diff --git a/gigacode/README.md b/gigacode/README.md
index 3ebbd89..bc18d95 100644
--- a/gigacode/README.md
+++ b/gigacode/README.md
@@ -2,7 +2,7 @@
This is not a fork (and never will be).
It's powered by Sandbox Agent SDK's wizardry.
Experimental & just for fun.
@@ -19,23 +19,23 @@
┌─ Gigacode ────────────────────────────────────────────────────────┐
│ ┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐ │
│ │ OpenCode TUI │───▶│ Sandbox Agent │───▶│ Claude Code / │ │
-│ │ │ │ │ │ Codex / Amp │ │
+│ │ │ │ │ │ Codex / Pi / Amp │ │
│ └─────────────────┘ └─────────────────┘ └─────────────────┘ │
└───────────────────────────────────────────────────────────────────┘
```
-- [Sandbox Agent SDK](https://sandboxagent.dev) provides a universal HTTP API for controlling Claude Code, Codex, and Amp
+- [Sandbox Agent SDK](https://sandboxagent.dev) provides a universal HTTP API for controlling Claude Code, Codex, Pi, and Amp
- Sandbox Agent SDK exposes an [OpenCode-compatible endpoint](https://sandboxagent.dev/docs/opencode-compatibility) so OpenCode can talk to any agent
- OpenCode connects to Sandbox Agent SDK via [`attach`](https://opencode.ai/docs/cli/#attach)
## OpenCode Models vs Gigacode Agents
- **OpenCode** supports **switching between inference providers** (Anthropic, OpenAI, etc.). This is OpenCode talking directly to the models with its own tools, system prompts, and agentic loop.
-- **Gigacode** automates other coding agent harnesses, so it's using the **exact same logic that you would if you ran Claude Code**, Codex, or Amp natively.
+- **Gigacode** automates other coding agent harnesses, so it's using the **exact same logic that you would if you ran Claude Code**, Codex, Pi, or Amp natively.
```
OpenCode (native): Model → OpenCode's tool loop → result
-Gigacode: Model → Claude Code / Codex / Amp CLI → result
+Gigacode: Model → Claude Code / Codex / Pi / Amp CLI → result
```
This means you get each agent's specialized capabilities (such as Claude Code's `Read`/`Write`/`Bash` tools, Codex's sandboxed execution, and Amp's permission rules) rather than a single tool loop with different models behind it.
diff --git a/server/packages/sandbox-agent/src/opencode_compat.rs b/server/packages/sandbox-agent/src/opencode_compat.rs
index 1393f94..357c81f 100644
--- a/server/packages/sandbox-agent/src/opencode_compat.rs
+++ b/server/packages/sandbox-agent/src/opencode_compat.rs
@@ -614,6 +614,7 @@ fn available_agent_ids() -> Vec