feat(persona): add role-based review personas (#51)
CI / test (pull_request) Successful in 15s
CI / review (/openai/v1, gpt-4.1, gpt41, openai, GPT_REVIEW_TOKEN) (pull_request) Failing after 17s
CI / review (/anthropic/v1, claude-sonnet-4-6, sonnet, anthropic, SONNET_REVIEW_TOKEN) (pull_request) Failing after 17s
CI / review (/openai/v1, gpt-4.1-mini, gpt41-mini, openai, GPT_REVIEW_TOKEN) (pull_request) Failing after 16s
CI / review (/openai/v1, gpt-5-mini, gpt5-mini, openai, GPT_REVIEW_TOKEN) (pull_request) Failing after 14s
CI / review (/openai/v1, gpt-5, security, openai, SECURITY_REVIEW.md, SECURITY_REVIEW_TOKEN) (pull_request) Successful in 1m28s
CI / review (/openai/v1, gpt-5, gpt, openai, GPT_REVIEW_TOKEN) (pull_request) Successful in 1m41s
CI / test (pull_request) Successful in 15s
CI / review (/openai/v1, gpt-4.1, gpt41, openai, GPT_REVIEW_TOKEN) (pull_request) Failing after 17s
CI / review (/anthropic/v1, claude-sonnet-4-6, sonnet, anthropic, SONNET_REVIEW_TOKEN) (pull_request) Failing after 17s
CI / review (/openai/v1, gpt-4.1-mini, gpt41-mini, openai, GPT_REVIEW_TOKEN) (pull_request) Failing after 16s
CI / review (/openai/v1, gpt-5-mini, gpt5-mini, openai, GPT_REVIEW_TOKEN) (pull_request) Failing after 14s
CI / review (/openai/v1, gpt-5, security, openai, SECURITY_REVIEW.md, SECURITY_REVIEW_TOKEN) (pull_request) Successful in 1m28s
CI / review (/openai/v1, gpt-5, gpt, openai, GPT_REVIEW_TOKEN) (pull_request) Successful in 1m41s
Implement role-based review personas that provide specialized review focus: - Security: vulnerabilities, auth, secrets, injection attacks - Architect: design patterns, code organization, API contracts - Docs: documentation quality, API clarity, error messages Changes: - Add persona loading from JSON files and embedded built-ins - Add --persona and --persona-file CLI flags (mutually exclusive) - Add BuildPersonaSystemPrompt for persona-specific prompts - Add FormatMarkdownWithDisplay for persona display names - Update action.yml with persona and persona-file inputs - Add comprehensive tests for all new functionality - Document personas in README with examples The persona system replaces the generic 'You are an expert code reviewer' prompt with domain-specific identity, focus areas, ignore list, and severity calibration. This reduces redundancy between multiple reviewers and catches domain-specific issues that generic reviewers miss. Closes #51
This commit is contained in:
@@ -71,6 +71,14 @@ inputs:
|
||||
required: false
|
||||
default: 'true'
|
||||
system-prompt-file:
|
||||
persona:
|
||||
description: 'Built-in persona name (security, architect, docs)'
|
||||
required: false
|
||||
default: ''
|
||||
persona-file:
|
||||
description: 'Path to persona JSON file with custom review focus'
|
||||
required: false
|
||||
default: ''
|
||||
description: 'Local file with additional system prompt instructions (e.g. security review focus)'
|
||||
required: false
|
||||
default: ''
|
||||
@@ -155,6 +163,8 @@ runs:
|
||||
LLM_PROVIDER: ${{ inputs.llm-provider }}
|
||||
UPDATE_EXISTING: ${{ inputs.update-existing }}
|
||||
SYSTEM_PROMPT_FILE: ${{ inputs.system-prompt-file }}
|
||||
PERSONA: ${{ inputs.persona }}
|
||||
PERSONA_FILE: ${{ inputs.persona-file }}
|
||||
run: |
|
||||
ARGS=""
|
||||
if [ "${{ inputs.dry-run }}" = "true" ]; then
|
||||
|
||||
Reference in New Issue
Block a user