diff options
| author | Claude <noreply@anthropic.com> | 2026-05-25 19:02:19 +0000 |
|---|---|---|
| committer | Claude <noreply@anthropic.com> | 2026-05-25 19:02:19 +0000 |
| commit | 65cd7ea65d9c6fe0fad39bb2c5cac70d61153444 (patch) | |
| tree | 693dc265879bc39872e490989ece62ef07aef9eb /internal/api/events_test.go | |
| parent | c0fabf5a2f4ca371403571b82e29c5073bed24fb (diff) | |
feat(executor): wire the agent MCP back-channel for gemini containers (Phase 4)
ContainerRunner previously skipped the MCP back-channel for gemini agents, so
they ran tool-less. It now mints a per-task token for gemini too and registers
the agent MCP server in the gemini CLI's user settings
(agentHome/.gemini/settings.json → $HOME/.gemini in-container) using the
gemini-cli mcpServers/httpUrl schema with a bearer header. With MCP enabled,
gemini also receives the planning preamble that points at the ask_user/
report_summary/spawn_subtask/record_progress tools.
Config generation is unit-tested (TestWriteGeminiMCPSettings) and the write is
in the run setup path. CAVEAT: whether the gemini CLI actually invokes these
tools in non-interactive (-p) mode — and how it handles tool auto-approval —
is NOT verified against a live gemini binary in this environment; this lands
the plumbing for a follow-up spike. No regression risk for gemini runs: a
config issue degrades to the prior tool-less behavior.
https://claude.ai/code/session_01SESwn7kQ7oP62trWw6pc39
Diffstat (limited to 'internal/api/events_test.go')
0 files changed, 0 insertions, 0 deletions
