b2ff4be4c6
fix: Text content blocks must contain non-whitespace text ( #3194 )
2025-10-15 13:00:26 -05:00
b3fcc9a81d
tweak: consolidate session lock logic ( #3185 )
2025-10-15 01:12:51 -05:00
682d30bd12
fix: custom model ( #3156 )
2025-10-13 19:58:19 -05:00
dbe9fd00b7
fix: make shell more robust ( #3051 )
2025-10-13 17:37:35 -05:00
53d9717d90
fix: pass options to compact ( #3136 )
2025-10-13 10:42:39 -05:00
225adc46ba
feat: allow read tool to handle images ( #3052 )
2025-10-09 09:05:11 -05:00
cd528ae78f
fix: mcp error ( #3006 )
2025-10-07 00:45:46 -05:00
10998d62b9
core: improve session API reliability with proper input validation
2025-10-06 19:37:44 -04:00
cdd6e98af9
Add missing files and fix type aliases for opentui features
2025-10-06 18:53:35 -04:00
9a0735de76
Add session forking functionality and simplify remove logic
2025-10-06 18:50:56 -04:00
889c276558
fix: file references & grep tool for windows ( #2980 )
2025-10-05 14:32:07 -05:00
71a7e8ef36
fix: max output tokens when using large thinking budget ( #2976 )
2025-10-04 23:38:41 -05:00
6e19200fca
overhaul file search and support @ mentioning directories
2025-10-01 03:37:01 -04:00
5a507023a6
update anthropic system prompts
2025-09-30 04:41:36 -04:00
d0043a4a78
sync
2025-09-27 02:53:20 -04:00
5d95846df1
fix: openai reasoning issue ( #2780 )
2025-09-26 01:23:30 -04:00
ffa5689885
docs: subtask config option ( #2682 )
2025-09-18 17:52:23 -05:00
71076d5c68
fix: add synthetic user prompt after session compaction ( #2659 )
...
Co-authored-by: Julián Díaz <git@jdiaz.io >
2025-09-17 23:27:37 -04:00
ff6a93f355
fix: only keep aborted messages if they have sufficient parts ( #2651 )
2025-09-17 14:24:53 -05:00
3c3d6b65c2
Revert "fix: type 'reasoning' was provided without its required follo… ( #2648 )
2025-09-17 11:17:26 -05:00
8c2aec43b8
fix: type 'reasoning' was provided without its required following item ( #2633 )
2025-09-17 09:45:13 -05:00
2564801bde
tweak: adjust title gen when using models like gpt-5-nano on non open… ( #2646 )
2025-09-17 08:39:34 -05:00
259c722208
only prune messages from more than 2 turns ago
2025-09-17 03:30:09 -04:00
3aeac02bf1
enable session pruning and allow disabling with OPENCODE_DISABLE_PRUNE
2025-09-16 04:53:17 -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
52fb571739
fix: restore chat.message plugin hook ( #2619 )
2025-09-15 21:44:07 -05:00
c1b4e1f19d
Upgrade to Zod v4 ( #2605 )
...
Co-authored-by: GitHub Action <action@github.com >
2025-09-15 03:12:07 -04:00
e3e459fc50
fix: reasoning metadata persistence ( #2602 )
2025-09-14 16:28:06 -05:00
16d66c209d
respect subagent in command, add subtask flag ( #2569 )
2025-09-13 12:47:18 -05:00
6506e48c54
tweak: keep aborted msgs in context ( #2583 )
2025-09-13 12:25:30 -05:00
a00b49d65b
disable autocompact if context is 0
2025-09-13 05:59:18 -04:00
b1589be4ba
add disable OPENCODE_DISABLE_AUTOCOMPACT
2025-09-13 05:55:04 -04:00
eb24d2f847
ignore: fix
2025-09-13 05:53:03 -04:00
9bb25a9260
Session management and prompt handling improvements ( #2577 )
...
Co-authored-by: GitHub Action <action@github.com >
2025-09-13 05:46:14 -04:00
555fb53505
nudge llm to continue properly after compaction
2025-09-13 01:23:54 -04:00
c02f58c2af
fix: await cleanupRevert() to prevent dupe msgs after undo ( #2572 )
2025-09-12 18:42:39 -05:00
f2094b7bb3
temporarily disable midstream compaction
2025-09-12 14:00:54 -04:00
3e2478ebf9
undo session pruning
2025-09-12 13:20:13 -04:00
0290b4aaf0
ignore: internal
2025-09-12 10:45:44 +00:00
469dc9095f
add microcompact
2025-09-12 06:38:47 -04:00
983e3b2ee3
fix compaction issues
2025-09-12 06:01:11 -04:00
4c94753eda
compaction improvements
2025-09-11 02:22:51 -04:00
29310957c8
fix: handle @dir in command ( #2533 )
2025-09-10 13:27:44 -05:00
bdc0f7c86d
tweak: wrap build-switch w/ system-reminder ( #2525 )
2025-09-09 23:57:13 -05:00
e69d10b6c9
repair tool calls when casing is wrong
2025-09-09 23:25:27 -04:00
74469a0d3d
fix: shell invocations are dropped if last interaction was revert ( #2485 )
2025-09-07 21:45:13 -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
93c2f5060e
fix: title gen w/ gpt-5-nano ( #2473 )
2025-09-06 22:50:16 -05:00
564143071e
fix: title not generated if first msg is shell invocation ( #2451 )
2025-09-06 09:47:42 -05:00
bffe547417
fix: command model selection ( #2448 )
2025-09-05 20:54:39 -05:00
Aiden Cline