Update Task Agent

POST

/org/:org_id/project/:project_id/task-agent/:task_agent_id

POST

/api/v1/org/:org_id/project/:project_id/task-agent/:task_agent_id

$ curl -X POST https://app.rightbrain.ai/api/v1/org/org_id/project/project_id/task-agent/task_agent_id \
>      -H "Authorization: Bearer <token>" \
>      -H "Content-Type: application/json" \
>      -d '{}'

1 {
2   "id": "string",
3   "name": "string",
4   "task_agent_run_visibility": "owner_only",
5   "is_deleted": true,
6   "created": "string",
7   "modified": "string",
8   "active_revision": {
9     "id": "string",
10     "task_agent_id": "string",
11     "created": "string",
12     "modified": "string"
13   },
14   "revisions": [
15     {
16       "id": "string",
17       "task_agent_id": "string",
18       "description": "string",
19       "instruction": "string",
20       "mode": "agentic",
21       "llm_model_id": "string",
22       "fallback_llm_model_id": "string",
23       "created": "string",
24       "llm_model": {
25         "provider": "OpenAI",
26         "vendor": "openai",
27         "name": "gpt-4-turbo-preview",
28         "alias": "GPT-4 Turbo",
29         "description": "Latest GPT-4 model with 128k context window and knowledge cutoff of December 2023.",
30         "supports_vision": true,
31         "max_context_window": 128000,
32         "id": "string",
33         "supports_image_output": false,
34         "supports_pdf_vision": false,
35         "supports_tool_calling": false,
36         "pdf_vision_config": {
37           "max_file_size_mb": 50,
38           "max_pages": 1,
39           "max_visual_pages": 1
40         },
41         "model_params": {},
42         "created": "string",
43         "modified": "string",
44         "replaced_by": "string",
45         "retired": "string",
46         "llm_model_comments": [
47           {
48             "title": "Performance Issue",
49             "description": "Model exhibits inconsistent response quality with complex reasoning tasks.",
50             "id": "string",
51             "llm_model_id": "string",
52             "active": true,
53             "created": "string",
54             "modified": "string"
55           }
56         ]
57       },
58       "fallback_llm_model": {
59         "provider": "OpenAI",
60         "vendor": "openai",
61         "name": "gpt-4-turbo-preview",
62         "alias": "GPT-4 Turbo",
63         "description": "Latest GPT-4 model with 128k context window and knowledge cutoff of December 2023.",
64         "supports_vision": true,
65         "max_context_window": 128000,
66         "id": "string",
67         "supports_image_output": false,
68         "supports_pdf_vision": false,
69         "supports_tool_calling": false,
70         "pdf_vision_config": {
71           "max_file_size_mb": 50,
72           "max_pages": 1,
73           "max_visual_pages": 1
74         },
75         "model_params": {},
76         "created": "string",
77         "modified": "string",
78         "replaced_by": "string",
79         "retired": "string",
80         "llm_model_comments": [
81           {
82             "title": "Performance Issue",
83             "description": "Model exhibits inconsistent response quality with complex reasoning tasks.",
84             "id": "string",
85             "llm_model_id": "string",
86             "active": true,
87             "created": "string",
88             "modified": "string"
89           }
90         ]
91       },
92       "task_tools": [
93         {
94           "id": "string",
95           "task_id": "string",
96           "task_name": "Summarize",
97           "order": 0,
98           "enabled": true,
99           "task_revision_id": "string",
100           "is_output_formatter": false
101         }
102       ],
103       "integrations": [
104         {
105           "id": "string",
106           "project_integration_id": "string",
107           "integration_type": "google_sheets",
108           "integration_name": "string",
109           "order": 1,
110           "enabled": true,
111           "provision_source": "manual",
112           "tool_count": 1,
113           "allowed_tool_ids": [
114             "string"
115           ],
116           "source_skill_id": "string",
117           "source_skill_revision_id": "string",
118           "source_capability_id": "string"
119         }
120       ],
121       "skills": [
122         {
123           "id": "string",
124           "skill_id": "string",
125           "skill_slug": "string",
126           "skill_display_name": "string",
127           "order": 1,
128           "enabled": true,
129           "skill_revision_id": "string"
130         }
131       ],
132       "mcp_servers": [
133         {
134           "id": "string",
135           "task_mcp_server_id": "string",
136           "task_mcp_server_name": "string",
137           "order": 1,
138           "enabled": true,
139           "provision_source": "manual",
140           "tool_count": 1,
141           "allowed_tool_ids": [
142             "string"
143           ],
144           "source_skill_id": "string",
145           "source_skill_revision_id": "string",
146           "source_capability_id": "string"
147         }
148       ],
149       "registered_tools": [
150         {
151           "id": "string",
152           "registered_tool_key": "string",
153           "registered_tool_version": "string",
154           "order": 1,
155           "enabled": true,
156           "provision_source": "manual",
157           "name": "string",
158           "tool_names": [
159             "string"
160           ],
161           "description": "string",
162           "source_skill_id": "string",
163           "source_skill_revision_id": "string",
164           "source_capability_id": "string"
165         }
166       ],
167       "tags": [
168         {
169           "name": "production",
170           "entity_type": "task",
171           "id": "string",
172           "created_at": "string",
173           "is_project_tag": true,
174           "is_global_tag": true,
175           "parent_id": "01909843-3596-da54-4756-28af46917e74",
176           "project_id": "string",
177           "children": [
178             null
179           ],
180           "tagged_entities": [
181             "string"
182           ]
183         }
184       ],
185       "memory_strategy": "string",
186       "memory_config": {},
187       "max_turns": 1,
188       "active": false,
189       "modified": "string"
190     }
191   ]
192 }

Update Task Agent metadata, create a new revision, or activate an existing revision.

Modifiable fields:

Root metadata: name and run visibility
Revision configuration: description, instruction, LLM models, execution mode, memory settings, task tools, MCP servers, integrations, and skills
Activation: active_revision_id

Updating revision configuration creates a new inactive revision. Activate it with a separate request that only includes active_revision_id.

To update task tools, pass a task_tools array. This performs a full replacement:

Omit the field to leave task tools unchanged
Pass an empty array to remove all task tools
Pass a new array to replace all task tools (array order = execution order)

Update Task Agent metadata, create a new revision, or activate an existing revision. Modifiable fields: - Root metadata: name and run visibility - Revision configuration: description, instruction, LLM models, execution mode, memory settings, task tools, MCP servers, integrations, and skills - Activation: `active_revision_id` Updating revision configuration creates a new inactive revision. Activate it with a separate request that only includes `active_revision_id`. To update task tools, pass a `task_tools` array. This performs a full replacement: - Omit the field to leave task tools unchanged - Pass an empty array to remove all task tools - Pass a new array to replace all task tools (array order = execution order)

Authentication

AuthorizationBearer

Bearer token authentication using JWT tokens from Ory Kratos/Hydra

Path parameters

org_idstringRequiredformat: "uuid"

The organization ID

project_idstringRequiredformat: "uuid"

The project ID

task_agent_idstringRequiredformat: "uuid"

The task agent ID

Request

This endpoint expects an object.

namestring or nullOptional<=255 characters

descriptionstring or nullOptional

instructionstring or nullOptional

modeenum or nullOptional

Execution mode for TaskAgent.

llm_model_idstring or nullOptionalformat: "uuid"

fallback_llm_model_idstring or nullOptionalformat: "uuid"

task_toolslist of objects or nullOptional

Full replacement of task tools. Omit field to leave task tools unchanged. Pass empty list to remove all task tools.

mcp_serverslist of objects or nullOptional

Full replacement of MCP servers. Omit field to leave unchanged. Pass empty list to remove all.

integrationslist of objects or nullOptional

Full replacement of integrations. Omit field to leave unchanged. Pass empty list to remove all.

skillslist of objects or nullOptional

Full replacement of declarative skills. Omit field to leave unchanged. Pass empty list to remove all.

memory_strategyenum or nullOptional

memory_configmap from strings to any or nullOptional

max_turnsinteger or nullOptional1-500

task_agent_run_visibilityenum or nullOptional

Controls who can see all TaskAgent runs for this agent.

active_revision_idstring or nullOptionalformat: "uuid"

Existing TaskAgent revision to activate. Omit to leave the active revision unchanged.

Response

Task Agent updated

idstringformat: "uuid"

namestring

task_agent_run_visibilityenum

is_deletedboolean

createdstring

modifiedstring

active_revisionobject or null

Summary of the active TaskAgent revision.

revisionslist of objects

Errors

400

Bad Request Error

401

Unauthorized Error

403

Forbidden Error

404

Not Found Error

422

Unprocessable Entity Error

500

Internal Server Error