Set claude 2.1 as model for slash commands

What does this MR do and why?

• The ensure that all tools have a model set
• Otherwise, they use the model default, which is Claude 3 sonnet if the user has a feature flag enabled. But these tools are still sending json request bodies for the completions API.
• See code here for default model config
• We eventually want to migrate these tools to Claude 3, but we want to support them staying on Claude 2.1 for now so we can selectively enroll users into Claude 3 without degrading behavior for existing customers.
• Resolves #454849 (closed)

MR acceptance checklist

Please evaluate this MR against the MR acceptance checklist. It helps you analyze changes to reduce risks in quality, performance, reliability, security, and maintainability.

Screenshots or screen recordings

Screenshots are required for UI changes, and strongly recommended for all other merge requests.

Before	After

How to set up and validate locally

1. In rails console enable the experiment fully

   Feature.enable(:ai_claude_3_sonnet)

2. Test the slash commands: /explain, /refactor, and /tests. All should work and be using Claude 2.1

Also good to ensure that all anthropic prompts have the model option set:

 git ls-files | grep anthropic.rb
ee/lib/api/ai/experimentation/anthropic.rb
ee/lib/code_suggestions/prompts/code_generation/anthropic.rb

ee/lib/gitlab/llm/chain/agents/zero_shot/prompts/anthropic.rb
ee/lib/gitlab/llm/chain/requests/anthropic.rb
ee/lib/gitlab/llm/chain/tools/ci_editor_assistant/prompts/anthropic.rb
ee/lib/gitlab/llm/chain/tools/epic_identifier/prompts/anthropic.rb
ee/lib/gitlab/llm/chain/tools/epic_reader/prompts/anthropic.rb
ee/lib/gitlab/llm/chain/tools/explain_code/prompts/anthropic.rb
ee/lib/gitlab/llm/chain/tools/issue_identifier/prompts/anthropic.rb
ee/lib/gitlab/llm/chain/tools/issue_reader/prompts/anthropic.rb
ee/lib/gitlab/llm/chain/tools/refactor_code/prompts/anthropic.rb
ee/lib/gitlab/llm/chain/tools/summarize_comments/prompts/anthropic.rb
ee/lib/gitlab/llm/chain/tools/write_tests/prompts/anthropic.rb

We can ignore the first 2 serach results because code suggestions doesn't use the AiGateway::Client and sets model headers here

Manual check for MODEL being set in all other tools:

• ee/lib/gitlab/llm/chain/agents/zero_shot/prompts/anthropic.rb (this prompt works for claude 3 when feature flag enabled so no MODEL needed)
• ee/lib/gitlab/llm/chain/requests/anthropic.rb (not a tool so not applicable)
• ee/lib/gitlab/llm/chain/tools/ci_editor_assistant/prompts/anthropic.rb
• ee/lib/gitlab/llm/chain/tools/epic_identifier/prompts/anthropic.rb
• ee/lib/gitlab/llm/chain/tools/epic_reader/prompts/anthropic.rb
• ee/lib/gitlab/llm/chain/tools/explain_code/prompts/anthropic.rb
• ee/lib/gitlab/llm/chain/tools/issue_identifier/prompts/anthropic.rb
• ee/lib/gitlab/llm/chain/tools/issue_reader/prompts/anthropic.rb
• ee/lib/gitlab/llm/chain/tools/refactor_code/prompts/anthropic.rb
• ee/lib/gitlab/llm/chain/tools/summarize_comments/prompts/anthropic.rb
• ee/lib/gitlab/llm/chain/tools/write_tests/prompts/anthropic.rb

changed milestone to %16.11

added bugfunctional devopsai-powered groupai framework sectiondata-science typebug workflowin review labels

assigned to @jessieay

added backend label

	1 Message
	CHANGELOG missing: If this merge request needs a changelog entry, add the Changelog trailer to the commit message you want to add to the changelog. If this merge request doesn't need a CHANGELOG entry, feel free to ignore this message.

Reviewer roulette

Category	Reviewer	Maintainer
backend	@jhyson (UTC+12, 16 hours ahead of author)	@dskim_gitlab (UTC+10, 14 hours ahead of author)

Please check reviewer's status!

• Reviewer is available!
• Reviewer is unavailable!

Please refer to documentation page for guidance on how you can benefit from the Reviewer Roulette, or use the GitLab Review Workload Dashboard to find other available reviewers.

If needed, you can retry the danger-review job that generated this comment.

Generated by Danger

added 1 commit

• 1d7b51d0 - Set claude 2.1 as model for slash commands

Compare with previous version

changed the description

added 1 commit

• a10b1a2d - Also set model for json reader

Compare with previous version

requested review from @lesley-r

added 1 commit

• 076f96a6 - Set claude 2.1 as model for slash commands

Compare with previous version

added 209 commits

• 076f96a6...b1f401f1 - 208 commits from branch master
• 7480a5d8 - Set claude 2.1 as model for slash commands

Compare with previous version

changed the description

changed the description

@jessieay Changes LGTM!

I also verified the original error with /explain on master and the fact that this MR fixes it.

@mfanGitLab, can you do the backend maintainer review? Thank you!

requested review from @mfanGitLab and removed review request for @lesley-r

mentioned in issue #455112 (closed)

resolved all threads

resolved all threads

approved this merge request

Thanks @jessieay ! This MR LGTM

We're missing the EE: true trailer, so I'll amend the commit to add that.

Pipeline's also failing due to job timeout so will trigger a new one and put MWPS

added pipeline:mr-approved label

@mfanGitLab, thanks for approving this merge request.

This is the first time the merge request has been approved. To ensure we don't only run predictive pipelines, and we don't break master, a new pipeline will be started shortly.

Please wait for the pipeline to start before resolving this discussion and set auto-merge for the new pipeline. See merging a merge request for more details.

resolved all threads

enabled an automatic merge when the pipeline for f528c42d succeeds

resolved all threads

E2E Test Result Summary

allure-report-publisher generated test report!

e2e-test-on-gdk: test report for 7480a5d8

expand test summary

+------------------------------------------------------------------+
|                          suites summary                          |
+-------------+--------+--------+---------+-------+-------+--------+
|             | passed | failed | skipped | flaky | total | result |
+-------------+--------+--------+---------+-------+-------+--------+
| Create      | 77     | 0      | 9       | 0     | 86    | ✅     |
| Plan        | 51     | 0      | 2       | 0     | 53    | ✅     |
| Package     | 24     | 0      | 6       | 0     | 30    | ✅     |
| Verify      | 35     | 0      | 1       | 0     | 36    | ✅     |
| Govern      | 66     | 0      | 0       | 0     | 66    | ✅     |
| Data Stores | 31     | 0      | 0       | 0     | 31    | ✅     |
| Release     | 5      | 0      | 0       | 0     | 5     | ✅     |
| Monitor     | 7      | 0      | 0       | 0     | 7     | ✅     |
| Manage      | 0      | 0      | 1       | 0     | 1     | ➖     |
| Analytics   | 2      | 0      | 0       | 0     | 2     | ✅     |
+-------------+--------+--------+---------+-------+-------+--------+
| Total       | 298    | 0      | 19      | 0     | 317   | ✅     |
+-------------+--------+--------+---------+-------+-------+--------+

merged

mentioned in commit f39a6bc8

mentioned in issue gitlab-org/modelops/ai-model-validation-and-research/ai-evaluation/ai-experiments#28

added workflowstaging-canary label and removed workflowin review label

added workflowcanary label and removed workflowstaging-canary label

added workflowstaging label and removed workflowcanary label

mentioned in issue gitlab-org/modelops/ai-model-validation-and-research/ai-evaluation/prompt-library#153 (closed)

added workflowproduction label and removed workflowstaging label

mentioned in issue #454849 (closed)

added workflowpost-deploy-db-production label and removed workflowproduction label

added releasedcandidate label

added releasedpublished label and removed releasedcandidate label

added pipelinetier-3 label