docs: comprehensive documentation audit — fix 9 HIGH, 20+ MEDIUM gaps (#4087)

Reference docs fixes:
- cli-commands.md: remove non-existent --provider alibaba, add hermes
  profile/completion/plugins/mcp to top-level table, add --profile/-p
  global flag, add --source chat option
- slash-commands.md: add /yolo and /commands, fix /q alias conflict
  (resolves to /queue not /quit), add missing aliases (/bg, /set-home,
  /reload_mcp, /gateway)
- toolsets-reference.md: fix hermes-api-server (not same as hermes-cli,
  omits clarify/send_message/text_to_speech)
- profile-commands.md: fix show name required not optional, --clone-from
  not --from, add --remove/--name to alias, fix alias path, fix export/
  import arg types, remove non-existent fish completion
- tools-reference.md: add EXA_API_KEY to web tools requires_env
- mcp-config-reference.md: add auth key for OAuth, tool name sanitization
- environment-variables.md: add EXA_API_KEY, update provider values
- plugins.md: remove non-existent ctx.register_command(), add
  ctx.inject_message()

Feature docs additions:
- security.md: add /yolo mode, approval modes (manual/smart/off),
  configurable timeout, expanded dangerous patterns table
- cron.md: add wrap_response config, [SILENT] suppression
- mcp.md: add dynamic tool discovery, MCP sampling support
- cli.md: add Ctrl+Z suspend, busy_input_mode, tool_preview_length
- docker.md: add skills/credential file mounting

Messaging platform docs:
- telegram.md: add webhook mode, DoH fallback IPs
- slack.md: add multi-workspace OAuth support
- discord.md: add DISCORD_IGNORE_NO_MENTION
- matrix.md: add MSC3245 native voice messages
- feishu.md: expand from 129 to 365 lines (encrypt key, verification
  token, group policy, card actions, media, rate limiting, markdown,
  troubleshooting)
- wecom.md: expand from 86 to 264 lines (per-group allowlists, media,
  AES decryption, stream replies, reconnection, troubleshooting)

Configuration docs:
- quickstart.md: add DeepSeek, Copilot, Copilot ACP providers
- configuration.md: add DeepSeek provider, Exa web backend, terminal
  env_passthrough/images, browser.command_timeout, compression params,
  discord config, security/tirith config, timezone, auxiliary models

21 files changed, ~1000 lines added

website/docs/user-guide/features/mcp.md

@@ -277,6 +277,14 @@ That keeps the tool list clean.
 
 Hermes discovers MCP servers at startup and registers their tools into the normal tool registry.
 
+### Dynamic Tool Discovery
+
+MCP servers can notify Hermes when their available tools change at runtime by sending a `notifications/tools/list_changed` notification. When Hermes receives this notification, it automatically re-fetches the server's tool list and updates the registry — no manual `/reload-mcp` required.
+
+This is useful for MCP servers whose capabilities change dynamically (e.g. a server that adds tools when a new database schema is loaded, or removes tools when a service goes offline).
+
+The refresh is lock-protected so rapid-fire notifications from the same server don't cause overlapping refreshes. Prompt and resource change notifications (`prompts/list_changed`, `resources/list_changed`) are received but not yet acted on.
+
 ### Reloading
 
 If you change MCP config, use:
@@ -285,7 +293,7 @@ If you change MCP config, use:
 /reload-mcp
 ```
 
-This reloads MCP servers from config and refreshes the available tool list.
+This reloads MCP servers from config and refreshes the available tool list. For runtime tool changes pushed by the server itself, see [Dynamic Tool Discovery](#dynamic-tool-discovery) above.
 
 ### Toolsets
 
@@ -403,6 +411,39 @@ Because Hermes now only registers those wrappers when both are true:
 
 This is intentional and keeps the tool list honest.
 
+## MCP Sampling Support
+
+MCP servers can request LLM inference from Hermes via the `sampling/createMessage` protocol. This allows an MCP server to ask Hermes to generate text on its behalf — useful for servers that need LLM capabilities but don't have their own model access.
+
+Sampling is **enabled by default** for all MCP servers (when the MCP SDK supports it). Configure it per-server under the `sampling` key:
+
+```yaml
+mcp_servers:
+  my_server:
+    command: "my-mcp-server"
+    sampling:
+      enabled: true            # Enable sampling (default: true)
+      model: "openai/gpt-4o"  # Override model for sampling requests (optional)
+      max_tokens_cap: 4096     # Max tokens per sampling response (default: 4096)
+      timeout: 30              # Timeout in seconds per request (default: 30)
+      max_rpm: 10              # Rate limit: max requests per minute (default: 10)
+      max_tool_rounds: 5       # Max tool-use rounds in sampling loops (default: 5)
+      allowed_models: []       # Allowlist of model names the server may request (empty = any)
+      log_level: "info"        # Audit log level: debug, info, or warning (default: info)
+```
+
+The sampling handler includes a sliding-window rate limiter, per-request timeouts, and tool-loop depth limits to prevent runaway usage. Metrics (request count, errors, tokens used) are tracked per server instance.
+
+To disable sampling for a specific server:
+
+```yaml
+mcp_servers:
+  untrusted_server:
+    url: "https://mcp.example.com"
+    sampling:
+      enabled: false
+```
+
 ## Running Hermes as an MCP server
 
 In addition to connecting **to** MCP servers, Hermes can also **be** an MCP server. This lets other MCP-capable agents (Claude Code, Cursor, Codex, or any MCP client) use Hermes's messaging capabilities — list conversations, read message history, and send messages across all your connected platforms.