When enabled, /tree navigation skips the 'Summarize branch?' prompt and
defaults to no summary, reducing friction for users who never want branch
summaries.
Closes#1791
GNU screen does not support truecolor escape sequences. When pi emits
truecolor SGR sequences (e.g. \x1b[38;2;102;102;102m for the dim color
#666666), screen misparses the semicolon-separated parameters as
individual SGR codes. The RGB value 102;102;102 maps directly to
SGR 102 (bright green background), which then bleeds into every
subsequent \x1b[2K line-erase, producing a bright green background
on most info/status messages.
detectColorMode() now returns '256color' for any TERM value that is
'screen', starts with 'screen-' (e.g. screen-256color), or starts
with 'screen.' (e.g. screen.xterm-256color). The existing COLORTERM
check at the top of the function already handles the opt-in case for
users who have configured screen's truecolor passthrough.
Messages submitted while a branch summary was being generated were
processed immediately instead of being queued. This happened because
isCompacting only checked compaction abort controllers, not the branch
summary abort controller.
Include _branchSummaryAbortController in the isCompacting getter so all
existing guards (message queueing, reload blocking) also apply during
branch summarization.
createBranchedSession() wrote the file and set flushed=true even when the
branched path had no assistant message. The next _persist() call saw no
assistant, reset flushed=false, and the subsequent flush appended all
in-memory entries to the already-populated file, duplicating the header
and entries.
Fix: defer file creation when the branched path has no assistant message,
matching the newSession() contract. _persist() creates the file on the
first assistant response.
closes#1672
When resolving --model zai/glm-5, the resolver now correctly interprets
'zai' as the provider and 'glm-5' as the model id, rather than matching
a vercel-ai-gateway model whose id is literally 'zai/glm-5'.
If the provider/model split fails to find a match, falls back to raw id
matching to still support OpenRouter-style ids like 'openai/gpt-4o:extended'.
The extension system currently only forwards agent_start, agent_end,
turn_start, and turn_end events. This means extensions cannot access
streaming text (token-by-token), message lifecycle, or tool execution
progress — all of which are available to internal subscribers.
This adds forwarding for the remaining 6 agent event types:
- message_start, message_update, message_end
- tool_execution_start, tool_execution_update, tool_execution_end
These follow the exact same pattern as the existing forwarded events:
new interfaces in types.ts, exports in index.ts, and else-if blocks
in _emitExtensionEvent(). The new types are included in ExtensionEvent
and automatically flow through RunnerEmitEvent (they're not in the
exclusion list).
This enables extensions to build real-time UIs, streaming WebSocket
bridges, and other integrations that need fine-grained event access.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Mario Zechner <badlogicgames@gmail.com>
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
