docs: add model allowlist + reasoning safety notes

CHANGELOG.md

@@ -45,6 +45,7 @@
 - Providers/Doctor: warn when Telegram config expects unmentioned group messages but Bot API privacy mode is likely enabled; surface WhatsApp login/disconnect hints.
 - Providers/Doctor: add last inbound/outbound activity timestamps in `providers status` and extend `--probe` with Discord channel permission + Telegram group membership audits.
 - Docs: add provider troubleshooting index (`/providers/troubleshooting`) and link it from the main troubleshooting guide.
+- Docs: clarify model allowlist errors and add safety notes for verbose/reasoning in groups.
 - Telegram: include the user id in DM pairing messages and label it clearly in `clawdbot pairing list --provider telegram`.
 - Apps: refresh iOS/Android/macOS app icons for Clawdbot branding. (#521) — thanks @fishfisher
 - Docs: expand parameter descriptions for agent/wake hooks. (#532) — thanks @mcinteerj

docs/gateway/security.md

@@ -77,6 +77,13 @@ Even with strong system prompts, **prompt injection is not solved**. What helps
 - Run sensitive tool execution in a sandbox; keep secrets out of the agent’s reachable filesystem.
 - **Model choice matters:** we recommend Anthropic Opus 4.5 because it’s quite good at recognizing prompt injections (see [“A step forward on safety”](https://www.anthropic.com/news/claude-opus-4-5)). Using weaker models increases risk.
 
+## Reasoning & verbose output in groups
+
+`/reasoning` and `/verbose` can expose internal reasoning or tool output that
+was not meant for a public channel. In group settings, treat them as **debug
+only** and keep them off unless you explicitly need them. If you enable them,
+do so only in trusted DMs or tightly controlled rooms.
+
 ## Lessons Learned (The Hard Way)
 
 ### The `find ~` Incident 🦞

docs/start/faq.md

@@ -277,6 +277,18 @@ Use the `/model` command as a standalone message:
 
 You can list available models with `/model`, `/model list`, or `/model status`.
 
+### Why do I see “Model … is not allowed” and then no reply?
+
+If `agent.models` is set, it becomes the **allowlist** for `/model` and any
+session overrides. Choosing a model that isn’t in that list returns:
+
+```
+Model "provider/model" is not allowed. Use /model to list available models.
+```
+
+That error is returned **instead of** a normal reply. Fix: add the model to
+`agent.models`, remove the allowlist, or pick a model from `/model list`.
+
 ### Are opus / sonnet / gpt built‑in shortcuts?
 
 Yes. Clawdbot ships a few default shorthands (only applied when the model exists in `agent.models`):

docs/tools/slash-commands.md

@@ -52,6 +52,8 @@ Text-only:
 
 Notes:
 - Commands accept an optional `:` between the command and args (e.g. `/think: high`, `/send: on`, `/help:`).
+- `/verbose` is meant for debugging and extra visibility; keep it **off** in normal use.
+- `/reasoning` (and `/verbose`) are risky in group settings: they may reveal internal reasoning or tool output you did not intend to expose. Prefer leaving them off, especially in group chats.
 
 ## Surface notes