srivatsa-source/DockDesk Neural Auditor

Local-first semantic audit of code vs documentation using Ollama. Auto-tunes model selection for your codebase.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
modelDefault LLM model (used for both detection and fix if dedicated models are not set). Recommended audit-suitable models: - qwen2.5-coder:3b (fast, <5k LOC) - qwen2.5-coder:7b (default, balanced) - codellama:7b (alternative, code-focused) - qwen2.5-coder:14b (thorough, >50k LOC) Use 'auto' for automatic selection based on codebase size. noqwen2.5-coder:7b
detect_model[DEPRECATED] Use reasoning_model instead. Model for Phase 1 (detection / risk assessment). no""
fix_model[DEPRECATED] Use reasoning_model instead. Model for Phase 2 (fix generation). no""
reasoning_modelDeepSeek-R1 reasoning model for logical risk assessment and safety judgement. Default: deepseek-r1-distill-qwen:1.5b This model acts as the "brain" — it judges risk, validates fixes, and decides push safety. nodeepseek-r1:1.5b
discord_webhookDiscord webhook URL for posting audit summaries and push-guard notifications. Leave empty to disable Discord notifications. no""
auto_tuneAutomatically select the best model based on codebase LOC (overrides model input)nofalse
ollama_hostOllama API endpoint (for self-hosted instances)nohttp://localhost:11434
fail_on_riskRisk level that triggers workflow failure (HIGH, MEDIUM, LOW)noHIGH
output_formatOutput format: md (markdown), json, sarif (for VS Code/IDE integration)nomd
auto_fixAutomatically apply documentation fixesnofalse
workspace_pathPath to the workspace to audit (relative to repository root)no.
skip_ragSkip RAG retrieval for faster audits and reduced disk usage (recommended for CI)nofalse
custom_rulesComma-separated custom audit rules injected into LLM prompts. Example: "Flag hardcoded secrets,Ensure all public functions have docstrings" no""
python_versionPython version to useno3.11
namedescription
report_pathPath to the generated audit report
statusAudit status (pass/fail)
files_auditedNumber of files audited
high_risk_countNumber of HIGH risk findings
fixes_appliedNumber of fixes automatically applied
sarif_pathPath to SARIF report (for GitHub Code Scanning integration)