5da7e801f2
feat(core): port v2 runtime fixes onto dev
...
Cherry-picks the packages/core changes from the v2 branch onto dev:
- combined ordered stdout/stderr in AppProcess + bash structured output
- edit/apply-patch return FileDiff info with status and line stats
- ignore no-op model switches; record reasoning timestamps
- return unexpected local tool defects to the model and continue
- keep OAuth account metadata out of request bodies
- nest OpenAI reasoning effort/summary options
- load OpenCode provider config asynchronously; batch plugin boot
- export latest public event manifest
Includes the supporting schema reasoning time field and regenerated
client/SDK types.
2026-06-27 00:07:25 -04:00
505d3a8c88
feat(core): split MCP timeout configuration ( #33977 )
...
Co-authored-by: Test <test@opencode.test >
2026-06-25 20:31:00 -05:00
c31dc9c7b7
refactor(schema): tighten public contracts ( #33771 )
2026-06-25 17:10:23 +00:00
bae9461364
fix(core): lower OpenAI text verbosity
2026-06-24 19:32:59 -04:00
d359001a2b
refactor(schema): extract public event definitions ( #33579 )
2026-06-24 16:43:17 -04:00
b406ebb11d
refactor(core): simplify model requests
2026-06-24 13:17:14 -04:00
55f00c0b50
refactor(core): simplify event model ( #33238 )
2026-06-21 10:34:57 -04:00
6b1b23d280
feat(opencode): support cwd on local MCP servers ( #30676 )
...
Co-authored-by: Aiden Cline <aidenpcline@gmail.com >
2026-06-11 16:05:45 -05:00
c306e804cd
fix(opencode): surface content-filter finish reason as visible error ( #31745 )
...
Co-authored-by: Aiden Cline <aidenpcline@gmail.com >
2026-06-11 10:41:11 -05:00
61270944d8
fix: recover from expired enterprise auth on remote config load ( #31661 )
2026-06-10 11:02:09 -04:00
309d613ee5
fix(core): accept deprecated reference config key ( #31659 )
2026-06-10 10:32:35 +00:00
1add617766
feat(core): add project reference guidance ( #31601 )
2026-06-10 04:08:26 +00:00
ec87cf82cb
refactor(core): consolidate references ( #31539 )
2026-06-09 16:08:58 +00:00
0722ed6208
feat: add "reasoning" as interleaved field option for vLLM providers ( #30477 )
...
Co-authored-by: Ben Sandbrook <1126483+delta9000@users.noreply.github.com >
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com >
2026-06-08 23:16:05 -05:00
78e00d13c6
fix(core): preserve model request semantics ( #30990 )
2026-06-05 14:23:31 -04:00
80da87da0e
feat(core): compact v2 session context ( #30986 )
2026-06-05 13:17:23 -04:00
6488b2ff11
fix(core): respect v2 default agents ( #30969 )
2026-06-05 10:47:31 -04:00
9e11b45908
feat(core): add command registry ( #30624 )
2026-06-04 02:57:43 -04:00
2f858757e9
docs: correct compaction prune default ( #30670 )
2026-06-03 22:37:39 -05:00
540e83b6c8
feat(core): add embedded v2 session runtime and tool foundation ( #30632 )
2026-06-03 23:02:17 -04:00
c7cc459436
feat(core): add skill registry and file agent loading ( #30617 )
2026-06-03 16:58:34 -04:00
ff0744b4af
refactor(core): nest model api id ( #30603 )
2026-06-03 14:11:38 -04:00
84806a8689
test(core): cover v1 provider option lowering ( #30599 )
2026-06-03 17:49:28 +00:00
82f03dd036
chore: generate
2026-06-03 17:35:02 +00:00
f60ac3b450
refactor(core): remove ai sdk option fields ( #30581 )
2026-06-03 17:32:58 +00:00
5b07e70ecf
chore: generate
2026-06-03 02:43:28 +00:00
fbda5fadda
refactor(core): move v1 schemas into core ( #30473 )
2026-06-03 02:42:13 +00:00
Dax Raad