feat: add sparv enhanced rules v1.1

- Add Uncertainty Declaration (G3): declare assumptions when score < 2
- Add Requirement Routing: Quick/Full mode based on scope
- Add Context Acquisition: optional kb.md check before Specify
- Add Knowledge Base: .sparv/kb.md for cross-session patterns
- Add changelog-update.sh: maintain CHANGELOG by type

Generated with SWE-Agent.ai

Co-Authored-By: SWE-Agent.ai <noreply@swe-agent.ai>
This commit is contained in:
cexll
2026-01-17 13:12:10 +08:00
parent 6985a30a6a
commit e122d8ff25
4 changed files with 228 additions and 0 deletions

View File

@@ -17,6 +17,56 @@ Goal: Complete "requirements → verifiable delivery" in one pass, recording key
- **EHRB**: Require explicit user confirmation when high-risk detected (production/sensitive data/destructive/billing API/security-critical).
- **Fixed Phase Names**: `specify|plan|act|review|vault` (stored in `.sparv/state.yaml:current_phase`).
## Enhanced Rules (v1.1)
### Uncertainty Declaration (G3)
When any Specify dimension scores < 2:
- Declare: `UNCERTAIN: <what> | ASSUMPTION: <fallback>`
- List all assumptions in journal before Plan
- Offer 2-3 options for ambiguous requirements
Example:
```
UNCERTAIN: deployment target | ASSUMPTION: Docker container
UNCERTAIN: auth method | OPTIONS: JWT / OAuth2 / Session
```
### Requirement Routing
| Mode | Condition | Flow |
|------|-----------|------|
| **Quick** | score >= 9 AND <= 3 files AND no EHRB | Specify → Act → Review |
| **Full** | otherwise | Specify → Plan → Act → Review → Vault |
Quick mode skips formal Plan phase but still requires:
- Completion promise written to journal
- 2-action save rule applies
- Review phase mandatory
### Context Acquisition (Optional)
Before Specify scoring:
1. Check `.sparv/kb.md` for existing patterns/decisions
2. If insufficient, scan codebase for relevant files
3. Document findings in journal under `## Context`
Skip if user explicitly provides full context.
### Knowledge Base Maintenance
During Vault phase, update `.sparv/kb.md`:
- **Patterns**: Reusable code patterns discovered
- **Decisions**: Architectural choices + rationale
- **Gotchas**: Common pitfalls + solutions
### CHANGELOG Update
Use during Review or Vault phase for non-trivial changes:
```bash
~/.claude/skills/sparv/scripts/changelog-update.sh --type <Added|Changed|Fixed|Removed> --desc "..."
```
## External Memory (Two Files)
Initialize (run in project root):

View File

@@ -10,6 +10,42 @@ This document is a quick reference; the canonical spec is in `SKILL.md`.
- **Review**: Spec conformance → Code quality; maximum 3 fix rounds
- **Vault**: Archive session (state + journal)
## Enhanced Rules (v1.1)
### Uncertainty Declaration (G3)
When any Specify dimension scores < 2:
- Declare: `UNCERTAIN: <what> | ASSUMPTION: <fallback>`
- List all assumptions in journal before Plan
- Offer 2-3 options for ambiguous requirements
### Requirement Routing
| Mode | Condition | Flow |
|------|-----------|------|
| **Quick** | score >= 9 AND <= 3 files AND no EHRB | Specify → Act → Review |
| **Full** | otherwise | Specify → Plan → Act → Review → Vault |
### Context Acquisition (Optional)
Before Specify scoring:
1. Check `.sparv/kb.md` for existing patterns/decisions
2. If insufficient, scan codebase for relevant files
3. Document findings in journal under `## Context`
### Knowledge Base Maintenance
During Vault phase, update `.sparv/kb.md`:
- **Patterns**: Reusable code patterns discovered
- **Decisions**: Architectural choices + rationale
- **Gotchas**: Common pitfalls + solutions
### CHANGELOG Update
```bash
~/.claude/skills/sparv/scripts/changelog-update.sh --type <Added|Changed|Fixed|Removed> --desc "..."
```
## Specify (10-Point Scale)
Each item scores 0/1/2, total 0-10; `>=9` required to enter Plan:

View File

@@ -0,0 +1,112 @@
#!/bin/bash
# SPARV Changelog Update Script
# Adds entries to .sparv/CHANGELOG.md under [Unreleased] section
set -e
usage() {
cat <<'EOF'
Usage: changelog-update.sh --type <TYPE> --desc "description" [--file PATH]
Adds a changelog entry under [Unreleased] section.
Options:
--type TYPE Change type: Added|Changed|Fixed|Removed
--desc DESC Description of the change
--file PATH Custom changelog path (default: .sparv/CHANGELOG.md)
Examples:
changelog-update.sh --type Added --desc "User authentication module"
changelog-update.sh --type Fixed --desc "Login timeout issue"
EOF
}
CHANGELOG=".sparv/CHANGELOG.md"
TYPE=""
DESC=""
while [ $# -gt 0 ]; do
case "$1" in
-h|--help) usage; exit 0 ;;
--type) TYPE="$2"; shift 2 ;;
--desc) DESC="$2"; shift 2 ;;
--file) CHANGELOG="$2"; shift 2 ;;
*) usage >&2; exit 1 ;;
esac
done
# Validate inputs
if [ -z "$TYPE" ] || [ -z "$DESC" ]; then
echo "❌ Error: --type and --desc are required" >&2
usage >&2
exit 1
fi
# Validate type
case "$TYPE" in
Added|Changed|Fixed|Removed) ;;
*)
echo "❌ Error: Invalid type '$TYPE'. Must be: Added|Changed|Fixed|Removed" >&2
exit 1
;;
esac
# Check changelog exists
if [ ! -f "$CHANGELOG" ]; then
echo "❌ Error: Changelog not found: $CHANGELOG" >&2
echo " Run init-session.sh first to create it." >&2
exit 1
fi
# Check if [Unreleased] section exists
if ! grep -q "## \[Unreleased\]" "$CHANGELOG"; then
echo "❌ Error: [Unreleased] section not found in $CHANGELOG" >&2
exit 1
fi
# Check if the type section already exists under [Unreleased]
# We need to insert after [Unreleased] but before the next ## section
TEMP_FILE=$(mktemp)
trap "rm -f $TEMP_FILE" EXIT
# Find if ### $TYPE exists between [Unreleased] and next ## section
IN_UNRELEASED=0
TYPE_FOUND=0
TYPE_LINE=0
UNRELEASED_LINE=0
NEXT_SECTION_LINE=0
line_num=0
while IFS= read -r line; do
((line_num++))
if [[ "$line" =~ ^##[[:space:]]\[Unreleased\] ]]; then
IN_UNRELEASED=1
UNRELEASED_LINE=$line_num
elif [[ $IN_UNRELEASED -eq 1 && "$line" =~ ^##[[:space:]] && ! "$line" =~ ^###[[:space:]] ]]; then
NEXT_SECTION_LINE=$line_num
break
elif [[ $IN_UNRELEASED -eq 1 && "$line" =~ ^###[[:space:]]$TYPE ]]; then
TYPE_FOUND=1
TYPE_LINE=$line_num
fi
done < "$CHANGELOG"
if [ $TYPE_FOUND -eq 1 ]; then
# Append under existing ### $TYPE section
awk -v type_line="$TYPE_LINE" -v desc="$DESC" '
NR == type_line { print; getline; print; print "- " desc; next }
{ print }
' "$CHANGELOG" > "$TEMP_FILE"
else
# Create new ### $TYPE section after [Unreleased]
awk -v unreleased_line="$UNRELEASED_LINE" -v type="$TYPE" -v desc="$DESC" '
NR == unreleased_line { print; print ""; print "### " type; print "- " desc; next }
{ print }
' "$CHANGELOG" > "$TEMP_FILE"
fi
mv "$TEMP_FILE" "$CHANGELOG"
echo "✅ Added to $CHANGELOG:"
echo " ### $TYPE"
echo " - $DESC"

View File

@@ -137,6 +137,35 @@ Format based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
EOF
}
# Initialize kb.md (knowledge base) if not exists
init_kb() {
local kb_file="$SPARV_ROOT/kb.md"
[ -f "$kb_file" ] && return 0
cat > "$kb_file" << 'EOF'
# Knowledge Base
Cross-session knowledge accumulated during SPARV workflows.
---
## Patterns
<!-- Reusable code patterns discovered -->
## Decisions
<!-- Architectural choices + rationale -->
<!-- Format: - [YYYY-MM-DD]: decision | rationale -->
## Gotchas
<!-- Common pitfalls + solutions -->
<!-- Format: - [issue]: cause | solution -->
EOF
}
# Check for active session
active_session="$(find_active_session)"
@@ -162,6 +191,7 @@ mkdir -p "$HISTORY_DIR"
# Initialize global files
init_history_index
init_changelog
init_kb
# Create state.yaml
cat > "$SESSION_DIR/state.yaml" << EOF