New page for Chunk flaky test fix

docs/guides/modules/ROOT/nav.adoc

@@ -146,6 +146,7 @@
 *** xref:test:test.adoc[Automated testing]
 *** xref:test:collect-test-data.adoc[Collecting test data]
 *** xref:insights:insights-tests.adoc[Test Insights]
+*** xref:test:fix-flaky-tests.adoc[Fix flaky tests]
 ** Testing strategies
 *** xref:test:testing-llm-enabled-applications-through-evaluations.adoc[Testing LLM-enabled applications through evaluations]
 *** xref:test:browser-testing.adoc[Browser testing]

docs/guides/modules/test/pages/fix-flaky-tests.adoc

@@ -0,0 +1,292 @@
+= Fix flaky tests - Private beta
+:page-platform: Cloud
+:page-description: Learn about Chunk by CircleCI and how it can automatically identify and fix flaky tests in your CI/CD pipelines.
+:experimental:
+
+NOTE: Chunk by CircleCI is currently in private beta. If you would like to join the private beta, sign up link:https://www2.circleci.com/chunk-waitlist[here for the waiting list, window=_blank]. There are no extra costs during beta, Chunk uses credits and your AI provider token. Chunk tasks will be a paid feature after the beta.
+
+Use Chunk by CircleCI to automatically identify and present resolutions to flaky tests in your CI/CD pipelines.
+
+Chunk provides automated capabilities to identify and resolve common issues in your CI/CD pipelines. Chunk can automatically detect flaky tests and generate fixes to help you reduce the time spent debugging intermittent failures.
+
+TIP: Chunk by CircleCI is an AI agent that you can choose to set up in your organization to help with CI/CD related tasks.
+
+== Introduction
+
+Flaky tests are tests that pass and fail inconsistently. Flaky tests create uncertainty about code quality and slow down development workflows. Chunk can help address the problem of flaky tests by using artificial intelligence to analyze test patterns, identify root causes of flakiness, and propose validated solutions.
+
+Chunk integrates with your existing CircleCI workflows and GitHub repositories. When configured, Chunk tasks run automatically on a schedule you define to monitor your test suite for signs of flakiness. When issues are detected, Chunk goes through the following steps:
+
+* Generate potential fixes.
+* Validate fixes through multiple test runs in an isolated environment.
+* Create pull requests with recommended changes after successful validation.
+
+== Set up Chunk and assign a task
+
+To get started with automating flaky test fixes, you need to fulfill the following prerequisites and complete several setup steps to get Chunk set up in your organization. You can then assign tasks for Chunk to run.
+
+=== Prerequisites
+
+* You will need an API key from either link:https://console.anthropic.com/settings/keys[Anthropic, window=_blank] or link:https://auth.openai.com/log-in[OpenAI, window=_blank] for Chunk to process and generate fixes. Your source code is not stored nor used for training purposes by CircleCI. If you are using OpenAI you should also check the following:
+** Make sure your organization link:https://help.openai.com/en/articles/10910291-api-organization-verification#h_c6efff0719[has gpt-5 model access, window=_blank].
+** Verify your organization. For guidance see the link:https://help.openai.com/en/articles/10910291-api-organization-verification[OpenAI help, window=_blank]. If you cannot get your OpenAI organization verified, see the troubleshooting item <<i-cannot-get-my-openai-organization-verified>>.
+* Ensure your CircleCI jobs store test results using the `store_test_results` step. Read more about this step in the xref:reference:ROOT:configuration-reference.adoc#storetestresults[configuration reference].
+* Ensure you have the CircleCI GitHub app installed in your GitHub organization. Check menu:Organization Settings[VCS Connections], where you can see if you have the App already installed, or select btn:[Install GitHub App]. Chunk needs the GitHub App to be installed to be able to recommend fixes and open pull requests.
+* Make sure you are following the projects you want Chunk to fix. CircleCI identifies flaky tests in your CI/CD pipelines on the *Tests* tab for workflows in the Insights dashboard (menu:Insights[Select project > Select workflow > Tests]).
+
+=== Setup
+
+. In the link:https://app.circleci.com/home[CircleCI web app, window=_blank], select your organization and then select *Chunk Tasks* from the sidebar.
+. Select btn:[Get started] and then btn:[Continue] when prompted.
+. If you followed the prerequisites, you should see a image:guides:ROOT:icons/passed.svg[passed icon, role="no-border"] to indicate you already have the GitHub App installed for your organization. If not use the btn:[Install CircleCI GitHub App] button to install it.
+. Select your AI Model provider (Anthropic or OpenAI).
+. Enter your API key for your chosen model provider.
+. Select btn:[Next] to complete the setup.
+
+image::guides:ROOT:chunk/set-up-chunk.png[Chunk setup modal]
+
+=== Assign a task
+
+Once you have Chunk set up for your organization you can start assigning tasks.
+
+To set up a "Fix flaky tests" task follow these steps:
+
+. Select the project you want to assign the task to.
+. Choose a run frequency (daily, weekly, monthly).
+. Choose the number of tests you want Chunk to try to fix per run, between one and three.
+. Choose a maximum for the number of solutions you want Chunk to try for each test, between one and three.
+. Choose a number of validation runs to allow per test between one and 20.
+. Choose a maximum number of concurrent open PRs for flaky test fixes. You can choose between one and 20, or the default, "Unlimited".
+. The "Chunk environment setup" section is there to guide you to set up a `cci-agent-setup.yml` if you would like to control the environment in which Chunk runs your tests. For more information see <<chunk-environment-setup>>. This step is optional.
+. The "Post-run commands" section gives you the option to add commands for Chunk to run after each test run. This step is optional.
+. Select btn:[Start task] to complete the setup.
+
+When you select btn:[Start task] Chunk starts running immediately and follows the schedule you set up.
+
+image::guides:ROOT:chunk/assign-task.png[Chunk assign task modal]
+
+=== Chunk environment setup
+
+To improve verification success, create an "agent environment" CircleCI YAML file. Copy the environment setup parts of your existing CircleCI configuration into a dedicated file for Chunk.
+
+* Name the file `cci-agent-setup.yml` and save it to your `.circleci` directory on your default branch.
+* `cci-agent-setup.yml` needs to include a single workflow (the name of the workflow can be anything you want) with a single job named `cci-agent-setup`. The `cci-agent-setup` job needs to set up your environment for Chunk to use. You do not need to include any steps to run tests, this is purely for environment setup.
++
+.Example config file for cci-agent-setup.yml
+[source,yaml]
+----
+version: 2.1
+workflows:
+  main:
+    jobs:
+      - cci-agent-setup
+jobs:
+  cci-agent-setup:
+    docker:
+    - image: cimg/python:3.12
+    - image: cimg/postgres:15.3
+    steps:
+      - checkout
+      - run:
+          name: Hello World
+          command: |
+            echo "Hello, World!"
+      # insert more environment setup here
+----
+
+
+== How Chunk by CircleCI works
+
+Chunk operates through an automated analysis and remediation process that runs independently of your regular CI/CD workflows.
+
+[mermaid]
+----
+flowchart TD
+    Start([Chunk Task Runs on Schedule]) --> Monitor[Monitor Test Results in CircleCI]
+    Monitor --> Analyze[Analyze Historical Test Data]
+    Analyze --> Detect{Detect Flaky<br/>Test Patterns?}
+
+    Detect -->|No flaky tests found| End1([Task Complete])
+    Detect -->|Flaky tests identified| Select[Select Tests to Fix<br/>Based on Task Config]
+
+    Select --> Generate[Generate Potential Solutions<br/>Based on Failure Patterns]
+    Generate --> Solutions{Multiple<br/>Solutions<br/>Configured?}
+
+    Solutions -->|Yes| CreateMultiple[Create Multiple Fix Approaches]
+    Solutions -->|No| CreateSingle[Create Single Fix Approach]
+
+    CreateMultiple --> TrySolution[Try Solution Approach]
+    CreateSingle --> TrySolution
+
+    TrySolution --> Validate[Validate Fix in Isolated Environment]
+    Validate --> RunTests[Run Test Multiple Times<br/>Per Validation Config]
+
+    RunTests --> CheckValidation{Validation<br/>Successful?}
+
+    CheckValidation -->|No| MoreSolutions{More Solutions<br/>to Try?}
+    MoreSolutions -->|Yes| TrySolution
+    MoreSolutions -->|No| CreatePRFailed[Create PR with<br/>Failed Validation Status]
+    CreatePRFailed --> CheckMore{More Tests<br/>to Fix?}
+
+    CheckValidation -->|Yes| CheckPRLimit{Under PR<br/>Limit?}
+    CheckPRLimit -->|No| Queue[Queue Fix for Later]
+    CheckPRLimit -->|Yes| CreatePR[Create Pull Request<br/>with Validated Fix]
+
+    CreatePR --> AddDetails[Include Code Diff,<br/>Analysis & Logs]
+    AddDetails --> CheckMore
+    Queue --> CheckMore
+
+    CheckMore -->|Yes| Select
+    CheckMore -->|No| End2([Task Complete])
+
+    style Start fill:#e1f5ff
+    style End1 fill:#d4edda
+    style End2 fill:#d4edda
+    style Detect fill:#fff3cd
+    style CheckValidation fill:#fff3cd
+    style CheckPRLimit fill:#fff3cd
+    style CreatePR fill:#d4edda
+    style CreatePRFailed fill:#f8d7da
+----
+
+=== Test analysis and detection
+
+Chunk continuously monitors test results stored in CircleCI to identify patterns of flakiness. It analyzes historical test data to distinguish between genuine failures caused by code issues and intermittent failures that indicate flaky behavior. Tests are flagged as flaky when they show inconsistent pass/fail patterns across multiple runs with the same code.
+
+The detection process considers factors such as failure frequency, timing patterns, and error message consistency. This helps Chunk focus on tests that genuinely exhibit flaky behavior rather than tests that fail consistently due to code problems.
+
+=== Solution generation
+
+When a flaky test is identified, Chunk generates potential solutions based on common flaky test patterns and best practices. Chunk can create multiple solution approaches for each test, allowing it to try different fixes if the first attempt does not resolve the issue.
+
+Solutions may include adding explicit waits, improving element selectors, handling race conditions, or stabilizing test data setup. Chunk tailors its recommendations to the specific failure patterns observed in your test.
+
+=== Validation process
+
+Before proposing any changes, Chunk validates potential solutions through multiple test runs in an isolated environment. This validation process ensures that proposed fixes actually resolve the flakiness without breaking existing functionality. Chunk runs the modified test multiple times to confirm consistent passing behavior.
+
+=== Pull request creation
+
+When Chunk has created a solution, it automatically creates a pull request in your GitHub repository. Each pull request includes detailed information about the changes made and the reasoning behind them. Pull requests will also include details of the validation process and the outcome of validation tests. If validation was not successful, this will be explicitly stated in the pull request to alert you to the need for manual validation.
+
+Pull requests contain code diffs showing what changes Chunk recommends, along with logs that explain Chunk's analysis and decision-making process. This transparency allows your team to understand and review the proposed fixes before merging.
+
+== The Chunk tasks dashboard
+
+Once you have set up some Chunk tasks, you can view an activity timeline on the Chunk tasks dashboard.
+
+image::guides:ROOT:chunk/chunk-tasks-dashboard.png[Chunk tasks dashboard]
+
+Once a fix is available the row is marked as "PR opened". Select a row to view the task overview. This includes the following information:
+
+* Summary of the fix
+* Root cause of the flakiness
+* Details of the proposed fix
+* Details of the level of verification achieved
+
+You also get a code diff of the proposed fix along with logs of the decision process presented as a conversation between "User" (Chunk) and "Assistant" (AI model provider). The diff and logs are designed to help you understand Chunk's reasoning and analysis process.
+
+== Flaky test fix configuration options
+
+The following table shows the configuration options available when setting up Chunk:
+
+.Chunk configuration options
+[cols=3*]
+|===
+|Setting |Description |Default
+
+|Run frequency
+|How often Chunk analyzes and fixes flaky tests
+a|* Daily (Sunday through Thursday at 22:00 UTC )
+* Weekly every Sunday at 22:00 UTC (default)
+* Monthly on the first day of the month at 22:00 UTC
+
+|Maximum tests to fix per run
+|Limits the number of tests Chunk will attempt to fix in a single execution.
+| 1, 2, 3 (default)
+
+|Number of solutions to try per test
+|How many different fix approaches Chunk will generate for each flaky test.
+|1 (default), 2, 3
+
+|Number of validation runs per test
+|How many times Chunk runs a test to validate that a fix works consistently.
+|1-20. 10 is the default.
+
+|Maximum concurrent open PRs
+|Limits the number of pull requests Chunk can have open at one time.
+|1-20 or "Unlimited" (default).
+|===
+
+== Limitations
+
+*It is not possible to edit the Chunk task configurations*. You cannot directly edit setup scripts or post-run commands once a Chunk task is created. To modify these settings, you must delete the existing Chunk task and create a new one.
+
+== Troubleshooting
+
+=== Unable to run verification tests
+
+Chunk runs in a xref:execution-managed:using-linuxvm.adoc[Linux VM] with link:https://discuss.circleci.com/t/ubuntu-20-04-22-04-24-04-q4-edge-release/52429[basic software installed by default, window=_blank]. To verify that a proposed fix resolves flakiness, it re-runs the affected test several times. To do this, Chunk may install additional software needed to set up the test environment, using clues from your CircleCI configuration file  to determine how to run the tests.
+
+View attempts in the CircleCI web app as follows:
+
+. Open the Chunk task from the timeline.
+. Select *Task logs*.
+. Select the btn:[Expand All] option, then search for `attempt`. This will take you to the section where Chunk is trying to run the tests.
+
+Consider setting up a `cci-agent-setup.yml` file to control the environment in which Chunk runs your tests. For more information see <<chunk-environment-setup>>.
+
+Also consider including a markdown file, named `claude.md` or `agents.md` at the root of your repository with instructions for running tests. Chunk should pick this up automatically.
+
+
+=== Invalid OpenAI modal specified
+
+If you get the following error:
+
+[source,shell]
+Invalid OpenAI model specified. Please check the model name and ensure it is available for your account.
+
+You will need to make sure your organization has GPT-5 access. To verify this in link:https://platform.openai.com/settings/organization/general[OpenAI Platform, window=_blank], follow these steps:
+
+. Switch to the project you want to check in the top left dropdown.
+. Go to menu:Settings[Limits] in the left-hand menu. This page shows the models and rate limits for your project. `gpt-5` will be listed if you have access.
+
+=== I cannot get my OpenAI organization verified
+
+If organization verification is not possible, you can bypass this requirement by adding an environment variable to your `circleci-agents` context, as follows:
+
+. In the CircleCI web app, go to menu:Organization Settings[Contexts].
+. Use the search to find the `circleci-agents` context. Select it by name to open configuration options.
+. Scroll down to the "Environment variables" section.
+. Select btn:[Add environment variable] to enter the variable name and value.
+** Under "Environment variable name", enter `CCI_AGENT_OPENAI_MODEL`.
+** Under "Value", enter `gtp-5-nano`.
+
+=== Verification required error
+
+If you get the following error inside a Chunk task, this indicates that your Open AI organization verification is pending.
+
+[source,shell]
+OpenAI organization verification required. Please verify your organization at https://platform.openai.com/settings/organization/generaland see our community forum for more debugging help.
+
+To fix this issues, head to link:https://platform.openai.com/settings/organization/general[OpenAI Platform, window=_blank], navigate to menu:General[Organization Settings] and select btn:[Verify Organization]. Then follow the steps to get your organization verified.
+
+=== Action required error
+
+If you get the following error inside a Chunk task, this indicates that your Open AI organization verification is pending.
+
+[source,shell]
+Action required - agent execution error
+The agent ran into an error while executing this task. See our community forum for how to solve this error.
+
+Contact mailto:[email protected][[email protected]] for assistance.
+
+== Frequently asked questions
+
+=== Does CircleCI use my data to train AI models?
+
+No, CircleCI does not store your source code or use it for training purposes. Chunk processes your code temporarily to generate fixes but does not retain or share this information with model providers for training.
+
+=== How long are Chunk's logs stored?
+
+Chunks logs are stored by CircleCI for 90 days. 90 days is a fixed retention period that applies to all organizations, link:https://support.circleci.com/hc/en-us/articles/5645222646939-Cloud-Data-Retention-Policy-and-Settings[regardless of your plan’s standard data retention policy, window=_blank]. After 90 days, logs are automatically deleted to keep your workspace at optimal performance.

styles/config/vocabularies/Docs/accept.txt

@@ -77,6 +77,7 @@ Certbot
 cgroup
 Chocolatey
 chruby
+[Cc]hunk
 CircleCI\b
 \bCircleCI cloud\b
 \bCircleCI server\b