Back to Signal Feed
CodeTracked since May 18, 2026

Add LSP-based code-completion and diagnostics tools for AI agents

This PR adds new Serena tools (`completion`, `hover`, `get_diagnostics`, `inlay_hints`) so AI agents can inspect symbol members, documentation, and diagnostics through the language server interface across Java, TypeScript, Python, and Rust; manual testing confirms completion/hover/diagnostics behavior for those languages, while inlay hints return empty results in Java and TypeScript.

SerenaLanguage Server Protocolcompletionhover

What Happened

  • This PR adds new Serena tools (`completion`, `hover`, `get_diagnostics`, `inlay_hints`) so AI agents can inspect symbol members, documentation, and diagnostics through the language server interface across Java, TypeScript, Python, and Rust; manual testing confirms completion/hover/diagnostics behavior for those languages, while inlay hints return empty results in Java and TypeScript.
  • This PR adds new Serena tools (`completion`, `hover`, `get_diagnostics`, `inlay_hints`) so AI agents can inspect symbol members, documentation, and diagnostics through the language server interface across Java, TypeScript, Python, and Rust; manual testing confirms completion/hover/diagnostics behavior for those languages, while inlay hints return empty results in Java and TypeScript.
  • 1 evidence item attached for review.

What is Different

Before

Scattered source updates, isolated context, and manual follow-up across multiple feeds.

Now

Implemented new LSP-backed interaction endpoints (`completion`, `hover`, `get_diagnostics`, `inlay_hints`) to let AI assistants query symbol information and compile-time warnings/errors without requiring full local source inspection or repeated build cycles.

Why Track This

Why It Matters

Developers and AI coding assistants using Serena can get immediate symbol docs, completion suggestions, and diagnostic feedback while working, which can reduce API mistakes and shorten troubleshooting before running larger build/test steps. This depends on each language server’s capability support, so the remaining risk is uneven tool behavior—`inlay_hints` is still empty for Java/TypeScript in current tests—and operators should watch whether hint and diagnostics responses stay consistent as more languages or setups are used.

Impact

Developers and AI coding assistants using Serena can get immediate symbol docs, completion suggestions, and diagnostic feedback while working, which can reduce API mistakes and shorten troubleshooting before running larger build/test steps. This depends on each language server’s capability support, so the remaining risk is uneven tool behavior—`inlay_hints` is still empty for Java/TypeScript in current tests—and operators should watch whether hint and diagnostics responses stay consistent as more languages or setups are used.

What To Watch Next

  • Watch whether Serena becomes a repeated pattern.
  • Track follow-up changes around AI Integration in IDEs.
  • Compare future signals against this evidence trail.
  • Re-check risk flags: inlay_hints_empty_for_java, inlay_hints_empty_for_typescript.
Open Topic TimelineOpen Technical EventOpen Original Sourceinlay_hints_empty_for_java / inlay_hints_empty_for_typescript / language_server_capability_variance / no_automated_validation_reported / open_pull_request_not_merged

Supporting Evidence