@kjerneverk/riotplan 1.0.7-dev.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.
- package/LICENSE +190 -0
- package/MCP-ELICITATION-NOTES.md +211 -0
- package/MCP-EXPLORE-IDEA-FIX.md +122 -0
- package/MCP-FIXES.md +50 -0
- package/MCP-PROMPT-FIXES.md +207 -0
- package/README.md +446 -0
- package/idea-plan-conceptual-model/.history/timeline.jsonl +1 -0
- package/idea-plan-conceptual-model/IDEA.md +39 -0
- package/idea-plan-conceptual-model/LIFECYCLE.md +21 -0
- package/package.json +96 -0
- package/package.json~ +85 -0
- package/scripts/build-mcp.js +88 -0
package/LICENSE
ADDED
|
@@ -0,0 +1,190 @@
|
|
|
1
|
+
Apache License
|
|
2
|
+
Version 2.0, January 2004
|
|
3
|
+
http://www.apache.org/licenses/
|
|
4
|
+
|
|
5
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
6
|
+
|
|
7
|
+
1. Definitions.
|
|
8
|
+
|
|
9
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
10
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
11
|
+
|
|
12
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
13
|
+
the copyright owner that is granting the License.
|
|
14
|
+
|
|
15
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
16
|
+
other entities that control, are controlled by, or are under common
|
|
17
|
+
control with that entity. For the purposes of this definition,
|
|
18
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
19
|
+
direction or management of such entity, whether by contract or
|
|
20
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
21
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
22
|
+
|
|
23
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
24
|
+
exercising permissions granted by this License.
|
|
25
|
+
|
|
26
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
27
|
+
including but not limited to software source code, documentation
|
|
28
|
+
source, and configuration files.
|
|
29
|
+
|
|
30
|
+
"Object" form shall mean any form resulting from mechanical
|
|
31
|
+
transformation or translation of a Source form, including but
|
|
32
|
+
not limited to compiled object code, generated documentation,
|
|
33
|
+
and conversions to other media types.
|
|
34
|
+
|
|
35
|
+
"Work" shall mean the work of authorship, whether in Source or
|
|
36
|
+
Object form, made available under the License, as indicated by a
|
|
37
|
+
copyright notice that is included in or attached to the work
|
|
38
|
+
(an example is provided in the Appendix below).
|
|
39
|
+
|
|
40
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
41
|
+
form, that is based on (or derived from) the Work and for which the
|
|
42
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
43
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
44
|
+
of this License, Derivative Works shall not include works that remain
|
|
45
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
46
|
+
the Work and Derivative Works thereof.
|
|
47
|
+
|
|
48
|
+
"Contribution" shall mean any work of authorship, including
|
|
49
|
+
the original version of the Work and any modifications or additions
|
|
50
|
+
to that Work or Derivative Works thereof, that is intentionally
|
|
51
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
|
52
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
|
53
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
|
54
|
+
means any form of electronic, verbal, or written communication sent
|
|
55
|
+
to the Licensor or its representatives, including but not limited to
|
|
56
|
+
communication on electronic mailing lists, source code control systems,
|
|
57
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
|
58
|
+
Licensor for the purpose of discussing and improving the Work, but
|
|
59
|
+
excluding communication that is conspicuously marked or otherwise
|
|
60
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
|
61
|
+
|
|
62
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
63
|
+
on behalf of whom a Contribution has been received by Licensor and
|
|
64
|
+
subsequently incorporated within the Work.
|
|
65
|
+
|
|
66
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
67
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
68
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
69
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
70
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
71
|
+
Work and such Derivative Works in Source or Object form.
|
|
72
|
+
|
|
73
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
74
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
75
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
76
|
+
(except as stated in this section) patent license to make, have made,
|
|
77
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
78
|
+
where such license applies only to those patent claims licensable
|
|
79
|
+
by such Contributor that are necessarily infringed by their
|
|
80
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
|
81
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
82
|
+
institute patent litigation against any entity (including a
|
|
83
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
84
|
+
or a Contribution incorporated within the Work constitutes direct
|
|
85
|
+
or contributory patent infringement, then any patent licenses
|
|
86
|
+
granted to You under this License for that Work shall terminate
|
|
87
|
+
as of the date such litigation is filed.
|
|
88
|
+
|
|
89
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
90
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
91
|
+
modifications, and in Source or Object form, provided that You
|
|
92
|
+
meet the following conditions:
|
|
93
|
+
|
|
94
|
+
(a) You must give any other recipients of the Work or
|
|
95
|
+
Derivative Works a copy of this License; and
|
|
96
|
+
|
|
97
|
+
(b) You must cause any modified files to carry prominent notices
|
|
98
|
+
stating that You changed the files; and
|
|
99
|
+
|
|
100
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
101
|
+
that You distribute, all copyright, patent, trademark, and
|
|
102
|
+
attribution notices from the Source form of the Work,
|
|
103
|
+
excluding those notices that do not pertain to any part of
|
|
104
|
+
the Derivative Works; and
|
|
105
|
+
|
|
106
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
107
|
+
distribution, then any Derivative Works that You distribute must
|
|
108
|
+
include a readable copy of the attribution notices contained
|
|
109
|
+
within such NOTICE file, excluding those notices that do not
|
|
110
|
+
pertain to any part of the Derivative Works, in at least one
|
|
111
|
+
of the following places: within a NOTICE text file distributed
|
|
112
|
+
as part of the Derivative Works; within the Source form or
|
|
113
|
+
documentation, if provided along with the Derivative Works; or,
|
|
114
|
+
within a display generated by the Derivative Works, if and
|
|
115
|
+
wherever such third-party notices normally appear. The contents
|
|
116
|
+
of the NOTICE file are for informational purposes only and
|
|
117
|
+
do not modify the License. You may add Your own attribution
|
|
118
|
+
notices within Derivative Works that You distribute, alongside
|
|
119
|
+
or as an addendum to the NOTICE text from the Work, provided
|
|
120
|
+
that such additional attribution notices cannot be construed
|
|
121
|
+
as modifying the License.
|
|
122
|
+
|
|
123
|
+
You may add Your own copyright statement to Your modifications and
|
|
124
|
+
may provide additional or different license terms and conditions
|
|
125
|
+
for use, reproduction, or distribution of Your modifications, or
|
|
126
|
+
for any such Derivative Works as a whole, provided Your use,
|
|
127
|
+
reproduction, and distribution of the Work otherwise complies with
|
|
128
|
+
the conditions stated in this License.
|
|
129
|
+
|
|
130
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
131
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
132
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
133
|
+
this License, without any additional terms or conditions.
|
|
134
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
135
|
+
the terms of any separate license agreement you may have executed
|
|
136
|
+
with Licensor regarding such Contributions.
|
|
137
|
+
|
|
138
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
139
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
140
|
+
except as required for reasonable and customary use in describing the
|
|
141
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
142
|
+
|
|
143
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
144
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
145
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
146
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
147
|
+
implied, including, without limitation, any warranties or conditions
|
|
148
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
149
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
150
|
+
appropriateness of using or redistributing the Work and assume any
|
|
151
|
+
risks associated with Your exercise of permissions under this License.
|
|
152
|
+
|
|
153
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
154
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
155
|
+
unless required by applicable law (such as deliberate and grossly
|
|
156
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
157
|
+
liable to You for damages, including any direct, indirect, special,
|
|
158
|
+
incidental, or consequential damages of any character arising as a
|
|
159
|
+
result of this License or out of the use or inability to use the
|
|
160
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
161
|
+
work stoppage, computer failure or malfunction, or any and all
|
|
162
|
+
other commercial damages or losses), even if such Contributor
|
|
163
|
+
has been advised of the possibility of such damages.
|
|
164
|
+
|
|
165
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
166
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
167
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
168
|
+
or other liability obligations and/or rights consistent with this
|
|
169
|
+
License. However, in accepting such obligations, You may act only
|
|
170
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
|
171
|
+
of any other Contributor, and only if You agree to indemnify,
|
|
172
|
+
defend, and hold each Contributor harmless for any liability
|
|
173
|
+
incurred by, or claims asserted against, such Contributor by reason
|
|
174
|
+
of your accepting any such warranty or additional liability.
|
|
175
|
+
|
|
176
|
+
END OF TERMS AND CONDITIONS
|
|
177
|
+
|
|
178
|
+
Copyright 2025 Tim O'Brien
|
|
179
|
+
|
|
180
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
181
|
+
you may not use this file except in compliance with the License.
|
|
182
|
+
You may obtain a copy of the License at
|
|
183
|
+
|
|
184
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
185
|
+
|
|
186
|
+
Unless required by applicable law or agreed to in writing, software
|
|
187
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
188
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
189
|
+
See the License for the specific language governing permissions and
|
|
190
|
+
limitations under the License.
|
|
@@ -0,0 +1,211 @@
|
|
|
1
|
+
# MCP Elicitation Notes
|
|
2
|
+
|
|
3
|
+
## Understanding MCP Elicitation
|
|
4
|
+
|
|
5
|
+
### What It Is
|
|
6
|
+
|
|
7
|
+
MCP elicitation (introduced in the 2025-06-18 specification) is a protocol feature that allows **servers** to request structured data from users dynamically during interactions. It uses JSON schemas to validate responses and enables interactive workflows.
|
|
8
|
+
|
|
9
|
+
### How It Works
|
|
10
|
+
|
|
11
|
+
Servers send `elicitation/create` requests to clients:
|
|
12
|
+
|
|
13
|
+
```json
|
|
14
|
+
{
|
|
15
|
+
"jsonrpc": "2.0",
|
|
16
|
+
"id": 1,
|
|
17
|
+
"method": "elicitation/create",
|
|
18
|
+
"params": {
|
|
19
|
+
"message": "Please provide your GitHub username",
|
|
20
|
+
"requestedSchema": {
|
|
21
|
+
"type": "object",
|
|
22
|
+
"properties": {
|
|
23
|
+
"name": { "type": "string" }
|
|
24
|
+
},
|
|
25
|
+
"required": ["name"]
|
|
26
|
+
}
|
|
27
|
+
}
|
|
28
|
+
}
|
|
29
|
+
```
|
|
30
|
+
|
|
31
|
+
Clients respond with:
|
|
32
|
+
|
|
33
|
+
```json
|
|
34
|
+
{
|
|
35
|
+
"jsonrpc": "2.0",
|
|
36
|
+
"id": 1,
|
|
37
|
+
"result": {
|
|
38
|
+
"action": "accept",
|
|
39
|
+
"content": { "name": "octocat" }
|
|
40
|
+
}
|
|
41
|
+
}
|
|
42
|
+
```
|
|
43
|
+
|
|
44
|
+
### Key Limitation for Prompts
|
|
45
|
+
|
|
46
|
+
**Prompts cannot directly trigger elicitation requests.** Prompts are static text templates that return messages to inject into the conversation. They don't have the ability to make protocol-level requests.
|
|
47
|
+
|
|
48
|
+
Only **tools** and **resources** can trigger elicitation by making `elicitation/create` requests during their execution.
|
|
49
|
+
|
|
50
|
+
## Our Approach: Prompt Arguments + Model Instructions
|
|
51
|
+
|
|
52
|
+
Since prompts can't trigger elicitation directly, we use a hybrid approach:
|
|
53
|
+
|
|
54
|
+
### 1. Define Prompt Arguments
|
|
55
|
+
|
|
56
|
+
```typescript
|
|
57
|
+
{
|
|
58
|
+
name: 'create_plan',
|
|
59
|
+
description: 'Create a new plan with AI-generated steps for a complex task',
|
|
60
|
+
arguments: [
|
|
61
|
+
{
|
|
62
|
+
name: 'code',
|
|
63
|
+
description: 'Plan code/identifier',
|
|
64
|
+
required: false,
|
|
65
|
+
},
|
|
66
|
+
{
|
|
67
|
+
name: 'description',
|
|
68
|
+
description: 'Detailed description of what to accomplish',
|
|
69
|
+
required: false,
|
|
70
|
+
},
|
|
71
|
+
{
|
|
72
|
+
name: 'directory',
|
|
73
|
+
description: 'Parent directory where the plan should be created',
|
|
74
|
+
required: false,
|
|
75
|
+
},
|
|
76
|
+
],
|
|
77
|
+
}
|
|
78
|
+
```
|
|
79
|
+
|
|
80
|
+
### 2. Template Variable Substitution
|
|
81
|
+
|
|
82
|
+
The prompt template uses `${code}`, `${description}`, etc.:
|
|
83
|
+
|
|
84
|
+
```markdown
|
|
85
|
+
## Step 1: Review Provided Information
|
|
86
|
+
|
|
87
|
+
Check what information has already been provided:
|
|
88
|
+
- **code**: ${code}
|
|
89
|
+
- **description**: ${description}
|
|
90
|
+
- **directory**: ${directory}
|
|
91
|
+
```
|
|
92
|
+
|
|
93
|
+
When arguments are missing, we substitute with markers like `[code]`, `[description]`:
|
|
94
|
+
|
|
95
|
+
```typescript
|
|
96
|
+
if (!filledArgs.code) filledArgs.code = '[code]';
|
|
97
|
+
if (!filledArgs.description) filledArgs.description = '[description]';
|
|
98
|
+
```
|
|
99
|
+
|
|
100
|
+
### 3. Model Instructions
|
|
101
|
+
|
|
102
|
+
The prompt explicitly tells the model to check for these markers:
|
|
103
|
+
|
|
104
|
+
```markdown
|
|
105
|
+
## Step 2: Gather Missing Information
|
|
106
|
+
|
|
107
|
+
For any information marked as "[code]", "[description]", "[directory]",
|
|
108
|
+
ask the user to provide it:
|
|
109
|
+
|
|
110
|
+
1. **Plan Code** (if missing) - Ask for a short identifier
|
|
111
|
+
2. **Plan Description** (if missing) - Ask for a detailed description
|
|
112
|
+
3. **Target Directory** (if missing) - Ask where to create the plan
|
|
113
|
+
```
|
|
114
|
+
|
|
115
|
+
## Benefits of This Approach
|
|
116
|
+
|
|
117
|
+
### Client-Side Elicitation (Future)
|
|
118
|
+
|
|
119
|
+
MCP clients could potentially:
|
|
120
|
+
1. See that `create_plan` has arguments
|
|
121
|
+
2. Elicit those arguments from the user BEFORE invoking the prompt
|
|
122
|
+
3. Pass the collected values when calling the prompt
|
|
123
|
+
|
|
124
|
+
This would provide a form-based UI for gathering information upfront.
|
|
125
|
+
|
|
126
|
+
### Model-Side Fallback (Current)
|
|
127
|
+
|
|
128
|
+
If the client doesn't elicit arguments:
|
|
129
|
+
1. The prompt is invoked with missing arguments
|
|
130
|
+
2. Template substitution marks them as `[code]`, `[description]`, etc.
|
|
131
|
+
3. The model sees these markers and knows to ask the user
|
|
132
|
+
4. The model uses natural language to gather information
|
|
133
|
+
|
|
134
|
+
### Progressive Enhancement
|
|
135
|
+
|
|
136
|
+
- Works today with explicit model instructions
|
|
137
|
+
- Can be enhanced in the future if clients add argument elicitation
|
|
138
|
+
- Provides clear structure for what information is needed
|
|
139
|
+
|
|
140
|
+
## Alternative: Tool-Based Elicitation
|
|
141
|
+
|
|
142
|
+
Another approach would be to create a tool that triggers elicitation:
|
|
143
|
+
|
|
144
|
+
```typescript
|
|
145
|
+
{
|
|
146
|
+
name: 'riotplan_elicit_plan_info',
|
|
147
|
+
description: 'Gather plan information from user',
|
|
148
|
+
inputSchema: {
|
|
149
|
+
type: 'object',
|
|
150
|
+
properties: {}
|
|
151
|
+
}
|
|
152
|
+
}
|
|
153
|
+
|
|
154
|
+
async function executeElicitPlanInfo(args, context) {
|
|
155
|
+
// Make elicitation/create request
|
|
156
|
+
const result = await context.elicit({
|
|
157
|
+
message: "Please provide plan information",
|
|
158
|
+
requestedSchema: {
|
|
159
|
+
type: "object",
|
|
160
|
+
properties: {
|
|
161
|
+
code: { type: "string", description: "Plan code" },
|
|
162
|
+
description: { type: "string", description: "What to accomplish" },
|
|
163
|
+
directory: { type: "string", description: "Where to create plan" }
|
|
164
|
+
},
|
|
165
|
+
required: ["code", "description"]
|
|
166
|
+
}
|
|
167
|
+
});
|
|
168
|
+
|
|
169
|
+
return result;
|
|
170
|
+
}
|
|
171
|
+
```
|
|
172
|
+
|
|
173
|
+
However, this has drawbacks:
|
|
174
|
+
- Requires the model to know to call this tool
|
|
175
|
+
- Adds an extra step (call tool, then call create)
|
|
176
|
+
- Less integrated with the prompt workflow
|
|
177
|
+
|
|
178
|
+
## Recommendation
|
|
179
|
+
|
|
180
|
+
The **prompt arguments + model instructions** approach is the best solution because:
|
|
181
|
+
|
|
182
|
+
1. **Works today** - Model instructions ensure it works immediately
|
|
183
|
+
2. **Future-proof** - Can be enhanced if clients add argument elicitation
|
|
184
|
+
3. **Clear structure** - Arguments document what's needed
|
|
185
|
+
4. **Flexible** - Users can provide info upfront OR be prompted
|
|
186
|
+
5. **Natural** - Model asks in conversational way, not just forms
|
|
187
|
+
|
|
188
|
+
## Implementation Status
|
|
189
|
+
|
|
190
|
+
✅ Added prompt arguments to `create_plan`
|
|
191
|
+
✅ Added template variable substitution
|
|
192
|
+
✅ Added explicit model instructions
|
|
193
|
+
✅ Rebuilt MCP server with changes
|
|
194
|
+
⏳ Waiting for client support for argument elicitation (future enhancement)
|
|
195
|
+
|
|
196
|
+
## Testing
|
|
197
|
+
|
|
198
|
+
To test the current implementation:
|
|
199
|
+
|
|
200
|
+
1. Invoke `create_plan` prompt without arguments
|
|
201
|
+
2. Model should see `[code]`, `[description]`, `[directory]` markers
|
|
202
|
+
3. Model should ask user for missing information
|
|
203
|
+
4. Model should use `riotplan_create` tool with collected info
|
|
204
|
+
|
|
205
|
+
To test future client elicitation (when supported):
|
|
206
|
+
|
|
207
|
+
1. Client sees `create_plan` has arguments
|
|
208
|
+
2. Client shows form to collect: code, description, directory
|
|
209
|
+
3. Client invokes prompt with collected values
|
|
210
|
+
4. Model sees actual values, not markers
|
|
211
|
+
5. Model proceeds directly to creating the plan
|
|
@@ -0,0 +1,122 @@
|
|
|
1
|
+
# Fix: explore_idea Command UX Issue
|
|
2
|
+
|
|
3
|
+
## Problem
|
|
4
|
+
|
|
5
|
+
The `explore_idea` MCP prompt had a workflow mismatch that created a confusing user experience:
|
|
6
|
+
|
|
7
|
+
1. User invokes the prompt (via MCP or Cursor command)
|
|
8
|
+
2. AI would immediately stop and ask for structured input:
|
|
9
|
+
- "Please provide a code/identifier"
|
|
10
|
+
- "Please provide an initial description"
|
|
11
|
+
3. User had to provide these in a second interaction
|
|
12
|
+
4. Only then would the AI create the idea and begin exploration
|
|
13
|
+
|
|
14
|
+
This created a jarring, form-filling experience instead of a natural conversational flow.
|
|
15
|
+
|
|
16
|
+
## Root Cause
|
|
17
|
+
|
|
18
|
+
The MCP prompt file (`src/mcp/prompts/explore_idea.md`) had outdated instructions that told the AI to:
|
|
19
|
+
1. Ask the user for code and description
|
|
20
|
+
2. Wait for response
|
|
21
|
+
3. Then create the idea
|
|
22
|
+
|
|
23
|
+
Meanwhile, the Cursor command version (`.cursor/commands/explore_idea.md`) had already been updated with smart extraction logic.
|
|
24
|
+
|
|
25
|
+
## Solution
|
|
26
|
+
|
|
27
|
+
Updated the MCP prompt to match the improved Cursor command version with smart extraction:
|
|
28
|
+
|
|
29
|
+
### Key Changes
|
|
30
|
+
|
|
31
|
+
1. **Smart Extraction First**: AI now checks if the user already provided code/description in their message
|
|
32
|
+
2. **Derive Missing Info**: If description is provided but code is missing, AI derives a kebab-case code from the description
|
|
33
|
+
3. **Natural Fallback**: Only asks for missing information if truly needed
|
|
34
|
+
4. **Immediate Creation**: Creates the idea as soon as it has the required info
|
|
35
|
+
5. **Start Exploration**: Begins the exploration conversation immediately after creation
|
|
36
|
+
|
|
37
|
+
### Updated Workflow
|
|
38
|
+
|
|
39
|
+
```
|
|
40
|
+
1. Extract or Gather Idea Details
|
|
41
|
+
- Check user's message for code and description
|
|
42
|
+
- Extract if present
|
|
43
|
+
- Derive code from description if only description provided
|
|
44
|
+
- Only ask if both are missing
|
|
45
|
+
|
|
46
|
+
2. Create the Idea
|
|
47
|
+
- Call riotplan_idea_create immediately with extracted/derived values
|
|
48
|
+
|
|
49
|
+
3. Begin Exploration
|
|
50
|
+
- Start asking open-ended questions immediately
|
|
51
|
+
- Don't wait for further prompting
|
|
52
|
+
```
|
|
53
|
+
|
|
54
|
+
### Example Flows
|
|
55
|
+
|
|
56
|
+
**Before Fix:**
|
|
57
|
+
```
|
|
58
|
+
User: /riotplan/explore_idea
|
|
59
|
+
AI: "Please provide: 1. A short code/identifier 2. Initial description"
|
|
60
|
+
User: "Ugh, okay... code is 'my-feature', description is 'Add feature X'"
|
|
61
|
+
AI: *calls riotplan_idea_create*
|
|
62
|
+
AI: "What's driving this?"
|
|
63
|
+
```
|
|
64
|
+
|
|
65
|
+
**After Fix - Full Info:**
|
|
66
|
+
```
|
|
67
|
+
User: /riotplan/explore_idea real-time-notifications Add push notifications
|
|
68
|
+
AI: *extracts code="real-time-notifications", description="Add push notifications"*
|
|
69
|
+
AI: *calls riotplan_idea_create immediately*
|
|
70
|
+
AI: "Let's explore this idea. What's driving the need for push notifications?"
|
|
71
|
+
```
|
|
72
|
+
|
|
73
|
+
**After Fix - Partial Info:**
|
|
74
|
+
```
|
|
75
|
+
User: /riotplan/explore_idea I want to add notifications
|
|
76
|
+
AI: *derives code="add-notifications", description="I want to add notifications"*
|
|
77
|
+
AI: *calls riotplan_idea_create immediately*
|
|
78
|
+
AI: "Let's explore this notification idea. What's driving this?"
|
|
79
|
+
```
|
|
80
|
+
|
|
81
|
+
**After Fix - No Info:**
|
|
82
|
+
```
|
|
83
|
+
User: /riotplan/explore_idea
|
|
84
|
+
AI: "What idea would you like to explore? Give me a short name and brief description."
|
|
85
|
+
User: "I'm thinking about real-time notifications"
|
|
86
|
+
AI: *extracts and creates immediately*
|
|
87
|
+
AI: "Great! Let's explore this. What's driving the need?"
|
|
88
|
+
```
|
|
89
|
+
|
|
90
|
+
## Files Changed
|
|
91
|
+
|
|
92
|
+
- `/Users/tobrien/gitw/kjerneverk/riotplan/src/mcp/prompts/explore_idea.md`
|
|
93
|
+
- Updated workflow section with smart extraction logic
|
|
94
|
+
- Added detailed examples showing extraction patterns
|
|
95
|
+
- Added anti-pattern: "Don't ask for information the user already provided"
|
|
96
|
+
- Added principle: "Smart Extraction: Use information the user already provided"
|
|
97
|
+
|
|
98
|
+
## Testing
|
|
99
|
+
|
|
100
|
+
- All existing tests pass (623 tests, 92.84% coverage)
|
|
101
|
+
- No breaking changes to MCP tool schemas
|
|
102
|
+
- Backward compatible with all existing workflows
|
|
103
|
+
|
|
104
|
+
## Benefits
|
|
105
|
+
|
|
106
|
+
1. **Better UX**: Natural conversational flow instead of form-filling
|
|
107
|
+
2. **Fewer Steps**: Reduces interaction from 2-3 messages to 1
|
|
108
|
+
3. **Smarter AI**: AI extracts and derives information intelligently
|
|
109
|
+
4. **Consistent**: MCP prompt now matches Cursor command behavior
|
|
110
|
+
5. **Flexible**: Still supports all three scenarios (full info, partial info, no info)
|
|
111
|
+
|
|
112
|
+
## Related Work
|
|
113
|
+
|
|
114
|
+
The Cursor command version (`.cursor/commands/explore_idea.md`) already had this smart extraction logic. This fix brings the MCP prompt in sync with that improved version.
|
|
115
|
+
|
|
116
|
+
## Future Considerations
|
|
117
|
+
|
|
118
|
+
This pattern could be applied to other interactive prompts/commands that currently ask for structured input upfront. Candidates to review:
|
|
119
|
+
- `checkpoint_create` (asks for name and message)
|
|
120
|
+
- Any other prompts that immediately request structured data
|
|
121
|
+
|
|
122
|
+
The key insight: **Extract first, ask later**. If the user has already provided information in their message, use it instead of asking them to repeat it.
|
package/MCP-FIXES.md
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
1
|
+
# MCP Implementation Fixes Needed
|
|
2
|
+
|
|
3
|
+
## TypeScript Errors to Fix
|
|
4
|
+
|
|
5
|
+
### 1. Plan.path -> Plan.metadata.path
|
|
6
|
+
- Plan type doesn't have `path` property
|
|
7
|
+
- Use `plan.metadata.path` instead
|
|
8
|
+
|
|
9
|
+
### 2. PlanStep.file -> PlanStep.filename
|
|
10
|
+
- PlanStep has `filename` not `file`
|
|
11
|
+
|
|
12
|
+
### 3. PlanState property names
|
|
13
|
+
- `lastCompleted` -> `lastCompletedStep`
|
|
14
|
+
- `lastUpdated` -> `lastUpdatedAt`
|
|
15
|
+
|
|
16
|
+
### 4. PlanMetadata property names
|
|
17
|
+
- `created` -> `createdAt`
|
|
18
|
+
|
|
19
|
+
### 5. Blocker[] and Issue[] types
|
|
20
|
+
- StatusResource expects `string[]` but Plan has `Blocker[]` and `Issue[]`
|
|
21
|
+
- Need to convert to strings or update types
|
|
22
|
+
|
|
23
|
+
### 6. ValidateOptions
|
|
24
|
+
- `fix` property doesn't exist
|
|
25
|
+
- Need to check actual API
|
|
26
|
+
|
|
27
|
+
### 7. CreatePlanResult
|
|
28
|
+
- Doesn't have `steps` property
|
|
29
|
+
- Check actual return type
|
|
30
|
+
|
|
31
|
+
### 8. GenerationContext
|
|
32
|
+
- Missing `planName` property
|
|
33
|
+
- Need to provide it
|
|
34
|
+
|
|
35
|
+
### 9. MCP Build Externals
|
|
36
|
+
- Need to add execution provider packages to externals in build-mcp.js
|
|
37
|
+
|
|
38
|
+
## Files to Update
|
|
39
|
+
|
|
40
|
+
1. `src/mcp/resources/plan.ts` - Fix property names
|
|
41
|
+
2. `src/mcp/resources/status.ts` - Fix property names and types
|
|
42
|
+
3. `src/mcp/resources/step.ts` - Fix property names
|
|
43
|
+
4. `src/mcp/resources/steps.ts` - Fix property names
|
|
44
|
+
5. `src/mcp/tools/status.ts` - Fix property names
|
|
45
|
+
6. `src/mcp/tools/step.ts` - Fix property names
|
|
46
|
+
7. `src/mcp/tools/create.ts` - Fix return type handling
|
|
47
|
+
8. `src/mcp/tools/generate.ts` - Fix GenerationContext
|
|
48
|
+
9. `src/mcp/tools/validate.ts` - Fix options
|
|
49
|
+
10. `src/mcp/types.ts` - Update StatusResource type
|
|
50
|
+
11. `scripts/build-mcp.js` - Add externals
|