38f157a148
fix(openai): prefer configured Codex OAuth for images
2026-04-23 22:49:37 +01:00
e64da8bde0
ci: rebase test performance agent updates
2026-04-23 22:46:38 +01:00
58dc22c099
docs: refresh documentation
2026-04-23 21:43:52 +00:00
d40dd9088e
feat(memory): configurable local embedding contextSize (default 4096) ( #70544 )
...
node-llama-cpp defaults contextSize to "auto", which on large embedding
models like Qwen3-Embedding-8B (trained context 40,960) inflates gateway
VRAM from ~8.8 GB to ~32 GB and causes OOM on single-GPU hosts that share
the gateway with an LLM runtime.
Expose memorySearch.local.contextSize in openclaw.json (number | "auto"),
default to 4096 which comfortably covers typical memory-search chunks
(128–512 tokens) while keeping non-weight VRAM bounded.
Closes #69667 .
2026-04-23 14:21:53 -07:00
f3aaafbd70
ci: use latest stable install smoke baseline
2026-04-23 22:11:53 +01:00
ddcc39de91
fix(openai): reuse Codex OAuth for OpenAI images
2026-04-23 22:06:36 +01:00
76276b876d
docs: refresh documentation
2026-04-23 21:04:33 +00:00
137dbc71f0
feat: expose harness selection decisions ( #70760 )
...
Codex harness selection now keeps the decision helper internal, logs debug-only selection reasons and candidates, and documents `/status` as the primary user-facing signal.
Thanks @100yenadmin.
Co-authored-by: Eva <eva@100yen.org >
2026-04-23 21:57:09 +01:00
235e17a08f
docs: update config baseline
2026-04-23 21:55:36 +01:00
10202f9279
fix(codex): approve bundled MCP loopback tools
2026-04-23 21:55:36 +01:00
8af3d91668
docs(openai): clarify codex oauth image generation
2026-04-23 21:47:33 +01:00
d9aacbd3f9
ci: skip duplicate npm global install smoke
2026-04-23 21:43:06 +01:00
c84a2f5244
feat(openai): add codex oauth image generation
2026-04-23 21:34:24 +01:00
7ce36b4d12
ci: isolate non-root install smoke cache
2026-04-23 21:31:13 +01:00
f5042adf27
feat: add forked subagent context
2026-04-23 21:28:58 +01:00
abedf9c1f4
fix(acpx): remove codex auth file fallback
2026-04-23 21:26:46 +01:00
c5c163d078
docs: standardize frontmatter field order (summary before title)
2026-04-23 13:18:17 -07:00
bb63f3c26b
docs: document embedded harness status indicator
2026-04-23 21:17:20 +01:00
82a847f3b4
docs(providers): standardize Related card titles, config-reference links, and Advanced heading
2026-04-23 13:16:53 -07:00
f6336c5521
fix(openai): retire removed Codex Spark model
2026-04-23 21:16:46 +01:00
2777b089b5
docs: normalize frontmatter titles to sentence case
2026-04-23 13:15:17 -07:00
831d6c3bbe
docs: fix msteams federated auth link
2026-04-23 21:12:00 +01:00
4a2cd533ac
docs: remove duplicate H1 where frontmatter title already sets it
2026-04-23 13:11:14 -07:00
219a11d2bd
docs: fix googlechat entity and dedup gateway multiple-gateways section
2026-04-23 13:08:13 -07:00
0905e5f7b6
docs(channels): msteams - drop duplicate minimal-setup block, cardify related, accordion env vars, remove H1 and dante quote
2026-04-23 13:07:23 -07:00
ea25d7ed5b
fix(qr): replace qrcode-terminal with qrcode-tui
...
Replace legacy qrcode-terminal usage with shared qrcode-tui media helpers, bound QR PNG rendering options, and raise bundled plugin host floors for the new SDK runtime surface.
2026-04-23 13:06:14 -07:00
956350bb9c
ci: share npm cache in install smoke
2026-04-23 20:57:31 +01:00
629ed9f702
ci: run test performance agent on hosted ubuntu
2026-04-23 20:51:40 +01:00
648422a6c1
fix(openai): send image edits as multipart uploads ( #70657 )
2026-04-23 20:48:55 +01:00
a8173276bf
docs(openai): canonicalize GPT model refs
2026-04-23 20:47:38 +01:00
360cb3dbf1
ci: add test performance agent
2026-04-23 20:40:52 +01:00
aad31817ef
ci: add bun global install smoke
2026-04-23 20:27:04 +01:00
6896692111
docs(sidebar): sort tools group alphabetically
2026-04-23 12:25:25 -07:00
ba890a4578
docs(channels): telegram - collapse prose field list into accordion summary, cardify related, remove H1
2026-04-23 12:22:02 -07:00
c43a447b38
docs(channels): slack - collapse duplicate HTTP slash-commands JSON, cardify related, accordion config pointers, remove H1
2026-04-23 12:20:25 -07:00
89051c6bf6
docs(openai): document GPT-5.5 defaults
2026-04-23 20:19:15 +01:00
54731492a2
fix(gateway): persist webchat images as managed media ( #70719 )
...
* fix(gateway): persist webchat images as managed media
* fix(ui): keep managed image auth same-origin
* docs: note managed webchat image fix
2026-04-23 20:17:41 +01:00
e9405318b4
fix(openai): default realtime voice to gpt-realtime-1.5
2026-04-23 19:39:24 +01:00
c1f423f845
fix(secrets): harden Windows ACL fallback and strip BOM ( #70662 )
...
Fail closed when Windows ACL checks cannot be verified for file and exec secret providers unless the provider explicitly opts into allowInsecurePath. Strip UTF-8 BOMs from file-backed secrets and document the trusted-path override.\n\nThanks @zhanggpcsu.
2026-04-23 19:32:15 +01:00
884d7929d1
docs: format testing accordion notes
2026-04-23 19:28:24 +01:00
fd1d6b0241
ci: serialize extension shard batches
2026-04-23 19:25:14 +01:00
314041a885
docs(channels): discord - drop duplicate developer-portal block, cardify related, accordion config pointers, remove H1
2026-04-23 11:19:28 -07:00
36c89ecaf6
ci: cap extension shard vitest workers
2026-04-23 19:14:15 +01:00
e4534efe8e
docs(help): testing - drop redundant H1, progressive-disclose unit/integration maintainer notes into AccordionGroup
2026-04-23 11:13:14 -07:00
b0efa8d43d
docs(gateway): security — sentence-case headings, remove manual TOC and H1, drop custom anchors, tuck triage notes into Accordion
2026-04-23 11:09:33 -07:00
802646e004
fix: catch Mintlify accordion parse hazards
2026-04-23 19:04:35 +01:00
75df14cbbc
test: mark video capability mirror intentional
2026-04-23 18:54:33 +01:00
393a71991f
fix: decouple approval startup from replay
2026-04-23 18:49:57 +01:00
184c4e3788
ci: add duplicate PR cleanup workflow
2026-04-23 18:41:32 +01:00
12de62bfd8
docs(plugins): architecture — sentence-case title, CardGroup intro, dedup provider-hook prose list, progressive-disclose bundled-provider examples
2026-04-23 10:39:57 -07:00
Peter Steinberger