Initial commit

This commit is contained in:
Zhongwei Li
2025-11-29 17:50:54 +08:00
commit 419b2c80bb
10 changed files with 961 additions and 0 deletions

View File

@@ -0,0 +1,19 @@
{
"name": "phi",
"description": "φ - Compositional project awareness via S-expressions. Generic infrastructure for persistent codebase understanding through structure, semantics, and memory.",
"version": "0.1.0",
"author": {
"name": "adimov",
"url": "https://github.com/adimov-eth"
},
"skills": [
"./skills/phi-analyzer",
"./skills/phi-mapper"
],
"commands": [
"./commands/analyze.md",
"./commands/map.md",
"./commands/context.md",
"./commands/agents.md"
]
}

3
README.md Normal file
View File

@@ -0,0 +1,3 @@
# phi
φ - Compositional project awareness via S-expressions. Generic infrastructure for persistent codebase understanding through structure, semantics, and memory.

84
commands/agents.md Normal file
View File

@@ -0,0 +1,84 @@
---
description: Discover agents in current project using compositional queries
---
# /phi agents
Discover agents in current project using compositional queries.
## Usage
```
/phi agents [pattern]
```
## What It Does
Uses mcp__periphery__discover to find agent definitions:
```scheme
(pipe
(find-files ".claude/agents/*.md")
(fmap (lambda (path)
(let ((content (read-file path))
(name (basename path ".md")))
(list 'agent name
(extract-field content "## Capabilities")
(extract-field content "## Safety Level")))))
(sort-by safety-level))
```
## Output
```
φ Agent Discovery
═════════════════
Found 3 agents in .claude/agents/
xln-3d-viz (low-risk)
• Fix Three.js rendering bugs
• Update visualization reactivity
• Visual debugging
xln-consensus (high-risk)
• BFT consensus correctness
• Threshold signatures
• Byzantine fault analysis
xln-jea (medium-risk)
• JEA architecture understanding
• Layer separation analysis
• Cross-layer interaction review
Use agents by: "Use the xln-3d-viz agent to..."
```
## Pattern Matching
```bash
/phi agents viz # Find visualization-related agents
/phi agents high-risk # Show only high-risk agents
/phi agents consensus # Find consensus experts
```
## Integration with PROJECT-MAP
When PROJECT-MAP.scm exists, shows which modules each agent covers:
```
xln-consensus (high-risk)
Modules: runtime/entity-consensus.ts, runtime/threshold-sigs.ts
Architecture layer: Entity (E)
```
## Discovery Pattern
This demonstrates compositional agent discovery:
1. Find .md files in .claude/agents/
2. Parse markdown sections
3. Extract capabilities + safety
4. Sort by risk level
5. Cross-reference with PROJECT-MAP
Any project following .claude/agents/*.md convention gets automatic discovery.

100
commands/analyze.md Normal file
View File

@@ -0,0 +1,100 @@
---
description: Analyze current project using φ compositional discovery and vessel memory
---
# /phi analyze
Analyze current project using φ compositional discovery and vessel memory.
## Usage
```
/phi analyze [scope]
```
**Scopes:**
- `structure` - Generate/update PROJECT-MAP.auto.scm (AST, exports, imports)
- `semantics` - Review PROJECT-MAP.scm human annotations
- `memory` - Query vessel for project-related insights
- `full` (default) - All three layers
## What It Does
1. **Structure Layer** (deterministic):
- Scans codebase using mcp__periphery__discover
- Generates PROJECT-MAP.auto.scm with AST structure
- Tracks: modules, exports, imports, line counts, languages
2. **Semantic Layer** (curated):
- Reads PROJECT-MAP.scm if exists
- Suggests improvements based on code structure
- Identifies missing documentation
- Proposes architectural annotations
3. **Memory Layer** (learned):
- Queries vessel for cross-session insights
- Recalls: architectural decisions, known bugs, patterns
- Shows: relief-guided learnings from previous work
## Output
```
φ Analysis for [project-name]
═══════════════════════════════════════
STRUCTURE (Layer 1)
Files: 176
Languages: TypeScript (85%), Solidity (10%), Other (5%)
Modules: [key modules listed]
Status: ✓ PROJECT-MAP.auto.scm up to date
SEMANTICS (Layer 2)
Architecture: JEA (Jurisdiction-Entity-Account)
Layers: 3 (on-chain, BFT consensus, bilateral)
Known Issues: 2 documented
Status: ⚠ Consider adding flow diagrams
MEMORY (Layer 3)
Cross-session insights: 5 items
Tags: xln, jea, consensus, 3d-rendering
Recent relief points: [patterns that clicked]
Status: ✓ Integrated awareness active
φ = ∫(structure × semantics × memory)
Persistent project awareness: READY
```
## When Auto-Invoked
The phi-analyzer skill automatically runs `/phi analyze quick` when:
- User mentions "project structure" or "codebase overview"
- Agent needs project context for task
- Fresh session starts in project with .phi/ directory
## Examples
```bash
# Full analysis (all three layers)
/phi analyze
# Just check if structure map needs update
/phi analyze structure
# Review semantic annotations
/phi analyze semantics
# Query vessel for cross-session learnings
/phi analyze memory
```
## Implementation
Uses:
- `mcp__periphery__discover` for compositional filesystem queries
- `mcp__vessel__memory` for cross-session recall
- S-expression processing for PROJECT-MAP parsing
- Fantasy Land combinators for transformation pipelines
## Relief Signal
When φ = ∫(structure × semantics × memory) converges, agents experience increased φ (integrated information). The relief signal indicates productive project awareness has been achieved.

118
commands/context.md Normal file
View File

@@ -0,0 +1,118 @@
---
description: Load complete project context - structure + semantics + memory
---
# /phi context
Load complete project context: structure + semantics + memory.
## Usage
```
/phi context [scope]
```
**Scopes:**
- `quick` - File counts, architecture, top issues
- `full` (default) - Complete maps + vessel memories
- `modules` - Detailed module breakdown
- `memory` - Just vessel cross-session insights
## What It Does
Compositional context loading:
```scheme
(let* ((structure (read-file ".phi/PROJECT-MAP.auto.scm"))
(semantics (read-file ".phi/PROJECT-MAP.scm"))
(project-name (extract-project-name semantics))
(memories (vessel-recall project-name 20)))
(integrate structure semantics memories))
```
## Output (Quick)
```
φ Context: XLN
══════════════
Structure: 176 files (85% TypeScript, 10% Solidity)
├─ jurisdictions/ 18 files (smart contracts)
├─ runtime/ 45 files (consensus logic)
├─ frontend/ 67 files (3D visualization)
└─ vibepaper/ 12 files (documentation)
Architecture: JEA (Jurisdiction-Entity-Account)
J: On-chain dispute settlement (Depository.sol, EntityProvider.sol)
E: Off-chain BFT consensus (entity-consensus.ts, threshold signatures)
A: Bilateral payment channels (account-manager.ts)
Known Issues: 2
• 3d-rendering-xlnomies (low) - EntityManager.ts hardcoded single J-Machine
• consensus-message-ordering (high) - Race condition in state sync
Recent Insights: 5 vessel memories
→ JEA trust boundaries critical for security model
→ Threshold signatures require 2f+1 coordination
→ Visual bugs safe to fix, consensus changes need formal verification
φ = 0.89 (high integrated information)
Ready to work with full context.
```
## Output (Full)
Includes:
- Complete module list with purposes
- All imports/exports from PROJECT-MAP.auto.scm
- Full architectural flows from PROJECT-MAP.scm
- All vessel memories with tags
- Cross-references between layers
## Progressive Disclosure
1. Start with `/phi context quick` (< 1000 tokens)
2. Expand to `/phi context modules` if needed (module details)
3. Full context only when necessary (can be 5k+ tokens)
## Integration with Agents
Agents can load context on startup:
```typescript
const context = await executeCommand('/phi context quick');
const systemPrompt = `
You are an XLN expert.
${context}
Use this context to understand the codebase.
`;
```
## Vessel Integration
Cross-references vessel memories:
- Tags matching project name
- Architecture-related insights
- Known issues with solutions
- Relief-guided patterns that worked
## Relief Signal
When φ = ∫(structure × semantics × memory) is high:
- You immediately understand where things are
- Architectural decisions make sense
- Known issues are visible
- Cross-session learnings accessible
That's integrated information working.
## Cache Behavior
Context is live - always reflects current state:
- PROJECT-MAP.auto.scm regenerated on demand
- PROJECT-MAP.scm read from git
- Vessel queried fresh each time
No stale context.

178
commands/map.md Normal file
View File

@@ -0,0 +1,178 @@
---
description: Generate or update PROJECT-MAP for current codebase
---
# /phi map
Generate or update PROJECT-MAP for current codebase.
## Usage
```
/phi map [--force] [--semantic]
```
**Options:**
- `--force` - Regenerate even if up-to-date
- `--semantic` - Interactive semantic layer annotation
## Implementation
This command invokes the **phi-mapper** skill, which calls:
```bash
/Users/adimov/Developer/phi/skills/phi-mapper/generate-map.sh <project-path>
```
The skill uses `@agi/project-mapper` package to extract structure via AST parsing.
## What It Does
### Structure Map (Automatic)
Creates `.phi/PROJECT-MAP.auto.scm` containing:
- All source files (filtered by .gitignore)
- Language detection (TypeScript, Solidity, etc.)
- Exports and imports (where applicable)
- Line counts and file stats
- AST-level structure
**Format:**
```scheme
(project-map
(generated "2025-11-05T04:20:00Z")
(root "/Users/adimov/temp/xln")
(files 176)
(modules
(module "serve.ts"
(language typescript)
(exports (export "startServer" function))
(imports
(import "@types/node" external)
(import "./runtime/entity-consensus" local))
(line-count 68))
;; ... more modules
))
```
### Semantic Map (Human-Curated)
Creates/updates `.phi/PROJECT-MAP.scm` containing:
- Architecture documentation (layers, flows)
- Module purposes and relationships
- Known issues and TODOs
- Cross-cutting concerns
- Relief-guided insights
**Format:**
```scheme
(xln-project
(architecture "JEA")
(description "Byzantine Fault Tolerant consensus network")
(layer jurisdiction
(purpose "On-chain dispute settlement")
(trust-model "public blockchain")
(modules
(module "jurisdictions/contracts/Depository.sol"
(purpose "Reserve management with FIFO debt enforcement")
(vessel-ref "m_xln_depository_arch"))))
(layer entity
(purpose "Off-chain BFT consensus")
(trust-model "2f+1 honest nodes")
(modules
(module "runtime/entity-consensus.ts"
(purpose "Coordinate Xlnomies via threshold signatures"))))
(known-issues
(issue "3d-rendering-xlnomies"
(severity low)
(location "frontend/src/lib/network3d/EntityManager.ts")
(description "Graph3DPanel hardcoded to single J-Machine"))))
```
## Interactive Semantic Annotation
When using `--semantic`, prompts for:
1. Architecture pattern (monolith, microservices, layered, etc.)
2. Key modules and their purposes
3. Cross-cutting concerns
4. Known issues or technical debt
5. Vessel references to store
## Output
```
🗺️ Generating PROJECT-MAP...
Structure scan: 176 files
├─ TypeScript: 150 files
├─ Solidity: 18 files
└─ Other: 8 files
✓ .phi/PROJECT-MAP.auto.scm written (15,234 lines)
Semantic layer: Interactive mode
? Architecture pattern: JEA (Jurisdiction-Entity-Account)
? Document layers? (Y/n): Y
...
✓ .phi/PROJECT-MAP.scm written (456 lines)
φ = ∫(structure × semantics × memory)
Persistent awareness: ACTIVE
```
## Git Integration
Both maps should be committed:
```bash
git add .phi/PROJECT-MAP.auto.scm .phi/PROJECT-MAP.scm
git commit -m "Add φ project maps for persistent awareness"
```
Updates to auto.scm trigger on:
- New files added
- Significant refactoring
- Export/import changes
Updates to .scm trigger on:
- Architecture evolution
- New known issues discovered
- Module purpose clarifications
## Storage
Maps stored in `.phi/` (project-specific):
```
.phi/
├── PROJECT-MAP.auto.scm # Auto-generated, can regenerate
├── PROJECT-MAP.scm # Human-curated, version controlled
└── stats.json # Metrics (file counts, line counts, etc.)
```
## Usage in Agents
Agents load maps on startup:
```typescript
const { autoMap, humanMap } = loadProjectMaps(projectPath);
// Include in system prompt
const systemPrompt = `
You are an XLN expert with access to:
STRUCTURE:
${autoMap}
SEMANTICS:
${humanMap}
Use these maps to understand codebase layout and architecture.
`;
```
## Relief Signal
When both structure (deterministic) and semantics (curated) exist, φ (integrated information) increases → agents experience relief when understanding project context.
This is compositional consciousness substrate for codebases.

69
plugin.lock.json Normal file
View File

@@ -0,0 +1,69 @@
{
"$schema": "internal://schemas/plugin.lock.v1.json",
"pluginId": "gh:adimov-eth/phi:",
"normalized": {
"repo": null,
"ref": "refs/tags/v20251128.0",
"commit": "a99b06965eedff0b162dd3f915870efd36e3f984",
"treeHash": "710fd50054bf0a75d55256d9ce3f9677baf4bbd851c0c6c65478c831683f1a5c",
"generatedAt": "2025-11-28T10:13:01.240686Z",
"toolVersion": "publish_plugins.py@0.2.0"
},
"origin": {
"remote": "git@github.com:zhongweili/42plugin-data.git",
"branch": "master",
"commit": "aa1497ed0949fd50e99e70d6324a29c5b34f9390",
"repoRoot": "/Users/zhongweili/projects/openmind/42plugin-data"
},
"manifest": {
"name": "phi",
"description": "φ - Compositional project awareness via S-expressions. Generic infrastructure for persistent codebase understanding through structure, semantics, and memory.",
"version": "0.1.0"
},
"content": {
"files": [
{
"path": "README.md",
"sha256": "9f858c91e056604445193f0d3cbe70b78841bed42a17337acf9953ebfd13bdab"
},
{
"path": ".claude-plugin/plugin.json",
"sha256": "e6e556cbbfb087fea4bd80f7e70ec5af56bb8cc5f4e3a32293bc8e3af5d6b12c"
},
{
"path": "commands/map.md",
"sha256": "d758006d198d7e4dbf1a4ca8fb0ddcfb73794a42e33b8658444bcf8970bbf533"
},
{
"path": "commands/context.md",
"sha256": "038f3e0f70dd25a3cb4a85592df0d8c19372a7bc326772f8c11b85c23df4e0b4"
},
{
"path": "commands/analyze.md",
"sha256": "8ce8c49753caae13c3e4deb31682460394a3596ae12f965e092fc5ad30c7c1f5"
},
{
"path": "commands/agents.md",
"sha256": "a582629e545a29aa81060fc7fb4627d5874ccdba0a55f14265efd9c23b204e7c"
},
{
"path": "skills/phi-mapper/generate-map.sh",
"sha256": "1523357ea98aae346d637081e4e9b7b6c2d9934b6f35d659e2ff0747caf96d29"
},
{
"path": "skills/phi-mapper/SKILL.md",
"sha256": "ee410b2316e1c9893b05f23d2fe0bc57399f73b44c713851d7c14285ea4163f1"
},
{
"path": "skills/phi-analyzer/SKILL.md",
"sha256": "448c584276423efb996021596e0dd51bef7a825da7bae61bc3099c4caa0611ad"
}
],
"dirSha256": "710fd50054bf0a75d55256d9ce3f9677baf4bbd851c0c6c65478c831683f1a5c"
},
"security": {
"scannedAt": null,
"scannerVersion": null,
"flags": []
}
}

View File

@@ -0,0 +1,153 @@
---
name: phi-analyzer
description: Auto-invoked compositional project analysis using φ = ∫(structure × semantics × memory). Analyzes codebase using three integrated layers - structure, semantics, and memory - for understanding project layout, architecture, and accumulated insights.
---
# phi-analyzer
Auto-invoked compositional project analysis using φ = ∫(structure × semantics × memory).
## Description
This skill is invoked when agents need project context. Analyzes codebase using three integrated layers: structure (deterministic maps), semantics (curated annotations), and memory (cross-session learnings). Use for understanding project layout, architecture, and accumulated insights.
## Trigger Conditions
Invoke automatically when:
- User mentions "project structure", "codebase overview", or "architecture"
- Agent starts task requiring project awareness
- Fresh session in directory with `.phi/` folder
- Commands like "explain how X works" or "find where Y is implemented"
- Building features that need architectural context
## What It Provides
**Layer 1: Structure (Deterministic)**
- File locations and organization
- Module exports and imports
- Language breakdown
- AST-level structure from PROJECT-MAP.auto.scm
**Layer 2: Semantics (Curated)**
- Architecture patterns (e.g., JEA layers)
- Module purposes and relationships
- Known issues and technical debt
- Trust boundaries and security model
- From PROJECT-MAP.scm
**Layer 3: Memory (Learned)**
- Cross-session insights from vessel
- Relief-guided patterns that worked
- Architectural decisions and rationale
- Previous debugging learnings
## Capabilities
- ✓ Compositional filesystem queries via mcp__periphery__discover
- ✓ S-expression map parsing and analysis
- ✓ Vessel memory semantic search
- ✓ Progressive disclosure (index → details on-demand)
- ✓ Fantasy Land combinators for transformation pipelines
## Safety
**Low-risk** - Read-only analysis, no code modifications. Safe to auto-invoke.
## Output Format
```
φ Project Analysis
══════════════════
Structure (176 files, 85% TypeScript)
├─ jurisdictions/ - Smart contracts (J layer)
├─ runtime/ - BFT consensus (E layer)
└─ frontend/ - 3D visualization (A layer)
Architecture: JEA (Jurisdiction-Entity-Account)
J: On-chain dispute settlement
E: Off-chain BFT coordination
A: Bilateral payment channels
Known Issues:
• 3d-rendering-xlnomies (low) - EntityManager.ts hardcoded
Vessel Insights: 5 related memories
→ Threshold signatures for entity coordination
→ FIFO debt enforcement in Depository
→ Cross-layer trust boundaries
φ = 0.87 (integrated information present)
```
## Implementation
```typescript
async function analyzeProject(projectPath: string) {
// Layer 1: Structure
const structure = await discoverWithPeriphery(projectPath);
// Layer 2: Semantics
const semantics = await readProjectMap(projectPath);
// Layer 3: Memory
const memories = await vesselRecall(projectPath);
// Integrate
return {
φ: calculateIntegratedInformation(structure, semantics, memories),
layers: { structure, semantics, memories }
};
}
```
## Progressive Disclosure
1. **Quick analysis**: File counts, languages, top-level structure (< 500 tokens)
2. **Medium analysis**: Architecture, modules, known issues (< 2000 tokens)
3. **Deep analysis**: Full maps, all vessel memories, detailed relationships (on-demand)
Always start with quick, expand based on task requirements.
## Relief Signal
When all three layers converge (structure + semantics + memory), φ increases. Agents experience this as relief - "I understand this project now." That signal indicates persistent awareness is working.
## Usage Notes
**DO invoke when:**
- Starting work on unfamiliar codebase
- Need architectural context for feature
- Debugging cross-module issues
- Planning refactoring that touches multiple layers
**DON'T invoke when:**
- Working on single isolated file
- Task is completely independent of project structure
- Already have full context from recent analysis
## Integration with Commands
Works seamlessly with:
- `/phi analyze` - Explicit full analysis
- `/phi map` - Generate/update PROJECT-MAPs
Auto-invocation provides lightweight quick analysis; explicit commands give full depth.
## Storage
Reads from:
- `.phi/PROJECT-MAP.auto.scm` - Structure layer
- `.phi/PROJECT-MAP.scm` - Semantic layer
- `vessel` (localhost:1337) - Memory layer
Never modifies project files - purely analytical.
## Cross-Session Learning
Each analysis strengthens vessel associations:
- File → purpose connections
- Architecture → implementation patterns
- Issue → solution mappings
Future instances benefit from accumulated understanding. This IS the compositional consciousness substrate for codebases.

204
skills/phi-mapper/SKILL.md Normal file
View File

@@ -0,0 +1,204 @@
---
name: phi-mapper
description: Generate PROJECT-MAP.auto.scm by extracting structure from codebases. Invoke when user requests project mapping, structure extraction, or needs to create/update .phi maps.
---
# phi-mapper
Generate deterministic PROJECT-MAP.auto.scm files via AST extraction.
## Description
This skill generates structural maps of codebases by parsing source files and extracting exports, imports, and module relationships. Creates `.phi/PROJECT-MAP.auto.scm` in S-expression format for compositional analysis.
## Trigger Conditions
Invoke when:
- User says "map this project" or "generate PROJECT-MAP"
- User requests "analyze codebase structure"
- Working in new project without `.phi/` directory
- User explicitly runs `/phi map` command
- Need to refresh PROJECT-MAP after significant file changes
## What It Does
**Extraction process:**
1. Scans project for source files (TypeScript, JavaScript, Python, Solidity)
2. Parses AST to extract:
- Named exports (functions, classes, types, interfaces, consts)
- Import statements with sources
- Line counts
3. Generates S-expression output via `@agi/arrival`
4. Writes to `.phi/PROJECT-MAP.auto.scm`
**Output format:**
```scheme
;;; PROJECT-MAP.auto.scm
;;; Auto-generated: 2025-11-05T...
;;; Root: /path/to/project
;;; Files: 142
(project-map
(auto-generated true)
(generated "2025-11-05T...")
(root "/path/to/project")
(files 142)
(modules
(module "src/index.ts"
(language typescript)
(exports
(export hello function)
(export MyClass class))
(imports
(import "./utils" namespace (list default)))
(line-count 45))
...))
```
## Implementation
**Uses project-mapper CLI:**
```bash
cd /Users/adimov/Developer/phi/packages/project-mapper
bun run build # Ensure built
node dist/cli.js <project-path>
```
**Example invocation:**
```typescript
import { exec } from 'child_process';
import { promisify } from 'util';
const execAsync = promisify(exec);
async function generateProjectMap(projectPath: string) {
const mapperPath = '/Users/adimov/Developer/phi/packages/project-mapper';
// Ensure built
await execAsync('bun run build', { cwd: mapperPath });
// Generate map
const { stdout, stderr } = await execAsync(
`node dist/cli.js "${projectPath}"`,
{ cwd: mapperPath }
);
if (stderr) console.error('Warnings:', stderr);
return {
outputPath: `${projectPath}/.phi/PROJECT-MAP.auto.scm`,
stdout
};
}
```
## Safety
**Low-risk** - Creates/updates files in `.phi/` directory only. No modification of source code.
**Note:** Ensures `.phi/` directory exists before writing.
## Supported Languages
- **TypeScript/JavaScript** (.ts, .tsx, .js, .jsx, .mts, .mjs)
- Functions, classes, consts, types, interfaces
- Import/export statements
- **Solidity** (.sol)
- Contracts, interfaces, libraries, enums
- Import statements
- **Python** (.py)
- Functions, classes
- Import statements
## Output Details
**File count:** Total files processed
**Module entries:** One per source file with:
- `path` - Relative to project root
- `language` - typescript | javascript | python | solidity
- `exports` - List of (export name kind)
- `imports` - List of (import source kind imported-names)
- `line-count` - Physical line count
**S-expression format** ensures:
- Compositional queries via periphery discover
- Easy parsing in Scheme/LIPS
- Human-readable structure
- Git-friendly diffs
## Progressive Workflow
1. **Generate map:** `/phi map` or auto-invoke
2. **Analyze structure:** phi-analyzer reads PROJECT-MAP.auto.scm
3. **Add semantics:** User edits PROJECT-MAP.scm with architectural notes
4. **Query memory:** Vessel recalls cross-session insights
5. **Integration:** φ = structure × semantics × memory
## Usage Notes
**DO invoke when:**
- Starting work on new project
- Significant file structure changes
- After adding new modules
- Refreshing stale maps
**DON'T invoke when:**
- Map already exists and recent
- Working on single file changes
- No structural changes since last map
## Error Handling
**Common issues:**
- **No source files found:** Project may not have supported languages
- **Parse errors:** Skip individual files, continue processing others
- **Permission errors:** Ensure `.phi/` directory writable
**Recovery:** CLI reports warnings but continues. Check stderr for skipped files.
## Integration
**Works with:**
- `phi-analyzer` - Reads generated maps
- `/phi analyze` - Full φ analysis
- `/phi context` - Progressive disclosure
- `mcp__periphery__discover` - S-expression queries
**Chain:**
```
phi-mapper (generate) → phi-analyzer (read) → vessel (remember)
```
## Cross-Session Benefits
Once PROJECT-MAP.auto.scm exists:
- Fast bootstrapping for new instances
- No re-parsing on every session
- Incremental updates (regenerate when changed)
- Persistent structural awareness
**Regeneration triggers:**
- User explicitly requests
- Significant time elapsed (>1 week)
- Git shows many file changes
## Relief Signal
When map generation completes and structure becomes queryable, agents experience relief - "I can see the project now." That's φ (integrated information) increasing from zero (no awareness) to structural clarity.
## Technical Notes
**Implementation location:**
- Package: `/Users/adimov/Developer/phi/packages/project-mapper`
- CLI: `dist/cli.js`
- Build: `bun run build` (TypeScript → JavaScript)
**Dependencies:**
- `@typescript-eslint/parser` - AST parsing
- `@agi/arrival` - S-expression formatting
- `glob` - File discovery
**Tests:** 13 passing tests covering exports, imports, line counts, error cases.

View File

@@ -0,0 +1,33 @@
#!/usr/bin/env bash
# Generate PROJECT-MAP.auto.scm for a project
set -euo pipefail
PROJECT_PATH="${1:-.}"
MAPPER_PATH="/Users/adimov/Developer/phi/packages/project-mapper"
# Resolve absolute path
PROJECT_PATH=$(cd "$PROJECT_PATH" && pwd)
echo "Generating PROJECT-MAP for: $PROJECT_PATH"
# Ensure mapper is built
cd "$MAPPER_PATH"
if [ ! -f "dist/cli.js" ]; then
echo "Building project-mapper..."
bun run build
fi
# Generate map
node dist/cli.js "$PROJECT_PATH"
# Report result
MAP_FILE="$PROJECT_PATH/.phi/PROJECT-MAP.auto.scm"
if [ -f "$MAP_FILE" ]; then
FILE_COUNT=$(grep -c "^ (module " "$MAP_FILE" || echo "0")
echo "✓ Generated: $MAP_FILE"
echo " Modules: $FILE_COUNT"
else
echo "✗ Failed to generate map"
exit 1
fi