021e42c0bb
core: fix issue when switching models (mainly between providers) where past reasoning/metadata would be sent to server and cause 400 errors since they came from another account/provider
2026-01-20 16:39:00 -06:00
0c4ffec857
chore: rename toModelMessage -> toModelMessages
2026-01-20 16:16:23 -06:00
8d720f9463
fix(opencode): add input limit for compaction ( #8465 )
2026-01-15 01:35:16 -06:00
2b054bec95
core: fix compaction config checks to properly respect user settings
2025-12-26 19:48:56 -05:00
ed06de5e30
core: add configurable compaction settings to allow users to disable auto-compaction and pruning via config instead of flags
2025-12-26 19:31:48 -05:00
eab177f5e7
feat(plugin): allow compaction hook to replace prompt entirely ( #5907 )
2025-12-22 22:19:14 -06:00
046e351140
feat: add native skill tool with permission system ( #5930 )
...
Co-authored-by: Dax Raad <d@ironbay.co>
2025-12-22 18:24:06 -05:00
24430287c5
feat(plugin): add experimental.session.compacting hook for pre-compaction context injection ( #5698 )
...
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
2025-12-17 13:57:09 -06:00
fed4776451
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
89d51ad596
compaction: improve compaction prompt ( #5348 )
2025-12-10 17:21:38 -06:00
18d3c054a3
more interleaved thinking fixes ( #5334 )
2025-12-10 13:29:26 -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
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
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
aaa31f02af
tweak: compaction prompt ( #4838 )
...
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
2025-11-30 14:31:57 -06:00
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
75c29d4d1c
summary optimizaitons
2025-11-22 11:32:49 -05:00
416f2964b5
fix: preserve agent context during compaction ( #4556 )
2025-11-21 02:13:10 -06:00
759635eefa
fix gpt compaction issue
2025-11-18 13:10:00 -05:00
a1214fff2e
Refactor agent loop ( #4412 )
2025-11-17 10:57:18 -05:00
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
34ff87d504
chore: format code
2025-11-08 01:59:02 +00:00
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
96bdeb3c7b
OpenTUI is here ( #2685 )
2025-10-31 15:07:36 -04:00
51e4c9fc4c
add optional headers field to model config ( #3546 )
2025-10-30 23:35:26 -05:00
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
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
0af4505756
fix: litellm error tool= param must be specified
2025-10-27 14:03:42 -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
7c7ebb0a9d
feat: retry parts ( #3369 )
2025-10-22 18:31:36 -05:00
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
1f869bccc1
make compact interruptable ( #3251 )
2025-10-18 11:49:29 -05:00
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
53d9717d90
fix: pass options to compact ( #3136 )
2025-10-13 10:42:39 -05:00
10998d62b9
core: improve session API reliability with proper input validation
2025-10-06 19:37:44 -04:00
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
c1b4e1f19d
Upgrade to Zod v4 ( #2605 )
...
Co-authored-by: GitHub Action <action@github.com>
2025-09-15 03:12:07 -04:00
Aiden Cline