@salesforce/plugin-agent 1.11.1 → 1.12.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -1,121 +0,0 @@
1
- # summary
2
-
3
- Generate an agent spec, which is a YAML file that captures what an agent can do.
4
-
5
- # description
6
-
7
- Before you use Salesforce CLI to create an agent in your org, you must first generate an agent spec with this command. An agent spec is a YAML-formatted file that contains information about the agent, such as its role and company description, and then an AI-generated list of topics based on this information. Topics define the range of jobs your agent can handle.
8
-
9
- Use flags, such as --role and --company-description, to provide details about your company and the role that the agent plays in your company. If you prefer, you can also be prompted for the information. Upon command execution, the large language model (LLM) associated with your org uses the information you provided to generate a list of topics for the agent. Because the LLM uses the company and role information to generate the topics, we recommend that you provide accurate and specific details so the LLM generates the best and most relevant topics. Once generated, you can edit the spec file; for example, you can remove topics that don't apply to your agent or change the description of a particular topic.
10
-
11
- You can iterate the spec generation process by using the --spec flag to pass an existing agent spec file to this command, and then using the --role, --company-description, etc, flags to refine your agent properties. Iteratively improving the description of your agent allows the LLM to generate progressively better topics.
12
-
13
- You can also specify a custom prompt template that the agent uses, and ground the prompt template to add context and personalization to the agent's prompts.
14
-
15
- When your agent spec is ready, you then create the agent in your org by running the "agent create" CLI command and specifying the spec with the --spec flag.
16
-
17
- # flags.type.summary
18
-
19
- Type of agent to create.
20
-
21
- # flags.role.summary
22
-
23
- Role of the agent.
24
-
25
- # flags.company-name.summary
26
-
27
- Name of your company.
28
-
29
- # flags.company-description.summary
30
-
31
- Description of your company.
32
-
33
- # flags.company-website.summary
34
-
35
- Website URL of your company.
36
-
37
- # flags.output-file.summary
38
-
39
- Path for the generated YAML agent spec file; can be an absolute or relative path.
40
-
41
- # flags.max-topics.summary
42
-
43
- Maximum number of topics to generate in the agent spec; default is 10.
44
-
45
- # flags.max-topics.prompt
46
-
47
- Max number of topics to generate (1-30)
48
-
49
- # flags.prompt-template.summary
50
-
51
- API name of a customized prompt template to use instead of the default prompt template.
52
-
53
- # flags.grounding-context.summary
54
-
55
- Context information and personalization that's added to your prompts when using a custom prompt template.
56
-
57
- # flags.spec.summary
58
-
59
- Agent spec file, in YAML format, to use as input to the command.
60
-
61
- # flags.full-interview.summary
62
-
63
- Prompt for both required and optional flags.
64
-
65
- # flags.agent-user.summary
66
-
67
- Username of a user in your org to assign to your agent; determines what your agent can access and do.
68
-
69
- # flags.agent-user.prompt
70
-
71
- Username for agent
72
-
73
- # flags.enrich-logs.summary
74
-
75
- Adds agent conversation data to event logs so you can view all agent session activity in one place.
76
-
77
- # flags.enrich-logs.prompt
78
-
79
- Enrich event logs
80
-
81
- # flags.tone.summary
82
-
83
- Conversational style of the agent, such as how it expresses your brand personality in its messages through word choice, punctuation, and sentence structure.
84
-
85
- # flags.tone.prompt
86
-
87
- Agent conversation tone
88
-
89
- # flags.primary-language.summary
90
-
91
- Language the agent uses in conversations.
92
-
93
- # flags.no-prompt.summary
94
-
95
- Don't prompt the user to confirm spec file overwrite.
96
-
97
- # examples
98
-
99
- - Generate an agent spec in the default location and use flags to specify the agent properties, such as its role and your company details; use your default org:
100
-
101
- <%= config.bin %> <%= command.id %> --type customer --role "Field customer complaints and manage employee schedules." --company-name "Coral Cloud Resorts" --company-description "Provide customers with exceptional destination activities, unforgettable experiences, and reservation services."
102
-
103
- - Generate an agent spec by being prompted for the required agent properties and generate a maxiumum of 5 topics; write the generated file to the "specs/resortManagerSpec.yaml" file and use the org with alias "my-org":
104
-
105
- <%= config.bin %> <%= command.id %> --max-topics 5 --output-file specs/resortManagerAgent.yaml --target-org my-org
106
-
107
- - Specify an existing agent spec file called "specs/resortManagerAgent.yaml", and then overwrite it with a new version that contains newly AI-generated topics based on the updated role information passed in with the --role flag:
108
-
109
- <%= config.bin %> <%= command.id %> --spec specs/resortManagerAgent.yaml --output-file specs/resortManagerAgent.yaml --role "Field customer complaints, manage employee schedules, and ensure all resort operations are running smoothly" --target-org my-org
110
-
111
- # error.missingRequiredFlags
112
-
113
- Missing required flags: %s
114
-
115
- # confirmSpecOverwrite
116
-
117
- Confirm overwrite of spec file %s?
118
-
119
- # commandCanceled
120
-
121
- Command canceled by user confirmation.
@@ -1,145 +0,0 @@
1
- {
2
- "$schema": "http://json-schema.org/draft-07/schema#",
3
- "$ref": "#/definitions/AgentCreateResult",
4
- "definitions": {
5
- "AgentCreateResult": {
6
- "type": "object",
7
- "additionalProperties": false,
8
- "properties": {
9
- "previewFilePath": {
10
- "type": "string"
11
- },
12
- "isSuccess": {
13
- "type": "boolean"
14
- },
15
- "errorMessage": {
16
- "type": "string"
17
- },
18
- "agentId": {
19
- "type": "object",
20
- "properties": {
21
- "botId": {
22
- "type": "string"
23
- },
24
- "botVersionId": {
25
- "type": "string"
26
- },
27
- "plannerId": {
28
- "type": "string"
29
- }
30
- },
31
- "required": ["botId", "botVersionId", "plannerId"],
32
- "additionalProperties": false,
33
- "description": "If the agent was created with saveAgent=true, these are the IDs that make up an agent; Bot, BotVersion, and GenAiPlanner metadata."
34
- },
35
- "agentDefinition": {
36
- "type": "object",
37
- "properties": {
38
- "agentDescription": {
39
- "type": "string"
40
- },
41
- "topics": {
42
- "type": "array",
43
- "items": {
44
- "type": "object",
45
- "properties": {
46
- "scope": {
47
- "type": "string"
48
- },
49
- "topic": {
50
- "type": "string"
51
- },
52
- "actions": {
53
- "type": "array",
54
- "items": {
55
- "type": "object",
56
- "properties": {
57
- "actionName": {
58
- "type": "string"
59
- },
60
- "exampleOutput": {
61
- "type": "string"
62
- },
63
- "actionDescription": {
64
- "type": "string"
65
- },
66
- "inputs": {
67
- "type": "array",
68
- "items": {
69
- "type": "object",
70
- "properties": {
71
- "inputName": {
72
- "type": "string"
73
- },
74
- "inputDataType": {
75
- "type": "string"
76
- },
77
- "inputDescription": {
78
- "type": "string"
79
- }
80
- },
81
- "required": ["inputName", "inputDataType", "inputDescription"],
82
- "additionalProperties": false
83
- },
84
- "minItems": 1,
85
- "maxItems": 1
86
- },
87
- "outputs": {
88
- "type": "array",
89
- "items": {
90
- "type": "object",
91
- "properties": {
92
- "outputName": {
93
- "type": "string"
94
- },
95
- "outputDataType": {
96
- "type": "string"
97
- },
98
- "outputDescription": {
99
- "type": "string"
100
- }
101
- },
102
- "required": ["outputName", "outputDataType", "outputDescription"],
103
- "additionalProperties": false
104
- },
105
- "minItems": 1,
106
- "maxItems": 1
107
- }
108
- },
109
- "required": ["actionName", "exampleOutput", "actionDescription", "inputs", "outputs"],
110
- "additionalProperties": false
111
- },
112
- "minItems": 1,
113
- "maxItems": 1
114
- },
115
- "instructions": {
116
- "type": "array",
117
- "items": {
118
- "type": "string"
119
- }
120
- },
121
- "classificationDescription": {
122
- "type": "string"
123
- }
124
- },
125
- "required": ["scope", "topic", "actions", "instructions", "classificationDescription"],
126
- "additionalProperties": false
127
- },
128
- "minItems": 1,
129
- "maxItems": 1
130
- },
131
- "sampleUtterances": {
132
- "type": "array",
133
- "items": {
134
- "type": "string"
135
- }
136
- }
137
- },
138
- "required": ["agentDescription", "topics", "sampleUtterances"],
139
- "additionalProperties": false
140
- }
141
- },
142
- "required": ["agentDefinition", "isSuccess"]
143
- }
144
- }
145
- }
@@ -1,85 +0,0 @@
1
- {
2
- "$schema": "http://json-schema.org/draft-07/schema#",
3
- "$ref": "#/definitions/AgentCreateSpecResult",
4
- "definitions": {
5
- "AgentCreateSpecResult": {
6
- "type": "object",
7
- "additionalProperties": false,
8
- "properties": {
9
- "topics": {
10
- "$ref": "#/definitions/DraftAgentTopics"
11
- },
12
- "agentType": {
13
- "type": "string",
14
- "enum": [
15
- "customer",
16
- "internal"
17
- ],
18
- "description": "Internal type is copilots; used by customers' employees. Customer type is agents; used by customers' customers."
19
- },
20
- "role": {
21
- "type": "string"
22
- },
23
- "companyName": {
24
- "type": "string"
25
- },
26
- "companyDescription": {
27
- "type": "string"
28
- },
29
- "companyWebsite": {
30
- "type": "string"
31
- },
32
- "maxNumOfTopics": {
33
- "type": "number",
34
- "description": "The maximum number of topics to create in the spec. Default is 10."
35
- },
36
- "promptTemplateName": {
37
- "type": "string",
38
- "description": "Developer name of the prompt template."
39
- },
40
- "groundingContext": {
41
- "type": "string",
42
- "description": "Context info to be used in customized prompt template"
43
- },
44
- "isSuccess": {
45
- "type": "boolean"
46
- },
47
- "errorMessage": {
48
- "type": "string"
49
- },
50
- "specPath": {
51
- "type": "string"
52
- }
53
- },
54
- "required": [
55
- "agentType",
56
- "companyDescription",
57
- "companyName",
58
- "isSuccess",
59
- "role",
60
- "topics"
61
- ]
62
- },
63
- "DraftAgentTopics": {
64
- "type": "array",
65
- "items": {
66
- "type": "object",
67
- "properties": {
68
- "name": {
69
- "type": "string"
70
- },
71
- "description": {
72
- "type": "string"
73
- }
74
- },
75
- "required": [
76
- "name",
77
- "description"
78
- ],
79
- "additionalProperties": false
80
- },
81
- "minItems": 1,
82
- "maxItems": 1
83
- }
84
- }
85
- }