feat: Add research-decision-brief-agent template - #340
Conversation
|
Important Review skippedNo new commits to review since the last review. ⚙️ Run configurationConfiguration used: Repository UI (base), Organization UI (inherited) Review profile: ASSERTIVE Plan: Pro Plus Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
WalkthroughThe change adds a Research Decision Brief Agent template. It defines the agent contract and safeguards, connects structured research input to an evidence-assessment LLM flow, and documents configuration, invocation, and output behavior. ChangesResearch Decision Brief Agent
Suggested reviewers: 🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
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 |
:robot_face: AgentKit Structural ValidationNew Contributions Detected
Check Results
🎉 All checks passed! This contribution follows the AgentKit structure. |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 4
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@kits/research-decision-brief-agent/.gitignore`:
- Around line 1-2: Update the environment-file patterns in .gitignore so .env
and its .env.* variants are ignored, while explicitly allowing example
environment files such as .env.example to remain trackable.
In `@kits/research-decision-brief-agent/flows/research-decision-brief-agent.ts`:
- Around line 41-51: Update the triggerNode_1 inline request schema by defining
advance_schema with fields for objective, constraints, timeline, audience, and
evidence, matching the inputs referenced by the prompt while preserving the
existing trigger configuration.
In
`@kits/research-decision-brief-agent/model-configs/research-decision-brief-agent_assess-evidence.ts`:
- Around line 4-8: Replace the recursive configuration in
kits/research-decision-brief-agent/model-configs/research-decision-brief-agent_assess-evidence.ts
by regenerating generativeModelName from Studio with a concrete provider and
model, while preserving Studio-generated credential identifiers. In
kits/research-decision-brief-agent/flows/research-decision-brief-agent.ts lines
75-78, set memories and messages to "[]".
In `@kits/research-decision-brief-agent/README.md`:
- Line 3: Add one blank line after each Markdown section heading in the README,
including “Problem Statement” and the headings at the referenced locations, so
the document satisfies markdownlint MD022 without changing the section content.
🪄 Autofix
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository UI (base), Organization UI (inherited)
Review profile: ASSERTIVE
Plan: Pro Plus
Run ID: b75be8f2-eaa2-441e-9ff2-cee971192f3f
📒 Files selected for processing (9)
kits/research-decision-brief-agent/.gitignorekits/research-decision-brief-agent/README.mdkits/research-decision-brief-agent/agent.mdkits/research-decision-brief-agent/constitutions/default.mdkits/research-decision-brief-agent/flows/research-decision-brief-agent.tskits/research-decision-brief-agent/lamatic.config.tskits/research-decision-brief-agent/model-configs/research-decision-brief-agent_assess-evidence.tskits/research-decision-brief-agent/prompts/research-decision-brief-agent_assess-evidence_system.mdkits/research-decision-brief-agent/prompts/research-decision-brief-agent_assess-evidence_user.md
There was a problem hiding this comment.
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
kits/research-decision-brief-agent/flows/research-decision-brief-agent.ts (1)
83-95: 🗄️ Data Integrity & Integration | 🟠 Major | ⚡ Quick winUse
responseNodeforgraphqlResponseNodeSet this node’s
typeto"responseNode". The current"dynamicNode"type does not declare the API response node, so theresponseEdgeand output mapping may not produce the flow response.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@kits/research-decision-brief-agent/flows/research-decision-brief-agent.ts` around lines 83 - 95, Update the node with id "graphqlResponseNode_201" and nodeName "API Response" to use type "responseNode" instead of "dynamicNode", preserving its existing responseEdge compatibility and outputMapping.
♻️ Duplicate comments (1)
kits/research-decision-brief-agent/model-configs/research-decision-brief-agent_assess-evidence.ts (1)
5-10: 🗄️ Data Integrity & Integration | 🟠 Major | 🏗️ Heavy liftMission requirement: complete the model configuration before deployment.
generativeModelNameomits the provider and credential metadata present in the supplied Studio-generated configuration contract. The flow references this artifact, so the LLM node may not resolve a provider credential at runtime.Regenerate this configuration in Lamatic Studio with a valid provider and credential. Do not hand-edit credential identifiers.
This repeats the earlier model-configuration finding; the current change adds a model name but does not complete the configuration.
#!/bin/bash set -euo pipefail rg -n -C 6 \ 'generativeModelName|model_name|provider_name|credentialId|credential_name' \ kits --glob 'model-configs/*.ts'Based on learnings: Preserve Studio-generated credential identifiers and regenerate the artifact instead of editing identifiers manually.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@kits/research-decision-brief-agent/model-configs/research-decision-brief-agent_assess-evidence.ts` around lines 5 - 10, Complete the generativeModelName configuration with the provider and credential metadata required by the Studio-generated contract, using a valid configuration regenerated from Lamatic Studio. Do not manually invent or edit credential identifiers; preserve the generated provider_name, credentialId, and credential_name values.Source: Learnings
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Outside diff comments:
In `@kits/research-decision-brief-agent/flows/research-decision-brief-agent.ts`:
- Around line 83-95: Update the node with id "graphqlResponseNode_201" and
nodeName "API Response" to use type "responseNode" instead of "dynamicNode",
preserving its existing responseEdge compatibility and outputMapping.
---
Duplicate comments:
In
`@kits/research-decision-brief-agent/model-configs/research-decision-brief-agent_assess-evidence.ts`:
- Around line 5-10: Complete the generativeModelName configuration with the
provider and credential metadata required by the Studio-generated contract,
using a valid configuration regenerated from Lamatic Studio. Do not manually
invent or edit credential identifiers; preserve the generated provider_name,
credentialId, and credential_name values.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository UI (base), Organization UI (inherited)
Review profile: ASSERTIVE
Plan: Pro Plus
Run ID: 19c5b3f3-8ee3-4c66-aae5-b0a897f2ec82
📒 Files selected for processing (4)
kits/research-decision-brief-agent/.gitignorekits/research-decision-brief-agent/README.mdkits/research-decision-brief-agent/flows/research-decision-brief-agent.tskits/research-decision-brief-agent/model-configs/research-decision-brief-agent_assess-evidence.ts
|
/validate |
|
📡 Running Studio validation — results will appear here shortly. |
Studio Runtime Validation (Phase 2)❌ Studio validation failed. The kit was rejected by Lamatic Studio. Errorsresearch-decision-brief-agent
Please fix the errors above and push a new commit to re-run validation. |
|
@yooumarr please check the above error |
|
/validate |
|
📡 Running Studio validation — results will appear here shortly. |
|
@coderabbitai review |
|
|
/validate |
|
📡 Running Studio validation — results will appear here shortly. |
1 similar comment
|
📡 Running Studio validation — results will appear here shortly. |
|
phase 2 is failing @yooumarr https://github.com/Lamatic/AgentKit/actions/runs/31719623147 |
|
@coderabbitai review |
|
2 participants
Summary
Adds a new template: research-decision-brief-agent.
This template converts research evidence into an actionable decision brief for product and engineering teams, including:
Why this is useful
Teams often have paper summaries but no clear implementation direction. This template bridges that gap by producing decision-ready output instead of plain summarization.
Included files
kits/research-decision-brief-agent/lamatic.config.tskits/research-decision-brief-agent/agent.mdkits/research-decision-brief-agent/README.mdkits/research-decision-brief-agent/flows/research-decision-brief-agent.tskits/research-decision-brief-agent/constitutions/default.mdkits/research-decision-brief-agent/prompts/research-decision-brief-agent_assess-evidence_system.mdkits/research-decision-brief-agent/prompts/research-decision-brief-agent_assess-evidence_user.mdkits/research-decision-brief-agent/model-configs/research-decision-brief-agent_assess-evidence.tskits/research-decision-brief-agent/.gitignoreresearch-decision-brief-agenttemplate..gitignorefiles.triggerNodethat accepts structured research objectives, constraints, timeline, audience, and evidence.dynamicNodethat usesgpt-4o-minito assess evidence and generate a decision brief.decision_brief.defaultEdgeandresponseEdgeflow transitions.