Same architecture as the codex sister change:
1. mcp-host subcommand routes argv[1] to mcpbridge.Run, reading
PLEXUM_MCP_SOCKET / PLEXUM_MCP_AGENT_ID from gemini-cli's
`gemini mcp add --env` env baking.
2. EnsureGeminiMCPRegistered handles per-agent stable registration
under `-s user --trust` so gemini auto-approves the tool surface.
3. Post-turn ParseGeminiToolCalls + EmitGeminiToolCalls scans the
chat JSONL at ~/.gemini/tmp/<ws>/chats/session-*.jsonl. Pairs
gemini's nested `toolCalls[].id` with the matching
`functionResponse.id` from later user lines.
4. MutateGeminiSession rewrites the chat JSONL: toolCalls[].args
→ {} (heavy), functionResponse.response.output → marker.
E2E verified: gemini call exec via plexum-host → dynamic.jsonl
records the call → dynamic-tool-clear consumes → gemini session
mirrored → resume gemini sees consumed marker not the original.
