Add a parallel effectiveAllowedToolsDisplay field on the runtime status payload so the SkillMarket detail drawer can render mcp_<server>_<slug>_<hash> with the raw tool name appended in parentheses, while leaving the original prefixed list unchanged for any caller that needs the machine name. McpSkillBridge#decorateToolNameForDisplay reverses a prefixed name via the per-server cached tool list; the frontend prefers the new display field and falls back to effectiveAllowedTools when the field is absent.
Replace hardcoded zh-CN locale with vue-i18n locale.value, add a yesterday bucket reusing the security.activity.yesterday key, and fall back to YYYY/MM/DD HH:mm for older messages. Computes the previous day with setDate(getDate()-1) so DST transitions stay correct, and short-circuits invalid Date inputs.
WeCom quoted-message context:
- Parse the body.quote field that arrives alongside any inbound message
(text / image / voice / file / mixed sub-types). When a user long-
presses a previous bot bubble and types a follow-up like "解释一下",
the agent now sees both the user's new text and the referenced
content as proper context — replies stay on topic instead of
guessing what was being explained.
- Quoted images / files are downloaded through the same pipeline as
inbound new media (magic-byte sniff, ZIP container peek for
DOCX / XLSX / PPTX recovery, chat-uploads layout) so the vision
sidecar and document tools can actually analyse what was quoted.
- Reading order in the assembled prompt: "[引用消息: ...]\n<user text>"
first, then quoted media parts, then the user's own current-message
media. Mixed quotes flatten into a space-joined summary.
Multimodal sidecar settings preservation:
- The bulk settings PUT used to unconditionally overwrite the vision /
video sidecar model ids — null in a partial payload became "" in
the DB, silently wiping the configured sidecar every time a user
saved an unrelated settings page (System / Music / Image / etc.).
Symptom: "I picked a vision model, saved a different settings tab,
now the bot can't see images anymore."
- Bulk save now guards both keys with non-null checks, matching the
pattern used for music / 3D / image / video / tts / stt blocks.
- A dedicated /settings/sidecar endpoint always writes both keys, so
the sidecar UI can still explicitly clear via null without leaking
the write-on-null semantics into every other settings save.
- Frontend sidecar card switches to the dedicated endpoint; other
settings pages keep their existing partial-payload behaviour.
When an agent had any skill bound, the runtime tool gate was silently
hiding @Tool beans that aren't declared in any skill manifest, even
though the global system prompts (SOUL.md / "Web Search Capability" /
"File Reading Guidelines") explicitly tell the LLM these tools are
available. Result: the model would call search / renderDocx / read_file
/ etc., hit "Tool not found", then either give up or fall back to
unhelpful behaviour (e.g. dumping markdown text instead of producing a
.docx download).
This commit:
- Adds universally-promised, agent-wide tools to SYSTEM_LEVEL_TOOLS so
they bypass the manifest restriction: document/media generation
(renderDocx*, image_generate, music_generate, video_generate),
global capability tools the system prompt mentions (search,
browser_use, read_file / write_file / edit_file /
execute_shell_command, detect_file_type, extract_*_text,
readMateClawDoc), skill discovery siblings (listSkillFiles,
listAvailableSkills), and the delegate triplet (delegateToAgent,
delegateParallel, listAvailableAgents).
- Fixes 5 entries in the prior whitelist whose names did not match
any real @Tool bean and were therefore silently dead:
read_workspace_file -> read_workspace_memory_file
write_workspace_file -> write_workspace_memory_file
list_workspace_files -> list_workspace_memory_files
delegate_agent -> delegateToAgent
datetime -> getCurrentDate / getCurrentDateTime / getCurrentTime
Also adds the missing edit_workspace_memory_file.
- In the chat markdown renderer, strips any hallucinated
https?://<host> prefix from /api/v1/files/generated/<id> download
links before building the <a href>. Multiple LLMs have been
observed prepending bogus hosts when echoing tool-returned download
URLs back to the user, breaking the click. One-line defensive
normalization independent of which model is in use.
Verified end-to-end on a previously-broken agent: search / browser_use
/ execute_shell_command / renderDocx all dispatch correctly now and
the final markdown link is a clean same-origin path. 36 whitelist
entries cross-checked against real @Tool method names.
AgentBindingServiceTest green.
Three layers landed together because they share the same routing /
lifecycle plumbing:
1. Cron output unification
- New CronConversationResolver routes web-origin jobs to the per-workspace
tasks_<wsId> conversation; IM-bound jobs go to the channel session
conversation when one exists (matched by senderId then targetId);
legacy cron_<id> remains as the fallback.
- CronJobLifecycleService inserts a system-role header divider when a
run starts so users browsing the unified tasks_<wsId> view can tell
which job started a run. BaseAgent.sanitizeForLlm filters these
headers so they never reach the model.
- WorkspaceService seeds tasks_<wsId> on workspace creation; V65
migration backfills existing workspaces.
- DeliveryConfig gains a userId field so IM session lookup can match
by senderId (replyToken-based targetId is not stable across runs).
- ConversationVO recognizes tasks_/cron_ underscore prefix as cron
source. MessageList renders the system header as a labeled divider.
- ChatConsole pins tasks_* conversations and tracks per-conversation
read state so new cron output gets a visible unread dot.
2. Reminder task type
- New task_type='reminder' in CronJobEntity + service validation.
- CronJobRunner short-circuits 'reminder' jobs: hands trigger_message
to finishRunAndPublish verbatim, no LLM call. Fixes a regression
where reminders were rephrased into echoed wrappers.
- New create_reminder tool alongside create_cron_job, with descriptions
tightened so the model picks the right one (verbatim push vs LLM
query that needs computation).
- CronJobs.vue gets a third radio option + dedicated reminder field.
3. In-flight progress placeholder
- Cron uses non-streaming chat()/execute(); tool-heavy ReAct loops
can run 1-5 minutes between start and finish with no visible
state, looking hung.
- New GET /api/v1/cron-jobs/active-runs returns runs in status=running
for a conversation. ChatConsole polls it on the existing 4s tick
(and on conversation switch) and shows a spinner bar with elapsed
time. When run count drops to zero, it refetches messages so the
assistant bubble appears within ~1s of finish.
User-reported field issues + a deeper code audit revealed multiple
overlapping bugs in the prior cron-channel delivery change. This fixes
all six.
#1 — Concurrency race on ToolExecutionExecutor (root cause of 'sometimes
succeeds, sometimes fails' tool calls). The volatile instance fields
currentRequesterId / currentWorkspaceBasePath / currentChatOrigin
were shared by every conversation routed through the same per-agent
executor; one user mid-build-loop while another's execute()
overwrote the field would cross-contaminate the captured values into
PreparedToolCall. Fix: kill the instance fields, thread
origin/requester/workspace as method params straight into
PreparedToolCall snapshot. Comment pins the rule so it cannot regress.
#2 — CHAT_ORIGIN missing from KeyStrategyFactory (latent timebomb,
masked by spring-ai-alibaba-graph-core's non-filtering builder path).
Without an addStrategy registration, multi-node state merges in long
ReAct / Plan-Execute loops drop the key, ActionNode reads
ChatOrigin.EMPTY, and the cron persists with channel_id=NULL. Also
caught 4 more keys that were latently unregistered:
WORKSPACE_BASE_PATH, STOP_REQUESTED, RETURN_DIRECT_TRIGGERED,
DIRECT_TOOL_OUTPUTS. All five now registered in both ReAct and
Plan-Execute factories.
#3 — CronJobs UI didn't surface channel binding. CronJobDTO carried
channelId / deliveryConfig but the list page never rendered them.
Added: (a) 'channel' column on list page, (b) channel + targetId
rows in the detail modal, (c) backend batch-loads channel names via
ChannelMapper.selectBatchIds so the column shows the human-readable
name, (d) i18n keys (zh + en), (e) channelName field on TS CronJob
type.
#4a — DingTalk targetId expiry. ChannelChatOriginFactory.resolveTargetId
used to prefer ChannelMessage.replyToken which for DingTalk encodes
a sessionWebhook URL that expires ~90 minutes after the inbound
message. Cron persisted with that webhook then dies with 401/403 and
marks NOT_DELIVERED forever. Fix: prefer the stable chatId, fall
back to senderId — both work indefinitely via DingTalk's Robot API.
#4b — Scheduler pool exhaustion under long LLM. CronJobService's
ThreadPoolTaskScheduler ran with poolSize=4 AND the LLM call lived
on the scheduler thread. Four concurrent crons saturated the pool
and the 5th silently missed its tick. Fix: keep scheduler tiny (it
just fires triggers) and offload runAgent to a dedicated
virtual-thread executor (cron-execute-* threads). LLM workload is
I/O-bound — virtual threads scale to thousands at trivial cost.
#5 — Minor latent bugs:
- AbstractCronResultDelivery.claimRun used .in(... 'NONE','PENDING',null),
but SQL IN never matches NULL. Rewrote as IS NULL OR IN
(NONE,PENDING) so legacy pre-V57 rows can still claim.
- CronDeliveryListener.onCompletedRaw was an empty @EventListener
with a wrong-headed comment about test fallbackExecution. Removed.
- CronJobTool.resolveAgentId silently returned 1L when origin
lacked an agentId — would silently bind to whatever agent #1
happens to be. Replaced with explicit error so wiring bugs surface
immediately instead of producing scheduled-but-never-runs crons.
State-key registration guard. New StateKeyRegistrationCoverageTest
scans MateClawStateKeys via reflection and parses
AgentGraphBuilder.java to extract every
.addStrategy(MateClawStateKeys.X, ...). Asserts every non-_NODE
constant appears in at least one factory. Caught the 4 unregistered
keys above on first run; will catch any future 'forgot to register'
regression.
Tests: 33 unit/arch tests + 27 regression in touched areas — all green.
Vue typecheck clean.
Refs: #25, #16
Replaces the prior ThreadLocal context plumbing with explicit Spring AI
ToolContext threading carried by an immutable ChatOrigin value object,
so a cron created from inside WeChat (or any IM channel) delivers its
results back to the originating channel.
Architecture
- ChatOrigin / ChannelTarget value objects + per-entry-point factories
(ChannelChatOriginFactory in vip.mate.channel, CronChatOriginFactory
in vip.mate.cron — symmetric, no cyclic deps).
- LocaleAwareToolCallback now forwards call(String, ToolContext) and
getToolMetadata so the decorator chain cannot silently drop the origin.
- AgentService 6-method overhaul + ChatOriginHolder bridge into
StateGraph buildInitialState which writes CHAT_ORIGIN; ActionNode +
StepExecutionNode forward it to ToolExecutionExecutor.
- ToolExecutionExecutor builds ToolContext per call; 8/8 tools migrated
(CronJobTool, WorkspacePathGuard, Video/Image/Browser/ReadFile/Music,
DelegateAgentTool with parent-origin inheritance).
- CronJobRunner + CronJobLifecycleService 3-segment REQUIRES_NEW model
(T1 startRun / no-tx runAgent / T2 finishRunAndPublish); ArchUnit
pins CronJobRunner as @Transactional-free.
- CronResultDelivery Strategy + AbstractCronResultDelivery Template
with SQL CAS idempotency on mate_cron_job_run.delivery_status —
replaces the prior process-local Caffeine TTL, cluster-safe.
- CronJobCompletedEvent + @Async @TransactionalEventListener(AFTER_COMMIT);
cronDeliveryExecutor (core=2, max=4, queue=1000, AbortPolicy + audit).
- CronRunStaleCleanup @Scheduled(5min) sweeps PENDING-15min and
status='running'-30min in one query each.
- CronJobRunner.wrapWithDeliveryGuard prepends a system note for
channel-bound crons to suppress hallucinated 'install CLI to send
WeChat' suggestions.
- ApprovalWorkflowService Memento: persist ChatOrigin snapshot on
create, restore on replay so cross-restart approvals keep channel
binding; ChannelMessageRouter + ChatController web-replay both prefer
the Memento and fall back to fresh-build.
- ChannelManager.sendToChannel 4-arg DeliveryOptions overload;
ChannelAdapter#proactiveSend default 4-arg pass-through; Slack
overrides for thread_ts and Telegram overrides for message_thread_id.
- CronJobs UI: read-only 'last delivery' badge driven by
CronJobMapper.selectListWithDeliveryStatus subquery.
Schema migrations V57/V58/V59 (V56 was already taken by an unrelated
provider migration — Flyway processes versions in order regardless of
gaps):
- V57: mate_cron_job_run delivery_status / target / error + composite
index (delivery_status, started_at) covering the cleanup sweep.
- V58: mate_cron_job channel_id (indexed) + delivery_config TEXT (JSON
via MyBatis Plus JacksonTypeHandler).
- V59: mate_tool_approval chat_origin TEXT (Memento).
All idempotent in both H2 (IF NOT EXISTS) and MySQL (INFORMATION_SCHEMA
guard + PREPARE).
ArchUnit guards (test scope, archunit-junit5 1.3.0):
- every concrete vip.mate.* ToolCallback must override
call(String, ToolContext) — pins the decorator-forward fix.
- CronJobRunner must NOT carry @Transactional on the class or any
method — pins the 3-segment lifecycle rule.
Tests: 32 new unit tests + 21 regression tests in touched areas, all
53 green:
- ChatOriginTest (6) — value-object invariants + JSON round-trip.
- LocaleAwareToolCallbackToolContextTest (2) — decorator forward.
- DeliveryConfigTest (4) — Jackson round-trip + forward-compat.
- ToolCallbackToolContextForwardArchTest (2) — both ArchUnit guards.
- CronJobRunnerDeliveryGuardTest (3) — channel-cron prefix injection.
- AbstractCronResultDeliveryTest (4) — claim CAS + concurrent CAS.
- ChannelCronResultDeliveryTest (6) — supports / doDeliver / errors.
- ApprovalReplayContinuityTest (5) — Memento round-trip + corrupt
payload fallback + unknown-field tolerance.
Refs: #25, #16
Adds explicit user-intent gating to the provider catalog. Fresh installs
get an empty dropdown by default — built-in cloud + local providers
(OpenAI, Anthropic, Ollama, LM Studio, MLX, llama.cpp, etc.) live in a
new 'Add Provider' drawer until the user opts them in. Existing installs
upgrade conservatively: V55 promotes any provider with evidence of use
(real api_key, OAuth token, recent chat usage, or current default model).
Backend
- V55 migration (H2 + MySQL): adds enabled BOOLEAN DEFAULT FALSE on
mate_model_provider, plus 4 promote-to-true UPDATE rules. Also
CREATE INDEX idx_message_runtime_provider_time so the 30-day usage
lookup doesn't full-scan mate_message on heavy users.
- ModelProviderEntity, ProviderInfoDTO: enabled field.
- ModelProviderService:
* listProviders() now filters WHERE enabled = TRUE — chat path,
ModelSelector, Settings/Models main grid see only opted-in rows.
* listCatalog() new — full catalog (enabled + disabled) for the drawer.
* setEnabled(id, enabled) flips the flag, publishes
ModelConfigChangedEvent (re-probe via the existing listener), and
on disable auto-promotes a replacement default model when the
disabled provider owned the current default. Returns EnableResult
so the frontend can fire a toast.
* createCustomProvider sets enabled=true (user just made the row).
- ProviderInitProbe.listConfiguredProviders also filters enabled=true —
no point probing rows the user can't see.
- ModelConfigController: GET /catalog, POST /{id}/enable, POST /{id}/disable.
- Plugin-registered ChatModels are unaffected — they live in
pluginChatModels (in-memory map), don't go through DB listProviders,
so the enabled filter doesn't strand them.
Frontend
- New types: ProviderInfo.enabled, EnableResult.
- New API: catalog / enableProvider / disableProvider.
- New composable useProviderEnablement: catalog ref, drawerOpen,
togglingId, loadCatalog, openDrawer / closeDrawer, enableProvider,
disableProvider (fires defaultSwitchedToast on auto-switch).
- AddProviderDrawer.vue: lazy-loaded, reuses DoctorDrawer's Teleport +
overlay + slide-in panel pattern. Two groups (cloud / local),
unenabled rows surface to the top of each group, enabled rows show
an 'Enabled' badge instead of a button. Mobile: full-screen sheet
that slides up from below.
- ProviderCard: new 'Disable' button with soft-danger styling on
enabled providers — soft-hide that keeps the config; user can
re-enable from the drawer.
- Settings/Models index.vue:
* Two top CTAs: 'Enable Provider' (drawer) and 'Custom' (existing
custom-create modal) — distinct workflows, both surfaced.
* Empty state with prominent 'Enable Provider' CTA when zero
enabled providers — paired with onMounted auto-open of the
drawer (sessionStorage guard so closing it doesn't bring it
back on the next route visit in the same session).
* Deep-link: ?addProvider=1 query forces the drawer open and
strips itself after, so a back/forward doesn't re-fire the open.
- ModelSelector: when groups.length === 0 and not searching, show
'No providers configured -> Configure' CTA linking to
/settings/models?addProvider=1 — the natural flow when a fresh
user opens chat before configuring anything.
- i18n: 13 new keys per locale (zh-CN + en-US) plus common.close.
Migration safety
- Conservative default policy: only rows with concrete evidence of
use are auto-enabled; everything else stays hidden. Upgrade users
may notice unused built-ins disappearing from their dropdown —
that's the intended cleanup.
- mate_message index added so the 30-day usage rule doesn't full-scan
on large installations; FlywayRepairConfig handles redeploy idempotency.
Tests
- ModelProviderServiceEnableTest covers all 7 enable/disable branches:
flag flip + event publish, no-op on already-{enabled,disabled},
default-switch when disabled provider owned current default,
no-switch when default belongs elsewhere, no-replacement returns
unchanged, getDefaultModel exception path, candidates with no
models are skipped.
- ProviderInitProbeTest: helper provider() now sets enabled=true so
the new probe filter doesn't strand existing fixtures.
- vip.mate.llm.** suite: 125 tests green. vue-tsc 0 errors. Browser
page renders with both new buttons + drawer.
Reshapes the Settings/Models frontend to match the channel-module split
convention (commit 22894ac4 'perf(channels): split Channels.vue...'),
zero behavior change. Paves the way for a follow-up that adds an enabled
column + AddProviderDrawer without bloating useProviders back to monolith.
Frontend split
- useProviders.ts goes from 615-line monolith to a 48-line facade that
composes five single-responsibility slices:
* useProviderList — providers / activeModels / currentProvider,
loaders, status pill, icons
* useProviderForm — create/edit modal + form, save/delete
* useProviderDiscovery — manage-models modal, discovery, connection
and per-model tests
* useProviderOAuth — openai-chatgpt + claude-code OAuth flows
* useProviderPool — manual reprobe (most pool surface inlined to
ProviderInfo.liveness in the prior liveness change)
Cross-composable refs flow via dep-injection arguments — no module-
level state, no circular deps. Each composable stays independently
testable.
- Pure helpers extracted to src/utils:
* safeJson.ts — strict JSON-object parser
* modelProtocol.ts — protocol <-> ChatModel class translation
- Modals (ProviderConfigModal, ManageModelsModal) loaded via
defineAsyncComponent so the route's first paint doesn't drag along
~30KB of form/auth UI.
- el-skeleton placeholder during the initial Promise.all so the page
paints something instead of blank-then-pop.
Layout regression fix
- MainLayout's <keep-alive> slot used :key='workspaceRouteKey' (a
workspace-scoped string), shared between two <component v-if> blocks.
Adding a second keepAlive route would have caused two components to
mount side by side, because Vue saw identical keys and patched in
place across the v-if boundary. Switched the key to
${workspaceRouteKey}:${route.path} so different routes get distinct
vnode identities while workspace switching still busts the cache.
Discovered while implementing the split — the multi-line HTML
comment also had to live OUTSIDE <keep-alive>, since KeepAlive
treats comments as children and rejects 'more than one'.
Embedding section title fix (drive-by)
- EmbeddingModelsSection.vue's scoped style didn't redeclare
.group-title's flex layout, so the icon stacked above the title
text instead of sitting inline. Added the missing flex rules
locally — now matches the local-models / cloud-models group headers.
Verification
- vue-tsc 0 errors.
- Browser end-to-end: 27 cards render correctly, modals open via lazy
load, /channels <-> /settings/models switch four times in a row with
exactly one page title visible at each step (no stacking).
Phase 1 of the model-module refactor: combine pool / cooldown / probe-
completion signals into a single Liveness state surfaced through the
provider DTO, so the dropdown stops listing providers that are provably
unreachable. Zero schema change; one PR backend + frontend.
Backend
- Liveness enum with five mutually-exclusive states: LIVE, COOLDOWN,
REMOVED, UNPROBED, UNCONFIGURED. Computed in ModelProviderService
from AvailableProviderPool / ProviderHealthTracker / ProviderInitProbe
snapshots batched once per listProviders() call.
- ProviderInitProbe.hasBeenProbed exposes a monotonic Set so the UI
can distinguish 'still booting' from 'probed and removed' — without
it the startup window flashes false REMOVED states.
- ProviderInfoDTO gains liveness + unavailableReason +
cooldownRemainingMs + lastProbedAtMs. The legacy 'available' boolean
stays but is now derived from liveness == LIVE so the chat fallback
walker and the dropdown agree about what's usable.
- ProviderInitProbe injected into ModelProviderService via
ObjectProvider to break the startup cycle (probe already depends on
the service).
Frontend
- ProviderInfo type extended with liveness + the three detail fields.
- ModelSelector filters UNCONFIGURED + REMOVED out of the dropdown,
shows COOLDOWN / UNPROBED with a status dot and dimmed rows that the
user can still click to override.
- ProviderCard renders a five-state badge driven by liveness instead
of the old configured + pool-entry combo. Reprobe button now keys
off liveness in {REMOVED, COOLDOWN}.
- useProviders drops loadProviderPool / providerPool — pool data ships
inline on each ProviderInfo, saves a round trip per page load and
keeps a single source of truth.
- i18n: 8 new keys across zh-CN and en-US for liveness labels and the
cooldown countdown tooltips.
Bonus fix (discovered during verification): AgentGraphBuilder.buildOpenAiApi
hard-required a usable API key on every OpenAI-compat provider, ignoring
the per-provider requireApiKey flag. That bug stranded keyless local
runtimes (LM Studio / MLX / llama.cpp) the moment a user actually
launched them; Ollama only worked by accident because its seed row
carries a placeholder string in api_key. keyRequired now honors
requireApiKey, and Spring AI's NoopApiKey is used when no key is needed
so the Authorization header is omitted entirely.
Test
- ModelProviderServiceLivenessTest covers all five Liveness states +
the probe-bean-absent fallback branch.
- vip.mate.llm.** suite (118 tests) green; vue-tsc clean.
- End-to-end browser sanity: 27 raw providers reduce to 6 LIVE groups
in the chat dropdown; LM Studio / MLX / llama.cpp render REMOVED red
badges with reprobe buttons; cloud providers without keys show
UNCONFIGURED.
Reported issue: click 'scan to create' -> button momentarily flickers
loading -> button re-enables but no QR shows up -> blank for 1-2 seconds
-> QR suddenly appears. Looks broken even though it works.
Root cause: loading.value flipped back to false the moment the begin HTTP
call returned (sessionId in hand), but the actual QR image only arrives on
the first status poll, which the existing code waited a full 2 seconds
for. Between begin completing and the first poll firing the UI was a
disabled button + nothing.
Three coordinated changes:
- useFeishuAppRegister and useDingTalkAppRegister: keep loading.value true
through begin AND across the polls, only flip false when the QR image
is actually populated (or a terminal failure status arrives). Also run
an immediate first poll right after begin instead of waiting for the
setInterval tick — usually the first poll already has the rendered QR
for dingtalk, and pushes the feishu user roughly 2 seconds closer.
- ChannelEditModal: same-sized loading placeholder (min-height 240px,
matching the QR card) that renders when loading is true and no QR is
in hand. CSS spinner ring tinted with the channel brand color (feishu
indigo, dingtalk blue) and a new
channels.{feishu,dingtalk}Register.qrcodeLoading hint. The placeholder
swaps to the real image with no layout shift.
- i18n: new qrcodeLoading key in zh-CN and en-US for both flows.
Net effect: click to spinner-visible is ~50ms; the user is never staring
at a frozen button-without-content again.
Mirrors the feishu one-click flow: scan a QR with the DingTalk app,
approve, and the bot's client_id / client_secret get auto-filled instead
of forcing the user through the open-dev console. Saves about seven
manual steps per channel setup.
Backend
- Bump dingtalk-stream from 1.3.5 to 1.3.12. Diff against the classes we
depend on (OpenDingTalkStreamClient, ChatbotMessage, MessageContent,
GenericEventListener) is empty — pure point-release bumps, no API churn.
- New DingTalkAppRegistrationService: synchronously runs init + begin
against /app/registration/{init,begin} on oapi.dingtalk.com to obtain
the device_code and verification URL, then spawns a daemon worker that
polls /app/registration/poll every 5s until SUCCESS / FAIL / EXPIRED is
returned. Sessions evict after 7 minutes, worker has a 6-minute hard
runtime cap, transient HTTP errors do not terminate the loop. Same
shape as the feishu service, but written from scratch because the
dingtalk-stream SDK doesn't wrap this OAuth device flow.
- Two new endpoints under /api/v1/channels/webhook:
POST /dingtalk/register/begin returns session_id;
GET /dingtalk/register/status returns status + qrcode_img (data URI
PNG, ZXing-encoded from the verification URL, matching the feishu and
weixin flows). Status surface: waiting / confirmed / expired / denied.
Frontend
- channelApi.dingtalkRegisterBegin / dingtalkRegisterStatus.
- New useDingTalkAppRegister composable, structurally identical to
useFeishuAppRegister minus the domain argument. Stops polling on
terminal status, fires onConfirmed with {clientId, clientSecret}.
- ChannelEditModal: dingtalk-register-card rendered when channelType is
dingtalk, scoped DingTalk blue (#1f79ff) to differentiate from feishu's
indigo. onConfirmed writes channelConfig.client_id / client_secret so
the existing form fields update reactively.
- i18n: channels.dingtalkRegister.* keys for title / hint / button states
/ scan / confirmed / expired / denied / startFailed.
Saves the user the entire 'go to the open platform -> create an enterprise
app -> copy App ID and Secret' detour. Click a button in the channel form,
scan the QR code, confirm authorization, credentials are auto-filled.
Backend
- Bump com.larksuite.oapi:oapi-sdk from 2.5.3 to 2.6.1, which adds the
scene/registration package wrapping the device-code flow.
- New FeishuAppRegistrationService: each begin() creates a sessionId,
spawns a worker thread, runs the SDK's blocking RegisterApp.register
with onQRCode and onStatusChange wired into a per-session state machine
(PENDING -> WAITING -> CONFIRMED / EXPIRED / DENIED / ERROR). The
session caches the QR data URI so ZXing only encodes once per attempt.
Sessions evict after 5 minutes so closed browsers don't leak the map.
- Two new webhook endpoints under /api/v1/channels/webhook/feishu:
POST /register/begin returns session_id, GET /register/status returns
status + qrcode_img (data URI base64 PNG, ZXing-encoded from the SDK's
verification URL — the raw URL would render as a broken image, so the
encoding step matches the WeCom flow).
- SDK detail caught the hard way: don't pass .domain() or .larkDomain().
The SDK defaults are accounts.feishu.cn / accounts.larksuite.com (the
registration endpoints). open.feishu.cn is the open-API endpoint, a
completely different service. Passing the wrong one makes the SDK parse
HTML as JSON and emit invalid_response.
Frontend
- channelApi: feishuRegisterBegin / feishuRegisterStatus.
- New useFeishuAppRegister composable: state machine that begins the
session, polls status every 2s, prefers qrcode_img over qrcode_url for
the <img> src, stops on terminal status, fires onConfirmed with
{appId, appSecret}.
- ChannelEditModal: a new feishu-register-card above the wecom one. The
composable's onConfirmed writes channelConfig.app_id / app_secret, so
the existing form fields update reactively.
- i18n: channels.feishuRegister.* keys for title / hint / button states /
scan / confirmed / expired / denied / error.
Backend (FeishuChannelAdapter):
- Default connection_mode flips webhook -> websocket on doStart and doReconnect.
- Stale event filter: drop events whose message.create_time is older than
stale_event_threshold_seconds (default 30s) so SDK reconnect replays do not
re-trigger the agent.
- Silent disconnect watchdog runs every 60s; if no events arrive for
silent_disconnect_threshold_seconds (default 1800s) after the first event,
call onDisconnected to force a reconnect cycle. Setting the threshold to 0
disables the watchdog. The watchdog is scheduled before wsClient.start() on
the bring-up path because that call blocks indefinitely.
- Quoted message context: when a reply has parent_id set, fetch the parent
via GET /open-apis/im/v1/messages/{id}, summarize per msg_type (text / post
first paragraph / [Image]/[File]/[Audio]/[Video] placeholders, capped at
200 chars), and prepend [Quoted: ...] to both content text and the first
content part. LRU-cached (200) per message_id.
- AbstractChannelAdapter gains getConfigLong helper for numeric config keys.
Frontend:
- types/index.ts feishu fields: default connection_mode is websocket; the
recommended option moves to the top; verification_token and encrypt_key
get showIf so they only render in webhook mode; new enable_quoted_context
switch (default on) exposes the quoted-message feature.
- ChannelEditModal builds a feishu-specific WEBHOOK_GUIDES path that picks
webhookStep vs websocketStep based on connection_mode, so users only see
steps for the mode they're using.
- i18n: split feishu.step3/step4 into webhookStep/websocketStep, rename
step5 to permissionStep. Channel type labels in zh-CN drop bilingual
prefix (e.g. 'Feishu / Lark (飞书)' -> '飞书').
Migrations:
- V52 was a no-op the first time it ran (matched compact JSON only) and
Flyway refused to re-run after the SQL was fixed. V52 is documented as a
no-op; V53 carries the actual UPDATE with REPLACE covering both compact
and pretty-printed JSON, and an idempotent WHERE for rows already on
websocket. h2 and mysql variants stay in lockstep.
- Extract create/edit modal into ChannelEditModal.vue (defineAsyncComponent),
shrinking Channels.vue from 1438 to 370 lines and dropping ~30KB from the
initial route chunk.
- Move side-effect logic into composables: useWeixinQrcodePoll (QR + 2s status
poll, auto-cleanup) and useWecomBotAuth (lazy SDK script with module-level
promise dedupe). Pure config-JSON helpers move to utils/channelConfigJson.ts.
- Switch i18n locales from static imports to dynamic import keyed by current
locale; applyLocale becomes async to avoid first-render flicker.
- /channels route opts into keep-alive (meta.keepAlive=true). Channels.vue
pauses status polling in onDeactivated and resumes in onActivated, with an
isActive guard to prevent late-resolving timers from leaking after navigation.
- Initial load goes from serial 3-RTT to Promise.all + 4-card el-skeleton.
When SSE setup fails (e.g. workspace permission denied for shared channel
conversations opened from the web console), the failed turn is never
persisted on the backend. Two issues made the failure invisible to the user:
- The fallback errorInfo dropped data.message, so the inline retry card fell
back to the generic "请求过程中遇到了意外问题" template instead of the
actual reason. Carry rawMessage through, and lower the MessageBubble
display threshold from >8 to >3 chars so short-but-informative messages
(7-char Chinese / "Forbidden") aren't filtered out.
- The status-poll loop in useChat overwrote the local-only failed turn
with the server's "no message" view, erasing the inline retry card.
Skip the merge for turns that exist only locally and are in error state,
so the user can still see the failure and retry.
- Reconcile approval status atomically: DB row, message metadata, in-memory store
- Approve and deny both flip the tool-call card + timeline segment to a terminal
state on the gate message — no more orange spinner stuck after a decision
- Frontend hydrate matches by pendingId and reverse-converges to expired so a
refresh after server-side timeout / consume clears the banner without restart
- Stop sweep, GC timeout, and JVM restart all close the loop with consistent
state
- Remove the dead REST /approve endpoint + matching frontend client export so
there is only one resolve path to maintain
Three bugs surfaced when a non-admin workspace member opened the channel
admin page:
- vue-i18n "Invalid linked format" when '@' appeared in message strings
without the linked-format escape. Replaced literal '@' with vue-i18n v9
literal interpolation {'@'} in both zh-CN.ts and en-US.ts (6 strings:
QQ guide step3, accessControl requireMention/Tooltip).
- 403 from WorkspaceAccessInterceptor was being treated as 401 by the
axios interceptor and the chat SSE handler, clearing the token and
redirecting to /login. Split the two:
* 401 = authentication failure -> handleAuthFailure (logout)
* 403 = authorization failure -> keep session, surface to caller
Now a member who lacks workspace permission sees a toast instead of
being silently logged out.
- Two backend exception sites threw with the default code=500 for what
is semantically an auth/authz event, contradicting the codes returned
elsewhere for the same business event:
* AuthService.login() bad credentials 500 -> 401
* WorkspaceService.requirePermission() 500 -> 403
This aligns service-layer denials with SecurityConfig (401 for missing
JWT) and WorkspaceAccessInterceptor (403 for permission denied), so
the same business event always produces the same code.
The two tools-sync scripts ran on every startup and used H2 MERGE INTO
... KEY(id), which overwrites every column on existing rows. That
silently reverted UI-toggled `enabled` and was the proximate cause of
a recent WriteFileTool/EditFileTool outage.
They were also a strict subset of the fresh-install seed (data-zh.sql /
data-en.sql register all 19 builtins; the sync scripts only 16) and out
of date. Per-tool Flyway migrations (V3, V31) are already the canonical
'register a new builtin' path, so the sync layer was duplicated and
error-prone.
Delete both files and the runToolSyncScript() loader. Tool descriptions
shown to the LLM come from @Tool annotations in code, not the DB row,
so removing per-startup metadata refresh has no functional impact.
Three small but high-impact fixes that all surfaced together while
verifying the long-form generation flow.
1. ChatConsole onBeforeUnmount no longer kills the backend turn.
Previously, switching tabs / route navigation / any cause that
unmounted the chat view called stopChatGeneration(), which POSTs
/chat/{cid}/stop and aborts the in-flight LLM call. The user
reported a turn dying mid-generation just from switching pages.
Replaced with resetForNewConversation() — front-end SSE disconnect
only, no /stop. Backend keeps running; pollActivity / status probe
reconnects on return. Aligns with the existing comment in
selectConversation: "let A's backend agent run continue running."
2. Agent max_iterations raised 25 → 100 with a hard ceiling.
The previous 25-step ceiling caused LimitExceededNode to fire on
substantive multi-tool tasks (document generation + image conversion
+ retry loops). 100 matches QwenPaw's _MAX_MAX_ITERATIONS upper
bound. New plumbing:
- BaseAgent.MAX_ITERATIONS_HARD_CEILING = 100 public constant
- BaseAgent default field 25 → 100 (Java-side fallback)
- AgentGraphBuilder clamps any per-agent DB override to the
ceiling at runtime; if the row holds 200, runtime sees 100 and
a WARN is logged with the original value.
- V47 migration (h2 + mysql) idempotently bumps the three default
seeded agents (1000000001, 1000000002, 1000000003) only if they
still hold the old defaults (25 / 20). User-customized values
are not touched.
- data-en/zh/-mysql-en/-mysql-zh seed files updated to 100 for
fresh installs.
3. DocxRenderTool tells the LLM not to prepend a host to the URL.
DeepSeek and Claude have both been observed wrapping the
/api/v1/files/generated/{id} relative path returned by renderDocx
into an absolute URL with a hallucinated domain (e.g.
https://ai-tools-system.com/...), breaking the download link in
the rendered chat bubble. The tool's return string now appends an
explicit "must use the relative path verbatim, do not add any
https:// or http:// prefix" instruction, which Claude and
DeepSeek both honor.
A bundle of stability fixes that all surfaced together while running
the same long-form generation task across multiple turns. Each one
addresses a distinct way the previous behavior silently dropped
content the user had already seen on screen.
1. Mid-turn narrative persistence (StateGraphReActAgent +
SummarizingNode). Intermediate ReasoningNode rounds and
SummarizingNode broadcast their content_delta directly to the
SSE channel for live display, but the StreamAccumulator only
received the final answer. After refresh the assistant message
showed only tool_call cards with no body text.
StateGraphReActAgent now also forwards STREAMED_CONTENT (already
set per round) as a persistOnly StreamDelta whenever it changes,
so every narrative chunk lands in the accumulator's content
buffer and gets written to mate_message. SummarizingNode now
writes its summary into the same key so summarize narratives
persist too.
2. Follow-up message queue, not dispose (ChatController#interruptStream).
Sending a new message while a turn was running called
requestInterrupt, which dispose()d the active Reactor chain mid
LLM call. That cancelled the in-flight generation, lost partial
tokens, and left the user staring at a half-finished bubble.
The endpoint now uses enqueueMessage in all paths, matching
the "wait for current turn, then run" behavior. The old
requestInterrupt API is kept for any future force-replace UI
but no caller routes to it.
3. Queued user message ordering (ChatStreamTracker.QueuedInput +
ChatController.startQueuedMessage). interruptStream used to save
the queued user message immediately, before the in-flight
assistant message finalized in doOnError. listMessages orders
by create_time ASC, so the queued user message ended up above
the assistant reply it was supposed to follow. QueuedInput now
carries contentParts; persistence is delayed to startQueuedMessage,
which runs only after Asst-N is on disk.
4. JVM shutdown flush (ChatStreamTracker @PreDestroy +
emergencySaveAccumulator). A mvn spring-boot:run restart used to
wipe in-flight turns: SSE emitter timed out, ShutdownHook fired,
HikariPool closed before doOnError could save. ChatStreamTracker
now exposes an emergency-save callback per RunState; ChatController
registers one per stream that snapshots the accumulator and
writes status="interrupted_shutdown". @PreDestroy walks active
runs, invokes the callback, then disposes. Spring's reverse-order
bean teardown keeps ConversationService and Hikari alive long
enough for the save to complete.
5. Observation thresholds for summarize (GraphObservationProperties +
application.yml). The previous total-chars threshold of 12 KB
triggered summarize after one or two RFC reads, costing a 40 to
80 second compaction LLM call per loop. Tuned to: total 200 KB,
single 16 KB, large-result 32 KB, rounds safety net 25. Java
field defaults reverted to the conservative original values so
application.yml stays the source of truth.
6. Frontend thinking segmentation (useChat.ts thinking_delta +
phase). Multi-round ReAct turns merged every reasoning + summarize
round's thinking into one segment, accumulating to 9 KB+ in a
single bubble. thinking_delta now uses findLast(running) so a
tool_call_started or phase transition closes the previous segment
and the next delta opens a fresh one. phase event also closes
running thinking/content segments.
7. Other small things bundled: removed a debug metadata-keys log
that flooded the log file with one line per stream chunk; fixed
three stale tests that didn't compile after earlier constructor
changes (WikiLogServiceTest, WikiOverviewSpliceTest,
WikiProcessingServiceLazyTest); added rfc-066 documenting the
unified message queue + priority refactor as the next logical
step on top of these stabilizations.
Verified end-to-end with multiple full sessions: a four-minute
generation that produced the expected docx and a follow-up enqueue
that ran cleanly after the previous turn naturally completed,
without the old "Disposable unavailable" interrupt path.
- Drag-over highlight (orange border + shadow + arrow icon) on the upload
zone, using dragCounter to prevent flicker over nested children
- Optimistic list items appear immediately on drop/select with UPLOADING
badge and progress bar, before the HTTP request completes
- Wire axios onUploadProgress through api.uploadRaw → store.uploadRawFile
so the progress bar tracks real byte transfer (0–100%), with an
indeterminate shimmer until the first tick
- try/catch around every upload: on failure, placeholder flips to an error
state with ElMessage.error toast and a × dismiss button
- Upload all dropped/selected files concurrently via Promise.all
- i18n keys added (zh-CN + en-US): dropToUpload, uploading, uploadFailed,
status.uploading, progress.uploading
Three bugs fixed:
1. Badge stays "processing" after job completes: pollJobs() never called
fetchRawMaterials() when a job reached terminal status, so
raw.processingStatus stayed processing in the store. Fix: detect
terminal job status in pollJobs, trigger fetchRawMaterials to sync.
2. "Completed" dot pulses instead of solid: dotClass() treated completed
the same as in-progress (target === cur → active). Fix: add
isTerminal computed (includes completed), return done for all
dots at or before the terminal position — no pulse animation.
3. Stage label stays orange at terminal: same cause — active class
applied regardless of terminal state. Fix: use done class for
terminal labels (green instead of orange).
Also: v-if on JobStageBar now shows for terminal status jobs (not just
stage !== queued), so completed/failed stage bars remain visible.
Root cause: processRawMaterial() created a job record at queued stage
but never called jobService.transition() during processing. The job row
stayed at queued forever, so the stage bar never advanced.
Backend (WikiProcessingService):
- Transition job to ROUTING immediately after creation
- Transition to PHASE_A_RUNNING before chunk processing begins
- Transition to COMPLETED/PARTIAL/FAILED at the end based on finalStatus
- Transition to FAILED in the catch block on unhandled exceptions
Backend (WikiProcessingJobService.transition):
- Handle FAILED, PARTIAL terminal stages (set finishedAt + status)
- Handle non-terminal intermediate stages (set status to running)
Frontend (JobStageBar.vue):
- Add stageMapping for backend stages not shown as dots: phase_a_done →
phase_b_running, failed/partial/cancelled → completed position
- Guard stageIndex() against -1 (unknown stages default to all-pending)
- Terminal failure states show red failed dot instead of pulsing active
Root cause: addFile()/addText() hash dedup only matched rows with
status=completed, so the same file uploaded while in partial/pending/
processing/failed status would create a duplicate row.
Fix:
- Remove .eq(processingStatus, "completed") from dedup queries — match
any non-deleted row with the same content hash in the KB
- On dedup hit: completed/pending/processing → return as-is;
partial/failed → trigger reprocess (partial enters resume branch)
- Clean up the newly uploaded temp file when dedup discards it
- Frontend: uploadRawFile/addRawText check for existing id in the list
before unshift to prevent visual duplicates
Test: WikiRawMaterialDedupTest — 10 cases covering all 5 statuses,
reprocess triggers for partial/failed, no-op for others, insert only
when no match.
Three root causes for broken progress:
1. JobStageBar was shown whenever a job record existed (even at queued
stage), hiding the working SSE-driven progress bar. Fix: only show
JobStageBar when job.stage !== queued.
2. SSE connection only opened when hasProcessing was true (status ===
processing), but reprocess sets status to pending first. Fix:
include pending in the hasProcessing check.
3. After reprocess, if processing finished before SSE connected, the
status badge stayed on pending forever. Fix: immediately set local
status to processing after reprocess API call, clear stale job
entries, and add delayed re-fetches (5s/15s) as safety net.
Also: clear rawJobs entries on raw.completed/raw.failed SSE events to
prevent stale JobStageBar from lingering after processing ends.
Two related issues from the Kimi-401 user report:
1. Backend (NodeStreamingChatHelper): a primary AUTH_ERROR (e.g. Kimi 401
with an invalid API key) returned immediately without trying the
fallback chain — a fallback provider with a different, valid key
never got a chance. Even with DashScope correctly configured as the
fallback, the user chat dead-ended on a 401.
The original assumption ("auth never self-heals so do not retry")
holds for the primary same-model retry loop but is wrong for the
fallback chain — different providers have different keys. Apply the
same break-into-fallback policy that BILLING and MODEL_NOT_FOUND
already use. recordPrimary(false) is preserved so the cooldown
counter still accumulates.
2. Frontend (chatError.ts + i18n): the error-text matching for
/认证|auth|unauthorized|401/i was so broad it matched the substring
"auth" inside URLs like https://api.kimi.com/.../auth, classifying
any model 401 as user "session expired" and rendering the misleading
"页面将自动跳转到登录页" copy. (The redirect itself only fires from
/api/v1/auth/* axios paths and SSE-connection 401s, not from this
payload-text path — but the copy alone is the worst kind of false
alarm.)
Add a new ChatErrorCategory provider_auth_error and split the
pattern matching: narrow auth_expired (HTTP 401 / 登录已过期 /
session expired / 凭证失效) is matched FIRST, then the broad
401-ish pattern routes to provider_auth_error. BACKEND_ERROR_TYPE_MAP
for AUTH_ERROR is also remapped, since structured backend payloads
currently always come from LLM providers — never from our own
/api/v1/auth path.
Tests
- NodeStreamingChatHelperFailoverTest (5 cases): primary 401 →
fallback succeeds; chain skips auth-failing fallback to next healthy
one; whole-chain failure surfaces last AUTH_ERROR (no silent drop);
BILLING regression unchanged; primary-success path does not touch
chain
- Browser preview verified: new i18n keys resolve in en-US, classifier
correctly routes "[错误] 401 from kimi.com" → provider_auth_error
while "[错误] HTTP 401 from /api/v1/auth/ping" stays auth_expired
- 186 tests pass (was 181 + 5 new); vue-tsc clean
Do-not-touch list: handleAuthFailure() in useStream/api/index.ts (real
session-expiry path) is unmodified — only the misclassification
upstream is fixed. auth_expired i18n copy is unchanged.
UI — Failover priority editor
- ProviderConfigRequest + ProviderInfoDTO carry fallbackPriority
- ModelProviderService.updateProviderConfig persists it (null = unchanged);
toProviderInfo exposes the current value to the UI (defaults to 0)
- ProviderConfigModal advanced panel exposes a number input with hint
- ProviderCard shows a "Fallback #N" badge for chain members so the
priority order is visible at a glance without opening the modal
- 5 new i18n keys (zh + en) — verified to resolve at runtime via i18n.global.t
Backend — Per-provider health tracker
- ProviderHealthTracker: ConcurrentHashMap-backed counters; N consecutive
failures (default 3) push the provider into a cooldown window (default
5 min) during which the chain walker skips it. Success resets both
counter and cooldown atomically. Lazy expiry on lookup so dead entries
do not accumulate.
- ProviderHealthProperties exposed under mateclaw.llm.failover.health.*
with sane production defaults
- New FallbackEntry record (providerId + ChatModel) replaces raw
List<ChatModel> in the chain so the walker can correlate cooldown
state to entries; AgentGraphBuilder.buildFallbackChain returns the
new type
- NodeStreamingChatHelper takes the tracker through a new 4-arg
constructor and consults it before each fallback call; records
success/failure on each chain attempt. Legacy 2/3-arg constructors
preserved as @Deprecated wrappers (synthetic providerId means no
health tracking on the legacy path — that path is opt-out anyway)
Tests
- ProviderHealthTrackerTest (9 tests): below/at threshold, success
reset, cooldown expiry (via reflection on the min-clamp setter),
disabled-tracker no-op, null-providerId safety, per-provider
isolation, snapshot output
- NodeStreamingChatHelperFallbackChainTest updated to FallbackEntry
field type — verifies providerId + ChatModel survive the chain
- 168 tests pass (was 159 + 9 new)
Verification
- mvn test green; vue-tsc clean; live UI confirms i18n resolution
Pasted prompts (test cases, structured asks, JSON dumps) currently render
through the same markdown pipeline as assistant output, so '#'/'-'/'**'
characters are processed and long prompts dominate the scrollback.
- New UserMessageContent.vue: plain-text rendering (white-space: pre-wrap
preserves user-typed newlines and indentation), with auto-collapse beyond
8 lines and a "Show more (N more lines) / Show less" toggle. Soft mask
gradient at the collapse boundary instead of a hard cut.
- MessageBubble.vue: route role==='user' messages through the new component;
assistant messages keep the existing markdown pipeline unchanged.
- Add chat.expandLines / chat.collapse i18n keys (zh + en).
Verified end-to-end in browser preview: 15-line content collapses to 8,
toggle expands to full 15 with "Show less" label, raw '#' / '**' / '`' chars
shown literally with no <strong>/<h1>/<li> tags emitted.
- db/migration/mysql: replace ADD COLUMN/CREATE INDEX IF NOT EXISTS with
idempotent checks via information_schema (MySQL 8.0 <8.0.29 and some
forks don't support IF NOT EXISTS for ADD COLUMN). Affects V2/V4/V5/V7
/V8/V9/V11/V12/V13/V14. Fix: gitee#IIYHLJ.
- application-mysql.yml: add createDatabaseIfNotExist=true so MySQL
Connector/J auto-creates the schema on first connection (requires
CREATE privilege — documented fallback for restricted accounts).
- llm/OllamaAutoDiscoveryRunner: rewrite seed tag when fuzzy-matching,
prefer exact tag for default; skip models without tool support when
auto-activating a default (prevents the phantom ':latest' trap when
users pulled a specific size).
- agent/graph/NodeStreamingChatHelper: detect 'does not support tools'
and 'model not found' errors from Ollama and emit actionable Chinese
prompts guiding users to qwen3 / qwen2.5:7b+ / llama3.1:8b+ etc.
- ui/MessageBubble + types/chatError: surface the backend's actionable
rawMessage in the failed-message card instead of a generic '未知错误';
strip redundant prefixes (Bad request: / [错误] / LLM 调用失败:) since
the title already conveys the category.
- ChannelMessageRouter: include assistantMessageId in message_complete
and done broadcasts so ChatConsole observers can reconcile the
streaming placeholder to the persisted DB row by id instead of
falling back to the FIFO 'claim' heuristic (which occasionally
dropped the assistant bubble on external channel conversations).
Capture the id from ConversationService.saveMessage in both the
sync agentService.chat path and the streaming processWithStreaming
path; switch to HashMap since Map.of rejects null values when save
is skipped (e.g. under approval).
- ChatConsole: add a 'running' indicator on the sidebar so users can
tell which conversations have an in-flight agent run. Pulsing amber
dot on the channel icon (both expanded and collapsed modes) plus a
'生成中…' / 'Generating…' pill in expanded mode.
- ChatConsole: don't cancel the previous conversation's streaming run
when switching conversations — let it keep running in the background
and reconcile when the user comes back.
