Peter Steinberger
b9b97f2653
test: raise Docker aggregate resource caps
2026-04-25 00:52:52 +01:00
Peter Steinberger
a7696b496a
test: improve Docker aggregate scheduling
2026-04-24 23:44:02 +01:00
Peter Steinberger
6e985a421d
fix(webchat): keep runtime context out of visible transcripts
...
Keep WebChat runtime context available to the model while persisting only the transcript-facing user prompt across gateway, CLI, queued follow-up, and embedded Pi paths.
Adds regression coverage for history sanitization, CLI transcript persistence, media-only auto-reply prompts, and embedded Pi prompt rewrite against a real SessionManager file.
Co-authored-by: 91wan <91wan@users.noreply.github.com >
2026-04-24 22:17:03 +01:00
Vincent Koc
86099ec62a
refactor(web-fetch): move readability extraction to plugin
...
* refactor(web-fetch): move readability extraction to plugin
* fix(web-fetch): cache extractor resolution by config
* fix(test): remove redundant stat assertions
2026-04-24 13:34:37 -07:00
Peter Steinberger
0f689d22f4
test: add weighted Docker aggregate scheduler
2026-04-24 20:41:27 +01:00
Vincent Koc
1042b893f6
docs: drop parenthetical H1s across gateway, channels, providers, concepts, and reference pages
2026-04-24 10:49:23 -07:00
Peter Steinberger
62adf6349d
docs(release): require tmux for 1password fallback
2026-04-24 18:44:43 +01:00
Peter Steinberger
38caa6832d
test: stagger docker aggregate starts
2026-04-24 08:38:41 +01:00
Ayaan Zaidi
0baa8c1763
ci(release): add manual npm telegram beta e2e
2026-04-24 12:06:33 +05:30
Ayaan Zaidi
bd1b8448a5
test(release): support convex npm telegram credentials
2026-04-24 12:06:33 +05:30
Peter Steinberger
01e4824fd3
test: parallelize docker aggregate lanes
2026-04-24 05:55:27 +01:00
Ayaan Zaidi
9755c8a05f
test(release): add npm telegram live smoke
2026-04-24 10:23:56 +05:30
Josh Lehman
51186d2725
feat(codex): run context-engine lifecycle in app-server harness ( #70809 )
...
Port the Codex app-server harness onto the context-engine lifecycle, add Codex context projection and compaction integration, and cover bootstrap/history/compaction fallback behavior.
Thanks @jalehman.
2026-04-24 05:06:45 +01:00
Vincent Koc
2fb9c7e3e5
docs: add Related sections to remaining platform, reference template, and misc pages
2026-04-23 20:40:15 -07:00
Peter Steinberger
dbdf2863d6
docs: fix broken internal links
2026-04-24 04:13:20 +01:00
Vincent Koc
07cee914aa
docs(gateway): split configuration-reference by extracting agent-defaults cluster into config-agents
2026-04-23 20:11:12 -07:00
Vincent Koc
f0b6c65e3b
docs(install,reference): add Related sections to pages missing them
2026-04-23 20:07:25 -07:00
Peter Steinberger
2af88fab6c
docs: document local memory embedding provider
2026-04-24 03:11:22 +01:00
Peter Steinberger
e28fca2e11
chore: separate commit formatting from changed gate
2026-04-23 23:55:52 +01:00
Peter Steinberger
14c4143723
docs: clarify OpenAI GPT-5.5 auth routes
2026-04-23 23:49:17 +01:00
openclaw-docs-agent[bot]
58dc22c099
docs: refresh documentation
2026-04-23 21:43:52 +00:00
aalekh-sarvam
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
Vincent Koc
c5c163d078
docs: standardize frontmatter field order (summary before title)
2026-04-23 13:18:17 -07:00
Vincent Koc
2777b089b5
docs: normalize frontmatter titles to sentence case
2026-04-23 13:15:17 -07:00
Vincent Koc
4a2cd533ac
docs: remove duplicate H1 where frontmatter title already sets it
2026-04-23 13:11:14 -07:00
Vincent Koc
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
Peter Steinberger
a8173276bf
docs(openai): canonicalize GPT model refs
2026-04-23 20:47:38 +01:00
Peter Steinberger
360cb3dbf1
ci: add test performance agent
2026-04-23 20:40:52 +01:00
Peter Steinberger
89051c6bf6
docs(openai): document GPT-5.5 defaults
2026-04-23 20:19:15 +01:00
Peter Steinberger
deb1364dfb
refactor: centralize root memory file policy
2026-04-23 16:40:41 +01:00
Mariano
10a9acbf29
fix: keep root memory uppercase ( #70621 )
...
Thanks @mbelinky.
2026-04-23 16:10:36 +01:00
Peter Steinberger
1bbca1d910
ci: run full docker checks daily
2026-04-23 14:32:30 +01:00
Peter Steinberger
e98331b0be
test: parallelize docker aggregate
2026-04-23 14:31:18 +01:00
Vincent Koc
c8aec6b951
docs: Control UI identity + gateway pairing hardening + release verification
2026-04-22 23:52:37 -07:00
Peter Steinberger
938af16289
docs: deep audit documentation against source
2026-04-23 07:32:58 +01:00
Peter Steinberger
834fdc4832
docs: align documentation with current surfaces
2026-04-23 07:25:06 +01:00
Peter Steinberger
c78562d8a2
ci: fan out qa lab lanes
2026-04-23 06:15:01 +01:00
Peter Steinberger
db332aa8e9
ci: schedule qa lab gates
2026-04-23 06:08:29 +01:00
pashpashpash
6f6fa5c90b
Remove Codex CLI auth import
2026-04-22 19:27:52 -07:00
Peter Steinberger
8d1b3d4578
ci: speed up release metadata pre-commit checks
2026-04-21 21:56:06 +01:00
Peter Steinberger
b485ee7e36
docs: support release branch workflow
2026-04-21 05:33:21 +01:00
Peter Steinberger
bd0c9024a2
docs: document Kimi cost live smoke
2026-04-21 03:10:56 +01:00
Peter Steinberger
04cdc33731
test: fix unit coverage scope
2026-04-20 23:36:33 +01:00
Peter Steinberger
97e79bb5f6
test: balance extension shard scheduling
2026-04-20 17:41:38 +01:00
Peter Steinberger
0603ceba23
test: split heavy extension test shards
2026-04-20 16:50:01 +01:00
Peter Steinberger
788b47536c
feat: add changed-lane local gate
2026-04-20 15:48:20 +01:00
Peter Steinberger
3ecb713b00
perf: speed local checks and warm builds
2026-04-20 15:08:41 +01:00
Peter Steinberger
91d31197be
ci: run architecture check before release
2026-04-20 13:24:49 +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
Ayaan Zaidi
33154ce745
fix: simplify ollama onboarding ( #67005 )
...
* feat(ollama): split interactive cloud and local setup
* test(ollama): cover cloud onboarding flow
* docs(ollama): simplify provider setup docs
* docs(onboarding): update ollama wizard copy
* fix(ollama): restore web search auth helper
* fix(ollama): harden setup auth and ssrf handling
* fix(ollama): address review regressions
* fix(ollama): scope ssrf hardening to ollama
* feat(ollama): add hybrid onboarding mode
* fix(ollama): tighten cloud credential setup
* refactor(ollama): distill host-backed setup modes
* fix(ollama): preserve cloud api key in config
* fix: simplify ollama onboarding (#67005 )
2026-04-15 19:06:21 +05:30
