Agent matrix
Coldtea launches agent CLIs. It does not install them, log in for them, or replace their own permission model.
Use this page when an agent is missing from the launcher, starts with the wrong defaults, or behaves differently from another agent.
Supported local launchers
| Agent | Command Coldtea looks for | Default local launch | Setup owner | Notes |
|---|---|---|---|---|
| Claude Code | claude | --permission-mode default | Claude | Coldtea can pass task and MCP context where supported. Claude still owns slash commands, model choice, auth, and permissions. |
| Codex CLI | codex | --sandbox workspace-write --ask-for-approval on-request | Codex | Coldtea can attach MCP through Codex config args for launched panes. Codex sandbox and approval behavior still comes from Codex. |
| Gemini CLI | gemini | --approval-mode default | Gemini | Coldtea registers a coldtea MCP server in Gemini settings using session environment variables. Gemini still owns provider auth and approval modes. |
| OpenCode | opencode | no extra args | OpenCode | Coldtea runs OpenCode through its managed wrapper/plugin path when launched from the app. OpenCode owns /connect, provider setup, model switching, and its TUI prompts. |
The exact visible list depends on your build, workspace settings, and which binaries Coldtea can find on your machine.
How discovery works
Coldtea checks for known agent binaries through the shell environment and common install locations. It launches the bare command name, such as codex, so package-manager shims and version managers still choose the runtime.
If an agent is missing:
- Run the command in a normal terminal.
- Finish the agent's own first-run login or setup.
- Make sure the binary is on
PATHfor the shell Coldtea opens. - Restart Coldtea after changing shell setup.
- Check Settings → Agents for saved launch args.
Do not debug provider auth from Coldtea first. If the agent cannot start outside Coldtea, fix the agent install first.
Launch presets
Settings can save default launch args per agent. The presets are convenience wrappers around each CLI's own flags.
| Preset idea | What it usually means |
|---|---|
| Supervised | Start with the agent's normal approval flow. |
| Plan/read-only | Prefer inspection and planning before edits. Availability depends on the agent. |
| Auto-edit | Let the agent apply edits more freely while keeping other prompts. Availability depends on the agent. |
| Full autonomy / full access | Bypass more approval or sandbox checks. Treat this as a deliberate risk choice. |
OpenCode is different here: Coldtea's default local preset runs the OpenCode TUI directly and lets OpenCode own provider and permission prompts.
Task tools and MCP
Agent panes launched by Coldtea may receive session-scoped MCP access. That can let an agent inspect panes, read task context, write logs, or work with labels and QA runs when those tools are available.
Tool availability is not a guarantee across every pane:
- The agent must be launched from Coldtea.
- The session must have the right local API and MCP environment.
- Some tools require TeaHouse or task access.
- Feature flags and workspace setup can change the available tool list.
If MCP tools are missing, see MCP and local API.
What Coldtea does not own
Coldtea does not choose the model response, bypass a provider's account limits, or make an unsafe command safe.
For every agent, keep the same rule: if the CLI is asking to run a command, read the command as if you typed it yourself.
Next: agent setup or permissions.