docs: capture the content/context-surface underuse task from the operator transcript

Nine of ten turns in the exported transcript answered in markdown prose where
the content surface (grids/cards) and context surface should have carried it.
Records each turn against the surface it should drive, plus two security items
found in the same evidence: a cleartext rpcpassword rendered into the chat, and
the RED screen_outbound test that lets a seed-shaped body reach a third-party
inference provider.

.planning/todos/pending/2026-08-06-aiui-answers-in-prose-instead-of-the-content-and-context-surfaces.md

@@ -0,0 +1,76 @@
+# AIUI answers in prose where the content + context surfaces should carry it
+
+Operator-reported 2026-08-06, with a full exported transcript as evidence
+("Exploring My Node", exported 8/7/2026 12:57 AM). Add to the
+fix → test → debug → fix loop.
+
+## The complaint
+
+Almost every answer in that transcript is rendered as **markdown prose in the chat
+window** — bullet lists, fenced code blocks, a hand-built table — when the phase
+already has a **content surface** (cards/grids) and a **context surface** for exactly
+this. The chat window is doing work the surfaces exist to do, so the product reads as
+a chatbot that talks about the node rather than an interface onto it.
+
+## Every case in the transcript, and what should have rendered
+
+| Turn | Rendered as | Should drive |
+|---|---|---|
+| "What apps do I have installed?" | bulleted list of 6 apps | app grid — icon, status pill, Open action per app |
+| "How's my Bitcoin node doing?" | bold key/value prose | node status card — height, sync %, mempool gauge, fee band |
+| "What's my Lightning balance?" | bold key/value prose | balance card + channel list (5 channels, 8 peers) |
+| "What files do I have stored?" | bulleted list of 10 of 47 | file grid — type icons, folders navigable, open actions |
+| "Read my todo.txt" | fenced code block | file viewer surface |
+| "Show me my bitcoin.conf" | fenced code block | config viewer, **redacted** (see below) |
+| "Mempool seems slow, check?" | 10 log lines in a fence | log viewer surface — scrollback, level filter, follow |
+| "Open Mempool" | ✅ opened the app frame | (this one is right — the model of the rest) |
+| "What other apps can I install?" | 3 grouped bullet lists | marketplace grid with Install actions |
+| "Full status summary" | a hand-built markdown table of 14 apps | dashboard surface — system health tiles + app grid |
+
+Only 1 of 10 turns used a surface. The content is correct in every case; the
+*presentation channel* is wrong.
+
+## Why this is more than cosmetics
+
+- The grids/cards carry **actions** (open, install, restart, follow logs). Prose
+  carries none, so every answer dead-ends and the user has to go find the app.
+- It burns model tokens re-formatting structured data the node already has
+  structured, and invites the transcription errors we already fixed once in the
+  content-card parser (title *n* paired with description *n−1*).
+- A markdown table of 14 apps is unreadable on mobile; the app grid is responsive.
+
+## Security defect found in the same transcript — fix regardless
+
+The `bitcoin.conf` answer printed **`rpcpassword=archipelago123` in cleartext** into
+the chat. Whatever the source (this looks like mock data), the rule has to hold: a
+config file rendered by the assistant must be **redacted before it reaches the model
+or the transcript** — `rpcpassword`, `rpcauth`, tokens, keys, mnemonics. This is the
+phase's own non-negotiable (keys out of the browser and the model).
+
+Related and currently RED — likely the same gap, and a real failing test on main:
+
+    assistant::backends::routstr::tests::secret_shaped_content_never_reaches_the_stub
+    panicked at archipelago/src/assistant/backends/routstr.rs:1073
+    "a secret-shaped body must be blocked"
+
+`screen_outbound` (`assistant/egress.rs:411`) is NOT blocking a 12-word BIP-39-shaped
+seed in a user turn on the Routstr paid leg, so it would be sent to a third-party
+inference provider. Pre-existing, from 13-13 — confirmed unrelated to the appgate
+Authorization fix (that commit touched only `appgate/mod.rs`; `routstr.rs` has no
+reference to appgate). 1300 passed / 1 failed.
+
+## Suggested shape of the work
+
+1. Fix `screen_outbound` first — it is a live security hole with a failing test.
+2. Redact secrets in file/config rendering, on the node side, before the model sees it.
+3. Audit which intents already have a surface and are simply not being routed to it
+   vs. which have no surface yet. Ties directly to the open item "audit all ten
+   `AIContextCategory` values in `fetchAndSanitize` for real coverage, not stubs".
+4. Make structured model output the contract for these intents rather than parsing
+   prose back into cards — the same conclusion the content-card parser item reached.
+
+## Loop
+
+Per `RESUME-2026-08-06-media-loop.md`: fix → build → deploy to archi-dev-box → test
+live → verify the shipped bundle changed → commit → push. No item is done without a
+live check on the node.