Cody: AI Code Assistant

Generates single-line and multi-function code completions by analyzing the current file context and broader codebase semantics. Cody indexes the full codebase to understand project structure, imports, and symbol definitions, enabling completions that respect local conventions and architecture patterns. Works across 40+ programming languages including Python, JavaScript, TypeScript, Go, Rust, Java, Kotlin, PHP, Swift, CSS, and HTML configuration files.

Enables multi-turn chat conversations about the codebase where users can ask questions about specific files, functions, classes, or entire architectural patterns. Cody retrieves relevant code context using semantic search or full-text indexing, then synthesizes answers by combining retrieved context with LLM reasoning. Supports both general programming questions and codebase-specific queries (e.g., 'How does the payment resolver work?' or 'Why is this function deprecated?').

Maintains a persistent index of the codebase (via Sourcegraph backend) that enables semantic search, symbol resolution, and context retrieval for all Cody features. The index tracks code structure (functions, classes, imports), relationships (dependencies, usages), and patterns (repeated code, architectural conventions). Search queries are resolved against this index to retrieve relevant code context, which is then passed to LLMs for reasoning. Indexing is automatic for Sourcegraph Enterprise deployments and happens in the background.

Provides enterprise administrators with controls over user access, model selection, and usage tracking. Admins can restrict which models are available to users, enforce code governance policies, and audit AI-assisted code changes. Cody integrates with Sourcegraph's enterprise authentication (SAML, OAuth, LDAP) and provides audit logs of all AI interactions for compliance and security monitoring. Usage analytics are available to track adoption and identify high-value use cases.

Analyzes code across 40+ programming languages using language-specific parsers and Abstract Syntax Tree (AST) analysis, enabling accurate understanding of code structure, semantics, and relationships. Rather than treating code as plain text, Cody parses code into ASTs to understand function signatures, type information, imports, and dependencies. This enables more accurate completions, refactorings, and context retrieval compared to regex-based or token-based approaches.

Detects user intent in natural language queries and automatically orchestrates a workflow combining codebase search, LLM reasoning, and code generation. When a user asks 'How do I add a new GraphQL resolver?', the system searches for existing resolvers, retrieves relevant patterns, synthesizes an explanation, and optionally generates boilerplate code. This is implemented as a unified interface where search results, AI reasoning, and generated code are presented together in a single chat context.

Generates unit tests for selected functions or classes by analyzing the implementation and learning test patterns from existing tests in the codebase. Cody retrieves similar test files, identifies testing conventions (assertion style, mock setup, test naming), and generates new tests that follow the same patterns. Supports multiple testing frameworks (Jest, pytest, JUnit, etc.) detected from project configuration.

Generates documentation (docstrings, README sections, API docs) by analyzing function signatures, implementations, and existing documentation patterns in the codebase. Cody extracts parameter types, return values, and side effects from code, then synthesizes documentation that matches the project's style (JSDoc, Sphinx, Javadoc, etc.). Supports generating function-level docs, module-level overviews, and API endpoint documentation.

Suggests and applies code refactorings (renaming, extracting functions, simplifying logic) by analyzing code patterns and understanding the broader codebase context. Cody identifies refactoring opportunities (e.g., 'this function is too long', 'this pattern is repeated 5 times'), proposes changes, and can apply them inline in the editor. Refactorings respect project conventions and avoid breaking dependent code by checking usage across the codebase.

Analyzes error messages, stack traces, and code context to diagnose root causes and suggest fixes. When a user pastes an error or selects code with a syntax/runtime error, Cody retrieves similar errors from the codebase history (if available), analyzes the implementation, and generates targeted fix suggestions. Supports multiple error types: syntax errors, type errors, runtime exceptions, and logic bugs.

Allows users to create, save, and reuse custom prompts that encode common development workflows (e.g., 'Generate a GraphQL resolver', 'Write a security audit', 'Refactor for performance'). Saved prompts are stored in a library accessible from the chat interface, and can include placeholders for dynamic context (selected code, file name, etc.). Prompts can be shared across teams (in enterprise deployments) to standardize AI-assisted workflows.

Allows individual users to select their preferred LLM from available options (Claude Sonnet 4, Gemini 1.5 Pro, Mixtral 8x7B, Claude 3 Opus, GPT-4o), with enterprise administrators able to restrict available models for compliance or cost control. Model selection is configurable per-user or per-organization, and can be changed on a per-chat or per-action basis. Supports both cloud-hosted models (OpenAI, Anthropic, Google) and self-hosted models (Ollama, local deployments).

Provides inline code editing capabilities where Cody can suggest edits directly in the editor and apply them with a single click. The 'Auto-edit' feature performs inline completions and refactorings without requiring copy-paste workflows. Changes are applied directly to the open file, with undo support for safe experimentation. Supports both single-line edits and multi-line transformations.