Commit Graph

248 Commits

Author SHA1 Message Date
Peter Steinberger
0bbb0eb735 fix(image): honor generation timeout config 2026-04-25 18:25:26 +01:00
Vincent Koc
ab1d1a5c9e fix(browser): configure Chrome MCP existing-session launch (#71560) 2026-04-25 05:46:39 -07:00
skylee-01
f7b71abf48 fix(agents): pass Claude system prompt via file 2026-04-25 17:59:25 +05:30
Vincent Koc
ec1f72b6c5 fix(gateway): preserve restart drain for active runs
Fixes https://github.com/openclaw/openclaw/issues/65485
2026-04-25 01:35:47 -07:00
Peter Steinberger
2011de69d3 feat: add Crestodian setup helper 2026-04-25 08:58:21 +01:00
Peter Steinberger
5376a4a5d6 fix(browser): default act timeout budget
Co-authored-by: Andy Lin <andyylin@users.noreply.github.com>
2026-04-25 08:11:48 +01:00
Peter Steinberger
b34ece705f fix: retire idle bundled MCP runtimes 2026-04-25 07:49:12 +01:00
Peter Steinberger
f44759073b feat(gateway): auto-approve trusted CIDR node pairing (#61004) (thanks @sahilsatralkar) 2026-04-25 06:40:25 +01:00
Peter Steinberger
b0e834b2d9 fix(browser): support per-profile executable paths
Co-authored-by: nobrainer-tech <nobrainer-tech@users.noreply.github.com>
2026-04-25 05:50:20 +01:00
Peter Steinberger
70fd1c91aa fix(channels): harden tool progress previews 2026-04-25 04:54:29 +01:00
statxc
ed03d91ae0 fix(config): allow per-agent contextTokens override in agents.list 2026-04-25 09:17:47 +05:30
Peter Steinberger
7920f8d4fd fix(compaction): honor manual keepRecentTokens 2026-04-25 04:03:09 +01:00
Peter Steinberger
d610e2cc6c feat(browser): support per-profile headless
Co-authored-by: nakamotoliu <nakamotoliu2026@gmail.com>
Co-authored-by: Nakamoto <nakamoto@claude.ai>
2026-04-25 01:49:22 +01:00
Vincent Koc
d4d4a8c14e feat(diagnostics-otel): add content capture controls
Add opt-in diagnostics OTEL content capture controls, keep raw content export default-off, and guard the content-capture tests against magic truncation bounds.
2026-04-24 16:41:28 -07:00
Peter Steinberger
e2f13959d4 feat(voice-call): share realtime agent consult tool
Centralize the shared realtime agent consult tool for browser Talk, Google Meet, and Voice Call.
2026-04-24 23:11:18 +01:00
pashpashpash
11804a484d Fail closed when an explicit agent harness is missing (#71265)
* Fail closed for explicit agent harness selection

* Scope explicit harness fallback opt in
2026-04-25 06:39:57 +09:00
BillChirico
51dd4f288f fix(config): allow plugin conversation access hook policy (#71221) 2026-04-24 20:28:42 +01:00
Tak Hoffman
59e2825274 fix: deprecate models add command (#71175) 2026-04-24 12:20:59 -05:00
Tak Hoffman
cc57d56b92 fix: Align silent reply prompt guidance (#70954)
* Align silent reply prompt guidance

* Pass explicit silent reply conversation types

* Handle dm alias in direct prompt guidance

* Respect policy session type for routed replies

* Preserve routed silent reply policy type

* Propagate silent reply dispatcher chat type

* Align prompt silent reply target policy

* Avoid direct silent fallback prompt token

* Use inbound key for prompt silent policy

* Rewrite direct silent replies in dispatcher
2026-04-24 12:06:54 -05:00
Peter Steinberger
69566e43cb feat(codex): add app-server protocol bridge 2026-04-24 04:24:08 +01:00
Peter Steinberger
e0072ef91a chore: bump version to 2026.4.24 2026-04-24 02:13:50 +01:00
Peter Steinberger
235e17a08f docs: update config baseline 2026-04-23 21:55:36 +01:00
Peter Steinberger
87c85c507a fix: align docs with cli and provider surfaces 2026-04-23 06:39:11 +01:00
Gustavo Madeira Santana
28818f9140 Improve gateway diagnostics export for support reports (#70324)
Merged via squash.

Prepared head SHA: 3d6ee85993
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras
2026-04-22 20:47:14 -04:00
Peter Steinberger
3d07eadec3 fix: restore model-level base url contract (#70340) 2026-04-23 00:52:32 +01:00
Peter Steinberger
2cd3164a0f feat(providers): share GPT-5 prompt overlay 2026-04-22 23:36:06 +01:00
Tak Hoffman
78d491d909 feat(commands): gate /models add with modelsWrite (#70321) 2026-04-22 14:49:07 -05:00
Peter Steinberger
557f4fc689 docs: update claude cli stdio notes 2026-04-22 18:40:51 +01:00
Ayaan Zaidi
81ca7bc40b fix: keep claude cli sessions warm (#69679)
* feat(cli): keep claude cli sessions warm

* test(cli): cover claude live session reuse

* fix(cli): harden claude live session reuse

* fix(cli): redact mcp session key logs

* fix(cli): bound claude live session turns

* fix(cli): reuse claude live sessions on resume

* refactor(cli): canonicalize claude live argv

* fix(cli): preserve claude live resume state

* fix(cli): close dead claude live sessions

* fix(cli): serialize claude live session creates

* fix(cli): count pending claude live sessions

* fix(cli): tighten claude live resume abort

* fix(cli): reject closed claude live sessions

* fix(cli): refresh claude live fingerprints

* fix(cli): stabilize MCP resume hash

* fix: preserve claude live inline resume (#69679)

---------

Co-authored-by: Frank Yang <frank.ekn@gmail.com>
2026-04-22 13:44:18 +05:30
Peter Steinberger
d8892ee227 test: harden qa private runtime staging 2026-04-22 08:52:55 +01:00
Peter Steinberger
d8d0380297 fix: use transport activity for stale health 2026-04-22 08:52:55 +01:00
pashpashpash
dc4e97472d Make harness failures fail honestly (#69981)
* Agents: fail honestly on harness errors

* Docs: clarify Codex harness fallback
2026-04-22 14:33:21 +09:00
Peter Steinberger
1801b90460 chore: bump version to 2026.4.22 2026-04-22 03:04:53 +01:00
Peter Steinberger
0b1a35363e chore: start 2026.4.21 development 2026-04-21 21:42:15 +01:00
Omar Shahine
14506aeca4 fix(bluebubbles): add opt-in coalesceSameSenderDms for split-send DMs (#69258)
Merged via squash.

Prepared head SHA: 8f1bd3cf53
Co-authored-by: omarshahine <10343873+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
Tak Hoffman
1303b03241 fix: add silent reply policy by conversation type (#68644)
Thanks @Takhoffman.
2026-04-21 05:17:55 +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
Sebastian B Otaegui
f48d040bf5 feat: send compaction start and completion notices (#67830)
Merged via squash.

Prepared head SHA: abedf6cf11
Co-authored-by: feniix <91633+feniix@users.noreply.github.com>
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Reviewed-by: @jalehman
2026-04-20 11:55:17 -07:00
Omar Shahine
e89b41fce7 fix(bluebubbles): configurable sendTimeoutMs, bump send default to 30s (#69193)
Merged via squash.

Prepared head SHA: 358204f963
Co-authored-by: omarshahine <10343873+omarshahine@users.noreply.github.com>
Co-authored-by: omarshahine <10343873+omarshahine@users.noreply.github.com>
Reviewed-by: @omarshahine
2026-04-20 10:04:52 -07:00
Peter Steinberger
8116e638f3 chore: release 2026.4.20 2026-04-20 13:16:40 +01:00
Peter Steinberger
ac8f0c9c0d chore: prepare 2026.4.19-beta.1 release 2026-04-19 02:09:43 +01:00
Vincent Koc
68502c90d1 fix(openrouter): parse visible reasoning_details output (#68577)
* fix(openrouter): parse visible reasoning_details output

* fix(openrouter): preserve reasoning_details ordering

* fix(openrouter): harden reasoning details compat

* fix(openrouter): queue post-tool-call reasoning text

* chore(config): refresh generated schema baselines

* fix(openrouter): keep fallback reasoning with visible details

* fix(openrouter): bound streaming tool-call buffers
2026-04-18 08:18:13 -07:00
Peter Steinberger
3f2e73b723 chore(release): bump version to 2026.4.18 2026-04-18 15:46:33 +01:00
Rubén Cuevas
a0dd5f7e8e Align documented bootstrap context defaults with runtime values (#67968)
* Fix bootstrap default limit docs to match runtime

* docs(context): fix stale bootstrap max/file example
2026-04-18 09:00:21 +05:30
Peter Steinberger
c635efd233 chore: prepare 2026.4.15-beta.2 release 2026-04-16 19:58:08 +01:00
Daniel Salmerón Amselem
687ede50a5 fix(agents): add prompt cache compatibility opt-out
Add compat.supportsPromptCacheKey for OpenAI Responses prompt_cache_key handling, update generated config baseline, changelog, and A2UI dependency-layout test compatibility.
2026-04-16 10:48:51 -07:00
Peter Steinberger
a177d8d454 build: refresh release baselines 2026-04-15 19:41:32 +01:00
Tak Hoffman
4f00b76925 fix(context-window): Tighten context limits and bound memory excerpts (#67277)
* Tighten context limits and bound memory excerpts

* Align startup context defaults in config docs

* Align qmd memory_get bounds with shared limits

* Preserve qmd partial memory reads

* Fix shared memory read type import

* Add changelog entry for context bounds
2026-04-15 13:06:02 -05:00
Vincent Koc
f09a4d9ba0 fix(agents): move lean local-model mode behind experimental flag 2026-04-15 11:41:28 +01:00
Peter Steinberger
7611d41136 build: refresh config docs baseline 2026-04-15 10:18:24 +01:00