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
