Skip to content

v0.10.4

Choose a tag to compare

@lvndry lvndry released this 02 May 11:35
· 42 commits to main since this release

What's Changed

Agent Workflow Enhancements

Your agents have become self‑aware accountants! 🎩💰 The new AgentResponse now tells you exactly how many tokens each run gobbled and what the bill looks like. Plus, if a scheduled run trips up, you’ll see a friendly “I failed!” notice on startup so you can rescue it faster than a cat on a keyboard.

Web Search Auto‑Detection

No more hunting for API keys in your env‑vars. The web‑search engine now sniffs them out automatically, turning a tedious setup step into a breeze. Your searches start firing faster than a caffeinated squirrel.

Conversation History & Chat Improvements

Chat is now a true diary. 📖 Sessions are stored, letting you scroll back through past talks. Messages stack neatly, one per line, and you can type while the agent thinks—no more “please wait” dead air. Also, the UI now echoes your prompt so you never wonder what you typed.

CLI Polish & Performance

The command line got a spa day: live panels are bounded for smoother reasoning, tables and code blocks buffer adaptively, and streaming deltas now arrive every ~80 ms instead of a sluggish crawl. Rendering quirks were polished away—blank lines before metrics and clearer reasoning separators make the output as tidy as a fresh‑rolled sushi platter.

Auto‑Update & Docs

The auto‑update routine got a makeover: the changelog link is swapped for a direct “Releases” page, guiding you straight to the latest goodies without hunting through markdown.

Developer Experience

VSCode config tweaks give you a richer editing vibe, obsolete TODO files were evicted, and dead code plus unused dependencies were trimmed—your repo is now leaner than a minimalist diet.


Commits

  • 8a29a3c feat(workflow): expose per-run cost and token usage in AgentResponse (#226) by @Landry Monga
  • 62d0053 feat(web-search): auto-detect provider API keys from environment variables (#225) by @Landry Monga
  • 01c645d fix(auto-update): replace changelog with releases link (#224) by @Landry Monga
  • fa3286b chore: improve vscode config (#223) by @Landry Monga
  • d250540 chore: remove TODO.md and README.proposed.md (#222) by @Landry Monga
  • fa069c0 feat(history): session storage and conversation history (#221) by @Landry Monga
  • 0d166d8 feat(chat): stack queued messages, one entry per line (#220) by @Landry Monga
  • 9ba9840 feat(cli): bounded live panels for reasoning and subagents (#213) by @Landry Monga
  • b674518 fix(chat): echo "You: " when draining the queued message (#217) by @Landry Monga
  • fb4f804 chore: prune dead files and unused dependencies (#219) by @Landry Monga
  • 17fdcec perf(cli): adaptive buffering for tables and code blocks (#218) by @Landry Monga
  • d1150b4 feat(chat): queue messages typed while agent is busy (#212) by @Landry Monga
  • 91972f7 fix(workflow): record failed scheduled runs and surface them on startup (#215) by @Landry Monga
  • 861bcf2 perf(cli): buffer streaming deltas to ~80ms cadence (#216) by @Landry Monga
  • 859929c fix(cli): rendering polish — blank line before metrics + reasoning delimiter (#211) by @Landry Monga
  • e480f06 fix(cli): polish input flows — optional agent description + mask API key echo (#210) by @Landry Monga

Full diff

v0.10.3...v0.10.4