torbjorn/my-pal-mcp-server
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: refactored and improved codereview in line with precommit. Reviews are now either external (default) or internal. Takes away anxiety and loss of tokens when Claude incorrectly decides to be 'confident' about its own changes and bungle things up.

Browse Source 
fix: Minor tweaks to prompts
fix: Improved support for smaller models that struggle with strict structured JSON output
Rearranged reasons to use the MCP above quick start (collapsed)
This commit is contained in:
Fahad
2025-08-21 14:04:32 +04:00
parent d30c212029
commit 80d21e57c0
6 changed files with 300 additions and 122 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
simulator_tests/test_codereview_validation.py
View File

@@ -316,10 +316,6 @@ class ConfigurationManager:
self.logger.error("Relevant context not properly tracked")
return False
if review_status.get("review_confidence") != "high":
self.logger.error("Review confidence level not properly tracked")
return False
# Check issues by severity
issues_by_severity = review_status.get("issues_by_severity", {})
if issues_by_severity.get("critical", 0) != 2:
@@ -571,7 +567,7 @@ class ConfigurationManager:
{"severity": "critical", "description": "Hardcoded API key security vulnerability"},
{"severity": "high", "description": "Performance bottleneck in payment history"},
],
"confidence": "certain", # This should skip expert analysis
"review_validation_type": "internal", # This should skip expert analysis
"model": "flash",
},
)
@@ -596,7 +592,10 @@ class ConfigurationManager:
return False
expert_analysis = response_certain_data.get("expert_analysis", {})
if expert_analysis.get("status") != "skipped_due_to_certain_review_confidence":
if expert_analysis.get("status") not in [
"skipped_due_to_certain_review_confidence",
"skipped_due_to_internal_analysis_type",
]:
self.logger.error("Expert analysis should be skipped for certain confidence")
return False