70e4efe429
chore: format code
2025-12-14 17:46:46 +00:00
92948ed8a4
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
3d2ef28fa8
add topK function to transform, add temp defaults for glm and minimax
2025-12-13 23:27:11 -06:00
15caecdb45
shell tweaks, better handling for windows ( #5455 )
...
Co-authored-by: GitHub Action <action@github.com>
2025-12-12 16:11:07 -06:00
6e9833acce
Shell: No -l in fallback, for max compatibility ( #5452 )
2025-12-12 15:43:35 -06:00
651a10d6db
only gen summary if diffs
2025-12-12 16:24:26 -05:00
0400024d02
core: fix missing Flag import in session prompt
2025-12-11 16:18:04 -05:00
d4dc142cc2
core: add client identification to user agent and request headers for better tracking
2025-12-11 16:18:04 -05:00
2a9269c347
add experimental.chat.messages.transform hook ( #5207 )
...
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-12-11 14:38:45 -06:00
578072bb8e
use new share url
2025-12-11 00:43:00 -05:00
89d51ad596
compaction: improve compaction prompt ( #5348 )
2025-12-10 17:21:38 -06:00
cbb591eb7d
fix: more descriptive tool or subtask execution failed error ( #5337 )
...
Signed-off-by: Christian Stewart <christian@aperture.us>
2025-12-10 17:12:49 -06:00
936a6be5d6
stuff adam needs
2025-12-10 15:59:42 -05:00
18d3c054a3
more interleaved thinking fixes ( #5334 )
2025-12-10 13:29:26 -06:00
cc3b699823
chore: format code
2025-12-10 06:02:31 +00:00
301f1a191b
fix: add Windows support for shell mode (! command) ( #5311 )
2025-12-10 00:01:56 -06:00
df64612d54
better interleaved thinking support ( #5298 )
2025-12-09 16:32:12 -06:00
1e3bdcc71c
rename bus
2025-12-09 14:32:09 -05:00
8326640670
feat(telemetry): Add userId and sessionId metadata to experimental_telemetry ( #5279 )
2025-12-09 09:46:48 -06:00
f8bd4ff705
core: refactor providerOptions function to accept Provider.Model for cleaner API
2025-12-09 01:25:36 -06:00
a3bb4a3c85
pdf support in read tool ( #5222 )
...
Co-authored-by: ammi1378 <ammi1378@users.noreply.github.com>
2025-12-07 21:54:00 -06:00
9ff39503e9
tweak: additional error msg parsing case
2025-12-07 20:10:54 -06:00
81ee8541ab
feat: add experimental.text.complete plugin hook ( #4962 )
2025-12-07 19:44:04 -06:00
40eb8b93e1
feat: add max steps for supervisor and sub-agents ( #4062 )
...
Co-authored-by: opencode-agent[bot] <opencode-agent[bot]@users.noreply.github.com>
Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com>
2025-12-05 12:26:44 -06:00
864c098701
add experimental.open_telemetry config option to enable OTEL spans ( #4978 )
...
Co-authored-by: noamzbr <noamzbr@users.noreply.github.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>
2025-12-05 10:48:22 -06:00
350a32274a
fix: model not being passed correctly to tool
2025-12-04 11:15:30 -06:00
0237905b96
fix: TypeError: undefined is not an object
2025-12-03 22:03:42 -06:00
32b5db754e
fix: provider id issue
2025-12-03 20:45:55 -06:00
f33f8ca109
fix: compaction type issue
2025-12-03 20:43:47 -06:00
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
91db82c138
add retry case for grok resource exhausted
2025-12-03 11:16:27 -06:00
1f11d4fb1a
zen: data dumper
2025-12-02 14:51:27 -05:00
027d43b5ea
fix case where opencode wasn't retrying
2025-12-01 13:02:33 -06:00
b1b82977ec
tweak: better err msgs
2025-12-01 01:33:32 -06:00
aaa31f02af
tweak: compaction prompt ( #4838 )
...
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
2025-11-30 14:31:57 -06:00
a4eba2e6e9
tweak: plan prompt
2025-11-30 01:03:35 -06:00
0e280017e6
Revert "fix: title gen when first msg(s) are shell invocations ( #4874 )"
...
This reverts commit 17e8322c29
2025-11-28 12:18:02 -06:00
17e8322c29
fix: title gen when first msg(s) are shell invocations ( #4874 )
...
Co-authored-by: GitHub Action <action@github.com>
2025-11-28 11:55:22 -06:00
13f89fdb8f
fix: filter empty messages in toModelMessage ( #4811 )
2025-11-28 00:26:48 -06:00
cc78d50ef6
bump anthropic package
2025-11-28 00:25:16 -06:00
382758790c
fix(tui): dedupe file references in prompt ( #4775 )
2025-11-26 11:26:05 -06:00
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
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
eb04cdac41
better overloaded message
2025-11-25 21:10:31 +00:00
9eabbe2e76
retry anthropic overloaded errors
2025-11-25 15:47:34 -05:00
4a95db6013
fix: add missing compacted event
2025-11-25 13:47:10 -06:00
020ee56f25
fix: dont auto continue if compaction was manual
2025-11-25 12:11:09 -06:00
16dbac6026
Revert "config: add setCacheKey in provider options ( #4654 )"
...
This reverts commit 9b6d03c497
2025-11-24 22:30:56 -06:00
9b6d03c497
config: add setCacheKey in provider options ( #4654 )
...
Co-authored-by: GitHub Action <action@github.com>
2025-11-24 22:20:52 -06:00
acf1dd8500
wip(share): more styling
2025-11-24 15:10:40 -06:00
ac1e2bfd49
bump copilot plugin, give better error message for copilot ( #4678 )
2025-11-24 00:40:15 -06:00
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
bbc9142fc5
wip: zen
2025-11-23 15:21:47 -05:00
7413c2715c
tweak: slight improvements to title gen
2025-11-23 14:04:39 -06:00
2509d03f42
tweak: fix bool
2025-11-23 11:43:09 -06:00
30ffcaa667
tweak: start bundling in some ai-sdk packages ( #4649 )
2025-11-23 01:29:20 -06:00
bdcf864678
proper fix for image attachments ( #4562 )
...
Co-authored-by: GitHub Action <action@github.com>
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com>
2025-11-22 12:47:57 -06:00
2938a25ec5
sync
2025-11-22 16:43:47 +00:00
75c29d4d1c
summary optimizaitons
2025-11-22 11:32:49 -05:00
49408c00e9
enterprise ( #4617 )
...
Co-authored-by: GitHub Action <action@github.com>
Co-authored-by: Adam <2363879+adamdotdevin@users.noreply.github.com>
2025-11-21 20:41:27 -05:00
00f991162f
if finish reason is unknown, continue
2025-11-21 16:51:32 -05:00
416f2964b5
fix: preserve agent context during compaction ( #4556 )
2025-11-21 02:13:10 -06:00
23ea8ba1ce
Tui onboarding ( #4569 )
...
Co-authored-by: GitHub Action <action@github.com>
2025-11-21 00:21:06 -05:00
43c021ed80
feat: add field to allow user only messages ( #4554 )
...
Co-authored-by: GitHub Action <action@github.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>
2025-11-20 19:13:42 -06:00
ec5c96e10d
Revert "Image tag fix for real this time ( #4540 )"
...
This reverts commit eb975bb89c
2025-11-20 14:14:02 -06:00
d2a61290b9
Revert "ignore: write todo"
...
This reverts commit 5aa2078852
2025-11-20 14:13:56 -06:00
5aa2078852
ignore: write todo
2025-11-20 12:35:34 -06:00
eb975bb89c
Image tag fix for real this time ( #4540 )
...
Co-authored-by: GitHub Action <action@github.com>
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com>
2025-11-20 12:34:39 -06:00
c472734933
tweak: make getUsage function handle missing usage data
2025-11-19 14:29:19 -06:00
16fdc90976
fix: resolve issue 4475 ( #4505 )
2025-11-19 13:10:09 -05:00
d50f825c6d
fix: pass model info to ReadTool to enable image support check ( #4473 )
...
Co-authored-by: GitHub Action <action@github.com>
2025-11-18 17:20:03 -06:00
47bfae52c0
fix: permission checks for external_directory and doom_loop ( #4433 )
...
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
Co-authored-by: AerionDyseti <AerionDyseti@users.noreply.github.com>
2025-11-18 17:18:23 -06:00
3b72857124
fix: update reasoningEffort logic for gpt-5.1 models in SessionPrompt-ensureTitle ( #4456 )
...
Co-authored-by: opencode-agent[bot] <opencode-agent[bot]@users.noreply.github.com>
Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com>
2025-11-18 14:22:44 -06:00
759635eefa
fix gpt compaction issue
2025-11-18 13:10:00 -05:00
fc5fc2c570
wip(desktop): new layout work
2025-11-18 17:07:34 +00:00
c66def2049
fix: noreply
2025-11-17 20:52:25 -06:00
bdfa213ccf
deprecated session.idle event
2025-11-17 11:42:45 -05:00
8b19c6c7e4
better retry display
2025-11-17 11:31:10 -05:00
a1214fff2e
Refactor agent loop ( #4412 )
2025-11-17 10:57:18 -05:00
f5230d1f02
fix: incorrect sonnet price calculation
2025-11-14 18:46:43 -05:00
37cf365927
feat: support images in mcp tool responses ( #4100 )
...
Co-authored-by: opencode-agent[bot] <opencode-agent[bot]@users.noreply.github.com>
Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com>
2025-11-14 15:00:52 -06:00
986c60353e
set `promptCacheKey` for openai compatible providers ( #4203 )
...
Co-authored-by: GitHub Action <action@github.com>
2025-11-14 11:41:01 -06:00
0c51feb9c2
fix: max tokens when using models like opus with providers other than anthropic ( #4307 )
2025-11-13 16:39:09 -06:00
b63b6d04c6
Fix usage & billing for custom model aliases and cached/reasoning tokens ( #4222 )
...
Co-authored-by: Melih Mucuk <melih@monkeysteam.com>
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
2025-11-12 13:59:35 -06:00
c8bda598f5
fix: correct cache cost for OpenRouter and other OpenAI-compatible providers ( #4256 )
2025-11-12 12:41:44 -06:00
491a2adf8d
fix: resolve @file references in slash commands with subagents ( #4221 )
2025-11-11 19:38:50 -06:00
4e549b1c05
fix: allow user to configure doom loop & external dir perms ( #4095 )
2025-11-09 20:21:38 -06:00
10bde356b1
chore: rm comment
2025-11-09 11:50:02 -06:00
f7cc46cd9f
set cap for max time to wait between retries ( #4135 )
...
Co-authored-by: GitHub Action <action@github.com>
2025-11-09 11:46:58 -06:00
d85eb1b880
feat: add input context to chat.params and chat.message ( #4085 )
2025-11-08 23:29:27 -06:00
062023fa06
chore(prompt): refine polaris instructions for practical behavior
2025-11-07 21:18:49 -05:00
954a796b8a
core: route polaris-alpha models to polaris system prompt
2025-11-07 21:07:59 -05:00
34ff87d504
chore: format code
2025-11-08 01:59:02 +00:00
dabb1aa719
fix(prompt): prevent title generation refusal responses
2025-11-07 20:50:15 -05:00
5f7e1e099b
chore: format code
2025-11-07 19:47:53 +00:00
d462e380f4
fix: update references after moving message functions to MessageV2 namespace
2025-11-07 14:47:05 -05:00
9554abb56e
message storage performance improvements
2025-11-07 01:11:47 -05:00
2bcc00dbf0
chore: format code
2025-11-06 18:21:59 +00:00
e45e94634f
only display last 100 messages in TUI
2025-11-06 13:21:15 -05:00
1ea3a8eb9b
big format
2025-11-06 13:03:12 -05:00
05ae99a09b
fix sidebar modified files
2025-11-05 16:49:17 -05:00
b7262b8527
performance improvements
2025-11-05 15:33:23 -05:00
1f44c7f750
include file count in summary
2025-11-05 14:23:10 -05:00
01b9148c04
fix: image reading error, also add error toast for event bus
2025-11-04 17:30:58 -06:00
7a7060ef15
fix session performance issue from large diffs
2025-11-04 13:35:44 -05:00
40f577e5e7
fix modified files being empty
2025-11-01 11:48:47 -04:00
041353f4ff
make /init a default slash command on server side ( #3677 )
2025-11-01 01:14:09 -05:00
96bdeb3c7b
OpenTUI is here ( #2685 )
2025-10-31 15:07:36 -04:00
c1ada302f9
fix: Opencode hangs after exit ( #3481 )
...
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
2025-10-30 23:57:58 -05:00
51e4c9fc4c
add optional headers field to model config ( #3546 )
2025-10-30 23:35:26 -05:00
dc87659791
tweak: move zod validation for tools to ensure it always runs ( #3565 )
2025-10-30 11:31:44 -05:00
149f5eaa2e
fix: preserve metadata from MCP tool results in `tool.execute.after` hook ( #3573 )
2025-10-30 11:10:42 -05:00
7a2b8eae76
tweak: catch err
2025-10-30 00:29:30 -05:00
d983b9485d
fix: add doom loop detection ( #3445 )
...
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
2025-10-30 00:13:18 -05:00
a9cae7b335
feat: add positional argument support to slash commands ( #3456 )
...
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
2025-10-29 14:54:24 -05:00
5553efea5e
only generate user message summary if no diffs
2025-10-29 14:28:43 -04:00
4407d5d96f
fix: ensure tool inputs are zod validated
2025-10-29 10:46:57 -05:00
12782fff14
remove log
2025-10-29 11:27:51 -04:00
ca463a2346
session diff only include modified files
2025-10-29 11:26:21 -04:00
7265cdf817
ignore: rm
2025-10-29 10:19:02 -05:00
37380e1f94
add --title flag to opencode run ( #3507 )
2025-10-28 13:32:36 -05:00
1309ca7a81
ignore
2025-10-28 14:13:47 -04:00
b66e7b6fce
tweak: add experimental chatMaxRetries to config ( #2116 )
...
Co-authored-by: GitHub Action <action@github.com>
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
2025-10-28 12:09:41 -05:00
643c22d21f
add catch for mcp tool execution
2025-10-28 10:23:04 -05:00
74acd08ead
add catch for mcp tool execution
2025-10-28 10:23:03 -05:00
22821744ef
feat: add OPENCODE_FAKE_VCS flag for VCS testing and update todo tracking instructions
2025-10-28 02:54:29 -04:00
982954cc1b
feat (acp): mcp server support, file diffs, some default slash commands (/init, /compact), show todos properly ( #3490 )
...
The mcp server support does not mean acp didn't allow u to use mcp servers previously, it means that now you can connect new servers via ACP instead of relying on the opencode defined ones
2025-10-28 00:08:30 -05:00
3c56dbcf58
chore: rm comment
2025-10-27 16:15:13 -05:00
0af4505756
fix: litellm error tool= param must be specified
2025-10-27 14:03:42 -05:00
e6301ca5d5
tweak: rename event
2025-10-27 10:42:47 -05:00
b562863fcc
feat: add `session.started` event that triggers when a new session is created ( #3413 )
2025-10-27 07:18:23 -05:00
1a6fd018f6
Revert "fix: Explicitly exit CLI to prevent hanging subprocesses ( #3083 )"
...
This reverts commit a9624c0fff
2025-10-27 01:30:13 -05:00
a9624c0fff
fix: Explicitly exit CLI to prevent hanging subprocesses ( #3083 )
...
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
2025-10-27 00:03:10 -05:00
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
0a778a2789
make title gen more reliable
2025-10-25 22:14:29 -05:00
795b845782
update anthropic prompt
2025-10-25 17:26:27 -04:00
2e434a459a
feat: add noReply parameter ( #3433 )
...
Co-authored-by: opencode-agent[bot] <opencode-agent[bot]@users.noreply.github.com>
Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com>
2025-10-25 14:56:54 -05:00
98d51dde6a
acp: slash commands, agents, permissions, @ references, code cleanup ( #3403 )
...
Co-authored-by: yetone <yetoneful@gmail.com>
2025-10-25 01:32:46 -05:00
21880e199d
mroe summary tweaks
2025-10-24 12:37:23 -04:00
736a85d427
track finish reason
2025-10-24 12:23:24 -04:00
fb40dc6b20
generate user message title and body
2025-10-24 11:50:42 -04:00
7003efd2da
fix summary
2025-10-24 09:24:58 -04:00
8b9b8ca15b
update codex prompt
2025-10-23 23:36:32 -04:00
cee7106054
session summaries in data
2025-10-23 16:28:20 -04:00
f4dfae0bb0
ignore: diff stuff
2025-10-23 16:04:58 -04:00
913c3ae799
tweak: split out title before newline
2025-10-23 12:44:43 -05:00
3c7b229d8b
fix: allow `tool.execute.after` hook to modify MCP tool output ( #3381 )
2025-10-23 10:38:55 -05:00
7c7ebb0a9d
feat: retry parts ( #3369 )
2025-10-22 18:31:36 -05:00
9def7cff2d
summary tweaks
2025-10-22 19:03:08 -04:00
f435049d36
sync
2025-10-22 18:49:57 -04:00
1f80de2fa6
core: add experimental turn summarization to compact conversation history
2025-10-22 18:33:46 -04:00
28d8af48a0
add parent id to assistant messages
2025-10-22 15:01:13 -04:00
ca0f3902b7
fix: provider option transforms ( #3331 )
2025-10-21 11:08:21 -05:00
e9996342a7
core: provide line-level statistics in file diffs to help users understand the scale of changes
2025-10-21 11:54:41 -04:00
96efede846
fix: openai options when using @ai-sdk/azure ( #3315 )
2025-10-20 23:30:13 -05:00
a0a09f421c
core: add session diff API to show file changes between snapshots
2025-10-20 17:59:26 -04:00
f3f21194ae
feat: Add ACP (Agent Client Protocol) support ( #2947 )
...
Co-authored-by: opencode-bot <devnull@opencode.local>
Co-authored-by: Dax Raad <d@ironbay.co>
Co-authored-by: GitHub Action <action@github.com>
2025-10-20 16:55:22 -05:00
1c7bd6365e
replace all $ARGUMENTS ( #3276 )
2025-10-18 23:37:17 -05:00
1f869bccc1
make compact interruptable ( #3251 )
2025-10-18 11:49:29 -05:00
d69366b00c
Revert "try to avoid persisting empty thinking/text blocks"
...
This reverts commit d8a15e7bc9
2025-10-16 22:04:55 -05:00
d8a15e7bc9
try to avoid persisting empty thinking/text blocks
2025-10-16 10:54:10 -04:00
1c59530115
Revert "fix: Text content blocks must contain non-whitespace text" ( #3200 )
2025-10-15 20:02:17 -05:00
790fe72f39
sync
2025-10-15 19:48:57 -04:00
ca534a36e5
feat: make compact feature use streaming API ( #3079 )
...
Co-authored-by: fku <fabian.kukuck@ipt.ch>
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
2025-10-15 13:44:16 -05:00
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
GitHub Action