List Task Agent Revisions

GET

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

GET

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

$ curl https://app.rightbrain.ai/api/v1/org/org_id/project/project_id/task-agent/task_agent_id/revision \
>      -H "Authorization: Bearer <token>"

1 [
2   {
3     "id": "019df849-e12a-b57e-62d4-0e5875e91ef4",
4     "task_agent_id": "019df849-e106-3301-5894-291b4c9c6cab",
5     "description": "Triages inbound client support emails, looks up the client's account, and drafts a reply.",
6     "instruction": "You triage inbound client support emails for Fenwick & Co Bookkeeping. For every message: (1) run the Customer Support Analyzer to classify the sender's sentiment and issue category, (2) look up the client's account in the Customer Database sheet using their email address to confirm their plan, billing status, and any existing notes before you say anything about their account, (3) draft a reply that directly answers what they asked, references specific figures from the account lookup rather than the analyzer's summary, and matches a warm but professional tone, and (4) once a team member confirms the reply, log a one-line resolution note back to the Tickets sheet so the team can see the case was handled. Never promise a refund or credit yourself — say that a member of the team will confirm and action it within one business day. If the account lookup returns no match for the sender's email, say so plainly in the draft and ask the client to confirm the email address on file rather than guessing.",
7     "mode": "agentic",
8     "llm_model_id": "ec217e75-72ea-4281-a1b8-cb7bd0ef9f41",
9     "fallback_llm_model_id": "af2a9bbf-5f36-4b12-bd3f-92c57be96dec",
10     "created": "2026-06-12T09:30:00Z",
11     "llm_model": {
12       "provider": "OpenAI",
13       "vendor": "openai",
14       "name": "gpt-4-turbo",
15       "alias": "GPT-4 Turbo",
16       "description": "Latest GPT-4 Turbo model with vision capabilities. 128K context window with training cut off of Dec 2023.",
17       "supports_vision": true,
18       "max_context_window": 128000,
19       "id": "ec217e75-72ea-4281-a1b8-cb7bd0ef9f41",
20       "supports_image_output": false,
21       "supports_pdf_vision": false,
22       "supports_tool_calling": true,
23       "supports_context_caching": false,
24       "price": "average",
25       "speed": "fast",
26       "knowledge_cutoff": "2023-12-01",
27       "created": "2024-01-16T13:33:25.247662Z",
28       "modified": "2024-01-16T13:33:25.247662Z",
29       "llm_model_comments": []
30     },
31     "fallback_llm_model": {
32       "provider": "OpenAI",
33       "vendor": "openai",
34       "name": "gpt-3.5-turbo",
35       "alias": "GPT-3.5 Turbo",
36       "description": "Fast, efficient model suitable for simple tasks. 16K context window.",
37       "supports_vision": false,
38       "max_context_window": 16385,
39       "id": "af2a9bbf-5f36-4b12-bd3f-92c57be96dec",
40       "supports_image_output": false,
41       "supports_pdf_vision": false,
42       "supports_tool_calling": true,
43       "supports_context_caching": false,
44       "price": "cheap",
45       "speed": "standard",
46       "knowledge_cutoff": "2021-09-01",
47       "created": "2024-01-16T13:33:25.247662Z",
48       "modified": "2024-01-16T13:33:25.247662Z",
49       "llm_model_comments": []
50     },
51     "task_tools": [
52       {
53         "id": "019df7a2-44a0-7ee9-8876-25aa7a902f38",
54         "task_id": "019df7a2-44a0-7f6b-8a18-d81df57049d0",
55         "task_name": "Customer Support Analyzer",
56         "order": 0,
57         "enabled": true,
58         "task_revision_id": "019df7a2-44a0-75d6-b036-4e86f6d45302",
59         "revision_strategy": "pinned",
60         "is_output_formatter": false,
61         "action_mode": "auto_run",
62         "rejection_behavior": "end_run"
63       },
64       {
65         "id": "019ebb2a-b9c0-7d29-a460-f6aa6fd9edbb",
66         "task_id": "019df7a2-44a0-7186-92a6-a8e45e78537b",
67         "task_name": "Draft Support Reply",
68         "order": 1,
69         "enabled": true,
70         "task_revision_id": "019df7a2-44a0-78c4-ba7b-6ae382a6253a",
71         "revision_strategy": "pinned",
72         "is_output_formatter": true,
73         "action_mode": "auto_run",
74         "rejection_behavior": "end_run"
75       }
76     ],
77     "integrations": [
78       {
79         "id": "019ebb2a-b9c0-7af9-b42d-e9cd2819667d",
80         "project_integration_id": "019df7a2-44a0-7a75-ae4f-4c8edcdac22e",
81         "integration_type": "google_sheets",
82         "integration_name": "Customer Database",
83         "order": 0,
84         "enabled": true,
85         "provision_source": "manual",
86         "tool_count": 2,
87         "allowed_tool_ids": [
88           "019df7a2-44a0-7b09-afd0-c59cbc20126d",
89           "019df7a2-44a0-7923-9ea9-87be4ba93be9"
90         ],
91         "default_action_mode": "auto_run",
92         "default_rejection_behavior": "end_run",
93         "tool_action_modes": {
94           "019df7a2-44a0-7923-9ea9-87be4ba93be9": "require_approval"
95         },
96         "tool_rejection_behaviors": {}
97       }
98     ],
99     "skills": [],
100     "mcp_servers": [],
101     "registered_tools": [],
102     "tags": [],
103     "max_turns": 50,
104     "active": true,
105     "modified": "2026-06-12T09:30:00Z"
106   },
107   {
108     "id": "019df7a2-44a0-7d66-b496-52c6c197bca1",
109     "task_agent_id": "019df849-e106-3301-5894-291b4c9c6cab",
110     "description": "Triages inbound client support emails and drafts a reply.",
111     "instruction": "You triage inbound client support emails for Fenwick & Co Bookkeeping. For every message, run the Customer Support Analyzer to classify the sender's sentiment and issue category, then draft a reply that directly answers what they asked in a warm but professional tone. Never promise a refund or credit yourself — say that a member of the team will confirm and action it within one business day.",
112     "mode": "agentic",
113     "llm_model_id": "ec217e75-72ea-4281-a1b8-cb7bd0ef9f41",
114     "fallback_llm_model_id": "af2a9bbf-5f36-4b12-bd3f-92c57be96dec",
115     "created": "2026-05-05T10:15:00Z",
116     "llm_model": {
117       "provider": "OpenAI",
118       "vendor": "openai",
119       "name": "gpt-4-turbo",
120       "alias": "GPT-4 Turbo",
121       "description": "Latest GPT-4 Turbo model with vision capabilities. 128K context window with training cut off of Dec 2023.",
122       "supports_vision": true,
123       "max_context_window": 128000,
124       "id": "ec217e75-72ea-4281-a1b8-cb7bd0ef9f41",
125       "supports_image_output": false,
126       "supports_pdf_vision": false,
127       "supports_tool_calling": true,
128       "supports_context_caching": false,
129       "price": "average",
130       "speed": "fast",
131       "knowledge_cutoff": "2023-12-01",
132       "created": "2024-01-16T13:33:25.247662Z",
133       "modified": "2024-01-16T13:33:25.247662Z",
134       "llm_model_comments": []
135     },
136     "fallback_llm_model": {
137       "provider": "OpenAI",
138       "vendor": "openai",
139       "name": "gpt-3.5-turbo",
140       "alias": "GPT-3.5 Turbo",
141       "description": "Fast, efficient model suitable for simple tasks. 16K context window.",
142       "supports_vision": false,
143       "max_context_window": 16385,
144       "id": "af2a9bbf-5f36-4b12-bd3f-92c57be96dec",
145       "supports_image_output": false,
146       "supports_pdf_vision": false,
147       "supports_tool_calling": true,
148       "supports_context_caching": false,
149       "price": "cheap",
150       "speed": "standard",
151       "knowledge_cutoff": "2021-09-01",
152       "created": "2024-01-16T13:33:25.247662Z",
153       "modified": "2024-01-16T13:33:25.247662Z",
154       "llm_model_comments": []
155     },
156     "task_tools": [
157       {
158         "id": "019df7a2-44a0-7ee9-8876-25aa7a902f38",
159         "task_id": "019df7a2-44a0-7f6b-8a18-d81df57049d0",
160         "task_name": "Customer Support Analyzer",
161         "order": 0,
162         "enabled": true,
163         "task_revision_id": "019df7a2-44a0-75d6-b036-4e86f6d45302",
164         "revision_strategy": "pinned",
165         "is_output_formatter": false,
166         "action_mode": "auto_run",
167         "rejection_behavior": "end_run"
168       },
169       {
170         "id": "019ebb2a-b9c0-7d29-a460-f6aa6fd9edbb",
171         "task_id": "019df7a2-44a0-7186-92a6-a8e45e78537b",
172         "task_name": "Draft Support Reply",
173         "order": 1,
174         "enabled": true,
175         "task_revision_id": "019df7a2-44a0-78c4-ba7b-6ae382a6253a",
176         "revision_strategy": "pinned",
177         "is_output_formatter": true,
178         "action_mode": "auto_run",
179         "rejection_behavior": "end_run"
180       }
181     ],
182     "integrations": [],
183     "skills": [],
184     "mcp_servers": [],
185     "registered_tools": [],
186     "tags": [],
187     "max_turns": 50,
188     "active": false,
189     "modified": "2026-05-05T10:15:00Z"
190   }
191 ]

List immutable executable revisions for a Task Agent.

Each revision contains the runtime configuration and pinned attachments that can be executed by new runs, long-lived sessions, or pinned triggers. The active revision is marked with active. Revisions are returned newest first.

Authentication

AuthorizationBearer

API key or access token, sent as Authorization: Bearer <token>. The simplest option: create an API key in your dashboard under Settings, then paste it here.

AuthorizationBearer

API key or access token, sent as Authorization: Bearer <token>. The simplest option: create an API key in your dashboard under Settings, then paste it here.

Path parameters

org_idstringRequiredformat: "uuid"

The organization ID

project_idstringRequiredformat: "uuid"

The project ID

task_agent_idstringRequiredformat: "uuid"

The task agent ID

Response

Task Agent revisions

idstringformat: "uuid"

task_agent_idstringformat: "uuid"

descriptionstring or null

instructionstring

modeenum

Execution mode for TaskAgent.

llm_model_idstring or nullformat: "uuid"

fallback_llm_model_idstring or nullformat: "uuid"

createdstring

llm_modelobject or nullOptional

fallback_llm_modelobject or nullOptional

task_toolslist of objectsOptional

integrationslist of objectsOptional

skillslist of objectsOptional

mcp_serverslist of objectsOptional

registered_toolslist of objectsOptional

tagslist of objectsOptional

memory_strategystring or nullOptional

memory_configmap from strings to any or nullOptional

max_turnsinteger or nullOptional

activebooleanOptionalDefaults to false

modifiedstring or nullOptional

Errors

400

Bad Request Error

401

Unauthorized Error

403

Forbidden Error

404

Not Found Error

422

Unprocessable Entity Error

500

Internal Server Error