e9484d7368
plugin(hook): add task tool execution hooks and command context tracking ( #5642 )
2025-12-16 19:28:09 -06:00
1e0e9549ce
github: add configurable mentions input ( #5655 )
2025-12-16 19:14:50 -06:00
603f2cd47f
fix: user invoked subtasks causing tool_use or missing thinking signa… ( #5650 )
2025-12-16 15:42:21 -06:00
47459c2816
feat: add experimental oxfmt formatter ( #5620 )
2025-12-16 14:43:14 -06:00
ece7816a60
fix: git branch filewatcher, add flag to completely disable watcher
publish-github-action / publish (push) Has been cancelled
Update Nix Hashes / update (push) Has been cancelled
2025-12-16 14:31:09 -06:00
254a5e07fd
core: update plugin dependency and config loading for .opencode directory support
2025-12-16 15:06:50 -05:00
bd3580f627
core: fix Tauri desktop app SSE connection timeout
...
- Add heartbeat events to /global/event and /event SSE endpoints
- Send server.heartbeat event every 30s to prevent WKWebView 60s timeout
- Fixes desktop app disconnecting from global events after 1 minute
2025-12-16 14:45:03 -05:00
ca052fdec3
tui: fix autocomplete file loading and update dependencies
2025-12-16 13:37:22 -05:00
7b3a87c40f
fix: enable shell alias expansion in ! command ( #5621 )
2025-12-16 11:32:31 -06:00
780439d6d2
fix: github install cmd if repo has . in it
2025-12-16 11:19:18 -06:00
a493a99de1
fix: use system prompt field from prompt input ( #5633 )
...
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
2025-12-16 10:52:22 -06:00
26a71d29aa
fix: preserve argument boundaries in run command ( #4979 )
2025-12-16 06:21:51 -06:00
670f8a0771
tui: fix dialog select items taking up 2 lines when truncated
...
Prevents text wrapping in dialog select options by removing wrapMode,
ensuring truncated text stays on single line and maintains proper timestamp visibility
2025-12-15 22:57:52 -05:00
7d98484c51
fix: debounce LSP diagnostics to get complete results ( #5600 )
2025-12-15 21:26:59 -06:00
3058eb76cf
fix: rejoin system prompt if experimental plugin hook triggers to preserve caching ( #5550 )
...
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-12-15 20:00:26 -06:00
f5eda26794
tui: update dialog context and server to use new single dialog system
2025-12-15 19:35:19 -05:00
2e85975124
fix(win32): Normalise LSP paths on windows (fixes lua) ( #5597 )
2025-12-15 18:01:03 -06:00
8ddb0fcd82
tweak: add .catch for extractZip calls
2025-12-15 17:41:28 -06:00
b44ff619fb
fix(win32): Missing LSP can now unzip on windows ( #5594 )
2025-12-15 17:29:30 -06:00
93b87e3d73
fix(win32): correct ElixirLS extension typo ( #5590 )
2025-12-15 16:47:27 -06:00
38b2e646b2
fix(win32): use path.delimiter for PATH separator in LSP server lookups ( #5589 )
2025-12-15 16:39:42 -06:00
0cda6742de
fix(windows): opencode github install ( #5587 )
2025-12-15 16:12:54 -06:00
915fded8a1
fix: restore ability to bind keys for model_cycle_favorite model_cycle_favorite_reverse ( resolves #5198 ) ( #5202 )
2025-12-15 16:03:50 -06:00
364cfe2993
tweak: add model flag support for agent create command
2025-12-15 14:55:59 -06:00
f97f184807
fix: record shell mode in history ( resolves #5454 ) ( #5551 )
2025-12-15 14:42:17 -06:00
682a721975
add ability to set topK
2025-12-15 14:34:56 -06:00
98c97b99fb
tweak: prioritize fuzzysort results that start with user input ( #5571 )
2025-12-15 14:22:37 -06:00
fb2c26e7b2
core: fix server response handling to prevent connection timeouts
2025-12-15 15:07:20 -05:00
91fa6a804d
core: fix message caching for Anthropic models to improve response consistency
2025-12-15 14:33:14 -05:00
6d86d7f8b2
fix: terminal in desktop
2025-12-15 13:09:13 -06:00
c8ad4ed1e8
feat: add F# language server support ( #5549 )
2025-12-15 10:52:16 -06:00
50a574f7fc
core: reorganize agent configuration to separate primary agents (build, plan) from subagents
2025-12-15 09:58:23 -05:00
e9e1f3302e
Provider fix, anthropic Errorhandling if empty image file is read ( #5521 )
2025-12-14 23:56:47 -06:00
e276eecdb2
fix: input lip visibility for transparent themes ( #5544 )
2025-12-14 23:10:33 -06:00
b77b643b18
fix(edit): add per-file lock to prevent read-before-write race ( #4388 )
2025-12-14 23:01:50 -06:00
c75944ba1f
ignore: fix debug var in last commit
2025-12-14 22:59:30 -06:00
f6db7bfabe
Add dismiss button to Getting Started box ( #5543 )
...
Co-authored-by: opencode-agent[bot] <opencode-agent[bot]@users.noreply.github.com>
Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com >
Co-authored-by: Aiden Cline <aidenpcline@gmail.com >
2025-12-14 22:58:26 -06:00
bf49451930
feat: restore experimental.chat.messages.transform and add experimental.chat.system.transform hooks ( #5542 )
2025-12-14 22:51:11 -06:00
f757fd55a1
fix(session): fix unshare command not clearing share state ( #5523 )
2025-12-14 22:05:06 -06:00
798a172a4b
wip(desktop): progress
2025-12-14 21:38:58 -06:00
16416d139c
feat(cli): auto-submit prompt when using --prompt flag ( #4510 )
2025-12-14 21:06:04 -06:00
712c8e9c40
ci: fix test failures in CI by pre-populating models cache
...
Tests were failing in CI because the models.json cache file doesn't exist
and the data() macro fallback only works at build time, not runtime.
The preload now pre-fetches models.json and disables the background
refresh to prevent race conditions during test execution.
2025-12-14 21:23:45 -05:00
c9c6b26a2e
LLM cleanup ( #5462 )
...
Co-authored-by: GitHub Action <action@github.com >
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com >
2025-12-14 21:11:30 -05:00
f426e98947
fix(tui): --continue selects wrong session ( #5513 )
2025-12-14 19:50:54 -06:00
42d900ddbd
feat: add experimental.continue_loop_on_deny config option ( #4729 )
...
Co-authored-by: Aiden Cline <aidenpcline@gmail.com >
2025-12-14 17:13:32 -06:00
e3bd8cd9ed
tweak: fallback to provider default for temperature
2025-12-14 11:57:12 -06:00
70d06daef0
chore: format code
2025-12-14 17:48:34 +00:00
f78ea561c9
fix: ensure input borders are drawn in transparent themes ( #5524 )
2025-12-14 11:48:02 -06:00
ab1778fa09
chore: format code
2025-12-14 17:46:46 +00:00
523591e2d9
feat: add server_error, rate_limit, and no_kv_space retry logic to accommodate Foundry API issues ( #5527 )
...
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com >
2025-12-14 11:46:14 -06:00
Spoon