DOCS · REFERENCE · COMMANDS · SETUP

configure-multi-model/synthex:configure-multi-model

Setup

Wizard that detects installed model CLIs, checks auth, and enables multi-model review.

Invocation

Run from inside Claude Code in any project where Synthex is installed:

/synthex:configure-multi-model

Some commands accept parameters; see the source-of-truth file linked below for the full parameter list and workflow.

Lifecycle phase

Setup. One-time project scaffolding.

No agents declare this command's lifecycle phase. The command runs structurally — delegating to whichever agents the command's workflow names directly.

Source

The command's parameters, workflow, and sub-agent invocations are defined in markdown at bluminal/lumenai/blob/main/plugins/synthex/commands/configure-multi-model.md.

Last modified:

What it does, end-to-end

configure-multi-model/synthex:configure-multi-model is the setup wizard for the multi_model_review block in .synthex/config.yaml. You can re-run it any time. init/synthex:init runs the same step on a new project. Each run:

  1. Checks what's already there. If multi-model review is already on, it shows your current reviewers and aggregator and asks what to do (see Re-running it). Otherwise it starts fresh. Other keys in an existing multi_model_review block are kept.
  2. Detects installed CLIs. For each supported CLI it checks, in parallel, both that the binary is installed and that it's logged in. Only the exit code counts.
  3. Asks you to pick one of three options, listing what it found.
  4. Shows the data-transmission warning before it writes enabled: true.
  5. Writes the config and runs preflight, then prints a summary such as 3 reviewers configured, 3 available, 3 families, aggregator: codex-review-prompter. It also creates docs/reviews/ for audit records.

What it detects

CLIInstalled checkLogin check
codexwhich codexcodex login status
geminiwhich geminigcloud auth list
ollamawhich ollamacurl -sf http://localhost:11434/api/tags (server running)
llmwhich llmllm keys list
awswhich awsaws sts get-caller-identity --output text
claudewhich claudeclaude --version

Results fall into three groups: installed and logged in, installed but not logged in, and not installed. CLIs that are installed but not logged in are listed separately with a fix, for example gemini — run gcloud auth login to enable.

The three options

  • Enable with detected CLIs. Writes multi_model_review.enabled: true and a reviewers list with only the CLIs that passed both checks. If none passed, the option is still offered so you can fix logins afterwards.
  • Enable later (show snippet). Prints a commented-out multi_model_review: block with your detected CLIs, for you to paste in when ready. Nothing is written.
  • Skip. Writes nothing. Multi-model review stays off.

If preflight fails, the wizard prints how to fix it but doesn't stop. During init/synthex:init, the rest of setup carries on.

The data-transmission warning

Before it turns the feature on, the wizard shows:

Multi-model review sends your code, diffs, and (for write-implementation-plan) draft plan markdown to the configured external CLIs. Each CLI relays this content to its underlying provider (OpenAI, Google, etc.) per the provider's terms of service. Synthex does not store, log, or modify this content beyond what's needed to invoke the CLI.

If you need to keep all review content local, configure ONLY local-model adapters (Ollama, Bedrock with on-prem model) and remove hosted-model adapters from reviewers.

Parameters

ParameterDescriptionDefaultRequired
config_pathWhere the config file lives.synthex/config.yamlNo

Re-running it

When multi-model review is already on, the wizard offers:

  1. Re-run the wizard. Detect CLIs again and replace multi_model_review.reviewers. The data warning is shown again before anything is written.
  2. Reset to disabled. Sets multi_model_review.enabled: false and keeps the rest of the block. The explicit false records that you opted out.
  3. Leave as-is. Exits with no changes.

After the wizard: turn it on per command

The wizard sets only the master switch. review-code/synthex:review-code and

write-implementation-plan/synthex:write-implementation-plan also check their own per-command switch, and both default to false. To have them use multi-model review automatically, add:

multi_model_review:
  per_command:
    review_code:
      enabled: true
    write_implementation_plan:
      enabled: true

Or pass --multi-model for a single run. See Multi-model review for how each command decides.

What it does not do

  • Ask for or store API keys. Each CLI handles its own login (codex login, gcloud auth login, ollama serve, and so on). Config files never hold keys.
  • Set per-command switches, models, or permission modes. Edit those keys yourself. Put model choices (multi_model_review.per_reviewer) in your user config at ~/.config/synthex/config.yaml.
  • Delete the block when you disable it. Reset keeps the block and sets enabled: false.

See also

  • Multi-model review — how it works, adapters, and failure behavior.
  • Configuration — why enabled: false in any layer wins.
  • review-code/synthex:review-code — the main command that uses it.