- Remove unused import normalizeOptionalLowercaseString from commands-compact.ts
- Remove unused type import ReplyPayload from bot-native-commands.ts
- Replace spread-in-map with Object.assign to satisfy oxlint
- Delete orphaned native-command-ack-fallback.ts and its test (superseded by direct delivery)
- Add isStatusNotice to ReplyPayloadLike test type
- Update test to verify status notices bypass dispatch pipeline
The dispatch pipeline (foreground fence, operation-busy checks, hooks)
silently dropped status-notice replies for /compact. Resolve the command
reply directly via getReplyFromConfig and deliver status notices through
deliverReplies without entering the full dispatch pipeline. Non-status
commands still use the buffered dispatch for streaming/tools.
Adds deliverDespiteSourceReplySuppression metadata for command replies,
a dedicated native-command-ack-fallback module, and regression tests.
Fixes#89525
Co-authored-by: Cursor <cursoragent@cursor.com>
Adds /context detail diagnostics for active transcript compactability so prompt/cache usage is not mistaken for compactable conversation history.
Fixes#91150. Supersedes #91158.
Co-authored-by: Rain <94058511+Pluviobyte@users.noreply.github.com>
drainNextQueueItem captured items[0], awaited the run, then shift()-ed
index 0 assuming it still held the item it ran. Concurrent inbound
messages mutate the same shared items array, and at or over cap
applyQueueDropPolicy splices items off the front, so a burst arriving
while item[0] is in flight can shift a different, still-undelivered
survivor into index 0. shift() then deletes that survivor: it is never
run and is not counted in the overflow summary, so the agent silently
ignores a message it should have answered.
Remove the item that actually ran by identity via a new
removeQueuedItemsByRef helper, and apply the same reference-based
removal to the collect path in drain.ts, which had the same positional
splice(0, groupItems.length) assumption after an awaited group run.
Inter-tool commentary (assistant text emitted before a tool call, surfaced by
the CLI parser as a stream:"item", kind:"preamble" agent event) landed on the
agent-event bus with no subscriber and was silently dropped: runCliAgentWithLifecycle
bridges the assistant, reasoning, and tool streams to channel callbacks, but the
item/preamble stream had no bridge. Add createCommentaryEventBridge to forward it
to onItemEvent, so CLI commentary reaches the channel's commentary render hook.
This is the CLI-dispatch delivery half of the commentary feature: the parser
emission (claude-cli) feeds the bus; this bridge delivers it to the channel.
Addresses the claude-cli case of intermediate-text-lost (#87326 / #84486).
Summary:
- The branch adds provider error classification for generic HTTP 429 runtime failures and Volcengine `InvalidSubscription` billing errors, plus focused regression tests and SIGTERM test stabilization.
- PR surface: Source +62, Tests +137. Total +199 across 8 files.
- Reproducibility: yes. at source level. Current main lacks the HTTP 429 metadata classifier and Volcengine subscription billing matcher, and the PR body reports a live Volcengine failure shape plus after-fix tests.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix: clarify provider quota errors
Validation:
- ClawSweeper review passed for head 5e10848a37.
- Required merge gates passed before the squash merge.
Prepared head SHA: 5e10848a37
Review: https://github.com/openclaw/openclaw/pull/91390#issuecomment-4647819660
Co-authored-by: Mason Huang <masonxhuang@tencent.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: hxy91819
Co-authored-by: hxy91819 <8814856+hxy91819@users.noreply.github.com>
Queued answer block rotations can split assistant messages while the previous Telegram preview is stale. Materialize the previous block through the existing delivery fallback before resetting the draft lane, and keep assistant-message correlation on the internal dispatcher path instead of expanding the public Plugin SDK payload API.
Constraint: ClawSweeper flagged missing live Telegram proof and a public Plugin SDK helper surface; the code path must stay a Telegram/channel bugfix without adding a third-party SDK contract.
Rejected: Export getReplyPayloadAssistantMessageIndex from openclaw/plugin-sdk/reply-payload | it exposes internal reply metadata solely for this Telegram fix.
Rejected: Match queued block rotations only by text | plugin rewrites, repeated text, and media-only transformed block deliveries need assistant-message correlation.
Confidence: high
Scope-risk: narrow
Directive: Keep intermediate block materialization non-durable unless it is the actual final answer path, and keep assistant-message correlation off public reply-payload SDK exports.
Tested: OPENCLAW_HEAVY_CHECK_LOCK_SCOPE=worktree node scripts/run-vitest.mjs extensions/telegram/src/bot-message-dispatch.test.ts extensions/telegram/src/lane-delivery.test.ts src/auto-reply/reply/before-deliver.test.ts src/auto-reply/dispatch.test.ts src/auto-reply/reply/dispatch-from-config.test.ts src/plugins/wired-hooks-reply-payload-sending.test.ts
Tested: node_modules/.bin/oxlint --tsconfig config/tsconfig/oxlint.extensions.json extensions/telegram/src/bot-message-dispatch.ts extensions/telegram/src/bot-message-dispatch.test.ts extensions/telegram/src/lane-delivery-text-deliverer.ts extensions/telegram/src/lane-delivery.test.ts
Tested: node_modules/.bin/oxlint --tsconfig config/tsconfig/oxlint.core.json src/auto-reply/reply/reply-dispatcher.ts src/auto-reply/reply/before-deliver.test.ts src/auto-reply/dispatch.ts src/auto-reply/dispatch.test.ts src/auto-reply/reply/dispatch-from-config.ts src/auto-reply/reply/dispatch-from-config.test.ts src/auto-reply/reply/reply-payload-sending-hook.ts
Tested: git diff --check origin/main
Not-tested: Redacted live Telegram Bot API/Desktop proof; no Telegram credentials or chat target are configured in this local environment.
Not-tested: tsgo extensions test command was attempted locally and terminated after running over six minutes without output; prior known local run failed on unrelated Discord voice libopus-wasm errors.
Constraint: Telegram draft previews are mutable until stopped, while OpenClaw block streaming can emit multiple chunks for one assistant message and separate assistant messages around tool calls.
Rejected: Finalizing every answer block | same-message chunks would become duplicate standalone Telegram messages before the final payload.
Rejected: Exposing full reply payload metadata through the public plugin SDK | Telegram only needs assistant block identity, and broader metadata would make internal dispatch fields a third-party API contract.
Rejected: Leaving queued block rotations as FIFO text-only state | delivery hooks can rewrite, cancel, skip, or remove answer text after queueing.
Confidence: high
Scope-risk: moderate
Directive: Keep same-message block chunks in one draft; rotate only at assistant-message/tool-progress boundaries, and expire cancelled, skipped, or non-answer queued blocks without deleting still-pending earlier rotations.
Tested: git diff --check origin/main; /Users/alex/PR/projects/openclaw__openclaw/repo/node_modules/oxfmt/bin/oxfmt --check --threads=1 docs/.generated/plugin-sdk-api-baseline.sha256 extensions/telegram/src/bot-message-dispatch.test.ts extensions/telegram/src/bot-message-dispatch.ts extensions/telegram/src/draft-stream.test-helpers.ts extensions/telegram/src/lane-delivery-text-deliverer.ts extensions/telegram/src/lane-delivery.test.ts src/auto-reply/dispatch.test.ts src/auto-reply/dispatch.ts src/auto-reply/reply/before-deliver.test.ts src/auto-reply/reply/dispatch-from-config.test.ts src/auto-reply/reply/dispatch-from-config.ts src/auto-reply/reply/reply-dispatcher.ts src/auto-reply/reply/reply-payload-sending-hook.ts src/plugin-sdk/reply-payload.ts; ./node_modules/.bin/oxlint extensions/telegram/src/bot-message-dispatch.test.ts extensions/telegram/src/bot-message-dispatch.ts extensions/telegram/src/lane-delivery-text-deliverer.ts extensions/telegram/src/lane-delivery.test.ts extensions/telegram/src/draft-stream.test-helpers.ts src/plugin-sdk/reply-payload.ts src/auto-reply/dispatch.ts src/auto-reply/dispatch.test.ts src/auto-reply/reply/before-deliver.test.ts src/auto-reply/reply/dispatch-from-config.ts src/auto-reply/reply/dispatch-from-config.test.ts src/auto-reply/reply/reply-dispatcher.ts src/auto-reply/reply/reply-payload-sending-hook.ts; node --max-old-space-size=8192 --import tsx scripts/generate-plugin-sdk-api-baseline.ts --check; CI=1 NODE_OPTIONS=--max-old-space-size=4096 node scripts/run-tsgo.mjs -p test/tsconfig/tsconfig.extensions.test.json --incremental --tsBuildInfoFile .artifacts/tsgo-cache/extensions-test.tsbuildinfo; CI=1 NODE_OPTIONS=--max-old-space-size=4096 node scripts/run-tsgo.mjs -p test/tsconfig/tsconfig.core.test.non-agents.json --incremental --tsBuildInfoFile .artifacts/tsgo-cache/core-test-non-agents.tsbuildinfo; OPENCLAW_HEAVY_CHECK_LOCK_SCOPE=worktree node scripts/run-vitest.mjs extensions/telegram/src/bot-message-dispatch.test.ts; OPENCLAW_HEAVY_CHECK_LOCK_SCOPE=worktree node scripts/run-vitest.mjs extensions/telegram/src/bot-message-dispatch.test.ts extensions/telegram/src/lane-delivery.test.ts extensions/telegram/src/draft-stream.test.ts src/plugin-sdk/reply-payload.test.ts src/plugins/contracts/plugin-sdk-index.test.ts; OPENCLAW_HEAVY_CHECK_LOCK_SCOPE=worktree node scripts/run-vitest.mjs src/auto-reply/reply/before-deliver.test.ts src/auto-reply/dispatch.test.ts; OPENCLAW_HEAVY_CHECK_LOCK_SCOPE=worktree node scripts/run-vitest.mjs src/auto-reply/reply/dispatch-from-config.test.ts -t "forwards payload metadata into onBlockReplyQueued context"
Not-tested: Live Telegram bot roundtrip with real credentials. codex review --base origin/main was run twice but did not complete a final verdict after hitting local heavy-check lock, unsupported --runInBand, and .vite-temp EPERM in the review tool sandbox; no actionable P1/P2 finding was emitted before termination.
* fix(infra/agents): session-routing guard for coalesced gateway restart continuations (#86742)
When two sessions issue gateway.restart with continuationMessage close
together, the scheduler Path B updatePendingRestartEmitHooks
unconditionally overwrote the existing pending hooks, silently dropping
the first sessions continuation and potentially routing the second
sessions continuation back to the first session (CWE-200 finding
flagged by aisle-research-bot on prior attempt #74443).
Add a session-routing guard: scheduleGatewaySigusr1Restart now accepts
an optional sessionKey and tracks the pending restarts owning session.
Coalesced callers from a different session are rejected at the hook-
update step and the new ScheduledRestart.emitHooksQueued: false field
surfaces the drop to the caller. The gateway tool propagates this as
continuationQueued: false in the tool response, matching #83370 narrow
report-only surface.
Same-session debounce/replace and legacy hookless callers behave the
same as before.
Refs #86742
* fix(infra): preserve queued restart continuation on forced bypass
* fix(infra): make forced restart hook preservation explicit
* fix(infra): guard restart continuation ownership before reschedule
* fix(infra): report hookless coalesced restarts accurately
* fix(infra): trust runtime session for restart sentinel routing
* fix(infra): preserve earlier restart reschedule semantics
* fix(agents): trust runtime session for update continuations
* fix(infra): preserve hookless forced restart continuations
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
