featDeepSeek becomes the default provider; prefix-cache headline added across the READMEs #365–#367◆featDeepSeek prefix-cache exploitation — byte-stable prefix makes cache-hit input over 200× cheaper #363◆featZ.ai GLM-5.2 support — new zai provider for the GLM Coding Plan #343◆statCodebase stats: 1,093 Python files, 233,520 lines of Python◆featDynamic workflow engine + /deep-research wired end-to-end #262–#271◆featWeb tooling refresh — Tavily-backed WebSearch, rebuilt WebFetch #265◆featInteractive command-system parity (/theme, /model, /mcp, /tasks, …) #230–#261◆featDeepSeek becomes the default provider; prefix-cache headline added across the READMEs #365–#367◆featDeepSeek prefix-cache exploitation — byte-stable prefix makes cache-hit input over 200× cheaper #363◆featZ.ai GLM-5.2 support — new zai provider for the GLM Coding Plan #343◆statCodebase stats: 1,093 Python files, 233,520 lines of Python◆featDynamic workflow engine + /deep-research wired end-to-end #262–#271◆featWeb tooling refresh — Tavily-backed WebSearch, rebuilt WebFetch #265◆featInteractive command-system parity (/theme, /model, /mcp, /tasks, …) #230–#261◆