feat: add DetectiveAI investigation kit - #363
Open
YashSatyawali wants to merge 1 commit into
Open
Conversation
Contributor
|
Important Review skippedToo many files! This PR contains 167 files, which is 67 over the limit of 100. To get a review, reduce the PR to 100 files or fewer by splitting it into smaller PRs or changing its base branch. Upgrade to a paid plan to raise the limit. This review couldn't start because sufficient usage credits or metered capacity aren't available. Add credits or update usage-based reviews in the billing tab, then retry. ⚙️ Run configurationConfiguration used: Repository UI (base), Organization UI (inherited) Review profile: ASSERTIVE Plan: Pro Plus Run ID: ⛔ Files ignored due to path filters (7)
📒 Files selected for processing (167)
You can disable this status message by setting the Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Contributor
:robot_face: AgentKit Structural ValidationNew Contributions Detected
Check Results
🎉 All checks passed! This contribution follows the AgentKit structure. |
Author
|
Hi, I noticed that the studio-check workflow is failing at the actions/checkout@v4 step because GitHub is refusing to checkout fork PR code from the workflow_run workflow: Refusing to check out fork pull request code from a 'workflow_run' workflow The checkout is running with allow-unsafe-pr-checkout: false. It looks like this is related to the repository workflow/security configuration rather than the contribution itself. Could a maintainer please verify the studio-check workflow for fork PRs? The Node.js 20 message appears to be a separate deprecation warning. |
Contributor
|
@coderabbitai review |
Contributor
|
/validate |
Contributor
|
📡 Running Studio validation — results will appear here shortly. |
Contributor
Studio Runtime Validation (Phase 2)❌ Studio validation failed. The kit was rejected by Lamatic Studio. Errorsdetective-ai
Please fix the errors above and push a new commit to re-run validation. |
Contributor
|
@coderabbitai review |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Overview
DetectiveAI is an AI-powered detective investigation game built as a Lamatic AgentKit kit.
It combines deterministic game mechanics with Lamatic-powered AI agents for suspect
interrogation, forensic evidence examination, and final case reasoning evaluation.
Problem
Most AI agent demos focus on isolated conversations or single-turn tasks.
DetectiveAI demonstrates how multiple AI workflows can operate inside a
stateful investigation while keeping authoritative game state and sensitive
ground truth outside the LLM.
Approach
Result
The complete investigation can be played end-to-end through the CLI or web UI.
The included
the_midnight_archivescenario supports:Validation
Tradeoffs / Design Decisions
The GameEngine remains authoritative for objective game state,
while Lamatic agents are treated as untrusted reasoning components.
Sensitive solution information is never provided to player-facing
agents or exposed through the frontend.