feat: fork conversation/thread

codex-rs/app-server-protocol/src/protocol/common.rs

@@ -109,6 +109,10 @@ client_request_definitions! {
         params: v2::ThreadResumeParams,
         response: v2::ThreadResumeResponse,
     },
+    ThreadFork => "thread/fork" {
+        params: v2::ThreadForkParams,
+        response: v2::ThreadForkResponse,
+    },
     ThreadArchive => "thread/archive" {
         params: v2::ThreadArchiveParams,
         response: v2::ThreadArchiveResponse,
@@ -221,6 +225,11 @@ client_request_definitions! {
         params: v1::ResumeConversationParams,
         response: v1::ResumeConversationResponse,
     },
+    /// Fork a recorded Codex conversation into a new session.
+    ForkConversation {
+        params: v1::ForkConversationParams,
+        response: v1::ForkConversationResponse,
+    },
     ArchiveConversation {
         params: v1::ArchiveConversationParams,
         response: v1::ArchiveConversationResponse,

codex-rs/app-server-protocol/src/protocol/v1.rs

@@ -83,6 +83,15 @@ pub struct ResumeConversationResponse {
     pub rollout_path: PathBuf,
 }
 
+#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct ForkConversationResponse {
+    pub conversation_id: ThreadId,
+    pub model: String,
+    pub initial_messages: Option<Vec<EventMsg>>,
+    pub rollout_path: PathBuf,
+}
+
 #[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
 #[serde(untagged)]
 pub enum GetConversationSummaryParams {
@@ -148,6 +157,14 @@ pub struct ResumeConversationParams {
     pub overrides: Option<NewConversationParams>,
 }
 
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+pub struct ForkConversationParams {
+    pub path: Option<PathBuf>,
+    pub conversation_id: Option<ThreadId>,
+    pub overrides: Option<NewConversationParams>,
+}
+
 #[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
 #[serde(rename_all = "camelCase")]
 pub struct AddConversationSubscriptionResponse {

codex-rs/app-server-protocol/src/protocol/v2.rs

@@ -1064,6 +1064,47 @@ pub struct ThreadResumeResponse {
     pub reasoning_effort: Option<ReasoningEffort>,
 }
 
+#[derive(Serialize, Deserialize, Debug, Default, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+#[ts(export_to = "v2/")]
+/// There are two ways to fork a thread:
+/// 1. By thread_id: load the thread from disk by thread_id and fork it into a new thread.
+/// 2. By path: load the thread from disk by path and fork it into a new thread.
+///
+/// If using path, the thread_id param will be ignored.
+///
+/// Prefer using thread_id whenever possible.
+pub struct ThreadForkParams {
+    pub thread_id: String,
+
+    /// [UNSTABLE] Specify the rollout path to fork from.
+    /// If specified, the thread_id param will be ignored.
+    pub path: Option<PathBuf>,
+
+    /// Configuration overrides for the forked thread, if any.
+    pub model: Option<String>,
+    pub model_provider: Option<String>,
+    pub cwd: Option<String>,
+    pub approval_policy: Option<AskForApproval>,
+    pub sandbox: Option<SandboxMode>,
+    pub config: Option<HashMap<String, serde_json::Value>>,
+    pub base_instructions: Option<String>,
+    pub developer_instructions: Option<String>,
+}
+
+#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
+#[serde(rename_all = "camelCase")]
+#[ts(export_to = "v2/")]
+pub struct ThreadForkResponse {
+    pub thread: Thread,
+    pub model: String,
+    pub model_provider: String,
+    pub cwd: PathBuf,
+    pub approval_policy: AskForApproval,
+    pub sandbox: SandboxPolicy,
+    pub reasoning_effort: Option<ReasoningEffort>,
+}
+
 #[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
 #[serde(rename_all = "camelCase")]
 #[ts(export_to = "v2/")]
@@ -1238,7 +1279,7 @@ pub struct Thread {
     pub source: SessionSource,
     /// Optional Git metadata captured when the thread was created.
     pub git_info: Option<GitInfo>,
-    /// Only populated on `thread/resume` and `thread/rollback` responses.
+    /// Only populated on `thread/resume`, `thread/rollback`, `thread/fork` responses.
     /// For all other responses and notifications returning a Thread,
     /// the turns field will be an empty list.
     pub turns: Vec<Turn>,
@@ -1314,7 +1355,7 @@ impl From<CoreTokenUsage> for TokenUsageBreakdown {
 #[ts(export_to = "v2/")]
 pub struct Turn {
     pub id: String,
-    /// Only populated on a `thread/resume` response.
+    /// Only populated on a `thread/resume` or `thread/fork` response.
     /// For all other responses and notifications returning a Turn,
     /// the items field will be an empty list.
     pub items: Vec<ThreadItem>,

codex-rs/app-server/README.md

@@ -41,7 +41,7 @@ Use the thread APIs to create, list, or archive conversations. Drive a conversat
 ## Lifecycle Overview
 
 - Initialize once: Immediately after launching the codex app-server process, send an `initialize` request with your client metadata, then emit an `initialized` notification. Any other request before this handshake gets rejected.
-- Start (or resume) a thread: Call `thread/start` to open a fresh conversation. The response returns the thread object and you’ll also get a `thread/started` notification. If you’re continuing an existing conversation, call `thread/resume` with its ID instead.
+- Start (or resume) a thread: Call `thread/start` to open a fresh conversation. The response returns the thread object and you’ll also get a `thread/started` notification. If you’re continuing an existing conversation, call `thread/resume` with its ID instead. If you want to branch from an existing conversation, call `thread/fork` to create a new thread id with copied history.
 - Begin a turn: To send user input, call `turn/start` with the target `threadId` and the user's input. Optional fields let you override model, cwd, sandbox policy, etc. This immediately returns the new turn object and triggers a `turn/started` notification.
 - Stream events: After `turn/start`, keep reading JSON-RPC notifications on stdout. You’ll see `item/started`, `item/completed`, deltas like `item/agentMessage/delta`, tool progress, etc. These represent streaming model output plus any side effects (commands, tool calls, reasoning notes).
 - Finish the turn: When the model is done (or the turn is interrupted via making the `turn/interrupt` call), the server sends `turn/completed` with the final turn state and token usage.
@@ -72,6 +72,7 @@ Example (from OpenAI's official VSCode extension):
 
 - `thread/start` — create a new thread; emits `thread/started` and auto-subscribes you to turn/item events for that thread.
 - `thread/resume` — reopen an existing thread by id so subsequent `turn/start` calls append to it.
+- `thread/fork` — fork an existing thread into a new thread id by copying the stored history; emits `thread/started` and auto-subscribes you to turn/item events for the new thread.
 - `thread/list` — page through stored rollouts; supports cursor-based pagination and optional `modelProviders` filtering.
 - `thread/archive` — move a thread’s rollout file into the archived directory; returns `{}` on success.
 - `thread/rollback` — drop the last N turns from the agent’s in-memory context and persist a rollback marker in the rollout so future resumes see the pruned history; returns the updated `thread` (with `turns` populated) on success.
@@ -120,6 +121,14 @@ To continue a stored session, call `thread/resume` with the `thread.id` you prev
 { "id": 11, "result": { "thread": { "id": "thr_123", … } } }
 ```
 
+To branch from a stored session, call `thread/fork` with the `thread.id`. This creates a new thread id and emits a `thread/started` notification for it:
+
+```json
+{ "method": "thread/fork", "id": 12, "params": { "threadId": "thr_123" } }
+{ "id": 12, "result": { "thread": { "id": "thr_456", … } } }
+{ "method": "thread/started", "params": { "thread": { … } } }
+```
+
 ### Example: List threads (with pagination & filters)
 
 `thread/list` lets you render a history UI. Pass any combination of: