 Dax Raad
|
7ec3900208
core: enable reasoning.encrypted_content and reasoningSummary for opencode provider\ntui: adjust editorY position calculation
|
5 months ago |
|
Dax Raad
|
71b43fd02e
fix codex errors
|
5 months ago |
|
Dax Raad
|
d4c01f858b
disable thinking for opencode zen and gpt-5 temporarily
|
5 months ago |
|
Dax Raad
|
2d5bd26a59
feat: enhance provider model mapping and reasoning capabilities
|
5 months ago |
 Dax
|
c1b4e1f19d
Upgrade to Zod v4 (#2605)
|
5 months ago |
 Ytzhak
|
4654fb88de
fix: max output tokens when setting budget thinking tokens (#2056)
|
5 months ago |
|
Dax Raad
|
4c261ab1db
switch gpt-5 to default to codex prompt + high reasoning
|
5 months ago |
 Aiden Cline
|
b5d61b77f7
fix: reasoning not supported (#1882)
|
6 months ago |
|
Dax Raad
|
5785ded6e2
add openai prompt cache key
|
6 months ago |
|
Dax Raad
|
5f34dcc792
azure reasoning effort
|
6 months ago |
|
Dax Raad
|
dac1506680
update anthropic prompt and variables
|
6 months ago |
|
Dax Raad
|
279edb6f24
fix azure gpt config
|
6 months ago |
 adamdotdevin
|
b8d2aebf09
feat: thinking blocks rendered in tui and share page
|
6 months ago |
|
Dax Raad
|
d3ff66e911
use minimal reasoning effort for gpt-5
|
6 months ago |
|
Dax Raad
|
53630ebdce
gpt-5 lower verbosity
|
6 months ago |
|
Aiden Cline
|
0b132c032a
ignore: fix dev branch (#1529)
|
6 months ago |
 Ricardo Gonzalez
|
8f45a0e227
feat(models): enable Kimi k2 ⇄ Claude trajectory handoff (#1525)
|
6 months ago |
|
Dax Raad
|
e1b7e25f4d
make top_p configurable
|
6 months ago |
|
Dax Raad
|
6b7058fe1c
qwen optimizations it works good now
|
7 months ago |
|
Dax Raad
|
e97613ef9f
allow temperature to be configured per mode
|
7 months ago |
 Dominik Engelhardt
|
827469c725
fix: apply content-level caching for non-anthropic providers (#1305)
|
7 months ago |
 Jesse van der Pluijm
|
34f6ffe1d7
Check if modelID includes "claude" for antropic/claude prompt caching (#1284)
|
7 months ago |
|
Dax Raad
|
6465c9c44a
fix openrouter caching
|
7 months ago |
|
Dax
|
f884766445
v2 message format and upgrade to ai sdk v5 (#743)
|
7 months ago |
|
Dax Raad
|
969ad80ed2
fix openrouter caching with anthropic, should be a lot cheaper
|
7 months ago |
|
Dax Raad
|
ca48a4f0fb
better amazon bedrock caching with anthropic models
|
8 months ago |
 Márk Magyar
|
137e964131
fix: session title generation (#293)
|
8 months ago |
|
Dax Raad
|
1684042fb6
huge optimization for token usage with anthropic
|
8 months ago |
|
Dax Raad
|
f1a2b2eba4
support token caching for anthropic via openrouter
|
8 months ago |
