vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-04-13 10:11:20 +00:00
Code Issues Packages Projects Releases Wiki Activity
28,549 Commits 1,252 Branches 105 Tags
4329d94de3a71803db177ee50af68eb75d7ea06b
Commit Graph

6269 Commits

Author SHA1 Message Date
Vincent Koc
2988203a5e feat(context-engine): add memory prompt helper 2026-04-07 08:56:41 +01:00
Vincent Koc
6a559f0293 feat(memory-wiki): gate compiled digest prompts 2026-04-07 08:56:25 +01:00
Vincent Koc
0d3cd4ac42 feat(memory-wiki): use digests for retrieval 2026-04-07 08:56:25 +01:00
Vincent Koc
44fd8b0d6e feat(memory-wiki): add claim health reports 2026-04-07 08:56:24 +01:00
Vincent Koc
947a43dae3 feat(memory-wiki): add belief-layer digests and compat migration 2026-04-07 08:56:24 +01:00
Ayaan Zaidi
e811d04db4 fix: openai tts groq wav (#62233) (thanks @neeravmakwana) 2026-04-07 12:56:22 +05:30
Neerav Makwana
68bfc6fcf5 Mistral: enable reasoning_effort for mistral-small-latest 
Made-with: Cursor
 2026-04-07 12:52:47 +05:30
Neerav Makwana
de2182877a fix: classify HTTP 404 errors for model fallback chain (#62244) (thanks @neeravmakwana) 
* Fix: classify HTTP 404 errors for model fallback chain

* Address PR review: preserve context overflow on HTTP 404, fix changelog order

* fix: add changelog attribution for HTTP 404 fallback fix (#62244) (thanks @neeravmakwana)

---------

Co-authored-by: Ayaan Zaidi <hi@obviy.us>
 2026-04-07 12:47:54 +05:30
Neerav Makwana
9a9dc1dbec fix: allowlist compat for capability provider fallback (#62234) (thanks @neeravmakwana) 
* Plugins: allowlist compat for capability provider fallback (#62205)

* test: cover all capability fallback keys

---------

Co-authored-by: Ayaan Zaidi <hi@obviy.us>
 2026-04-07 12:45:56 +05:30
Neerav Makwana
242b2e66f2 fix: normalize cron jobId load path (#62251) (thanks @neeravmakwana) 
* Cron: normalize jobId to id when loading jobs.json

* Cron: address review — changelog order, warn on legacy jobId
 2026-04-07 12:42:59 +05:30
Gustavo Madeira Santana
7155aa9c15 fix(docker): use built bundled plugins in runtime images (#62316) 
Merged via squash.

Prepared head SHA: c2bbfef188
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras
 2026-04-07 02:18:24 -04:00
Chunyue Wang
e8fb140642 fix: preserve Slack guarded media transport (#62239) (thanks @openperf) 
* fix(slack ): prevent undici dispatcher leak to globalThis.fetch causing media download failure

* fix(slack): preserve guarded media transport

* fix: preserve Slack guarded media transport (#62239) (thanks @openperf)

---------

Co-authored-by: Ayaan Zaidi <hi@obviy.us>
 2026-04-07 11:15:53 +05:30
Sam Padilla
f1b7dd6c0a fix: honor lightContext in spawned subagents (#62264) (thanks @theSamPadilla) 
* Add lightContext support for spawned subagents

* Clarify and guard lightContext usage in sessions_spawn

* test: guard sessions_spawn lightContext acp misuse

* fix: honor lightContext in spawned subagents (#62264) (thanks @theSamPadilla)

---------

Co-authored-by: Jaz <jaz@bycrux.com>
Co-authored-by: Ayaan Zaidi <hi@obviy.us>
 2026-04-07 11:05:45 +05:30
Ayaan Zaidi
47e6c57a7a fix: preserve telegram default auth promotion 2026-04-07 09:28:05 +05:30
Ayaan Zaidi
44f3539c4f fix: preserve telegram doctor allowlist fallback (#62263) 
* test: cover telegram doctor multi-account fallback

* fix: skip telegram default-account doctor seeding

* fix: preserve telegram doctor allowlist fallback (#62263)

* fix: keep doctor promotion keys plugin-owned (#62263)
 2026-04-07 09:11:11 +05:30
Gustavo Madeira Santana
9fd47a5aed Matrix: prompt invite auto-join during onboarding (#62168) 
Merged via squash.

Prepared head SHA: aec7a2249a
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras
 2026-04-06 23:22:01 -04:00
Vignesh Natarajan
338c7b8d66 changelog: note dreaming session corpus (#62227) (thanks @vignesh07) 2026-04-06 19:14:42 -07:00
Val Alexander
f0ba7b95da ui: fix light scrollbar selector 2026-04-06 21:10:00 -05:00
Bruce MacDonald
ac3f55504c feat(ollama): detect vision capability from /api/show and set image i… (#62193) 
Merged via squash.

Prepared head SHA: 85f85d1036
Co-authored-by: BruceMacD <5853428+BruceMacD@users.noreply.github.com>
Co-authored-by: BruceMacD <5853428+BruceMacD@users.noreply.github.com>
Reviewed-by: @BruceMacD
 2026-04-06 17:29:40 -07:00
scoootscooob
f4fcaa09a3 feat(gateway): add compaction checkpoints (#62146) 
Merged via squash.

Prepared head SHA: e37542554a
Co-authored-by: scoootscooob <167050519+scoootscooob@users.noreply.github.com>
Co-authored-by: scoootscooob <167050519+scoootscooob@users.noreply.github.com>
Reviewed-by: @scoootscooob
 2026-04-06 17:27:43 -07:00
Praktika Engineer
b8c8139138 feat(slack): add thread.requireExplicitMention config option (#58276) 
* feat(slack): add thread.requireExplicitMention config option

When requireMention is true in a Slack channel, replying inside a thread
where the bot previously participated currently bypasses mention gating
via implicit mention detection. This makes the bot respond to every
thread message even without an explicit @mention.

Add channels.slack.thread.requireExplicitMention (default: false) which,
when set to true, suppresses implicit thread mentions. Only explicit
@bot mentions will trigger replies inside threads.

Closes #34389
Closes #49972

* slack: refresh changelog and generated config artifacts

* slack: restore bundled channel metadata generation

---------

Co-authored-by: praktika-devops <devops@praktika.ai>
Co-authored-by: George Pickett <gpickett00@gmail.com>
 2026-04-06 17:05:11 -07:00
Peter Steinberger
425592cf9c refactor: share media normalization across runtimes 2026-04-06 23:50:27 +01:00
Peter Steinberger
096e6462c7 docs(changelog): reorder unreleased notes 2026-04-06 23:33:26 +01:00
Peter Steinberger
a463a33eee feat: preserve media intent across provider fallback 2026-04-06 23:23:06 +01:00
Vincent Koc
d88eb0e031 fix(exa): show Exa in setup pickers 2026-04-06 23:09:46 +01:00
Devin Robison
e420468ebd fix: openclaw allows normal reply text to carry media (#345) (#62136) 
* fix: openclaw allows normal reply text to carry media (#345)
 2026-04-06 16:08:33 -06:00
Onur
08296e9645 chore: bump bundled acpx to 0.5.1 (#62148) 
* chore: bump bundled acpx to 0.5.1

* chore: note acpx 0.5.1 pin bump (#62148) (thanks @onutc)
 2026-04-06 23:54:26 +02:00
Peter Steinberger
9d7459f182 fix(auth): recover Codex OAuth refresh after store reload 
Co-authored-by: Owen <oh.whenever@gmail.com>
 2026-04-06 22:45:04 +01:00
Devin Robison
48a3511233 fix: lower trust background runtime output is injecte (#327) (#62111) 
* fix: lower trust background runtime output is injecte (#327)

* fix: lower trust background runtime output is injecte (#327)

---------

Co-authored-by: OpenClaw Dummy Agent <octriage-dummy@example.invalid>
 2026-04-06 15:14:52 -06:00
Agustin Rivera
5b6e552b51 fix(hooks): mark wake hook events untrusted (#62003) 
* fix(hooks): mark wake hook events untrusted

* docs(changelog): add wake-hook trust entry

---------

Co-authored-by: Devin Robison <drobison@nvidia.com>
 2026-04-06 14:17:48 -06:00
Devin Robison
37d7c716f4 fix: the bundled qq bot extension extensions qqbot pe (#329) (#62082) 2026-04-06 13:50:33 -06:00
Devin Robison
681931345b fix: this is a real approval boundary bypass that tur (#323) (#62078) 2026-04-06 13:13:35 -06:00
Devin Robison
7306cf3707 fix: multiple dangerous build tool environment variab (#317) (#62079) 2026-04-06 13:10:38 -06:00
Peter Steinberger
1b7e16668e fix: finalize arcee provider landing (#62068) (thanks @arthurbr11) 2026-04-06 19:53:27 +01:00
arthurbr11
95106be59b feat: enhance Arcee AI provider with OpenRouter support and update onboarding instructions 2026-04-06 19:53:27 +01:00
arthurbr11
5ac2f58c57 feat: add Arcee AI provider plugin 
Add a bundled Arcee AI provider plugin with ARCEEAI_API_KEY onboarding,
Trinity model catalog (mini, large-preview, large-thinking), and
OpenAI-compatible API support.

- Trinity Large Thinking: 256K context, reasoning enabled
- Trinity Large Preview: 128K context, general-purpose
- Trinity Mini 26B: 128K context, fast and cost-efficient
 2026-04-06 19:53:27 +01:00
Peter Steinberger
a211f09259 docs: note discord voice recovery fix (#41536) (thanks @wit-oc) 2026-04-06 18:44:19 +01:00
Peter Steinberger
dfa14001a4 fix: harden discord voice receive recovery (#41536) (thanks @wit-oc) 2026-04-06 18:44:19 +01:00
Peter Steinberger
725cbcc362 fix(plugins): narrow provider hook reentry guard 2026-04-06 17:57:49 +01:00
EVA
594ea6e1b9 fix(agents): backfill missing sessionKey in embedded PI runner — prevents undefined key in model selection and live-switch (#60555) 
Merged via squash.

Prepared head SHA: 8081345f1c
Co-authored-by: 100yenadmin <239388517+100yenadmin@users.noreply.github.com>
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Reviewed-by: @jalehman
 2026-04-06 09:51:05 -07:00
Vincent Koc
e7fe087677 fix(openai): normalize prompt overlay personality config 2026-04-06 17:24:51 +01:00
Peter Steinberger
220d10cad3 docs(changelog): add unreleased entries for 2026.4.6 2026-04-06 17:05:30 +01:00
Yossi Eliaz
0f5919a4ba fix(ssrf): disable HTTP/2 for pinned SSRF-guard dispatchers (undici 8.0 compat) 
Undici 8.0 defaults HTTPS clients to negotiate HTTP/2 via ALPN, which is
incompatible with the custom `connect.lookup` callback used for SSRF DNS
pinning. This caused `TypeError: fetch failed` in web_fetch/web_search.

Explicitly set `allowH2: false` on all dispatcher creation paths (Agent,
EnvHttpProxyAgent, ProxyAgent) to restore HTTP/1.1 behavior and keep the
pinned DNS lookup working reliably.

Closes #61738
 2026-04-06 17:02:10 +01:00
Peter Steinberger
0b36423f97 docs: reorder unreleased changelog entries 2026-04-06 16:58:28 +01:00
Peter Steinberger
21f59a0ad5 fix: suppress commentary history leaks (#61747) (thanks @afurm) 2026-04-06 16:54:34 +01:00
Peter Steinberger
aa6f6135db fix: tighten TUI phase handling and heartbeat session guards (#61463) (thanks @100yenadmin) 2026-04-06 16:35:22 +01:00
Peter Steinberger
0b9993df95 fix(agents): keep phaseless OpenAI WS text buffered until phase resolves (#61968) 
* fix(agents): gate WS text delta emission on valid phase value, not map key existence

When output_item.added arrives without phase metadata, outputItemPhaseById
stores undefined. The previous .has() check returned true for undefined
values, bypassing the buffering gate and leaking commentary as unphased
visible content.

Fix: change .has() to .get() !== undefined on both delta and done handlers.

Fixes #61477

* docs: note WS phase buffering fix (#61954) (thanks @100yenadmin)

* test(agents): cover phaseless WS output_text.done buffering (#61954)

* test(commands): fix session-store import path for tsgo (#61968)

---------

Co-authored-by: Eva <eva@100yen.org>
 2026-04-06 16:35:16 +01:00
Peter Steinberger
7785dc21e6 fix(discord): drop generated thread title temperature 2026-04-06 16:29:43 +01:00
Peter Steinberger
16d0f0567e fix: preserve legacy replay phase boundaries (#61529) (thanks @100yenadmin) 2026-04-06 23:09:29 +08:00
Peter Steinberger
baf4119ae3 fix: harden local TLS gateway probes (#61935) (thanks @ThanhNguyxn07) 2026-04-06 15:44:30 +01:00