Group of 3 Under the hood
Claude Code's MCP bridge, non-interactive query, and interactive REPL tool contexts all now carry a runQuery hook
What
- The isolated tool-execution context used to expose Claude Code's tools over an MCP server connection now includes a
runQueryfunction in its options. - The function that builds options for a non-interactive/analysis query now accepts a
runQueryparameter from its caller and passes it into the agent context options, alongside existing options likecommands,tools, andmcpClients. - The interactive REPL's tool-use context now also includes a
runQueryentry, alongside existing options likeresolveCommandDialogandrenderDebugControls.
Why
Giving all three tool-execution contexts (MCP bridge, non-interactive queries, and the interactive REPL) the same runQuery hook lets them share a consistent way to run queries, rather than each context wiring this up separately or lacking the capability.
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubt
What runQuery is actually used for and what capability it unlocks is not stated in the finding.