docs: harden Mermaid diagrams for GitHub

Replace Mermaid blocks with punctuation-free quoted labels and remove subgraphs to avoid GitHub renderer parse errors.

Made-with: Cursor

Author: Sayeem3051

README.md

@@ -52,11 +52,11 @@ If you want the shortest summary: **Cursor/Copilot help you ask; ctxeng helps yo
 
 ```mermaid
 flowchart LR
-  U[You / task] --> C[ctxeng]
-  R[(Your repo)] --> C
-  C --> O[LLM-ready context (XML, Markdown, plain)]
-  O --> A[LLM (ChatGPT/Claude/Gemini/API)]
-  A --> B[Better answers, less hallucination]
+  U["You and your task"] --> C["ctxeng"]
+  R["Your repo"] --> C
+  C --> O["LLM ready context"]
+  O --> A["LLM"]
+  A --> B["Better answers"]
 ```
 
 Docs:

docs/ARCHITECTURE.md

@@ -4,33 +4,9 @@
 
 ```mermaid
 flowchart TD
-  subgraph Inputs
-    Q[Task / query]
-    R[(Repository root)]
-    O[Options / flags]
-  end
-
-  subgraph Pipeline
-    D[Discover files]
-    S[Score + rank]
-    IG[Import-graph expansion (optional)]
-    RAG[RAG chunk retrieval (optional)]
-    SK[AST skeleton (optional)]
-    RX[Redact secrets + PII (optional, default on)]
-    B[Fit token budget]
-    RND[Render output (XML, Markdown, plain)]
-  end
-
-  Q --> S
-  R --> D --> S --> IG --> RAG --> SK --> RX --> B --> RND
-  O --> D
-  O --> S
-  O --> IG
-  O --> RAG
-  O --> SK
-  O --> RX
-  O --> B
-  RND --> OUT[Context output + metadata]
+  Q["Task query"] --> S["Score and rank"]
+  R["Repo root"] --> D["Discover files"] --> S --> IG["Import graph optional"] --> RAG["RAG optional"] --> SK["Skeleton optional"] --> RX["Redact optional"] --> B["Fit token budget"] --> RND["Render output"]
+  RND --> OUT["Context output"]
 ```
 
 ## Key design goals