feat: Enhance Markdown formatting in output schemas for improved readability and clarity#169
Conversation
…ability and clarity
rostilos
changed the title
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (1)
💤 Files with no reviewable changes (1)
📝 WalkthroughWalkthroughUpdates include a frontend submodule reference change, deletion of a generated test-report artifact, minor license header edit, and expanded Markdown-formatting guidance in prompt templates and schema field descriptions for the inference-orchestrator. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
📝 Coding Plan
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 |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
🧹 Nitpick comments (1)
python-ecosystem/inference-orchestrator/src/utils/prompts/constants_stage_1.py (1)
128-130: Consider centralizing Markdown-format guidance text to prevent drift.The same formatting rules now appear in multiple prompt/schema locations; extracting a shared constant/template would make future edits safer and keep Stage 1/Stage 2/schema wording in sync.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@python-ecosystem/inference-orchestrator/src/utils/prompts/constants_stage_1.py` around lines 128 - 130, Extract the repeated Markdown-format guidance into a single shared constant (e.g., PROMPT_MARKDOWN_GUIDANCE) and replace the duplicate literal strings used for the "reason", "resolutionReason", and "suggestedFixDescription" entries in constants_stage_1.py with that constant; update any other prompt/schema modules that contain the same text to import and reuse this constant so Stage 1/Stage 2/schema wording remains centralized and consistent, and ensure the constant name is exported so callers (prompt builders that reference "reason", "resolutionReason", or "suggestedFixDescription") can reference it.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Nitpick comments:
In
`@python-ecosystem/inference-orchestrator/src/utils/prompts/constants_stage_1.py`:
- Around line 128-130: Extract the repeated Markdown-format guidance into a
single shared constant (e.g., PROMPT_MARKDOWN_GUIDANCE) and replace the
duplicate literal strings used for the "reason", "resolutionReason", and
"suggestedFixDescription" entries in constants_stage_1.py with that constant;
update any other prompt/schema modules that contain the same text to import and
reuse this constant so Stage 1/Stage 2/schema wording remains centralized and
consistent, and ensure the constant name is exported so callers (prompt builders
that reference "reason", "resolutionReason", or "suggestedFixDescription") can
reference it.
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: d9d7751b-c959-40e5-8994-4451fa1bfd79
📒 Files selected for processing (5)
frontendjava-ecosystem/target/failsafe-reports/failsafe-summary.xmlpython-ecosystem/inference-orchestrator/src/model/output_schemas.pypython-ecosystem/inference-orchestrator/src/utils/prompts/constants_stage_1.pypython-ecosystem/inference-orchestrator/src/utils/prompts/constants_stage_2.py
💤 Files with no reviewable changes (1)
- java-ecosystem/target/failsafe-reports/failsafe-summary.xml
|
| Status | PASS WITH WARNINGS |
| Risk Level | LOW |
| Review Coverage | 5 files analyzed in depth |
| Confidence | HIGH |
Executive Summary
This PR updates Markdown formatting within output schemas and prompt constants to improve readability and clarity. While the changes are primarily cosmetic, they affect the structure of strings processed by the inference orchestrator. The primary risk involves potential inconsistencies between Stage 1 and Stage 2 prompts, which could impact downstream regex-based parsing or JSON extraction.
Recommendation
Decision: PASS WITH WARNINGS
The PR is technically sound, but approval is conditioned on verifying that Markdown enhancements are applied consistently across both pipeline stages. Ensure that updated formatting does not interfere with existing data flow parsers before merging.
Issues Overview
| Severity | Count | |
|---|---|---|
| 🔵 Low | 1 | Minor issues and improvements |
Analysis completed on 2026-03-17 07:51:13 | View Full Report | Pull Request
📋 Detailed Issues (1)
🔵 Low Severity Issues
Id on Platform: 3805
Category: 🏗️ Architecture
File: .../prompts/constants_stage_2.py:1
Potential Formatting Inconsistency Between Stage 1 and Stage 2 Prompts
Potential Formatting Inconsistency Between Stage 1 and Stage 2 Prompts
The PR aims to enhance Markdown formatting in output schemas. There is a risk that formatting updates applied to constants_stage_2.py (or its associated schema) may not be mirrored in constants_stage_1.py, leading to a disjointed user experience or inconsistent LLM parsing behavior across the inference pipeline stages.
Evidence: Dependency analysis shows constants_stage_2.py is linked to constants_stage_1.py within the same package. Changes to output schemas typically require synchronization across all pipeline stages to ensure the LLM maintains a consistent 'persona' and formatting style.
Business impact: Inconsistent formatting can lead to downstream parsing errors if regex or JSON extractors expect a unified Markdown structure across different stages of the inference orchestrator.
Also affects: python-ecosystem/inference-orchestrator/src/utils/prompts/constants_stage_1.py
💡 Suggested Fix
Verify that any Markdown enhancements (such as bolding keys, list indentation, or code block usage) are applied consistently to both constants_stage_1.py and constants_stage_2.py. If a shared schema utility exists, consider centralizing the formatting logic there.
Files Affected
- .../prompts/constants_stage_2.py: 1 issue
1 participant
Summary by CodeRabbit
Documentation
Chores