docs: accuracy sweep + coverage for 2 months of shipped features

Accuracy pass (all 373 pages audited against code, 13 parallel audits):
- configuration.md: 12 stale defaults/keys (file-sync rewrite, clarify
  timeout, streaming knobs, iteration budget, TTS/STT enums)
- reference/: commands/env-vars/toolsets/tools synced with
  COMMAND_REGISTRY, argparse tree, OPTIONAL_ENV_VARS, TOOLSETS
  (28 env vars added, 3 phantom removed, mcp__ naming, webhook
  platform restricted toolset)
- features/, messaging/, developer-guide/, guides/: ~60 factual fixes
  (web_extract truncation, dashboard auth fail-closed, delegation
  blocked tools, adapter signatures, session schema v23, phantom
  Matrix env vars, hermes setup tts, auth spotify, webhook --skills)
- zh-Hans: explicit heading IDs fix 2 broken WSL2 anchors

New coverage for features shipped in the last 2 months (verified
against code before writing):
- compression.in_place, verify-on-stop (+v31/v32 migration reality),
  ${env:VAR} SecretRef, display.timestamp_format, session:compress
  hook + thread_id/chat_type fields
- /journey learning timeline, per-channel model/system-prompt
  overrides, /sessions search, clarify multi-select, -z --usage-file,
  uninstall --dry-run, config get/unset
- MCP elicitation, extra_headers, discover_models, api-server run cap,
  Bedrock cachePoint, Discord reasoning_style, Google Chat clarify
  cards, vibe reactions, resume cwd restore, Yuanbao forwarded
  messages, api_content sidecar, roaming pet, tool_progress log mode,
  WhatsApp polls/locations, kanban per-task model + lifecycle hooks

website/docs/developer-guide/plugins/index.md

@@ -577,7 +577,11 @@ def register(ctx):
 
 Without `override=True`, the registry rejects any registration that would
 shadow an existing tool from a different toolset — this prevents
-accidental overwrites. The override is logged at INFO level so it's
+accidental overwrites. Overriding a **built-in** tool additionally
+requires the operator to opt in via
+`plugins.entries.<plugin_id>.allow_tool_override: true` in `config.yaml`;
+without that gate, `register_tool(override=True)` raises
+`PluginToolOverrideError`. The override is logged so it's
 auditable in `~/.hermes/logs/agent.log`. Plugins load after built-in
 tools, so the registration order is correct: your handler replaces the
 built-in one.
@@ -599,7 +603,7 @@ Each hook is documented in full on the **[Event Hooks reference](/user-guide/fea
 
 | Hook | Fires when | Callback signature | Returns |
 |------|-----------|-------------------|---------|
-| [`pre_tool_call`](/user-guide/features/hooks#pre_tool_call) | Before any tool executes | `tool_name: str, args: dict, task_id: str` | ignored |
+| [`pre_tool_call`](/user-guide/features/hooks#pre_tool_call) | Before any tool executes | `tool_name: str, args: dict, task_id: str` | optional directive: `{"action": "block", "message": ...}` vetoes the call; `{"action": "approve", "message": ...}` escalates to the human-approval gate |
 | [`post_tool_call`](/user-guide/features/hooks#post_tool_call) | After any tool returns | `tool_name: str, args: dict, result: str, task_id: str, duration_ms: int` | ignored |
 | [`pre_llm_call`](/user-guide/features/hooks#pre_llm_call) | Once per turn, before the tool-calling loop | `session_id: str, user_message: str, conversation_history: list, is_first_turn: bool, model: str, platform: str` | [context injection](#pre_llm_call-context-injection) |
 | [`post_llm_call`](/user-guide/features/hooks#post_llm_call) | Once per turn, after the tool-calling loop (successful turns only) | `session_id: str, user_message: str, assistant_response: str, conversation_history: list, model: str, platform: str` | ignored |
@@ -611,7 +615,7 @@ Each hook is documented in full on the **[Event Hooks reference](/user-guide/fea
 | `kanban_task_completed` | A kanban task completes (worker process) | `task_id, board, assignee, run_id, profile_name, summary: str \| None` | ignored |
 | `kanban_task_blocked` | A kanban task is blocked (worker process) | `task_id, board, assignee, run_id, profile_name, reason: str \| None` | ignored |
 
-Most hooks are fire-and-forget observers — their return values are ignored. The exception is `pre_llm_call`, which can inject context into the conversation.
+Most hooks are fire-and-forget observers — their return values are ignored. The exceptions are `pre_llm_call`, which can inject context into the conversation, and `pre_tool_call`, which can return a block/approve directive.
 
 All callbacks should accept `**kwargs` for forward compatibility. If a hook callback crashes, it's logged and skipped. Other hooks and the agent continue normally.
 
@@ -1063,7 +1067,8 @@ class MyContextEngine(ContextEngine):
 
     def update_from_response(self, usage) -> None: ...
     def should_compress(self, prompt_tokens: int = None) -> bool: ...
-    def compress(self, messages, current_tokens=None, focus_topic=None) -> list: ...
+    def compress(self, messages, current_tokens=None, focus_topic=None,
+                 force=False, memory_context="") -> list: ...
 
 def register(ctx):
     ctx.register_context_engine(MyContextEngine())