hzhang
a63f477463
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.
Plexum-gemini-provider
Plexum ProviderPlugin that wraps the local gemini CLI binary
(Google Gemini CLI) — same CLI-driven pattern as
Plexum-anthropic-provider's contractor mode. Each Plexum turn forks
one gemini -p subprocess in the agent's workspace.
Reference: openclaw/extensions/google/cli-backend.ts.
Status
v0.1: subprocess-per-turn, JSON output parsing, per-workspace
session continuity via --resume. Models: gemini (CLI default),
gemini-pro, gemini-flash, gemini-flash-lite.
Install
cd ~/Plexum-gemini-provider
./scripts/install.sh
Then:
-
Allow in
~/.plexum/plexum.json:{"plugins": {"allow": ["plexum-gemini-provider"]}} -
Bind an agent:
plexum agent-add --model gemini-flash my-agent -
Restart + talk:
systemctl --user restart plexum plexum say --agent-id my-agent --session-id $(plexum new-session --agent-id my-agent) "hello"
Auth
There is no API key in this plugin's config. The gemini CLI handles
auth itself via ~/.gemini/ (OAuth or GEMINI_API_KEY). Run
gemini auth login (or set env) once, then this plugin just shells
out.
How it works
For each Plexum turn the plugin forks:
gemini --skip-trust --output-format json [--model <m>] [--resume <sid>] -p "<last user msg>"
with cwd = <agent workspace>. The CLI exits with a single JSON blob:
{
"session_id": "uuid",
"response": "...",
"stats": {"models": {...}}
}
We capture session_id into <workspace>/.plexum-gemini-session so the
next turn passes --resume and Gemini sees the full prior context. The
response text is emitted as one text_delta followed by message_end.
Models
| Plexum model id | CLI invocation |
|---|---|
gemini |
no --model flag (CLI default — currently gemini-3-flash-preview) |
gemini-pro |
--model pro (CLI alias → gemini-3.1-pro-preview) |
gemini-flash |
--model flash (CLI alias → gemini-3.1-flash-preview) |
gemini-flash-lite |
--model flash-lite (CLI alias → gemini-3.1-flash-lite-preview) |
Any other id is passed through as --model <id> verbatim so operators
can pin a specific Gemini model the local CLI knows about.
Config options
| Field | Default | Notes |
|---|---|---|
binary |
gemini |
executable name or absolute path |
extra_args |
[] |
appended after the standard flags, before -p |
License
Same as Plexum.