Struct ThreadResumeParams 

pub struct ThreadResumeParams {

    pub approval_policy: Option<AskForApproval>,
    pub approvals_reviewer: Option<ApprovalsReviewer>,
    pub base_instructions: Option<String>,
    pub config: Option<Map<String, Value>>,
    pub cwd: Option<String>,
    pub developer_instructions: Option<String>,
    pub exclude_turns: Option<bool>,
    pub history: Option<Vec<ResponseItem>>,
    pub initial_turns_page: Option<ThreadResumeInitialTurnsPageParams>,
    pub model: Option<String>,
    pub model_provider: Option<String>,
    pub path: Option<String>,
    pub permissions: Option<String>,
    pub personality: Option<Personality>,
    pub runtime_workspace_roots: Option<Vec<AbsolutePathBuf>>,
    pub sandbox: Option<SandboxMode>,
    pub service_tier: Option<String>,
    pub thread_id: String,
}

There are three ways to resume a thread: 1. By thread_id: load the thread from disk by thread_id and resume it. 2. By history: instantiate the thread from memory and resume it. 3. By path: load the thread from disk by path and resume it.

For non-running threads, the precedence is: history > non-empty path > thread_id. If using history or a non-empty path for a non-running thread, the thread_id param will be ignored.

If thread_id identifies a running thread, app-server rejoins that thread and treats a non-empty path as a consistency check against the active rollout path. Empty string path values are treated as absent.

Prefer using thread_id whenever possible.

JSON schema

{
 "title": "ThreadResumeParams",
 "description": "There are three ways to resume a thread: 1. By thread_id: load the thread from disk by thread_id and resume it. 2. By history: instantiate the thread from memory and resume it. 3. By path: load the thread from disk by path and resume it.\n\nFor non-running threads, the precedence is: history > non-empty path > thread_id. If using history or a non-empty path for a non-running thread, the thread_id param will be ignored.\n\nIf thread_id identifies a running thread, app-server rejoins that thread and treats a non-empty path as a consistency check against the active rollout path. Empty string path values are treated as absent.\n\nPrefer using thread_id whenever possible.",
 "type": "object",
 "required": [
   "threadId"
 ],
 "properties": {
   "approvalPolicy": {
     "anyOf": [
       {
         "$ref": "#/definitions/AskForApproval"
       },
       {
         "type": "null"
       }
     ]
   },
   "approvalsReviewer": {
     "description": "Override where approval requests are routed for review on this thread and subsequent turns.",
     "anyOf": [
       {
         "$ref": "#/definitions/ApprovalsReviewer"
       },
       {
         "type": "null"
       }
     ]
   },
   "baseInstructions": {
     "type": [
       "string",
       "null"
     ]
   },
   "config": {
     "type": [
       "object",
       "null"
     ],
     "additionalProperties": true
   },
   "cwd": {
     "type": [
       "string",
       "null"
     ]
   },
   "developerInstructions": {
     "type": [
       "string",
       "null"
     ]
   },
   "excludeTurns": {
     "description": "When true, return only thread metadata and live-resume state without populating `thread.turns`. This is useful when the client plans to call `thread/turns/list` immediately after resuming.",
     "type": "boolean"
   },
   "history": {
     "description": "[UNSTABLE] FOR CODEX CLOUD - DO NOT USE. If specified, the thread will be resumed with the provided history instead of loaded from disk.",
     "type": [
       "array",
       "null"
     ],
     "items": {
       "$ref": "#/definitions/ResponseItem"
     }
   },
   "initialTurnsPage": {
     "description": "When present, include a `thread/turns/list` page in the resume response so clients can bootstrap recent turns without a second request.",
     "anyOf": [
       {
         "$ref": "#/definitions/ThreadResumeInitialTurnsPageParams"
       },
       {
         "type": "null"
       }
     ]
   },
   "model": {
     "description": "Configuration overrides for the resumed thread, if any.",
     "type": [
       "string",
       "null"
     ]
   },
   "modelProvider": {
     "type": [
       "string",
       "null"
     ]
   },
   "path": {
     "description": "[UNSTABLE] Specify the rollout path to resume from. If specified for a non-running thread, the thread_id param will be ignored. If thread_id identifies a running thread, the path must match the active rollout path.",
     "default": null,
     "type": [
       "string",
       "null"
     ]
   },
   "permissions": {
     "description": "Named profile id for the resumed thread. Cannot be combined with `sandbox`.",
     "type": [
       "string",
       "null"
     ]
   },
   "personality": {
     "anyOf": [
       {
         "$ref": "#/definitions/Personality"
       },
       {
         "type": "null"
       }
     ]
   },
   "runtimeWorkspaceRoots": {
     "description": "Replace the thread's runtime workspace roots. Paths must be absolute.",
     "type": [
       "array",
       "null"
     ],
     "items": {
       "$ref": "#/definitions/AbsolutePathBuf"
     }
   },
   "sandbox": {
     "anyOf": [
       {
         "$ref": "#/definitions/SandboxMode"
       },
       {
         "type": "null"
       }
     ]
   },
   "serviceTier": {
     "type": [
       "string",
       "null"
     ]
   },
   "threadId": {
     "type": "string"
   }
 },
 "$schema": "http://json-schema.org/draft-07/schema#"
}

Fields

approval_policy: Option<AskForApproval>

approvals_reviewer: Option<ApprovalsReviewer>

Override where approval requests are routed for review on this thread and subsequent turns.

base_instructions: Option<String>

config: Option<Map<String, Value>>

cwd: Option<String>

developer_instructions: Option<String>

exclude_turns: Option<bool>

When true, return only thread metadata and live-resume state without populating thread.turns. This is useful when the client plans to call thread/turns/list immediately after resuming.

history: Option<Vec<ResponseItem>>

[UNSTABLE] FOR CODEX CLOUD - DO NOT USE. If specified, the thread will be resumed with the provided history instead of loaded from disk.

initial_turns_page: Option<ThreadResumeInitialTurnsPageParams>

When present, include a thread/turns/list page in the resume response so clients can bootstrap recent turns without a second request.

model: Option<String>

Configuration overrides for the resumed thread, if any.

model_provider: Option<String>

path: Option<String>

[UNSTABLE] Specify the rollout path to resume from. If specified for a non-running thread, the thread_id param will be ignored. If thread_id identifies a running thread, the path must match the active rollout path.

permissions: Option<String>

Named profile id for the resumed thread. Cannot be combined with sandbox.

personality: Option<Personality>

runtime_workspace_roots: Option<Vec<AbsolutePathBuf>>

Replace the thread’s runtime workspace roots. Paths must be absolute.

sandbox: Option<SandboxMode>

service_tier: Option<String>

thread_id: String

Trait Implementations

impl Clone for ThreadResumeParams

fn clone(&self) -> ThreadResumeParams

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for ThreadResumeParams

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for ThreadResumeParams

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for ThreadResumeParams

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.