d8249f32a8
do not set temperature for claude models
2025-10-28 01:14:25 -04:00
a606e1d2ec
fix: dont set reasoning effort to medium for gpt-5-pro ( #3474 )
2025-10-27 10:50:57 -05:00
0eb899a950
chore: cleanup versioned zod imports ( #3460 )
...
Signed-off-by: Jérôme Benoit <jerome.benoit@sap.com >
Co-authored-by: opencode-agent[bot] <opencode-agent[bot]@users.noreply.github.com>
Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com >
2025-10-26 14:50:41 -05:00
c70e393c81
Remove claude-haiku-4.5 from default priority for GitHub Copilot session title generation
2025-10-26 01:21:34 -05:00
ae62bc8b1f
fix: timeout param that allows user to disable provider timeout ( #3443 )
2025-10-25 12:08:27 -05:00
5fec5ff424
fix: bedrock reasoning
2025-10-24 17:35:08 -05:00
56528493dc
codex does not have reasoning effort set
2025-10-24 00:29:34 -04:00
a7b43d82ab
add Amazon Nova models to us-* prefix requirement list ( #3357 )
2025-10-22 11:41:38 -05:00
9005fd31ed
tweak
2025-10-22 11:29:10 -05:00
d2bded23c3
tweak
2025-10-22 11:28:06 -05:00
c0cbc37f85
tweak: model priority
2025-10-22 11:12:32 -05:00
9df61055e2
change default title model
2025-10-22 10:41:08 -05:00
ca0f3902b7
fix: provider option transforms ( #3331 )
2025-10-21 11:08:21 -05:00
ddb2e6957c
added AU inference for bedrock haiku 4.5 ( #3206 )
...
Co-authored-by: Matt Gillard <matt-github@gillard.biz >
2025-10-16 23:48:41 -05:00
b24f4e3d2c
fix: timeout option ( #3229 )
2025-10-16 17:47:41 -05:00
536934548a
fix: use ai-sdk openai chat language model instead of completion language model ( #3204 )
2025-10-16 00:59:49 -05:00
ab8471a7ff
core: filter out alpha status models from provider list
2025-10-15 20:12:37 -04:00
e29d1d339c
updated bedrock provider for the new Australian sonnet 4.5 cross region inference ( #3050 )
...
Co-authored-by: Matt Gillard <matt-github@gillard.biz >
2025-10-15 11:09:22 -05:00
b8249cde4b
core: improve dependency management and error handling for more reliable builds
2025-10-14 01:33:25 -04:00
682d30bd12
fix: custom model ( #3156 )
2025-10-13 19:58:19 -05:00
59765e0157
fix: typecheck ( #3149 )
2025-10-13 14:51:12 -05:00
d0519be0d0
fix: add useCompletionUrls option to fix certain azure setups ( #2528 )
...
Co-authored-by: andreas.blass <andreas.blass@outlook.com >
Co-authored-by: GitHub Action <action@github.com >
2025-10-13 14:16:21 -05:00
36cf9b9922
fix: add timeout to fetch models.dev refresh request ( #3059 )
2025-10-12 00:20:22 -05:00
225adc46ba
feat: allow read tool to handle images ( #3052 )
2025-10-09 09:05:11 -05:00
71a7e8ef36
fix: max output tokens when using large thinking budget ( #2976 )
2025-10-04 23:38:41 -05:00
e7b6ffb314
feat: Vertex AI support; add google-vertex and google-vertex-anthropic providers ( #2347 )
2025-10-04 01:10:38 -04:00
bd0ba5ab88
turn on codex medium reasoning again
2025-10-03 06:46:07 -04:00
bd69c5aca8
codex should not have reasoning effort
2025-10-01 05:06:37 -04:00
89167ae387
respect model id in opencode.json ( #2833 )
2025-09-27 17:09:21 -05:00
f5c7a94abe
turn reasoning summaries back on by default for zen
2025-09-26 01:37:44 -04:00
7ec3900208
core: enable reasoning.encrypted_content and reasoningSummary for opencode provider\ntui: adjust editorY position calculation
2025-09-26 01:27:53 -04:00
d47feb9969
tweak: include usage by default for openai compatible providers ( #2788 )
2025-09-25 21:06:58 -05:00
71b43fd02e
fix codex errors
2025-09-23 16:56:40 -04:00
079095d7a9
core: filter models without keys in opencode provider
2025-09-21 04:43:32 -04:00
d4c01f858b
disable thinking for opencode zen and gpt-5 temporarily
2025-09-16 13:49:37 -04:00
2d5bd26a59
feat: enhance provider model mapping and reasoning capabilities
...
- Add npm package tracking to provider model mapping
- Implement special handling for opencode provider with reasoning
- Update provider options mapping to use npm package names
2025-09-16 03:10:17 -04:00
c1b4e1f19d
Upgrade to Zod v4 ( #2605 )
...
Co-authored-by: GitHub Action <action@github.com >
2025-09-15 03:12:07 -04:00
f5b3992479
properly support model level npm definition
2025-09-11 16:22:44 -04:00
a3513244f1
wip: zen
2025-09-09 15:47:28 -04:00
02e8242c3b
Remove debug logging
2025-09-09 03:35:09 -04:00
0f263bfefe
Hide experimental models
2025-09-09 03:16:44 -04:00
d8fd7b155f
fix: aws bedrock add check for govcloud ( #2495 )
2025-09-08 11:54:06 -05:00
4654fb88de
fix: max output tokens when setting budget thinking tokens ( #2056 )
...
Co-authored-by: rekram1-node <aidenpcline@gmail.com >
2025-09-07 13:15:53 -05:00
dc99005e65
fix: default to last used model ( #2443 )
2025-09-05 17:25:25 -05:00
4c261ab1db
switch gpt-5 to default to codex prompt + high reasoning
2025-09-01 21:46:03 -04:00
f993541e0b
Refactor to support multiple instances inside single opencode process ( #2360 )
...
This release has a bunch of minor breaking changes if you are using opencode plugins or sdk
1. storage events have been removed (we might bring this back but had some issues)
2. concept of `app` is gone - there is a new concept called `project` and endpoints to list projects and get the current project
3. plugin receives `directory` which is cwd and `worktree` which is where the root of the project is if it's a git repo
4. the session.chat function has been renamed to session.prompt in sdk. it no longer requires model to be passed in (model is now an object)
5. every endpoint takes an optional `directory` parameter to operate as though opencode is running in that directory
2025-09-01 17:15:49 -04:00
e4cc05a975
feat: Allow provider timeout override ( #1982 )
2025-08-31 14:06:02 -04:00
133fe41cd5
slash commands ( #2157 )
...
Co-authored-by: adamdotdevin <2363879+adamdottv@users.noreply.github.com >
2025-08-22 17:04:28 -04:00
aa10f8a7f6
sonic model
2025-08-20 01:02:41 -04:00
796245d146
blacklist gpt-5-chat-latest ( #2048 )
2025-08-18 17:50:38 -04:00
Dax Raad