Model autocompletion improvements, subagent streaming optimizations, and MCP tool resolution fixes

Improves /model autocompletion with Tab acceptance, reduces subagent streaming telemetry overhead, and delivers stability fixes for prompt hooks, MCP tools in subagents, tool call IDs in request history, and OAuth token refreshes.

• Improved /model autocompletion to accept the proposed model name ghost text using Tab.
• Reduced subagent streaming overhead by sending subagent trajectory metadata once per subtrajectory instead of with every step.
• Fixed commands with subcommands (such as models or agents) hanging on inherited standard input pipes.
• Fixed CLI crashes caused by prompt hooks by catching hook panics and rejecting nil completion configurations in model requests.
• Fixed tool invocations and results omitting tool-call IDs when reconstructing request history for Gemini models.
• Fixed tool permission prompts for native and MCP tool calls displaying generic titles instead of human-readable action descriptions.
• Fixed unconfigured or interrupted Google Cloud authentication dropping into broken chat sessions instead of reprompting the sign-in screen.
• Fixed transient authentication errors from clock skew by proactively refreshing browser and WIF OAuth tokens 5 minutes before expiration.
• Fixed instructional cycle mode placeholders reappearing in the input prompt after typing and clearing content.
• Fixed subagents defined with enable_mcp_tools=true failing with unknown tool errors by ensuring the MCP dispatcher is available to the subagent executor.
• Fixed prompts submitted immediately after login being discarded by queueing them until background account verification finishes.
• Fixed cancelled or killed subagents remaining stuck in the "Running" state in the UI task drawer across ancestor conversations.
• Fixed parsing MCP JSON configuration files on Windows when saved with a UTF-8 byte order mark (BOM).