Turtle a0f59aac40 fix(llm-pi-ai): stop re-parsing streamed tool-call arguments on every delta (#4740) ...

pi-ai 0.85.1 runs parseStreamingJson over the whole accumulated argument
JSON on every tool-call delta, so one large tool call costs O(n²) CPU on
the event loop and a multi-megabyte argument stream stalls every session
in the process. Patch the six stream adapters to parse once at
toolcall_end, document the patch, and cover both OpenAI protocols.

Fixes #4739

2026-09-21 03:53:37 +00:00

..

@[email protected]

fix(llm-pi-ai): stop re-parsing streamed tool-call arguments on every delta (#4740)

2026-09-21 03:53:37 +00:00

@[email protected]

feat: 加速 mac sign

2026-09-08 17:44:05 +08:00

@[email protected]

fix(pkg): make SEA native addon extraction atomic

2026-09-20 14:36:27 +08:00

[email protected]

chore(subprocess-local): bump node-pty beta

2026-08-13 17:58:13 +08:00