CodeSesh

What changed, and where CodeSesh is going

The CodeSesh product changelog explains user-visible improvements in plain language. Each release covers what changed, why it matters for local AI coding history, and the product direction behind the work.

Release history

CodeSesh 1.0.5

View technical release details

Faster refreshes and more dependable live state

Large histories now refresh by updating only changed search documents, while cold session details load in background workers. You can also copy any session as clean Markdown from its action menu.

What changed

  • Copy sessions as Markdown

    Move a complete conversation into documentation, an issue, or another tool without rebuilding its structure by hand.

  • Refresh only what changed

    Incremental scans update changed search documents instead of rebuilding the entire index, reducing work on large archives.

  • Keep interaction responsive

    Cold session details load outside the main thread, and live project and session state stays consistent through reloads.

Product direction

CodeSesh should stay responsive as local histories grow, and its live scan and session state should always be easy to trust.

CodeSesh 1.0.4

View technical release details

Safer access and steadier large histories

This release adds a complete Japanese product site, protects loopback API access, preserves the last known-good scan during failures, and reduces indexing and rendering work across large archives.

What changed

  • A complete Japanese product site

    Japanese-speaking visitors can now understand CodeSesh, its local data boundary, and its core workflow in their own language.

  • Stronger local access controls

    Loopback API requests are authenticated, and trusted-proxy deployment now requires a safer host and HTTPS configuration.

  • Last known-good state survives failures

    Interrupted scans, unavailable agents, and failed cache migrations no longer replace usable history with partial state.

Product direction

Local-first privacy includes predictable access controls and durable recovery. Scale should not make either of them harder to understand.

CodeSesh 1.0.3

View technical release details

More accurate usage and more resilient recovery

Usage, tokens, and cost are now attributed to each message's time. Scan and cache failures remain visible instead of looking like empty history, while repeated parsing, queries, and rendering work has been removed.

What changed

  • Usage follows message time

    Sessions spanning several days no longer assign all tokens and cost to a single day in the dashboard.

  • Failures stay explicit

    Agent, scan, cache, and Web failures no longer silently appear as empty or successfully published state.

  • Less repeated work

    Cached metadata, reused queries, and localized rendering reduce startup, search, and live-update overhead.

Product direction

CodeSesh treats correct history as the foundation. Performance work follows from preserving facts and avoiding work that does not need to happen twice.