate`: Generate new db migrations (and create the db if it doesn't already exist). Note that after generating a new migration, you'll have to `npm i` to copy the migrations into `dist/`.
-- `db:migrate`: Run existing db migrations (and create the db if it doesn't already exist)
+- 🚀 **Developer-first**: Fast, with features like live reload and caching
+- 🔒 **Private**: Runs 100% locally - your prompts never leave your machine
+- 🔧 **Flexible**: Works with any LLM API or programming language
+- 💪 **Battle-tested**: Powers LLM apps serving 10M+ users in production
+- 📊 **Data-driven**: Make decisions based on metrics, not gut feel
+- 🤝 **Open source**: MIT licensed, with an active community
 
-To run the CLI during development you can run a command like: `npm run local -- eval --config $(readlink -f ./examples/cloudflare-ai/chat_config.yaml)`, where any parts of the command after `--` are passed through to our CLI entrypoint. Since the Next dev server isn't supported in this mode, see the instructions above for running the web server.
+## Learn More
 
-# [» View full documentation «](https://www.promptfoo.dev/docs/intro)
+- 📚 [Full Documentation](https://www.promptfoo.dev/docs/intro/)
+- 🔐 [Red Teaming Guide](https://www.promptfoo.dev/docs/red-team/)
+- 🎯 [Getting Started](https://www.promptfoo.dev/docs/getting-started/)
+- 💻 [CLI Usage](https://www.promptfoo.dev/docs/usage/command-line/)
+- 📦 [Node.js Package](https://www.promptfoo.dev/docs/usage/node-package/)
+- 🤖 [Supported Models](https://www.promptfoo.dev/docs/providers/)
 
-[providers-docs]: https://www.promptfoo.dev/docs/providers
+## Contributing
 
-### Adding a New Provider
+We welcome contributions! Check out our [contributing guide](https://www.promptfoo.dev/docs/contributing/) to get started.
 
-1. Create an implementation in `src/providers/SOME_PROVIDER_FILE`
-2. Update `loadApiProvider` in `src/providers.ts` to load your provider via string
-3. Add test cases in `test/providers.test.ts`
-   1. Test the actual provider implementation
-   2. Test loading the provider via a `loadApiProvider` test
+Join our [Discord community](https://discord.gg/gHPS9jjfbs) for help and discussion.

package/dist/package.json

@@ -2,7 +2,7 @@
     "name": "promptfoo",
     "description": "LLM eval & testing toolkit",
     "author": "Ian Webster",
-    "version": "0.103.0",
+    "version": "0.103.2",
     "license": "MIT",
     "type": "commonjs",
     "repository": {

package/dist/src/app/assets/{index-Vk7H3M29.css → index-DdUNCsxz.css}

@@ -1 +1 @@
-.nav{padding:.25rem 0 .25rem 1rem;gap:1rem;background-color:#333;margin-bottom:1rem;box-shadow:0 4px 6px #0000001a}[data-theme=dark] .nav{background-color:#121212}.nav a{text-decoration:none;align-self:center}@media (max-width: 760px){.nav{font-size:.75rem}}.nav .active{font-weight:700}.nav a{color:#f0f0f0}.nav .right-aligned{display:flex;align-items:center;gap:1rem;margin-left:auto;margin-right:.5rem}.nav a:hover{text-decoration:underline}.nav a:hover{color:#ddd}.prompt-var-highlight{background-color:var(--prompt-highlight-color);padding:.25rem;border-radius:4px}.glowing-border{border:1px solid #5cb3ff;box-shadow:0 0 8px 2px #5cb3ff}code[class*=language-],pre[class*=language-]{color:#000;background:none;text-shadow:0 1px white;font-family:Consolas,Monaco,Andale Mono,Ubuntu Mono,monospace;font-size:1em;text-align:left;white-space:pre;word-spacing:normal;word-break:normal;word-wrap:normal;line-height:1.5;-moz-tab-size:4;-o-tab-size:4;tab-size:4;-webkit-hyphens:none;-moz-hyphens:none;-ms-hyphens:none;hyphens:none}pre[class*=language-]::-moz-selection,pre[class*=language-] ::-moz-selection,code[class*=language-]::-moz-selection,code[class*=language-] ::-moz-selection{text-shadow:none;background:#b3d4fc}pre[class*=language-]::selection,pre[class*=language-] ::selection,code[class*=language-]::selection,code[class*=language-] ::selection{text-shadow:none;background:#b3d4fc}@media print{code[class*=language-],pre[class*=language-]{text-shadow:none}}pre[class*=language-]{padding:1em;margin:.5em 0;overflow:auto}:not(pre)>code[class*=language-],pre[class*=language-]{background:#f5f2f0}:not(pre)>code[class*=language-]{padding:.1em;border-radius:.3em;white-space:normal}.token.comment,.token.prolog,.token.doctype,.token.cdata{color:#708090}.token.punctuation{color:#999}.token.namespace{opacity:.7}.token.property,.token.tag,.token.boolean,.token.number,.token.constant,.token.symbol,.token.deleted{color:#905}.token.selector,.token.attr-name,.token.string,.token.char,.token.builtin,.token.inserted{color:#690}.token.operator,.token.entity,.token.url,.language-css .token.string,.style .token.string{color:#9a6e3a;background:#ffffff80}.token.atrule,.token.attr-value,.token.keyword{color:#07a}.token.function,.token.class-name{color:#dd4a68}.token.regex,.token.important,.token.variable{color:#e90}.token.important,.token.bold{font-weight:700}.token.italic{font-style:italic}.token.entity{cursor:help}.yaml-config{font-size:10px}.custom-metric-container{display:inline-flex;flex-wrap:wrap;gap:.25rem;font-weight:400}.custom-metric-container>span{padding:.25rem .5rem;border-radius:4px;color:var(--text-color);border:1px solid var(--border-color);margin-right:.25rem}.custom-metric-container>span.clickable{cursor:pointer}.custom-metric-container>span.clickable:hover{border-color:var(--link-color)}.fail-reason-carousel-controls{float:right;color:var(--text-color);font-weight:400}pre{white-space:pre-wrap}.font-bold{font-weight:700}table.results-table,.divTable{border-collapse:collapse;width:100%;margin:1rem 0;background-color:#fff}[data-theme=dark] table.results-table,[data-theme=dark] .divTable{background-color:#1a1a1a}.results-table ins{background-color:var(--insert-highlight-color);text-decoration:none}.results-table del{background-color:var(--delete-highlight-color);text-decoration:strikethrough}.tr{display:flex}.results-table tr,.tr{width:fit-content}.results-table tr:hover,.tr:hover{background-color:#00000005}.results-table th,.th,.results-table td,.td{position:relative;border:1px solid var(--border-color);vertical-align:top}.compact.results-table th,.compact .th,.compact.results-table td,.compact .td{padding:.5rem}.results-table th.variable,.th.variable,.results-table td.variable,.td.variable{background-color:var(--variable-background-color)}.variable .cell{max-height:100%;overflow-y:auto}.results-table tr.header{background-color:var(--header-background-color)}.results-table th,.th{padding:1rem;position:relative;vertical-align:bottom;text-align:left;white-space:pre-wrap;font-weight:400}.results-table th .action{cursor:pointer;margin-left:.5rem}.results-table th .action svg{vertical-align:middle}.results-table td,.results-table th{height:1px}@-moz-document url-prefix(){.results-table td,.results-table th{height:100%}}.firefox-fix{display:table;height:100%}.results-table tr .cell{display:flex;flex-direction:column;white-space:pre-wrap;height:100%;padding:1rem}.results-table tr .cell img{max-width:var(--max-image-width, 256px);max-height:var(--max-image-height, 256px);cursor:zoom-in}.results-table tr .cell .prompt{background-color:var(--variable-background-color);border:1px solid var(--border-color);padding:1rem;border-radius:4px;margin-bottom:.5rem;font-family:Courier New,Courier,monospace;font-size:.8rem}.results-table tr .cell .prompt .pill{display:block;background-color:var(--neutral-background-color);border:1px solid var(--border-color);border-radius:4px;padding:.25rem;width:fit-content;margin-bottom:.5rem}.results-table tr .cell-actions{display:flex;gap:.5rem;visibility:hidden;position:absolute;top:1.25rem;right:.75rem;line-height:0;font-size:1.25rem}.results-table .first-prompt-col:hover .cell-actions,.results-table .second-prompt-column:hover .cell-actions{visibility:visible}.results-table tr .cell-detail{display:flex;flex-wrap:wrap;column-gap:.5rem;row-gap:.25rem;padding-top:1rem;margin-top:auto}.results-table tr .stat-item{font-weight:400;font-size:.75rem;color:#888}.results-table tr .cell-actions .action{cursor:pointer}.results-table tr .cell table{width:100%;border-collapse:collapse;margin:1rem 0}.results-table tr .cell table th,.results-table tr .cell table td{border:1px solid var(--border-color);padding:.5rem;text-align:left}.results-table tr .cell table th{background-color:var(--header-background-color);font-weight:700}.results-table tr .cell table tr:nth-child(2n){background-color:var(--row-background-color)}.results-table tr .cell table tr:hover{background-color:var(--hover-background-color)}.results-table th .output-header{display:flex;flex-direction:column;height:100%;align-items:flex-start}.results-table th .output-header .pills{display:flex;flex-wrap:wrap;gap:.25rem;align-items:center;margin-bottom:.5rem}.results-table th .prompt-container{font-weight:700;margin-bottom:.5rem}.results-table th .prompt-container>*{display:inline}.results-table th .provider{display:inline-block;padding:.25rem .5rem;background-color:var(--neutral-background-color);border:1px solid var(--border-color);border-radius:4px;margin-right:.25rem}.results-table th .summary{font-weight:400}.results-table th .prompt-detail{display:flex;flex-wrap:wrap;column-gap:.5rem;row-gap:.25rem;font-size:.75rem;color:#888;margin-top:auto}.results-table th .summary .highlight{padding:.25rem .5rem;border-radius:4px;background-color:var(--fail-background-color);border:1px solid var(--border-color)}.results-table th .summary .highlight.success{background-color:var(--success-background-color);border:1px solid var(--pass-color)}.results-table .status{display:flex;flex-direction:column;gap:.25rem;font-weight:700;margin-bottom:.5rem}.results-table .status .pill{display:inline-block;padding:.25rem .5rem;border-radius:4px;margin-right:.25rem;align-self:flex-start}.results-table .pass .pill{background-color:var(--success-background-color);color:var(--pass-color);border:1px solid var(--pass-color)}.results-table .fail .pill{border:1px solid var(--fail-color)}.results-table .fail{color:var(--fail-color)}.fail-reason{color:var(--fail-color);font-weight:700}.compact .fail-reason{display:inline}.results-table .fail .pill{background-color:var(--fail-background-color)}.results-table td .score{font-weight:400}.results-table .comment{margin-top:.5rem;padding:.25rem .5rem;border-radius:4px;background-color:var(--neutral-background-color);font-style:italic;cursor:pointer}.results-table td.first-prompt-col{border-left:2px solid #888}.results-table td.first-prompt-row{border-top:2px solid #888}.search-highlight{color:var(--search-text-color);background-color:var(--search-highlight-color)}.results-table tr .cell .lightbox{position:fixed;top:0;left:0;right:0;bottom:0;background-color:#000000b3;display:flex;align-items:center;justify-content:center;z-index:1000}.results-table tr .cell .lightbox img{max-width:90%;max-height:90%;cursor:zoom-out}.resizer{position:absolute;right:0;top:0;height:100%;width:5px;cursor:col-resize;-webkit-user-select:none;user-select:none;touch-action:none;background:var(--text-color);opacity:.5}.resizer.isResizing{background:var(--text-color);opacity:1}@media (hover: hover){.resizer{opacity:0}*:hover>.resizer{opacity:1}}.results-table thead.sticky{position:sticky;top:0;z-index:100;transition:transform .2s ease-out}[data-theme=dark] .results-table thead.sticky{background:#1a1a1a}.header-dismiss{position:absolute;top:8px;right:8px;cursor:pointer;z-index:101;padding:4px;border-radius:4px;background:#eee;display:none}[data-theme=dark] .header-dismiss{background:#333}.header-dismiss:hover{background:#ddd}[data-theme=dark] .header-dismiss:hover{background:#444}thead.collapsed .header-dismiss{display:block}.results-table thead.collapsed .prompt-detail,.results-table thead.collapsed .custom-metric-container{display:none}.results-table thead.collapsed .MuiFormControlLabel-root{margin-top:-8px}.results-table{border-collapse:separate;border-spacing:0}.results-table thead.collapsed th{padding-top:4px;padding-bottom:4px}.results-table thead th{transition:padding .2s ease-out}.results-table thead .output-header{transition:max-height .2s ease-out}.results-table thead.collapsed{border-bottom:2px solid var(--border-color);box-shadow:0 2px 4px #0000001a}.results-table th{background:#fff;box-shadow:0 1px 2px #0000001a}[data-theme=dark] .results-table th{background:#1a1a1a}.lightbox{position:fixed;top:0;left:0;width:100%;height:100%;background:#000c;display:flex;justify-content:center;align-items:center;z-index:1000;cursor:pointer}.lightbox img{max-width:90%;max-height:90%;object-fit:contain}.error-pill{cursor:pointer}.description{cursor:pointer;transition:background-color .3s ease}.description:hover{background-color:#f0f0f0}[data-theme=dark] .description:hover{background-color:#2a2a2a}.eval-header{display:flex;align-items:center;flex-grow:1}.eval-header strong{font-weight:500}body{background-color:var(--background-color);color:var(--text-color)}.notice{display:flex;flex-direction:column;gap:1.5rem;justify-content:center;align-items:center;height:9rem}.framework-compliance-card{transition:box-shadow .3s ease-in-out;border-radius:12px;overflow:hidden;background-color:#f5f5f5}.framework-compliance-card:hover{box-shadow:0 8px 16px #0000001a}.compliance-summary{text-align:center;margin-bottom:32px;padding:24px;background-color:#fff;border-radius:8px;box-shadow:0 2px 4px #0000000d}.framework-grid{margin-top:24px}.framework-item{height:100%;transition:transform .3s ease,box-shadow .3s ease}.framework-item:hover{box-shadow:0 4px 8px #0000001a}.framework-item.compliant{background-color:#e8f5e9}.framework-item.non-compliant{background-color:#ffebee}.icon-compliant{color:#4caf50;font-size:24px}.icon-non-compliant{color:#f44336;font-size:24px}[data-theme=dark] .framework-compliance-card{background-color:#1e1e1e}[data-theme=dark] .compliance-summary{background-color:#2a2a2a}[data-theme=dark] .framework-item.compliant{background-color:#4caf501a}[data-theme=dark] .framework-item.non-compliant{background-color:#f443361a}[data-theme=dark] .framework-compliance-card:hover,[data-theme=dark] .framework-item:hover{box-shadow:0 8px 16px #ffffff1a}.framework-item .MuiList-root,.framework-item .MuiListItem-root{padding-top:0;padding-bottom:0}.framework-item .MuiListItemIcon-root{min-width:24px}.framework-item .MuiListItemText-root{margin-top:0;margin-bottom:0}.severity-card{transition:transform .3s ease-in-out,box-shadow .3s ease-in-out}.severity-card:hover{transform:translateY(-5px);box-shadow:0 8px 16px #0000001a;cursor:pointer}[data-theme=dark] .severity-card:hover{box-shadow:none}.card-critical{border-left:5px solid #ff1744}.card-high{border-left:5px solid #ff9100}.card-medium{border-left:5px solid #ffc400}.card-low{border-left:5px solid #00e676}.risk-category-drawer .MuiListItem-root.failure-item{border:1px solid #e0e0e0;border-radius:8px;margin-bottom:16px;padding:16px;transition:all .3s ease;box-shadow:0 2px 4px #0000000d}.risk-category-drawer .MuiListItem-root.failure-item:hover{border-color:#bdbdbd;box-shadow:0 4px 8px #0000001a}.risk-category-drawer .prompt{font-weight:500;margin-bottom:8px;word-break:break-word;max-width:100%;overflow-wrap:break-all}.risk-category-drawer .output{color:#555;white-space:pre-wrap;word-break:break-word;max-height:100px;overflow-y:auto;overflow-wrap:break-all;background-color:#f5f5f5;padding:8px;border-radius:4px}.risk-category-drawer .failed-tests-header{margin-top:8px;margin-bottom:8px;font-weight:500;border-top:2px solid #e0e0e0;padding-top:1.5rem}[data-theme=dark] .risk-category-drawer .MuiListItem-root.failure-item{border-color:#424242;background-color:#2c2c2c;box-shadow:0 2px 4px #0003}[data-theme=dark] .risk-category-drawer .MuiListItem-root.failure-item:hover{border-color:#616161;box-shadow:0 4px 8px #0000004d}[data-theme=dark] .risk-category-drawer .prompt{color:#e0e0e0}[data-theme=dark] .risk-category-drawer .output{color:#b0b0b0;background-color:#1e1e1e}[data-theme=dark] .risk-category-drawer .failed-tests-header{color:#e0e0e0;border-top-color:#424242}.risk-card-container{padding-top:3rem;padding-bottom:3rem}.risk-card-title{font-weight:700}.risk-card-progress{margin-bottom:1rem}.risk-card-issues{color:red}.risk-card-list-item{padding:0;transition:background-color .3s,box-shadow .3s}.risk-card-list-item:hover{background-color:#f0f8ff;box-shadow:0 0 0 1px #add8e6;border-radius:4px}[data-theme=dark] .risk-card-list-item:hover{background-color:#2a2a2a;box-shadow:0 0 0 1px #555;border-radius:4px}.risk-card-icon-passed{color:green;font-size:16px}.risk-card-icon-failed{color:red;font-size:16px}.risk-card-icon-no-tests{color:#888;font-size:16px}.risk-card-percentage{margin-left:8px;font-weight:700}.risk-card-percentage-high{color:#4caf50}.risk-card-percentage-medium{color:#ff9800}.risk-card-percentage-low{color:#f44336}[data-theme=dark] .risk-card-percentage-high{color:#81c784}[data-theme=dark] .risk-card-percentage-medium{color:#ffb74d}[data-theme=dark] .risk-card-percentage-low{color:#e57373}.strategy-stats-card{border-radius:.75rem}div.strategy-stats-content{padding:2rem}.strategy-grid{display:grid;grid-template-columns:repeat(2,1fr);gap:1.5rem}.strategy-item{border:1px solid #eee;border-radius:.5rem;padding:1rem;height:100%;transition:background-color .2s ease;border-radius:4px;padding:16px}.strategy-item:hover{background-color:#0000000a}[data-theme=dark] .strategy-item{border:1px solid #424242}.strategy-name{font-weight:500;margin-bottom:.25rem}.strategy-description{margin-bottom:.75rem}.progress-container{margin-bottom:.5rem}.fail-rate{text-align:right}.attack-stats{display:block;text-align:right}.pass-high{color:green!important}.pass-medium{color:#cb8503!important}.pass-low{color:red!important}.vuln-critical{color:red!important;font-weight:700!important}.vuln-high{color:red!important}.vuln-medium{color:#cb8503!important}.vuln-low{color:green!important}.report-header{padding:24px;border-radius:12px;box-shadow:0 4px 6px #0000001a}[data-theme=dark] .report-header{box-shadow:none}.report-details{display:flex;flex-wrap:wrap;gap:12px}.report-details .MuiChip-root{font-size:.875rem}.page-content{padding:0;margin-top:-15px}:root{font-family:Inter,system-ui,Avenir,Helvetica,Arial,sans-serif;font-style:normal;font-weight-normal:400;font-weight-bold:700;font-synthesis:none;text-rendering:optimizeLegibility;-webkit-font-smoothing:antialiased;-moz-osx-font-smoothing:grayscale;-webkit-text-size-adjust:100%;--background-color: #f5f5f5;--text-color: #404040;--link-color: #2e6585;--border-color: lightgray;--table-border-color: lightgray;--pass-color: green;--fail-color: #ad0000;--success-background-color: #d1ffd7;--fail-background-color: #ffd1d1;--neutral-background-color: #eee;--variable-background-color: #f7f7f7;--header-background-color: #fffdf7;--insert-highlight-color: #d4fcbc;--delete-highlight-color: #fbb6c2;--prompt-highlight-color: linen;--textarea-background-color: #ffffff;--textarea-color: #404040;--search-highlight-color: #ffff00;--search-text-color: inherit}[data-theme=dark]{--background-color: #1a1a1a;--text-color: #f0f0f0;--link-color: #6fcaff;--border-color: #444444;--table-border-color: #444444;--pass-color: #b1e9b3;--fail-color: #ee726a;--success-background-color: #216d2b;--fail-background-color: #6d2121;--neutral-background-color: #424242;--variable-background-color: #333;--header-background-color: #333;--insert-highlight-color: #4f8a34;--delete-highlight-color: #8a3434;--prompt-highlight-color: #67605a;--textarea-background-color: #2d2d2d;--textarea-color: #fff;--search-highlight-color: #ffff00;--search-text-color: #404040}html{font-size:16px;background-color:var(--background-color);color:var(--text-color)}body{margin:0}a{color:var(--link-color);text-decoration:none}a:hover{text-decoration:underline}textarea{background-color:var(--textarea-background-color);color:var(--textarea-color);padding:.5em;border:1px solid var(--border-color);border-radius:.25em;resize:vertical}*{box-sizing:border-box}
+.nav{padding:.25rem 0 .25rem 1rem;gap:1rem;background-color:#333;margin-bottom:1rem;box-shadow:0 4px 6px #0000001a}[data-theme=dark] .nav{background-color:#121212}.nav a{text-decoration:none;align-self:center}@media (max-width: 760px){.nav{font-size:.75rem}}.nav .active{font-weight:700}.nav a{color:#f0f0f0}.nav .right-aligned{display:flex;align-items:center;gap:1rem;margin-left:auto;margin-right:.5rem}.nav a:hover{text-decoration:underline}.nav a:hover{color:#ddd}.prompt-var-highlight{background-color:var(--prompt-highlight-color);padding:.25rem;border-radius:4px}.glowing-border{border:1px solid #5cb3ff;box-shadow:0 0 8px 2px #5cb3ff}code[class*=language-],pre[class*=language-]{color:#000;background:none;text-shadow:0 1px white;font-family:Consolas,Monaco,Andale Mono,Ubuntu Mono,monospace;font-size:1em;text-align:left;white-space:pre;word-spacing:normal;word-break:normal;word-wrap:normal;line-height:1.5;-moz-tab-size:4;-o-tab-size:4;tab-size:4;-webkit-hyphens:none;-moz-hyphens:none;-ms-hyphens:none;hyphens:none}pre[class*=language-]::-moz-selection,pre[class*=language-] ::-moz-selection,code[class*=language-]::-moz-selection,code[class*=language-] ::-moz-selection{text-shadow:none;background:#b3d4fc}pre[class*=language-]::selection,pre[class*=language-] ::selection,code[class*=language-]::selection,code[class*=language-] ::selection{text-shadow:none;background:#b3d4fc}@media print{code[class*=language-],pre[class*=language-]{text-shadow:none}}pre[class*=language-]{padding:1em;margin:.5em 0;overflow:auto}:not(pre)>code[class*=language-],pre[class*=language-]{background:#f5f2f0}:not(pre)>code[class*=language-]{padding:.1em;border-radius:.3em;white-space:normal}.token.comment,.token.prolog,.token.doctype,.token.cdata{color:#708090}.token.punctuation{color:#999}.token.namespace{opacity:.7}.token.property,.token.tag,.token.boolean,.token.number,.token.constant,.token.symbol,.token.deleted{color:#905}.token.selector,.token.attr-name,.token.string,.token.char,.token.builtin,.token.inserted{color:#690}.token.operator,.token.entity,.token.url,.language-css .token.string,.style .token.string{color:#9a6e3a;background:#ffffff80}.token.atrule,.token.attr-value,.token.keyword{color:#07a}.token.function,.token.class-name{color:#dd4a68}.token.regex,.token.important,.token.variable{color:#e90}.token.important,.token.bold{font-weight:700}.token.italic{font-style:italic}.token.entity{cursor:help}.yaml-config{font-size:10px}.custom-metric-container{display:inline-flex;flex-wrap:wrap;gap:.25rem;font-weight:400}.custom-metric-container>span{padding:.25rem .5rem;border-radius:4px;color:var(--text-color);border:1px solid var(--border-color);margin-right:.25rem}.custom-metric-container>span.clickable{cursor:pointer}.custom-metric-container>span.clickable:hover{border-color:var(--link-color)}.fail-reason-carousel-controls{float:right;color:var(--text-color);font-weight:400}pre{white-space:pre-wrap}.font-bold{font-weight:700}table.results-table,.divTable{border-collapse:collapse;width:100%;margin:1rem 0;background-color:#fff}[data-theme=dark] table.results-table,[data-theme=dark] .divTable{background-color:#1a1a1a}.results-table ins{background-color:var(--insert-highlight-color);text-decoration:none}.results-table del{background-color:var(--delete-highlight-color);text-decoration:strikethrough}.tr{display:flex}.results-table tr,.tr{width:fit-content}.results-table tr:hover,.tr:hover{background-color:#00000005}.results-table th,.th,.results-table td,.td{position:relative;border:1px solid var(--border-color);vertical-align:top}.compact.results-table th,.compact .th,.compact.results-table td,.compact .td{padding:.5rem}.results-table th.variable,.th.variable,.results-table td.variable,.td.variable{background-color:var(--variable-background-color)}.variable .cell{max-height:100%;overflow-y:auto}.results-table tr.header{background-color:var(--header-background-color)}.results-table th,.th{padding:1rem;position:relative;vertical-align:bottom;text-align:left;white-space:pre-wrap;font-weight:400}.results-table th .action{cursor:pointer;margin-left:.5rem}.results-table th .action svg{vertical-align:middle}.results-table td,.results-table th{height:1px}@-moz-document url-prefix(){.results-table td,.results-table th{height:100%}}.firefox-fix{display:table;height:100%}.results-table tr .cell{display:flex;flex-direction:column;white-space:pre-wrap;height:100%;padding:1rem}.results-table tr .cell img{max-width:var(--max-image-width, 256px);max-height:var(--max-image-height, 256px);cursor:zoom-in}.results-table tr .cell .prompt{background-color:var(--variable-background-color);border:1px solid var(--border-color);padding:1rem;border-radius:4px;margin-bottom:.5rem;font-family:Courier New,Courier,monospace;font-size:.8rem}.results-table tr .cell .prompt .pill{display:block;background-color:var(--neutral-background-color);border:1px solid var(--border-color);border-radius:4px;padding:.25rem;width:fit-content;margin-bottom:.5rem}.results-table tr .cell-actions{display:flex;gap:.5rem;visibility:hidden;position:absolute;top:1.25rem;right:.75rem;line-height:0;font-size:1.25rem}.results-table .first-prompt-col:hover .cell-actions,.results-table .second-prompt-column:hover .cell-actions{visibility:visible}.results-table tr .cell-detail{display:flex;flex-wrap:wrap;column-gap:.5rem;row-gap:.25rem;padding-top:1rem;margin-top:auto}.results-table tr .stat-item{font-weight:400;font-size:.75rem;color:#888}.results-table tr .cell-actions .action{cursor:pointer}.results-table tr .cell table{width:100%;border-collapse:collapse;margin:1rem 0}.results-table tr .cell table th,.results-table tr .cell table td{border:1px solid var(--border-color);padding:.5rem;text-align:left}.results-table tr .cell table th{background-color:var(--header-background-color);font-weight:700}.results-table tr .cell table tr:nth-child(2n){background-color:var(--row-background-color)}.results-table tr .cell table tr:hover{background-color:var(--hover-background-color)}.results-table th .output-header{display:flex;flex-direction:column;height:100%;align-items:flex-start}.results-table th .output-header .pills{display:flex;flex-wrap:wrap;gap:.25rem;align-items:center;margin-bottom:.5rem}.results-table th .prompt-container{font-weight:700;margin-bottom:.5rem}.results-table th .prompt-container>*{display:inline}.results-table th .provider{display:inline-block;padding:.25rem .5rem;background-color:var(--neutral-background-color);border:1px solid var(--border-color);border-radius:4px;margin-right:.25rem}.results-table th .summary{font-weight:400}.results-table th .prompt-detail{display:flex;flex-wrap:wrap;column-gap:.5rem;row-gap:.25rem;font-size:.75rem;color:#888;margin-top:auto}.results-table th .summary .highlight{padding:.25rem .5rem;border-radius:4px;background-color:var(--fail-background-color);border:1px solid var(--border-color)}.results-table th .summary .highlight.success{background-color:var(--success-background-color);border:1px solid var(--pass-color)}.results-table .status{display:flex;flex-direction:column;gap:.25rem;font-weight:700;margin-bottom:.5rem}.results-table .status .pill{display:inline-block;padding:.25rem .5rem;border-radius:4px;margin-right:.25rem;align-self:flex-start}.results-table .pass .pill{background-color:var(--success-background-color);color:var(--pass-color);border:1px solid var(--pass-color)}.results-table .fail .pill{border:1px solid var(--fail-color)}.results-table .fail{color:var(--fail-color)}.fail-reason{color:var(--fail-color);font-weight:700}.compact .fail-reason{display:inline}.results-table .fail .pill{background-color:var(--fail-background-color)}.results-table td .score{font-weight:400}.results-table .comment{margin-top:.5rem;padding:.25rem .5rem;border-radius:4px;background-color:var(--neutral-background-color);font-style:italic;cursor:pointer}.results-table td.first-prompt-col{border-left:2px solid #888}.results-table td.first-prompt-row{border-top:2px solid #888}.search-highlight{color:var(--search-text-color);background-color:var(--search-highlight-color)}.results-table tr .cell .lightbox{position:fixed;top:0;left:0;right:0;bottom:0;background-color:#000000b3;display:flex;align-items:center;justify-content:center;z-index:1000}.results-table tr .cell .lightbox img{max-width:90%;max-height:90%;cursor:zoom-out}.resizer{position:absolute;right:0;top:0;height:100%;width:5px;cursor:col-resize;-webkit-user-select:none;user-select:none;touch-action:none;background:var(--text-color);opacity:.5}.resizer.isResizing{background:var(--text-color);opacity:1}@media (hover: hover){.resizer{opacity:0}*:hover>.resizer{opacity:1}}.results-table thead.sticky{position:sticky;top:0;z-index:100;transition:transform .2s ease-out}[data-theme=dark] .results-table thead.sticky{background:#1a1a1a}.header-dismiss{position:absolute;top:8px;right:8px;cursor:pointer;z-index:101;padding:4px;border-radius:4px;background:#eee;display:none}[data-theme=dark] .header-dismiss{background:#333}.header-dismiss:hover{background:#ddd}[data-theme=dark] .header-dismiss:hover{background:#444}thead.collapsed .header-dismiss{display:block}.results-table thead.collapsed .prompt-detail,.results-table thead.collapsed .custom-metric-container{display:none}.results-table thead.collapsed .MuiFormControlLabel-root{margin-top:-8px}.results-table{border-collapse:separate;border-spacing:0}.results-table thead.collapsed th{padding-top:4px;padding-bottom:4px}.results-table thead th{transition:padding .2s ease-out}.results-table thead .output-header{transition:max-height .2s ease-out}.results-table thead.collapsed{border-bottom:2px solid var(--border-color);box-shadow:0 2px 4px #0000001a}.results-table th{background:#fff;box-shadow:0 1px 2px #0000001a}[data-theme=dark] .results-table th{background:#1a1a1a}.lightbox{position:fixed;top:0;left:0;width:100%;height:100%;background:#000c;display:flex;justify-content:center;align-items:center;z-index:1000;cursor:pointer}.lightbox img{max-width:90%;max-height:90%;object-fit:contain}.error-pill{cursor:pointer}.description{cursor:pointer;transition:background-color .3s ease}.description:hover{background-color:#f0f0f0}[data-theme=dark] .description:hover{background-color:#2a2a2a}.eval-header{display:flex;align-items:center;flex-grow:1}.eval-header strong{font-weight:500}body{background-color:var(--background-color);color:var(--text-color)}.notice{display:flex;flex-direction:column;gap:1.5rem;justify-content:center;align-items:center;height:9rem}.framework-compliance-card{transition:box-shadow .3s ease-in-out;border-radius:12px;overflow:hidden;background-color:#f5f5f5}.framework-compliance-card:hover{box-shadow:0 8px 16px #0000001a}.compliance-summary{text-align:center;margin-bottom:32px;padding:24px;background-color:#fff;border-radius:8px;box-shadow:0 2px 4px #0000000d}.framework-grid{margin-top:24px}.framework-item{height:100%;transition:transform .3s ease,box-shadow .3s ease}.framework-item:hover{box-shadow:0 4px 8px #0000001a}.framework-item.compliant{background-color:#e8f5e9}.framework-item.non-compliant{background-color:#ffebee}.icon-compliant{color:#4caf50;font-size:24px}.icon-non-compliant{color:#f44336;font-size:24px}[data-theme=dark] .framework-compliance-card{background-color:#1e1e1e}[data-theme=dark] .compliance-summary{background-color:#2a2a2a}[data-theme=dark] .framework-item.compliant{background-color:#4caf501a}[data-theme=dark] .framework-item.non-compliant{background-color:#f443361a}[data-theme=dark] .framework-compliance-card:hover,[data-theme=dark] .framework-item:hover{box-shadow:0 8px 16px #ffffff1a}.framework-item .MuiList-root,.framework-item .MuiListItem-root{padding-top:0;padding-bottom:0}.framework-item .MuiListItemIcon-root{min-width:24px}.framework-item .MuiListItemText-root{margin-top:0;margin-bottom:0}.severity-card{transition:transform .3s ease-in-out,box-shadow .3s ease-in-out}.severity-card:hover{transform:translateY(-5px);box-shadow:0 8px 16px #0000001a;cursor:pointer}[data-theme=dark] .severity-card:hover{box-shadow:none}.card-critical{border-left:5px solid #ff1744}.card-high{border-left:5px solid #ff9100}.card-medium{border-left:5px solid #ffc400}.card-low{border-left:5px solid #00e676}.risk-category-drawer .MuiListItem-root.failure-item{border:1px solid #e0e0e0;border-radius:8px;margin-bottom:16px;padding:16px;transition:all .3s ease;box-shadow:0 2px 4px #0000000d}.risk-category-drawer .MuiListItem-root.failure-item:hover{border-color:#bdbdbd;box-shadow:0 4px 8px #0000001a}.risk-category-drawer .prompt{font-weight:500;margin-bottom:8px;word-break:break-word;max-width:100%;overflow-wrap:break-all}.risk-category-drawer .output{color:#555;white-space:pre-wrap;word-break:break-word;max-height:100px;overflow-y:auto;overflow-wrap:break-all;background-color:#f5f5f5;padding:8px;border-radius:4px}.risk-category-drawer .failed-tests-header{margin-top:8px;margin-bottom:8px;font-weight:500;border-top:2px solid #e0e0e0;padding-top:1.5rem}[data-theme=dark] .risk-category-drawer .MuiListItem-root.failure-item{border-color:#424242;background-color:#2c2c2c;box-shadow:0 2px 4px #0003}[data-theme=dark] .risk-category-drawer .MuiListItem-root.failure-item:hover{border-color:#616161;box-shadow:0 4px 8px #0000004d}[data-theme=dark] .risk-category-drawer .prompt{color:#e0e0e0}[data-theme=dark] .risk-category-drawer .output{color:#b0b0b0;background-color:#1e1e1e}[data-theme=dark] .risk-category-drawer .failed-tests-header{color:#e0e0e0;border-top-color:#424242}.risk-card-container{padding-top:3rem;padding-bottom:3rem}.risk-card-title{font-weight:700}.risk-card-progress{margin-bottom:1rem}.risk-card-issues{color:red}.risk-card-list-item{padding:0;transition:background-color .3s,box-shadow .3s}.risk-card-list-item:hover{background-color:#f0f8ff;box-shadow:0 0 0 1px #add8e6;border-radius:4px}[data-theme=dark] .risk-card-list-item:hover{background-color:#2a2a2a;box-shadow:0 0 0 1px #555;border-radius:4px}.risk-card-icon-passed{color:green;font-size:16px}.risk-card-icon-failed{color:red;font-size:16px}.risk-card-icon-no-tests{color:#888;font-size:16px}.risk-card-percentage{margin-left:8px;font-weight:700}.risk-card-percentage-high{color:#4caf50}.risk-card-percentage-medium{color:#ff9800}.risk-card-percentage-low{color:#f44336}[data-theme=dark] .risk-card-percentage-high{color:#81c784}[data-theme=dark] .risk-card-percentage-medium{color:#ffb74d}[data-theme=dark] .risk-card-percentage-low{color:#e57373}.pass-high{color:green!important}.pass-medium{color:#cb8503!important}.pass-low{color:red!important}.vuln-critical{color:red!important;font-weight:700!important}.vuln-high{color:red!important}.vuln-medium{color:#cb8503!important}.vuln-low{color:green!important}.report-header{padding:24px;border-radius:12px;box-shadow:0 4px 6px #0000001a}[data-theme=dark] .report-header{box-shadow:none}.report-details{display:flex;flex-wrap:wrap;gap:12px}.report-details .MuiChip-root{font-size:.875rem}.page-content{padding:0;margin-top:-15px}:root{font-family:Inter,system-ui,Avenir,Helvetica,Arial,sans-serif;font-style:normal;font-weight-normal:400;font-weight-bold:700;font-synthesis:none;text-rendering:optimizeLegibility;-webkit-font-smoothing:antialiased;-moz-osx-font-smoothing:grayscale;-webkit-text-size-adjust:100%;--background-color: #f5f5f5;--text-color: #404040;--link-color: #2e6585;--border-color: lightgray;--table-border-color: lightgray;--pass-color: green;--fail-color: #ad0000;--success-background-color: #d1ffd7;--fail-background-color: #ffd1d1;--neutral-background-color: #eee;--variable-background-color: #f7f7f7;--header-background-color: #fffdf7;--insert-highlight-color: #d4fcbc;--delete-highlight-color: #fbb6c2;--prompt-highlight-color: linen;--textarea-background-color: #ffffff;--textarea-color: #404040;--search-highlight-color: #ffff00;--search-text-color: inherit}[data-theme=dark]{--background-color: #1a1a1a;--text-color: #f0f0f0;--link-color: #6fcaff;--border-color: #444444;--table-border-color: #444444;--pass-color: #b1e9b3;--fail-color: #ee726a;--success-background-color: #216d2b;--fail-background-color: #6d2121;--neutral-background-color: #424242;--variable-background-color: #333;--header-background-color: #333;--insert-highlight-color: #4f8a34;--delete-highlight-color: #8a3434;--prompt-highlight-color: #67605a;--textarea-background-color: #2d2d2d;--textarea-color: #fff;--search-highlight-color: #ffff00;--search-text-color: #404040}html{font-size:16px;background-color:var(--background-color);color:var(--text-color)}body{margin:0}a{color:var(--link-color);text-decoration:none}a:hover{text-decoration:underline}textarea{background-color:var(--textarea-background-color);color:var(--textarea-color);padding:.5em;border:1px solid var(--border-color);border-radius:.25em;resize:vertical}*{box-sizing:border-box}