* fix(agents): teach canonical automations tool in fallback guidance and reuse the identity source
Review follow-ups: the structured-list fallback still taught models the cron
tool; the cron-scope test echoed its own stub; MCP serve allowlist and voice
confirmation hardcoded the name instead of the canonical constant.
* fix(mcp): place automations identity import outside the header comment
* feat(agents): rename model- and user-facing scheduler strings to automations
Rewrites every string the model or user sees that names the feature:
tool label and terminal presentation, display-summary preset, subagents
catalog description, heartbeat guidance, subagent prompt, session labels
(Cron: -> Automation:), default job name, unattended-run preamble, delivery
awareness text, task-ledger progress summary, failure alerts, auto-disable
notification, model preflight diagnostics, validation errors, and the
shipped workspace AGENTS.md template. Adds a system-prompt backstop rule on
the automations tool line: the feature is called automations, never cron.
Cron stays only where it names the schedule syntax ({kind:"cron"}, cron
expressions), config keys (cron.triggers.enabled), RPC method names, and
session-key namespaces. Test fixtures with legacy labels are kept as
stored-data coverage. Part of RFC openclaw/rfcs#50 Phase 1 (PR B).
* docs(templates): keep workspace template on the live docs anchor until the docs PR renames it
* fix(cron): rename remaining failure-notification producers and stale test expectations
Codex review follow-ups: the per-run failure notification (server-cron-
notifications) and the doctor legacy-notify advisory still said Cron job;
failure-alert and incomplete-turn suites still asserted the old wording.
* chore(plugin-sdk): re-emit plugin-state test runtime dts
CI's extension-boundary runner holds stale tsgo incremental state whose
cached plugin-state-test-runtime.d.ts predates the keyed-store re-exports;
the freshness stamp validates it and reruns reuse the same sticky disk.
Touching the module forces incremental emit to regenerate the declaration.
Fresh builds of this head (local exact CI command and a forced Testbox
rebuild) both emit the exports correctly.
* fix(agents): rename residual model- and operator-facing cron prose
Found in combined dev-gateway E2E: fallback tool line still told models the
scheduler tool is cron; heartbeat scratch description, cron model preflight
rejection, doctor and Claw prose still said cron jobs.
* fix(agents): finish model-facing scheduler strings flagged in review
Loop work-order prompts, subagents tool description, cron-tool write errors,
and the headless exec denial label now say automations; loop builders covered
by prompt assertions; snapshots regenerated.
* chore(agents): refresh generated baselines and live docs anchor after rebase onto main
* fix(agents): rename new main-side cron tool error expectations to automations
* fix(gateway): rename main-side cron notification test expectations to automations
* chore(agents): apply review moves - automations commands in workspace template, drop unrelated sdk comment
---------
Co-authored-by: Omar Shahine <10343873+omarshahine@users.noreply.github.com>
Providers stream commentary as cumulative snapshots, and the draft line id was derived from the commentary text, so each snapshot minted a new id and stacked another line instead of replacing the open one. Id-less commentary now remembers its open line and reuses that id when the next snapshot continues it; a snapshot sanitized to nothing no longer clears the line, since only an explicit item id retracts.
Also fixes activation: the commentary gate guessed "partial" when streaming.mode was unset, which made progress.commentary a silent no-op on channels whose own default is progress (Telegram, Discord). It now takes the caller's resolved mode, matching resolveChannelStreamingPreviewToolProgress. Proven live on Telegram: three overlapping commentary lines collapse to one.
Three gates my own changes broke:
- docs/channels/telegram.md needed a blank line before </Note>; I formatted the
TypeScript but never ran the docs formatter over the pages I edited.
- The mock harness matched a literal with a regex, which oxlint's prefer-includes
rejects.
- Widening resolveChannelPreviewStreamMode's defaultMode to StreamingMode and
adding rendersRollingLinesNatively changes the exported plugin-SDK surface, so
the API baseline hash had to be regenerated.
* feat(gateway): add loopback locality controls
* fix(gateway): keep loopback auth delays enforced under concurrency
The pending-timer cap let an attacker park cheap failures in every slot and then guess without penalty. Delays now key off a per-key deadline, so parallel guesses wait out the same escalating penalty and are still bounded by the max delay.
* fix(gateway): share one loopback penalty timer per key
Concurrent failures on a key now share a single timer and deadline instead of allocating one per in-flight request. Also corrects the security doc: the delay raises the cost of repeated guessing from one source, but credentials are compared before the failure response is delayed, so it is not a defense against parallel fan-out.
* docs(gateway): record why loopback delay stays post-verification
* docs: refresh generated docs map
* docs: refresh plugin SDK API baseline
* test: update loopback locality CI expectations
Track full dispatch completion separately for error handling and shutdown drain while allowing same-session follow-ups to steer active runs. Fixes#113180.
Co-authored-by: Taksh <takshkothari09@gmail.com>
* feat(gateway): share the canonical browser-origin policy with plugins
Export resolveAcceptedBrowserOrigin through openclaw/plugin-sdk/webhook-request-guards
so browser-facing plugin routes reuse the Gateway's real origin contract instead of a
narrow allowedOrigins array check. Private LAN/Tailnet Control UI loads and the
Host-header fallback were previously rejected with 403 by plugin offer routes while the
Control UI itself worked.
Moves the loopback/forwarded-header helpers to net.ts (re-exported from auth.ts) so the
guard can delegate without importing gateway auth, and migrates the Codex realtime
broker onto the shared seam.
* feat(talk): let providers own agent delegation for realtime voice
Adds an optional runAgentConsult callback to the browser-session create request and
injects the existing embedded consult runtime from talk-client, bound to the same agent
and session key the GA tool path uses. Providers whose realtime protocol delegates work
through their own control channel (rather than GA function calls) can now reach the
OpenClaw agent without a client round-trip.
Threads the effective per-session model into browser-session capability resolution so a
request-level model override selects the right capability set, and propagates a caller
abort signal into consultRealtimeVoiceAgent so a superseded delegation stops its run.
* feat(openai): support GPT-Live realtime voice over ChatGPT OAuth
Implements OpenAI's quicksilver/frameless session natively for Talk browser sessions.
The Gateway creates the WebRTC call (multipart sdp+session to https://api.openai.com/v1/live)
and owns the sideband control socket, so the browser never holds upstream credentials;
delegation.created events run through the OpenClaw agent and stream back as speakable
context appends.
Verified end-to-end on 2026-07-28 against a ChatGPT Pro OAuth profile: call create 201
with an rtc_* id and answer SDP, sideband session.started, session.close teardown.
ChatGPT OAuth is preferred over a Platform API key because /v1/live access for platform
keys is waitlist-gated; the legacy chatgpt.com backend route returns 403 for every model
and protocol version and is not used.
Accepted models are gpt-live-1-codex and gpt-live-1-boulder-alpha; the voice allowlist is
the ten values the route actually accepts, since an invalid voice is rejected at call
creation and cannot be repaired afterwards (session.update reports immutable_field_update).
* docs: document GPT-Live Talk support and its route gotchas
Records the working route and auth, the accepted models and voices, the browser-only
scope, and the two traps that cost the most time: the chatgpt.com backend route returns
403 Voice session access denied for every model, and that same 403 is also what an
invalid voice returns, so it must not be read as an account entitlement block.
* fix(openai): resolve GPT-Live CI failures
* refactor(openai): own zod runtime dependency
* fix(openai): satisfy lint and live-shard gates for GPT-Live
Types the retry-delay finish callback as Error so the rejection reason is provably an
Error at the call site; the abort path already normalized a non-Error AbortSignal reason,
but the unknown parameter type hid that from static analysis.
Registers the new GPT-Live live test in the native-live-extensions-openai shard
expectation. The shard selector already picked the file up from the real tree; only the
hardcoded list in the tooling test lagged.
* fix(openai): clean up post-rebase capability resolver
* fix(openai): preserve GPT-Live delegation fragments
* fix(openai): close GPT-Live sideband handoff race
* fix(openai): accept UUID GPT-Live call ids
* style: apply oxfmt to GPT-Live sources and Talk docs
* style: format Talk docs after rebase
* fix(openai): keep GPT-Live transcript context across ignored delegations
* feat(memory): add provenance and recall metadata to the memory index
* feat(memory): provenance-gated promotion and capture hygiene
* feat(dreaming): LLM consolidation with deterministic gates, on by default
* feat(active-memory): deterministic recall lane with escalation default
* feat(memory): user model file and standing intents
* docs(memory): document the memory architecture
* fix(memory): live-QA fixes — metadata writers, provenance classes, intent scope, claim accumulation
* refactor(channels): own account status in one closed state machine
* fix(gateway): stop storing derived reasons and configured in channel runtime
* fix(channels): separate linkage from configuration in whatsapp and zalo personal
* fix(cli): render channel state reasons apart from runtime failures
* refactor(channels): keep account-state projection internal to its owner
* feat(plugins): deliver sessions.changed to plugin services
* docs: regenerate docs map
* refactor(clickclack): split reconcile scheduler and history formatting out of the discussion service
* style: format discussion service
* perf(logging): flush file transport asynchronously off the request path
* fix(ci): record flushLogger surface growth and drain before log reads
- +1 public export/callable budget with annotation: logger file-transport
flush for graceful shutdown drains; regenerate SDK API baseline
- three tests that read the log file right after logging now drain the
async file transport first (flushLogger) instead of racing the flusher
* test: drain async log transport before reading talk and request-trace logs
* test: drain async log transport in CLI logger file tests
* test: drop unused withTempDirSync import
* refactor(prompt): plain inbound context labels with a provenance marker
Replaces trust-worded inbound context labels ("(untrusted metadata)",
"(untrusted, for context)") with plain labels plus a fixed provenance
marker suffix appended to every OpenClaw-injected context header.
Detection keys on the marker, not label text, so strippers stay correct
across UI, TUI, replay, /trace segmentation, memory recall, and the Swift
chat preprocessor. Drops sanitizeInboundSystemTags in favor of the marker
boundary plus trusted system-prompt narration.
Renames the untrusted-named plugin SDK context identifiers to
channel-provenance names, keeping deprecated aliases registered for
removal after 2026-09-08.
Adds `openclaw doctor --fix` migrations that rewrite legacy inbound
labels in stored SQLite transcripts and purge legacy envelope-
contaminated LanceDB recall rows.
* fix(ci): resolve gate failures for plain inbound context labels
- doctor sqlite readers: open read-only connections via openNodeSqliteDatabase
so the Kysely connection-boundary guardrail holds; unexport the now-internal
transcript snapshot type (Knip unused-export gate).
- compat registry: split the record table into registry-records.ts and
plugin-sdk-subpath-records.ts. The new compat record pushed registry.ts past
the 700-line oxlint cap; suppressions are disallowed, so follow the existing
sibling record-module pattern. Public exports and PluginCompatCode literals
unchanged.
- acp-runtime test: assert current finalization behavior (newline normalization
only). The bracket de-fang and System: rewrite it expected were removed with
sanitizeInboundSystemTags; forged system lines are neutralized at the
system-event queue, the single chokepoint feeding the System:-per-line render.
- regenerate docs_map and the plugin SDK API baseline manifest.
* fix(prompt): harden inbound context label migration and drop in-band sanitizer
Review follow-ups on the plain-label + provenance-marker change:
- Remove src/security/system-tags.ts. Rewriting inbound text to neutralize
look-alike `System:`/`[System]` markers corrupted legitimate user text and is
not a real injection boundary; role separation plus external-content wrapping
is. Explicit product decision, recorded at the system-event queue.
- Narrow the LanceDB legacy-row purge so it cannot delete benign memories. It
now requires a complete known legacy sentinel line, a legacy label followed by
a fenced JSON body, or the complete legacy external-content header. The prior
predicates matched ordinary prose such as `Notes (untrusted metadata):`, and
deletion is irreversible.
- Make explicit-empty canonical ChannelStructuredContext win over the deprecated
alias via a present/absent result instead of collapsing `[]` to undefined.
- Keep `\r?` in the active-memory doctor rule. It is the only rule spanning the
header's line break, migrated assistant rows skip newline normalization, and
without it the marked-header replace wins and the body strips to empty. Added
a CRLF regression test.
- Fix stale comments that described removed behavior, and cover the Swift
prose-block strip path.
Claude-Session: https://claude.ai/code/session_01WNzsPddQmxy9Y7jKD4wAxH
* refactor(infra): move exec approvals into the shared SQLite state DB
Delete the file-runtime exec-approvals store (exec-approvals.json + .lock
sidecar machinery) on both runtimes and make the reserved
exec_approvals_config singleton row canonical. Doctor owns the one-time
import with claim/verify/receipt discipline; runtime fails closed with a
doctor instruction while un-migrated legacy state exists. The wire CAS
contract, socket semantics, and gateway auth-token derivations are
unchanged. Kills the #113929 lock-contention bug class structurally and
nets around -2.9k lines.
* fix(infra): green CI gates and retire file-era exec approvals tests
Break the migration-type import cycle with a leaf contract, regenerate the
plugin-SDK API and native i18n baselines for the intentional surface change,
drop unused exports, and replace the macOS file-era approvals test suite with
SQLite-backed behavior coverage per the obsolete-internals test policy.
* chore: green max-lines ratchet, native i18n baseline, and unused-export scan
* refactor(channels): remove flat streaming compat
maintainer-approved early removal of v2026.7.2-gated compat
* refactor(channels): remove group intro hint adapter
maintainer-approved early removal of v2026.7.2-gated compat
Plugin SDK surface baseline update is maintainer-approved for this intentional removal.
* feat(sdk): always persist media facts and ship facts-first replacements for legacy Media* surfaces
PR 1 of the media legacy retirement program (audit-frozen, 4 PRs).
- Every media-bearing user turn now persists normalized __openclaw.media
facts unconditionally while continuing to emit the legacy top-level
Media* projection byte-identically (dual-write bridge; the conditional
shouldPersistStructuredMediaEntries gate now always includes media).
- New replacement APIs, shipped before any removal: typed hook media
facts (media[], originalMedia[], mediaStagingPending) on message
events; {{AttachmentPath}}/{{AttachmentUrl}}/{{AttachmentContentType}}/
{{AttachmentDir}}/{{AttachmentIndex}} template variables; focused
openclaw/plugin-sdk/media-local-roots subpath split out of the
deprecated agent-media-payload facade.
- Every legacy surface carries @deprecated naming its replacement, under
one named compatibility record media-legacy-projection with the
operator-approved removeAfter 2026-10-01 (two release trains; deletion
additionally gates on a clean published-plugin artifact sweep).
- Generic transcript append invariant documented; SDK migration, hooks,
and configuration docs updated to the facts-first path.
Writer golden matrix proves legacy bytes and model prompt bytes are
unchanged while nested facts become unconditional. 2,189 broad media
tests green; SDK api-baseline regenerated on fresh-env Testbox.
* feat(sdk): register media-local-roots subpath exports and deprecation metadata
Completes PR 1: package export map for openclaw/plugin-sdk/media-local-roots
plus the deprecated-subpath inventory and doc metadata entries for the
media-legacy-projection record.
* chore(sdk): track media-local-roots entrypoint and deprecated-export budgets
* fix(sdk): keep deprecated MSTeams buildMediaPayload re-export through the compat window
Deleting shipped runtime-api re-exports belongs to retirement PR 4 after
the media-legacy-projection window; PR 1 only deprecates. Also formats
the migration-guide schedule table.
* docs: regenerate docs map for media migration additions
Josh Avant