This release adds 1 notable feature for engineering teams evaluating rollout.
Published 1mo
Developer Productivity
✓ No known CVEs patched
✓ No known CVEs patched in this version
Topics
agent
ai-agent
anthropic
claude
claude-code
claude-code-cli
+12 more
claude-code-tui
cli
coding-agent
web
developer-tools
digest
live-monitor
llm
monitor
observability
session-monitor
tui
Summary
AI summaryFixed validation for unknown --include report types and added oversize token warning.
Full changelog
New
agenthud summary --model <name>forwards--modeltoclaude -p. Summarization is a low-reasoning task, so cheaper models almost always suffice —sonnet(~40% cheaper than Opus, 1M context) orhaiku(~80% cheaper, 200K context). Accepts a short alias or a full model id. Default unchanged (claude's own default model).- Oversize report warning. The input stats line now includes an estimated token count. Reports above ~300K tokens print a loud warning and, in interactive mode, prompt one more time before sending. Range mode with
-yonly prints the warning and proceeds.
Fixed
report --includevalidates unknown types. A typo like--include response,basused to be silently accepted (no match, no error). Now unknown tokens trigger an error listing the offending values and the full list of valid types. Missing value after--includealso errors.
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About AgentHUD
All releases →Related context
Related tools
Earlier breaking changes
- v0.14.0 `h` key now aliases vim-left (←) instead of hide.
Beta — feedback welcome: [email protected]