Skip to content

Commit 2741518

Browse files
juliusmarmingecodex
authored andcommitted
docs: explain deferred oversized handoffs
Co-Authored-By: GPT-6.1-Sol at high effort <[email protected]> Co-Authored-By: GPT-6.1-Sol at xhigh effort, review subagent for PR 19414 maintenance rebase <[email protected]>
1 parent d41b6f1 commit 2741518

1 file changed

Lines changed: 3 additions & 3 deletions

File tree

‎docs/user/portable-handoffs.md‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -20,9 +20,9 @@ agent-written summary.
2020
## Context limits
2121

2222
A handoff must leave room for existing provider context, your request and attachments, instructions,
23-
tools, and subsequent work. If even its retrieval references cannot fit, T3 Code reports an error
24-
instead of shortening your request. Compact the target conversation or select a larger-context
25-
model before trying again.
23+
tools, and subsequent work. If even its retrieval references cannot fit, T3 Code sends your request
24+
without the handoff and retries it on later turns with the same provider, including after compaction
25+
frees enough room. Your request is never shortened to make the handoff fit.
2626

2727
Server operators can set `T3CODE_CONTEXT_HANDOFF_TOKEN_CAP` to change the initial history allowance
2828
(default 16,000; clamped to 1,024–64,000). This is an upper bound, not a provider context-window

0 commit comments

Comments
 (0)