3ea064ea2a
fix: support Bedrock API key login
2026-07-10 19:34:11 +02:00
34582ef34b
Add [Unreleased] section for next cycle
2026-07-10 01:16:58 +02:00
2b3fda9921
Release v0.80.6
2026-07-10 01:16:55 +02:00
1775fe4c52
docs: audit unreleased changelogs
2026-07-10 01:13:38 +02:00
a9ecf301fb
feat(ai): add input-based pricing tiers
2026-07-09 22:44:29 +02:00
fbdd46389c
feat(ai): add max thinking level
2026-07-09 22:30:53 +02:00
e3513193bf
Add [Unreleased] section for next cycle
2026-07-09 21:04:09 +02:00
cc62baa442
Release v0.80.5
2026-07-09 21:04:06 +02:00
ef793a983b
Add [Unreleased] section for next cycle
2026-07-09 20:53:01 +02:00
912d0953f6
Release v0.80.4
2026-07-09 20:52:57 +02:00
bf75b8aa39
docs: audit unreleased changelogs
2026-07-09 20:45:28 +02:00
7df2a94e0f
feat(ai): add GPT-5.6 model metadata
2026-07-09 20:32:29 +02:00
3f9aa5d10b
feat(coding-agent): add prompt cache miss tracking ( #6427 )
...
Detect prompt cache misses per turn by comparing each assistant message's
cache reads against the previous request's prompt tokens (core/cache-stats.ts).
Significant misses emit a warning-colored transcript notice at the turn they
occur, noting idle gaps past the cache TTL and model switches when relevant.
/session gained cache statistics: a compact token/cache breakdown with hit
rate, a $-prefixed cost section with per-model cost breakdown, and the
cumulative cost re-billed due to cache misses.
2026-07-09 14:12:57 +02:00
a6f720e6ca
fix(coding-agent): count custom messages in compaction budget
...
closes #6326
2026-07-09 12:46:03 +02:00
e9fa5a68a1
fix(coding-agent): add settled agent lifecycle event
...
closes #6363
2026-07-09 12:42:08 +02:00
1ffca0f2aa
fix(coding-agent): align reload descriptions
...
closes #6395
2026-07-09 11:47:44 +02:00
c4281a7dd1
fix(coding-agent): warn when session-id creates a session
...
closes #6407
2026-07-09 11:37:07 +02:00
2170363af4
fix(coding-agent): avoid Windows context file walk hang
...
closes #6369
2026-07-09 11:30:59 +02:00
c6251a866b
fix(coding-agent): apply modelOverrides to extension providers
...
closes #6367
2026-07-09 11:22:35 +02:00
4285712bae
fix(ai): retry Bun socket drops
...
closes #6431
2026-07-09 11:03:58 +02:00
312bc713bb
feat(coding-agent): support provider arguments for login
2026-07-08 12:06:26 +02:00
cc2db98002
fix(ai): refresh Xiaomi token plan model catalogs
...
Use the new provider-specific Xiaomi Token Plan catalogs from models.dev instead of cloning the API-billing Xiaomi catalog into every token-plan region. This removes API-billing-only models such as mimo-v2-omni from xiaomi-token-plan-{cn,ams,sgp}.
2026-07-08 10:17:48 +02:00
2b00dade7c
Revert "fix(coding-agent): abort stuck context hooks"
...
This reverts commit 6757561546
2026-07-07 07:14:27 +02:00
6efc09b7eb
fix(coding-agent): clear label timestamp cache on new sessions
...
closes #6354
2026-07-06 15:31:32 +02:00
a1b336d73e
fix(coding-agent): allow extra edit replacement fields
2026-07-04 01:52:17 +02:00
83cbfc6521
fix(coding-agent): remove Vercel AI Gateway attribution
2026-07-03 15:14:01 +02:00
ca09b2b1a8
fix(coding-agent): skip unauthenticated default model
...
closes #6231
2026-07-02 10:48:11 +02:00
6757561546
fix(coding-agent): abort stuck context hooks
...
closes #6234
2026-07-02 10:02:32 +02:00
ec857fece5
fix(coding-agent): set executionMode: sequential on question example tool
...
The question extension tool blocks on ctx.ui.custom() but omitted
executionMode, so multiple question calls in one assistant turn ran
under the default parallel mode and raced on the editor slot. Only the
last question rendered; earlier calls hung pending forever.
Set executionMode: "sequential" so the agent loop serializes the
batch. Wrappers already propagate the field to the core.
closes #6189
2026-07-02 09:01:15 +02:00
f8bec25f34
fix(coding-agent): surface auth storage save failures
...
closes #6223
2026-07-01 21:24:26 +02:00
f58c115626
fix(coding-agent): serialize split-turn compaction summaries
...
closes #5536
2026-07-01 15:37:00 +02:00
ba10b60b51
fix(coding-agent): add entry renderers for session entries
2026-07-01 11:30:26 +02:00
040f0a5197
feat(coding-agent): expose model resolution helpers
...
closes #6201
2026-07-01 10:22:35 +02:00
cbcf4e04c3
fix(coding-agent): reject oversized bash timeouts
...
closes #6181
2026-07-01 08:49:31 +02:00
dd87c02cbf
Add [Unreleased] section for next cycle
2026-06-30 22:29:44 +02:00
a23abe4a69
Release v0.80.3
2026-06-30 22:29:41 +02:00
f98a154d87
docs: audit changelog entries
2026-06-30 22:24:42 +02:00
fd6659dd5d
fix(coding-agent): preserve run prompt during tool refresh
...
closes #6162
2026-06-30 14:08:48 +02:00
9be55bc773
fix(coding-agent): apply output padding to user messages
...
closes #6168
2026-06-30 11:55:40 +02:00
6564d94717
feat(coding-agent): add configurable assistant output padding
...
Closes #6168
2026-06-30 11:44:34 +02:00
2117b61c6b
fix(coding-agent): handle undici mid-stream client errors
...
closes #6133
2026-06-30 11:44:14 +02:00
927e98068c
fix(coding-agent): fix compaction event regression test
2026-06-29 17:12:19 +02:00
5d499272a8
fix(coding-agent): stabilize interactive status indicators
...
Closes #6026
2026-06-29 16:53:39 +02:00
5a073885b5
feat(coding-agent): add external editor setting
...
Closes #6122
2026-06-27 23:57:46 +02:00
f2e9d75388
fix(coding-agent): preserve backslash escapes in user messages
...
closes #6105
2026-06-27 19:24:14 +02:00
543710f643
fix(coding-agent): reject invalid session files
...
closes #6002
2026-06-25 15:16:18 +02:00
f14b3594c1
fix(coding-agent): show length stop errors
...
closes #4290
2026-06-25 14:50:14 +02:00
e454f50b48
fix(coding-agent): allow session id for no-session runs
...
closes #6070
2026-06-25 14:44:44 +02:00
f78b163713
fix(ai): revert minimax max token clamp
2026-06-25 13:36:04 +02:00
4cc339f58d
fix(coding-agent): process BMP images from disk
...
closes #6047
2026-06-25 12:52:21 +02:00
Armin Ronacher