jaeminbird fb07f676a9 fix(anthropic): report max_tokens when the token budget is exhausted ...

/v1/messages always answered stop_reason "end_turn" for text replies,
even when generation stopped at max_tokens. Clients that continue a
truncated turn (the Anthropic SDKs, Claude Code) treated the cut-off
reply as complete. Use the same check the OpenAI endpoint uses for
finish_reason "length", in both the streaming and non-streaming paths.

Assisted-by: Claude:claude-opus-5-5
Signed-off-by: jaeminbird <jaeminbird@gmail.com>
(cherry picked from commit d905ab5fdc)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

2026-11-03 14:40:50 +00:00

..

advanced

feat(chats): server-side chats with steering, sub-agents and compaction (#12918)

2026-11-01 12:08:23 +01:00

development

feat(addons): declare typed host capabilities (#13034)

2026-11-02 23:50:40 +00:00

features

fix(anthropic): report max_tokens when the token budget is exhausted

2026-11-03 14:40:50 +00:00

getting-started

fix: restore the files that the previous commit removed by mistake

2026-11-03 14:33:05 +00:00

operations

feat(chats): server-side chats with steering, sub-agents and compaction (#12918)

2026-11-01 12:08:23 +01:00

reference

feat(http): add an opt-in client address to the access log

2026-11-03 14:32:55 +00:00

_index.md

feat(website): split the site, move docs to /docs, add a landing page (#11243)

2026-07-31 09:00:56 +02:00

faq.md

docs(faq): note OPENAI_BASE_URL env var for pointing clients at LocalAI (#11310)

2026-09-11 14:44:18 +02:00

integrations.md

docs: fix Discord, Slack and Telegram example links (#12392)

2026-10-01 08:40:26 +02:00

overview.md

feat(chats): server-side chats with steering, sub-agents and compaction (#12918)

2026-11-01 12:08:23 +01:00

whats-new.md

docs: point the News page at the blog instead of a stale highlights list

2026-08-03 20:29:50 +00:00