The managed llama-server default ctx-size was 8192, but the full OpenClaw
agent system prompt alone is ~31K tokens, so the first agent turn overflowed
the context window and forced immediate compaction (observed live on the Mac
app local-model onboarding). Raise the default to 65536 so a fresh local-model
install can run a real agent turn out of the box.
The default-download 16 GiB RAM floor already bounds weaker machines, and
Gemma 4 supports far more than 64K, so this only changes headroom, not the
offer gate. Docs updated to match.
* fix(slack): keep commentary progress on draft lane
* fix(channels): route commentary through one progress owner
Keep non-verbose commentary in Slack and Discord draft lanes while preserving one durable commentary payload when verbose progress makes those drafts yield. Freeze that owner decision for the turn so session changes apply on the next turn.
Co-authored-by: Dallin Romney <dallinromney@gmail.com>
Punchcard-Session: amber-workshop-workshop-36
* fix(channels): refresh queued commentary owner
Recompute the frozen draft-versus-durable commentary owner for every queued follow-up turn and carry that decision into final payload projection.
Punchcard-Session: amber-workshop-workshop-36
* fix(channels): clarify commentary owner opt-in
* fix(channels): preserve queued draft preambles
* fix(channels): require explicit queued progress ownership
* refactor(channels): record commentary progress owner
* fix(telegram): tolerate unscoped queued updates
* test(discord): use canonical draft fixture after rebase
---------
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
Reject reserved /healthz webhook configurations before registration, preventing silent Telegram update loss. Warn through Doctor and document recovery.
Co-authored-by: Peter Lee <22994703+xialonglee@users.noreply.github.com>
Co-authored-by: Ayaan Zaidi <hi@obviy.us>
Preserve reply and selected-quote metadata from later Telegram debounce and fragment-batch messages while keeping reply-chain recovery bounded.
Co-authored-by: iridescentWen <whatmakesbetter@outlook.com>
Co-authored-by: Ayaan Zaidi <hi@obviy.us>
Telegram native-command registration resolved provider names through the bundled channel-plugin fallback, which jiti-transpiles the entire plugin plus core graph from source when no registry entry is loaded (~190s silent CPU) — tripping the 300s no-output CI watchdog on the two Telegram test files that register at module scope. Telegram defines no resolveNativeCommandName hook, so the load resolved nothing. Thread the existing includeBundledChannelFallback option through the spec-listing helpers and use loaded-registry-only lookups in the Telegram plugin, matching the Discord sibling. Runtime names are byte-identical; both files drop from 200s to ~5s.
* feat(computer-use): computer.act v2 action contract with capability-filtered tool
* fix(computer-use): break contract import cycle, bound model-visible elements, regen swift protocol
* test(computer-use): satisfy curly rule in schema-cap helpers
* fix(computer-use): satisfy type-aware lint on contract and tool
* test(gateway-protocol): keep connect-params suite under the line cap
Reject unbound foreign-channel fallback at shared approval-account selection while preserving recorded bindings and explicit forwarding targets. Cover Telegram and Matrix routing contracts.
Co-authored-by: vatsalgargg <vatsalg80@gmail.com>
Co-authored-by: Ayaan Zaidi <hi@obviy.us>
* feat(browser): sync system cookies to a remote gateway profile
Add `openclaw browser cookie-sync`: decrypt allowlisted macOS Chrome-family
cookies locally and push them into a managed profile on a possibly-remote
Gateway over the existing operator channel. --watch re-syncs on cookie-DB
changes with a single Keychain prompt per session.
- New POST /cookies/set-many batch route (mirrors /cookies/set)
- Extract one canonical readSystemProfileCookies reused by import + sync
- Mandatory domain allowlist (never syncs an unrestricted cookie jar)
- Decryption stays host-local (macOS); no cookie values are logged
* feat(macos): cookie sync checkbox and configuration UI
Add an off-by-default 'Cookie sync' section (Settings > General): a toggle, an
editable domain allowlist editor, and a target-profile field, actionable only in
remote-gateway mode. CookieSyncManager supervises `openclaw browser cookie-sync
--watch` against the connected Gateway when enabled, resolving a LOCAL CLI (never
the SSH-redirect path, since decryption is host-local) and injecting gateway
URL + token/password via environment, never argv. A status row surfaces
running/stopped/error and the last sync summary.
* fix(macos): satisfy cookie sync lint gates
* chore(i18n): register cookie sync native source strings
Regenerate apps/.i18n/native-source.json baseline for the new macOS Cookie
sync settings strings (additive only). Satisfies the native:i18n:verify gate;
generated locale artifacts are refreshed separately by the locale-refresh job.
* test(cua-computer): freeze provider parity fixtures
* test(cua-computer): keep parity fixture type aliases file-local until a consumer exists
* test(cua-computer): split parity fixtures under the line cap and fix strict test types
* feat(codex): pass explicit skill selections as structured turn input
Thread OpenClaw-resolved explicit $skill selections through the reply
pipeline to the Codex app-server harness and emit them as structured
UserInput::Skill turn items when the Codex catalog (skills/list) knows the
same SKILL.md path. Codex then injects the skill natively and blocks its
text scanner from double-selecting the same name, while unmatched names
stay scannable for Codex-native-only skills and the prompt instruction
block keeps owning skills Codex cannot see. Catalog misses and RPC errors
fail open to the instruction path; the turn never fails on skill lookup.
Part of #123367
* fix(plugins): defer llama-cpp ssrf-runtime load out of the setup closure
The doctor-contract closure guard forbids the SSRF barrel in the
doctor/legacy-setup closure (cold-loads DNS, proxy state, logging); the
static import landed with the managed llama-server switch (#123105) and
first fails when a PR selects the guard lane. Defer to a dynamic import at
download time per the guard's stated remedy.
Preserve raw query separators in Telegram rich-message bare URLs by leaving parser-generated links to Telegram entity detection. Authored Markdown links remain typed, while file references remain code-formatted.
Co-authored-by: Ayaan Zaidi <hi@obviy.us>
Move llama.cpp chat and local embeddings onto a verified externally managed llama-server runtime. Remove the in-process native runtime, forked embedding workers, and node-llama-cpp dependency while preserving guided setup, local GGUF models, tool-capable agent runs, diagnostics, and operator docs.
* ci: codify manual-only Node 22 compatibility
* ci: split remaining hosted tail lanes
* fix(qa-lab): carry the validated part index into the plan id type
* test(ci): repair hosted tail lane guards
Codex byte-scans every turn text input for $name skill mentions and
[@name](plugin://...) links (codex-rs/skills/src/mentions.rs), so historical
$skill tokens inside OpenClaw's projected <conversation_context> block and
inbound quoted-reply/room-backlog context counted as current explicit
invocations and injected skill bodies the user never requested.
Neutralize mention sigils with same-length fullwidth lookalikes (the
escapeCodexChatText technique) in projected history and inbound context;
only the raw current request stays selectable.
Fixes#122812
Slack and Discord routed system events now retain route ownership when they enter literal-global queues, so sibling agents cannot consume them. Genuinely unbound routing remains an explicit error instead of falling back to a default agent.
Peter Steinberger