[AI assistant] Add setting to configure default LLM by KDKHD · Pull Request #231940 · elastic/kibana

KDKHD · 2025-08-15T12:35:27Z

Summary

Summarize your PR. If it involves visual changes include a screenshot or gif.

Introduces a new setting in /app/management/ai/genAiSettings that allows users to configure the default LLM. Currently, the setting is disabled since the changes in the assistants still need to be finalised. Once the changes in the assistants are completed, the settings can be made writable.

Warning

When reading the setting genAiSettings:defaultAIConnector and genAiSettings:defaultAIConnectorOnly from uiSettings, you must handle the case where the default connector that is currently set does not exist anymore (because it was deleted). In that case, you should fall back to "No default connector selected".

While we wait for the changes within the assistants, this setting will be disabled:

Access to modify these settings is permissioned by the Management > Advanced Settings in role privileges:

Checklist

Check the PR satisfies following conditions.

Reviewers should verify this PR satisfies this list as well.

Any text added follows EUI's writing guidelines, uses sentence case text and includes i18n support
Documentation was added for features that require explanation or tutorials
Unit or functional tests were updated or added to match the most common scenarios
If a plugin configuration key changed, check if it needs to be allowlisted in the cloud and added to the docker list
This was checked for breaking HTTP API changes, and any breaking changes have been approved by the breaking-change committee. The release_note:breaking label should be applied in these situations.
Flaky Test Runner was used on any tests changed
The PR description includes the appropriate Release Notes section, and the correct release_note:* label is applied per the guidelines
Review the backport guidelines and apply applicable backport:* labels.

Identify risks

Does this PR introduce any risks? For example, consider risks like hard to test bugs, performance regression, potential of data loss.

Describe the risk, its severity, and mitigation for each identified risk. Invite stakeholders and evaluate how to proceed before merging.

See some risk examples
...

KDKHD · 2025-08-18T10:20:41Z

@elasticmachine merge upstream

…no-cache --fix'

kibanamachine · 2025-09-10T18:49:18Z

Friendly reminder: Looks like this PR hasn’t been backported yet.
To create automatically backports add a backport:* label or prevent reminders by adding the backport:skip label.
You can also create backports manually by running node scripts/backport --pr 231940 locally
cc: @KDKHD

KDKHD · 2025-09-11T13:12:18Z

This PR could not be backported; instead, the setting was rebuilt for 9.1, 9.0, 8.19, 8.18 here: #233874

…i features (#234480) ## Summary Summarize your PR. If it involves visual changes include a screenshot or gif. This PR integrates the new [default LLM setting](#231940) with the security solution GenAI features (AI assistant and Attack discovery). The default LLM setting allows admins to configure the preferred AI connector. This PR make sure that this setting is actually respected in the AI assistant and Attack discovery. ### How to test: - Start Kibana locally from this branch - Make sure you have at least 3 LLM connectors configured (can be preconfigured ones). - Go to stack management > advanced settings and switch the following setting to "Security AI assistant in other apps". (This will make testing a little bit easier) <img width="1954" height="133" alt="image" src="https://github.com/user-attachments/assets/12fc4313-b2a5-45f7-bca9-8e0e7ee7f19e" /> - Enable the feature flag by adding the following to kibana.dev.yml: ``` feature_flags.overrides.aiAssistant.defaultLlmSettingEnabled: true ``` - Go to the GenAi Settings page: http://localhost:5601/app/management/ai/genAiSettings - Select a default LLM: <img width="2524" height="775" alt="image" src="https://github.com/user-attachments/assets/d8c51f46-04d2-42bf-871b-735fa3849d30" /> - Save the setting change using the footer at the bottom of the page. - Open the Security AI assistant (if you changed the Assistant visibility setting, you can open the assistant from the GenAi page directly) - Check that the LLM connector for the conversation is the one you configured as the default LLM. Also, verify that you can still change the connector used in your conversation to one of your other connectors. - Change the LLM to a non-default connector for the conversation. - Once you select a non-default connector, chat with the assistant and then start a new conversation, your non-default connector should still be active for the new conversation. - Now back on the GenAi settings page, check the `Disallow all other connectors` checkbox. - Open the AI assistant again and go to the existing conversation that has a few messages inside. - You should see a red banner indicating that a connector needs to be selected. - If you open the connector selector, you should now only see the default LLM you have configured as an option. #### Attack Discovery In attack discovery, you should observe the same behavior. - Go to attack discovery http://localhost:5601/app/security/attack_discovery - Open the manual run config flyout <img width="3081" height="1184" alt="image" src="https://github.com/user-attachments/assets/a5a11f1e-8b0b-40d9-8937-6fe4497cbf10" /> - Verify that only the default LLM is available as the connector: <img width="1698" height="833" alt="image" src="https://github.com/user-attachments/assets/45b68d6c-6f36-487f-ba08-030f41c10545" /> - Go back to the GenAi settings page http://localhost:5601/app/management/ai/genAiSettings and deselect the `Disallow all other connectors` checkbox and select a different default connector. - Go to Attack Discovery and open the manual run config flyout again. - Check that by default, your new default connector is used. Also, verify that you now again have the option of changing the connector to any of the other configured connectors. ### TODO The designs of the connector selector for Attack discovery and the Assistant still need to be implemented. That will be done in a separate PR. ### Checklist Check the PR satisfies following conditions. Reviewers should verify this PR satisfies this list as well. - [X] Any text added follows [EUI's writing guidelines](https://elastic.github.io/eui/#/guidelines/writing), uses sentence case text and includes [i18n support](https://github.com/elastic/kibana/blob/main/src/platform/packages/shared/kbn-i18n/README.md) - [X] [Documentation](https://www.elastic.co/guide/en/kibana/master/development-documentation.html) was added for feaures that require explanation or tutorials - [X] [Unit or functional tests](https://www.elastic.co/guide/en/kibana/master/development-tests.html) were updated or added to match the most common scenarios - [X] If a plugin configuration key changed, check if it needs to be allowlisted in the cloud and added to the [docker list](https://github.com/elastic/kibana/blob/main/src/dev/build/tasks/os_packages/docker_generator/resources/base/bin/kibana-docker) - [X] This was checked for breaking HTTP API changes, and any breaking changes have been approved by the breaking-change committee. The `release_note:breaking` label should be applied in these situations. - [X] [Flaky Test Runner](https://ci-stats.kibana.dev/trigger_flaky_test_runner/1) was used on any tests changed - [X] The PR description includes the appropriate Release Notes section, and the correct `release_note:*` label is applied per the [guidelines](https://www.elastic.co/guide/en/kibana/master/contributing.html#kibana-release-notes-process) - [X] Review the [backport guidelines](https://docs.google.com/document/d/1VyN5k91e5OVumlc0Gb9RPa3h1ewuPE705nRtioPiTvY/edit?usp=sharing) and apply applicable `backport:*` labels. ### Identify risks Does this PR introduce any risks? For example, consider risks like hard to test bugs, performance regression, potential of data loss. Describe the risk, its severity, and mitigation for each identified risk. Invite stakeholders and evaluate how to proceed before merging. - [ ] [See some risk examples](https://github.com/elastic/kibana/blob/main/RISK_MATRIX.mdx) - [ ] ... --------- Co-authored-by: kibanamachine <42973632+kibanamachine@users.noreply.github.com> Co-authored-by: Elastic Machine <elasticmachine@users.noreply.github.com>

…i features (elastic#234480) ## Summary Summarize your PR. If it involves visual changes include a screenshot or gif. This PR integrates the new [default LLM setting](elastic#231940) with the security solution GenAI features (AI assistant and Attack discovery). The default LLM setting allows admins to configure the preferred AI connector. This PR make sure that this setting is actually respected in the AI assistant and Attack discovery. ### How to test: - Start Kibana locally from this branch - Make sure you have at least 3 LLM connectors configured (can be preconfigured ones). - Go to stack management > advanced settings and switch the following setting to "Security AI assistant in other apps". (This will make testing a little bit easier) <img width="1954" height="133" alt="image" src="https://github.com/user-attachments/assets/12fc4313-b2a5-45f7-bca9-8e0e7ee7f19e" /> - Enable the feature flag by adding the following to kibana.dev.yml: ``` feature_flags.overrides.aiAssistant.defaultLlmSettingEnabled: true ``` - Go to the GenAi Settings page: http://localhost:5601/app/management/ai/genAiSettings - Select a default LLM: <img width="2524" height="775" alt="image" src="https://github.com/user-attachments/assets/d8c51f46-04d2-42bf-871b-735fa3849d30" /> - Save the setting change using the footer at the bottom of the page. - Open the Security AI assistant (if you changed the Assistant visibility setting, you can open the assistant from the GenAi page directly) - Check that the LLM connector for the conversation is the one you configured as the default LLM. Also, verify that you can still change the connector used in your conversation to one of your other connectors. - Change the LLM to a non-default connector for the conversation. - Once you select a non-default connector, chat with the assistant and then start a new conversation, your non-default connector should still be active for the new conversation. - Now back on the GenAi settings page, check the `Disallow all other connectors` checkbox. - Open the AI assistant again and go to the existing conversation that has a few messages inside. - You should see a red banner indicating that a connector needs to be selected. - If you open the connector selector, you should now only see the default LLM you have configured as an option. #### Attack Discovery In attack discovery, you should observe the same behavior. - Go to attack discovery http://localhost:5601/app/security/attack_discovery - Open the manual run config flyout <img width="3081" height="1184" alt="image" src="https://github.com/user-attachments/assets/a5a11f1e-8b0b-40d9-8937-6fe4497cbf10" /> - Verify that only the default LLM is available as the connector: <img width="1698" height="833" alt="image" src="https://github.com/user-attachments/assets/45b68d6c-6f36-487f-ba08-030f41c10545" /> - Go back to the GenAi settings page http://localhost:5601/app/management/ai/genAiSettings and deselect the `Disallow all other connectors` checkbox and select a different default connector. - Go to Attack Discovery and open the manual run config flyout again. - Check that by default, your new default connector is used. Also, verify that you now again have the option of changing the connector to any of the other configured connectors. ### TODO The designs of the connector selector for Attack discovery and the Assistant still need to be implemented. That will be done in a separate PR. ### Checklist Check the PR satisfies following conditions. Reviewers should verify this PR satisfies this list as well. - [X] Any text added follows [EUI's writing guidelines](https://elastic.github.io/eui/#/guidelines/writing), uses sentence case text and includes [i18n support](https://github.com/elastic/kibana/blob/main/src/platform/packages/shared/kbn-i18n/README.md) - [X] [Documentation](https://www.elastic.co/guide/en/kibana/master/development-documentation.html) was added for feaures that require explanation or tutorials - [X] [Unit or functional tests](https://www.elastic.co/guide/en/kibana/master/development-tests.html) were updated or added to match the most common scenarios - [X] If a plugin configuration key changed, check if it needs to be allowlisted in the cloud and added to the [docker list](https://github.com/elastic/kibana/blob/main/src/dev/build/tasks/os_packages/docker_generator/resources/base/bin/kibana-docker) - [X] This was checked for breaking HTTP API changes, and any breaking changes have been approved by the breaking-change committee. The `release_note:breaking` label should be applied in these situations. - [X] [Flaky Test Runner](https://ci-stats.kibana.dev/trigger_flaky_test_runner/1) was used on any tests changed - [X] The PR description includes the appropriate Release Notes section, and the correct `release_note:*` label is applied per the [guidelines](https://www.elastic.co/guide/en/kibana/master/contributing.html#kibana-release-notes-process) - [X] Review the [backport guidelines](https://docs.google.com/document/d/1VyN5k91e5OVumlc0Gb9RPa3h1ewuPE705nRtioPiTvY/edit?usp=sharing) and apply applicable `backport:*` labels. ### Identify risks Does this PR introduce any risks? For example, consider risks like hard to test bugs, performance regression, potential of data loss. Describe the risk, its severity, and mitigation for each identified risk. Invite stakeholders and evaluate how to proceed before merging. - [ ] [See some risk examples](https://github.com/elastic/kibana/blob/main/RISK_MATRIX.mdx) - [ ] ... --------- Co-authored-by: kibanamachine <42973632+kibanamachine@users.noreply.github.com> Co-authored-by: Elastic Machine <elasticmachine@users.noreply.github.com> (cherry picked from commit b543b8c) # Conflicts: # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/conversations/conversation_settings/conversation_settings_editor.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/helpers.test.ts # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/helpers.ts # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/settings/assistant_settings_management.test.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/settings/assistant_settings_management.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/settings/search_ai_lake_configurations_settings_management.test.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/connectorland/use_load_connectors/index.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/mock/test_providers/test_providers.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/tsconfig.json # x-pack/platform/plugins/private/gen_ai_settings/public/components/default_ai_connector/default_ai_connector.tsx # x-pack/solutions/security/packages/ecs-data-quality-dashboard/impl/data_quality_panel/mock/test_providers/test_providers.tsx

## Summary Summarize your PR. If it involves visual changes include a screenshot or gif. Follow-up to this change: elastic#231940 The PR linked above could not be backported to 8.18, 9.19, 9.1 because the GenAi settings page where the setting was added to does not exist in the versions just listed. As this setting is needed on these version, this PR is required. This PR adds the Default LLM setting to the Security, Obs & ES AI settings pages. <img width="1855" height="1171" alt="image" src="https://github.com/user-attachments/assets/ab09be60-97b6-40d4-bcfc-5e9859360502" /> <img width="1855" height="1171" alt="image" src="https://github.com/user-attachments/assets/b8c1ae43-e1ee-4f42-bbcb-d7f67be6a598" /> <img width="1855" height="1171" alt="image" src="https://github.com/user-attachments/assets/5647de7f-d1de-4e46-9940-f165b1ef8b7b" /> <img width="1855" height="1171" alt="image" src="https://github.com/user-attachments/assets/791c953e-a321-419c-a121-66974a6f8b34" /> ### How to test: - Enable the feature flag. Add `feature_flags.overrides.aiAssistant.defaultLlmSettingEnabled: true` to kibana.dev.yml - Start Kibana and go to http://localhost:5601/app/management/kibana/securityAiAssistantManagement?tab=connectors or http://localhost:5601/app/management/kibana/observabilityAiAssistantManagement - You should see the `genAiSettings:defaultAIConnector` setting. Changing the setting won't do anything just yet as changes within the assistants still need to be configured. TODO: When the feature flag is lifted, we should remove the following Kibana advanced setting as this one will rpelace it: <img width="2412" height="198" alt="image" src="https://github.com/user-attachments/assets/f3d1c421-f7c5-42b9-b5dc-85c29b8ef3eb" /> ### Checklist Check the PR satisfies following conditions. Reviewers should verify this PR satisfies this list as well. - [X] Any text added follows [EUI's writing guidelines](https://elastic.github.io/eui/#/guidelines/writing), uses sentence case text and includes [i18n support](https://github.com/elastic/kibana/blob/main/src/platform/packages/shared/kbn-i18n/README.md) - [X] [Documentation](https://www.elastic.co/guide/en/kibana/master/development-documentation.html) was added for features that require explanation or tutorials - [X] [Unit or functional tests](https://www.elastic.co/guide/en/kibana/master/development-tests.html) were updated or added to match the most common scenarios - [X] If a plugin configuration key changed, check if it needs to be allowlisted in the cloud and added to the [docker list](https://github.com/elastic/kibana/blob/main/src/dev/build/tasks/os_packages/docker_generator/resources/base/bin/kibana-docker) - [X] This was checked for breaking HTTP API changes, and any breaking changes have been approved by the breaking-change committee. The `release_note:breaking` label should be applied in these situations. - [X] [Flaky Test Runner](https://ci-stats.kibana.dev/trigger_flaky_test_runner/1) was used on any tests changed - [X] The PR description includes the appropriate Release Notes section, and the correct `release_note:*` label is applied per the [guidelines](https://www.elastic.co/guide/en/kibana/master/contributing.html#kibana-release-notes-process) - [X] Review the [backport guidelines](https://docs.google.com/document/d/1VyN5k91e5OVumlc0Gb9RPa3h1ewuPE705nRtioPiTvY/edit?usp=sharing) and apply applicable `backport:*` labels. ### Identify risks Does this PR introduce any risks? For example, consider risks like hard to test bugs, performance regression, potential of data loss. Describe the risk, its severity, and mitigation for each identified risk. Invite stakeholders and evaluate how to proceed before merging. - [ ] [See some risk examples](https://github.com/elastic/kibana/blob/main/RISK_MATRIX.mdx) - [ ] ... --------- Co-authored-by: kibanamachine <42973632+kibanamachine@users.noreply.github.com> Co-authored-by: Elastic Machine <elasticmachine@users.noreply.github.com> (cherry picked from commit 6141299) # Conflicts: # src/platform/packages/shared/kbn-management/settings/setting_ids/index.ts # src/platform/plugins/private/kibana_usage_collection/server/collectors/management/schema.ts # src/platform/plugins/private/kibana_usage_collection/server/collectors/management/types.ts # src/platform/plugins/shared/ai_assistant_management/selection/server/plugin.test.ts # src/platform/plugins/shared/ai_assistant_management/selection/server/plugin.ts # src/platform/plugins/shared/ai_assistant_management/selection/tsconfig.json # src/platform/plugins/shared/telemetry/schema/oss_platform.json # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/settings/assistant_settings_management.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/settings/search_ai_lake_configurations_settings_management.test.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/settings/search_ai_lake_configurations_settings_management.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/connectorland/ai_for_soc_connector_settings_management/index.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/tsconfig.json # x-pack/platform/plugins/private/observability_ai_assistant_management/public/routes/components/settings_tab/settings_tab.test.tsx # x-pack/platform/plugins/private/observability_ai_assistant_management/public/routes/components/settings_tab/ui_settings.tsx # x-pack/platform/plugins/private/observability_ai_assistant_management/tsconfig.json # x-pack/solutions/security/plugins/security_solution/public/assistant/stack_management/management_settings.tsx # x-pack/solutions/security/plugins/security_solution/public/configurations/tabs/ai_settings.test.tsx # x-pack/solutions/security/plugins/security_solution/public/configurations/tabs/ai_settings.tsx

…i features (elastic#234480) ## Summary Summarize your PR. If it involves visual changes include a screenshot or gif. This PR integrates the new [default LLM setting](elastic#231940) with the security solution GenAI features (AI assistant and Attack discovery). The default LLM setting allows admins to configure the preferred AI connector. This PR make sure that this setting is actually respected in the AI assistant and Attack discovery. ### How to test: - Start Kibana locally from this branch - Make sure you have at least 3 LLM connectors configured (can be preconfigured ones). - Go to stack management > advanced settings and switch the following setting to "Security AI assistant in other apps". (This will make testing a little bit easier) <img width="1954" height="133" alt="image" src="https://github.com/user-attachments/assets/12fc4313-b2a5-45f7-bca9-8e0e7ee7f19e" /> - Enable the feature flag by adding the following to kibana.dev.yml: ``` feature_flags.overrides.aiAssistant.defaultLlmSettingEnabled: true ``` - Go to the GenAi Settings page: http://localhost:5601/app/management/ai/genAiSettings - Select a default LLM: <img width="2524" height="775" alt="image" src="https://github.com/user-attachments/assets/d8c51f46-04d2-42bf-871b-735fa3849d30" /> - Save the setting change using the footer at the bottom of the page. - Open the Security AI assistant (if you changed the Assistant visibility setting, you can open the assistant from the GenAi page directly) - Check that the LLM connector for the conversation is the one you configured as the default LLM. Also, verify that you can still change the connector used in your conversation to one of your other connectors. - Change the LLM to a non-default connector for the conversation. - Once you select a non-default connector, chat with the assistant and then start a new conversation, your non-default connector should still be active for the new conversation. - Now back on the GenAi settings page, check the `Disallow all other connectors` checkbox. - Open the AI assistant again and go to the existing conversation that has a few messages inside. - You should see a red banner indicating that a connector needs to be selected. - If you open the connector selector, you should now only see the default LLM you have configured as an option. #### Attack Discovery In attack discovery, you should observe the same behavior. - Go to attack discovery http://localhost:5601/app/security/attack_discovery - Open the manual run config flyout <img width="3081" height="1184" alt="image" src="https://github.com/user-attachments/assets/a5a11f1e-8b0b-40d9-8937-6fe4497cbf10" /> - Verify that only the default LLM is available as the connector: <img width="1698" height="833" alt="image" src="https://github.com/user-attachments/assets/45b68d6c-6f36-487f-ba08-030f41c10545" /> - Go back to the GenAi settings page http://localhost:5601/app/management/ai/genAiSettings and deselect the `Disallow all other connectors` checkbox and select a different default connector. - Go to Attack Discovery and open the manual run config flyout again. - Check that by default, your new default connector is used. Also, verify that you now again have the option of changing the connector to any of the other configured connectors. ### TODO The designs of the connector selector for Attack discovery and the Assistant still need to be implemented. That will be done in a separate PR. ### Checklist Check the PR satisfies following conditions. Reviewers should verify this PR satisfies this list as well. - [X] Any text added follows [EUI's writing guidelines](https://elastic.github.io/eui/#/guidelines/writing), uses sentence case text and includes [i18n support](https://github.com/elastic/kibana/blob/main/src/platform/packages/shared/kbn-i18n/README.md) - [X] [Documentation](https://www.elastic.co/guide/en/kibana/master/development-documentation.html) was added for feaures that require explanation or tutorials - [X] [Unit or functional tests](https://www.elastic.co/guide/en/kibana/master/development-tests.html) were updated or added to match the most common scenarios - [X] If a plugin configuration key changed, check if it needs to be allowlisted in the cloud and added to the [docker list](https://github.com/elastic/kibana/blob/main/src/dev/build/tasks/os_packages/docker_generator/resources/base/bin/kibana-docker) - [X] This was checked for breaking HTTP API changes, and any breaking changes have been approved by the breaking-change committee. The `release_note:breaking` label should be applied in these situations. - [X] [Flaky Test Runner](https://ci-stats.kibana.dev/trigger_flaky_test_runner/1) was used on any tests changed - [X] The PR description includes the appropriate Release Notes section, and the correct `release_note:*` label is applied per the [guidelines](https://www.elastic.co/guide/en/kibana/master/contributing.html#kibana-release-notes-process) - [X] Review the [backport guidelines](https://docs.google.com/document/d/1VyN5k91e5OVumlc0Gb9RPa3h1ewuPE705nRtioPiTvY/edit?usp=sharing) and apply applicable `backport:*` labels. ### Identify risks Does this PR introduce any risks? For example, consider risks like hard to test bugs, performance regression, potential of data loss. Describe the risk, its severity, and mitigation for each identified risk. Invite stakeholders and evaluate how to proceed before merging. - [ ] [See some risk examples](https://github.com/elastic/kibana/blob/main/RISK_MATRIX.mdx) - [ ] ... --------- Co-authored-by: kibanamachine <42973632+kibanamachine@users.noreply.github.com> Co-authored-by: Elastic Machine <elasticmachine@users.noreply.github.com> (cherry picked from commit b543b8c) # Conflicts: # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/conversations/conversation_settings/conversation_settings_editor.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/helpers.test.ts # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/helpers.ts # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/settings/assistant_settings_management.test.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/settings/assistant_settings_management.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/settings/search_ai_lake_configurations_settings_management.test.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/connectorland/connector_selector/index.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/connectorland/use_load_connectors/index.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/mock/test_providers/test_providers.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/tsconfig.json # x-pack/platform/plugins/private/gen_ai_settings/public/components/default_ai_connector/default_ai_connector.tsx # x-pack/solutions/security/packages/ecs-data-quality-dashboard/impl/data_quality_panel/mock/test_providers/test_providers.tsx # x-pack/solutions/security/plugins/security_solution/public/management/pages/endpoint_hosts/view/details/components/insights/workflow_insights_scan.tsx

…i features (elastic#234480) ## Summary Summarize your PR. If it involves visual changes include a screenshot or gif. This PR integrates the new [default LLM setting](elastic#231940) with the security solution GenAI features (AI assistant and Attack discovery). The default LLM setting allows admins to configure the preferred AI connector. This PR make sure that this setting is actually respected in the AI assistant and Attack discovery. ### How to test: - Start Kibana locally from this branch - Make sure you have at least 3 LLM connectors configured (can be preconfigured ones). - Go to stack management > advanced settings and switch the following setting to "Security AI assistant in other apps". (This will make testing a little bit easier) <img width="1954" height="133" alt="image" src="https://github.com/user-attachments/assets/12fc4313-b2a5-45f7-bca9-8e0e7ee7f19e" /> - Enable the feature flag by adding the following to kibana.dev.yml: ``` feature_flags.overrides.aiAssistant.defaultLlmSettingEnabled: true ``` - Go to the GenAi Settings page: http://localhost:5601/app/management/ai/genAiSettings - Select a default LLM: <img width="2524" height="775" alt="image" src="https://github.com/user-attachments/assets/d8c51f46-04d2-42bf-871b-735fa3849d30" /> - Save the setting change using the footer at the bottom of the page. - Open the Security AI assistant (if you changed the Assistant visibility setting, you can open the assistant from the GenAi page directly) - Check that the LLM connector for the conversation is the one you configured as the default LLM. Also, verify that you can still change the connector used in your conversation to one of your other connectors. - Change the LLM to a non-default connector for the conversation. - Once you select a non-default connector, chat with the assistant and then start a new conversation, your non-default connector should still be active for the new conversation. - Now back on the GenAi settings page, check the `Disallow all other connectors` checkbox. - Open the AI assistant again and go to the existing conversation that has a few messages inside. - You should see a red banner indicating that a connector needs to be selected. - If you open the connector selector, you should now only see the default LLM you have configured as an option. #### Attack Discovery In attack discovery, you should observe the same behavior. - Go to attack discovery http://localhost:5601/app/security/attack_discovery - Open the manual run config flyout <img width="3081" height="1184" alt="image" src="https://github.com/user-attachments/assets/a5a11f1e-8b0b-40d9-8937-6fe4497cbf10" /> - Verify that only the default LLM is available as the connector: <img width="1698" height="833" alt="image" src="https://github.com/user-attachments/assets/45b68d6c-6f36-487f-ba08-030f41c10545" /> - Go back to the GenAi settings page http://localhost:5601/app/management/ai/genAiSettings and deselect the `Disallow all other connectors` checkbox and select a different default connector. - Go to Attack Discovery and open the manual run config flyout again. - Check that by default, your new default connector is used. Also, verify that you now again have the option of changing the connector to any of the other configured connectors. ### TODO The designs of the connector selector for Attack discovery and the Assistant still need to be implemented. That will be done in a separate PR. ### Checklist Check the PR satisfies following conditions. Reviewers should verify this PR satisfies this list as well. - [X] Any text added follows [EUI's writing guidelines](https://elastic.github.io/eui/#/guidelines/writing), uses sentence case text and includes [i18n support](https://github.com/elastic/kibana/blob/main/src/platform/packages/shared/kbn-i18n/README.md) - [X] [Documentation](https://www.elastic.co/guide/en/kibana/master/development-documentation.html) was added for feaures that require explanation or tutorials - [X] [Unit or functional tests](https://www.elastic.co/guide/en/kibana/master/development-tests.html) were updated or added to match the most common scenarios - [X] If a plugin configuration key changed, check if it needs to be allowlisted in the cloud and added to the [docker list](https://github.com/elastic/kibana/blob/main/src/dev/build/tasks/os_packages/docker_generator/resources/base/bin/kibana-docker) - [X] This was checked for breaking HTTP API changes, and any breaking changes have been approved by the breaking-change committee. The `release_note:breaking` label should be applied in these situations. - [X] [Flaky Test Runner](https://ci-stats.kibana.dev/trigger_flaky_test_runner/1) was used on any tests changed - [X] The PR description includes the appropriate Release Notes section, and the correct `release_note:*` label is applied per the [guidelines](https://www.elastic.co/guide/en/kibana/master/contributing.html#kibana-release-notes-process) - [X] Review the [backport guidelines](https://docs.google.com/document/d/1VyN5k91e5OVumlc0Gb9RPa3h1ewuPE705nRtioPiTvY/edit?usp=sharing) and apply applicable `backport:*` labels. ### Identify risks Does this PR introduce any risks? For example, consider risks like hard to test bugs, performance regression, potential of data loss. Describe the risk, its severity, and mitigation for each identified risk. Invite stakeholders and evaluate how to proceed before merging. - [ ] [See some risk examples](https://github.com/elastic/kibana/blob/main/RISK_MATRIX.mdx) - [ ] ... --------- Co-authored-by: kibanamachine <42973632+kibanamachine@users.noreply.github.com> Co-authored-by: Elastic Machine <elasticmachine@users.noreply.github.com> (cherry picked from commit b543b8c) # Conflicts: # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/api/chat_complete/use_chat_complete.ts # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/conversations/conversation_settings/conversation_settings_editor.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/helpers.test.ts # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/helpers.ts # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/index.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/settings/assistant_settings.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/settings/assistant_settings_management.test.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/settings/assistant_settings_management.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/settings/search_ai_lake_configurations_settings_management.test.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/settings/search_ai_lake_configurations_settings_management.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant_context/index.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/connectorland/connector_selector/index.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/connectorland/use_load_connectors/index.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/mock/test_providers/test_providers.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/tsconfig.json # x-pack/platform/plugins/private/gen_ai_settings/public/components/default_ai_connector/default_ai_connector.tsx # x-pack/solutions/security/packages/ecs-data-quality-dashboard/impl/data_quality_panel/mock/test_providers/test_providers.tsx # x-pack/solutions/security/plugins/elastic_assistant/public/src/context/assistant_context/assistant_provider.tsx # x-pack/solutions/security/plugins/security_solution/public/attack_discovery/pages/index.tsx # x-pack/solutions/security/plugins/security_solution/public/attack_discovery/pages/settings_flyout/schedule/create_flyout/index.tsx # x-pack/solutions/security/plugins/security_solution/public/attack_discovery/pages/settings_flyout/schedule/details_flyout/index.tsx # x-pack/solutions/security/plugins/security_solution/public/common/mock/mock_assistant_provider.tsx # x-pack/solutions/security/plugins/security_solution/public/management/pages/endpoint_hosts/view/details/components/insights/workflow_insights_scan.tsx # x-pack/solutions/security/plugins/security_solution/public/onboarding/components/onboarding_body/cards/assistant/assistant_card.tsx

…i features (elastic#234480) Summarize your PR. If it involves visual changes include a screenshot or gif. This PR integrates the new [default LLM setting](elastic#231940) with the security solution GenAI features (AI assistant and Attack discovery). The default LLM setting allows admins to configure the preferred AI connector. This PR make sure that this setting is actually respected in the AI assistant and Attack discovery. - Start Kibana locally from this branch - Make sure you have at least 3 LLM connectors configured (can be preconfigured ones). - Go to stack management > advanced settings and switch the following setting to "Security AI assistant in other apps". (This will make testing a little bit easier) <img width="1954" height="133" alt="image" src="https://github.com/user-attachments/assets/12fc4313-b2a5-45f7-bca9-8e0e7ee7f19e" /> - Enable the feature flag by adding the following to kibana.dev.yml: ``` feature_flags.overrides.aiAssistant.defaultLlmSettingEnabled: true ``` - Go to the GenAi Settings page: http://localhost:5601/app/management/ai/genAiSettings - Select a default LLM: <img width="2524" height="775" alt="image" src="https://github.com/user-attachments/assets/d8c51f46-04d2-42bf-871b-735fa3849d30" /> - Save the setting change using the footer at the bottom of the page. - Open the Security AI assistant (if you changed the Assistant visibility setting, you can open the assistant from the GenAi page directly) - Check that the LLM connector for the conversation is the one you configured as the default LLM. Also, verify that you can still change the connector used in your conversation to one of your other connectors. - Change the LLM to a non-default connector for the conversation. - Once you select a non-default connector, chat with the assistant and then start a new conversation, your non-default connector should still be active for the new conversation. - Now back on the GenAi settings page, check the `Disallow all other connectors` checkbox. - Open the AI assistant again and go to the existing conversation that has a few messages inside. - You should see a red banner indicating that a connector needs to be selected. - If you open the connector selector, you should now only see the default LLM you have configured as an option. In attack discovery, you should observe the same behavior. - Go to attack discovery http://localhost:5601/app/security/attack_discovery - Open the manual run config flyout <img width="3081" height="1184" alt="image" src="https://github.com/user-attachments/assets/a5a11f1e-8b0b-40d9-8937-6fe4497cbf10" /> - Verify that only the default LLM is available as the connector: <img width="1698" height="833" alt="image" src="https://github.com/user-attachments/assets/45b68d6c-6f36-487f-ba08-030f41c10545" /> - Go back to the GenAi settings page http://localhost:5601/app/management/ai/genAiSettings and deselect the `Disallow all other connectors` checkbox and select a different default connector. - Go to Attack Discovery and open the manual run config flyout again. - Check that by default, your new default connector is used. Also, verify that you now again have the option of changing the connector to any of the other configured connectors. The designs of the connector selector for Attack discovery and the Assistant still need to be implemented. That will be done in a separate PR. Check the PR satisfies following conditions. Reviewers should verify this PR satisfies this list as well. - [X] Any text added follows [EUI's writing guidelines](https://elastic.github.io/eui/#/guidelines/writing), uses sentence case text and includes [i18n support](https://github.com/elastic/kibana/blob/main/src/platform/packages/shared/kbn-i18n/README.md) - [X] [Documentation](https://www.elastic.co/guide/en/kibana/master/development-documentation.html) was added for feaures that require explanation or tutorials - [X] [Unit or functional tests](https://www.elastic.co/guide/en/kibana/master/development-tests.html) were updated or added to match the most common scenarios - [X] If a plugin configuration key changed, check if it needs to be allowlisted in the cloud and added to the [docker list](https://github.com/elastic/kibana/blob/main/src/dev/build/tasks/os_packages/docker_generator/resources/base/bin/kibana-docker) - [X] This was checked for breaking HTTP API changes, and any breaking changes have been approved by the breaking-change committee. The `release_note:breaking` label should be applied in these situations. - [X] [Flaky Test Runner](https://ci-stats.kibana.dev/trigger_flaky_test_runner/1) was used on any tests changed - [X] The PR description includes the appropriate Release Notes section, and the correct `release_note:*` label is applied per the [guidelines](https://www.elastic.co/guide/en/kibana/master/contributing.html#kibana-release-notes-process) - [X] Review the [backport guidelines](https://docs.google.com/document/d/1VyN5k91e5OVumlc0Gb9RPa3h1ewuPE705nRtioPiTvY/edit?usp=sharing) and apply applicable `backport:*` labels. Does this PR introduce any risks? For example, consider risks like hard to test bugs, performance regression, potential of data loss. Describe the risk, its severity, and mitigation for each identified risk. Invite stakeholders and evaluate how to proceed before merging. - [ ] [See some risk examples](https://github.com/elastic/kibana/blob/main/RISK_MATRIX.mdx) - [ ] ... --------- Co-authored-by: kibanamachine <42973632+kibanamachine@users.noreply.github.com> Co-authored-by: Elastic Machine <elasticmachine@users.noreply.github.com>

…i features (elastic#234480) ## Summary Summarize your PR. If it involves visual changes include a screenshot or gif. This PR integrates the new [default LLM setting](elastic#231940) with the security solution GenAI features (AI assistant and Attack discovery). The default LLM setting allows admins to configure the preferred AI connector. This PR make sure that this setting is actually respected in the AI assistant and Attack discovery. ### How to test: - Start Kibana locally from this branch - Make sure you have at least 3 LLM connectors configured (can be preconfigured ones). - Go to stack management > advanced settings and switch the following setting to "Security AI assistant in other apps". (This will make testing a little bit easier) <img width="1954" height="133" alt="image" src="https://github.com/user-attachments/assets/12fc4313-b2a5-45f7-bca9-8e0e7ee7f19e" /> - Enable the feature flag by adding the following to kibana.dev.yml: ``` feature_flags.overrides.aiAssistant.defaultLlmSettingEnabled: true ``` - Go to the GenAi Settings page: http://localhost:5601/app/management/ai/genAiSettings - Select a default LLM: <img width="2524" height="775" alt="image" src="https://github.com/user-attachments/assets/d8c51f46-04d2-42bf-871b-735fa3849d30" /> - Save the setting change using the footer at the bottom of the page. - Open the Security AI assistant (if you changed the Assistant visibility setting, you can open the assistant from the GenAi page directly) - Check that the LLM connector for the conversation is the one you configured as the default LLM. Also, verify that you can still change the connector used in your conversation to one of your other connectors. - Change the LLM to a non-default connector for the conversation. - Once you select a non-default connector, chat with the assistant and then start a new conversation, your non-default connector should still be active for the new conversation. - Now back on the GenAi settings page, check the `Disallow all other connectors` checkbox. - Open the AI assistant again and go to the existing conversation that has a few messages inside. - You should see a red banner indicating that a connector needs to be selected. - If you open the connector selector, you should now only see the default LLM you have configured as an option. #### Attack Discovery In attack discovery, you should observe the same behavior. - Go to attack discovery http://localhost:5601/app/security/attack_discovery - Open the manual run config flyout <img width="3081" height="1184" alt="image" src="https://github.com/user-attachments/assets/a5a11f1e-8b0b-40d9-8937-6fe4497cbf10" /> - Verify that only the default LLM is available as the connector: <img width="1698" height="833" alt="image" src="https://github.com/user-attachments/assets/45b68d6c-6f36-487f-ba08-030f41c10545" /> - Go back to the GenAi settings page http://localhost:5601/app/management/ai/genAiSettings and deselect the `Disallow all other connectors` checkbox and select a different default connector. - Go to Attack Discovery and open the manual run config flyout again. - Check that by default, your new default connector is used. Also, verify that you now again have the option of changing the connector to any of the other configured connectors. ### TODO The designs of the connector selector for Attack discovery and the Assistant still need to be implemented. That will be done in a separate PR. ### Checklist Check the PR satisfies following conditions. Reviewers should verify this PR satisfies this list as well. - [X] Any text added follows [EUI's writing guidelines](https://elastic.github.io/eui/#/guidelines/writing), uses sentence case text and includes [i18n support](https://github.com/elastic/kibana/blob/main/src/platform/packages/shared/kbn-i18n/README.md) - [X] [Documentation](https://www.elastic.co/guide/en/kibana/master/development-documentation.html) was added for feaures that require explanation or tutorials - [X] [Unit or functional tests](https://www.elastic.co/guide/en/kibana/master/development-tests.html) were updated or added to match the most common scenarios - [X] If a plugin configuration key changed, check if it needs to be allowlisted in the cloud and added to the [docker list](https://github.com/elastic/kibana/blob/main/src/dev/build/tasks/os_packages/docker_generator/resources/base/bin/kibana-docker) - [X] This was checked for breaking HTTP API changes, and any breaking changes have been approved by the breaking-change committee. The `release_note:breaking` label should be applied in these situations. - [X] [Flaky Test Runner](https://ci-stats.kibana.dev/trigger_flaky_test_runner/1) was used on any tests changed - [X] The PR description includes the appropriate Release Notes section, and the correct `release_note:*` label is applied per the [guidelines](https://www.elastic.co/guide/en/kibana/master/contributing.html#kibana-release-notes-process) - [X] Review the [backport guidelines](https://docs.google.com/document/d/1VyN5k91e5OVumlc0Gb9RPa3h1ewuPE705nRtioPiTvY/edit?usp=sharing) and apply applicable `backport:*` labels. ### Identify risks Does this PR introduce any risks? For example, consider risks like hard to test bugs, performance regression, potential of data loss. Describe the risk, its severity, and mitigation for each identified risk. Invite stakeholders and evaluate how to proceed before merging. - [ ] [See some risk examples](https://github.com/elastic/kibana/blob/main/RISK_MATRIX.mdx) - [ ] ... --------- Co-authored-by: kibanamachine <42973632+kibanamachine@users.noreply.github.com> Co-authored-by: Elastic Machine <elasticmachine@users.noreply.github.com> (cherry picked from commit b543b8c) # Conflicts: # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/api/chat_complete/use_chat_complete.ts # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/conversations/conversation_settings/conversation_settings_editor.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/helpers.test.ts # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/helpers.ts # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/settings/assistant_settings.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/settings/assistant_settings_management.test.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/settings/assistant_settings_management.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/settings/search_ai_lake_configurations_settings_management.test.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/settings/search_ai_lake_configurations_settings_management.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant_context/index.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/connectorland/use_load_connectors/index.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/mock/test_providers/test_providers.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/tsconfig.json # x-pack/platform/plugins/private/gen_ai_settings/public/components/default_ai_connector/default_ai_connector.tsx # x-pack/platform/plugins/private/gen_ai_settings/public/contexts/settings_context.tsx # x-pack/solutions/security/packages/ecs-data-quality-dashboard/impl/data_quality_panel/mock/test_providers/test_providers.tsx # x-pack/solutions/security/plugins/elastic_assistant/public/src/context/assistant_context/assistant_provider.tsx # x-pack/solutions/security/plugins/security_solution/public/attack_discovery/pages/index.tsx # x-pack/solutions/security/plugins/security_solution/public/attack_discovery/pages/settings_flyout/schedule/create_flyout/index.tsx # x-pack/solutions/security/plugins/security_solution/public/attack_discovery/pages/settings_flyout/schedule/details_flyout/index.tsx # x-pack/solutions/security/plugins/security_solution/public/common/mock/mock_assistant_provider.tsx # x-pack/solutions/security/plugins/security_solution/public/onboarding/components/onboarding_body/cards/assistant/assistant_card.tsx

…i features (elastic#234480) ## Summary Summarize your PR. If it involves visual changes include a screenshot or gif. This PR integrates the new [default LLM setting](elastic#231940) with the security solution GenAI features (AI assistant and Attack discovery). The default LLM setting allows admins to configure the preferred AI connector. This PR make sure that this setting is actually respected in the AI assistant and Attack discovery. ### How to test: - Start Kibana locally from this branch - Make sure you have at least 3 LLM connectors configured (can be preconfigured ones). - Go to stack management > advanced settings and switch the following setting to "Security AI assistant in other apps". (This will make testing a little bit easier) <img width="1954" height="133" alt="image" src="https://github.com/user-attachments/assets/12fc4313-b2a5-45f7-bca9-8e0e7ee7f19e" /> - Enable the feature flag by adding the following to kibana.dev.yml: ``` feature_flags.overrides.aiAssistant.defaultLlmSettingEnabled: true ``` - Go to the GenAi Settings page: http://localhost:5601/app/management/ai/genAiSettings - Select a default LLM: <img width="2524" height="775" alt="image" src="https://github.com/user-attachments/assets/d8c51f46-04d2-42bf-871b-735fa3849d30" /> - Save the setting change using the footer at the bottom of the page. - Open the Security AI assistant (if you changed the Assistant visibility setting, you can open the assistant from the GenAi page directly) - Check that the LLM connector for the conversation is the one you configured as the default LLM. Also, verify that you can still change the connector used in your conversation to one of your other connectors. - Change the LLM to a non-default connector for the conversation. - Once you select a non-default connector, chat with the assistant and then start a new conversation, your non-default connector should still be active for the new conversation. - Now back on the GenAi settings page, check the `Disallow all other connectors` checkbox. - Open the AI assistant again and go to the existing conversation that has a few messages inside. - You should see a red banner indicating that a connector needs to be selected. - If you open the connector selector, you should now only see the default LLM you have configured as an option. #### Attack Discovery In attack discovery, you should observe the same behavior. - Go to attack discovery http://localhost:5601/app/security/attack_discovery - Open the manual run config flyout <img width="3081" height="1184" alt="image" src="https://github.com/user-attachments/assets/a5a11f1e-8b0b-40d9-8937-6fe4497cbf10" /> - Verify that only the default LLM is available as the connector: <img width="1698" height="833" alt="image" src="https://github.com/user-attachments/assets/45b68d6c-6f36-487f-ba08-030f41c10545" /> - Go back to the GenAi settings page http://localhost:5601/app/management/ai/genAiSettings and deselect the `Disallow all other connectors` checkbox and select a different default connector. - Go to Attack Discovery and open the manual run config flyout again. - Check that by default, your new default connector is used. Also, verify that you now again have the option of changing the connector to any of the other configured connectors. ### TODO The designs of the connector selector for Attack discovery and the Assistant still need to be implemented. That will be done in a separate PR. ### Checklist Check the PR satisfies following conditions. Reviewers should verify this PR satisfies this list as well. - [X] Any text added follows [EUI's writing guidelines](https://elastic.github.io/eui/#/guidelines/writing), uses sentence case text and includes [i18n support](https://github.com/elastic/kibana/blob/main/src/platform/packages/shared/kbn-i18n/README.md) - [X] [Documentation](https://www.elastic.co/guide/en/kibana/master/development-documentation.html) was added for feaures that require explanation or tutorials - [X] [Unit or functional tests](https://www.elastic.co/guide/en/kibana/master/development-tests.html) were updated or added to match the most common scenarios - [X] If a plugin configuration key changed, check if it needs to be allowlisted in the cloud and added to the [docker list](https://github.com/elastic/kibana/blob/main/src/dev/build/tasks/os_packages/docker_generator/resources/base/bin/kibana-docker) - [X] This was checked for breaking HTTP API changes, and any breaking changes have been approved by the breaking-change committee. The `release_note:breaking` label should be applied in these situations. - [X] [Flaky Test Runner](https://ci-stats.kibana.dev/trigger_flaky_test_runner/1) was used on any tests changed - [X] The PR description includes the appropriate Release Notes section, and the correct `release_note:*` label is applied per the [guidelines](https://www.elastic.co/guide/en/kibana/master/contributing.html#kibana-release-notes-process) - [X] Review the [backport guidelines](https://docs.google.com/document/d/1VyN5k91e5OVumlc0Gb9RPa3h1ewuPE705nRtioPiTvY/edit?usp=sharing) and apply applicable `backport:*` labels. ### Identify risks Does this PR introduce any risks? For example, consider risks like hard to test bugs, performance regression, potential of data loss. Describe the risk, its severity, and mitigation for each identified risk. Invite stakeholders and evaluate how to proceed before merging. - [ ] [See some risk examples](https://github.com/elastic/kibana/blob/main/RISK_MATRIX.mdx) - [ ] ... --------- Co-authored-by: kibanamachine <42973632+kibanamachine@users.noreply.github.com> Co-authored-by: Elastic Machine <elasticmachine@users.noreply.github.com>

…i features (elastic#234480) ## Summary Summarize your PR. If it involves visual changes include a screenshot or gif. This PR integrates the new [default LLM setting](elastic#231940) with the security solution GenAI features (AI assistant and Attack discovery). The default LLM setting allows admins to configure the preferred AI connector. This PR make sure that this setting is actually respected in the AI assistant and Attack discovery. ### How to test: - Start Kibana locally from this branch - Make sure you have at least 3 LLM connectors configured (can be preconfigured ones). - Go to stack management > advanced settings and switch the following setting to "Security AI assistant in other apps". (This will make testing a little bit easier) <img width="1954" height="133" alt="image" src="https://github.com/user-attachments/assets/12fc4313-b2a5-45f7-bca9-8e0e7ee7f19e" /> - Enable the feature flag by adding the following to kibana.dev.yml: ``` feature_flags.overrides.aiAssistant.defaultLlmSettingEnabled: true ``` - Go to the GenAi Settings page: http://localhost:5601/app/management/ai/genAiSettings - Select a default LLM: <img width="2524" height="775" alt="image" src="https://github.com/user-attachments/assets/d8c51f46-04d2-42bf-871b-735fa3849d30" /> - Save the setting change using the footer at the bottom of the page. - Open the Security AI assistant (if you changed the Assistant visibility setting, you can open the assistant from the GenAi page directly) - Check that the LLM connector for the conversation is the one you configured as the default LLM. Also, verify that you can still change the connector used in your conversation to one of your other connectors. - Change the LLM to a non-default connector for the conversation. - Once you select a non-default connector, chat with the assistant and then start a new conversation, your non-default connector should still be active for the new conversation. - Now back on the GenAi settings page, check the `Disallow all other connectors` checkbox. - Open the AI assistant again and go to the existing conversation that has a few messages inside. - You should see a red banner indicating that a connector needs to be selected. - If you open the connector selector, you should now only see the default LLM you have configured as an option. #### Attack Discovery In attack discovery, you should observe the same behavior. - Go to attack discovery http://localhost:5601/app/security/attack_discovery - Open the manual run config flyout <img width="3081" height="1184" alt="image" src="https://github.com/user-attachments/assets/a5a11f1e-8b0b-40d9-8937-6fe4497cbf10" /> - Verify that only the default LLM is available as the connector: <img width="1698" height="833" alt="image" src="https://github.com/user-attachments/assets/45b68d6c-6f36-487f-ba08-030f41c10545" /> - Go back to the GenAi settings page http://localhost:5601/app/management/ai/genAiSettings and deselect the `Disallow all other connectors` checkbox and select a different default connector. - Go to Attack Discovery and open the manual run config flyout again. - Check that by default, your new default connector is used. Also, verify that you now again have the option of changing the connector to any of the other configured connectors. ### TODO The designs of the connector selector for Attack discovery and the Assistant still need to be implemented. That will be done in a separate PR. ### Checklist Check the PR satisfies following conditions. Reviewers should verify this PR satisfies this list as well. - [X] Any text added follows [EUI's writing guidelines](https://elastic.github.io/eui/#/guidelines/writing), uses sentence case text and includes [i18n support](https://github.com/elastic/kibana/blob/main/src/platform/packages/shared/kbn-i18n/README.md) - [X] [Documentation](https://www.elastic.co/guide/en/kibana/master/development-documentation.html) was added for feaures that require explanation or tutorials - [X] [Unit or functional tests](https://www.elastic.co/guide/en/kibana/master/development-tests.html) were updated or added to match the most common scenarios - [X] If a plugin configuration key changed, check if it needs to be allowlisted in the cloud and added to the [docker list](https://github.com/elastic/kibana/blob/main/src/dev/build/tasks/os_packages/docker_generator/resources/base/bin/kibana-docker) - [X] This was checked for breaking HTTP API changes, and any breaking changes have been approved by the breaking-change committee. The `release_note:breaking` label should be applied in these situations. - [X] [Flaky Test Runner](https://ci-stats.kibana.dev/trigger_flaky_test_runner/1) was used on any tests changed - [X] The PR description includes the appropriate Release Notes section, and the correct `release_note:*` label is applied per the [guidelines](https://www.elastic.co/guide/en/kibana/master/contributing.html#kibana-release-notes-process) - [X] Review the [backport guidelines](https://docs.google.com/document/d/1VyN5k91e5OVumlc0Gb9RPa3h1ewuPE705nRtioPiTvY/edit?usp=sharing) and apply applicable `backport:*` labels. ### Identify risks Does this PR introduce any risks? For example, consider risks like hard to test bugs, performance regression, potential of data loss. Describe the risk, its severity, and mitigation for each identified risk. Invite stakeholders and evaluate how to proceed before merging. - [ ] [See some risk examples](https://github.com/elastic/kibana/blob/main/RISK_MATRIX.mdx) - [ ] ... --------- Co-authored-by: kibanamachine <42973632+kibanamachine@users.noreply.github.com> Co-authored-by: Elastic Machine <elasticmachine@users.noreply.github.com> (cherry picked from commit b543b8c) # Conflicts: # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/api/chat_complete/use_chat_complete.ts # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/conversations/conversation_settings/conversation_settings_editor.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/helpers.test.ts # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/helpers.ts # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/settings/assistant_settings.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/settings/assistant_settings_management.test.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/settings/assistant_settings_management.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/settings/search_ai_lake_configurations_settings_management.test.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant/settings/search_ai_lake_configurations_settings_management.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/assistant_context/index.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/connectorland/use_load_connectors/index.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/impl/mock/test_providers/test_providers.tsx # x-pack/platform/packages/shared/kbn-elastic-assistant/tsconfig.json # x-pack/platform/plugins/private/gen_ai_settings/public/components/default_ai_connector/default_ai_connector.tsx # x-pack/solutions/security/packages/ecs-data-quality-dashboard/impl/data_quality_panel/mock/test_providers/test_providers.tsx # x-pack/solutions/security/plugins/elastic_assistant/public/src/context/assistant_context/assistant_provider.tsx # x-pack/solutions/security/plugins/security_solution/public/attack_discovery/pages/index.tsx # x-pack/solutions/security/plugins/security_solution/public/attack_discovery/pages/settings_flyout/schedule/create_flyout/index.tsx # x-pack/solutions/security/plugins/security_solution/public/attack_discovery/pages/settings_flyout/schedule/details_flyout/index.tsx # x-pack/solutions/security/plugins/security_solution/public/common/mock/mock_assistant_provider.tsx # x-pack/solutions/security/plugins/security_solution/public/onboarding/components/onboarding_body/cards/assistant/assistant_card.tsx

…y GenAi features (#234480) (#236461) # Backport This will backport the following commits from `main` to `9.1`: - [[Security Solution] [GenAi] Use default LLM setting for security GenAi features (#234480)](#234480)  ### Questions ? Please refer to the [Backport tool documentation](https://github.com/sorenlouv/backport)  --------- Co-authored-by: kibanamachine <42973632+kibanamachine@users.noreply.github.com>

…ty GenAi features (#234480) (#236464) # Backport This will backport the following commits from `main` to `8.19`: - [[Security Solution] [GenAi] Use default LLM setting for security GenAi features (#234480)](#234480)  ### Questions ? Please refer to the [Backport tool documentation](https://github.com/sorenlouv/backport)  --------- Co-authored-by: kibanamachine <42973632+kibanamachine@users.noreply.github.com>

…y GenAi features (#234480) (#236587) # Backport This will backport the following commits from `main` to `9.0`: - [[Security Solution] [GenAi] Use default LLM setting for security GenAi features (#234480)](#234480)  ### Questions ? Please refer to the [Backport tool documentation](https://github.com/sorenlouv/backport)  --------- Co-authored-by: kibanamachine <42973632+kibanamachine@users.noreply.github.com> Co-authored-by: Elastic Machine <elasticmachine@users.noreply.github.com>

…i features (#234480) ## Summary Summarize your PR. If it involves visual changes include a screenshot or gif. This PR integrates the new [default LLM setting](#231940) with the security solution GenAI features (AI assistant and Attack discovery). The default LLM setting allows admins to configure the preferred AI connector. This PR make sure that this setting is actually respected in the AI assistant and Attack discovery. ### How to test: - Start Kibana locally from this branch - Make sure you have at least 3 LLM connectors configured (can be preconfigured ones). - Go to stack management > advanced settings and switch the following setting to "Security AI assistant in other apps". (This will make testing a little bit easier) <img width="1954" height="133" alt="image" src="https://github.com/user-attachments/assets/12fc4313-b2a5-45f7-bca9-8e0e7ee7f19e" /> - Enable the feature flag by adding the following to kibana.dev.yml: ``` feature_flags.overrides.aiAssistant.defaultLlmSettingEnabled: true ``` - Go to the GenAi Settings page: http://localhost:5601/app/management/ai/genAiSettings - Select a default LLM: <img width="2524" height="775" alt="image" src="https://github.com/user-attachments/assets/d8c51f46-04d2-42bf-871b-735fa3849d30" /> - Save the setting change using the footer at the bottom of the page. - Open the Security AI assistant (if you changed the Assistant visibility setting, you can open the assistant from the GenAi page directly) - Check that the LLM connector for the conversation is the one you configured as the default LLM. Also, verify that you can still change the connector used in your conversation to one of your other connectors. - Change the LLM to a non-default connector for the conversation. - Once you select a non-default connector, chat with the assistant and then start a new conversation, your non-default connector should still be active for the new conversation. - Now back on the GenAi settings page, check the `Disallow all other connectors` checkbox. - Open the AI assistant again and go to the existing conversation that has a few messages inside. - You should see a red banner indicating that a connector needs to be selected. - If you open the connector selector, you should now only see the default LLM you have configured as an option. #### Attack Discovery In attack discovery, you should observe the same behavior. - Go to attack discovery http://localhost:5601/app/security/attack_discovery - Open the manual run config flyout <img width="3081" height="1184" alt="image" src="https://github.com/user-attachments/assets/a5a11f1e-8b0b-40d9-8937-6fe4497cbf10" /> - Verify that only the default LLM is available as the connector: <img width="1698" height="833" alt="image" src="https://github.com/user-attachments/assets/45b68d6c-6f36-487f-ba08-030f41c10545" /> - Go back to the GenAi settings page http://localhost:5601/app/management/ai/genAiSettings and deselect the `Disallow all other connectors` checkbox and select a different default connector. - Go to Attack Discovery and open the manual run config flyout again. - Check that by default, your new default connector is used. Also, verify that you now again have the option of changing the connector to any of the other configured connectors. ### TODO The designs of the connector selector for Attack discovery and the Assistant still need to be implemented. That will be done in a separate PR. ### Checklist Check the PR satisfies following conditions. Reviewers should verify this PR satisfies this list as well. - [X] Any text added follows [EUI's writing guidelines](https://elastic.github.io/eui/#/guidelines/writing), uses sentence case text and includes [i18n support](https://github.com/elastic/kibana/blob/main/src/platform/packages/shared/kbn-i18n/README.md) - [X] [Documentation](https://www.elastic.co/guide/en/kibana/master/development-documentation.html) was added for feaures that require explanation or tutorials - [X] [Unit or functional tests](https://www.elastic.co/guide/en/kibana/master/development-tests.html) were updated or added to match the most common scenarios - [X] If a plugin configuration key changed, check if it needs to be allowlisted in the cloud and added to the [docker list](https://github.com/elastic/kibana/blob/main/src/dev/build/tasks/os_packages/docker_generator/resources/base/bin/kibana-docker) - [X] This was checked for breaking HTTP API changes, and any breaking changes have been approved by the breaking-change committee. The `release_note:breaking` label should be applied in these situations. - [X] [Flaky Test Runner](https://ci-stats.kibana.dev/trigger_flaky_test_runner/1) was used on any tests changed - [X] The PR description includes the appropriate Release Notes section, and the correct `release_note:*` label is applied per the [guidelines](https://www.elastic.co/guide/en/kibana/master/contributing.html#kibana-release-notes-process) - [X] Review the [backport guidelines](https://docs.google.com/document/d/1VyN5k91e5OVumlc0Gb9RPa3h1ewuPE705nRtioPiTvY/edit?usp=sharing) and apply applicable `backport:*` labels. ### Identify risks Does this PR introduce any risks? For example, consider risks like hard to test bugs, performance regression, potential of data loss. Describe the risk, its severity, and mitigation for each identified risk. Invite stakeholders and evaluate how to proceed before merging. - [ ] [See some risk examples](https://github.com/elastic/kibana/blob/main/RISK_MATRIX.mdx) - [ ] ... --------- Co-authored-by: kibanamachine <42973632+kibanamachine@users.noreply.github.com> Co-authored-by: Elastic Machine <elasticmachine@users.noreply.github.com>

…ty GenAi features (#234480) (#236473) # Backport This will backport the following commits from `main` to `8.18`: - [[Security Solution] [GenAi] Use default LLM setting for security GenAi features (#234480)](#234480)  ### Questions ? Please refer to the [Backport tool documentation](https://github.com/sorenlouv/backport)  --------- Co-authored-by: kibanamachine <42973632+kibanamachine@users.noreply.github.com> Co-authored-by: Elastic Machine <elasticmachine@users.noreply.github.com>

…i features (elastic#234480) ## Summary Summarize your PR. If it involves visual changes include a screenshot or gif. This PR integrates the new [default LLM setting](elastic#231940) with the security solution GenAI features (AI assistant and Attack discovery). The default LLM setting allows admins to configure the preferred AI connector. This PR make sure that this setting is actually respected in the AI assistant and Attack discovery. ### How to test: - Start Kibana locally from this branch - Make sure you have at least 3 LLM connectors configured (can be preconfigured ones). - Go to stack management > advanced settings and switch the following setting to "Security AI assistant in other apps". (This will make testing a little bit easier) <img width="1954" height="133" alt="image" src="https://github.com/user-attachments/assets/12fc4313-b2a5-45f7-bca9-8e0e7ee7f19e" /> - Enable the feature flag by adding the following to kibana.dev.yml: ``` feature_flags.overrides.aiAssistant.defaultLlmSettingEnabled: true ``` - Go to the GenAi Settings page: http://localhost:5601/app/management/ai/genAiSettings - Select a default LLM: <img width="2524" height="775" alt="image" src="https://github.com/user-attachments/assets/d8c51f46-04d2-42bf-871b-735fa3849d30" /> - Save the setting change using the footer at the bottom of the page. - Open the Security AI assistant (if you changed the Assistant visibility setting, you can open the assistant from the GenAi page directly) - Check that the LLM connector for the conversation is the one you configured as the default LLM. Also, verify that you can still change the connector used in your conversation to one of your other connectors. - Change the LLM to a non-default connector for the conversation. - Once you select a non-default connector, chat with the assistant and then start a new conversation, your non-default connector should still be active for the new conversation. - Now back on the GenAi settings page, check the `Disallow all other connectors` checkbox. - Open the AI assistant again and go to the existing conversation that has a few messages inside. - You should see a red banner indicating that a connector needs to be selected. - If you open the connector selector, you should now only see the default LLM you have configured as an option. #### Attack Discovery In attack discovery, you should observe the same behavior. - Go to attack discovery http://localhost:5601/app/security/attack_discovery - Open the manual run config flyout <img width="3081" height="1184" alt="image" src="https://github.com/user-attachments/assets/a5a11f1e-8b0b-40d9-8937-6fe4497cbf10" /> - Verify that only the default LLM is available as the connector: <img width="1698" height="833" alt="image" src="https://github.com/user-attachments/assets/45b68d6c-6f36-487f-ba08-030f41c10545" /> - Go back to the GenAi settings page http://localhost:5601/app/management/ai/genAiSettings and deselect the `Disallow all other connectors` checkbox and select a different default connector. - Go to Attack Discovery and open the manual run config flyout again. - Check that by default, your new default connector is used. Also, verify that you now again have the option of changing the connector to any of the other configured connectors. ### TODO The designs of the connector selector for Attack discovery and the Assistant still need to be implemented. That will be done in a separate PR. ### Checklist Check the PR satisfies following conditions. Reviewers should verify this PR satisfies this list as well. - [X] Any text added follows [EUI's writing guidelines](https://elastic.github.io/eui/#/guidelines/writing), uses sentence case text and includes [i18n support](https://github.com/elastic/kibana/blob/main/src/platform/packages/shared/kbn-i18n/README.md) - [X] [Documentation](https://www.elastic.co/guide/en/kibana/master/development-documentation.html) was added for feaures that require explanation or tutorials - [X] [Unit or functional tests](https://www.elastic.co/guide/en/kibana/master/development-tests.html) were updated or added to match the most common scenarios - [X] If a plugin configuration key changed, check if it needs to be allowlisted in the cloud and added to the [docker list](https://github.com/elastic/kibana/blob/main/src/dev/build/tasks/os_packages/docker_generator/resources/base/bin/kibana-docker) - [X] This was checked for breaking HTTP API changes, and any breaking changes have been approved by the breaking-change committee. The `release_note:breaking` label should be applied in these situations. - [X] [Flaky Test Runner](https://ci-stats.kibana.dev/trigger_flaky_test_runner/1) was used on any tests changed - [X] The PR description includes the appropriate Release Notes section, and the correct `release_note:*` label is applied per the [guidelines](https://www.elastic.co/guide/en/kibana/master/contributing.html#kibana-release-notes-process) - [X] Review the [backport guidelines](https://docs.google.com/document/d/1VyN5k91e5OVumlc0Gb9RPa3h1ewuPE705nRtioPiTvY/edit?usp=sharing) and apply applicable `backport:*` labels. ### Identify risks Does this PR introduce any risks? For example, consider risks like hard to test bugs, performance regression, potential of data loss. Describe the risk, its severity, and mitigation for each identified risk. Invite stakeholders and evaluate how to proceed before merging. - [ ] [See some risk examples](https://github.com/elastic/kibana/blob/main/RISK_MATRIX.mdx) - [ ] ... --------- Co-authored-by: kibanamachine <42973632+kibanamachine@users.noreply.github.com> Co-authored-by: Elastic Machine <elasticmachine@users.noreply.github.com>

KDKHD added 2 commits August 15, 2025 14:35

Add setting to configure default LLM

d076ad1

Add tests

779ffdc

KDKHD force-pushed the feature/default-llm-setting branch from 16dbc05 to 779ffdc Compare August 15, 2025 14:44

KDKHD changed the title ~~Add setting to configure default LLM~~ [AI assistant] Add setting to configure default LLM (Work in progress) Aug 15, 2025

KDKHD marked this pull request as ready for review August 15, 2025 15:01

KDKHD requested review from a team as code owners August 15, 2025 15:01

KDKHD added 2 commits August 18, 2025 11:09

lint

208f283

lint

3563bde

KDKHD force-pushed the feature/default-llm-setting branch from e84b84c to 3563bde Compare August 18, 2025 09:13

KDKHD added 4 commits August 18, 2025 11:15

lint

48a2772

lint

041d4cf

lint

6ac17a7

lint

b4a1986

KDKHD added the release_note:skip Skip the PR/issue when compiling release notes label Aug 18, 2025

kibanamachine and others added 2 commits August 18, 2025 09:39

[CI] Auto-commit changed files from 'node scripts/notice'

3517b93

lint

3b01e0b

elasticmachine and others added 4 commits August 18, 2025 12:20

Merge branch 'main' into feature/default-llm-setting

9a3379c

[CI] Auto-commit changed files from 'node scripts/eslint_all_files --…

a791032

…no-cache --fix'

roles

f284831

types

8a78db9

KDKHD requested a review from a team as a code owner August 18, 2025 12:26

KDKHD added ci:project-deploy-security Create a Security Serverless Project v9.1.3 v8.19.3 v9.0.6 v8.18.6 backport:version Backport to applied version labels labels Aug 18, 2025

KDKHD mentioned this pull request Sep 10, 2025

[Security Solution] [GenAi] Use default LLM setting for security GenAi features #234480

Merged

10 tasks

KDKHD added backport:skip This PR does not require backporting and removed backport:version Backport to applied version labels labels Sep 11, 2025

kibanamachine removed the backport missing Added to PRs automatically when the are determined to be missing a backport. label Sep 11, 2025

KDKHD added backport missing Added to PRs automatically when the are determined to be missing a backport. and removed v9.1.3 v8.19.3 v9.0.6 v8.18.6 labels Sep 11, 2025

kibanamachine removed the backport missing Added to PRs automatically when the are determined to be missing a backport. label Sep 11, 2025

shubhaat mentioned this pull request Sep 18, 2025

Document how to change the default from Elastic Managed LLM elastic/docs-content#3012

Closed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[AI assistant] Add setting to configure default LLM#231940

[AI assistant] Add setting to configure default LLM#231940
KDKHD merged 30 commits intoelastic:mainfrom
KDKHD:feature/default-llm-setting

KDKHD commented Aug 15, 2025 •

edited by kibanamachine

Loading

Uh oh!

KDKHD commented Aug 18, 2025

Uh oh!

kibanamachine commented Sep 10, 2025

Uh oh!

KDKHD commented Sep 11, 2025

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

12 participants

Conversation

KDKHD commented Aug 15, 2025 • edited by kibanamachine Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Checklist

Identify risks

Uh oh!

KDKHD commented Aug 18, 2025

Uh oh!

kibanamachine commented Sep 10, 2025

Uh oh!

KDKHD commented Sep 11, 2025

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

12 participants

KDKHD commented Aug 15, 2025 •

edited by kibanamachine

Loading