Jochen
ad198a8501
add code exploration fast start
...
This tries to short-circuit multiple round-trips to llm for reading code.
It's a precursor to trying to context engineer tailored to specific tasks.
In initial experiments, it's only marginally faster than regular mode, and burns more tokens.
2025-11-25 22:51:32 +11:00
Jochen
9bffd8b1bf
cache_control removed from databricks
2025-11-19 12:15:49 +11:00
Jochen
a150ba6a55
adds ttl to cache control
2025-11-18 23:23:49 +11:00
Jochen
296bf5a449
adds cache_control
2025-11-18 22:38:52 +11:00
Dhanji Prasanna
22a0090cdc
fix unexpected EOF on streams
2025-11-04 16:28:41 +11:00
Dhanji Prasanna
d0ac222e2e
more macax tooling
2025-10-24 10:45:24 +11:00
Dhanji Prasanna
c5d6fbef08
control commands
2025-10-22 22:14:12 +11:00
Dhanji Prasanna
bb90cc7826
some fixes
2025-10-14 12:44:02 +11:00
Dhanji Prasanna
062e6de63f
fix for buffered messages at end, colorized context bars
2025-10-13 13:36:37 +11:00
Dhanji Prasanna
260c949576
token counting fixes
2025-10-09 12:11:21 +11:00
Dhanji Prasanna
bcba99ec6c
auto refresh token
2025-10-04 17:32:48 +10:00
Dhanji Prasanna
4e64555008
max tokens fix for databricks
2025-09-29 06:45:53 +10:00
Dhanji Prasanna
c490228824
databricks support
2025-09-27 17:28:02 +10:00
