Sarah Wooders
|
80db705db7
|
chore: enable flash and fix vertex integration (#2003)
|
2025-05-05 13:47:28 -07:00 |
|
Charles Packer
|
77f9e2d127
|
fix: patch o1 support (#1978)
|
2025-05-02 14:54:25 -07:00 |
|
cthomas
|
65280d6f3c
|
feat: add gemini to byok (#1993)
|
2025-05-02 14:01:23 -07:00 |
|
Andy Li
|
93cc510839
|
fix: handle malformed function calls in vertex (#1987)
|
2025-05-02 11:45:41 -07:00 |
|
cthomas
|
9280d85ba4
|
feat: always add user id to openai requests (#1969)
|
2025-04-30 23:23:01 -07:00 |
|
cthomas
|
25c188689a
|
feat: byok 2.0 (#1963)
|
2025-04-30 21:26:50 -07:00 |
|
Matthew Zhou
|
09cbb00d80
|
feat: Add thinking budget for vertex gemini (#1960)
|
2025-04-30 18:37:42 -07:00 |
|
cthomas
|
5187e79a43
|
feat: use new model-proxy in production (#1908)
|
2025-04-30 15:20:54 -07:00 |
|
Sarah Wooders
|
c6650de5fc
|
fix: trigger gemini retry with ValueError (#1918)
|
2025-04-28 18:47:29 -07:00 |
|
cthomas
|
dc1ecdc902
|
fix: put inner thoughts in kwargs for anthropic (#1911)
|
2025-04-28 16:37:29 -07:00 |
|
cthomas
|
83157c1949
|
feat: add letta-free endpoint constant (#1907)
|
2025-04-27 12:57:06 -07:00 |
|
Charles Packer
|
1568f6b5b4
|
fix: patch weird OSS / cloud drift by copying in OSS into cloud (#1904)
|
2025-04-26 23:21:00 -07:00 |
|
cthomas
|
7605675f23
|
feat: add llm config per request (#1866)
|
2025-04-23 16:37:05 -07:00 |
|
cthomas
|
167c6a1d2e
|
fix: pydantic serializer warning datetime -> int (#1701)
|
2025-04-23 14:53:58 -07:00 |
|
Charles Packer
|
e1fa7f0b40
|
fix: patch o-series (#1699)
|
2025-04-23 13:41:34 -07:00 |
|
cthomas
|
b0faff1ae9
|
fix: tool_name unreachable bug (#1803)
|
2025-04-19 16:29:14 -07:00 |
|
Kevin Lin
|
7e56c7dd3b
|
fix: llm_config.put_inner_thoughts_in_kwargs = True (#1718)
|
2025-04-15 14:47:54 -07:00 |
|
Matthew Zhou
|
cead849f19
|
feat: Implement resume step after request in new batch agent loop (#1676)
|
2025-04-15 13:56:22 -07:00 |
|
Charles Packer
|
1c0e1bffde
|
fix: patch grok-3 and grok-3-fast (skip reasoners for now) (#1703)
|
2025-04-14 12:55:20 -07:00 |
|
Kevin Lin
|
4f3d05e6a6
|
feat: add reasoning effort in LLMConfig (#1697)
Co-authored-by: cpacker <packercharles@gmail.com>
|
2025-04-13 17:44:10 -07:00 |
|
Sarah Wooders
|
32f08883ca
|
fix: force tool_choice to be auto for claude-3.7-sonnet (#1694)
|
2025-04-12 16:39:36 -07:00 |
|
Sarah Wooders
|
1dbf6cd4e5
|
feat: translate system to developer or o-series models (#1692)
Co-authored-by: cpacker <packercharles@gmail.com>
|
2025-04-11 21:59:48 -07:00 |
|
Charles Packer
|
79ffadaee1
|
fix: patch key error (unclear if we should fatally error here, or jus… (#1690)
|
2025-04-11 21:24:53 -07:00 |
|
Kevin Lin
|
14bf712cbe
|
fix: patch o1 and o3-mini (#1657)
|
2025-04-10 13:50:38 -07:00 |
|
Matthew Zhou
|
68fbcf33d8
|
feat: Finish step_until_request in new batch agent loop (#1656)
|
2025-04-10 10:19:06 -07:00 |
|
Charles Packer
|
ee8e095b69
|
fix: patch gemini 2.5 pro (#1643)
Co-authored-by: Sarah Wooders <sarahwooders@gmail.com>
|
2025-04-09 18:35:53 -07:00 |
|
Matthew Zhou
|
4536800b3d
|
fix: Fix build request data for OpenAI (#1654)
|
2025-04-09 16:31:20 -07:00 |
|
Matthew Zhou
|
6a2312a02d
|
chore: Inject LLM config directly to batch api request func (#1652)
|
2025-04-09 15:56:54 -07:00 |
|
cthomas
|
c7d4ce73b0
|
Add parent tool rule (#1648)
|
2025-04-09 15:22:15 -07:00 |
|
Matthew Zhou
|
7565ad4a8d
|
feat: Write batch request on base LLM client (#1646)
|
2025-04-09 14:58:26 -07:00 |
|
Charles Packer
|
9f7285fdb6
|
fix: patch incorrect use of name in function response (#1642)
|
2025-04-09 14:20:57 -07:00 |
|
Sarah Wooders
|
6c55720778
|
fix: patch summarizer for google and use new client (#1639)
|
2025-04-08 21:10:48 -07:00 |
|
Matthew Zhou
|
6573714d8a
|
fix: Fix streaming when there are child tool rules (#1638)
|
2025-04-08 19:06:39 -07:00 |
|
cthomas
|
0af857d3ba
|
fix: use message idx for anthropic legacy streaming (#1600)
|
2025-04-07 15:12:24 -07:00 |
|
Sarah Wooders
|
68b1ff85b1
|
feat: add gemini 2.5 to google vertex (#1590)
Co-authored-by: Charles Packer <packercharles@gmail.com>
|
2025-04-06 16:53:41 -07:00 |
|
cthomas
|
42bfe08ce1
|
fix: use message idx instead of chunk idx for streaming (#1587)
|
2025-04-06 11:23:19 -07:00 |
|
Matthew Zhou
|
b03af8eb60
|
feat: Add batch requests on Anthropic Client (#1574)
|
2025-04-04 14:58:18 -07:00 |
|
cthomas
|
9458f40d05
|
feat: add otid field for message idempotency (#1556)
|
2025-04-04 08:43:01 -07:00 |
|
Matthew Zhou
|
3ba79db859
|
feat: Enable Anthropic streaming on new agent loop (#1550)
|
2025-04-03 19:40:48 -07:00 |
|
cthomas
|
d4991a2de6
|
feat: sleeptime agent prompting improvements (#1547)
|
2025-04-03 11:04:42 -07:00 |
|
cthomas
|
6c30dcd209
|
fix: always strip thinking tags from anthropic stream (#1483)
|
2025-04-02 15:18:04 -07:00 |
|
Sarah Wooders
|
3109535297
|
fix: dont error on azure model listing and add local EmbeddingConfig (#1534)
|
2025-04-02 15:12:07 -07:00 |
|
Matthew Zhou
|
59ca61da58
|
feat: Simplify arguments for LLM clients (#1536)
|
2025-04-02 14:26:27 -07:00 |
|
cthomas
|
a0ebfa0cd1
|
fix: summarization bug (#1476)
|
2025-03-31 13:32:00 -07:00 |
|
Matthew Zhou
|
23434c6979
|
feat: New openai client (#1460)
|
2025-03-31 13:08:59 -07:00 |
|
cthomas
|
3dd3242c6d
|
fix: anthropic system event parse (#1471)
|
2025-03-31 09:49:15 -07:00 |
|
Charles Packer
|
f47263cc47
|
fix: catch context window exceeded error thrown from Anthropic (#1470)
|
2025-03-31 09:35:20 -07:00 |
|
Charles Packer
|
346caee7ca
|
fix: small patch for discord (due to python version i thnk) (#1469)
|
2025-03-30 20:09:46 -07:00 |
|
cthomas
|
df899ee05b
|
fix: anthropic system message parse (#1467)
|
2025-03-30 18:44:55 -07:00 |
|
Matthew Zhou
|
60ffc9e8ec
|
fix: Fix message_id ordering in agent serialization (#1458)
|
2025-03-28 15:13:33 -07:00 |
|