fix(agents): stream assistant deltas incrementally by vincentkoc · Pull Request #87671 · openclaw/openclaw

vincentkoc · 2026-05-28T14:37:56Z

Summary

stream ordinary non-phase assistant text deltas incrementally instead of stripping the accumulated deltaBuffer on every chunk
keep full recompute behavior for split block-tag fragments and reasoning tags where chunk-local stripping is unsafe
carry visible, hidden-reasoning, and enforced-final fenced-code state incrementally without letting stripped/suppressed text poison later visible parsing
final-flush block replies on agent_end before clearing pending fence fragments
add regressions for suffix streaming, split orphan close replacement, media-only replacement, hidden-code safety, split fence markers, strict-final fences, chunk-boundary fence context, agent-end final flush, and suppressed inline-code/fence edge cases

Fixes part of #86599.

Verification

OPENCLAW_VITEST_FS_MODULE_CACHE_PATH=.artifacts/vitest-cache/stream-subscriber-hiddenfence-$USER-$$ node scripts/run-vitest.mjs src/agents/embedded-agent-subscribe.handlers.lifecycle.test.ts src/agents/embedded-agent-subscribe.handlers.messages.test.ts src/agents/embedded-agent-subscribe.subscribe-embedded-agent-session.subscribeembeddedagentsession.test.ts src/agents/embedded-agent-subscribe.subscribe-embedded-agent-session.filters-final-suppresses-output-without-start-tag.test.ts - 8 files / 266 tests passed on bd46e30cb5
./node_modules/.bin/oxfmt --check --threads=1 src/markdown/fences.ts src/markdown/code-spans.ts src/agents/embedded-agent-subscribe.handlers.types.ts src/agents/embedded-agent-subscribe.handlers.messages.ts src/agents/embedded-agent-subscribe.handlers.messages.test.ts src/agents/embedded-agent-subscribe.subscribe-embedded-agent-session.subscribeembeddedagentsession.test.ts src/agents/embedded-agent-subscribe.subscribe-embedded-agent-session.filters-final-suppresses-output-without-start-tag.test.ts src/agents/embedded-agent-subscribe.ts src/agents/embedded-agent-subscribe.handlers.lifecycle.ts src/agents/embedded-agent-subscribe.handlers.lifecycle.test.ts
./node_modules/.bin/oxlint src/markdown/fences.ts src/markdown/code-spans.ts src/agents/embedded-agent-subscribe.handlers.types.ts src/agents/embedded-agent-subscribe.handlers.messages.ts src/agents/embedded-agent-subscribe.handlers.messages.test.ts src/agents/embedded-agent-subscribe.subscribe-embedded-agent-session.subscribeembeddedagentsession.test.ts src/agents/embedded-agent-subscribe.subscribe-embedded-agent-session.filters-final-suppresses-output-without-start-tag.test.ts src/agents/embedded-agent-subscribe.ts src/agents/embedded-agent-subscribe.handlers.lifecycle.ts src/agents/embedded-agent-subscribe.handlers.lifecycle.test.ts
git diff --check
.agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main - clean, no accepted/actionable findings
Earlier AWS Crabbox Linux corepack pnpm check:changed: run run_1a882b49b2af, lease cbx_fdfa7ac4ecbd, slug jade-prawn, passed for the current-main type gate unblocker fix(agents): loosen abort settle env typing #87750. Fresh broad changed-gate proof for this PR is waiting for fix(agents): loosen abort settle env typing #87750 to land or for a stacked proof run with fix(agents): loosen abort settle env typing #87750 overlaid.

Real behavior proof

Behavior addressed: repeated subscriber work over accumulated streamed text during normal non-phase assistant deltas.

Real environment tested: focused local Vitest/static checks in a Codex worktree after rebase, autoreview after regression fixes, plus AWS Crabbox Linux changed gate proof for the current-main gate unblocker.

Exact steps or command run after this patch: commands listed in Verification.

Evidence after fix: focused tests pass with 8 files / 266 tests; autoreview reports no accepted/actionable findings after fixing agent-end fence flush, suppressed inline-code state, and hidden reasoning split-fence cases.

Observed result after fix: ordinary text deltas append from the new chunk, while split tag, orphan close, hidden reasoning, strict-final, and fenced-code cases avoid leaking reasoning, dropping final output, or stripping literal code content.

What was not tested: fresh full check:changed completion on this latest SHA until #87750 lands or is overlaid in a stacked proof run.

clawsweeper · 2026-05-28T14:44:28Z

Codex review: needs maintainer review before merge. Reviewed May 28, 2026, 4:41 PM ET / 20:41 UTC.

Summary
The branch changes embedded-agent streaming to emit ordinary assistant text from chunk-local deltas, adds stateful markdown/reasoning/final-tag parsing across chunks, final-flushes block replies on agent_end, and adds regressions.

PR surface: Source +271, Tests +347. Total +618 across 10 files.

Reproducibility: no. live runtime reproduction was established in this read-only pass. The current-main source path clearly recomputes accumulated deltaBuffer for non-phase streams, and the PR adds focused regressions that exercise the intended incremental behavior.

Review metrics: none identified.

Merge readiness
Overall: 🐚 platinum hermit
Proof: 🐚 platinum hermit
Patch quality: 🐚 platinum hermit
Result: ready for maintainer review.

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

Rank-up moves:

[P2] Confirm required CI or an equivalent Crabbox changed gate on a34d208 before merge.

Risk before merge

[P1] This changes stateful assistant stream parsing, replacement decisions, fence tracking, and final flushing; a missed chunk-boundary case could drop, duplicate, suppress, or leak user-visible assistant text across channels.
[P1] The proof listed in the discussion includes strong focused tests and an AWS Crabbox changed gate on an earlier head, but the latest provided head is a34d208, so maintainers should require exact-head checks or equivalent proof before merge.

Maintainer options:

Wait for exact-head proof (recommended)
Run or wait for required checks or an equivalent Crabbox changed gate on a34d208 before merging this stateful message-delivery change.
Accept focused proof with maintainer judgment
A maintainer may choose to land from the focused regressions and prior Crabbox proof if they are comfortable that the final force-push did not change the risk profile.

Next step before merge

[P2] Protected maintainer-labeled core message-delivery PR; the remaining action is human review and exact-head verification rather than an automated repair.

Security
Cleared: No concrete security or supply-chain concern found; the diff only changes TypeScript source/tests in the embedded-agent streaming and markdown parsing path.

Review details

Best possible solution:

Land the focused streaming parser fix after maintainer review and exact-head CI or Crabbox proof confirm the chunk-boundary and channel-delivery regressions stay covered.

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

No live runtime reproduction was established in this read-only pass. The current-main source path clearly recomputes accumulated deltaBuffer for non-phase streams, and the PR adds focused regressions that exercise the intended incremental behavior.

Is this the best way to solve the issue?

Yes, this appears to be the right implementation boundary: it keeps the change inside embedded-agent subscriber parsing and shared markdown span helpers rather than adding channel-specific workarounds. The merge should still wait for exact-head proof because the parser is stateful and user-visible.

AGENTS.md: found and applied where relevant.

Codex review notes: model gpt-5.5, reasoning high; reviewed against 48291462ef98.

Label changes

Label changes:

add rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🐚 platinum hermit and patch quality is 🐚 platinum hermit.
remove rating: 🦞 diamond lobster: Current PR rating is rating: 🐚 platinum hermit, so this older rating label is no longer current.

Label justifications:

P1: The PR touches core assistant streaming and message delivery for active agent/channel workflows, so regressions would affect real user-visible replies.
merge-risk: 🚨 message-delivery: Merging this parser change could drop, duplicate, suppress, replace, or leak streamed assistant text if a chunk-boundary state case is missed.
rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🐚 platinum hermit and patch quality is 🐚 platinum hermit.
status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Not applicable: The external-contributor proof gate does not apply to this maintainer-labeled member PR; the body still lists focused tests and prior Crabbox proof, while exact-head broad proof remains a merge-readiness check.

Evidence reviewed

PR surface:

Source +271, Tests +347. Total +618 across 10 files.

View PR surface stats

Area	Files	Added	Removed	Net
Source	6	316	45	+271
Tests	4	348	1	+347
Docs	0	0	0	0
Config	0	0	0	0
Generated	0	0	0	0
Other	0	0	0	0
Total	10	664	46	+618

What I checked:

Repository policy read: Root AGENTS.md and the scoped src/agents/AGENTS.md were read in full; their message-delivery, proof, and agent hot-path review guidance affected this review. (AGENTS.md:1, 48291462ef98)
PR surface: The PR diff is limited to embedded-agent subscriber handlers/tests plus markdown fence/code-span helpers: 10 files, +664/-46, with no workflow, dependency, lockfile, config, or secret-handling changes. (a34d2087462a)
Current-main behavior: Current main computes non-phase visible text by stripping the accumulated deltaBuffer on every text chunk, then separately strips the current chunk for visible delta handling. (src/agents/embedded-agent-subscribe.handlers.messages.ts:570, 48291462ef98)
PR streaming implementation: The PR switches ordinary non-phase streaming to chunk-local stripping, while falling back to full recompute for pending tag fragments and reasoning-tag chunks. (src/agents/embedded-agent-subscribe.handlers.messages.ts:614, a34d2087462a)
Stateful parser implementation: The PR carries fence, hidden-reasoning, and final-tag code-span state across chunks so literal tags in fenced code do not get stripped or leaked incorrectly. (src/agents/embedded-agent-subscribe.ts:651, a34d2087462a)
Final flush implementation: handleAgentEnd now flushes the block reply buffer with final: true before clearing pending fence fragments, which matches the added final-flush regression. (src/agents/embedded-agent-subscribe.handlers.lifecycle.ts:176, a34d2087462a)

Likely related people:

Peter Steinberger: Current-main blame attributes the existing embedded subscriber streaming/tag-stripping and markdown fence/code-span helper implementations to commit f99259d. (role: introduced current behavior in checkout history; confidence: medium; commits: f99259d25cb8; files: src/agents/embedded-agent-subscribe.ts, src/agents/embedded-agent-subscribe.handlers.messages.ts, src/markdown/fences.ts)
Vincent Koc: The current PR is authored by Vincent Koc, and recent merged adjacent agent work in this cluster includes small-model live profile and abort-settle type fixes by the same author. (role: recent adjacent agent contributor and current patch author; confidence: medium; commits: a34d2087462a, 686751f639dc, 396a8ef6f807; files: src/agents/embedded-agent-subscribe.ts, src/agents/embedded-agent-subscribe.handlers.messages.ts, src/agents/models.profiles.live.test.ts)

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.

vincentkoc · 2026-05-28T20:04:57Z

Verification refresh after rebase onto 9cb4e48018:

AWS Crabbox corepack pnpm check:changed: run_904990ae8435, lease cbx_9658de947811, provider aws, exit 0.
Branch head: 8b329f63991e4b68b6461f0a64802714361e36d6.

Blacksmith Testbox is still unavailable on this machine because blacksmith auth login is required, so this used direct AWS Crabbox remote proof.

vincentkoc · 2026-05-28T20:46:19Z

Verification update after rebasing on current origin/main:

node scripts/run-vitest.mjs run --config test/vitest/vitest.agents-core.config.ts src/agents/embedded-agent-subscribe.subscribe-embedded-agent-session.keeps-indented-fenced-blocks-intact.test.ts src/agents/embedded-agent-subscribe.subscribe-embedded-agent-session.reopens-fenced-blocks-splitting-inside-them.test.ts --reporter=verbose - passed, 2 files / 4 tests.
.agents/skills/autoreview/scripts/autoreview --mode local - clean, no accepted/actionable findings.
AWS Crabbox corepack pnpm check:changed - passed. provider=aws, lease=cbx_1e918eb9ec7c, run=run_8a1dd157fec5, slug=violet-crayfish, exit=0.

The earlier AWS run run_45f3635c93b9 failed on stale-base src/media/* oxlint drift; this branch was rebased onto current origin/main where that media lint issue is already fixed, and the rerun passed through the same src:media shard cleanly.

…026.5.28) (#759) This PR contains the following updates: | Package | Update | Change | |---|---|---| | [ghcr.io/openclaw/openclaw](https://openclaw.ai) ([source](https://github.com/openclaw/openclaw)) | patch | `2026.5.27` → `2026.5.28` | --- ### Release Notes <details> <summary>openclaw/openclaw (ghcr.io/openclaw/openclaw)</summary> ### [`v2026.5.28`](https://github.com/openclaw/openclaw/blob/HEAD/CHANGELOG.md#2026528) [Compare Source](openclaw/openclaw@v2026.5.27...v2026.5.28) ##### Highlights - Agent and Codex runtime recovery is steadier: subagents keep cwd/workspace separation, hook context stays prompt-local, session locks release on timeout abort while live OpenClaw locks survive cleanup, stale restart continuations are avoided, and Codex app-server/helper failures no longer tear down shared runtime state. ([#87218](openclaw/openclaw#87218), [#86875](openclaw/openclaw#86875), [#87409](openclaw/openclaw#87409), [#87399](openclaw/openclaw#87399), [#87375](openclaw/openclaw#87375), [#88129](openclaw/openclaw#88129)) - Channel delivery and session identity got safer across outbound plugin hooks, Matrix room ids, iMessage reactions/approvals, Slack final replies, Discord recovered tool warnings, runtime-config message actions, WhatsApp profile auth roots, Telegram polling, and Microsoft Teams service URL trust checks. ([#73706](openclaw/openclaw#73706), [#75670](openclaw/openclaw#75670), [#87366](openclaw/openclaw#87366), [#87451](openclaw/openclaw#87451), [#87334](openclaw/openclaw#87334), [#84535](openclaw/openclaw#84535), [#82492](openclaw/openclaw#82492), [#83304](openclaw/openclaw#83304), [#87160](openclaw/openclaw#87160)) - Mobile and chat surfaces got a broader refresh: the iOS Pro UI, hosted push relay default, realtime Talk tab playback, Gateway chat transport, onboarding, Talk permissions, WebChat reconnect delivery, and session picker behavior now preserve more state across reconnects and empty searches. ([#87367](openclaw/openclaw#87367), [#87531](openclaw/openclaw#87531), [#87682](openclaw/openclaw#87682), [#88096](openclaw/openclaw#88096), [#88105](openclaw/openclaw#88105)) Thanks [@ngutman](https://github.com/ngutman) and [@BunsDev](https://github.com/BunsDev). - Browser, channel, and automation inputs are stricter: Browser tool timeouts, viewport/tab indices, Gateway ports, cron retry handling, Discord component ids, schema array refs, Telegram callback pages, and channel progress callbacks now reject malformed values earlier and preserve the intended delivery context. ([#82887](openclaw/openclaw#82887)) - Provider, media, and document coverage expands with Claude Opus 4.8, Fal Krea image schemas, NVIDIA featured models, MiniMax streaming music responses, encrypted PDF extraction, voice model catalogs, GitHub Copilot agent runtime support, and a Codex Supervisor plugin path for delegated Codex workflows. ([#87845](openclaw/openclaw#87845), [#87890](openclaw/openclaw#87890), [#80775](openclaw/openclaw#80775), [#84764](openclaw/openclaw#84764), [#87751](openclaw/openclaw#87751), [#87794](openclaw/openclaw#87794)) - CLI, auth, doctor, and provider paths fail faster and recover more clearly: malformed numeric/version options are rejected, workspace dotenv provider credentials are ignored, heartbeat defaults, OAuth/token lifetimes, and local service startup requests are bounded, agent auth health labels are clearer, legacy `api_key` auth profiles migrate to canonical form, and restart guidance is actionable. ([#87398](openclaw/openclaw#87398), [#86281](openclaw/openclaw#86281), [#87361](openclaw/openclaw#87361), [#88133](openclaw/openclaw#88133), [#83655](openclaw/openclaw#83655), [#87559](openclaw/openclaw#87559), [#88088](openclaw/openclaw#88088), [#85924](openclaw/openclaw#85924)) Thanks [@vincentkoc](https://github.com/vincentkoc) and [@giodl73-repo](https://github.com/giodl73-repo). - Plugin and Gateway hot paths do less repeated work while preserving cache correctness for install records, config JSON parsing, tool search catalogs, session stores, manifest model rows, auto-enabled plugin config, browser tokens, viewer assets, and release-split external plugin packages. ([#86699](openclaw/openclaw#86699)) - Release, QA, and E2E validation now bound more log, artifact, harness, and cross-OS waits so failing lanes produce proof instead of hanging or false-greening. ##### Changes - Status: show active subagent details in status output. - Diffs: split the default language pack and expand default Diffs language coverage while keeping the host floor aligned. ([#87370](openclaw/openclaw#87370), [#87372](openclaw/openclaw#87372)) Thanks [@RomneyDa](https://github.com/RomneyDa). - ClawHub: add plugin display names plus skill verification and trust surfaces. ([#87354](openclaw/openclaw#87354), [#86699](openclaw/openclaw#86699)) Thanks [@thewilloftheshadow](https://github.com/thewilloftheshadow) and [@Patrick-Erichsen](https://github.com/Patrick-Erichsen). - iOS: refresh the dev app with Pro Command, Chat, Agents, Settings, hosted push relay defaults, and realtime Talk playback wired to gateway sessions, diagnostics, chat, and realtime Talk. ([#87367](openclaw/openclaw#87367), [#88096](openclaw/openclaw#88096), [#88105](openclaw/openclaw#88105)) Thanks [@Solvely-Colin](https://github.com/Solvely-Colin) and [@ngutman](https://github.com/ngutman). - Docs: clarify Codex computer-use setup, paste-token stdin auth setup, macOS gateway sleep troubleshooting, native Codex hook relay recovery, container model auth, install deployment cards, device-token admin gating, CLI setup flow compatibility, Notte cloud browser CDP setup, and backport targets. ([#87313](openclaw/openclaw#87313), [#63050](openclaw/openclaw#63050), [#87685](openclaw/openclaw#87685)) Thanks [@bdjben](https://github.com/bdjben), [@liaoandi](https://github.com/liaoandi), and [@thewilloftheshadow](https://github.com/thewilloftheshadow). - PDF/tools: use ClawPDF for PDF extraction, support encrypted PDF extraction, and surface MCP structured content in agent tool results. ([#87670](openclaw/openclaw#87670), [#87751](openclaw/openclaw#87751)) - Providers: add Claude Opus 4.8 support, Fal Krea image model schemas, NVIDIA featured model catalogs, MiniMax streaming music responses, and provider-backed voice model catalogs. ([#87845](openclaw/openclaw#87845), [#87890](openclaw/openclaw#87890), [#80775](openclaw/openclaw#80775), [#84764](openclaw/openclaw#84764), [#87794](openclaw/openclaw#87794)) Thanks [@eleqtrizit](https://github.com/eleqtrizit) and [@vincentkoc](https://github.com/vincentkoc). - Codex/GitHub: add the GitHub Copilot agent runtime and the Codex Supervisor plugin package. - Plugins: externalize GitHub Copilot and Tokenjuice as official install-on-demand plugins with npm and ClawHub publish metadata. - Workboard: add agent coordination tools for tracking and handing off active agent work. - Discord: show commentary in progress drafts so live Discord runs expose useful in-progress context. ([#85200](openclaw/openclaw#85200)) - Plugin SDK: add a reply payload sending hook for plugins that need to deliver channel-owned replies and flatten package types for SDK declarations. ([#82823](openclaw/openclaw#82823), [#87165](openclaw/openclaw#87165)) Thanks [@piersonr](https://github.com/piersonr) and [@RomneyDa](https://github.com/RomneyDa). - Policy: add policy comparison, ingress-channel conformance, and sandbox-posture conformance checks. ([#85572](openclaw/openclaw#85572), [#85744](openclaw/openclaw#85744), [#86768](openclaw/openclaw#86768)) ##### Fixes - Agents: fall back to local config pruning when the optional `agents delete` Gateway probe cannot authenticate, so offline installs can still delete agents without removing shared workspaces. - Tighten phone-control mutation authorization \[AI]. ([#87150](openclaw/openclaw#87150)) Thanks [@pgondhi987](https://github.com/pgondhi987). - Clarify directive persistence authorization policy \[AI]. ([#86369](openclaw/openclaw#86369)) Thanks [@pgondhi987](https://github.com/pgondhi987). - Agents/Codex: keep spawned agent cwd/workspace state separated, forward ACP spawn attachments, keep hook context prompt-local, release session locks on timeout abort and runtime teardown without deleting live OpenClaw-owned locks during cleanup, avoid session event queue self-wait, clean up exec abort listeners, stream assistant deltas incrementally, recover raw missing-thread compaction failures, preserve rotated compaction session identity, keep compaction-timeout snapshots continuable, preserve shared app-server state across startup or helper failures, keep native hook relay alive across restarts and prune stale bridge files, close native hook relay replacement races, keep Claude live tool progress visible for watchdog recovery, suppress abandoned requester completion handoff, route workspace memory through tools, resolve Codex runtime models first, report quarantined dynamic tools, format `skills` command output, bind node auto-review to prepared plans, retry Claude CLI transcript probes, and bound compaction/steering retries. ([#87218](openclaw/openclaw#87218), [#86875](openclaw/openclaw#86875), [#86123](openclaw/openclaw#86123), [#88129](openclaw/openclaw#88129), [#87399](openclaw/openclaw#87399), [#87375](openclaw/openclaw#87375), [#72574](openclaw/openclaw#72574), [#87383](openclaw/openclaw#87383), [#87400](openclaw/openclaw#87400), [#83022](openclaw/openclaw#83022), [#87671](openclaw/openclaw#87671), [#87738](openclaw/openclaw#87738), [#87747](openclaw/openclaw#87747), [#87706](openclaw/openclaw#87706), [#87546](openclaw/openclaw#87546), [#87541](openclaw/openclaw#87541), [#81048](openclaw/openclaw#81048)) Thanks [@mbelinky](https://github.com/mbelinky), [@Alix-007](https://github.com/Alix-007), [@luoyanglang](https://github.com/luoyanglang), [@yetval](https://github.com/yetval), [@sjf](https://github.com/sjf), [@joshavant](https://github.com/joshavant), [@benjamin1492](https://github.com/benjamin1492), [@c19354837](https://github.com/c19354837), [@fuller-stack-dev](https://github.com/fuller-stack-dev), [@pfrederiksen](https://github.com/pfrederiksen), and [@dodge1218](https://github.com/dodge1218). - Codex Supervisor: keep real-home app-server MCP session listing on the loaded state path, bound stored history scans, and close WebSocket probes cleanly. - Channels: thread canonical session keys into outbound hooks, preserve Matrix room-id case, keep fallback tool warnings mention-inert, retain delivered Slack final replies during late cleanup, continue iMessage polling after denied reactions, suppress duplicate native exec approvals, resolve Gateway message actions against the active runtime config, preserve Telegram SecretRef prompt config and polling keepalives, preserve WhatsApp profile auth roots, QR display, document filenames, and plugin hook config, suppress Discord recovered tool warnings, preserve the Discord voice outbound helper, cap Discord/Signal/Zalo channel request and container timeouts, and block untrusted Teams service URLs while keeping TeamsSDK patterns aligned. ([#73706](openclaw/openclaw#73706), [#75670](openclaw/openclaw#75670), [#87366](openclaw/openclaw#87366), [#87451](openclaw/openclaw#87451), [#87465](openclaw/openclaw#87465), [#87334](openclaw/openclaw#87334), [#84535](openclaw/openclaw#84535), [#76262](openclaw/openclaw#76262), [#83304](openclaw/openclaw#83304), [#82492](openclaw/openclaw#82492), [#87581](openclaw/openclaw#87581), [#77114](openclaw/openclaw#77114), [#86426](openclaw/openclaw#86426), [#85529](openclaw/openclaw#85529), [#87160](openclaw/openclaw#87160)) Thanks [@zeroaltitude](https://github.com/zeroaltitude), [@lukeboyett](https://github.com/lukeboyett), [@jarvis-mns1](https://github.com/jarvis-mns1), [@xiaotian](https://github.com/xiaotian), [@funmerlin](https://github.com/funmerlin), [@joshavant](https://github.com/joshavant), [@eleqtrizit](https://github.com/eleqtrizit), [@heyitsaamir](https://github.com/heyitsaamir), [@amittell](https://github.com/amittell), [@lidge-jun](https://github.com/lidge-jun), [@liorb-mountapps](https://github.com/liorb-mountapps), [@masatohoshino](https://github.com/masatohoshino), [@bladin](https://github.com/bladin), and [@giodl73-repo](https://github.com/giodl73-repo). - CLI/auth/doctor/providers: reject malformed numeric/timeout/subcommand-version inputs, ignore workspace dotenv provider credentials, wait for respawn child shutdown, bound heartbeat defaults plus Codex, GitHub Copilot, OpenAI, Anthropic, Google, Feishu, LM Studio, MiniMax, Xiaomi TTS, and local-provider OAuth/token/model requests, harden Codex auth probes, label auth health by agent, preserve explicit agentRuntime pins during Codex model migration, warm provider auth off the main thread, honor Codex response timeouts, stop migrating current Claude Haiku 4.5 profiles to Sonnet, bound local service startup, resolve GPT-5.5 without cached catalog, migrate legacy memory auto-provider config, rewrite non-canonical `api_key` auth profiles, and make doctor restart follow-ups actionable. ([#87398](openclaw/openclaw#87398), [#86281](openclaw/openclaw#86281), [#87361](openclaw/openclaw#87361), [#88133](openclaw/openclaw#88133), [#83655](openclaw/openclaw#83655), [#87559](openclaw/openclaw#87559), [#87719](openclaw/openclaw#87719), [#88088](openclaw/openclaw#88088), [#85924](openclaw/openclaw#85924), [#84362](openclaw/openclaw#84362)) Thanks [@Patrick-Erichsen](https://github.com/Patrick-Erichsen), [@samzong](https://github.com/samzong), [@giodl73-repo](https://github.com/giodl73-repo), [@alkor2000](https://github.com/alkor2000), [@mmaps](https://github.com/mmaps), [@nxmxbbd](https://github.com/nxmxbbd), and [@vincentkoc](https://github.com/vincentkoc). - Gateway/security/session state: expire browser tokens after auth rotation, scope assistant idempotency dedupe, drain probe client closes, avoid stale restart continuation reuse, preserve retry-after fallbacks and stale rate-limit cooldown probes, bound webchat image and artifact transcript scans, include seconds in inbound metadata timestamps, clear completed session active runs, clear stale chat stream buffers, and evict current plugin-state namespaces at row caps. ([#87810](openclaw/openclaw#87810), [#87833](openclaw/openclaw#87833), [#75089](openclaw/openclaw#75089)) Thanks [@joshavant](https://github.com/joshavant) and [@litang9](https://github.com/litang9). - Config/parsing/network: reject partial numeric parsing, parse provider/Discord retry headers and dates strictly, honor IPv6 and bare IPv6 `no_proxy` entries, preserve empty plugin allowlists, canonicalize secret target array indexes, and reject malformed media content lengths, inspected TCP ports, marketplace content lengths, cron epochs, sandbox stat fields, unsafe duration values, empty config path segments, noncanonical schema array refs, unsafe Telegram callback pages, and invalid Teams attachment-fetch DNS targets. ([#87883](openclaw/openclaw#87883)) Thanks [@zhangguiping-xydt](https://github.com/zhangguiping-xydt). - Browser/input hardening: reject invalid tab indexes, excessive viewport resizes, explicit zero CDP ports, malformed geolocation options, unsafe screenshot or permission-grant timeouts, loose response-body limits, invalid cookie expiries, and non-finite Browser tool delays/timeouts. - Cron/automation: retry recurring jobs after transient model rate limits before waiting for the next scheduled slot, and preflight model fallbacks before skipping scheduled work. ([#82887](openclaw/openclaw#82887)) Thanks [@chen-zhang-cs-code](https://github.com/chen-zhang-cs-code). - Auto-reply/directives: respect provider and relayed channel metadata during directive persistence so channel-originated decisions keep their intended context. ([#87683](openclaw/openclaw#87683)) - WhatsApp: resolve the auth directory from the active profile so profile-scoped WhatsApp installs do not drift to the wrong credential root. ([#82492](openclaw/openclaw#82492)) Thanks [@lidge-jun](https://github.com/lidge-jun). - Gateway/session state: clear completed session active runs, avoid cold-loading providers for MCP inventory, cache single-session child indexes, cap handshake timers, and bound preauth, auth-guard, media, transcript, readiness, and port options. - Channels/replies: preserve channel-owned progress callbacks when verbose output is off, keep group-room progress suppression intact, prefer external session delivery context, escape Discord component id delimiters, force final TUI chat repaints, show Slack reasoning previews, and normalize Discord/Matrix/Mattermost channel numeric options. ([#87476](openclaw/openclaw#87476), [#87423](openclaw/openclaw#87423)) - Agents/tool args: harden smart-quoted argument repair for edit arrays and exact escaped arguments so model-produced tool calls recover without corrupting valid input. ([#86611](openclaw/openclaw#86611)) Thanks [@ferminquant](https://github.com/ferminquant). - Providers/agents: preserve seeded Anthropic signatures, preserve signed thinking payloads, concatenate signature-delta chunks, preserve DeepSeek `reasoning_content` replay across tier suffixes, apply OpenRouter strict9 ids to Mistral routes, promote Ollama plain-text tool calls, load NVIDIA featured model catalogs, stream MiniMax music generation responses, and recover empty preflight compaction. ([#87593](openclaw/openclaw#87593), [#87493](openclaw/openclaw#87493), [#80775](openclaw/openclaw#80775), [#84764](openclaw/openclaw#84764)) Thanks [@Pluviobyte](https://github.com/Pluviobyte) and [@eleqtrizit](https://github.com/eleqtrizit). - Media/images: skip CLI image cache refs when resolving generated images, allow trusted generated HTML attachments, and bound generated video downloads so stale refs and slow providers fail cleanly. ([#87523](openclaw/openclaw#87523), [#87982](openclaw/openclaw#87982)) - File transfer: handle late tar stdin pipe errors after archive validation or unpacking has already settled. - Performance: trust install-record caches between reloads, prefer native JSON parsing, reuse unchanged tool-search catalogs, reuse gateway session and plugin metadata paths, skip unchanged store serialization, patch single-entry session writes, add precomputed session patch writers, reduce store clone allocations, cache manifest model catalog rows and auto-enabled plugin config, avoid full session snapshots for entry reads, defer configured Slack full startup, prefer bundled plugin dist entries, and slim current metadata identity caches. ([#87760](openclaw/openclaw#87760)) - Docker/release/QA: package runtime workspace templates, stream cross-OS served artifacts, preserve sparse Crabbox run artifacts, isolate npm plugin installs per package, reject incompatible package plugin API installs, drop the leftover root Sharp dependency from package manifests after the Rastermill migration, bound OpenClaw instance logs, plugin gauntlet relay logs, MCP channel buffers, kitchen-sink scans, agent-turn assertions, QA-Lab credential broker calls, QA Matrix substrate requests, and release scenario logs, and keep release/google live guards current. ([#87647](openclaw/openclaw#87647), [#87477](openclaw/openclaw#87477)) Thanks [@rohitjavvadi](https://github.com/rohitjavvadi) and [@vincentkoc](https://github.com/vincentkoc). - Release/CI: bound manual git fetches, ClawHub verifier responses, ClawHub owner metadata, dependency-guard error bodies, Parallels limits, startup/test/memory budget parsing, and diffs viewer build warnings so release lanes fail with useful proof instead of hanging. ([#87839](openclaw/openclaw#87839)) </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/759

vincentkoc self-assigned this May 28, 2026

openclaw-barnacle Bot added agents Agent runtime and tooling size: M maintainer Maintainer-authored PR labels May 28, 2026

vincentkoc force-pushed the codex/stream-subscriber-delta branch 2 times, most recently from 9ad3179 to 5281ce6 Compare May 28, 2026 17:23

openclaw-barnacle Bot added size: L and removed size: M labels May 28, 2026

This was referenced May 28, 2026

fix(agents): broaden local model lean profile #87617

Open

test(agents): add small model live profile #87638

Merged

vincentkoc force-pushed the codex/stream-subscriber-delta branch 4 times, most recently from 68f0334 to 8b329f6 Compare May 28, 2026 19:53

vincentkoc marked this pull request as ready for review May 28, 2026 20:04

clawsweeper Bot added rating: 🦞 diamond lobster Very strong PR readiness with only minor maintainer review expected. and removed rating: 🐚 platinum hermit Good normal PR readiness with ordinary maintainer review expected. labels May 28, 2026

vincentkoc force-pushed the codex/stream-subscriber-delta branch from 8b329f6 to d31b9da Compare May 28, 2026 20:23

fix(agents): stream assistant deltas incrementally

a34d208

vincentkoc force-pushed the codex/stream-subscriber-delta branch from d31b9da to a34d208 Compare May 28, 2026 20:34

clawsweeper Bot added rating: 🐚 platinum hermit Good normal PR readiness with ordinary maintainer review expected. and removed rating: 🦞 diamond lobster Very strong PR readiness with only minor maintainer review expected. labels May 28, 2026

vincentkoc merged commit db66004 into main May 28, 2026
108 of 110 checks passed

vincentkoc deleted the codex/stream-subscriber-delta branch May 28, 2026 20:48

github-actions Bot mentioned this pull request May 28, 2026

📡 Upstream Digest — 2026-05-28 21:51 UTC curtismercier/openclaw-mods#966

Open

github-actions Bot pushed a commit to Desicool/openclaw that referenced this pull request May 29, 2026

fix(agents): stream assistant deltas incrementally (openclaw#87671)

b5adc8d

steipete pushed a commit that referenced this pull request May 29, 2026

fix(agents): stream assistant deltas incrementally (#87671)

c65afa9

vincentkoc mentioned this pull request May 29, 2026

fix(agents): count stream deltas incrementally #88153

Merged

osolmaz mentioned this pull request Jun 1, 2026

fix(gateway): keep dense stream updates incremental #87558

Closed

SYU8384 pushed a commit to SYU8384/openclaw that referenced this pull request Jun 3, 2026

fix(agents): stream assistant deltas incrementally (openclaw#87671)

179cfd1

gorkem2020 mentioned this pull request Jun 9, 2026

[Regression] WebChat does not render reasoning live for any model after #87671 (only appears after manual refresh) #91727

Open

sablehead pushed a commit to sablehead/openclaw that referenced this pull request Jun 10, 2026

fix(agents): stream assistant deltas incrementally (openclaw#87671)

efc2f55

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix(agents): stream assistant deltas incrementally#87671

fix(agents): stream assistant deltas incrementally#87671
vincentkoc merged 1 commit into
mainfrom
codex/stream-subscriber-delta

vincentkoc commented May 28, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 28, 2026 •

edited

Loading

Uh oh!

vincentkoc commented May 28, 2026

Uh oh!

vincentkoc commented May 28, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Uh oh!

Conversation

vincentkoc commented May 28, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Verification

Real behavior proof

Uh oh!

clawsweeper Bot commented May 28, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

vincentkoc commented May 28, 2026

Uh oh!

vincentkoc commented May 28, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

vincentkoc commented May 28, 2026 •

edited

Loading

clawsweeper Bot commented May 28, 2026 •

edited

Loading