…cel (lobehub#15173)

* 🐛 fix(agent-runtime): preserve streamed content across mid-stream cancel

LOBE-9523

Mid-stream STOP currently collapses the in-memory streamed assistant
content back to the LOADING_FLAT placeholder (cLen 5182 → 3 observed in
the agent-gateway probe dump at `.agent-gateway/caseD-prerefresh-…json`),
and a subsequent reload returns the same placeholder from DB so the
content is **permanently lost**.

Root cause (matrix-tested via Electron + probe, see updated LOBE-9523
description): when the user clicks STOP, `interruptOperation` flips
state.status to 'interrupted' and `coordinator.saveAgentState` publishes
`agent_runtime_end` carrying the `uiMessages` snapshot. The executor's
post-stream finalize at `RuntimeExecutors.call_llm:1078` hasn't run yet,
so the assistant row is still the empty placeholder — that placeholder
gets pushed to the client as SoT and clobbers the streamed content.

Three coordinated fixes:

1. **Executor partial-finalize on interrupt** (`RuntimeExecutors.ts`
   inner catch). When `isOperationInterrupted` is true AND the
   `onText`/`onThinking`/`onToolsCalling` callbacks accumulated partial
   content, do an extra `messageModel.update` before rethrowing. This
   makes the DB row carry the real partial content, so a later reload
   shows the streamed answer instead of an empty placeholder.

2. **Coordinator skips uiMessages on interrupted** (`AgentRuntimeCoordinator.ts`
   `resolveUiMessages`). Short-circuit when `state.status === 'interrupted'`
   so the agent_runtime_end payload omits `uiMessages` entirely. The
   executor's partial-finalize update from (1) is racy with this publish
   path — leaving the field undefined lets the client preserve its
   in-memory state instead of pulling whatever's in DB at publish time.

3. **Client skips DB refetch on `reason='interrupted'`** (`gatewayEventHandler.ts`
   agent_runtime_end case). The existing fallback at L540 does a
   `fetchAndReplaceMessages` whenever uiMessages is absent, which would
   defeat fix (2) by reading the still-pre-finalize DB row. Add a
   third branch: when reason='interrupted' AND no uiMessages, keep the
   in-memory state — the next explicit refresh (route change, user-driven
   mutate, page reload) will pick up the finalized partial content from
   (1).

Test matrix (5 new tests):
- `RuntimeExecutors`: persists on interrupt-with-content / skips on
  empty-interrupt / skips on non-interrupt error
- `AgentRuntimeCoordinator`: resolver not called on saveAgentState /
  saveStepResult when status='interrupted'
- `gatewayEventHandler`: no refetch + no replaceMessages when reason=
  'interrupted' and uiMessages absent / SoT still consumed when server
  did include uiMessages on an interrupted run (forward-compat)

Manual verification (probe dumps in `.agent-gateway/`):
- Case A/B/C/E (clean stream, mid-stream tab-switch, post-stream
  tab-switch, post-stream reload) all remain ✅ — no regression
- Case D (long stream → STOP) currently shows
  `cLen[gRojDUMG] 5182→3 near-event:[agent_runtime_end]` rollback;
  with this patch the client retains 5182 chars and the DB carries the
  same partial content for reload

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* 🐛 fix(chat-store): only skip interrupt refetch after stream progressed

Reviewer caught a regression in PR lobehub#15173's agent_runtime_end change:
unconditionally skipping the DB fallback when `reason === 'interrupted'`
leaves the optimistic `tmp_*` placeholder messages stuck in the store
when cancel arrives BEFORE any server state landed (no step_start, no
stream_start with server id, no chunks). Previously the fallback
`fetchAndReplaceMessages` cleaned those up by replacing them with the
server-side rows.

Track `hasStreamedContent` in the handler closure and flip it to true on:
- `stream_start` switching to a server-assigned assistant id
- `stream_chunk` dispatching text / reasoning / tools_calling

Gate the interrupted-skip on this flag:
- `hasStreamedContent === true`  → keep in-memory state (mid-stream cancel)
- `hasStreamedContent === false` → fall back to refetch (cancel-before-stream)

New test for the cancel-before-stream path; existing
"NOT refetch when reason=interrupted" test renamed and updated to set up
prior stream activity before sending the cancel.

---------

Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>

# 🚀 LobeHub Release (20260528)

**Release Date:** May 28, 2026  
**Since v2.2.0:** 220 merged PRs · 15 contributors

> This cycle brings heterogeneous "platform agents" you can dispatch to
local or remote devices, a rebuilt onboarding flow, document-centric
chat, and a unified model-runtime error model — with new DeepSeek V4 and
Gemini 3.5 Flash support along the way.

---

## ✨ Highlights

- **More Hetero Agents (OpenClaw / Hermes)** — Create heterogeneous
agents and dispatch them to local or remote devices through the device
gateway, with an execution-target switcher in the composer and
persistent CLI sessions. (#15065, #15179, #15022)
- **iMessage on Desktop** — New iMessage setup and bridge on desktop,
plus bot attachments across every platform. (#15228, #15227, #15029)
- **Skills in the Composer** — Drag skill chips into chat, trigger
installed skills from the slash menu mid-line, and surface project-level
skills in the homogeneous agent runtime. (#15095, #15061, #15110)
- **New Models** — DeepSeek V4 Flash/Pro and Gemini 3.5 Flash across
providers, with thinking params for structured output and chat cost
estimates. (#15031, #15001, #15051, #14876)
- **Agent Runtime Observability** — OpenTelemetry GenAI semantic
conventions plus per-call generation tracing. (#15123, #15124)

---

## 🤖 Agents & Heterogeneous Runtime

- **Platform agent creation** — OpenClaw/Hermes creation UI, device
guard, and remote dispatch backend. (#15065)
- **Execution-target switcher** — Pick local vs remote execution
directly in the composer; device-selection UX with actionable guidance.
(#15179, #15111)
- **CLI hetero dispatch** — OpenClaw/Hermes dispatch with persistent
sessions and a notify protocol. (#15022)
- **Gateway snapshot as source of truth** — Consume the gateway
`uiMessages` snapshot at step boundaries to keep chat state consistent.
(#15153, #15152)
- **Client sub-agent as a normal tool call** — Simplifies the sub-agent
execution path. (#15281)
- **Hermes agent chain** — Implements the Hermes agent chain logic.
(#15189)
- **Device registry** — TRPC endpoints to register, list, update, and
remove devices. (#15299)
- **Desktop device routing** — Route gateway agent runs through `lh
hetero exec`; restore `userId` in gateway dispatch and gate local-system
by execution target. (#15132, #15232)
- **Agent signals** — Anchor agent-signal receipts to messages and
isolate memory-agent messages into a child thread. (#14969, #14921)

---

## 🚀 Onboarding

- **Simplified first screen** — Defer topic creation to first send.
(#15090)
- **Market Agent Picker** — Added as a classic onboarding step, with
template prefetch. (#14980, #15041)
- **Welcome guidance** — Show agent welcome guidance on first run.
(#15098)
- **Mobile** — Adapt agent onboarding UI and restore Classic-step
padding on mobile. (#15019, #15032)
- **Discovery** — Streamline discovery to a single profession question.
(#14987)
- **Analytics** — Track onboarding step events and create-agent modal
source. (#15133, #15028)

---

## 📄 Documents, Pages & Knowledge

- **Thread chat in preview** — Embed thread chat in the document preview
portal. (#15216)
- **Non-markdown rendering** — Render non-markdown docs as a read-only
highlight. (#15272)
- **Multi-select** — Multi-select delete in the document tree. (#15125)
- **Page-agent streaming** — Preview `initPage` streaming arguments.
(#15039)
- **Per-agent topics** — Per-agent topic management page. (#15207)
- **Server-side category** — Derive document category server-side and
drop frontend predicates. (#15076)

---

## 🧩 Skills & Tools

- **Drag skill chips** — Drag skills into chat input and register
agent-document skills. (#15095)
- **Slash menu** — Installed skills appear in the slash menu with a
mid-line trigger. (#15061)
- **Project skills** — Recognize project-level skills in the homogeneous
agent runtime and surface them regardless of active device. (#15110,
#15177)
- **VFS archiving** — Archive oversized tool results to VFS instead of
truncating. (#15074)
- **@localfile mentions** — Drag folders into chat input as `@localFile`
mentions on desktop. (#15071)

---

## 🧠 Model Runtime & Providers

- **Error spec registry** — Unify error codes into a spec + pattern
registry, split `ProviderBizError` into finer codes, classify Cloud-only
codes via a tier digit, and add `DatabasePersistError`. (#15262, #15286,
#15278, #15279)
- **New models** — DeepSeek V4 Flash/Pro (opencode-go) and Gemini 3.5
Flash; DeepSeek V4 Pro on SiliconCloud. (#15031, #15001, #15017, #15267)
- **Structured output** — Thinking params for structured output, Bedrock
structured generation, and DeepSeek `generateObject` tool choice.
(#15051, #15174, #15054)
- **Cost** — Chat cost estimate support; preserve usage cost in custom
streams. (#14876, #15218)

---

## 💬 Chat & User Experience

- **Follow-up chips** — Extend follow-up chip suggestions to general
chat with scene-specific model config. (#15101, #14797)
- **Input drafts** — Persist unsent input drafts across tab switches and
prevent repeated draft restore. (#14992, #15024)
- **Command menu** — Order topic/message search by recency and promote
inline type filters. (#15094, #14986)
- **Zoom HUD** — Show a zoom-level HUD on Cmd +/− and Cmd 0. (#15294)
- **Copy** — Unescape markdown escapes when copying user messages.
(#15253)

---

## 🖥️ Desktop

- **App Nap fix** — Prevent App Nap from dropping the gateway WebSocket
during display sleep. (#14994)
- **File preview** — Preview `.cjs`/`.mjs`/no-extension files instead of
binary fallback and expand `~` when opening local files. (#15168,
#15284)
- **Cross-platform settings** — Open settings via main-window navigation
on Windows/Linux and restore the route after an update restart. (#15036,
#14922)
- **Token refresh** — Prevent frequent logout from token-refresh
retries. (#14928)

---

## 📊 Observability

- **OTel GenAI** — Instrument Agent Runtime with OpenTelemetry GenAI
semantic conventions. (#15123)
- **Generation tracing** — Per-call `llm_generation_tracing` with a
pre-allocated tracingId and recordFeedback router. (#15124, #15146)
- **Error classification** — Persist `ERROR_CODE_SPECS` classification
on operation errors. (#15273)

---

## 🗃️ Database Migrations

- **Batch migrations** — Topic usage stats, push tokens,
`tasks.editor_data`, and document shares. (#15280)
- **Tracing & eval tables** — Add `llm_generation_tracing` and agent
eval experiment tables. (#15126)

> Self-hosted operators should run the database migration (`pnpm
db:migrate`, or restart with auto-migrate enabled) after upgrading. The
changes are additive and backwards-compatible.

---

## 🔒 Security & Reliability

- **Security:** Remove the `getPlaintextCred` tool to prevent plaintext
credential exposure. (#14998)
- **Security:** Prompt account selection for Google OAuth and add
`prompt=consent` to the OIDC authorization URL to fix missing refresh
tokens. (#15234, #15010)
- **Reliability:** Preserve streamed content across a mid-stream cancel.
(#15173)
- **Reliability:** Bound the Redis command timeout and configure the
Anthropic client timeout. (#15091, #15042)
- **Reliability:** Prevent infinite recursion in the assistant chain.
(#15288)

---

## 👥 Contributors

Huge thanks to **15 contributors** who shipped **220 merged PRs** this
cycle.

@AnotiaWang · @sxjeru · @algojogacor · @hardy-one · @arvinxx · @Innei ·
@tjx666 · @lijian · @AmAzing129 · @rdmclin2 · @neko · @cy948 ·
@CanisMinor · @sudongyuer · @rivertwilight

Plus @lobehubbot and renovate[bot] for maintenance.

---

**Full Changelog**: v2.2.0...release/weekly-20260528