Files
gpt-pilot/src
Andrey 3d89f0f14a fix(reply): auto-inject replyToCurrent for reply threading
replyToMode "first"/"all" only filters replyToId but never generates
it — that required the LLM to emit [[reply_to_current]] tags. Inject
replyToCurrent:true on all payloads so applyReplyTagsToPayload sets
replyToId=currentMessageId, then let the existing mode filter decide
which replies keep threading (first only, all, or off).

Covers both final reply path (reply-payloads.ts) and block streaming
path (agent-runner-execution.ts).
2026-02-13 05:22:14 +01:00
..
2026-01-30 03:16:21 +01:00
2026-02-04 10:37:14 -05:00
2026-02-09 09:58:58 +09:00
2026-02-12 14:37:55 -08:00
2026-02-03 06:10:19 +00:00
2026-02-09 18:56:58 -08:00