fix(prompts): narrate the user's task, not sandbox or tool plumbing (E4)

The agent told a desktop user "The sandbox blocks network, so this needs
to go through it explicitly." Output guidance now says progress updates
narrate what was found, done next and decided, never sandboxing, network
routing, schema loading, tool search, retries or batching. A gate that
actually blocks and needs the user is still named, in the user's terms.

Checks: cargo test -p codewhale-tui --lib prompts:: (run with the web_run
and runtime filters): 146 passed, 0 failed.

Refs Hmbown/codewhale-app#99

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>

crates/tui/src/prompts/text.rs

@@ -143,6 +143,8 @@ You are rendering into a terminal, not a browser. Markdown tables almost never r
 Prefer plain prose for explanations; bulleted or numbered lists for sequential or parallel items; code blocks for code, paths, commands, and structured output; and definition-style lists (`- **Label**: value`) for comparisons or summaries.
 
 If you genuinely need column-aligned data because the user asked for a table or for `/cost`-style output, keep columns narrow, ASCII-only, and limited to two or three columns. Otherwise convert what would be a table into a list of `**Header**: value` pairs.
+
+Progress updates narrate the user's task — what you found, what you are doing next, what you decided — not the harness. Do not narrate tool plumbing: sandboxing, network routing, schema loading, tool search, retries, batching, or which tool you will call. When a gate actually blocks the work and needs the user, say what is blocked and what they can do, in their terms; otherwise just proceed.
 "#;
 
 // ── Personality overlays — voice and tone ──────────────────────────