Add passive mesh context awareness — observe channel traffic, inject into LLM prompts

New context.py module: ring buffer (50K hard cap, ~25MB ceiling) passively
records all channel broadcasts. Observations are formatted with relative
timestamps and injected into the system prompt when generating LLM responses.
Only public channel traffic is observed; DMs to the bot are excluded (already
in per-user history). Bot's own node ID is auto-added to ignore list.

Config: context.enabled, observe_channels, ignore_nodes, max_age, max_context_items
TUI: new Context settings submenu (menu item 7)
Hourly prune removes expired observations.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

meshai/config.py

@@ -64,6 +64,17 @@ class MemoryConfig:
     summarize_threshold: int = 8  # Messages before re-summarizing
 
 
+@dataclass
+class ContextConfig:
+    """Passive mesh context settings."""
+
+    enabled: bool = True
+    observe_channels: list[int] = field(default_factory=list)  # Empty = all channels
+    ignore_nodes: list[str] = field(default_factory=list)  # Node IDs to ignore
+    max_age: int = 2_592_000  # 30 days in seconds
+    max_context_items: int = 20  # Max observations injected into LLM context
+
+
 @dataclass
 class CommandsConfig:
     """Command settings."""
@@ -128,6 +139,7 @@ class Config:
     response: ResponseConfig = field(default_factory=ResponseConfig)
     history: HistoryConfig = field(default_factory=HistoryConfig)
     memory: MemoryConfig = field(default_factory=MemoryConfig)
+    context: ContextConfig = field(default_factory=ContextConfig)
     commands: CommandsConfig = field(default_factory=CommandsConfig)
     llm: LLMConfig = field(default_factory=LLMConfig)
     weather: WeatherConfig = field(default_factory=WeatherConfig)