Fred K. Schott
0d89a33373
feat(packages): Add selective pi-ai base entrypoints ( #5348 )
2026-06-19 00:41:49 +02:00
Armin Ronacher
75b0d723c0
fix(ai): support Z.AI GLM-5.2 effort levels
...
closes #5770
2026-06-16 14:29:27 +02:00
Armin Ronacher
0369bdb8f4
fix(ai): add Moonshot CN Kimi K2.7 metadata
...
closes #5760
2026-06-15 17:08:59 +02:00
Vegard Stikbakke
3f44d3e2eb
fix(ai): remove stale OpenRouter Kimi free model assertion ( #5650 )
2026-06-12 09:00:15 +02:00
Mario Zechner
3d02d1da11
fix(ai): map OpenCode max tokens
...
closes #5331
2026-06-09 13:41:08 +02:00
Mario Zechner
25a4a8ed1e
Add Ant Ling provider
2026-06-02 16:37:44 +02:00
Mario Zechner
2125221bfc
Fix OpenRouter Kimi reasoning compat
...
closes #5309
2026-06-02 15:36:52 +02:00
PriNova
74d81bd363
Fix OpenAI completions developer role test
2026-05-30 12:24:19 +02:00
PriNova
b55fe1bbd4
Fix OpenRouter reasoning instruction role
2026-05-30 11:15:30 +02:00
Armin Ronacher
4faac05419
fix(ai): handle OpenCode reasoning params
2026-05-29 12:21:37 +02:00
Mario Zechner
97ef317389
Fix Kimi and Xiaomi model metadata
...
Closes #5075 , closes #5078 . Refs #5087 .
2026-05-28 22:19:47 +02:00
Mario Zechner
2e02c74dcb
chore: pin dependencies and use native TypeScript
2026-05-20 12:46:17 +02:00
Mario Zechner
b8f51957a0
fix(ai): add Xiaomi reasoning replay compat
...
closes #4678
2026-05-18 11:15:20 +02:00
Mario Zechner
21d80deda2
fix(ai): normalize opencode go reasoning replay
...
closes #4251
2026-05-18 01:11:23 +02:00
Mario Zechner
0412f62f9e
Merge pull request #4558 from earendil-works/fix/openai-completions-throw-on-missing-finish_reason
...
fix(ai): openai-completions - throw error on missing finish-reason
2026-05-16 22:54:42 +02:00
Armin Ronacher
87881ca686
fix(ai): preserve OpenRouter cached token semantics
2026-05-16 11:55:16 +02:00
Ramiz Wachtler
98ffad0437
fix(ai): openai-completions - throw error on missing finish-reason
...
- require \ before treating \ streams as successful
- add regression coverage for truncated streams without \
- closes #4345
2026-05-15 15:26:57 +02:00
Armin Ronacher
6b271842e2
fix(ai): handle mixed chat completion deltas
...
Fixes #4228
2026-05-07 00:12:19 +02:00
Mario Zechner
65fc803671
fix(ai): refresh generated model catalog for release
2026-04-27 21:28:21 +02:00
Mario Zechner
c681d35d76
fix(ai): avoid double-counting reasoning tokens
...
closes #3581
2026-04-23 23:28:16 +02:00
Mario Zechner
01509156b3
fix(ai): coalesce malformed streamed tool calls closes #3576
2026-04-23 16:05:21 +02:00
Armin Ronacher
35ff2689ee
fix(typebox): migrate to v1 with extension compat ( #3474 )
...
* fix(typebox): migrate to v1 with extension compat
Replace AJV-based validation with TypeBox-native validation, keep legacy extension imports working (including @sinclair/typebox/compiler), and restore coercion for serialized/plain JSON schemas.
This change closes #3112 .
* fix(typebox): use canonical imports and harden coercion
Switch first-party code to canonical typebox imports while retaining legacy extension aliases in the loader.
Remove obsolete runtime codegen guards, expand serialized JSON-schema coercion coverage, and update related tests and fixtures.
Fixes #3112 .
---------
Co-authored-by: Mario Zechner <badlogicgames@gmail.com >
2026-04-22 19:59:33 +02:00
Mario Zechner
f84c4c89f5
fix(ai): restore FakeOpenAI mock .withResponse() so openai-completions tests pass
...
The openai-completions provider now calls .withResponse() on the
create() result to surface HTTP status/headers for the new onResponse
hook (d131fcd4 ). The FakeOpenAI test mock only returned an async
iterable, so 4 tests in openai-completions-tool-choice.test.ts that
actually consume the stream failed with "withResponse is not a function".
Updated the mock to return a Promise augmented with .withResponse()
resolving to { data: <async iterable>, response: { status, headers } }.
closes #3304
2026-04-16 22:57:30 +02:00
Mario Zechner
6044cabb15
fix(ai): preserve cache_write_tokens in completions stream usage closes #2802
2026-04-04 21:39:11 +02:00
Kao Félix
758ede4da0
Enable tool streaming for newer Z.ai models ( #2732 )
2026-03-31 14:28:24 +02:00
Mario Zechner
78833dfcbc
chore(ai): format openai completions test
2026-03-21 09:16:49 +01:00
Cheng-Zi-Qing
7e2689ac18
packages/ai: ignore null chunks in openai-completions streams ( #2466 )
2026-03-20 20:01:28 +01:00
PriNova
f704ee7255
fix(ai): use OpenRouter reasoning payload ( #2298 )
...
* fix(ai): use OpenRouter reasoning payload
* fix(coding-agent): stop updating packages on startup closes #1963
* fix(ai): add openrouter thinkingFormat compat
---------
Co-authored-by: Mario Zechner <badlogicgames@gmail.com >
2026-03-18 11:23:27 +01:00
Mario Zechner
d914d1c199
fix(coding-agent): handle z.ai network_error closes #2313
2026-03-17 22:34:49 +01:00
Mario Zechner
7b96041068
fix(ai): map groq qwen3 reasoning effort values closes #1745
2026-03-03 16:44:42 +01:00
Mario Zechner
ff0eb3ecd4
fix(ai): omit strict for unsupported openai completions
2026-02-02 00:44:55 +01:00
williamtwomey
41d2c7ff38
OpenAI completions toolChoice fix ( #998 )
...
* openai completions tools fix
* Reset generated file
---------
Co-authored-by: williamtwomey <ai@shadylawn.net >
2026-01-28 03:03:15 +01:00