nanobot

1,829 Commits 1 Branch 1 Tag

3 Commits

Author	SHA1	Message	Date
Leo fuandXubin Ren	42624f5bf3	test: update expected token display to match consistent 1000 divisor The test fixtures use 65536 as context_window_tokens. With the divisor corrected from 1024 to 1000, the display changes from 64k to 65k.	2026-04-09 10:40:20 +08:00
Leo fuandXubin Ren	66409784f4	fix(status): use consistent divisor (1000) for token count display The /status command divided context_used by 1000 but context_total by 1024, producing inconsistent values. For example a 128000-token window displayed as 125k instead of 128k. Tokens are not a binary unit, so both should use 1000.	2026-04-09 10:40:20 +08:00
Leo fuandXubin Ren	44c7992095	fix(filesystem): correct write success message from bytes to characters len(content) counts Unicode code points, not UTF-8 bytes. For non-ASCII content such as Chinese or emoji, the reported count would be lower than the actual bytes written to disk, which is misleading to the agent.	2026-04-07 13:22:00 +08:00

Author

SHA1

Message

Date

Leo fuandXubin Ren

42624f5bf3

test: update expected token display to match consistent 1000 divisor

The test fixtures use 65536 as context_window_tokens. With the divisor
corrected from 1024 to 1000, the display changes from 64k to 65k.

2026-04-09 10:40:20 +08:00

Leo fuandXubin Ren

66409784f4

fix(status): use consistent divisor (1000) for token count display

The /status command divided context_used by 1000 but context_total by
1024, producing inconsistent values. For example a 128000-token window
displayed as 125k instead of 128k. Tokens are not a binary unit, so
both should use 1000.

2026-04-09 10:40:20 +08:00

Leo fuandXubin Ren

44c7992095

fix(filesystem): correct write success message from bytes to characters

len(content) counts Unicode code points, not UTF-8 bytes. For non-ASCII
content such as Chinese or emoji, the reported count would be lower than
the actual bytes written to disk, which is misleading to the agent.

2026-04-07 13:22:00 +08:00