- The IRC wake monitor from PR #7108 calls the observer on every kept-alive
subagent finalize; fakes across the executor suites predate the method
and threw during finalization (69 failures).
- Bun 1.4 canary's posix_spawn intermittently rejects pipe-backed child
stdio (EBADF) inside test workers, failing telemetry-export and
shell-snapshot probes before their assertions ran.
- Probes now spawn with ignored stdio and capture output via exit status
or temp-file redirection; all behavioral assertions retained.
- #7163's context-token anchoring re-triggered #7153's dead-end warning on
the pre-prompt pass; a one-shot marker now spans agent loops and re-arms
only when a persisted cut point appears.
- Updated scrollback tests to the Alt+L display-reset binding main adopted.
reloadServers() now reads ctx.settings and session.setMCPPromptCommands, which
the shared /mcp reauth|unauth harness did not provide, so those tests threw
inside reload and failed their showError assertions. Add both members to the
fake context.
Fixes#7189
MCPManager.disconnectAll clears connections without notifying the session's
prompt-command consumer, so removed or disabled prompt servers left stale
/server:prompt commands after /reload-plugins and /mcp reload.
Clear the session MCP prompt-command registry immediately after disconnect and
before asynchronous rediscovery. Newly loaded prompts repopulate it through
the existing manager callback. Extend the reload regression coverage.
Fixes#7189
reloadServers() rediscovered MCP with no options, so loadAllMCPConfigs
defaulted enableProjectConfig to true — /reload-plugins (and /mcp reload)
could start project .mcp.json servers a user opted out of.
Derive discovery filters (enableProjectConfig, filterExa, filterBrowser)
from ctx.settings before reconnecting, matching startup discovery. Added a
regression test asserting the opt-out is forwarded.
Fixes#7189
/reload-plugins documents MCP in its reload scope but the TUI handler only
reset skill/command/capability caches and never reconnected MCP servers or
refreshed the session MCP tool registry, so .mcp.json edits stayed inactive
until process restart.
Route the TUI reload pipeline through a shared reloadTuiPluginState() helper
that also runs the disconnect/rediscover/refreshMCPTools path used by
/mcp reload, exposed as MCPCommandController.reloadServers().
Fixes#7189
ExtensionRunner cached cwd from its constructor argument, which is set
once at session start. /move (SessionManager.moveTo) relocates the
active session's directory, but ExtensionRunner never re-read it, so
every ExtensionContext built afterwards (tool calls, hooks, slash
commands) kept reporting the pre-move directory for the rest of the
session -- observed while building an extension that tracks the
session's git worktree via ctx.cwd.
Turn cwd into a getter over this.sessionManager.getCwd() instead of a
constructor-time snapshot. Session-scoped, not the process-global
project directory: the interactive /move handler happens to also
chdir the process (command-controller.ts -> applyCwdChange ->
setProjectDir), but moveTo() itself never touches that global, so a
programmatic AgentSession.moveSession()/SessionManager.moveTo() call,
a collab guest adopting a host's session cwd without chdir'ing, or an
SDK/ACP session opened via createAgentSession({ cwd }) with a cwd that
differs from the process's own would all still observe a stale
ctx.cwd under a getProjectDir()-based getter. Reading the runner's own
sessionManager -- already held for other purposes -- covers every one
of these instead of just the single-session interactive case.
The constructor parameter is kept (renamed _initialCwd, documented as
ignored) so the two existing call sites don't need touching.
Added a regression test constructing a real ExtensionRunner over an
in-memory SessionManager, relocating it via SessionManager.moveTo(),
and asserting both runner.cwd and createContext().cwd observe the new
directory.
can1357