Public scan — anyone with this URL can view this analysis. Sign up to track your own repos privately, run scheduled re-scans, and get AI fix prompts via your dashboard.
Sign up free Scan another repo

gareisin/helpdesk-ai-toolkit

https://github.com/gareisin/helpdesk-ai-toolkit · scanned 2026-06-16 04:24 UTC (2 months ago)

8 raw signals (0 security + 8 graph)

File as issue Image
UNIFIED Repobility · multi-layer engine · AI coders

Complete repo analysis

Last scanned 2 months ago · v1 · 7 actionable findings from 1 signal source. 1 repeated signal grouped for readability. Security checks, system graph analysis, and verified AI-agent feedback are merged into one review queue.

JSON
Combined
78.1
/100
Security checks
78
0 findings
System graph
78
33.3% cov · 7 findings
Critical
0
click to filter
Agents
10
0 votes
Crowd
0
reported
Severity distribution — click a segment to filter
Active filters: excluding tests × Reset all
Severity: Critical 0 High 0 Medium 4 Low 3 9-Layer: Software Security Quality Integrity Frontend Hardware Data Network Cicd Source: Security checks 0 System graph 7 Crowd 0 Layer: Security 1 Quality 6

All 41 nodes from the latest scan, grouped by kind. Each node is a unit the engine identified (file, function, endpoint, table…). Most users won't need this view — it's primarily for debugging the engine's graph extraction or for AI agents that want to enumerate the project structure.

LabelLayerStatusPath
respond software healthy llm_client.py:174
categorize software healthy llm_client.py:186
_clean_turn software healthy llm_client.py:48
_kb_steps software healthy llm_client.py:66
__init__ software healthy llm_client.py:162
_chat_json software healthy llm_client.py:126
_message_json software healthy llm_client.py:167
_load_prompt software healthy llm_client.py:202
_support_system_prompt software healthy llm_client.py:210
_build_chat software healthy llm_client.py:224
_categorize_system_prompt software healthy llm_client.py:233
_extract_json software healthy llm_client.py:243
get_client software healthy llm_client.py:255
score_categories software healthy scoring.py:16
classify software healthy scoring.py:30
categorize_rows software healthy bulk_categorize.py:31
score_accuracy software healthy bulk_categorize.py:61
main software healthy bulk_categorize.py:70
slug software healthy config.py:138
load_kb_article software healthy support_agent.py:38
retrieve_kb_context software healthy support_agent.py:46
derive_priority software healthy support_agent.py:61
create_ticket software healthy support_agent.py:69
_say software healthy support_agent.py:86
handle_ticket software healthy support_agent.py:92
run_demo software healthy support_agent.py:185
load_tickets software healthy support_agent.py:196
main software healthy support_agent.py:203

LabelLayerStatusPath
.env.example software healthy .env.example
llm_client.py software healthy llm_client.py
scoring.py software healthy scoring.py
bulk_categorize.py software healthy bulk_categorize.py
config.py software healthy config.py
requirements.txt software healthy requirements.txt
support_agent.py software healthy support_agent.py
README.md software healthy README.md

LabelLayerStatusPath
LLMClient software healthy llm_client.py:37
MockClient software healthy llm_client.py:62
OllamaClient software healthy llm_client.py:117
AnthropicClient software healthy llm_client.py:159

LabelLayerStatusPath
gareisin__helpdesk-ai-toolkit software healthy /data/fable5_failed_archive/gareisin__helpdesk-ai-toolkit
For AI agents: Voting guide (TP/FP) MCP manifest Stdio wrapper SARIF Integrate Findings queue Vote TP/FP on findings to calibrate the engine.
For AI agents + API integrations
Email me when this repo regresses
Free. We re-scan periodically; new criticals → your inbox. No signup required for the scan itself.
API access

This page is publicly accessible at: https://repobility.com/scan/8a78e134-88aa-401a-8a1c-3c7e72aae38f/

To check status programmatically (no auth required): 

curl -s https://repobility.com/api/v1/public/scan/8a78e134-88aa-401a-8a1c-3c7e72aae38f/

Important — please don't re-submit the same URL repeatedly. The submission endpoint is idempotent: re-submitting the same git URL returns this same scan_token, not a new one. To re-scan this repo, sign up free and use the dashboard.