docs(audit): sync Mermaid diagrams with v0.4.0 components#21
Merged
Conversation
ARCHITECTURE.md (layered subsystem diagram): - Runner node now lists CopilotSdkAgentRunner, HybridAgentRunner, and AutopilotRunner alongside AdaptiveRunner / MicrosoftAgentRunner so the diagram matches src/Drederick/Agent/ + src/Drederick/Autopilot/ today. POST_EXPLOITATION.md (post-ex data flow): - LLM node now includes LlmExecShellTool and LlmNotebookTool in addition to LlmExploitTools, reflecting src/Drederick/Exploit/LlmExecShellTool.cs and src/Drederick/Agent/LlmNotebookTool.cs. Other diagrams reviewed and current: - README.md short architecture diagram (already mentions HybridAgentRunner). - docs/UI.md (UI→Host→Scanners — structurally accurate). - docs/DATASETTE.md (ER diagram — schema accurate). Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Pass 4 of the docs audit: walk every ```mermaid block and reconcile against v0.4.0 reality (
src/Drederick/tree,AGENTS.mdfile→concept map).Diagrams reviewed
README.md:409docs/ARCHITECTURE.md:74docs/POST_EXPLOITATION.md:151docs/UI.md:147docs/DATASETTE.md:274SqliteReport.cs.ARCHITECTURE.md — Runner node
Before:
AdaptiveRunner (deterministic)+MicrosoftAgentRunner (LLM)only.After: adds
CopilotSdkAgentRunner(Copilot LLM provider),HybridAgentRunner(LLM-first with fallback, wired via--agent=hybrid), andAutopilotRunner(the recon→exploit→loot loop).All four runners exist in the tree today (
src/Drederick/Agent/{HybridAgentRunner,CopilotSdkAgentRunner}.cs,src/Drederick/Autopilot/AutopilotRunner.cs) and are documented in theAGENTS.mdfile→concept map.POST_EXPLOITATION.md — LLM node
Before:
LlmExploitToolsonly.After: also lists
LlmExecShellTool(src/Drederick/Exploit/LlmExecShellTool.cs) andLlmNotebookTool(src/Drederick/Agent/LlmNotebookTool.cs, thetake_notetool wired in v0.4.0). Both are LLM-callable surfaces the planner uses during post-ex.Verified-current (no edits)
FightNotebook/FightCorpus/Scaffolding/MalleableProfileLibrary/KbSubstitutionResolverare already represented in the ARCHITECTURE.md diagram (Present node, Exploit node, Empire C2 group).JeopardySwarmlives in a parallel pipeline that's described in adjacent prose +docs/JEOPARDY.md; no separate node added (out of scope for the main offensive-harness diagram).Minimal-diff updates only — no aesthetic redesign, no unrelated prose churn.
Co-authored-by: Copilot 223556219+Copilot@users.noreply.github.com