docs: clean up orphaned docs and add session event types

Delete orphaned docs not in docs.json navigation (gigacode.mdx,
foundry-self-hosting.mdx, session-transcript-schema.mdx, pi-support-plan.md).
Remove outdated musl/glibc troubleshooting section. Add event types
documentation with example payloads to agent-sessions.mdx.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Cargo.toml

@@ -4,7 +4,7 @@ members = ["server/packages/*", "gigacode"]
 exclude = ["factory/packages/desktop/src-tauri", "foundry/packages/desktop/src-tauri"]
 
 [workspace.package]
-version = "0.4.1"
+version = "0.4.2"
 edition = "2021"
 authors = [ "Rivet Gaming, LLC <developer@rivet.gg>" ]
 license = "Apache-2.0"
@@ -13,13 +13,13 @@ description = "Universal API for automatic coding agents in sandboxes. Supports
 
 [workspace.dependencies]
 # Internal crates
-sandbox-agent = { version = "0.4.1", path = "server/packages/sandbox-agent" }
+sandbox-agent = { version = "0.4.2", path = "server/packages/sandbox-agent" }
-sandbox-agent-error = { version = "0.4.1", path = "server/packages/error" }
+sandbox-agent-error = { version = "0.4.2", path = "server/packages/error" }
-sandbox-agent-agent-management = { version = "0.4.1", path = "server/packages/agent-management" }
+sandbox-agent-agent-management = { version = "0.4.2", path = "server/packages/agent-management" }
-sandbox-agent-agent-credentials = { version = "0.4.1", path = "server/packages/agent-credentials" }
+sandbox-agent-agent-credentials = { version = "0.4.2", path = "server/packages/agent-credentials" }
-sandbox-agent-opencode-adapter = { version = "0.4.1", path = "server/packages/opencode-adapter" }
+sandbox-agent-opencode-adapter = { version = "0.4.2", path = "server/packages/opencode-adapter" }
-sandbox-agent-opencode-server-manager = { version = "0.4.1", path = "server/packages/opencode-server-manager" }
+sandbox-agent-opencode-server-manager = { version = "0.4.2", path = "server/packages/opencode-server-manager" }
-acp-http-adapter = { version = "0.4.1", path = "server/packages/acp-http-adapter" }
+acp-http-adapter = { version = "0.4.2", path = "server/packages/acp-http-adapter" }
 
 # Serialization
 serde = { version = "1.0", features = ["derive"] }

docs/agent-sessions.mdx

@@ -51,6 +51,108 @@ await session.prompt([
 unsubscribe();
 ```
 
+### Event types
+
+Each event's `payload` contains a session update. The `sessionUpdate` field identifies the type.
+
+<AccordionGroup>
+<Accordion title="agent_message_chunk">
+Streamed text or content from the agent's response.
+
+```json
+{
+  "sessionUpdate": "agent_message_chunk",
+  "content": { "type": "text", "text": "Here's how the repository is structured..." }
+}
+```
+</Accordion>
+
+<Accordion title="agent_thought_chunk">
+Internal reasoning from the agent (chain-of-thought / extended thinking).
+
+```json
+{
+  "sessionUpdate": "agent_thought_chunk",
+  "content": { "type": "text", "text": "I should start by looking at the project structure..." }
+}
+```
+</Accordion>
+
+<Accordion title="user_message_chunk">
+Echo of the user's prompt being processed.
+
+```json
+{
+  "sessionUpdate": "user_message_chunk",
+  "content": { "type": "text", "text": "Summarize the repository structure." }
+}
+```
+</Accordion>
+
+<Accordion title="tool_call">
+The agent invoked a tool (file edit, terminal command, etc.).
+
+```json
+{
+  "sessionUpdate": "tool_call",
+  "toolCallId": "tc_abc123",
+  "title": "Read file",
+  "status": "in_progress",
+  "rawInput": { "path": "/src/index.ts" }
+}
+```
+</Accordion>
+
+<Accordion title="tool_call_update">
+Progress or result update for an in-progress tool call.
+
+```json
+{
+  "sessionUpdate": "tool_call_update",
+  "toolCallId": "tc_abc123",
+  "status": "completed",
+  "content": [{ "type": "text", "text": "import express from 'express';\n..." }]
+}
+```
+</Accordion>
+
+<Accordion title="plan">
+The agent's execution plan for the current task.
+
+```json
+{
+  "sessionUpdate": "plan",
+  "entries": [
+    { "content": "Read the project structure", "status": "completed" },
+    { "content": "Identify main entrypoints", "status": "in_progress" },
+    { "content": "Write summary", "status": "pending" }
+  ]
+}
+```
+</Accordion>
+
+<Accordion title="usage_update">
+Token usage metrics for the current turn.
+
+```json
+{
+  "sessionUpdate": "usage_update"
+}
+```
+</Accordion>
+
+<Accordion title="session_info_update">
+Session metadata changed (e.g. agent-generated title).
+
+```json
+{
+  "sessionUpdate": "session_info_update",
+  "title": "Repository structure analysis"
+}
+```
+</Accordion>
+</AccordionGroup>
+
 ## Fetch persisted event history
 
 ```ts

docs/architecture.mdx

@@ -56,7 +56,7 @@ Agents are installed lazily on first use. To avoid the cold-start delay, pre-ins
 sandbox-agent install-agent --all
 ```
 
-The `rivetdev/sandbox-agent:0.4.1-full` Docker image ships with all agents pre-installed.
+The `rivetdev/sandbox-agent:0.4.2-full` Docker image ships with all agents pre-installed.
 
 ## Production-ready agent orchestration
 

docs/deploy/daytona.mdx

@@ -44,7 +44,7 @@ try {
 }
 ```
 
-The `daytona` provider uses the `rivetdev/sandbox-agent:0.4.1-full` image by default and starts the server automatically.
+The `daytona` provider uses the `rivetdev/sandbox-agent:0.4.2-full` image by default and starts the server automatically.
 
 ## Using snapshots for faster startup
 

docs/deploy/docker.mdx

@@ -15,11 +15,11 @@ Run the published full image with all supported agents pre-installed:
 docker run --rm -p 3000:3000 \
   -e ANTHROPIC_API_KEY="$ANTHROPIC_API_KEY" \
   -e OPENAI_API_KEY="$OPENAI_API_KEY" \
-  rivetdev/sandbox-agent:0.4.1-full \
+  rivetdev/sandbox-agent:0.4.2-full \
   server --no-token --host 0.0.0.0 --port 3000
 ```
 
-The `0.4.1-full` tag pins the exact version. The moving `full` tag is also published for contributors who want the latest full image.
+The `0.4.2-full` tag pins the exact version. The moving `full` tag is also published for contributors who want the latest full image.
 
 If you also want the desktop API inside the container, install desktop dependencies before starting the server:
 
@@ -52,7 +52,7 @@ const docker = new Docker();
 const PORT = 3000;
 
 const container = await docker.createContainer({
-  Image: "rivetdev/sandbox-agent:0.4.1-full",
+  Image: "rivetdev/sandbox-agent:0.4.2-full",
   Cmd: ["server", "--no-token", "--host", "0.0.0.0", "--port", `${PORT}`],
   Env: [
     `ANTHROPIC_API_KEY=${process.env.ANTHROPIC_API_KEY}`,

docs/deploy/foundry-self-hosting.mdx

@@ -1,155 +0,0 @@
----
-title: "Foundry Self-Hosting"
-description: "Environment, credentials, and deployment setup for Sandbox Agent Foundry auth, GitHub, and billing."
----
-
-This guide documents the deployment contract for the Foundry product surface: app auth, GitHub onboarding, repository import, and billing.
-
-It also covers the local-development bootstrap that uses `.env.development` only when `NODE_ENV=development`.
-
-## Local Development
-
-For backend local development, the Foundry backend now supports a development-only dotenv bootstrap:
-
-- It loads `.env.development.local` and `.env.development`
-- It does this **only** when `NODE_ENV=development`
-- It does **not** load dotenv files in production
-
-The example file lives at [`/.env.development.example`](https://github.com/rivet-dev/sandbox-agent/blob/main/.env.development.example).
-
-To use it locally:
-
-```bash
-cp .env.development.example .env.development
-```
-
-Run the backend with:
-
-```bash
-just foundry-backend-start
-```
-
-That recipe sets `NODE_ENV=development`, which enables the dotenv loader.
-
-### Local Defaults
-
-These values can be safely defaulted for local development:
-
-- `APP_URL=http://localhost:4173`
-- `BETTER_AUTH_URL=http://localhost:7741`
-- `BETTER_AUTH_SECRET=sandbox-agent-foundry-development-only-change-me`
-- `GITHUB_REDIRECT_URI=http://localhost:7741/v1/auth/callback/github`
-
-These should be treated as development-only values.
-
-## Production Environment
-
-For production or self-hosting, set these as real environment variables in your deployment platform. Do not rely on dotenv file loading.
-
-### App/Auth
-
-| Variable | Required | Notes |
-|---|---:|---|
-| `APP_URL` | Yes | Public frontend origin |
-| `BETTER_AUTH_URL` | Yes | Public auth base URL |
-| `BETTER_AUTH_SECRET` | Yes | Strong random secret for auth/session signing |
-
-### GitHub OAuth
-
-| Variable | Required | Notes |
-|---|---:|---|
-| `GITHUB_CLIENT_ID` | Yes | GitHub OAuth app client id |
-| `GITHUB_CLIENT_SECRET` | Yes | GitHub OAuth app client secret |
-| `GITHUB_REDIRECT_URI` | Yes | GitHub OAuth callback URL |
-
-Use GitHub OAuth for:
-
-- user sign-in
-- user identity
-- org selection
-- access to the signed-in user’s GitHub context
-
-## GitHub App
-
-If your Foundry deployment uses GitHub App-backed organization install and repo import, also configure:
-
-| Variable | Required | Notes |
-|---|---:|---|
-| `GITHUB_APP_ID` | Yes | GitHub App id |
-| `GITHUB_APP_CLIENT_ID` | Yes | GitHub App client id |
-| `GITHUB_APP_CLIENT_SECRET` | Yes | GitHub App client secret |
-| `GITHUB_APP_PRIVATE_KEY` | Yes | PEM private key for installation auth |
-
-For `.env.development` and `.env.development.local`, store `GITHUB_APP_PRIVATE_KEY` as a quoted single-line value with `\n` escapes instead of raw multi-line PEM text.
-
-Recommended GitHub App permissions:
-
-- Repository `Metadata: Read`
-- Repository `Contents: Read & Write`
-- Repository `Pull requests: Read & Write`
-- Repository `Checks: Read`
-- Repository `Commit statuses: Read`
-
-Set the webhook URL to `https://<your-backend-host>/v1/webhooks/github` and generate a webhook secret. Store the secret as `GITHUB_WEBHOOK_SECRET`.
-
-This is required, not optional. Foundry depends on GitHub App webhook delivery for installation lifecycle changes, repo access changes, and ongoing repo / pull request sync. If the GitHub App is not installed for the workspace, or webhook delivery is misconfigured, Foundry will remain in an install / reconnect state and core GitHub-backed functionality will not work correctly.
-
-Recommended webhook subscriptions:
-
-- `installation`
-- `installation_repositories`
-- `pull_request`
-- `pull_request_review`
-- `pull_request_review_comment`
-- `push`
-- `create`
-- `delete`
-- `check_suite`
-- `check_run`
-- `status`
-
-Use the GitHub App for:
-
-- installation/reconnect state
-- org repo import
-- repository sync
-- PR creation and updates
-
-Use GitHub OAuth for:
-
-- who the user is
-- which orgs they can choose
-
-## Stripe
-
-For live billing, configure:
-
-| Variable | Required | Notes |
-|---|---:|---|
-| `STRIPE_SECRET_KEY` | Yes | Server-side Stripe secret key |
-| `STRIPE_PUBLISHABLE_KEY` | Yes | Client-side Stripe publishable key |
-| `STRIPE_WEBHOOK_SECRET` | Yes | Signing secret for billing webhooks |
-| `STRIPE_PRICE_TEAM` | Yes | Stripe price id for the Team plan checkout session |
-
-Stripe should own:
-
-- hosted checkout
-- billing portal
-- subscription status
-- invoice history
-- webhook-driven state sync
-
-## Mock Invariant
-
-Foundry’s mock client path should continue to work end to end even when the real auth/GitHub/Stripe path exists.
-
-That includes:
-
-- sign-in
-- org selection/import
-- settings
-- billing UI
-- workspace/task/session flow
-- seat accrual
-
-Use mock mode for deterministic UI review and local product development. Use the real env-backed path for integration and self-hosting.

docs/docs.json

@@ -1,6 +1,6 @@
 {
   "$schema": "https://mintlify.com/docs.json",
-  "theme": "willow",
+  "theme": "mint",
   "name": "Sandbox Agent SDK",
   "appearance": {
     "default": "dark",
@@ -25,11 +25,6 @@
   },
   "navbar": {
     "links": [
-      {
-        "label": "Gigacode",
-        "icon": "terminal",
-        "href": "https://github.com/rivet-dev/sandbox-agent/tree/main/gigacode"
-      },
       {
         "label": "Discord",
         "icon": "discord",
@@ -90,13 +85,10 @@
             "group": "System",
             "pages": ["file-system", "processes", "computer-use", "common-software"]
           },
-          {
-            "group": "Orchestration",
-            "pages": ["orchestration-architecture", "session-persistence", "observability", "multiplayer", "security"]
-          },
           {
             "group": "Reference",
             "pages": [
+              "troubleshooting",
               "architecture",
               "cli",
               "inspector",
@@ -129,5 +121,10 @@
       }
     ]
   },
-  "styles": ["/theme.css"]
+  "__removed": [
+	  {
+		"group": "Orchestration",
+		"pages": ["orchestration-architecture", "session-persistence", "observability", "multiplayer", "security"]
+	  }
+  ]
 }

docs/gigacode.mdx

@@ -1,6 +0,0 @@
----
-title: Gigacode
-url: "https://github.com/rivet-dev/sandbox-agent/tree/main/gigacode"
----
-
-

docs/openapi.json

@@ -10,7 +10,7 @@
     "license": {
       "name": "Apache-2.0"
     },
-    "version": "0.4.1"
+    "version": "0.4.2"
   },
   "servers": [
     {

docs/pi-support-plan.md

@@ -1,210 +0,0 @@
-# Pi Agent Support Plan (pi-mono)
-
-## Implementation Status Update
-
-- Runtime selection now supports two internal modes:
-  - `PerSession` (default for unknown/non-allowlisted Pi capabilities)
-  - `Shared` (allowlist-only compatibility path)
-- Pi sessions now use per-session process isolation by default, enabling true concurrent Pi sessions in Inspector and API clients.
-- Shared Pi server code remains available and is used only when capability checks allow multiplexing.
-- Session termination for per-session Pi mode hard-kills the underlying Pi process and clears queued prompts/pending waiters.
-- In-session concurrent sends are serialized with an unbounded daemon-side FIFO queue per session.
-
-## Investigation Summary
-
-### Pi CLI modes and RPC protocol
-- Pi supports multiple modes including interactive, print/JSON output, RPC, and SDK usage. JSON mode outputs a stream of JSON events suitable for parsing, and RPC mode is intended for programmatic control over stdin/stdout.
-- RPC mode is started with `pi --mode rpc` and supports options like `--provider`, `--model`, `--no-session`, and `--session-dir`.
-- The RPC protocol is newline-delimited JSON over stdin/stdout:
-  - Commands are JSON objects written to stdin.
-  - Responses are JSON objects with `type: "response"` and optional `id`.
-  - Events are JSON objects without `id`.
-- `prompt` can include images using `ImageContent` (base64 or URL) alongside text.
-- JSON/print mode (`pi -p` or `pi --print --mode json`) produces JSONL for non-interactive parsing and can resume sessions with a token.
-
-### RPC commands
-RPC commands listed in `rpc.md` include:
-- `new_session`, `get_state`, `list_sessions`, `delete_session`, `rename_session`, `clear_session`
-- `prompt`, `queue_message`, `abort`, `get_queued_messages`
-
-### RPC event types
-RPC events listed in `rpc.md` include:
-- `agent_start`, `agent_end`
-- `turn_start`, `turn_end`
-- `message_start`, `message_update`, `message_end`
-- `tool_execution_start`, `tool_execution_update`, `tool_execution_end`
-- `auto_compaction`, `auto_retry`, `hook_error`
-
-`message_update` uses `assistantMessageEvent` deltas such as:
-- `start`, `text_start`, `text_delta`, `text_end`
-- `thinking_start`, `thinking_delta`, `thinking_end`
-- `toolcall_start`, `toolcall_delta`, `toolcall_end`
-- `toolcall_args_start`, `toolcall_args_delta`, `toolcall_args_end`
-- `done`, `error`
-
-`tool_execution_update` includes `partialResult`, which is described as accumulated output so far.
-
-### Schema source locations (pi-mono)
-RPC types are documented as living in:
-- `packages/ai/src/types.ts` (Model types)
-- `packages/agent/src/types.ts` (AgentResponse types)
-- `packages/coding-agent/src/core/messages.ts` (message types)
-- `packages/coding-agent/src/modes/rpc/rpc-types.ts` (RPC protocol types)
-
-### Distribution assets
-Pi releases provide platform-specific binaries such as:
-- `pi-darwin-arm64`, `pi-darwin-x64`
-- `pi-linux-arm64`, `pi-linux-x64`
-- `pi-win-x64.zip`
-
-## Integration Decisions
-- Follow the OpenCode pattern: a shared long-running process (stdio RPC) with session multiplexing.
-- Primary integration path is RPC streaming (`pi --mode rpc`).
-- JSON/print mode is a fallback only (diagnostics or non-interactive runs).
-- Create sessions via `new_session`; store the returned `sessionId` as `native_session_id`.
-- Use `get_state` as a re-sync path after server restarts.
-- Use `prompt` for send-message, with optional image content.
-- Convert Pi events into universal events; emit daemon synthetic `session.started` on session creation and `session.ended` only on errors/termination.
-
-## Implementation Plan
-
-### 1) Agent Identity + Capabilities
-Files:
-- `server/packages/agent-management/src/agents.rs`
-- `server/packages/sandbox-agent/src/router.rs`
-- `docs/cli.mdx`, `docs/conversion.mdx`, `docs/session-transcript-schema.mdx`
-- `README.md`, `frontend/packages/website/src/components/FAQ.tsx`
-
-Tasks:
-- Add `AgentId::Pi` with string/binary name `"pi"` and parsing rules.
-- Add Pi to `all_agents()` and agent lists.
-- Define `AgentCapabilities` for Pi:
-  - `tool_calls=true`, `tool_results=true`
-  - `text_messages=true`, `streaming_deltas=true`, `item_started=true`
-  - `reasoning=true` (from `thinking_*` deltas)
-  - `images=true` (ImageContent in `prompt`)
-  - `permissions=false`, `questions=false`, `mcp_tools=false`
-  - `shared_process=true`, `session_lifecycle=false` (no native session events)
-  - `error_events=true` (hook_error)
-  - `command_execution=false`, `file_changes=false`, `file_attachments=false`
-
-### 2) Installer and Binary Resolution
-Files:
-- `server/packages/agent-management/src/agents.rs`
-
-Tasks:
-- Add `install_pi()` that:
-  - Downloads the correct release asset per platform (`pi-<platform>`).
-  - Handles `.zip` on Windows and raw binaries elsewhere.
-  - Marks binary executable.
-- Add Pi to `AgentManager::install`, `is_installed`, `version`.
-- Version detection: try `--version`, `version`, `-V`.
-
-### 3) Schema Extraction for Pi
-Files:
-- `resources/agent-schemas/src/pi.ts` (new)
-- `resources/agent-schemas/src/index.ts`
-- `resources/agent-schemas/artifacts/json-schema/pi.json`
-- `server/packages/extracted-agent-schemas/build.rs`
-- `server/packages/extracted-agent-schemas/src/lib.rs`
-
-Tasks:
-- Implement `extractPiSchema()`:
-  - Download pi-mono sources (zip/tarball) into a temp dir.
-  - Use `ts-json-schema-generator` against `packages/coding-agent/src/modes/rpc/rpc-types.ts`.
-  - Include dependent files per `rpc.md` (ai/types, agent/types, core/messages).
-  - Extract `RpcEvent`, `RpcResponse`, `RpcCommand` unions (exact type names from source).
-- Add fallback schema if remote fetch fails (minimal union with event/response fields).
-- Wire pi into extractor index and artifact generation.
-
-### 4) Universal Schema Conversion (Pi -> Universal)
-Files:
-- `server/packages/universal-agent-schema/src/agents/pi.rs` (new)
-- `server/packages/universal-agent-schema/src/agents/mod.rs`
-- `server/packages/universal-agent-schema/src/lib.rs`
-- `server/packages/sandbox-agent/src/router.rs`
-
-Mapping rules:
-- `message_start` -> `item.started` (kind=message, role=assistant, native_item_id=messageId)
-- `message_update`:
-  - `text_*` -> `item.delta` (assistant text delta)
-  - `thinking_*` -> `item.delta` with `ContentPart::Reasoning` (visibility=Private)
-  - `toolcall_*` and `toolcall_args_*` -> ignore for now (tool_execution_* is authoritative)
-  - `error` -> `item.completed` with `ItemStatus::Failed` (if no later message_end)
-- `message_end` -> `item.completed` (finalize assistant message)
-- `tool_execution_start` -> `item.started` (kind=tool_call, ContentPart::ToolCall)
-- `tool_execution_update` -> `item.delta` for a synthetic tool_result item:
-  - Maintain a per-toolCallId buffer to compute delta from accumulated `partialResult`.
-- `tool_execution_end` -> `item.completed` (kind=tool_result, output from `result.content`)
-  - If `isError=true`, set item status to failed.
-- `agent_start`, `turn_start`, `turn_end`, `agent_end`, `auto_compaction`, `auto_retry`, `hook_error`:
-  - Map to `ItemKind::Status` with a label like `pi.agent_start`, `pi.auto_retry`, etc.
-  - Do not emit `session.ended` for these events.
-- If event parsing fails, emit `agent.unparsed` (source=daemon, synthetic=true) and fail tests.
-
-### 5) Shared RPC Server Integration
-Files:
-- `server/packages/sandbox-agent/src/router.rs`
-
-Tasks:
-- Add a new managed stdio server type for Pi, similar to Codex:
-  - Create `PiServer` struct with:
-    - stdin sender
-    - pending request map keyed by request id
-    - per-session native session id mapping
-  - Extend `ManagedServerKind` to include Pi.
-  - Add `ensure_pi_server()` and `spawn_pi_server()` using `pi --mode rpc`.
-  - Add a `handle_pi_server_output()` loop to parse stdout lines into events/responses.
-- Session creation:
-  - On `create_session`, ensure Pi server is running, send `new_session`, store sessionId.
-  - Register session with `server_manager.register_session` for native mapping.
-- Sending messages:
-  - Use `prompt` command; include sessionId and optional images.
-  - Emit synthetic `item.started` only if Pi does not emit `message_start`.
-
-### 6) Router + Streaming Path Changes
-Files:
-- `server/packages/sandbox-agent/src/router.rs`
-
-Tasks:
-- Add Pi handling to:
-  - `create_session` (new_session)
-  - `send_message` (prompt)
-  - `parse_agent_line` (Pi event conversion)
-  - `agent_modes` (default to `default` unless Pi exposes a mode list)
-  - `agent_supports_resume` (true if Pi supports session resume)
-
-### 7) Tests
-Files:
-- `server/packages/sandbox-agent/tests/...`
-- `server/packages/universal-agent-schema/tests/...` (if present)
-
-Tasks:
-- Unit tests for conversion:
-  - `message_start/update/end` -> item.started/delta/completed
-  - `tool_execution_*` -> tool call/result mapping with partialResult delta
-  - failure -> agent.unparsed
-- Integration tests:
-  - Start Pi RPC server, create session, send prompt, stream events.
-  - Validate `native_session_id` mapping and event ordering.
-- Update HTTP/SSE test coverage to include Pi agent if relevant.
-
-## Risk Areas / Edge Cases
-- `tool_execution_update.partialResult` is cumulative; must compute deltas.
-- `message_update` may emit `done`/`error` without `message_end`; handle both paths.
-- No native session lifecycle events; rely on daemon synthetic events.
-- Session recovery after RPC server restart requires `get_state` + re-register sessions.
-
-## Acceptance Criteria
-- Pi appears in `/v1/agents`, CLI list, and docs.
-- `create_session` returns `native_session_id` from Pi `new_session`.
-- Streaming prompt yields universal events with proper ordering:
-  - message -> item.started/delta/completed
-  - tool execution -> tool call + tool result
-- Tests pass and no synthetic data is used in test fixtures.
-
-## Sources
-- https://upd.dev/badlogic/pi-mono/src/commit/d36e0ea07303d8a76d51b4a7bd5f0d6d3c490860/packages/coding-agent/docs/rpc.md
-- https://buildwithpi.ai/pi-cli
-- https://takopi.dev/docs/pi-cli/
-- https://upd.dev/badlogic/pi-mono/releases

docs/quickstart.mdx

@@ -64,7 +64,7 @@ icon: "rocket"
         docker run -p 2468:2468 \
           -e ANTHROPIC_API_KEY="sk-ant-..." \
           -e OPENAI_API_KEY="sk-..." \
-          rivetdev/sandbox-agent:0.4.1-full \
+          rivetdev/sandbox-agent:0.4.2-full \
           server --no-token --host 0.0.0.0 --port 2468
         ```
       </Tab>

docs/session-transcript-schema.mdx

@@ -1,388 +0,0 @@
----
-title: "Session Transcript Schema"
-description: "Universal event schema for session transcripts across all agents."
----
-
-Each coding agent outputs events in its own native format. The sandbox-agent converts these into a universal event schema, giving you a consistent session transcript regardless of which agent you use.
-
-The schema is defined in [OpenAPI format](https://github.com/rivet-dev/sandbox-agent/blob/main/docs/openapi.json). See the [HTTP API Reference](/api-reference) for endpoint documentation.
-
-## Coverage Matrix
-
-This table shows which agent feature coverage appears in the universal event stream. All agents retain their full native feature coverage—this only reflects what's normalized into the schema.
-
-| Feature            | Claude | Codex | OpenCode     | Amp          | Pi (RPC)     |
-|--------------------|:------:|:-----:|:------------:|:------------:|:------------:|
-| Stability          | Stable | Stable| Experimental | Experimental | Experimental |
-| Text Messages      |   ✓    |   ✓   |      ✓       |      ✓       |      ✓       |
-| Tool Calls         |   ✓    |   ✓   |      ✓       |      ✓       |      ✓       |
-| Tool Results       |   ✓    |   ✓   |      ✓       |      ✓       |      ✓       |
-| Questions (HITL)   |   ✓    |       |      ✓       |              |              |
-| Permissions (HITL) |   ✓    |   ✓   |      ✓       |      -       |              |
-| Images             |   -    |   ✓   |      ✓       |      -       |      ✓       |
-| File Attachments   |   -    |   ✓   |      ✓       |      -       |              |
-| Session Lifecycle  |   -    |   ✓   |      ✓       |      -       |              |
-| Error Events       |   -    |   ✓   |      ✓       |      ✓       |      ✓       |
-| Reasoning/Thinking |   -    |   ✓   |      -       |      -       |      ✓       |
-| Command Execution  |   -    |   ✓   |      -       |      -       |              |
-| File Changes       |   -    |   ✓   |      -       |      -       |              |
-| MCP Tools          |   ✓    |   ✓   |      ✓       |      ✓       |              |
-| Streaming Deltas   |   ✓    |   ✓   |      ✓       |      -       |      ✓       |
-| Variants           |        |   ✓   |      ✓       |      ✓       |      ✓       |
-
-Agents: [Claude Code](https://docs.anthropic.com/en/docs/agents-and-tools/claude-code/overview) · [Codex](https://github.com/openai/codex) · [OpenCode](https://github.com/opencode-ai/opencode) · [Amp](https://ampcode.com) · [Pi](https://buildwithpi.ai/pi-cli)
-
-- ✓ = Appears in session events
-- \- = Agent supports natively, schema conversion coming soon
-- (blank) = Not supported by agent
-- Pi runtime model is router-managed per-session RPC (`pi --mode rpc`); it does not use generic subprocess streaming.
-
-<AccordionGroup>
-  <Accordion title="Text Messages">
-    Basic message exchange between user and assistant.
-  </Accordion>
-  <Accordion title="Tool Calls & Results">
-    Visibility into tool invocations (file reads, command execution, etc.) and their results. When not natively supported, tool activity is embedded in message content.
-  </Accordion>
-  <Accordion title="Questions (HITL)">
-    Interactive questions the agent asks the user. Emits `question.requested` and `question.resolved` events.
-  </Accordion>
-  <Accordion title="Permissions (HITL)">
-    Permission requests for sensitive operations. Emits `permission.requested` and `permission.resolved` events.
-  </Accordion>
-  <Accordion title="Images">
-    Support for image attachments in messages.
-  </Accordion>
-  <Accordion title="File Attachments">
-    Support for file attachments in messages.
-  </Accordion>
-  <Accordion title="Session Lifecycle">
-    Native `session.started` and `session.ended` events. When not supported, the daemon emits synthetic lifecycle events.
-  </Accordion>
-  <Accordion title="Error Events">
-    Structured error events for runtime failures.
-  </Accordion>
-  <Accordion title="Reasoning/Thinking">
-    Extended thinking or reasoning content with visibility controls.
-  </Accordion>
-  <Accordion title="Command Execution">
-    Detailed command execution events with stdout/stderr.
-  </Accordion>
-  <Accordion title="File Changes">
-    Structured file modification events with diffs.
-  </Accordion>
-  <Accordion title="MCP Tools">
-    Model Context Protocol tool support.
-  </Accordion>
-  <Accordion title="Streaming Deltas">
-    Native streaming of content deltas. When not supported, the daemon emits a single synthetic delta before `item.completed`.
-  </Accordion>
-  <Accordion title="Variants">
-    Model variants such as reasoning effort or depth. Agents may expose different variant sets per model.
-  </Accordion>
-</AccordionGroup>
-
-Want support for another agent? [Open an issue](https://github.com/rivet-dev/sandbox-agent/issues/new) to request it.
-
-## UniversalEvent
-
-Every event from the API is wrapped in a `UniversalEvent` envelope.
-
-| Field | Type | Description |
-|-------|------|-------------|
-| `event_id` | string | Unique identifier for this event |
-| `sequence` | integer | Monotonic sequence number within the session (starts at 1) |
-| `time` | string | RFC3339 timestamp |
-| `session_id` | string | Daemon-generated session identifier |
-| `native_session_id` | string? | Provider-native session/thread identifier (e.g., Codex `threadId`, OpenCode `sessionID`) |
-| `source` | string | Event origin: `agent` (native) or `daemon` (synthetic) |
-| `synthetic` | boolean | Whether this event was generated by the daemon to fill gaps |
-| `type` | string | Event type (see [Event Types](#event-types)) |
-| `data` | object | Event-specific payload |
-| `raw` | any? | Original provider payload (only when `include_raw=true`) |
-
-```json
-{
-  "event_id": "evt_abc123",
-  "sequence": 1,
-  "time": "2025-01-28T12:00:00Z",
-  "session_id": "my-session",
-  "native_session_id": "thread_xyz",
-  "source": "agent",
-  "synthetic": false,
-  "type": "item.completed",
-  "data": { ... }
-}
-```
-
-## Event Types
-
-### Session Lifecycle
-
-| Type | Description | Data |
-|------|-------------|------|
-| `session.started` | Session has started | `{ metadata?: any }` |
-| `session.ended` | Session has ended | `{ reason, terminated_by, message?, exit_code? }` |
-
-### Turn Lifecycle
-
-| Type | Description | Data |
-|------|-------------|------|
-| `turn.started` | Turn has started | `{ phase: "started", turn_id?, metadata? }` |
-| `turn.ended` | Turn has ended | `{ phase: "ended", turn_id?, metadata? }` |
-
-**SessionEndedData**
-
-| Field | Type | Values |
-|-------|------|--------|
-| `reason` | string | `completed`, `error`, `terminated` |
-| `terminated_by` | string | `agent`, `daemon` |
-| `message` | string? | Error message (only present when reason is `error`) |
-| `exit_code` | int? | Process exit code (only present when reason is `error`) |
-| `stderr` | StderrOutput? | Structured stderr output (only present when reason is `error`) |
-
-**StderrOutput**
-
-| Field | Type | Description |
-|-------|------|-------------|
-| `head` | string? | First 20 lines of stderr (if truncated) or full stderr (if not truncated) |
-| `tail` | string? | Last 50 lines of stderr (only present if truncated) |
-| `truncated` | boolean | Whether the output was truncated |
-| `total_lines` | int? | Total number of lines in stderr |
-
-### Item Lifecycle
-
-| Type | Description | Data |
-|------|-------------|------|
-| `item.started` | Item creation | `{ item }` |
-| `item.delta` | Streaming content delta | `{ item_id, native_item_id?, delta }` |
-| `item.completed` | Item finalized | `{ item }` |
-
-Items follow a consistent lifecycle: `item.started` → `item.delta` (0 or more) → `item.completed`.
-
-### HITL (Human-in-the-Loop)
-
-| Type | Description | Data |
-|------|-------------|------|
-| `permission.requested` | Permission request pending | `{ permission_id, action, status, metadata? }` |
-| `permission.resolved` | Permission decision recorded | `{ permission_id, action, status, metadata? }` |
-| `question.requested` | Question pending user input | `{ question_id, prompt, options, status }` |
-| `question.resolved` | Question answered or rejected | `{ question_id, prompt, options, status, response? }` |
-
-**PermissionEventData**
-
-| Field | Type | Description |
-|-------|------|-------------|
-| `permission_id` | string | Identifier for the permission request |
-| `action` | string | What the agent wants to do |
-| `status` | string | `requested`, `accept`, `accept_for_session`, `reject` |
-| `metadata` | any? | Additional context |
-
-**QuestionEventData**
-
-| Field | Type | Description |
-|-------|------|-------------|
-| `question_id` | string | Identifier for the question |
-| `prompt` | string | Question text |
-| `options` | string[] | Available answer options |
-| `status` | string | `requested`, `answered`, `rejected` |
-| `response` | string? | Selected answer (when resolved) |
-
-### Errors
-
-| Type | Description | Data |
-|------|-------------|------|
-| `error` | Runtime error | `{ message, code?, details? }` |
-| `agent.unparsed` | Parse failure | `{ error, location, raw_hash? }` |
-
-The `agent.unparsed` event indicates the daemon failed to parse an agent payload. This should be treated as a bug.
-
-## UniversalItem
-
-Items represent discrete units of content within a session.
-
-| Field | Type | Description |
-|-------|------|-------------|
-| `item_id` | string | Daemon-generated identifier |
-| `native_item_id` | string? | Provider-native item/message identifier |
-| `parent_id` | string? | Parent item ID (e.g., tool call/result parented to a message) |
-| `kind` | string | Item category (see below) |
-| `role` | string? | Actor role for message items |
-| `status` | string | Lifecycle status |
-| `content` | ContentPart[] | Ordered list of content parts |
-
-### ItemKind
-
-| Value | Description |
-|-------|-------------|
-| `message` | User or assistant message |
-| `tool_call` | Tool invocation |
-| `tool_result` | Tool execution result |
-| `system` | System message |
-| `status` | Status update |
-| `unknown` | Unrecognized item type |
-
-### ItemRole
-
-| Value | Description |
-|-------|-------------|
-| `user` | User message |
-| `assistant` | Assistant response |
-| `system` | System prompt |
-| `tool` | Tool-related message |
-
-### ItemStatus
-
-| Value | Description |
-|-------|-------------|
-| `in_progress` | Item is streaming or pending |
-| `completed` | Item is finalized |
-| `failed` | Item execution failed |
-
-## Content Parts
-
-The `content` array contains typed parts that make up an item's payload.
-
-### text
-
-Plain text content.
-
-```json
-{ "type": "text", "text": "Hello, world!" }
-```
-
-### json
-
-Structured JSON content.
-
-```json
-{ "type": "json", "json": { "key": "value" } }
-```
-
-### tool_call
-
-Tool invocation.
-
-| Field | Type | Description |
-|-------|------|-------------|
-| `name` | string | Tool name |
-| `arguments` | string | JSON-encoded arguments |
-| `call_id` | string | Unique call identifier |
-
-```json
-{
-  "type": "tool_call",
-  "name": "read_file",
-  "arguments": "{\"path\": \"/src/main.ts\"}",
-  "call_id": "call_abc123"
-}
-```
-
-### tool_result
-
-Tool execution result.
-
-| Field | Type | Description |
-|-------|------|-------------|
-| `call_id` | string | Matching call identifier |
-| `output` | string | Tool output |
-
-```json
-{
-  "type": "tool_result",
-  "call_id": "call_abc123",
-  "output": "File contents here..."
-}
-```
-
-### file_ref
-
-File reference with optional diff.
-
-| Field | Type | Description |
-|-------|------|-------------|
-| `path` | string | File path |
-| `action` | string | `read`, `write`, `patch` |
-| `diff` | string? | Unified diff (for patches) |
-
-```json
-{
-  "type": "file_ref",
-  "path": "/src/main.ts",
-  "action": "write",
-  "diff": "@@ -1,3 +1,4 @@\n+import { foo } from 'bar';"
-}
-```
-
-### image
-
-Image reference.
-
-| Field | Type | Description |
-|-------|------|-------------|
-| `path` | string | Image file path |
-| `mime` | string? | MIME type |
-
-```json
-{ "type": "image", "path": "/tmp/screenshot.png", "mime": "image/png" }
-```
-
-### reasoning
-
-Model reasoning/thinking content.
-
-| Field | Type | Description |
-|-------|------|-------------|
-| `text` | string | Reasoning text |
-| `visibility` | string | `public` or `private` |
-
-```json
-{ "type": "reasoning", "text": "Let me think about this...", "visibility": "public" }
-```
-
-### status
-
-Status indicator.
-
-| Field | Type | Description |
-|-------|------|-------------|
-| `label` | string | Status label |
-| `detail` | string? | Additional detail |
-
-```json
-{ "type": "status", "label": "Running tests", "detail": "3 of 10 passed" }
-```
-
-## Source & Synthetics
-
-### EventSource
-
-The `source` field indicates who emitted the event:
-
-| Value | Description |
-|-------|-------------|
-| `agent` | Native event from the agent |
-| `daemon` | Synthetic event generated by the daemon |
-
-### Synthetic Events
-
-The daemon emits synthetic events (`synthetic: true`, `source: "daemon"`) to provide a consistent event stream across all agents. Common synthetics:
-
-| Synthetic | When |
-|-----------|------|
-| `session.started` | Agent doesn't emit explicit session start |
-| `session.ended` | Agent doesn't emit explicit session end |
-| `turn.started` | Agent doesn't emit explicit turn start |
-| `turn.ended` | Agent doesn't emit explicit turn end |
-| `item.started` | Agent doesn't emit item start events |
-| `item.delta` | Agent doesn't stream deltas natively |
-| `question.*` | Claude Code plan mode (from ExitPlanMode tool) |
-
-### Raw Payloads
-
-Pass `include_raw=true` to event endpoints to receive the original agent payload in the `raw` field. Useful for debugging or accessing agent-specific data not in the universal schema.
-
-```typescript
-const events = await client.getEvents("my-session", { includeRaw: true });
-// events[0].raw contains the original agent payload
-```

docs/troubleshooting.mdx

@@ -29,25 +29,6 @@ Verify the agent is installed:
 ls -la ~/.local/share/sandbox-agent/bin/
 ```
 
-### 4. Binary libc mismatch (musl vs glibc)
-
-Claude Code binaries are available in both musl and glibc variants. If you see errors like:
-
-```
-cannot execute: required file not found
-Error loading shared library libstdc++.so.6: No such file or directory
-```
-
-This means the wrong binary variant was downloaded.
-
-**For sandbox-agent 0.2.0+**: Platform detection is automatic. The correct binary (musl or glibc) is downloaded based on the runtime environment.
-
-**For sandbox-agent 0.1.x**: Use Alpine Linux which has native musl support:
-
-```dockerfile
-FROM alpine:latest
-RUN apk add --no-cache curl ca-certificates libstdc++ libgcc bash
-```
 
 ## Daytona Network Restrictions
 

examples/shared/src/docker.ts

@@ -9,7 +9,7 @@ const __dirname = path.dirname(fileURLToPath(import.meta.url));
 const REPO_ROOT = path.resolve(__dirname, "..", "..", "..");
 
 /** Pre-built Docker image with all agents installed. */
-export const FULL_IMAGE = "rivetdev/sandbox-agent:0.4.1-full";
+export const FULL_IMAGE = "rivetdev/sandbox-agent:0.4.2-full";
 
 export interface DockerSandboxOptions {
   /** Container port used by sandbox-agent inside Docker. */

sdks/acp-http-client/package.json

@@ -1,6 +1,6 @@
 {
   "name": "acp-http-client",
-  "version": "0.4.1",
+  "version": "0.4.2",
   "description": "Protocol-faithful ACP JSON-RPC over streamable HTTP client.",
   "license": "Apache-2.0",
   "repository": {

sdks/cli-shared/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sandbox-agent/cli-shared",
-  "version": "0.4.1",
+  "version": "0.4.2",
   "description": "Shared helpers for sandbox-agent CLI and SDK",
   "license": "Apache-2.0",
   "repository": {

sdks/cli/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sandbox-agent/cli",
-  "version": "0.4.1",
+  "version": "0.4.2",
   "description": "CLI for sandbox-agent - run AI coding agents in sandboxes",
   "license": "Apache-2.0",
   "repository": {

sdks/cli/platforms/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sandbox-agent/cli-darwin-arm64",
-  "version": "0.4.1",
+  "version": "0.4.2",
   "description": "sandbox-agent CLI binary for macOS ARM64",
   "license": "Apache-2.0",
   "repository": {

sdks/cli/platforms/darwin-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sandbox-agent/cli-darwin-x64",
-  "version": "0.4.1",
+  "version": "0.4.2",
   "description": "sandbox-agent CLI binary for macOS x64",
   "license": "Apache-2.0",
   "repository": {

sdks/cli/platforms/linux-arm64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sandbox-agent/cli-linux-arm64",
-  "version": "0.4.1",
+  "version": "0.4.2",
   "description": "sandbox-agent CLI binary for Linux arm64",
   "license": "Apache-2.0",
   "repository": {

sdks/cli/platforms/linux-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sandbox-agent/cli-linux-x64",
-  "version": "0.4.1",
+  "version": "0.4.2",
   "description": "sandbox-agent CLI binary for Linux x64",
   "license": "Apache-2.0",
   "repository": {

sdks/cli/platforms/win32-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sandbox-agent/cli-win32-x64",
-  "version": "0.4.1",
+  "version": "0.4.2",
   "description": "sandbox-agent CLI binary for Windows x64",
   "license": "Apache-2.0",
   "repository": {

sdks/gigacode/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sandbox-agent/gigacode",
-  "version": "0.4.1",
+  "version": "0.4.2",
   "description": "Gigacode CLI (sandbox-agent with OpenCode attach by default)",
   "license": "Apache-2.0",
   "repository": {

sdks/gigacode/platforms/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sandbox-agent/gigacode-darwin-arm64",
-  "version": "0.4.1",
+  "version": "0.4.2",
   "description": "gigacode CLI binary for macOS arm64",
   "license": "Apache-2.0",
   "repository": {

sdks/gigacode/platforms/darwin-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sandbox-agent/gigacode-darwin-x64",
-  "version": "0.4.1",
+  "version": "0.4.2",
   "description": "gigacode CLI binary for macOS x64",
   "license": "Apache-2.0",
   "repository": {

sdks/gigacode/platforms/linux-arm64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sandbox-agent/gigacode-linux-arm64",
-  "version": "0.4.1",
+  "version": "0.4.2",
   "description": "gigacode CLI binary for Linux arm64",
   "license": "Apache-2.0",
   "repository": {

sdks/gigacode/platforms/linux-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sandbox-agent/gigacode-linux-x64",
-  "version": "0.4.1",
+  "version": "0.4.2",
   "description": "gigacode CLI binary for Linux x64",
   "license": "Apache-2.0",
   "repository": {

sdks/gigacode/platforms/win32-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sandbox-agent/gigacode-win32-x64",
-  "version": "0.4.1",
+  "version": "0.4.2",
   "description": "gigacode CLI binary for Windows x64",
   "license": "Apache-2.0",
   "repository": {

sdks/persist-indexeddb/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sandbox-agent/persist-indexeddb",
-  "version": "0.4.1",
+  "version": "0.4.2",
   "description": "IndexedDB persistence driver for the Sandbox Agent TypeScript SDK (DEPRECATED)",
   "license": "Apache-2.0",
   "repository": {

sdks/persist-postgres/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sandbox-agent/persist-postgres",
-  "version": "0.4.1",
+  "version": "0.4.2",
   "description": "PostgreSQL persistence driver for the Sandbox Agent TypeScript SDK (DEPRECATED)",
   "license": "Apache-2.0",
   "repository": {

sdks/persist-rivet/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sandbox-agent/persist-rivet",
-  "version": "0.4.1",
+  "version": "0.4.2",
   "description": "Rivet Actor persistence driver for the Sandbox Agent TypeScript SDK (DEPRECATED)",
   "license": "Apache-2.0",
   "repository": {

sdks/persist-sqlite/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sandbox-agent/persist-sqlite",
-  "version": "0.4.1",
+  "version": "0.4.2",
   "description": "SQLite persistence driver for the Sandbox Agent TypeScript SDK (DEPRECATED)",
   "license": "Apache-2.0",
   "repository": {

sdks/react/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sandbox-agent/react",
-  "version": "0.4.1",
+  "version": "0.4.2",
   "description": "React components for Sandbox Agent frontend integrations",
   "license": "Apache-2.0",
   "repository": {

sdks/typescript/package.json

@@ -1,6 +1,6 @@
 {
   "name": "sandbox-agent",
-  "version": "0.4.1",
+  "version": "0.4.2",
   "description": "Universal API for automatic coding agents in sandboxes. Supports Claude Code, Codex, OpenCode, and Amp.",
   "license": "Apache-2.0",
   "repository": {

server/packages/agent-management/src/agents.rs

@@ -1093,9 +1093,9 @@ fn write_mock_agent_process_launcher(path: &Path) -> Result<(), AgentError> {
         fs::create_dir_all(parent)?;
     }
     let script = if cfg!(windows) {
-        "@echo off\r\nsandbox-agent mock-agent-process %*\r\n"
+        "@echo off\r\nif not \"%SANDBOX_AGENT_BIN%\"==\"\" (\r\n  \"%SANDBOX_AGENT_BIN%\" mock-agent-process %*\r\n  exit /b %errorlevel%\r\n)\r\nsandbox-agent mock-agent-process %*\r\n"
     } else {
-        "#!/usr/bin/env sh\nexec sandbox-agent mock-agent-process \"$@\"\n"
+        "#!/usr/bin/env sh\nif [ -n \"${SANDBOX_AGENT_BIN:-}\" ]; then\n  exec \"$SANDBOX_AGENT_BIN\" mock-agent-process \"$@\"\nfi\nexec sandbox-agent mock-agent-process \"$@\"\n"
     };
     write_text_file(path, script)
 }
@@ -1969,6 +1969,34 @@ exit 0
         assert_eq!(result.artifacts[0].source, InstallSource::Builtin);
     }
 
+    #[test]
+    fn mock_launcher_prefers_sandbox_agent_bin() {
+        let temp_dir = tempfile::tempdir().expect("create tempdir");
+        let manager = AgentManager::with_platform(temp_dir.path(), Platform::LinuxX64);
+
+        manager
+            .install(
+                AgentId::Mock,
+                InstallOptions {
+                    reinstall: true,
+                    version: None,
+                    agent_process_version: None,
+                },
+            )
+            .expect("mock install");
+
+        let launcher = manager.agent_process_path(AgentId::Mock);
+        let mut file = fs::File::open(&launcher).expect("open mock launcher");
+        let mut contents = String::new();
+        file.read_to_string(&mut contents)
+            .expect("read mock launcher");
+
+        assert!(
+            contents.contains("SANDBOX_AGENT_BIN"),
+            "mock launcher should reference SANDBOX_AGENT_BIN"
+        );
+    }
+
     #[test]
     fn install_pi_skips_native_and_installs_fallback_npm_launcher() {
         let _env_lock = env_lock().lock().expect("env lock");

server/packages/sandbox-agent/src/acp_proxy_runtime.rs

@@ -298,7 +298,7 @@ impl AcpProxyRuntime {
 
         let resolve_started = std::time::Instant::now();
         let manager = self.inner.agent_manager.clone();
-        let launch = tokio::task::spawn_blocking(move || manager.resolve_agent_process(agent))
+        let mut launch = tokio::task::spawn_blocking(move || manager.resolve_agent_process(agent))
             .await
             .map_err(|err| SandboxError::StreamError {
                 message: format!("failed to resolve agent process launch spec: {err}"),
@@ -307,6 +307,16 @@ impl AcpProxyRuntime {
                 message: err.to_string(),
             })?;
 
+        if agent == AgentId::Mock {
+            if let Ok(exe) = std::env::current_exe() {
+                let path = exe.to_string_lossy().to_string();
+                launch
+                    .env
+                    .entry("SANDBOX_AGENT_BIN".to_string())
+                    .or_insert(path);
+            }
+        }
+
         tracing::info!(
             server_id = server_id,
             agent = agent.as_str(),