Preserve Telegram streamed text blocks between tool calls by alexzhu0 · Pull Request #88682 · openclaw/openclaw

alexzhu0 · 2026-05-31T15:49:44Z

Summary

Preserve Telegram streamed answer blocks across tool-call / assistant-message boundaries instead of letting later blocks edit the same draft preview.
Keep same-assistant chunks on one Telegram draft, and rotate only when the next answer block belongs to a different assistant message or after tool-progress-only drafts.
Preserve reply-payload assistant-message metadata through internal auto-reply metadata helpers across beforeDeliver, TTS cleanup, reply-payload-sending hooks, message-sending hooks, and block coalescing so Telegram can still match queued blocks after payload rewrites.
Materialize a stale queued answer-block preview through normal non-durable delivery before resetting the draft lane, so a failed/stale preview is not lost during rotation.
Keep the public Plugin SDK API surface unchanged for this Telegram/channel bugfix.

User-facing bug

When Telegram block streaming was enabled, answer text emitted between tool calls could be visible briefly and then disappear. A later assistant block or final answer could edit the same Telegram draft preview, so users lost intermediate findings such as "Site A shows X" after the agent checked another tool.

Exact repro

The focused repro shape is:

Stream a partial answer for assistant message 0.
Queue the final block for assistant message 0.
Cross an assistant-message/tool boundary.
Deliver assistant message 0's block.
Stream assistant message 1.

Before the fix, the message-1 partial could overwrite the message-0 draft. After the fix, the message-0 block is delivered first, then Telegram rotates to a fresh answer draft for message 1.

The stale-preview path from review feedback is:

Deliver assistant message 0's block into the answer draft.
Observe Telegram draft state has stale visible text before the next queued block arrives.
Queue assistant message 1's block.
Verify the stale message-0 block is cleared and delivered normally before forceNewMessage().
Verify message 1 writes to the fresh answer draft.

Fix summary

Telegram dispatch now tracks queued answer blocks by assistant-message index. The queue is filled from onBlockReplyQueued, matched after final beforeDeliver / TTS / message-sending rewrites, and drained when a queued block is cancelled, skipped, or no longer contains answer text. Assistant-message-start no longer rotates immediately when there are queued prior blocks; it delays rotation until those blocks settle so the old message is finalized before the next assistant message writes to a fresh draft.

For stale previews, queued-block rotation now first materializes the previous answer block using the existing clear + normal-send fallback path. That materialization is explicitly non-durable: it does not use durable final delivery and does not mirror the intermediate block as the final answer transcript. Media fallback for this intermediate path also stays non-durable.

To make matching reliable, reply-payload metadata is preserved across the auto-reply delivery hooks and coalescer paths that may replace payload objects. The public Plugin SDK API surface stays unchanged: this branch has no diff for src/plugin-sdk/reply-payload.ts, src/plugin-sdk/reply-runtime.ts, src/auto-reply/get-reply-options.types.ts, or docs/.generated/plugin-sdk-api-baseline.sha256.

Real behavior proof

Behavior addressed: Telegram answer text emitted between tool calls remains visible after the next assistant block starts. If the previous answer draft is stale before rotation, the previous block is delivered normally before the lane reset, then the next assistant message writes to a fresh draft.

Real environment tested: local OpenClaw source checkout on Node v24.4.1, branch fix/telegram-preserve-stream-blocks, commit d48cb9ee13057e8ed5b005bb680031e69f9d7615, rebased on current origin/main commit ec47d1cdd5. The run executed the real dispatchTelegramMessage entrypoint, channel inbound lifecycle, queued block matching, draft lane rotation, and lane delivery code with a local transport capture so the runtime could log send/edit/rotate order.

Exact steps or command run after this patch: from /Users/alex/PR/projects/openclaw__openclaw/worktrees/88682, ran:

node --import tsx -e 'await import("./.artifacts/pr-88682-runtime-log.mjs"); process.exit(0)'

Evidence after fix: copied redacted runtime log from .artifacts/pr-88682-runtime-log.txt:

OpenClaw Telegram dispatch runtime proof
started_at=2026-06-03T17:06:32.220Z
commit=d48cb9ee13057e8ed5b005bb680031e69f9d7615
channel=telegram account=default chat=[redacted-chat] message=[redacted-message]

01 session.recordInboundSession sessionKey="agent:proof:telegram:direct:redacted"
02 runtime.dispatch.start channel="telegram" account="default" chatId="[redacted-chat]" sessionKey="agent:proof:telegram:direct:redacted"
03 runtime.block.queued assistantMessageIndex=0 text="Site A shows X."
04 draft.update lane="answer" messageId=2001 previewRevision=1 text="Site A shows X."
05 draft.flush lane="answer" messageId=2001
06 runtime.observed_stale_draft lane="answer" messageId=2001 lastDeliveredText="stale draft still visible"
07 runtime.block.queued assistantMessageIndex=1 text="Site B shows Y."
08 draft.update lane="answer" messageId=2001 previewRevision=2 text="Site A shows X."
09 draft.stop lane="answer" messageId=2001 lastDeliveredText="stale draft still visible"
10 draft.clear lane="answer" messageId=2001 lastDeliveredText="stale draft still visible"
11 telegram.deliverReplies chatId="[redacted-chat]" text="Site A shows X." transcriptMirror="absent" silent=false
12 draft.stop lane="answer" messageId=2001 lastDeliveredText="stale draft still visible"
13 draft.forceNewMessage lane="answer" previousMessageId=2001
14 draft.update lane="answer" messageId=2002 previewRevision=1 text="Site B shows Y."
15 draft.flush lane="answer" messageId=2002
16 runtime.dispatch.complete queuedFinal=true visibleReplySent=true
17 draft.clear lane="answer" messageId=2002 lastDeliveredText="Site B shows Y."
18 runtime.proof.complete result="stale first block was sent through normal delivery before forceNewMessage, then second block updated fresh draft"

result=PASS
proof_statement=stale queued answer block used normal delivery before lane rotation; next answer block used fresh draft

Observed result after fix: the stale first answer block is sent through telegram.deliverReplies at event 11 before draft.forceNewMessage at event 13. That delivery has transcriptMirror="absent", so the intermediate block is not treated as the durable final transcript. The next assistant block updates message 2002 after rotation, proving it uses a fresh answer draft instead of overwriting message 2001.

What was not tested: native Telegram Desktop recording and live Telegram Bot API credentials were not available in this workspace. The runtime proof above covers the OpenClaw dispatch/send/rotate order but is not a native Telegram client video. The local TSX runner wrote the PASS artifact and stdout but did not exit on its own after the proof completed, so I terminated that runner after capturing the log.

Supplemental validation

Commands run after the fix:

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/reply/block-reply-pipeline.test.ts src/auto-reply/reply/dispatch-from-config.test.ts src/auto-reply/dispatch.test.ts src/plugins/wired-hooks-reply-payload-sending.test.ts

git diff --check origin/main...HEAD

git diff origin/main...HEAD -- src/plugin-sdk/reply-payload.ts docs/.generated/plugin-sdk-api-baseline.sha256 src/auto-reply/get-reply-options.types.ts src/plugin-sdk/reply-runtime.ts

node_modules/.bin/oxlint --tsconfig config/tsconfig/oxlint.core.json src/auto-reply/reply/block-reply-coalescer.ts src/auto-reply/reply/block-reply-pipeline.ts src/auto-reply/reply/block-reply-pipeline.test.ts 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

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

codex review --base origin/main

Results:

Rebased onto current origin/main commit ec47d1cdd5; branch is ahead by 2 commits and not behind. This rebase had to reconcile with main's e4993ec00f (fix(telegram): prevent preview duplication in partial and block streaming modes, [Bug]: Telegram streaming.mode: "partial" and "block" duplicate the full preview when reply >4096 chars #87624), which introduced a skipTextOnlyBlock duplicate-draft suppression on the same answer-block delivery path this PR rotates. The merge keeps both behaviors: a duplicate text-only block is still suppressed at delivery time, but when it is owned by a queued-block rotation (assistant-message split) or is followed by tool progress, the preserved block is materialized before the lane rotates instead of being dropped. Progress-draft state introduced by main was migrated into the createChannelProgressDraftCompositor helper (progressDraft.reset() / .suppress()).
Focused Vitest set: 7 files passed, 412 tests passed (extensions/telegram/src/bot-message-dispatch.test.ts 128, extensions/telegram/src/lane-delivery.test.ts 169 incl. the auto-reply files, plus the auto-reply and wired-hooks suites). Both regression tests that encode this PR's contract pass: does not rotate a partial preview before queued block delivery drains and keeps tool progress visible after a partial-streamed intermediate block. Main's duplicate-dedup regression tests (finalizes a duplicate text-only block when no final follows, materializes a pending duplicate text-only block before finalizing it) still pass.
tsgo extensions typecheck (tsconfig.extensions.json) passed for all Telegram sources (the only remaining diagnostics are a pre-existing, unrelated extensions/discord/.../receive-recovery.ts ↔ libopus-wasm API mismatch in this local environment, untouched by this PR).
git diff --check origin/main...HEAD: passed.
Public SDK/API surface check: no output, so no public Plugin SDK helper or generated API baseline change remains in this branch.
Changed auto-reply/core oxlint command: passed.
Changed Telegram oxlint command: passed.
Not run after the final rebase: broad pnpm check, full repository test suite, native Telegram Bot API/Desktop recording.

AI-assisted disclosure

This change was implemented with AI assistance.

clawsweeper · 2026-05-31T15:51:50Z

Codex review: needs real behavior proof before merge. Reviewed June 8, 2026, 5:30 AM ET / 09:30 UTC.

Summary
Review failed before ClawSweeper could summarize the requested change.

PR surface: Source +377, Tests +1123. Total +1500 across 15 files.

Reproducibility: unclear. The review failed before ClawSweeper could establish a reproduction path.

Review metrics: none identified.

Merge readiness
Overall: 🌊 off-meta tidepool
Proof: 🌊 off-meta tidepool
Patch quality: 🌊 off-meta tidepool
Result: rating does not apply to this item.

Overall follows the weaker of proof and patch quality, so missing proof can cap an otherwise strong patch.

Risk before merge

[P1] No close action taken because the review did not complete.

Maintainer options:

Decide the mitigation before merge
Retry the Codex review after fixing the execution failure.
Pause or close
Do not merge this PR until maintainers decide whether the risk is worth taking.

Next step before merge

[P1] Review did not complete, so no work-lane recommendation was made.

Review details

Best possible solution:

Retry the Codex review after fixing the execution failure.

Do we have a high-confidence way to reproduce the issue?

Unclear. The review failed before ClawSweeper could establish a reproduction path.

Is this the best way to solve the issue?

Unclear. Retry the review first so ClawSweeper can evaluate the actual issue and fix direction.

AGENTS.md: unclear because the file could not be read completely.

Codex review notes: model gpt-5.5, reasoning high; reviewed against fc6400ede389.

Label changes

Label changes:

add rating: 🌊 off-meta tidepool: Overall readiness is 🌊 off-meta tidepool; proof is 🌊 off-meta tidepool and patch quality is 🌊 off-meta tidepool.
remove mantis: telegram-visible-proof: Current Telegram visible-proof status is not_needed.
remove P1: Current review triage priority is none.
remove rating: 🦐 gold shrimp: Current PR rating is rating: 🌊 off-meta tidepool, so this older rating label is no longer current.
remove merge-risk: 🚨 compatibility: Current PR review selected no merge-risk labels.
remove merge-risk: 🚨 message-delivery: Current PR review selected no merge-risk labels.
remove status: 📣 needs proof: Current PR status no longer selects a status label.

Label justifications:

rating: 🌊 off-meta tidepool: Overall readiness is 🌊 off-meta tidepool; proof is 🌊 off-meta tidepool and patch quality is 🌊 off-meta tidepool.

Evidence reviewed

PR surface:

Source +377, Tests +1123. Total +1500 across 15 files.

View PR surface stats

Area	Files	Added	Removed	Net
Source	9	434	57	+377
Tests	6	1126	3	+1123
Docs	0	0	0	0
Config	0	0	0	0
Generated	0	0	0	0
Other	0	0	0	0
Total	15	1560	60	+1500

What I checked:

failure reason: timeout.
codex failure detail: Codex review failed for this PR: spawnSync codex ETIMEDOUT.
codex stdout: Per-item Codex failure; continuing with the rest of the shard.

Likely related people:

unknown: Codex failed before it could trace repository history. (role: review did not complete; confidence: low)

What the crustacean ranks mean

🦀 challenger crab: rare, exceptional readiness with strong proof, clean implementation, and convincing validation.
🦞 diamond lobster: very strong readiness with only minor maintainer review expected.
🐚 platinum hermit: good normal PR, likely mergeable with ordinary maintainer review.
🦐 gold shrimp: useful signal, but proof or patch confidence is still limited.
🦪 silver shellfish: thin signal; proof, validation, or implementation needs work.
🧂 unranked krab: not merge-ready because proof is missing/unusable or there are serious correctness or safety concerns.
🌊 off-meta tidepool: rating does not apply to this item.

Shiny media proof means a screenshot, video, or linked artifact directly shows the changed behavior. Runtime, network, CSP, and security claims still need visible diagnostics.

How this review workflow works

ClawSweeper keeps one durable marker-backed review comment per issue or PR.
Re-runs edit this comment so the latest verdict, findings, and automation markers stay together instead of adding duplicate bot comments.
A fresh review can be triggered by eligible @clawsweeper re-review comments, exact-item GitHub events, scheduled/background review runs, or manual workflow dispatch.
PR/issue authors and users with repository write access can comment @clawsweeper re-review or @clawsweeper re-run on an open PR or issue to request a fresh review only.
Maintainers can also comment @clawsweeper review to request a fresh review only.
Fresh-review commands do not start repair, autofix, rebase, CI repair, or automerge.
Maintainer-only repair and merge flows require explicit commands such as @clawsweeper autofix, @clawsweeper automerge, @clawsweeper fix ci, or @clawsweeper address review.
Maintainers can comment @clawsweeper explain to ask for more context, or @clawsweeper stop to stop active automation.

alexzhu0 · 2026-06-02T08:25:48Z

@clawsweeper re-review

clawsweeper · 2026-06-02T08:25:51Z

🦞🧹
ClawSweeper re-review requested.

I asked ClawSweeper to review this item again.
Action: item re-review queued (workflow sweep.yml, event repository_dispatch).
Result: the existing ClawSweeper review comment will be edited in place when the review finishes.

alexzhu0 · 2026-06-02T08:42:50Z

@clawsweeper re-review

clawsweeper · 2026-06-02T08:42:53Z

🦞👀
ClawSweeper picked this up.

Command router queued. I will update this comment with the next step.

Re-review progress:

State: Complete
Detail: The targeted re-review finished, the durable review comment was updated, and the synced verdict was routed.
Run: https://github.com/openclaw/clawsweeper/actions/runs/26808730233
Updated: 2026-06-02T08:49:53.259Z

clawsweeper · 2026-06-03T17:18:37Z

🦞🧹
ClawSweeper re-review requested.

I asked ClawSweeper to review this item again.
Action: item re-review queued (workflow sweep.yml, event repository_dispatch).
Result: the existing ClawSweeper review comment will be edited in place when the review finishes.

Re-review progress:

State: Complete
Detail: The targeted re-review finished, the durable review comment was updated, and the synced verdict was routed.
Run: https://github.com/openclaw/clawsweeper/actions/runs/26901113235
Updated: 2026-06-03T17:26:16.504Z

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.

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.

obviyus · 2026-06-08T10:01:13Z

Landed via rebase onto main.

Scoped tests: node scripts/run-vitest.mjs extensions/telegram/src/bot-message-dispatch.test.ts -t '<focused Telegram dispatch regression set>'
Scoped tests: node scripts/run-vitest.mjs extensions/telegram/src/lane-delivery.test.ts src/auto-reply/reply/before-deliver.test.ts src/auto-reply/reply/block-reply-pipeline.test.ts src/auto-reply/reply/dispatch-from-config.test.ts -t '<focused lane/auto-reply metadata and delivery set>'
Whitespace: git diff --check origin/main...HEAD
Real Telegram smoke: bot-to-bot mock SUT replied OPENCLAW_E2E_OK
Changelog: not edited; release-note context is already in the PR body per OpenClaw changelog policy.
Land commit: e8435ab
Merge commit: 310d28f

Thanks @alexzhu0!

…26.6.6) (#1040) This PR contains the following updates: | Package | Update | Change | |---|---|---| | [ghcr.io/openclaw/openclaw](https://openclaw.ai) ([source](https://github.com/openclaw/openclaw)) | patch | `2026.6.5` → `2026.6.6` | --- ### Release Notes <details> <summary>openclaw/openclaw (ghcr.io/openclaw/openclaw)</summary> ### [`v2026.6.6`](https://github.com/openclaw/openclaw/blob/HEAD/CHANGELOG.md#202666) [Compare Source](openclaw/openclaw@v2026.6.5...v2026.6.6) ##### Highlights - Security boundaries are substantially tighter across transcripts, sandbox binds, host environment inheritance, MCP stdio, Codex HTTP access, native search policy, elevated sender checks, deleted-agent ACP bypasses, loopback tools, Discord moderation, and Teams group actions; exec approvals now fail closed on timeout. ([#91529](openclaw/openclaw#91529), [#91618](openclaw/openclaw#91618), [#91615](openclaw/openclaw#91615), [#91619](openclaw/openclaw#91619), [#91741](openclaw/openclaw#91741), [#91745](openclaw/openclaw#91745), [#91746](openclaw/openclaw#91746), [#91748](openclaw/openclaw#91748), [#91749](openclaw/openclaw#91749), [#91750](openclaw/openclaw#91750), [#91751](openclaw/openclaw#91751), [#91752](openclaw/openclaw#91752), [#91763](openclaw/openclaw#91763), [#89938](openclaw/openclaw#89938)) Thanks [@joshavant](https://github.com/joshavant), [@pgondhi987](https://github.com/pgondhi987), [@mmaps](https://github.com/mmaps), [@eleqtrizit](https://github.com/eleqtrizit), [@shakkernerd](https://github.com/shakkernerd), and [@drobison00](https://github.com/drobison00). - Telegram delivery is safer and more coherent: account-scoped topics route to the right agent, streamed text survives tool calls, `/compact` works on generic ingress, callback handling uses concrete APIs, draft chunking is shared, durable dispatch dedupe moved into the SDK, and unauthorized DM text stays out of cache and prompt context. ([#91189](openclaw/openclaw#91189), [#88682](openclaw/openclaw#88682), [#89588](openclaw/openclaw#89588), [#90212](openclaw/openclaw#90212), [#91876](openclaw/openclaw#91876), [#91874](openclaw/openclaw#91874), [#91904](openclaw/openclaw#91904), [#91478](openclaw/openclaw#91478), [#91915](openclaw/openclaw#91915)) Thanks [@codysai001](https://github.com/codysai001), [@alexzhu0](https://github.com/alexzhu0), [@joelnishanth](https://github.com/joelnishanth), [@snowzlm](https://github.com/snowzlm), [@obviyus](https://github.com/obviyus), and [@sallyom](https://github.com/sallyom). - iMessage recovery and delivery now cover always-on inbound restart, durable echo markers, block streaming, idle approval discovery, hardened outbound transport, and actionable inbound startup diagnostics. ([#91335](openclaw/openclaw#91335), [#91449](openclaw/openclaw#91449), [#88969](openclaw/openclaw#88969), [#88530](openclaw/openclaw#88530), [#91783](openclaw/openclaw#91783), [#91785](openclaw/openclaw#91785)) Thanks [@omarshahine](https://github.com/omarshahine), [@jmissig](https://github.com/jmissig), and [@colmbrogan](https://github.com/colmbrogan). - Browser and MCP connectivity gained existing-session CDP support, discovered WebSocket validation, default-profile `cdpUrl` handling, safer browser-output boundaries, Streamable HTTP loopback transport, corrected OAuth/SSE authorization handling, and broader schema compatibility. ([#91422](openclaw/openclaw#91422), [#89851](openclaw/openclaw#89851), [#91736](openclaw/openclaw#91736), [#91747](openclaw/openclaw#91747), [#91451](openclaw/openclaw#91451), [#80143](openclaw/openclaw#80143)) Thanks [@pgondhi987](https://github.com/pgondhi987), [@anagnorisis2peripeteia](https://github.com/anagnorisis2peripeteia), [@lifuyue](https://github.com/lifuyue), [@eleqtrizit](https://github.com/eleqtrizit), [@LiuwqGit](https://github.com/LiuwqGit), and [@HemantSudarshan](https://github.com/HemantSudarshan). - Control UI startup and first-reply latency are lower through cached model metadata, removal of the startup catalog wait, lazy slash-command loading, and first-event tracing with slow-reply diagnostics. ([#91531](openclaw/openclaw#91531), [#91538](openclaw/openclaw#91538), [#91568](openclaw/openclaw#91568), [#91583](openclaw/openclaw#91583), [#91598](openclaw/openclaw#91598)) - Provider support expands with OpenRouter OAuth onboarding and Claude Fable 5 adaptive thinking, while Codex sessions keep correct compaction ownership, local models skip guardian review, dynamic tool progress normalizes cleanly, and Gemma 4 reasoning replay is preserved. ([#91830](openclaw/openclaw#91830), [#91882](openclaw/openclaw#91882), [#91590](openclaw/openclaw#91590), [#88630](openclaw/openclaw#88630), [#88768](openclaw/openclaw#88768), [#91696](openclaw/openclaw#91696)) Thanks [@Patrick-Erichsen](https://github.com/Patrick-Erichsen), [@joshavant](https://github.com/joshavant), [@bdjben](https://github.com/bdjben), and [@Coder-Wangyankun](https://github.com/Coder-Wangyankun). ##### Changes - CLI progress: emit Claude CLI commentary progress events and bridge inter-tool commentary into channel progress without exposing internal protocol scaffolding. ([#89834](openclaw/openclaw#89834), [#90883](openclaw/openclaw#90883)) Thanks [@anagnorisis2peripeteia](https://github.com/anagnorisis2peripeteia). - Observability: allow trusted diagnostics channels to capture tool input/output content, add first-assistant-event traces, and warn on slow initial replies. ([#91256](openclaw/openclaw#91256), [#91568](openclaw/openclaw#91568), [#91583](openclaw/openclaw#91583)) Thanks [@amknight](https://github.com/amknight). - Plugins/ClawHub: dogfood reusable package publishing, let dry runs skip publish approval, allow declared installed trusted hooks, report managed plugin version drift, and warn instead of failing on retired Skill Workshop configuration. ([#91574](openclaw/openclaw#91574), [#91591](openclaw/openclaw#91591), [#90004](openclaw/openclaw#90004), [#90927](openclaw/openclaw#90927), [#90838](openclaw/openclaw#90838)) Thanks [@Patrick-Erichsen](https://github.com/Patrick-Erichsen), [@brokemac79](https://github.com/brokemac79), and [@lonexreb](https://github.com/lonexreb). - Memory/providers: move the local llama.cpp runtime into its provider plugin, batch embeddings across files, persist the agent model catalog cache, and keep QMD JSON search one-shot while filtering stale REM recall previews. ([#91324](openclaw/openclaw#91324), [#89138](openclaw/openclaw#89138), [#90457](openclaw/openclaw#90457), [#91837](openclaw/openclaw#91837), [#91851](openclaw/openclaw#91851)) Thanks [@osolmaz](https://github.com/osolmaz), [@mushuiyu886](https://github.com/mushuiyu886), [@ai-hpc](https://github.com/ai-hpc), and [@TurboTheTurtle](https://github.com/TurboTheTurtle). - Channels/mobile: add the QQBot group mention toggle, improve iPad and iPhone control surfaces, and expose the active connection host in the TUI footer. ([#91423](openclaw/openclaw#91423), [#91557](openclaw/openclaw#91557), [#89909](openclaw/openclaw#89909)) Thanks [@cxyhhhhh](https://github.com/cxyhhhhh), [@Solvely-Colin](https://github.com/Solvely-Colin), and [@baskduf](https://github.com/baskduf). - Performance: prewarm TUI runtime plugins, deduplicate plugin auto-enable fanout, trim dense text-delta snapshots, and reuse prepared startup model metadata. ([#90782](openclaw/openclaw#90782), [#89978](openclaw/openclaw#89978), [#91580](openclaw/openclaw#91580), [#91531](openclaw/openclaw#91531)) Thanks [@RomneyDa](https://github.com/RomneyDa) and [@ai-hpc](https://github.com/ai-hpc). ##### Fixes - Agent/session recovery: drop stale approval follow-ups after session rebind, remove drained reply-queue items by identity, recover stale main and visible replies, preserve Codex context-engine compaction ownership, lower the default compaction timeout to 180 seconds while respecting explicit configuration, and keep provider-failure terminal lifecycle state correct. ([#85679](openclaw/openclaw#85679), [#91450](openclaw/openclaw#91450), [#91566](openclaw/openclaw#91566), [#91840](openclaw/openclaw#91840), [#91590](openclaw/openclaw#91590), [#91361](openclaw/openclaw#91361), [#91895](openclaw/openclaw#91895)) Thanks [@openperf](https://github.com/openperf), [@yetval](https://github.com/yetval), [@joshavant](https://github.com/joshavant), [@wangmiao0668000666](https://github.com/wangmiao0668000666), and [@TurboTheTurtle](https://github.com/TurboTheTurtle). - User-visible content boundaries: suppress Codex/Harmony protocol artifacts, neutralize browser and LanceDB memory media directives, redact transcript images, and preserve native `/compact` replies through source suppression. ([#89151](openclaw/openclaw#89151), [#91422](openclaw/openclaw#91422), [#91425](openclaw/openclaw#91425), [#91529](openclaw/openclaw#91529), [#90212](openclaw/openclaw#90212)) Thanks [@joelnishanth](https://github.com/joelnishanth), [@pgondhi987](https://github.com/pgondhi987), [@joshavant](https://github.com/joshavant), and [@snowzlm](https://github.com/snowzlm). - Channel delivery: keep WhatsApp captured replies attached to the successor controller after restart, retry Feishu rate limits, preserve Mattermost thread replies, canonicalize LINE webhook paths, restore Discord reply hydration and runtime timeout exports, and show OpenAI Realtime WebRTC assistant transcripts. ([#85823](openclaw/openclaw#85823), [#89659](openclaw/openclaw#89659), [#91684](openclaw/openclaw#91684), [#91649](openclaw/openclaw#91649), [#90263](openclaw/openclaw#90263), [#91686](openclaw/openclaw#91686), [#90426](openclaw/openclaw#90426)) Thanks [@itsuzef](https://github.com/itsuzef), [@ladygege](https://github.com/ladygege), [@jacobtomlinson](https://github.com/jacobtomlinson), [@fuller-stack-dev](https://github.com/fuller-stack-dev), and [@shushushv](https://github.com/shushushv). - Cron: cancel active task runs cleanly, preserve terminal timeout/cancel state, and recover no-deliver tool warnings instead of silently losing the outcome. ([#90666](openclaw/openclaw#90666), [#90678](openclaw/openclaw#90678)) Thanks [@ai-hpc](https://github.com/ai-hpc). - Gateway/config/auth: share the approval runtime socket token, replace arrays explicitly in `config.patch`, skip the deleted-agent guard only for valid ACP harness sessions, surface headless LaunchAgent state, verify SQLite auth migration before cleanup, and arm QMD startup maintenance. ([#87105](openclaw/openclaw#87105), [#91551](openclaw/openclaw#91551), [#91219](openclaw/openclaw#91219), [#91614](openclaw/openclaw#91614), [#91740](openclaw/openclaw#91740), [#91978](openclaw/openclaw#91978)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev) and [@scotthuang](https://github.com/scotthuang). - Providers/Codex: clarify quota errors, restore the Codex synthetic usage line, canonicalize Codex protocol assets, require API-key auth for realtime voice, normalize ACP model refs, preserve Gemma 4 `reasoning_content`, and avoid guardian review for local models. ([#91390](openclaw/openclaw#91390), [#91709](openclaw/openclaw#91709), [#91507](openclaw/openclaw#91507), [#91567](openclaw/openclaw#91567), [#88630](openclaw/openclaw#88630), [#91696](openclaw/openclaw#91696)) Thanks [@hxy91819](https://github.com/hxy91819), [@brokemac79](https://github.com/brokemac79), [@RomneyDa](https://github.com/RomneyDa), [@joshavant](https://github.com/joshavant), and [@Coder-Wangyankun](https://github.com/Coder-Wangyankun). - Updates/builds: recover package Gateway restarts after refresh failure, expose plugin convergence repair, fall back to Corepack in PATH-less pnpm environments, seed the correct Docker store packages, and keep ClawHub dry-run and publish paths reusable. ([#91581](openclaw/openclaw#91581), [#91599](openclaw/openclaw#91599), [#91547](openclaw/openclaw#91547), [#91591](openclaw/openclaw#91591)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev), [@sallyom](https://github.com/sallyom), and [@Patrick-Erichsen](https://github.com/Patrick-Erichsen). - UI: require explicit user intent before opening chat sessions and drain restored chat queues after session switches. ([#91480](openclaw/openclaw#91480)) Thanks [@TurboTheTurtle](https://github.com/TurboTheTurtle). - Android: avoid the `dataSync` foreground-service type for persistent nodes. ([#80082](openclaw/openclaw#80082)) Thanks [@davelutztx](https://github.com/davelutztx). - Native hooks: bound relay lifetimes so abandoned native hook connections cannot linger indefinitely. ([#91550](openclaw/openclaw#91550)) Thanks [@joshavant](https://github.com/joshavant). </details> --- ### Configuration 📅 **Schedule**: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined). 🚦 **Automerge**: Disabled by config. Please merge this manually once you are satisfied. ♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox. 🔕 **Ignore**: Close this PR and you won't be reminded about these updates again. --- - [ ] If you want to rebase/retry this PR, check this box --- This PR has been generated by [Renovate Bot](https://github.com/renovatebot/renovate).  Reviewed-on: https://git.erwanleboucher.dev/eleboucher/homelab/pulls/1040

openclaw-barnacle Bot added channel: telegram Channel integration: telegram size: S triage: mock-only-proof Candidate: PR proof only shows tests, mocks, snapshots, lint, typecheck, or CI. labels May 31, 2026

clawsweeper Bot added the rating: 🌊 off-meta tidepool PR readiness rating does not apply to this item. label May 31, 2026

alexzhu0 marked this pull request as ready for review June 1, 2026 02:05

clawsweeper Bot had a problem deploying to qa-live-shared June 1, 2026 02:15 Failure

alexzhu0 force-pushed the fix/telegram-preserve-stream-blocks branch from 3b4a2ec to 2fe27b4 Compare June 1, 2026 02:23

openclaw-barnacle Bot added proof: supplied External PR includes structured after-fix real behavior proof. and removed triage: mock-only-proof Candidate: PR proof only shows tests, mocks, snapshots, lint, typecheck, or CI. labels Jun 1, 2026

alexzhu0 force-pushed the fix/telegram-preserve-stream-blocks branch from 2fe27b4 to 83ad501 Compare June 2, 2026 01:02

clawsweeper Bot mentioned this pull request Jun 2, 2026

feat(telegram): opt-in interleaved progress lane #87072

Merged

2 tasks

alexzhu0 force-pushed the fix/telegram-preserve-stream-blocks branch from 83ad501 to 4fee663 Compare June 2, 2026 08:25

openclaw-barnacle Bot removed the docs Improvements or additions to documentation label Jun 2, 2026

openclaw-barnacle Bot removed the proof: supplied External PR includes structured after-fix real behavior proof. label Jun 2, 2026

openclaw-barnacle Bot added the triage: mock-only-proof Candidate: PR proof only shows tests, mocks, snapshots, lint, typecheck, or CI. label Jun 2, 2026

clawsweeper Bot added the merge-risk: 🚨 compatibility 🚨 May break existing users, config, migrations, defaults, or upgrade paths. label Jun 2, 2026

openclaw-barnacle Bot added proof: supplied External PR includes structured after-fix real behavior proof. and removed triage: mock-only-proof Candidate: PR proof only shows tests, mocks, snapshots, lint, typecheck, or CI. labels Jun 2, 2026

clawsweeper Bot added rating: 🦪 silver shellfish Thin PR readiness signal; proof, validation, or implementation needs work. and removed rating: 🧂 unranked krab Not merge-ready due to missing proof or serious correctness/safety concerns. labels Jun 2, 2026

alexzhu0 force-pushed the fix/telegram-preserve-stream-blocks branch 2 times, most recently from 1d79155 to d48cb9e Compare June 3, 2026 17:09

clawsweeper Bot added rating: 🦐 gold shrimp Decent PR readiness signal, but merge confidence is limited. and removed rating: 🦪 silver shellfish Thin PR readiness signal; proof, validation, or implementation needs work. labels Jun 3, 2026

obviyus self-assigned this Jun 8, 2026

obviyus force-pushed the fix/telegram-preserve-stream-blocks branch from d48cb9e to b8b4130 Compare June 8, 2026 09:18

alexzhu0 and others added 4 commits June 8, 2026 15:23

refactor(telegram): distill streamed block rotation cleanup

0f2895e

test(telegram): trim block rotation coverage

e8435ab

obviyus force-pushed the fix/telegram-preserve-stream-blocks branch from 84b3acb to e8435ab Compare June 8, 2026 09:59

obviyus merged commit 310d28f into openclaw:main Jun 8, 2026
157 checks passed

anagnorisis2peripeteia mentioned this pull request Jun 8, 2026

feat(cli): emit commentary progress events from Claude CLI parser #89834

Merged

bhattman-dev mentioned this pull request Jun 12, 2026

[Bug]: Codex native tool statuses surface expected checks as channel-visible OpenClaw failures #88332

Open

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Preserve Telegram streamed text blocks between tool calls#88682

Preserve Telegram streamed text blocks between tool calls#88682
obviyus merged 4 commits into
openclaw:mainfrom
alexzhu0:fix/telegram-preserve-stream-blocks

alexzhu0 commented May 31, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 31, 2026 •

edited

Loading

Uh oh!

alexzhu0 commented Jun 2, 2026

Uh oh!

clawsweeper Bot commented Jun 2, 2026 •

edited

Loading

Uh oh!

alexzhu0 commented Jun 2, 2026

Uh oh!

clawsweeper Bot commented Jun 2, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented Jun 3, 2026 •

edited

Loading

Uh oh!

Uh oh!

obviyus commented Jun 8, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

alexzhu0 commented May 31, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

User-facing bug

Exact repro

Fix summary

Real behavior proof

Supplemental validation

AI-assisted disclosure

Uh oh!

clawsweeper Bot commented May 31, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

alexzhu0 commented Jun 2, 2026

Uh oh!

clawsweeper Bot commented Jun 2, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

alexzhu0 commented Jun 2, 2026

Uh oh!

clawsweeper Bot commented Jun 2, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

clawsweeper Bot commented Jun 3, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Uh oh!

obviyus commented Jun 8, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

alexzhu0 commented May 31, 2026 •

edited

Loading

clawsweeper Bot commented May 31, 2026 •

edited

Loading

clawsweeper Bot commented Jun 2, 2026 •

edited

Loading

clawsweeper Bot commented Jun 2, 2026 •

edited

Loading

clawsweeper Bot commented Jun 3, 2026 •

edited

Loading