swadhinbiswas f9ef22b05f call-agent: never speak reasoning prefilled by the chat template (#2428) ...

Some chat templates write the opening think tag into the prompt
(Spark-X2.5, Qwen3 thinking variants, DeepSeek-R1-0528 served without a
reasoning parser), so the model streams only …SAY:. ReplyParser had no
opening tag to match, settled on plain mode at the first non-format
characters, and spoke every reasoning sentence — to the person on the
phone, in the user's voice — plus the stray tags.

Implements the reporter's recommended parser-side fix (FenjuFu,
option 1):

- _body now drops everything up to a closing tag found anywhere, or up
  to a line-start SAY: when no closing tag comes either. Both searches
  are stable on the append-only raw text, so _emitted stays aligned.
- _decide_mode no longer settles plain early: the system prompt
  requires replies to start with SAY: or {, so a body with neither is
  held while it streams (it may be prefilled thinking) and only
  finish() speaks it as plain text. Format-following replies keep
  first-sentence streaming.

Regression tests fail before the parser change; the reporter's exact
repro now returns only the SAY: text in both variants.

2026-09-29 21:24:12 +06:00

..

calls.md

call-agent: never speak reasoning prefilled by the chat template (#2428)

2026-09-29 21:24:12 +06:00

n8n.md

fix(n8n): validate real imports and cover cold-start budgets

2026-09-20 21:42:50 +05:30

twilio.md

feat(integrations): guided Twilio setup and responsive integration pages (#2304)

2026-09-23 17:40:46 +05:30