feat: v4.0.0 — Novel R&D + Tool Coverage Expansion#19
Merged
Conversation
…ated security tools, AI providers, and workflow management, including Docker deployment.
Track A — AI/Agent R&D (7 items) - A1 RAG knowledge base (SQLite + FTS5 + optional embeddings) - A2 Multi-agent debate triage (red/blue/judge) - A3 Vision-LLM screenshot analysis (playwright + visual triage) - A4 Plugin contract + Ollama/OpenAI-compat providers - A5 Learned tool selection (offline ranker + telemetry) - A6 Eval harness (3 tiers: parser/workflow/agent) - A7 Judge model upgrade for think_deeply Track B — Tool Coverage Expansion (7 items) - B8 Active Directory toolkit (4 tools) - B9 Mobile Android toolkit (3 tools) - B10 API-spec fuzzers (3 tools) - B11 SAST + secrets at scale (3 tools) - B12 LLM red-team toolkit (3 tools) - B13 Burp/ZAP automation bridge (2 tools) - B14 SARIF + DefectDojo + Slack exporters 50 tools registered. 6 AI providers. 296 tests pass (+93% from v3). All v3 hardening preserved (key scrub, prompt-injection delimiters, DNS-resolve scope, atomic checkpoints, lazy tool loading). New CLI surfaces: guardian kb, guardian telemetry. New workflows shipped: web_pentest_with_debate, web_visual_pentest, ad_assessment, mobile_android, llm_redteam, sast_review, api_pentest_v2.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
v4.0.0 ships 14 items across 2 tracks: Novel AI/Agent R&D + Tool Coverage Expansion. 296 tests pass (+93% from v3 baseline of 153). All v3 hardening preserved.
Track A — AI / Agent R&D (7)
think_deeply— ~10x cost reductionTrack B — Tool Coverage Expansion (7)
Numbers
guardian kb,guardian telemetrySecurity posture
All v3 hardening preserved:
Test plan
pytest tests/ evals/— 296 passguardian --helpstartup time <500msguardian kb seed && guardian kb query "log4j JNDI"— retrieval worksguardian telemetry export ./reports --out t.jsonl && guardian telemetry train t.jsonl— round-trip worksweb_pentest_with_debateagainst authorized DVWA instanceweb_visual_pentestwith--provider openaiDocs
CHANGELOG.md— full v4.0.0 entrydocs/V4_FEATURES.md— feature reference per itemdocs/EVAL_GUIDE.md— eval harness usagedocs/PLUGIN_GUIDE.md— third-party provider/tool authoringREADME.md— features section, latest updates, v4 quick-startQUICKSTART.md— v4 quick-wins added