docs: comprehensive update for recent merged PRs (#9019)

Audit and update documentation across 12 files to match changes from
~50 recently merged PRs. Key updates:

Slash commands (slash-commands.md):
- Add 5 missing commands: /snapshot, /fast, /image, /debug, /restart
- Fix /status incorrectly labeled as messaging-only (available in both)
- Add --global flag to /model docs
- Add [focus topic] arg to /compress docs

CLI commands (cli-commands.md):
- Add hermes debug share section with options and examples
- Add hermes backup section with --quick and --label flags
- Add hermes import section

Feature docs:
- TTS: document global tts.speed and per-provider speed for Edge/OpenAI
- Web dashboard: add docs for 5 missing pages (Sessions, Logs,
  Analytics, Cron, Skills) and 15+ API endpoints
- WhatsApp: add streaming, 4K chunking, and markdown formatting docs
- Skills: add GitHub rate-limit/GITHUB_TOKEN troubleshooting tip
- Budget: document CLI notification on iteration budget exhaustion

Config migration (compression.summary_* → auxiliary.compression.*):
- Update configuration.md, environment-variables.md,
  fallback-providers.md, cli.md, and context-compression-and-caching.md
- Replace legacy compression.summary_model/provider/base_url references
  with auxiliary.compression.model/provider/base_url
- Add legacy migration info boxes explaining auto-migration

Minor fixes:
- wecom-callback.md: clarify 'text only' limitation (input only)
- Escape {session_id}/{job_id} in web-dashboard.md headings for MDX

website/docs/user-guide/messaging/whatsapp.md

@@ -174,6 +174,33 @@ whatsapp:
 
 ---
 
+## Message Formatting & Delivery
+
+WhatsApp supports **streaming (progressive) responses** — the bot edits its message in real-time as the AI generates text, just like Discord and Telegram. Internally, WhatsApp is classified as a TIER_MEDIUM platform for delivery capabilities.
+
+### Chunking
+
+Long responses are automatically split into multiple messages at **4,096 characters** per chunk (WhatsApp's practical display limit). You don't need to configure anything — the gateway handles splitting and sends chunks sequentially.
+
+### WhatsApp-Compatible Markdown
+
+Standard Markdown in AI responses is automatically converted to WhatsApp's native formatting:
+
+| Markdown | WhatsApp | Renders as |
+|----------|----------|------------|
+| `**bold**` | `*bold*` | **bold** |
+| `~~strikethrough~~` | `~strikethrough~` | ~~strikethrough~~ |
+| `# Heading` | `*Heading*` | Bold text (no native headings) |
+| `[link text](url)` | `link text (url)` | Inline URL |
+
+Code blocks and inline code are preserved as-is since WhatsApp supports triple-backtick formatting natively.
+
+### Tool Progress
+
+When the agent calls tools (web search, file operations, etc.), WhatsApp displays real-time progress indicators showing which tool is running. This is enabled by default — no configuration needed.
+
+---
+
 ## Troubleshooting
 
 | Problem | Solution |