After compaction, context token count is unknown until the next LLM
response. Instead of showing stale pre-compaction values or heuristic
estimates, the footer now shows ?/200k.
ContextUsage.tokens and ContextUsage.percent are now number | null
(breaking change). Removed usageTokens, trailingTokens, lastUsageIndex
from ContextUsage (internal details).
Also fixed _checkCompaction() using .find() (first compaction) instead
of getLatestCompactionEntry() (latest), which caused incorrect overflow
detection with multiple compactions.
Closes#1382
The invalid-params error paths already listed available agents,
but the unknown-agent path in runSingleAgent just returned
'Unknown agent: claude' with no hint what exists.
Now: 'Unknown agent: "claude". Available agents: "worker".'
Model would guess names like "claude", "default", or skill names
like "brave-search". Now it self-corrects on the next call.
Tested with Opus 4.6: without fix, model gave up on subagent
and ran the tool calls itself instead. With fix, 1 wasted call.
Demonstrates overriding built-in tool rendering to show only tool calls
in collapsed mode and full output in expanded mode. Shows how users can
implement a 'minimal mode' using the existing extension API.
- Add OSC 99 notification support for Kitty terminal (detected via KITTY_WINDOW_ID)
- Add Windows toast notifications for Windows Terminal/WSL (detected via WT_SESSION)
- Refactor into separate functions for each notification method
- OSC 777 remains the fallback for Ghostty, iTerm2, WezTerm, rxvt-unicode
Co-authored-by: Soleone (Windows Terminal support)
- Add example extension demonstrating pi.getCommands() API
- Export SlashCommandInfo, SlashCommandLocation, SlashCommandSource from main index.ts
Follow-up to #1210
