docs: fix all remaining minor accuracy issues

- updating.md: Note that 'hermes update' auto-handles config migration
- cli.md: Add summary_model to compression config, fix display config
  (add personality/compact), remove unverified pastes/ claim
- configuration.md: Add 5 missing config sections (stt, human_delay,
  code_execution, delegation, clarify), fix display defaults,
  fix reasoning_effort default to empty/unset
- messaging/index.md: Add GATEWAY_ALLOWED_USERS to security section
- skills.md: Add category field to skills_list return value
- mcp.md: Document auto-registered utility tools (resources/prompts)
- architecture.md: Fix file_tools.py reference, base_url default to None,
  synchronous agent loop pseudocode
- cli-commands.md: Fix hermes logout description
- environment-variables.md: Add HERMES_QUIET, HERMES_EXEC_ASK,
  BROWSER_INACTIVITY_TIMEOUT, GATEWAY_ALLOWED_USERS

Verification scan: 27/27 checks passed, zero issues remaining.

website/docs/developer-guide/architecture.md

@@ -43,7 +43,8 @@ hermes-agent/
 │   ├── registry.py               # Central tool registry (schemas, handlers, dispatch)
 │   ├── approval.py               # Dangerous command detection + per-session approval
 │   ├── terminal_tool.py          # Terminal orchestration (sudo, env lifecycle, backends)
-│   ├── file_operations.py        # read_file, write_file, search, patch
+│   ├── file_operations.py        # File tool implementations (read, write, search, patch)
+│   ├── file_tools.py             # File tool registration
 │   ├── web_tools.py              # web_search, web_extract
 │   ├── vision_tools.py           # Image analysis via multimodal models
 │   ├── delegate_tool.py          # Subagent spawning and parallel task execution
@@ -102,7 +103,7 @@ while turns < max_turns:
 
     if response.tool_calls:
         for tool_call in response.tool_calls:
-            result = await execute_tool(tool_call)
+            result = execute_tool(tool_call)
             messages.append(tool_result_message(result))
         turns += 1
     else:
@@ -117,7 +118,7 @@ class AIAgent:
         self,
         model: str = "anthropic/claude-opus-4.6",
         api_key: str = None,
-        base_url: str = "https://openrouter.ai/api/v1",
+        base_url: str = None,  # Resolved internally based on provider
         max_iterations: int = 60,
         enabled_toolsets: list = None,
         disabled_toolsets: list = None,
@@ -195,7 +196,7 @@ Key UX behaviors:
 - Thinking spinner shows animated kawaii face + verb (`(⌐■_■) deliberating...`)
 - Tool execution results appear as `┊ {emoji} {verb} {detail} {duration}`
 - Prompt shows `⚕ ❯` when working, `❯` when idle
-- Pasting 5+ lines auto-saves to `~/.hermes/pastes/` and collapses
+- Multi-line paste support with automatic formatting
 
 ## Messaging Gateway Architecture
 

website/docs/getting-started/updating.md

@@ -17,7 +17,7 @@ hermes update
 This pulls the latest code, updates dependencies, and prompts you to configure any new options that were added since your last update.
 
 :::tip
-After updating, run `hermes config check` to see if there are new configuration options available, then `hermes config migrate` to interactively add any missing ones.
+`hermes update` automatically detects new configuration options and prompts you to add them. If you skipped that prompt, you can manually run `hermes config check` to see missing options, then `hermes config migrate` to interactively add them.
 :::
 
 ### Updating from Messaging Platforms

website/docs/reference/cli-commands.md

@@ -29,7 +29,7 @@ These are commands you run from your shell.
 |---------|-------------|
 | `hermes model` | Switch provider and model interactively |
 | `hermes login` | OAuth login to a provider (use `--provider` to specify) |
-| `hermes logout` | Clear stored OAuth credentials |
+| `hermes logout` | Clear provider authentication |
 
 ### Configuration
 

website/docs/reference/environment-variables.md

@@ -37,6 +37,7 @@ All variables go in `~/.hermes/.env`. You can also set them with `hermes config
 | `FIRECRAWL_API_KEY` | Web scraping ([firecrawl.dev](https://firecrawl.dev/)) |
 | `BROWSERBASE_API_KEY` | Browser automation ([browserbase.com](https://browserbase.com/)) |
 | `BROWSERBASE_PROJECT_ID` | Browserbase project ID |
+| `BROWSER_INACTIVITY_TIMEOUT` | Browser session inactivity timeout in seconds |
 | `FAL_KEY` | Image generation ([fal.ai](https://fal.ai/)) |
 | `ELEVENLABS_API_KEY` | Premium TTS voices ([elevenlabs.io](https://elevenlabs.io/)) |
 | `HONCHO_API_KEY` | Cross-session user modeling ([honcho.dev](https://honcho.dev/)) |
@@ -96,6 +97,7 @@ All variables go in `~/.hermes/.env`. You can also set them with `hermes config
 | `WHATSAPP_MODE` | `bot` (separate number) or `self-chat` (message yourself) |
 | `WHATSAPP_ALLOWED_USERS` | Comma-separated phone numbers (with country code) |
 | `MESSAGING_CWD` | Working directory for terminal in messaging (default: `~`) |
+| `GATEWAY_ALLOWED_USERS` | Comma-separated user IDs allowed across all platforms |
 | `GATEWAY_ALLOW_ALL_USERS` | Allow all users without allowlist (`true`/`false`, default: `false`) |
 
 ## Agent Behavior
@@ -108,6 +110,8 @@ All variables go in `~/.hermes/.env`. You can also set them with `hermes config
 | `HERMES_HUMAN_DELAY_MODE` | Response pacing: `off`/`natural`/`custom` |
 | `HERMES_HUMAN_DELAY_MIN_MS` | Custom delay range minimum (ms) |
 | `HERMES_HUMAN_DELAY_MAX_MS` | Custom delay range maximum (ms) |
+| `HERMES_QUIET` | Suppress non-essential output (`true`/`false`) |
+| `HERMES_EXEC_ASK` | Enable execution approval prompts in gateway mode (`true`/`false`) |
 
 ## Session Settings
 

website/docs/user-guide/cli.md

@@ -171,7 +171,7 @@ There are two ways to enter multi-line messages:
 ```
 
 :::info
-Pasting 5+ lines of text automatically saves to `~/.hermes/pastes/` and collapses to a reference, keeping your prompt clean.
+Pasting multi-line text is supported — use `Alt+Enter` or `Ctrl+J` to insert newlines, or simply paste content directly.
 :::
 
 ## Interrupting the Agent
@@ -251,6 +251,7 @@ Long conversations are automatically summarized when approaching context limits:
 compression:
   enabled: true
   threshold: 0.85    # Compress at 85% of context limit
+  summary_model: "google/gemini-3-flash-preview"  # Model used for summarization
 ```
 
 When compression triggers, middle turns are summarized while the first 3 and last 4 turns are always preserved.

website/docs/user-guide/configuration.md

@@ -139,10 +139,10 @@ Control how much "thinking" the model does before responding:
 
 ```yaml
 agent:
-  reasoning_effort: "xhigh"   # xhigh (max), high, medium, low, minimal, none
+  reasoning_effort: ""   # empty = use model default. Options: xhigh (max), high, medium, low, minimal, none
 ```
 
-Higher reasoning effort gives better results on complex tasks at the cost of more tokens and latency.
+When unset (default), the model's own default reasoning level is used. Setting a value overrides it — higher reasoning effort gives better results on complex tasks at the cost of more tokens and latency.
 
 ## TTS Configuration
 
@@ -164,6 +164,8 @@ tts:
 ```yaml
 display:
   tool_progress: all    # off | new | all | verbose
+  personality: "kawaii"  # Default personality for the CLI
+  compact: false         # Compact output mode (less whitespace)
 ```
 
 | Mode | What you see |
@@ -173,6 +175,58 @@ display:
 | `all` | Every tool call with a short preview (default) |
 | `verbose` | Full args, results, and debug logs |
 
+## Speech-to-Text (STT)
+
+```yaml
+stt:
+  provider: "openai"           # STT provider
+```
+
+Requires `VOICE_TOOLS_OPENAI_KEY` in `.env` for OpenAI STT.
+
+## Human Delay
+
+Simulate human-like response pacing in messaging platforms:
+
+```yaml
+human_delay:
+  mode: "off"                  # off | natural | custom
+  min_ms: 500                  # Minimum delay (custom mode)
+  max_ms: 2000                 # Maximum delay (custom mode)
+```
+
+## Code Execution
+
+Configure the sandboxed Python code execution tool:
+
+```yaml
+code_execution:
+  timeout: 300                 # Max execution time in seconds
+  max_tool_calls: 50           # Max tool calls within code execution
+```
+
+## Delegation
+
+Configure subagent behavior for the delegate tool:
+
+```yaml
+delegation:
+  max_iterations: 50           # Max iterations per subagent
+  default_toolsets:             # Toolsets available to subagents
+    - terminal
+    - file
+    - web
+```
+
+## Clarify
+
+Configure the clarification prompt behavior:
+
+```yaml
+clarify:
+  timeout: 120                 # Seconds to wait for user clarification response
+```
+
 ## Context Files (SOUL.md, AGENTS.md)
 
 Drop these files in your project directory and the agent automatically picks them up:

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

@@ -159,6 +159,10 @@ mcp_{server_name}_{tool_name}
 
 Tools appear alongside built-in tools — the agent calls them like any other tool.
 
+:::info
+In addition to the server's own tools, each MCP server also gets 4 utility tools auto-registered: `list_resources`, `read_resource`, `list_prompts`, and `get_prompt`. These allow the agent to discover and use MCP resources and prompts exposed by the server.
+:::
+
 ### Reconnection
 
 If an MCP server disconnects, Hermes automatically reconnects with exponential backoff (1s, 2s, 4s, 8s, 16s — max 5 attempts). Initial connection failures are reported immediately.

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

@@ -36,7 +36,7 @@ hermes chat --toolsets skills -q "Show me the axolotl skill"
 Skills use a token-efficient loading pattern:
 
 ```
-Level 0: skills_list()           → [{name, description}, ...]   (~3k tokens)
+Level 0: skills_list()           → [{name, description, category}, ...]   (~3k tokens)
 Level 1: skill_view(name)        → Full content + metadata       (varies)
 Level 2: skill_view(name, path)  → Specific reference file       (varies)
 ```

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

@@ -113,6 +113,9 @@ Configure per-platform overrides in `~/.hermes/gateway.json`:
 TELEGRAM_ALLOWED_USERS=123456789,987654321
 DISCORD_ALLOWED_USERS=123456789012345678
 
+# Or allow specific users across all platforms (comma-separated user IDs):
+GATEWAY_ALLOWED_USERS=123456789,987654321
+
 # Or explicitly allow all users (NOT recommended for bots with terminal access):
 GATEWAY_ALLOW_ALL_USERS=true
 ```