Aiden Cline
3d2ef28fa8
add topK function to transform, add temp defaults for glm and minimax
2025-12-13 23:27:11 -06:00
Aiden Cline
d4cfbd8219
chore: reduce duplication of field in transform
2025-12-13 18:07:22 -06:00
Aiden Cline
f9674793af
tweak: 5.1 -> 5. in transform
2025-12-12 15:17:11 -06:00
Aiden Cline
909013320b
tweak: 5.1 -> 5. reasoning effort match
2025-12-12 13:21:57 -06:00
Aiden Cline
342595e0f7
tweak: setting chat_template_args in transform
2025-12-11 16:22:10 -06:00
Aiden Cline
7b4f852f33
ignore: tmp transform exclusion
2025-12-10 21:18:19 -06:00
Aiden Cline
439aebb4e9
tweak: correct thinkingLevel
2025-12-10 21:13:10 -06:00
Seb Duerr
df55ad89ab
Add Cerebras integration header with opencode identifier ( #5354 )
2025-12-10 19:36:58 -06:00
Dax Raad
ffc4d53923
add models.dev family
2025-12-10 14:30:28 -05:00
Aiden Cline
18d3c054a3
more interleaved thinking fixes ( #5334 )
2025-12-10 13:29:26 -06:00
Aiden Cline
59c5da9b6c
tweak: set gemini thinkingLevel to high by default
2025-12-10 13:09:27 -06:00
Tom Aylott
117de64f39
fix: upgrade OpenRouter sdk pkg ( #5302 )
...
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
2025-12-10 13:02:26 -06:00
Aiden Cline
df64612d54
better interleaved thinking support ( #5298 )
2025-12-09 16:32:12 -06:00
Aiden Cline
f8bd4ff705
core: refactor providerOptions function to accept Provider.Model for cleaner API
2025-12-09 01:25:36 -06:00
Jérôme Benoit
52bb43eebd
fix: SAP AI Core Vercel AI SDK v2 support ( #5180 )
...
Signed-off-by: Jérôme Benoit <jerome.benoit@sap.com>
Signed-off-by: Jérôme Benoit <jerome.benoit@piment-noir.org>
2025-12-08 11:27:47 -06:00
Aiden Cline
a3bb4a3c85
pdf support in read tool ( #5222 )
...
Co-authored-by: ammi1378 <ammi1378@users.noreply.github.com>
2025-12-07 21:54:00 -06:00
Aiden Cline
c30b1130ee
fix: provider url merging logic
2025-12-07 13:01:05 -06:00
Dax Raad
1b05d5dd8e
tui: prevent deprecated models from appearing in model picker
2025-12-06 18:18:45 -05:00
Julian Visser
52db0f23a6
fix : #5064 ProviderInitError github-copilot-enterprise ( #5123 )
2025-12-05 09:53:32 -06:00
Jérôme Benoit
bef4fdfc4b
fix: add getModel to SAP AI Core provider for correct SDK initialization ( #5086 )
...
Signed-off-by: Jérôme Benoit <jerome.benoit@piment-noir.org>
2025-12-04 22:43:22 -06:00
Dax Raad
668d5a76d5
core: ensure model npm package falls back to dev models config when not explicitly defined
2025-12-04 15:39:52 -05:00
Jérôme Benoit
b9c1f10016
feat: Add SAP AI Core provider support ( #5023 )
...
Signed-off-by: Jérôme Benoit <jerome.benoit@piment-noir.org>
2025-12-04 14:07:23 -06:00
Dax Raad
10cc15aabe
fix anthropic api key error
2025-12-03 23:18:24 -05:00
Jakub Matjanowski
46790e57e9
feat: Enhance DeepSeek reasoning content handling ( #4975 )
...
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
2025-12-03 21:31:36 -06:00
Aiden Cline
598d63db63
fix: dax typo
2025-12-03 20:39:11 -06:00
Dax
6d3fc63658
core: refactor provider and model system ( #5033 )
...
Co-authored-by: opencode-agent[bot] <opencode-agent[bot]@users.noreply.github.com>
Co-authored-by: thdxr <thdxr@users.noreply.github.com>
2025-12-03 21:09:03 -05:00
Dax Raad
ee4437ff32
core: add provider test coverage for upcoming refactor
...
Add comprehensive test suite for Provider module to ensure safe
refactoring of provider internals. Tests cover:
- Provider loading from env vars and config
- Provider filtering (disabled_providers, enabled_providers)
- Model whitelist/blacklist
- Model aliasing and custom providers
- getModel, getProvider, closest, defaultModel functions
Also adds Env module for instance-scoped environment variable access,
enabling isolated test environments without global state pollution.
2025-12-03 18:30:42 -05:00
Aiden Cline
b457923970
core: fix GitHub Copilot Enterprise authentication failing with sdk.chat undefined error
2025-12-02 23:37:10 -06:00
Aiden Cline
0331931f56
fix: sanitize more invalid schema cases for gemini models
2025-12-01 16:19:10 -06:00
Aiden Cline
f1bb5870ce
fix: copilot responses bug w/ gpt 5 mini
2025-12-01 14:36:49 -06:00
Aiden Cline
027d43b5ea
fix case where opencode wasn't retrying
2025-12-01 13:02:33 -06:00
Aiden Cline
b1b82977ec
tweak: better err msgs
2025-12-01 01:33:32 -06:00
Aiden Cline
6e2379a28c
get codex working in copilot ( #4914 )
...
Co-authored-by: OpeOginni <107570612+OpeOginni@users.noreply.github.com>
Co-authored-by: GitHub Action <action@github.com>
2025-11-29 21:47:29 -06:00
Dax Raad
813d287a09
core: add explore agent for fast codebase navigation and improve task UI display
2025-11-28 21:13:07 -05:00
Dmitry Halushka
ee946d8128
fix: transform MCP tool schemas for Google/Gemini compatibility ( #4538 )
...
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
Co-authored-by: Github Action <action@github.com>
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com>
2025-11-26 00:58:20 -06:00
Aiden Cline
b44971668c
fix: global prefix handling w/ aws bedrock ( #4757 )
2025-11-26 00:21:59 +00:00
Shantur Rathore
69c2dd53ad
config: add setCacheKey in provider options ( #4738 )
...
Co-authored-by: GitHub Action <action@github.com>
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com>
2025-11-25 17:53:56 -06:00
Aiden Cline
16dbac6026
Revert "config: add setCacheKey in provider options ( #4654 )"
...
This reverts commit 9b6d03c497
2025-11-24 22:30:56 -06:00
Shantur Rathore
9b6d03c497
config: add setCacheKey in provider options ( #4654 )
...
Co-authored-by: GitHub Action <action@github.com>
2025-11-24 22:20:52 -06:00
Aiden Cline
23a721f0a2
remove hardcoded openrouter provider
2025-11-24 16:11:12 -06:00
Aiden Cline
9e44085a69
adjust bundled provider logic, fix tree shaking stuff ( #4708 )
2025-11-24 15:48:54 -06:00
Adam
acf1dd8500
wip(share): more styling
2025-11-24 15:10:40 -06:00
Aiden Cline
ac1e2bfd49
bump copilot plugin, give better error message for copilot ( #4678 )
2025-11-24 00:40:15 -06:00
Huang Qi
b4fd4bb257
fix: add explicit fallback model and prevent direct opencode provider calls ( #4653 )
...
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
2025-11-23 22:51:15 -06:00
Frank
bbc9142fc5
wip: zen
2025-11-23 15:21:47 -05:00
Aiden Cline
30ffcaa667
tweak: start bundling in some ai-sdk packages ( #4649 )
2025-11-23 01:29:20 -06:00
Dax Raad
75c29d4d1c
summary optimizaitons
2025-11-22 11:32:49 -05:00
Frank
e34df15ff5
update logic for local and dev providers
2025-11-21 13:31:33 -05:00
Ian Maurer
e018e16898
fix(cli): ensure clean exit on provider/model errors ( #4223 )
...
Co-authored-by: GitHub Action <action@github.com>
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
2025-11-21 02:01:19 -06:00
Aiden Cline
fffe20cbe5
add provider whitelist
2025-11-21 01:24:44 -06:00
geril07
c0d9f21c0f
feat: whitelist/blacklist config options for provider ( #3416 )
...
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
2025-11-21 01:01:30 -06:00
Dax
23ea8ba1ce
Tui onboarding ( #4569 )
...
Co-authored-by: GitHub Action <action@github.com>
2025-11-21 00:21:06 -05:00
Aiden Cline
cf934357c9
fix: make use openrouter ai sdk package to fix interlevened thinking models
2025-11-20 16:32:44 -06:00
Aiden Cline
97893bd7e6
tweak: make /export go to cwd
2025-11-19 22:45:40 -06:00
Aiden Cline
51bba6e634
tweak: default to disabling fetch timeout in provider options
2025-11-19 16:20:29 -06:00
Aiden Cline
9d068c20bb
fix: openrouter ai sdk package support
2025-11-19 14:22:51 -06:00
Tommy D. Rossi
9de1242d9b
fix: show reasoning summaries for gemini models ( #4491 )
...
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-11-19 11:25:18 -06:00
Aiden Cline
a9981441ae
tweak: use temperature 1 for gemini 3 pro
2025-11-18 11:49:39 -06:00
Dax Raad
7c0cc94023
rework default model
2025-11-18 12:01:41 -05:00
Albert O'Shea
5e13527416
feat: nix support for the nix folks ( #3924 )
...
Co-authored-by: opencode <opencode@sst.dev>
Co-authored-by: opencode-agent[bot] <opencode-agent[bot]@users.noreply.github.com>
2025-11-18 00:46:49 -06:00
Dax Raad
bc232045a1
respect server suggestion for default model
2025-11-17 20:53:48 -05:00
Youssef Achy
58cc5cdf2a
add support for azure cognitive services provider ( #4397 )
2025-11-17 00:01:45 -06:00
Aiden Cline
25678fa504
fix: vercel gateway options
2025-11-16 18:39:31 -06:00
Aiden Cline
cf266f6162
fix: promptCacheKey set unnecessarily
2025-11-16 14:32:57 -06:00
xiaojie.zj
0e4703b227
add: add zenmux doc and header ( #3597 )
...
Co-authored-by: xiaojie.zj <xiaojie.zj@antgroup.com>
2025-11-15 21:37:30 -06:00
Frank
f5230d1f02
fix: incorrect sonnet price calculation
2025-11-14 18:46:43 -05:00
GitHub Action
078111bd96
chore: format code
2025-11-14 22:44:36 +00:00
sredfern
736f8882f5
fix(provider): support local file paths for custom providers ( #4323 )
2025-11-14 16:43:59 -06:00
Aiden Cline
b939470302
fix: add azure exclusion
2025-11-14 11:54:00 -06:00
Aiden Cline
ef4b2baedc
set verbosity to low for gpt-5.1 (match codex)
2025-11-14 11:52:29 -06:00
Shantur Rathore
986c60353e
set promptCacheKey for openai compatible providers ( #4203 )
...
Co-authored-by: GitHub Action <action@github.com>
2025-11-14 11:41:01 -06:00
Frank
1d8330331c
zen: use gpt-5-nano as small model
2025-11-14 00:59:00 -05:00
Aiden Cline
0c51feb9c2
fix: max tokens when using models like opus with providers other than anthropic ( #4307 )
2025-11-13 16:39:09 -06:00
Aiden Cline
8addaa7e08
fix: custom model name merging
2025-11-12 13:55:13 -06:00
Aiden Cline
c5e096c76a
fix: costs being 0 when using custom model id overrides ( #4219 )
2025-11-11 15:58:14 -06:00
OpeOginni
bba72c82ae
Fix/google vertex configs ( #4169 )
...
Co-authored-by: GitHub Action <action@github.com>
2025-11-10 13:25:03 -06:00
Dax Raad
4d20e1c3c6
Merge remote-tracking branch 'origin/dev' into dev
2025-11-08 20:21:02 -05:00
Dax Raad
4bb7ea9127
improve startup speed
2025-11-08 20:18:36 -05:00
GitHub Action
34ff87d504
chore: format code
2025-11-08 01:59:02 +00:00
Nicolai van der Smagt
9e04ff013c
fix: resolve Mistral API compatibility issues ( #2440 )
...
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
2025-11-06 20:05:59 -05:00
Dax Raad
25f31f3096
codex tweaks
2025-11-06 19:14:01 -05:00
Nicolai van der Smagt
a2ab019317
fix: resolve Mistral API compatibility issues ( #2440 )
...
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
2025-11-06 16:53:02 -06:00
Dax Raad
1ea3a8eb9b
big format
2025-11-06 13:03:12 -05:00
Aiden Cline
af7b9e77d1
fix: eu-west-2 aws bedrock issue
2025-11-05 10:14:08 -06:00
Ola
fe94bb8e50
feat(provider): add GitHub Enterprise support for Copilot ( #2522 )
...
Co-authored-by: Jon-Mikkel Korsvik <48263282+jkorsvik@users.noreply.github.com>
Co-authored-by: GitHub Action <action@github.com>
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
2025-11-04 15:36:12 -06:00
Aiden Cline
46d675b980
tweak: filter out deprecated models
2025-10-31 10:48:51 -05:00
Filip
51e4c9fc4c
add optional headers field to model config ( #3546 )
2025-10-30 23:35:26 -05:00
Dax Raad
d8249f32a8
do not set temperature for claude models
2025-10-28 01:14:25 -04:00
Aurelien Ribon
a606e1d2ec
fix: dont set reasoning effort to medium for gpt-5-pro ( #3474 )
2025-10-27 10:50:57 -05:00
Jérôme Benoit
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
Aiden Cline
c70e393c81
Remove claude-haiku-4.5 from default priority for GitHub Copilot session title generation
2025-10-26 01:21:34 -05:00
Paulo Edgar Castro
ae62bc8b1f
fix: timeout param that allows user to disable provider timeout ( #3443 )
2025-10-25 12:08:27 -05:00
Aiden Cline
5fec5ff424
fix: bedrock reasoning
2025-10-24 17:35:08 -05:00
Dax Raad
56528493dc
codex does not have reasoning effort set
2025-10-24 00:29:34 -04:00
theVinchi
a7b43d82ab
add Amazon Nova models to us-* prefix requirement list ( #3357 )
2025-10-22 11:41:38 -05:00
Aiden Cline
9005fd31ed
tweak
2025-10-22 11:29:10 -05:00
Aiden Cline
d2bded23c3
tweak
2025-10-22 11:28:06 -05:00
Aiden Cline
c0cbc37f85
tweak: model priority
2025-10-22 11:12:32 -05:00
Aiden Cline
9df61055e2
change default title model
2025-10-22 10:41:08 -05:00
Aiden Cline
ca0f3902b7
fix: provider option transforms ( #3331 )
2025-10-21 11:08:21 -05:00
Matt Gillard
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
Aiden Cline
b24f4e3d2c
fix: timeout option ( #3229 )
2025-10-16 17:47:41 -05:00
seridescent
536934548a
fix: use ai-sdk openai chat language model instead of completion language model ( #3204 )
2025-10-16 00:59:49 -05:00
Dax Raad
ab8471a7ff
core: filter out alpha status models from provider list
2025-10-15 20:12:37 -04:00
Matt Gillard
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
Dax Raad
b8249cde4b
core: improve dependency management and error handling for more reliable builds
2025-10-14 01:33:25 -04:00
Aiden Cline
682d30bd12
fix: custom model ( #3156 )
2025-10-13 19:58:19 -05:00
Aiden Cline
59765e0157
fix: typecheck ( #3149 )
2025-10-13 14:51:12 -05:00
AB
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
OpeOginni
36cf9b9922
fix: add timeout to fetch models.dev refresh request ( #3059 )
2025-10-12 00:20:22 -05:00
Aiden Cline
225adc46ba
feat: allow read tool to handle images ( #3052 )
2025-10-09 09:05:11 -05:00
Aiden Cline
71a7e8ef36
fix: max output tokens when using large thinking budget ( #2976 )
2025-10-04 23:38:41 -05:00
Yuku Kotani
e7b6ffb314
feat: Vertex AI support; add google-vertex and google-vertex-anthropic providers ( #2347 )
2025-10-04 01:10:38 -04:00
Dax Raad
bd0ba5ab88
turn on codex medium reasoning again
2025-10-03 06:46:07 -04:00
Dax Raad
bd69c5aca8
codex should not have reasoning effort
2025-10-01 05:06:37 -04:00
Aiden Cline
89167ae387
respect model id in opencode.json ( #2833 )
2025-09-27 17:09:21 -05:00
Dax Raad
f5c7a94abe
turn reasoning summaries back on by default for zen
2025-09-26 01:37:44 -04:00
Dax Raad
7ec3900208
core: enable reasoning.encrypted_content and reasoningSummary for opencode provider\ntui: adjust editorY position calculation
2025-09-26 01:27:53 -04:00
Aiden Cline
d47feb9969
tweak: include usage by default for openai compatible providers ( #2788 )
2025-09-25 21:06:58 -05:00
Dax Raad
71b43fd02e
fix codex errors
2025-09-23 16:56:40 -04:00
Dax Raad
079095d7a9
core: filter models without keys in opencode provider
2025-09-21 04:43:32 -04:00
Dax Raad
d4c01f858b
disable thinking for opencode zen and gpt-5 temporarily
2025-09-16 13:49:37 -04:00
Dax Raad
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
Dax
c1b4e1f19d
Upgrade to Zod v4 ( #2605 )
...
Co-authored-by: GitHub Action <action@github.com>
2025-09-15 03:12:07 -04:00
Dax Raad
f5b3992479
properly support model level npm definition
2025-09-11 16:22:44 -04:00
Frank
a3513244f1
wip: zen
2025-09-09 15:47:28 -04:00
Frank
02e8242c3b
Remove debug logging
2025-09-09 03:35:09 -04:00
Frank
0f263bfefe
Hide experimental models
2025-09-09 03:16:44 -04:00
Douglas Dennis
d8fd7b155f
fix: aws bedrock add check for govcloud ( #2495 )
2025-09-08 11:54:06 -05:00
Ytzhak
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
Aiden Cline
dc99005e65
fix: default to last used model ( #2443 )
2025-09-05 17:25:25 -05:00
Dax Raad
4c261ab1db
switch gpt-5 to default to codex prompt + high reasoning
2025-09-01 21:46:03 -04:00
Dax
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
Beshoy Girgis
e4cc05a975
feat: Allow provider timeout override ( #1982 )
2025-08-31 14:06:02 -04:00
Dax
133fe41cd5
slash commands ( #2157 )
...
Co-authored-by: adamdotdevin <2363879+adamdottv@users.noreply.github.com>
2025-08-22 17:04:28 -04:00
Dax Raad
aa10f8a7f6
sonic model
2025-08-20 01:02:41 -04:00
Aiden Cline
796245d146
blacklist gpt-5-chat-latest ( #2048 )
2025-08-18 17:50:38 -04:00
Dax Raad
a433766a31
allow plugins to create custom auth providers
2025-08-14 16:25:08 -04:00
Aiden Cline
b5d61b77f7
fix: reasoning not supported ( #1882 )
2025-08-13 06:26:07 -05:00
Dax Raad
5785ded6e2
add openai prompt cache key
2025-08-12 17:37:15 -04:00
Dax Raad
5f34dcc792
azure reasoning effort
2025-08-11 23:04:32 -04:00
Dax Raad
dac1506680
update anthropic prompt and variables
2025-08-11 21:01:33 -04:00
Dax Raad
0ce7d92a8b
ignore: fix share page
2025-08-11 16:12:26 -04:00
Dax Raad
279edb6f24
fix azure gpt config
2025-08-11 10:56:16 -04:00
adamdotdevin
b8d2aebf09
feat: thinking blocks rendered in tui and share page
2025-08-10 19:25:03 -05:00
Dax Raad
d3ff66e911
use minimal reasoning effort for gpt-5
2025-08-09 15:38:48 -04:00
Dax Raad
53630ebdce
gpt-5 lower verbosity
2025-08-08 20:42:22 -04:00
Dax Raad
4f164c53d2
temporary fix for max output token
2025-08-07 22:54:59 -04:00
Dax Raad
ea4e1913c0
increase models.dev polling interval to hourly
2025-08-03 14:58:35 -04:00
Dax Raad
ca031278ca
wip: plugins
2025-08-02 18:50:19 -04:00
Aiden Cline
0b132c032a
ignore: fix dev branch ( #1529 )
2025-08-02 09:11:38 -05:00
Ricardo Gonzalez
8f45a0e227
feat(models): enable Kimi k2 ⇄ Claude trajectory handoff ( #1525 )
2025-08-01 23:05:06 -04:00
Dax Raad
71cd84dbbb
force models.dev refresh on auth login
2025-08-01 17:48:01 -04:00
Dax Raad
e1b7e25f4d
make top_p configurable
2025-08-01 17:03:33 -04:00
Dax Raad
50e4b3e6a7
add version to user-agent
2025-08-01 12:18:09 -04:00
Dax Raad
a0d2e53bde
poll for models.dev changes
2025-07-31 23:47:42 -04:00
Dax Raad
851e900982
add user agent for models.dev request
2025-07-31 22:00:45 -04:00
Simon Westlin Green
b09ebf4645
Use responses API for Azure ( #1428 )
2025-07-30 23:22:59 -04:00
Josh
4a221868da
Add http-referer header for vercel ai gateway requests ( #1403 )
2025-07-30 23:22:24 -04:00
Dax Raad
6b7058fe1c
qwen optimizations it works good now
2025-07-25 18:31:08 -04:00
Dax Raad
e97613ef9f
allow temperature to be configured per mode
2025-07-25 13:29:44 -04:00
Dominik Engelhardt
827469c725
fix: apply content-level caching for non-anthropic providers ( #1305 )
2025-07-25 12:19:44 -04:00
Dax Raad
8dcd39f5b7
real life totally configurabl ai subasians
2025-07-24 21:21:02 -04:00
Jesse van der Pluijm
34f6ffe1d7
Check if modelID includes "claude" for antropic/claude prompt caching ( #1284 )
2025-07-24 11:31:28 -04:00
Dax Raad
6465c9c44a
fix openrouter caching
2025-07-19 15:11:21 -04:00
Dax Raad
86d5b25d18
pass through model.options properly without having to nest it under provider name. you may have to update your configs see https://opencode.ai/docs/models/#openrouter for an example
2025-07-19 12:41:58 -04:00
Rami Chowdhury
f1da70b1de
feat(provider): add Gemini tool schema sanitization ( #1132 )
2025-07-18 16:02:54 -04:00
Timo Clasen
18abcab208
feat(config): make small model configurable ( #1030 )
2025-07-18 14:16:50 -04:00
adamdotdevin
9964d8e6c0
fix: model cost overrides
2025-07-18 05:08:35 -05:00
Wendell Misiedjan
e681d610de
feat: support AWS_BEARER_TOKEN_BEDROCK for amazon bedrock provider autoloading ( #1094 )
2025-07-17 09:12:30 -05:00
Dax Raad
b1ab641905
add small model for title generation
2025-07-15 14:00:52 -04:00
Dax Raad
4b2ce14ff3
bring back task tool
2025-07-15 00:05:54 -04:00
zWing
3249420ad1
fix: avoid overwriting the provider.option.baseURL ( #880 )
2025-07-11 18:01:28 -04:00
Timo Clasen
21fbf21cb6
fix(copilot): add vision request header ( #773 )
2025-07-08 14:01:54 -05:00
Dax
f884766445
v2 message format and upgrade to ai sdk v5 ( #743 )
...
Co-authored-by: GitHub Action <action@github.com>
Co-authored-by: Liang-Shih Lin <liangshihlin@proton.me>
Co-authored-by: Dominik Engelhardt <dominikengelhardt@ymail.com>
Co-authored-by: Jay V <air@live.ca>
Co-authored-by: adamdottv <2363879+adamdottv@users.noreply.github.com>
2025-07-07 15:53:43 -04:00
Dax Raad
969ad80ed2
fix openrouter caching with anthropic, should be a lot cheaper
2025-07-05 11:39:54 -04:00
adamdottv
f1c925795d
fix: typescript error
2025-07-02 16:08:41 -05:00
Ciaran McAleer
63e783ef79
Changed handling of OpenRouter requests to add some custom headers so that it can see the app ( #613 )
...
Co-authored-by: Dax Raad <d@ironbay.co>
2025-07-02 14:43:59 -04:00
Mark Huggins
b89d4a16fd
fix: Copilot Premium Requests ( #595 )
2025-07-02 12:04:53 -04:00
Dax Raad
fea56d8de6
fix loading api key from env for openai compatible providers
2025-06-30 19:07:51 -04:00
adamdottv
58baca2a5b
chore: typescript error
2025-06-30 15:46:18 -05:00
adamdottv
ef73926db6
chore: include model release date
2025-06-30 15:46:18 -05:00
Jeremy Mack
c573270e66
chore: remove duplicate EditTool in TOOLS array ( #556 )
2025-06-30 15:32:15 -04:00
Timo Clasen
d090c08ef0
feat: update user and agent messages width and alignment ( #515 )
...
Co-authored-by: adamdottv <2363879+adamdottv@users.noreply.github.com>
2025-06-30 11:57:56 -05:00
Dmytro Yankovskyi
68e82e4d94
fix( #467 ): more granular bedrock modelID based on aws region ( #482 )
2025-06-30 11:12:30 -04:00
Dax Raad
ca48a4f0fb
better amazon bedrock caching with anthropic models
2025-06-29 19:27:07 -04:00
adamdottv
79bbf90b72
chore: rework openapi spec and use stainless sdk
2025-06-27 14:26:25 -05:00
Dax Raad
8ca713b737
disable task tool temporarily
2025-06-26 18:27:49 -04:00
Dax Raad
4e7f6c47fd
fix codex not working
2025-06-25 10:01:35 -04:00
Dax Raad
7dd0918d32
remove accidental opanai autoloader
2025-06-24 21:11:11 -04:00
Dax Raad
7050cc0ac3
ignore: fix type errors
2025-06-24 11:09:36 -04:00
Dax Raad
4d3d63294d
externalize github copilot code
2025-06-24 10:42:19 -04:00
GitMurf
0dc586faef
fix: typescript error (any) from models ( #347 )
2025-06-23 18:44:57 -04:00
Dax Raad
bc34f08333
bundle models.dev at build time and ignore refresh errors
2025-06-23 14:50:19 -04:00
GitMurf
5140e83012
feat(copilot): edit headers for better rate limit avoidance ( #321 )
2025-06-23 10:44:19 -04:00
Dax Raad
f0e19a6542
aws autoload include more env vars
2025-06-22 20:16:10 -04:00
Martin Palma
6e6fe6e013
Add Github Copilot OAuth authentication flow ( #305 )
2025-06-22 19:11:37 -04:00
Márk Magyar
137e964131
fix: session title generation ( #293 )
2025-06-21 14:32:11 -05:00
Dax Raad
1684042fb6
huge optimization for token usage with anthropic
2025-06-20 22:43:04 -04:00
Saatvik Arya
b8144c5654
fix: return false for missing AWS_PROFILE in amazon-bedrock provider ( #277 )
2025-06-20 17:27:27 -04:00
