Code Intelligence

Code Intelligence (Codegraph)

CortexPrism's code intelligence system provides deep structural understanding of codebases using tree-sitter WASM parsing with FTS5-backed full-text search over a graph database of code symbols and their relationships.

Architecture

┌──────────────────────────────────────────────────────────────┐
│                    Code Intelligence                          │
│                                                               │
│  tree-sitter WASM (14+ languages)                             │
│          │                                                    │
│          ▼                                                    │
│  ┌──────────────────────────────────────┐                    │
│  │          AST Extraction               │                    │
│  │  - Functions, classes, interfaces     │                    │
│  │  - Imports, exports, calls            │                    │
│  │  - Decorators, HTTP calls, async      │                    │
│  │  - Complexity estimation              │                    │
│  └──────────────────────────────────────┘                    │
│          │                                                    │
│          ▼                                                    │
│  ┌──────────────────────────────────────┐                    │
│  │        Code Graph (memory.db)         │                    │
│  │  - 14 node labels (CodeFunction,      │                    │
│  │    CodeClass, CodeInterface, etc.)     │                    │
│  │  - 18 edge types (CALLS, IMPORTS,     │                    │
│  │    DEFINES, IMPLEMENTS, INHERITS)      │                    │
│  │  - FTS5 full-text search              │                    │
│  └──────────────────────────────────────┘                    │
│          │                                                    │
│          ▼                                                    │
│  ┌──────────────────────────────────────┐                    │
│  │        Codegraph Resolver             │                    │
│  │  - Exact symbol match                 │                    │
│  │  - Method on class resolution         │                    │
│  │  - Wildcard/relative import           │                    │
│  │  - Type inference                     │                    │
│  │  - Fallback search                    │                    │
│  └──────────────────────────────────────┘                    │
│          │                                                    │
│          ▼                                                    │
│  ┌──────────────────────────────────────┐                    │
│  │           6 Agent Tools               │                    │
│  │  code_index    code_search_symbol     │                    │
│  │  code_trace_path  code_get_architecture│                   │
│  │  code_analyze_impact  code_list_projects│                  │
│  └──────────────────────────────────────┘                    │
│                                                               │
│  Web UI: D3.js force-directed graph                           │
│  ┌──────────────────────────────────────┐                    │
│  │  - Interactive dependency graph       │                    │
│  │  - Symbol search with FTS5            │                    │
│  │  - Impact analysis (blast radius)     │                    │
│  │  - Path tracer (caller ↔ callee)      │                    │
│  └──────────────────────────────────────┘                    │
└──────────────────────────────────────────────────────────────┘

Supported Languages

Tree-sitter WASM parsers with lazy-loading from CDN:

Language	File Extensions	Parser
TypeScript	.ts, .tsx	tree-sitter-typescript
JavaScript	.js, .jsx	tree-sitter-javascript
Python	.py	tree-sitter-python
Go	.go	tree-sitter-go
Rust	.rs	tree-sitter-rust
Java	.java	tree-sitter-java
Kotlin	.kt	tree-sitter-kotlin
C	.c, .h	tree-sitter-c
C++	.cpp, .hpp	tree-sitter-cpp
Ruby	.rb	tree-sitter-ruby
PHP	.php	tree-sitter-php
Swift	.swift	tree-sitter-swift
Lua	.lua	tree-sitter-lua
Bash	.sh, .bash	tree-sitter-bash

Node Labels (14)

CodeProject, CodeFile, CodeFunction, CodeClass, CodeInterface, CodeEnum, CodeType, CodeVariable, CodeConstant, CodeModule, CodeDecorator, CodeEndpoint, CodeDatabaseQuery, CodeTest

Edge Types (18)

CALLS, IMPORTS, DEFINES, IMPLEMENTS, INHERITS, HTTP_CALLS, ASYNC_CALLS, DECORATES, EXPORTS, REFERENCES, RETURNS, PARAMETER_OF, THROWS, TESTS, MOCKS, CONFIGURES, MIGRATES, DEPENDS_ON

Ingestion Pipeline

Indexing (code_index)

code_index(projectPath)
  1. Directory walk (max 200K files, depth 100)
  2. File hash comparison (skip unchanged)
  3. Language detection by extension
  4. WASM parser validation (integrity check)
  5. AST extraction per file
  6. Chunked bulk insert (BFS-batched: 2 queries/level instead of N+1)
  7. FTS5 index refresh

Resolver (6 strategies)

1. Exact symbol match — direct name lookup
2. Method on class — resolve ClassName.methodName
3. Wildcard import — expand import * as X references
4. Relative import path — resolve ./path/to/module
5. Type inference — follow type declarations to methods
6. Fallback search — FTS5 full-text lookup

Agent Tools

code_index

Full repository indexing with incremental sync.

Parameter	Type	Description
projectPath	string	Root directory to index
projectName	string	Optional project identifier
force	boolean	Re-index all files (skip hash check)

code_search_symbol

FTS5-backed symbol search across projects.

Parameter	Type	Description
query	string	Symbol name to search
project	string	Optional project filter
kind	string	Optional node label filter
limit	number	Max results (default 20)

code_trace_path

Bidirectional call graph traversal.

Parameter	Type	Description
symbolId	string	Starting symbol node ID
direction	string	"inbound", "outbound", or "both"
maxDepth	number	Maximum traversal depth (default 5)

code_get_architecture

System architecture diagram extraction.

Parameter	Type	Description
project	string	Project name

Returns layers, modules, and dependency structure.

code_analyze_impact

Blast radius analysis for a symbol.

Parameter	Type	Description
symbolId	string	Target symbol node ID

Returns direct/indirect callers, callees, dead code detection, and complexity metrics.

code_list_projects

Project registry with language statistics.

Returns per-project node counts, edge counts, language breakdowns, and last-indexed timestamps.

Web UI (Codegraph Page)

• D3.js force-directed graph — interactive zoomable dependency visualization
• Symbol search — FTS5-powered search with type filters
• Impact analysis — click a node to see blast radius (callers + callees)
• Path tracer — trace calls between any two symbols
• Hotspot detection — identify high-complexity nodes

API Endpoints

Method	Path	Description
GET	/api/codegraph/projects	List indexed projects
POST	/api/codegraph/index	Start code indexing
GET	/api/codegraph/search?q=&project=	Search symbols
POST	/api/codegraph/impact	Impact analysis
GET	/api/codegraph/architecture?project=	Architecture extraction
POST	/api/codegraph/trace	Path tracing

See Also

• Architecture — System overview
• Built-in Tools — Complete tool catalog
• Agent Loop — How tools integrate into agent turns

Cross-Repository Search (#74)

Search across all indexed projects simultaneously:

• GET /api/codegraph/search-all?q=&language= returns ranked cross-repo results
• Project name labels distinguish results from different repositories
• Codegraph web UI: 🌐 All repos button in the sidebar search panel

Language Filtering (#84)

• ftsSearchNodes() accepts optional language parameter
• getLanguages() returns distinct languages per project
• Language dropdown in the Codegraph sidebar filters search results

Code Ownership (#81)

• GET /api/codegraph/ownership?file= returns git blame author attribution
• Owners ranked by lines authored (name and email)

Codebase Archeologist (#229)

• GET /api/codegraph/history?file= returns recent commits via git log
• Hash, message context for each commit

Live Codebase Q&A (#239)

• GET /api/codegraph/qa?q=&project= returns symbol citations with provenance
• Citations include file, line, signature, and language context

Architecture Fitness (#238)

• GET /api/codegraph/fitness?project= runs naming conventions, circular dependency, and layer isolation checks

Codebase Pilot Config (#295)

• GET /api/codegraph/pilot-config returns token budget and pruning mode
• PUT /api/codegraph/pilot-config updates pilot settings

Alcove Private Documentation (#294)

• GET /api/alcove/search?q= performs semantic search over .cortex/data/docs/
• Returns snippets with surrounding context lines from markdown/text files