Peter Steinberger
8d1b3d4578
ci: speed up release metadata pre-commit checks
2026-04-21 21:56:06 +01:00
Peter Steinberger
aa94501f5f
feat(openai): default images to gpt-image-2
2026-04-21 21:49:16 +01:00
Peter Steinberger
0b1a35363e
chore: start 2026.4.21 development
2026-04-21 21:42:15 +01:00
Vincent Koc
8f1a87ea47
docs: note Kimi K2.6 thinking-disabled on Fireworks and Ollama cloud onboard live-tag fetch
2026-04-21 13:41:10 -07:00
Vincent Koc
9702f0bf21
docs: tool-progress preview streaming, Control UI avatar auth, exec heredoc and external-content token sanitization
2026-04-21 13:39:55 -07:00
Peter Steinberger
674feda214
docs(plugins): document message presentation cards
2026-04-21 21:29:44 +01:00
Peter Steinberger
c742a706bf
feat(plugins): add experimental skill workshop
2026-04-21 21:29:44 +01:00
Peter Steinberger
fd0970c077
refactor(channels): decouple presentation rendering
2026-04-21 21:29:44 +01:00
Peter Steinberger
d7a173e60e
feat(plugin-sdk): add presentation and skills runtime contracts
2026-04-21 21:29:44 +01:00
Vincent Koc
78030d0d52
docs: plugin manifest precedence, QQBot engine/bot-approve/QR onboarding, web-search plugin-scoped SecretRefs
2026-04-21 13:26:25 -07:00
Vincent Koc
b4a59be9b6
docs: document stdio env filter, enforceOwnerForCommands, OPENCLAW_* .env blocking
2026-04-21 13:21:34 -07:00
Vincent Koc
32ccf27e60
docs: document WS broadcast scope gating and Control UI img-src CSP
2026-04-21 13:14:15 -07:00
Vincent Koc
7d7c0b1dfe
docs: cover BB tapback fallback, iMessage/SMS routing, Mattermost streaming, Matrix mention-prefixed slash
2026-04-21 13:09:09 -07:00
Peter Steinberger
6f004ed4d4
feat(fireworks): add Kimi K2.6 model
2026-04-21 20:31:33 +01:00
Peter Steinberger
2514746b32
fix: sanitize LLM special tokens in external content
2026-04-21 20:29:02 +01:00
Shakker
2161ed8259
fix: update Copilot Opus default to 4.7
2026-04-21 20:00:06 +01:00
Peter Steinberger
11efbf5a2e
fix: prevent stale subagent failure announces
2026-04-21 19:59:12 +01:00
Tak Hoffman
dcf131e54c
docs: restore general multi-gateway guidance ( #69810 )
2026-04-21 13:34:18 -05:00
Peter Steinberger
b2b43085bc
ci: use larger Blacksmith macOS runners
2026-04-21 19:03:50 +01:00
Tak Hoffman
5218c1a01f
docs: front-load rescue bot quickstart ( #69803 )
...
* docs: front-load rescue bot quickstart
* docs: recommend rescue port 19789
* docs: show rescue port in quickstart command
2026-04-21 13:01:23 -05:00
Agustin Rivera
38356c658a
fix(synology): validate webhook file urls ( #69784 )
...
* fix(synology): validate webhook file urls
* fix(synology): restore file send throttle
* docs(changelog): note synology webhook file_url SSRF guard (#69784 )
---------
Co-authored-by: Devin Robison <drobison@nvidia.com >
2026-04-21 12:00:28 -06:00
Peter Steinberger
bcfa781a1b
fix: remap thinking levels on model switch
2026-04-21 18:53:49 +01:00
Gustavo Madeira Santana
24db09a19b
fix(cli): keep channel status checks off plugin runtimes ( #69479 )
...
Merged via squash.
Prepared head SHA: 63f6e416a95599352+gumadeiras@users.noreply.github.com >
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com >
Reviewed-by: @gumadeiras
2026-04-21 13:53:08 -04:00
Tak Hoffman
09c5669299
docs: clarify rescue bot gateway setup ( #69788 )
...
* docs: clarify rescue bot gateway setup
* docs: make rescue bot guide more prescriptive
2026-04-21 12:29:40 -05:00
Shadow
38aaa23e63
feat(channels): stream tool progress into preview edits ( #69611 ) (thanks @thewilloftheshadow)
2026-04-21 11:51:16 -05:00
Tak Hoffman
714598774f
feat: add soft reset command ( #68635 )
...
* feat: add soft reset command
* fix: harden soft reset follow-up behavior
* fix: accept whitespace-delimited soft reset tails
* test: cover newline soft reset normalization
* fix: preserve stale sessions for soft reset
* fix: gate soft reset stale bypass
* fix: align soft reset auth gating
* fix: normalize soft reset session detection
* test: cover multiline soft reset session state
* test: cover multiline soft reset parsing
2026-04-21 10:17:52 -05:00
Omar Shahine
14506aeca4
fix(bluebubbles): add opt-in coalesceSameSenderDms for split-send DMs ( #69258 )
...
Merged via squash.
Prepared head SHA: 8f1bd3cf5310343873+omarshahine@users.noreply.github.com >
Co-authored-by: omarshahine <10343873+omarshahine@users.noreply.github.com >
Reviewed-by: @omarshahine
2026-04-21 01:43:17 -07:00
Peter Steinberger
f1805ab54d
fix: centralize provider thinking profiles
2026-04-21 09:13:35 +01:00
Peter Steinberger
047acaa176
fix: stage ACP and Codex runtime deps
2026-04-21 08:47:24 +01:00
Peter Steinberger
f14e91b39f
test: add bundled channel dependency Docker smoke
2026-04-21 08:26:23 +01:00
Peter Steinberger
7b1871b99b
fix(browser): clarify DevToolsActivePort attach failures
2026-04-21 08:11:41 +01:00
Ayaan Zaidi
c18b6fc9da
feat(cron): preview resolved delivery targets
2026-04-21 12:01:06 +05:30
Ayaan Zaidi
8d6ed34e4a
docs(cron): clarify delivery modes
2026-04-21 12:01:06 +05:30
Peter Steinberger
4a846dd129
fix(exec): honor yolo host exec semantics
2026-04-21 07:23:46 +01:00
Peter Steinberger
6ce17db11a
fix: gate max thinking by model support
2026-04-21 07:02:43 +01:00
Peter Steinberger
e4adb0b0e3
fix: hide adaptive think option for GPT models
2026-04-21 06:19:29 +01:00
Peter Steinberger
0da5e0e34e
fix(openai): tighten gpt prompt contract
2026-04-21 06:14:54 +01:00
Pavan Kumar Gondhi
5275d008ed
fix(gateway): enforce allowRequestSessionKey gate on template-rendered mapping sessionKeys ( #69381 )
...
* fix: address issue
* fix: address review feedback
* fix: finalize issue changes
* fix: address PR review feedback
* fix: address review-pr skill feedback
* fix: address PR review feedback
* fix: address build failures
* fix: address PR review feedback
* fix: address PR review feedback
* fix: address PR review feedback
* fix: address PR review feedback
* docs: add changelog entry for PR merge
2026-04-21 10:12:10 +05:30
Peter Steinberger
b485ee7e36
docs: support release branch workflow
2026-04-21 05:33:21 +01:00
Tak Hoffman
1303b03241
fix: add silent reply policy by conversation type ( #68644 )
...
Thanks @Takhoffman.
2026-04-21 05:17:55 +01:00
Peter Steinberger
2641b052dc
fix: align OpenAI reasoning effort handling
2026-04-21 04:58:31 +01:00
Peter Steinberger
22bff819ab
fix: strengthen agent completion bias
2026-04-21 04:19:26 +01:00
Omar Shahine
b5f25de352
bluebubbles: forward per-group systemPrompt into GroupSystemPrompt ( #69198 )
...
Forward per-group systemPrompt config into inbound context GroupSystemPrompt so configured group-specific behavioral instructions (for example threaded-reply and tapback conventions) are injected on every turn. Supports "*" wildcard fallback matching the existing requireMention pattern.
Closes #60665 .
Co-authored-by: Omar Shahine <omarshahine@users.noreply.github.com >
2026-04-20 20:01:03 -07:00
Peter Steinberger
5c85624eeb
Revert "ci: use Blacksmith checkout cache"
...
This reverts commit 43734b1dbd
2026-04-21 03:21:48 +01:00
Peter Steinberger
bd0c9024a2
docs: document Kimi cost live smoke
2026-04-21 03:10:56 +01:00
Peter Steinberger
43734b1dbd
ci: use Blacksmith checkout cache
2026-04-21 03:09:13 +01:00
Sliverp
b938e6398b
feat: add tiered model pricing support ( #67605 )
...
Adds tiered model pricing support for cost tracking, keeps configured pricing ahead of cached catalog values, and includes latest Moonshot Kimi K2.6/K2.5 cost estimates.\n\nThanks @sliverp.
2026-04-21 03:02:57 +01:00
Peter Steinberger
525e66e513
fix(openai): use tagged GPT-5 prompt contract
2026-04-21 02:45:17 +01:00
Peter Steinberger
82b8a4aab6
docs(openai): clarify GPT-5 prompt defaults
2026-04-21 02:36:16 +01:00
Peter Steinberger
ab03d4e037
fix(openai): default GPT-5 prompt overlay
2026-04-21 02:36:16 +01:00
