Skip to content

Commit 2cf032d

Browse files
akoclaude
ako
and
claude
committed
feat: add AI enhancement guide workflow for issue triage
When an issue is opened or labeled with 'enhancement', this workflow posts an implementation guide comment covering: - Completeness assessment (asks followup questions if details missing) - Overlap check against existing features and skills - Proposed MDL syntax following design guidelines - Step-by-step implementation roadmap with specific files - BSON investigation steps - Testing strategy - Common gotchas and risks The guide is informed by CLAUDE.md, the MDL quick reference, syntax design guidelines, implementation pipeline skill, and feature matrix. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
1 parent 550e338 commit 2cf032d

File tree

1 file changed

+197
-0
lines changed

1 file changed

+197
-0
lines changed

‎.github/workflows/ai-enhancement-guide.yml‎

Lines changed: 197 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,197 @@
1+
name: Enhancement Guide
2+
3+
on:
4+
issues:
5+
types: [opened, labeled]
6+
7+
permissions:
8+
issues: write
9+
contents: read
10+
11+
jobs:
12+
guide:
13+
# Only run for issues with 'enhancement' label
14+
if: contains(github.event.issue.labels.*.name, 'enhancement')
15+
runs-on: ubuntu-latest
16+
steps:
17+
- uses: actions/checkout@v5
18+
with:
19+
fetch-depth: 1
20+
21+
- name: Get issue details
22+
env:
23+
GH_TOKEN: ${{ github.token }}
24+
run: |
25+
gh issue view ${{ github.event.issue.number }} \
26+
--repo ${{ github.repository }} \
27+
--json title,body,labels > /tmp/issue.json
28+
29+
- name: Gather project context
30+
run: |
31+
# Architecture and key concepts
32+
cat CLAUDE.md > /tmp/claude-md.txt
33+
34+
# MDL quick reference (all current syntax)
35+
if [ -f "docs/01-project/MDL_QUICK_REFERENCE.md" ]; then
36+
cat docs/01-project/MDL_QUICK_REFERENCE.md > /tmp/mdl-reference.txt
37+
else
38+
echo "No MDL quick reference found." > /tmp/mdl-reference.txt
39+
fi
40+
41+
# Feature implementation pipeline
42+
if [ -f ".claude/skills/implement-mdl-feature.md" ]; then
43+
cat .claude/skills/implement-mdl-feature.md > /tmp/implement-skill.txt
44+
else
45+
echo "No implementation skill found." > /tmp/implement-skill.txt
46+
fi
47+
48+
# MDL syntax design guidelines
49+
if [ -f ".claude/skills/design-mdl-syntax.md" ]; then
50+
cat .claude/skills/design-mdl-syntax.md > /tmp/design-skill.txt
51+
else
52+
echo "No design skill found." > /tmp/design-skill.txt
53+
fi
54+
55+
# List existing skills (what features already exist)
56+
ls .claude/skills/mendix/ 2>/dev/null > /tmp/skills-list.txt || echo "none" > /tmp/skills-list.txt
57+
58+
# List existing doctype tests (what's already covered)
59+
ls mdl-examples/doctype-tests/ 2>/dev/null > /tmp/doctype-tests.txt || echo "none" > /tmp/doctype-tests.txt
60+
61+
# Current feature matrix
62+
if [ -f "docs/01-project/MDL_FEATURE_MATRIX.md" ]; then
63+
cat docs/01-project/MDL_FEATURE_MATRIX.md > /tmp/feature-matrix.txt
64+
else
65+
echo "No feature matrix found." > /tmp/feature-matrix.txt
66+
fi
67+
68+
- name: Build API request
69+
run: |
70+
cat > /tmp/user-prompt.txt <<'PROMPT'
71+
Analyze this enhancement request and provide an implementation guide.
72+
73+
## Enhancement Request
74+
PROMPT
75+
cat /tmp/issue.json >> /tmp/user-prompt.txt
76+
77+
cat >> /tmp/user-prompt.txt <<'PROMPT'
78+
79+
## Project Context (CLAUDE.md — architecture, key concepts, review checklist)
80+
PROMPT
81+
cat /tmp/claude-md.txt >> /tmp/user-prompt.txt
82+
83+
cat >> /tmp/user-prompt.txt <<'PROMPT'
84+
85+
## MDL Syntax Design Guidelines
86+
PROMPT
87+
cat /tmp/design-skill.txt >> /tmp/user-prompt.txt
88+
89+
cat >> /tmp/user-prompt.txt <<'PROMPT'
90+
91+
## Implementation Pipeline (step-by-step for new MDL features)
92+
PROMPT
93+
cat /tmp/implement-skill.txt >> /tmp/user-prompt.txt
94+
95+
cat >> /tmp/user-prompt.txt <<'PROMPT'
96+
97+
## Current MDL Quick Reference (all existing syntax)
98+
PROMPT
99+
cat /tmp/mdl-reference.txt >> /tmp/user-prompt.txt
100+
101+
cat >> /tmp/user-prompt.txt <<'PROMPT'
102+
103+
## Feature Matrix
104+
PROMPT
105+
cat /tmp/feature-matrix.txt >> /tmp/user-prompt.txt
106+
107+
cat >> /tmp/user-prompt.txt <<'PROMPT'
108+
109+
## Existing skill files (features already documented)
110+
PROMPT
111+
cat /tmp/skills-list.txt >> /tmp/user-prompt.txt
112+
113+
cat >> /tmp/user-prompt.txt <<'PROMPT'
114+
115+
## Existing doctype test scripts
116+
PROMPT
117+
cat /tmp/doctype-tests.txt >> /tmp/user-prompt.txt
118+
119+
# Truncate to 120k to stay within API limits
120+
if [ "$(wc -c < /tmp/user-prompt.txt)" -gt 120000 ]; then
121+
head -c 120000 /tmp/user-prompt.txt > /tmp/user-prompt-truncated.txt
122+
mv /tmp/user-prompt-truncated.txt /tmp/user-prompt.txt
123+
fi
124+
125+
jq -n --rawfile prompt /tmp/user-prompt.txt '{
126+
model: "nvidia/nemotron-3-super-120b-a12b:free",
127+
messages: [
128+
{
129+
role: "system",
130+
content: "You are an implementation guide for mxcli, a Go CLI tool that reads and modifies Mendix application projects (.mpr files) using MDL (Mendix Definition Language), a SQL-like syntax.\n\nYour job is to analyze enhancement requests and produce a practical implementation guide that helps developers (human or AI agent) implement the feature correctly.\n\nYou have deep knowledge of:\n- The full-stack MDL pipeline: ANTLR4 grammar → AST → visitor → executor → BSON writer\n- Mendix BSON serialization (storage names vs qualified names, required defaults)\n- MDL syntax design principles (reads as English, standard CRUD verbs, qualified names)\n- The PR review checklist (overlap, full-stack consistency, test coverage, security)\n\nYour response MUST include these sections:\n\n1. **Completeness Assessment** — Does the issue have enough detail? If NOT, list specific questions to ask the reporter (Mendix version? example of desired syntax? which Mendix concepts are involved?).\n\n2. **Overlap Check** — Could this already be done with existing syntax? List any existing features/skills that partially cover this.\n\n3. **Proposed MDL Syntax** — Draft the MDL syntax following design guidelines. Show 2-3 examples. If the issue already proposes syntax, evaluate it against guidelines.\n\n4. **Implementation Roadmap** — Step-by-step checklist of files to create/modify, following the full-stack pipeline. Be specific: name the actual files, functions, and patterns to follow.\n\n5. **BSON Investigation** — What BSON structures need to be understood? Suggest specific investigation steps (which reflection data to check, what to create in Studio Pro for reference).\n\n6. **Testing Strategy** — What doctype test script to add, what mx check validations to expect, what integration tests to write.\n\n7. **Gotchas & Risks** — Common pitfalls for this type of feature (storage name vs qualified name, missing BSON defaults, CE error codes to expect).\n\nKeep it practical and actionable. Reference specific files and patterns from the project context. If the enhancement is unclear, prioritize section 1 (questions) and keep other sections brief."
131+
},
132+
{
133+
role: "user",
134+
content: $prompt
135+
}
136+
],
137+
max_tokens: 4000,
138+
temperature: 0.3
139+
}' > /tmp/request.json
140+
141+
echo "Request payload size: $(wc -c < /tmp/request.json) bytes"
142+
143+
- name: Call OpenRouter API
144+
env:
145+
OPENROUTER_API_KEY: ${{ secrets.OPENROUTER_API_KEY }}
146+
run: |
147+
if [ -z "$OPENROUTER_API_KEY" ]; then
148+
echo "::warning::OPENROUTER_API_KEY secret is not set"
149+
exit 0
150+
fi
151+
152+
HTTP_CODE=$(curl -s -w "%{http_code}" -o /tmp/response.json -X POST \
153+
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
154+
-H "Content-Type: application/json" \
155+
-d @/tmp/request.json \
156+
https://openrouter.ai/api/v1/chat/completions)
157+
158+
echo "HTTP status: $HTTP_CODE"
159+
160+
if [ "$HTTP_CODE" != "200" ]; then
161+
echo "::warning::OpenRouter API returned HTTP $HTTP_CODE"
162+
cat /tmp/response.json | head -c 1000
163+
exit 0
164+
fi
165+
166+
REVIEW=$(jq -r '.choices[0].message.content // empty' /tmp/response.json)
167+
168+
if [ -z "$REVIEW" ]; then
169+
echo "::warning::AI returned empty content. Response:"
170+
cat /tmp/response.json | head -c 1000
171+
exit 0
172+
fi
173+
174+
echo "$REVIEW" > /tmp/guide.txt
175+
echo "Guide generated ($(wc -c < /tmp/guide.txt) bytes)"
176+
177+
- name: Post guide comment
178+
env:
179+
GH_TOKEN: ${{ github.token }}
180+
run: |
181+
if [ ! -f /tmp/guide.txt ]; then
182+
echo "No guide to post."
183+
exit 0
184+
fi
185+
186+
{
187+
echo "## Enhancement Implementation Guide"
188+
echo ""
189+
cat /tmp/guide.txt
190+
echo ""
191+
echo "---"
192+
echo "*Automated guide via OpenRouter — [workflow source](${{ github.server_url }}/${{ github.repository }}/blob/main/.github/workflows/ai-enhancement-guide.yml)*"
193+
} > /tmp/comment.md
194+
195+
gh issue comment ${{ github.event.issue.number }} \
196+
--repo ${{ github.repository }} \
197+
--body-file /tmp/comment.md

0 commit comments

Comments
 (0)