75d469d17d
feat(opencode): configure Cohere North model ( #31536 )
2026-06-09 10:54:03 -05:00
6591b34560
fix(opencode): generate reasoning variants for all OpenRouter models. ( #30332 )
...
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com >
Co-authored-by: Aiden Cline <aidenpcline@gmail.com >
2026-06-08 20:22:02 -05:00
306b67d957
fix: adjust item id stripping to happen prior to request signing ( #31429 )
2026-06-08 17:43:48 -05:00
9fc8deab6e
fix(opencode): support MiniMax M3 thinking toggle ( #31426 )
2026-06-08 17:03:31 -05:00
291d8e4167
fix(opencode): honor Bedrock Mantle config ( #31001 )
2026-06-05 13:14:55 -05:00
4e541c586a
fix(opencode): gate reasoning summaries by provider ( #30973 )
2026-06-05 10:08:39 -05:00
14e2b0d799
chore: generate
2026-06-04 06:59:09 +00:00
9e11b45908
feat(core): add command registry ( #30624 )
2026-06-04 02:57:43 -04:00
59d31f4a7e
feat: bump bedrock and add proper mantle support for openai models through aws bedrock ( #30464 )
2026-06-04 00:09:12 -05:00
514691e2ae
fix(opencode): route SAP AI Core reasoning variants through modelParams ( #30482 )
2026-06-03 18:40:39 -05:00
373fe67d55
fix(core): expose azure openai xhigh efforts ( #30620 )
2026-06-03 15:27:23 -05:00
02bbe2d583
chore: generate
2026-06-03 04:35:54 +00:00
647c0d1f08
fix: rm tool reorder logic from old bug ( #30483 )
2026-06-02 23:34:36 -05:00
5600ead468
Revert "fix(opencode): preserve signed thinking during anthropic reorder" ( #30502 )
2026-06-02 23:34:05 -05:00
66065eb7fe
fix(opencode): preserve signed thinking during anthropic reorder ( #30182 )
2026-06-02 23:33:48 -05:00
fbda5fadda
refactor(core): move v1 schemas into core ( #30473 )
2026-06-03 02:42:13 +00:00
7a9068f029
refactor(core): consolidate filesystem services ( #30447 )
2026-06-02 16:09:26 -04:00
78630b7907
test: widen provider header timeout margin ( #30427 )
2026-06-02 11:02:39 -05:00
c6f77e50f8
chore: generate
2026-05-31 01:09:55 +00:00
e2a8e18298
refactor(core): move database schema ownership ( #29068 )
...
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com >
2026-05-30 21:08:38 -04:00
c50ec8e5e4
fix(opencode): support sap-ai-core anthropic opus 4.7+ adaptive reasoning ( #29991 )
2026-05-30 18:30:21 -05:00
9122c853b4
fix(opencode): default display summarized for gateway opus 4.7+ adaptive reasoning ( #30027 )
2026-05-30 18:07:06 -05:00
6cb9868946
chore: generate
2026-05-30 04:07:26 +00:00
999db7786c
feat(core): add location-scoped config loading ( #29625 )
2026-05-30 04:06:08 +00:00
db24893a4e
fix(opencode): support vertex opus adaptive reasoning ( #29911 )
2026-05-29 11:35:26 -05:00
02a7158a86
fix(opencode): retry stalled SSE streams ( #29837 )
2026-05-29 00:19:54 -05:00
abaca781d0
fix(opencode): enable adaptive reasoning for opus 4.7+ ( #29769 )
2026-05-28 12:19:34 -05:00
db5ae81835
chore: generate
2026-05-27 02:24:30 +00:00
ea6ac8dcdc
feat: add headerTimeout cfg option, default it on only for openai w/ default of 10s ( #29484 )
2026-05-26 21:22:24 -05:00
7860241c5d
fix(llm): split OpenAI reasoning summary blocks ( #29000 )
2026-05-23 20:06:45 -05:00
2536f1ca6e
fix(provider): type default model failures ( #28881 )
2026-05-22 23:53:23 +05:30
8984a228e4
chore: generate
2026-05-22 04:04:41 +00:00
c137656108
fix(vertex): Vertex (Antropic) provider: use .rep.googleapis.com for continental multi-region endpoints (us, eu) ( #28347 )
...
Co-authored-by: Aiden Cline <aidenpcline@gmail.com >
2026-05-21 23:03:24 -05:00
40d2e55d11
chore: generate
2026-05-21 03:37:50 +00:00
65d8951700
refactor(opencode): roll out serviceUse proxy across 14 services + tests ( #28576 )
2026-05-21 03:36:27 +00:00
f86a87af2e
chore: generate
2026-05-21 02:44:38 +00:00
892a5d3c7a
test(opencode): port provider.test.ts to it.instance ( #28565 )
2026-05-21 02:43:14 +00:00
a96033078f
chore: generate
2026-05-21 02:32:58 +00:00
f9d5db4935
test(opencode): port amazon-bedrock.test.ts to it.instance ( #28559 )
2026-05-20 22:31:42 -04:00
252b5427c8
Migrate provider lookup tests to instance fixtures
...
Migrate provider env precedence, model lookup, and default model tests to Effect-aware instance fixtures while keeping behavior unchanged.
2026-05-18 18:01:53 +00:00
3a2fa1ef84
Migrate custom provider tests to instance fixtures
...
Migrate the next custom provider/model config tests to Effect-aware instance fixtures while keeping timing neutral and behavior unchanged.
2026-05-18 17:49:26 +00:00
d38b210d2a
Migrate provider config tests to instance fixtures
...
Convert the first provider env/config/filtering tests to Effect-aware instance fixtures while keeping behavior unchanged and documenting neutral timing.
2026-05-18 13:22:59 -04:00
b8048cd162
Speed up targeted opencode tests
...
Reduce avoidable setup costs in slow opencode tests while preserving reviewed coverage and recording the benchmark evidence for follow-up test-suite work.
2026-05-18 16:18:29 +00:00
5ada30c092
Load models.dev snapshot from build global ( #28077 )
2026-05-17 21:59:44 -04:00
c066b249b9
refactor(instance): retire WithInstance adapter ( #27782 )
2026-05-16 01:30:07 +05:30
12968615a0
refactor(instance): remove legacy runtime fallback ( #27757 )
2026-05-15 23:05:44 +05:30
5241715718
feat(provider): add NVIDIA endpoints origin header ( #27394 )
2026-05-14 17:21:58 -05:00
e484325387
refactor(provider): use runtime flag for experimental models ( #27606 )
2026-05-15 02:48:01 +05:30
4d33853872
chore: generate
2026-05-14 04:25:32 +00:00
7163b29b30
fix: bug encountered when using azure gpt-5.5 w/ completions api ( #26222 )
2026-05-13 23:24:16 -05:00
Aiden Cline