v1.5.0

Feature:

• Add ephemeral researcher subagents for isolated codebase analysis and research
• Add per-agent model selection with /model, including support for separate orchestrator, coder, and researcher models
• Dynamically load subagent definitions while preserving existing shared subagent model configuration
• Add --prompt to start the agent immediately with an initial instruction
• Show command descriptions in slash-command autocomplete

Fix:

• Use an embedded cl100k_base tokenizer for more accurate context and token estimates by @giveen in #101
• Harden multi-line paste handling against binary input and placeholder collisions by @giveen in #101
• Improve search_tool regex-to-glob conversion and .gitignore path handling by @giveen in #101
• Improve .gitignore test setup for symlinked working directories by @jpia in #108
• Improve streaming history rendering, scrolling, and repaint performance
• Preserve runtime configuration when continuing after a cancelled agent run
• Return clearer subagent failures to the orchestrator and improve coder recovery instructions
• Use valid, collision-safe MCP tool names while retaining bare-name configuration compatibility