feat: sentinel-based review cleanup + system prompt file + security review

Sentinel-based cleanup:
- Reviews embed <!-- review-bot:NAME --> in body (hidden HTML comment)
- Cleanup matches by sentinel, not token identity
- Each reviewer-name is a logical identity (sonnet, gpt, security)
- Same token can run multiple review types without conflict
- No extra API scopes needed

System prompt file (--system-prompt-file / SYSTEM_PROMPT_FILE):
- Loads a local file with additional review instructions
- Appended to system base as "Additional Review Instructions"
- Enables specialized reviews (security, performance, etc.)
- Partially addresses #5

Security review:
- SECURITY_REVIEW.md prompt focused on vulnerabilities
- 3rd CI matrix entry using same token, different prompt
- Focus: injection, auth, secrets, input validation, crypto, races

CI changes:
- REVIEWER_NAME passed from matrix.name
- SYSTEM_PROMPT_FILE passed from matrix (empty for standard reviews)
- 3 reviewers: sonnet (general), gpt (general), security (focused)

.gitea/actions/review/action.yml

@@ -70,6 +70,10 @@ inputs:
     description: 'Delete previous review from same bot before posting. Accepts: true/1/yes or false/0/no (default true)'
     required: false
     default: 'true'
+  system-prompt-file:
+    description: 'Local file with additional system prompt instructions (e.g. security review focus)'
+    required: false
+    default: ''
 
 runs:
   using: 'composite'
@@ -150,6 +154,7 @@ runs:
         LLM_TIMEOUT: ${{ inputs.timeout }}
         LLM_PROVIDER: ${{ inputs.llm-provider }}
         UPDATE_EXISTING: ${{ inputs.update-existing }}
+        SYSTEM_PROMPT_FILE: ${{ inputs.system-prompt-file }}
       run: |
         ARGS=""
         if [ "${{ inputs.dry-run }}" = "true" ]; then