Closes the authorization asymmetry between list endpoints (which filter
by workspaceId) and direct-access endpoints (which did not): a logged-in
user could reach another workspace's system / IM / webchat-owned
conversation by id and run any of messages / delete / rename / pin /
setModel / clear / chat-files download on it.
Per the maintainer's guidance on issue #344, workspaces are now treated
as untrusted isolation boundaries — the fix is the cross-cutting
hardening, kept out of feature work.
Behavior change (only for shared, non-direct convs):
- requester is a global admin (user.role=admin) → pass
- requester is a member of the conversation's workspace → pass
- otherwise → deny
Preserved to avoid regressions:
- direct owner (username == conv.username) → pass without lookup
- convs without workspace_id (legacy rows) → legacy system-owner check
- anonymous user (authService returns null, e.g. permitAll reconnect)
→ legacy system-owner check
Callers in ConversationController / ChatController / SubagentController /
GoalController / ApprovalController (18 sites) are unchanged — the
signature stays isConversationOwner(conversationId, username). The
workspace membership check is done via WorkspaceService.hasPermissionCached
(Caffeine-backed, same cache the WorkspaceAccessInterceptor uses) and
ignores the X-Workspace-Id header, which is client-controlled.
Tests: 11 cases in ConversationServiceOwnershipWorkspaceTest covering
each branch of the new logic. No caller-side test changes — the 66
caller tests (ConversationService*Test, ChatController*Test,
SubagentController*Test, GoalController*Test, ApprovalController*Test)
still pass.
Previously WebChatController.chatStream silently dropped every agent
lifecycle event except _usage_final (and content_delta / thinking_delta
derived from delta.payload). Visitors sat with nothing between the
meta event and the first content chunk — typically 3–10s when the
agent plans / recalls memory / runs tools, longer when the agent
chained multiple tool calls. The JWT chat path (ChatController) had
this wiring; webchat did not.
Curated 4-event subset (per design review):
- phase — high-level phase transition (planning / generating /
summarizing / ...). SDK shows a "AI is thinking..."
typing indicator before the first token.
- tool_start — agent invoked a tool. SDK shows a localized badge
("Searching...", "Reading file.pdf", ...).
- tool_end — tool completed. SDK clears the badge.
- plan — Plan-Execute agents expose their step list. SDK can
render a checklist.
Deliberately NOT forwarded (internal noise / leak risk):
- _usage_final, _routing_decision — consumed internally
- finish_reason — implicit in `done`
- feedback_event — visitor can't retry/regenerate anyway
- perf_summary, iteration_* — internal metrics
- plan_step_started/completed — too granular; the plan event covers
the visitor's needs
Critical safety constraint: tool_start / tool_end carry ONLY the tool
name. Tool arguments and results are dropped — agent tool calls can
contain PII (file paths, user queries, credentials), and relaying
those to a 3rd-party website frontend is a data leak. The SDK maps
tool name → localized label via its own lookup.
Backward compat: existing clients ignore unknown event types per the
SSE spec, so adding these is non-breaking.
Tests: 5 new cases in WebChatStreamE2ETest covering each event type
+ a regression case asserting internal events are silently dropped.
85/85 webchat tests green.
Docs: docs/zh/webchat.md gains a "实时进度事件" subsection.
Stack: feat/webchat-attachment-e2e → feat/webchat-stream-phase-events
Follow-up to epic #355.
AuditEventService gains recordAs(actor, workspaceId, ...) — an overload
that takes an explicit actor string instead of deriving one from
SecurityContext. Used for non-MateClaw principals (currently just
webchat visitors), where there is no Spring Security auth and the
default record() path would write "system".
WebChatController injects AuditEventService and adds an audit() helper
that constructs the canonical actor string "webchat:<channelId>:<visitorId>"
so audit-event searches can filter by channel or visitor. Eight write
endpoints now log an audit row on success:
webchat.create-session, webchat.rename-session, webchat.pin-session,
webchat.archive-session, webchat.delete-session, webchat.stop-session,
webchat.regenerate-session, webchat.upload-file
/stream is intentionally NOT audited — message-volume noise, and
conversationService.saveMessage already leaves a durable trail.
Each row carries:
- username = webchat:<channelId>:<visitorId>
- action = webchat.<verb>
- resource = CONVERSATION / <conversationId>
- detailJson = {sessionId, ...action-specific fields}
WebChatAuditTrailTest (@SpringBootTest, 2 cases):
- createSession lands a row with the exact actor string + action
- rename + pin + archive + stop each leave a row (4 distinct actions)
Audit insert is async; tests poll up to 3s for the row to appear.
Regression: 9 webchat test classes (64 tests) green.
Part of epic #355.
Two cleanups promised in the plan, kept narrow to avoid cascading churn:
1. New WebChatErrors enum — single source of truth for the visitor-facing
HTTP error codes + messages. All future R.fail() calls can reference
WebChatErrors.INVALID_API_KEY etc. instead of bare literals. This PR
doesn't migrate every existing call site (that's a noisy sweep better
done in a follow-up); the enum just needs to exist so audit/OpenAPI
work in PR 7/8 can quote canonical messages.
2. pageSessions now delegates auth to listSessions instead of duplicating
the resolveChannel + verifyVisitorToken block. Same external behavior;
-15 lines of duplication. The pagination/keyword logic stays where it
is (it's specific to the /page variant and doesn't belong in
listSessions).
Visitor-token `required=true` migration from plan §6 was dropped: changing
it would flip missing-token responses from 401 to 400, which violates the
current error-code contract that visitors and tests rely on. The
`required=false` + explicit-verify pattern stays.
Regression: 7 webchat test classes, 42/42 green.
Part of epic #355.
New endpoint POST /api/v1/channels/webchat/sessions/regenerate. Behavior:
1. Auth (API Key + visitorToken + ownsConversation — same chain as the
other session mutations).
2. streamTracker.requestStop() — kill any in-flight stream first so its
doOnComplete doesn't race the delete/save below.
3. Find last role=user message (seed) and last role=assistant message
(target).
4. Delete the last assistant message if present.
5. Reuse chatStream by handing it a synthetic WebChatRequest whose
message is the seed user content. chatStream saves a fresh user
message (new id, same content) and starts the agent turn.
Trade-off: chatStream saves a new user message rather than replaying the
existing one in place, so the user-side message count grows by 1 per
regenerate. Acceptable — the alternative (refactoring chatStream into
reusable chunks) is a 4-hour distraction from the actual feature, and the
extra row is harmless (history still reads naturally: user, asst, user,
asst, user, asst instead of user, asst, asst).
ConversationService gains findLastMessageByRole() and deleteMessageById()
helpers; both are scoped exactly to what regenerate needs.
WebChatRegenerateTest (@SpringBootTest, 5 cases):
- empty thread (no user message) → error event, no DB change
- deletes the last assistant reply (count strictly decreases)
- bad token → no DB change (auth fails before mutation)
- unknown sessionId → returns emitter without throwing
- seeds from the LAST user message when multiple exist
Tests don't assert on the actual LLM stream content — that's left for
PR 5's WebChatStreamE2ETest, which mocks the chat model.
Part of epic #355.
Two new session-state mutations, both following the rename endpoint's
shape (PUT + {flag: true|false} body + visitorId/sessionId query):
- PUT /api/v1/channels/webchat/sessions/pinned — flips mate_conversation.pinned
- PUT /api/v1/channels/webchat/sessions/archive — flips mate_conversation.archived
Archive complements delete as a "soft-close" — the thread stays on disk
(history preserved, addressable, downloadable) but is hidden from the
default /sessions listing. Pin makes a thread sort first in the visitor's
listing, mirroring the admin-console behavior.
Archive dominates pin: an archived+pinned thread is still hidden by
default. Callers opt back in via includeArchived=true (added in PR 1).
ConversationService gains setArchived(), mirroring the existing
setPinned() pattern.
WebChatArchivePinTest (@SpringBootTest, 6 cases):
- pin flips column + view reflects pinned=1
- archive hides from default listing, includeArchived=true shows it,
un-archive restores
- archived+pinned still hidden (archive dominates)
- malformed body / wrong type → 400
- unknown sessionId → 404
- bad token → 401
Part of epic #355.
Closes the "no way to ban a single visitor without burning the global
JWT secret" gap from the epic. Two changes:
1. Token format: HMAC payload now includes exp, format is
`<base64sig>.<expEpochSec>`. Default TTL 7 days (VISITOR_TOKEN_TTL_SECONDS).
Expiry participates in the HMAC, so bumping it client-side invalidates
the signature. /stream still mints fresh tokens on first contact — a
revoked visitor can start a new /stream (gets a new token), they just
can't use the old one on management endpoints.
2. WebChatTokenRevocationService — DB-backed registry (webchat_revoked_visitor
table from V148) with a 5-minute Caffeine cache in front. revoke() /
unrevoke() / isRevoked(). The cache accepts up to 10min eventual
consistency across instances — webchat is low-volume, and a fresh node
sees revocations immediately on cold cache. DB remains source of truth.
WebChatController.verifyVisitorToken becomes an instance method that chains
verifyVisitorTokenSignature (static, HMAC + exp) with isRevoked (instance,
DB + cache). All 9 management endpoints now check revocation transitively.
Admin endpoint: POST /api/v1/admin/webchat/revoked-visitor (and DELETE to
un-revoke). Mounted under /api/v1/admin/** so it requires a MateClaw JWT
— visitors can't reach it. Records an audit row (action=webchat.revoke-
visitor, resourceType=CHANNEL) via AuditEventService.
Tests:
- WebChatTokenRevocationTest (@SpringBootTest, 7 cases): revoke blocks
/sessions with 401, un-revoke restores, double-revoke idempotent,
expired token rejected even without revocation, /stream unaffected
(signature still verifies), admin endpoint inserts row + audit.
- WebChatVisitorTokenTest extended to 16 cases — added expired-token,
tampered-exp, and "differs when exp differs" coverage; existing
verify_* cases moved to verifyVisitorTokenSignature (the static half).
Regression: WebChatSchemaFieldsTest (5/5), WebChatCreateSessionTest (9/9),
WebChatSessionManagementTest (5/5), WebChatStopStreamTest (5/5).
Part of epic #355.
Schema foundations for the rest of the epic. Three additions:
1. mate_conversation.archived — INT default 0. Lets a visitor "soft-close"
a thread: stays on disk (history preserved, addressable, downloadable)
but excluded from default /sessions listing. Pinned/archived are
orthogonal; archive dominates (archived+pinned still hidden by default).
2. webchat_revoked_visitor — registry table consumed in PR 2 by the
WebChatTokenRevocationService. Unique on (channel_id, visitor_id, deleted)
so re-revoke is idempotent and deleted=1 un-revokes. Migration written
for all three DBs (h2 IF NOT EXISTS, MySQL INFORMATION_SCHEMA guard,
KingbaseES native IF NOT EXISTS) following the V147 pattern.
3. WebChatSessionView gains pinned/archived/streamStatus so the visitor-
side listing surfaces the same state the admin console sees. Closes
the "field exposure" gap from the epic.
loadVisitorSessions gains an includeArchived flag (default false) — the
default hides archived threads and excludes them from the empty-session
quota, since the visitor already declared they're done with them.
GET /sessions and GET /sessions/page thread an `includeArchived=true`
query param through.
Tests (WebChatSchemaFieldsTest, @SpringBootTest + H2 + V148):
- revoked-visitor table is queryable
- archived column is read/write
- view exposes pinned/archived/streamStatus
- archived hidden by default, visible with includeArchived=true
- archived empty threads don't saturate the 5-thread quota
Regression: WebChatCreateSessionTest (9/9), WebChatSessionManagementTest
(5/5) — both updated for the new includeArchived param.
Part of epic #355.
Until now webchat had no way to actually interrupt a running stream —
ChatController's /api/v1/chat/{id}/stop was technically permitAll'd but
silently no-op'd on webchat streams because WebChatController.chatStream
dropped the subscribe() return value, so ChatStreamTracker.requestStop
had no Disposable to dispose. Visitors could only "stop" client-side by
closing the SSE connection; the server-side LLM call kept running,
burning tokens and firing any side-effecting tools to completion.
Two changes (issue #353):
1. WebChatController.chatStream: keep the Disposable and register it
with streamTracker.setDisposable, mirroring ChatController#chatStream
line 495. Now requestStop actually disposes the Flux.
2. New endpoint POST /api/v1/channels/webchat/sessions/stop:
- Auth mirrors the other session-management endpoints: X-MC-Key +
X-MC-Visitor-Token + ownsConversation (404 on unknown sessionId,
so callers can't probe the namespace).
- Returns {stopped: true|false}; false means no active stream
(idempotent, not an error).
- No approval sweep — webchat has no MateClaw username and exposes
no approval UI today; defer until that surfaces.
WebChatStopStreamTest (@SpringBootTest, H2, V147) — 5 cases:
- stopActiveStream registers a real Flux.never() Disposable on the
tracker and asserts both stopped=true AND disposable.isDisposed(),
proving the chatStream wiring change is what makes the endpoint work.
- noActiveStreamReturnsFalse — idempotent path.
- bad token / bad API key → 401.
- unknown sessionId → 404.
Complements the implicit getOrCreate in /stream: lets a caller pre-create
an empty thread (message_count = 0) and receive sessionId / conversationId /
visitorToken up front, then decide when to send the first message via
/stream. Mirrors how downstream CRM/ticketing systems model "create the
conversation object first, message later".
Auth is the visitor's first touch — only X-MC-Key is required (no
X-MC-Visitor-Token, which the visitor can't have yet); the server signs
and returns a fresh visitorToken the caller must echo back on subsequent
GET/PUT/DELETE.
Behavior (issue #351):
- Idempotent on sessionId collision → returns the existing thread 200,
does NOT clobber title.
- Empty-session quota ≤ 5 per (channel, visitor); 409 with a clear
message when exceeded. Existing rows are exempt (re-create is idempotent).
- Caller-supplied title (1-100 chars) is persisted; absent title leaves
the default "新对话" so the first /stream user message still derives
it. getOrCreateWebchatConversation now accepts an optional title and
only writes it on insert (existing rows untouched).
- agentId override mirrors /stream's workspace check.
ConversationService.getOrCreateWebchatConversation gains a title-aware
overload; the original 5-arg signature delegates with title = null.
End-to-end coverage in WebChatCreateSessionTest (@SpringBootTest, H2
with V147 migration): happy path, caller-title survives first user
message, default-title still derived, idempotent collision, quota 409,
bad API key 401, illegal sessionId/title 400, listed after creation.
Two webchat hardening fixes:
- Session listing no longer pulls every system-owned conversation into
memory. listSessions/pageSessions went through listConversations(owner)
whose `username IN (owner, system)` loaded all IM/cron rows just to show
one visitor's handful of threads. New listWebchatConversations(username)
queries only the visitor's own rows; the channel prefix is matched
in-memory with a literal startsWith (so a '_'/'%' in the api key's first
8 chars can't act as a LIKE wildcard).
- Upload now enforces a per-conversation quota (file count + total bytes,
both configurable) so a visitor can't fill the disk with many
individually-under-cap files. Pairs with the existing staging TTL sweep.
When webchat:<key8>:<visitorId>:<sessionId> exceeds 64 chars the
conversationId folds visitorId+sessionId into an unrecoverable hash, so
the thread fell outside listSessions' conversationId-prefix filter and its
sessionId could not be recovered — the thread was invisible and
unaddressable (common with a UUID visitorId + a >10-char sessionId).
Persist the sessionId on creation (new nullable webchat_session_id column)
and enumerate by username + channel prefix (webchat:<key8>:), which also
matches the hashed form. sessionId is read from the column, falling back to
parsing the conversationId only for legacy rows.
Adds a @SpringBootTest covering listing (incl. the hashed thread), message
pagination, session paging/search, rename, and token rejection end-to-end.
Refs matevip/mateclaw#346
Bring the webchat visitor session API closer to the admin console's:
- GET /sessions/messages gains beforeId + limit. With a limit it returns
{messages, hasMore} (latest N, then pull-up for older) using the
external path-stripped view; without it, the full list as before.
- GET /sessions/page paginates + keyword-searches a visitor's threads
(in-memory: a visitor's thread set is bounded to its own namespace).
- PUT /sessions/title renames a thread (1-100 chars).
All keep the webchat auth model (API key + visitor token, server-derived
conversationId, ownership guard). Message views go through the shared
toExternalMessageViews helper so the paginated path is sanitized too.
Refs matevip/mateclaw#346
WebChat had no file support: the /stream body carried only text, and
agent-produced files had no visitor-reachable download path (the JWT
/chat/files endpoint is unreachable for API-key visitors).
Add webchat-authenticated file transfer, reusing MessageContentPart +
the existing upload dir + agent multimodal injection:
- WebChatFileService: validate (size cap, extension whitelist, filename
sanitize), store under the conversation's upload dir, stage by opaque
fileId, traversal-safe resolve. Untrusted-uploader hardening lives here.
- POST /upload (multipart) and GET /files, both authed by API key +
visitor token with a server-derived conversationId (never client paths).
Downloads send non-images as attachment + X-Content-Type-Options:nosniff.
- /stream gains attachmentIds; the server resolves each id from the
staging registry (client metadata is never trusted), builds parts, and
persists them on the user message so the agent's multimodal/file tools
pick them up from history — same path as the JWT web chat.
- Strip server-side file paths from the visitor-facing message view
(listMessageViewsExternal + includePath flag) so the filesystem layout
is not disclosed.
Refs matevip/mateclaw#342
The permitAll comment claimed a 10-minute TTL, but GeneratedFileCache.TTL
is 7 days. The stale figure could mislead future security reasoning about
how long an unauthenticated capability URL stays live. Align the comment
with the actual value; the unguessable UUID remains the access guard.
Refs matevip/mateclaw#344
WebChat conversations are owned by an external visitor principal
(webchat:<visitorId>) so each visitor's threads stay isolated for the
self-service session API. But the console list/page/owner-check only
recognized the current user + system owners, so these conversations were
invisible in the sidebar and the Sessions page — and would 403 on open
even if surfaced.
Treat webchat: owners like system owners for the console: include them in
the lenient list/page queries and in isConversationOwner. The strict
listConversations overload (used by the visitor self-service path) is
unchanged, so a visitor's own access is not widened.
Refs matevip/mateclaw#340
Turn a single natural-language requirement into a ready-to-review
employee: the model proposes name, persona, runtime type and a
validated set of skills/tools/knowledge base, which the user confirms
or tweaks before the agent is created.
- backend: POST /api/v1/agents/generate builds a draft from the
workspace's real capability catalog; every suggested tool/skill/KB is
re-validated against the catalog so nothing hallucinated is offered
- frontend: 3-step wizard at /agents/create reusing the existing
create + binding endpoints; reusable capability picker shows selected
items as compact chips with an on-demand searchable catalog
Add an opt-in named-entity extraction pass so the wiki knowledge graph
captures fine-grained entities (people, organizations, locations, ...)
and their relations, not just page-level link relations.
- new tables mate_wiki_entity / _mention / _relation (h2/mysql/kingbase)
- structured LLM extraction per chunk with entity resolution
(normalized-key dedup + embedding near-merge), mention/relation
persistence and page linking via chunk citations
- per-KB opt-in toggle (off by default); async dispatch after embedding
- read API: entity list, KB graph, entity ego-graph, manual extract
- UI: entity-layer toggle in the graph view + KB config toggle
- replace inline fully-qualified class names with imports in WikiProcessingService
Closes#336
Always-on memory (structured user/feedback blocks, PROFILE.md, MEMORY.md) is injected into every system prompt but only ever grew, inflating per-turn context over time. This adds deterministic size control across all always-on sources:
- Injection budget: cap the always-on structured block by total chars and per-type entry count, keeping the most-recently-updated entries (LRU by Updated date) and disclosing how many were omitted
- Nightly consolidation: a dedicated scheduled pass merges duplicate/stale user & feedback entries via the LLM, preserving each entry's original Updated date; runs per owner bucket (shared + personal) with a per-run cap and a never-grow safety guard
- File ceilings: deterministic backstop truncates PROFILE.md / MEMORY.md at a section boundary when a rewrite overruns its budget
- Manual trigger endpoint for the consolidation maintenance task
All knobs under mate.memory.*; covered by unit tests.
- goal: continue (not skip) on max-iterations and evidence-insufficient turns.
A max-iterations turn grants a fresh iteration budget ("hard continuation"),
bounded per run and sized into the graph recursion ceiling, so a task too big
for one budget keeps going instead of stalling until the next user message.
- plan-execute: re-plan the remaining work on a step exception, and on a
signature-based stall (repeated failures / identical results / no usable
result) instead of advancing dependent steps with junk; bounded by a per-run
re-plan cap, with a graduated change-strategy nudge before the hard stop.
- plan-execute: auto-derive a goal from a genuine multi-step plan, seeding the
acceptance criteria from the plan steps, so the goal subsystem engages without
the model calling setGoal; broadcast goal_created so the UI hydrates.
- react: refund the iteration for setup-only rounds (load_skill / enable_tool)
so a tight budget is not eaten by the load-then-use two-step.
- ui: re-fetch the active goal when a turn finishes so a goal created or mutated
mid-conversation surfaces without depending on an SSE event.
- streaming: make retry backoff / total-time budget instance fields with a
test-only seam; clarify that the wall-clock budget (not max-retries) bounds a
sustained SERVER_ERROR loop to ~8 attempts, fixing the slow/flaky retry test.
The knowledge-base trust verification recorded wiki citations from every
non-readFile tool response by sniffing its JSON for a top-level title /
pages / chunks field. Tools like getGoalStatus return a top-level title,
which falsely populated the citation set and then forced [n] citations on
the final answer (otherwise flagged EVIDENCE_INSUFFICIENT). Gate citation
mining on the wiki_* tool name instead.
Likewise, the grounded answer contract (cite-or-refuse) was appended to
every ReasoningNode call unconditionally, degrading general agents that
have no knowledge base. Append it only when the agent has a wiki_* tool
bound, scoping the strict regime to KB-grounded scenarios.
Adds a regression test asserting a non-wiki tool with a top-level title
creates no wiki citations.
- rescan: keep the KB id as a string end to end so the 19-digit snowflake id
isn't truncated past Number.MAX_SAFE_INTEGER (rescan no longer 404s)
- lint: resolve [[...]] targets against page slugs AND titles like the viewer,
so a title reference to an existing page is no longer reported broken
- ingest: derive the slug deterministically from the title (no inconsistent
romanization), auto-recompute broken links once a KB finishes importing,
and reconcile dangling [[concept]] links — redirect to the covering page via
declared aliases, or demote to plain text when uncovered
- add the page aliases column migration for h2 / mysql / kingbase
Surface the connected database product as a subtle chip in the Dashboard
header. SystemHealthService now reports a database label on /system/health
(reused by the front-end — no extra request), derived from a new
DatabaseBootstrapRunner.getDatabaseLabel() that reads the JDBC product name
once and normalizes it to a canonical label (MySQL / MariaDB / PostgreSQL /
H2, and 人大金仓 for the KingbaseES family), collapsing driver version noise.
Add ErrorClassificationTest regression cases for the AI-gateway retry
hardening: 5xx-before-4xx ordering (a proxy 502 whose body says
"bad request" stays retryable), Chinese / numeric provider billing
patterns, and DNS / TLS infrastructure-fatal detection.
Fix the cert-trust pattern while adding its test: Java's ValidatorException
emits "PKIX path building failed" with an uppercase PKIX and the error
chain is not lower-cased, so the previous lowercase pattern never matched
— an untrusted/expired cert chain fell through to the retryable
SERVER_ERROR bucket and was retried in vain instead of failing over.
The disk fallback's catch block logged at debug, so a failed scan
silently dropped recovered files — reproducing the same 'bot can't see
the file' symptom the fallback was added to fix. Promote to warn with
the full stack trace, matching cacheRecentFile's logging.
openAiCompatibleClientBuilder() was creating a new java.net.http.HttpClient
per request. Each instance spawns a selector thread and connection pool that
are never closed, exhausting the OS thread limit under frequent model-test
calls (e.g. DeepSeek provider).
Elevate the HttpClient to a static singleton so all OpenAI-compatible
provider requests share one connection pool and one selector thread.
Closesmatevip/mateclaw#328
loadRecentFilesFromDisk now filters out files older than RECENT_FILE_TTL_MINUTES
(60 min) so the disk fallback matches the Caffeine cache TTL and does not inject
stale attachments into future conversations.
Testability refactoring:
- recentFileCache: private → package-private (tests can seed the cache directly)
- chatUploadsRoot: new package-private Path field (tests redirect to @TempDir)
- loadRecentFilesFromDisk: add (Path dir, long cutoffMs) package-private overload;
private (String) wrapper delegates to it
- injectRecentFiles: private → package-private
New test class FeishuRecentFileCacheTest (14 cases):
- loadRecentFilesFromDisk: non-existent dir, empty dir, fresh files sorted
newest-first, stale files excluded by TTL, mixed fresh+stale, >5 files capped,
timestamp-prefix stripping, MIME guessing from extension
- injectRecentFiles: Caffeine cache hit, cache-miss disk fallback, empty disk,
duplicate-path dedup, image vs file part typing, null textContent guard
Relates to #325
The per-chat recent file cache (Caffeine, 60 min TTL) is purely
in-memory. After a process restart, GC eviction, or TTL expiry the
cache is empty, but the staged copies under data/chat-uploads/ survive
on disk. A follow-up text message that should have seen the cached file
instead found nothing — the bot replied as if no file was ever sent.
Changes:
- injectRecentFiles(): fall back to scanning data/chat-uploads/{id}/
when the Caffeine cache misses, sorted by last-modified time, capped
at RECENT_FILE_MAX_PER_CHAT (5).
- cacheRecentFile(): promote catch log from debug → warn with full
stack trace so silent download failures are visible in production
logs. Add entry-level info log for correlation.
- New helper loadRecentFilesFromDisk() + guessContentType().
Closes#325
Relates to #201
The KingbaseES change removed usingDbTime() unconditionally, which made
every deployment (MySQL/H2/PostgreSQL) fall back to app-server time for
distributed lock timing — reintroducing node clock-drift risk in
multi-instance setups. Re-enable usingDbTime() for databases in ShedLock's
built-in dialect map and skip it only for KingbaseES, which is not covered
and would otherwise throw at lock acquisition.
Add KingbaseES support as an opt-in profile: dedicated migration tree, bilingual seed data, runtime DbType detection (KINGBASE_ES / POSTGRE_SQL), and JDBC URL handling in the datasource manager.
* feat(wiki): unify raw materials & source watcher into a Sources tab with per-KB auto-sync
The raw-material directory scan and the Advanced "source watcher" sub-tab were
the same engine (same kb.sourceDirectory, same WikiDirectoryScanService) split
across two surfaces with two editable directory inputs. Merge them into one
"Sources" tab (upload / paste / directory manual scan + auto-sync toggle +
the raw-material list) and drop the watcher sub-tab from Advanced.
Auto-sync is now per-KB opt-in: a new watcher_enabled column (V146) gates the
periodic scan per knowledge base. The server-global mate.wiki.watcher-enabled
stays as an ops master switch — a KB is auto-scanned only when both are on
(AND). Manual scans are unaffected. Scan interval stays global for now
(tracked separately).
Closesmatevip/mateclaw#314
* docs(wiki): document source-watcher global switch env vars
Expose MATE_WIKI_WATCHER_ENABLED / MATE_WIKI_WATCHER_INTERVAL_MS as
explicit placeholders in application-mysql.yml, .env.example and
docker-compose.yml, mirroring MATE_WIKI_ALLOWED_SOURCE_ROOTS. Notes the
AND semantics (global ops gate + per-KB toggle) so operators know the
global switch alone is not sufficient.
- Fail closed to a global fallback sandbox root when a conversation has no
per-workspace base path, instead of leaving file/shell tools unconstrained
- Refuse shell commands that delete the workspace root directory itself
- Block workspace-boundary escapes at the policy layer before the approval
prompt, not only at execution time
- Approval bar now shows the actual command / target path being approved
Closes#289 — after an MCP server (re)connects, chat queries kept replying
"from memory" instead of calling MCP tools.
Root cause: agents snapshot their tool set at build time and are cached in
AgentService.agentInstances, but MCP server lifecycle changes never
invalidated that cache (unlike model-config / tool-guard changes which do).
A stale, tool-less agent graph survived until process restart.
Changes:
- Add McpServerChangedEvent; McpServerService publishes it on connect /
disconnect / reconnect / delete / (re)connect-failure / batch refresh /
startup init. AgentService listens and calls refreshAllAgents(), so the
next turn rebuilds against the live MCP tool set. Also closes the boot
race where the web server accepts requests before the @Order(200) MCP
init runner finishes.
- Make create/update/toggle connect asynchronously on a dedicated pool
("mcp-connect") so a slow/unreachable server can no longer freeze the
admin request; status returns immediately as "connecting".
- UI: render the new "connecting" status (pulsing amber dot), show a
friendly "connecting in background" toast, and poll until the status
settles (window widened to ~40s to outlast the default connect timeout).
- UI: MCP config modal no longer closes on outside/backdrop click — only
the × and Cancel buttons close it, so an accidental click can't discard
unsaved config.
Verified E2E: ckjia-shopping (参考价) MCP server connected at runtime with
no backend restart; the cached 通用助手 agent immediately enabled and called
ckjia_shopping_recommend, returning real product cards.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The webchat conversationId (webchat:<key8>:<visitorId>[:<sessionId>]) and the
derived username (webchat:<visitorId>) are written to VARCHAR(64) columns, but
visitorId had no validation and sessionId allows 64 chars — so a long visitorId,
or a legitimate 64-char sessionId, overflows the column and the getOrCreateConversation
INSERT throws (500 on /stream). Validate visitorId (charset + blank->UUID) and
fold the variable part into a stable hash when the derived id/username would
exceed 64 chars, keeping short ids byte-identical (backward compatible). Also
make listSessions filter on exact owner username, not just the conversationId
prefix, so system-owned rows can never leak via a crafted visitorId. Adds
boundary regression tests.
Add per-visitor session management for the WebChat Web/API access mode:
list a visitor's conversation threads, fetch a thread's messages, and
delete a thread.
Authorization: visitorId is a client-asserted request param, so it cannot
be trusted on its own — deriving conversationId from it and then checking
ownership against it is tautological (any caller passes). Instead, /stream
issues a per-visitor token = HMAC-SHA256(jwtSecret, channelId:visitorId),
returned in the meta event; the management endpoints require it back via
the X-MC-Visitor-Token header and verify it in constant time. The signing
secret is server-only (unlike the public channel API key) and the channelId
in the payload makes tokens non-portable across channels.
Includes regression tests for token issuance/verification semantics
(forged visitorId rejected, cross-visitor and cross-channel tokens rejected,
tampered tokens rejected).
The WebChat stream endpoint resolves agentId only when the
(visitorId + sessionId) conversation is first created; later requests
with a different agentId reuse the existing conversation's agent and
silently ignore the new value. Document this on WebChatRequest.agentId
so integrators know to use a new sessionId to reach another agent.
The vision/video sidecar dropdown filtered candidates through the built-in
capability heuristics, so provider-compatible models whose custom names match
no known prefix (and carry no declared modalities) were hidden and could not be
selected as a sidecar — even when they natively support the modality.
- listByType now returns every enabled chat model, annotating each row with a
transient modalityCapable flag and sorting known-capable rows first, instead
of hard-filtering recognized models only.
- MultimodalRouter honours an explicitly configured sidecar model instead of
dropping it when the heuristics don't recognize it; a wrong pick degrades
gracefully through the caption path rather than silently disabling routing.
- ModelPicker gains an optional capability badge; the sidecar UI tags
recognized vision models while keeping every enabled model selectable.
The mention alias-learning fed every identifier of every mention in a
delivery into the per-chat alias cache. A single delivery of "@bot @alice"
matched the bot by its global id and then learned alice's openId as a bot
alias, so every later "@alice" message was misdetected as @bot and the agent
replied to messages never addressed to it.
Only single-mention deliveries are unambiguous bot identities, so restrict
alias learning to them — a multi-mention delivery mixes the bot with
co-mentioned humans, and Feishu's dual-delivery alias form is itself a single
mention, so this is safe and keeps the learning feature working. Also cap the
per-chat alias set size. Adds a [bot, human] co-mention regression test.
Rename the webchat channel from "embed widget" to "Web / API access" (key
unchanged, docs/i18n only) and extend the backend SSE endpoint for pure
backend integration:
- WebChatRequest gains optional agentId (route one Key to multiple agents;
rejected unless the agent shares the channel's workspace) and sessionId
(one visitor, multiple isolated threads).
- sessionId is validated ([A-Za-z0-9_-]{1,64}) and only composed into the
server-derived conversationId — raw conversationIds are never accepted, so
the key+visitor namespace still bounds every thread.
- A `meta` SSE event echoes the effective sessionId/conversationId at stream
start so callers can persist and re-address a thread.
- Memory stays attributed per visitor (api:<visitorId>), shared across that
visitor's sessions.
All new fields are optional; omitting them reproduces the prior behaviour
byte-for-byte. Refs matevip/mateclaw#295.
ChannelMessageEventBridge.onChannelMessage() ran synchronously on the Lark
SDK WebSocket dispatch thread; when the DB pool was saturated its ingest
query blocked that thread and subsequent messages were silently dropped.
- @Async moves trigger ingest onto the (vthread + SecurityContext-propagating)
async executor, freeing the WS dispatch thread.
- Add a 10s timeout to the refreshTenantAccessToken() HTTP request, which
previously had none.
Scope narrowed per review to only fix#208: the @mention alias learning and
session-id changes are dropped (to be raised as separate PRs), and dev's
existing message dedup is left untouched.
Closes#208
Add an execute_code built-in tool that runs python/bash/node code the agent
writes on the fly, so a documentation-only skill (a SKILL.md with no bundled
scripts) can be acted on. Scoped runs inject the skill's secrets and run in
the skill directory; otherwise a private scratch directory is used. Host
secret env vars are scrubbed from the subprocess. execute_code is an
agent-wide capability, registered in the tool catalog (V143), and screened
by the tool guard with a dedicated set of destructive-pattern rules.
Tests cover python/bash/node execution, scratch-dir fallback, env scrubbing,
argument decoding, and guard gating.
- WikiPageTypeProfile: normalise pageType keys to lowercase on set, so a
user-authored profile with an uppercase key still matches the
case-insensitive hasPageType/get lookups.
- WikiDirectoryScanService: normalise the symlink-resolved glob base to
forward slashes so directory-scan globs work on Windows paths.
- Agents roster tag filter: keep selected tags that no longer exist on any
agent visible and deselectable (and show the filter bar when only such
orphan selections remain) instead of silently filtering with no way to clear.
A second POST to /reclassify on the same KB spawned an independent pass over
the same pages, doubling LLM spend and racing the first pass's page-type
writes. Add a per-KB in-flight guard that rejects a concurrent run with a
friendly message (409 via R.fail rather than a generic 500), released in a
finally once the async pass completes. Also count and broadcast per-page
failures so an all-failing run is visible instead of reporting changed=0, and
type the api modelId param as string|number per the snowflake ID convention.
The resilient connect() override started the child process into a local
variable and never set the parent's private process field, so the parent's
closeGracefully() logged "Process not started" and left the child running on
every reconnect/disable. Retain the started process and override
closeGracefully() to destroy it and interrupt the spawned I/O threads.
Also make the inboundSink/errorSink reflection fail loud (the transport is
useless without them — a silent null yielded a connected transport that timed
out on every call), force UTF-8 on the stdio reader/writer, honour a
cooperative closing flag in the reader loops, and drop duplicate PATH entries.
Add a backfill path so pages created before a KB's pageType profile changed
can be migrated into newly-added types. A per-page classify-only LLM call
(title + summary in, single page_type out) is normalised through the profile
and written back via a partial update that never touches page content.
Exposed as POST /knowledge-bases/{id}/reclassify (admin) and a "re-classify
existing pages" action in the Wiki advanced panel.
Wiki page classification was only profile-aware in the main ingest pipeline.
Transformation outputs hard-coded "synthesis", agent-created pages were left
untyped, and the frontend hard-coded the built-in ten types for ordering,
colouring and labels — so custom/synthesis types sank to the bottom, rendered
grey and showed raw keys.
Backend:
- Add nullable target_page_type column to mate_wiki_transformation (V142,
mysql + h2) plus the entity field and CRUD normalization (blank = use
profile fallbackType; membership validated at save time, not edit time).
- Route transformation single-run + KB-aggregate page saves through
WikiPageTypeProfileService.normalizePageType so output joins the KB
classification; agent wiki_create_page now lands on the profile fallbackType
instead of an untyped page.
Frontend:
- Load + parse the KB pageType profile into the wiki store (order, labels,
fallbackType) on KB select / refresh.
- New useWikiPageType composable: profile-driven label (3-tier fallback) and
colour (built-in fixed + deterministic hash palette for custom types).
- Sidebar grouping order, graph colouring, node panel, graph filter and the
page header badge now follow the profile; transformation editor gains a
target-type dropdown sourced from the profile when output target is a page.
Refs #292
Add 5-arg buildContextMessage overload that emits [system-context] Model:
for every origin (web/cron/IM). Legacy 3/4-arg overloads delegate to the
new one with null model args, keeping their output byte-identical.
Also fix pre-existing FeishuMentionTest compile error caused by removed
mentionMatchesAnyAlias/collectMentionIdentifiers methods.
A silent (no-op) cron run still makes a full LLM call, but the marker
message was persisted via the token-free saveMessage overload, so the
settings-page Token total (which aggregates MessageEntity token columns)
under-counted cron spend by exactly the silent runs.
Carry chatResult's prompt/completion tokens onto the marker message,
matching the non-silent branch. Closes#284.
The base directory is canonicalized via toRealPath before walking, so the
walked files carry the symlink-resolved prefix. The PathMatcher was built
from the literal pattern, so a symlinked base never matched and files were
silently dropped. Rebuild the glob against the resolved scan root, escaping
glob metacharacters in the base so a real directory name containing */?/{}/[]
is treated literally.
The upstream StdioClientTransport breaks out of its inbound read loop on
any JSON parse error, permanently killing the reader thread. Some MCP
servers write non-JSON debug output to stdout (e.g.
"=== Document parser messages ==="), which triggers this and causes all
subsequent valid JSON-RPC responses to be lost → 30s timeout → agent stuck.
Override connect() in CwdAwareStdioClientTransport to skip non-JSON lines
(log at DEBUG) instead of breaking, keeping the inbound thread alive.
Closes#226
The #254 fix changed resolveConventionPath to {name}-{hashCode} and folded
hyphens to underscores, which re-pathed every existing skill (browser-cdp ->
browser_cdp-<hash>) with no migration, orphaning already-created workspaces and
breaking SkillWorkspaceManagerApplyBundleTest. Drop the hash suffix and keep
hyphens: the bare Unicode-preserving sanitized name already prevents the
non-ASCII collision (distinct CJK names map to distinct dirs) and leaves ASCII
kebab-case paths identical to the legacy scheme. Add path regression tests.
Skills with non-ASCII (e.g. Chinese) names collapsed to underscores in the workspace path, so two such skills resolved to the same directory and overwrote each other. Preserve Unicode letters/digits when sanitizing the path so distinct names map to distinct directories. Also write SKILL.md with CREATE_NEW to avoid a TOCTOU race on concurrent uploads, and mount the skills workspace as a named Docker volume so packages survive container restarts.
Closes#254
updateTextContentFromScan / updateBinaryFileFromScan are only reached via
self-invocation from the ingest* methods, so the proxy-based @Transactional
never applied. Each runs a single atomic updateById; remove the misleading
annotation and document why.
Directory-scan ingestion deduped only by content hash, so when a file at a known path changed, the new hash missed the existing raw and a second row was inserted for the same source_path — both rows then generated wiki pages, accumulating duplicates. Make source path the primary dedup key: same path + same hash skips, same path + changed hash updates the existing raw in place (reset to pending, re-process), falling back to the content-hash check only for genuine copies at new paths. Reprocessing reuses the same rawId, so deleteExclusiveBySourceRawId cleans the old pages before regeneration — no duplicate rows and no duplicate pages. findBySourcePath gains LIMIT 1 to tolerate pre-existing duplicates; docs/fix-duplicate-raws.sql remediates existing data.
Closes#271
Gate MarkdownNormalizer behind mate.agent.markdown-normalize-enabled (default
true) so operators can disable the rewrite verbatim if a normalization edge
case ever mangles a legitimate answer.
LLMs routinely emit malformed Markdown (missing heading spaces, glued `---`, unaligned table pipes) that prompt rules cannot reliably prevent. Add a zero-token, regex-only MarkdownNormalizer applied on the FinalAnswerNode convergence path before persistence / channel delivery. It is code-fence aware, idempotent, and conservative (em-dash `---`, `#5`-style refs, stray prose pipes are left untouched). RETURN_DIRECT verbatim output and approval-wait paths return earlier and are unaffected.
Closes#274
Same-message attachment reads failed on Feishu: the content part carried the sandbox-external ~/.mateclaw/media/ path, so read_file/extract_document_text were rejected by WorkspacePathGuard and ChatUploadResolver's basename fallback missed (media names {messageId}_{key} vs chat-uploads {millis}_{fileName}). cacheRecentFile already copies the attachment into the per-conversation data/chat-uploads/ dir; return that absolute path and stamp it onto the current message's image/file/audio/media parts so the path surfaced to the LLM is resolver-reachable. Reuses the existing copy — no extra I/O, no new state. Rich-text post multi-image and other channels sharing the media dir are noted as follow-ups.
Closes#278
Allow knowledge base source paths to be configured as a newline-separated
list of absolute paths or glob patterns rather than a single directory.
- Each non-blank, non-# line is treated as one path or glob pattern
- Plain paths (no wildcards) retain the existing recursive-scan behaviour
filtered by SUPPORTED_EXTENSIONS
- Glob patterns (e.g. /data/ocr/**/*.txt) walk from the fixed-prefix base
and apply Java's PathMatcher against each candidate's absolute path
- Patterns whose filename segment explicitly specifies an extension
(*.txt, *.{xlsx,csv}) skip the SUPPORTED_EXTENSIONS secondary filter,
respecting the user's explicit choice (key for OCR pipelines that
produce .txt output and should ignore the original PDF scans)
- Candidates collected across multiple patterns are deduplicated by
resolved absolute path so overlapping patterns don't double-count
- Symlink-escape check uses each pattern's own validated scan root
- parseSourcePatterns / extractBasePath moved into WikiSourcePathValidator
to eliminate a static circular reference between the two services
- Frontend watcher panel: single-line <input> replaced with <textarea>
supporting multiline editing; i18n updated with example patterns
- No DB schema change; fully backward-compatible with existing single-path
configs stored in sourceDirectory
Closes #(pending issue)
finishRunAndPublish updated the run row with status and finished_at but dropped the LLM token usage, so mate_cron_job_run.token_usage stayed NULL and the scheduler history always showed 0. Write the prompt+completion token total (already computed for the assistant message row) to the run row, guarded so non-LLM paths (reminder direct-push with a null ChatResult) leave the column untouched.
Closes#262
The skill meta-tools (listAvailableSkills, readSkillFile, listSkillFiles, load_skill, runSkillScript) queried the full skill catalog without checking the calling agent's bindings, so an agent scoped to a subset of skills could still read, load, or execute any skill via direct tool calls. Resolve the agent's bound skill ids from the tool context and filter/deny accordingly: a null binding set means no restriction (backward compatible), a non-null set (including empty) restricts access to that set — matching the system-prompt catalog filtering.
Closes#264
Surface directory-scan failures to the user via toast and render ScanResult.errors[]; expose MATE_WIKI_ALLOWED_SOURCE_ROOTS as a Docker env entry with blank-entry filtering in the path validator; set C.UTF-8 locale in the runtime image so non-ASCII file names decode correctly during scans.
Fixes#259
Add a single global-proxy switch that routes the backend's outbound traffic
through a configured HTTP/HTTPS/SOCKS proxy, for deployments that cannot reach
overseas APIs directly or must use a unified egress.
- ProxyManager installs the proxy via a default ProxySelector (honored by
java.net.http and HttpURLConnection), the proxy system properties, and a
--proxy-server arg for the browser tool; restores direct egress when
disabled. One switch covers LLM, web search, media generation, channels,
MCP and the browser.
- SOCKS applies to the HttpURLConnection-based egress only; the java.net.http
LLM/streaming path uses an HTTP proxy, and the UI states this.
- New Settings -> Network Proxy page: enable toggle, address, bypass list,
test-connection, and a coverage summary. Config stored as key/value in
mate_system_setting (no migration).
refs #109
Streaming chat ran render tools on an async thread with no bound request,
so download links lost their host and arrived without a domain. Resolve the
host on the request thread and carry it through ChatOrigin/ToolContext;
falls back to a configurable public-base-url, then a relative path.
Agents now have a per-agent primary wiki KB stored on
mate_agent.primary_kb_id. KBs remain workspace-shared — selecting one in
the agent editor only chooses the default wiki target for that agent, it
does not change the KB's ownership or visibility.
Backend
- AgentEntity: add primary_kb_id field (FieldStrategy.ALWAYS so the UI
can clear it back to "no primary")
- AgentController#update: switch body to Map<String, Object> so we can
tell "field missing" apart from "explicit null" via containsKey, then
convertValue back to AgentEntity
- WikiKnowledgeBaseService:
- new resolvePrimaryKb(agentId): prefers agent.primary_kb_id when it
points to a workspace-visible KB; falls back to legacy
kb.agent_id marker, then to most-recently-updated workspace KB
- listByAgentId now returns the full workspace set (KBs are
workspace-shared under the new model)
- update(id, name, description) no longer touches agent_id
- WikiController: new GET /knowledge-bases/bindable for the UI picker;
PUT /knowledge-bases/{id} no longer reads agentId
- WikiKnowledgeBaseEntity: add FieldStrategy.ALWAYS on embeddingModelId
and configContent so explicit nulls actually unbind/clear instead of
being silently skipped by MyBatis-Plus's NOT_NULL default
- Migrations V129 (H2 + MySQL): add primary_kb_id column + index, backfill
from legacy kb.agent_id, MySQL uses INFORMATION_SCHEMA guard +
PREPARE/EXECUTE for idempotency
- WikiKnowledgeBaseServiceTest: 13 cases, all passing
Frontend
- Agents.vue: new "Knowledge Base" tab, radio-select bindable KBs
- API: listBindableKBs() + Agent.primaryKbId typed string | number | null
- IDs handled as strings throughout (Snowflake-safe)
- i18n keys for the new tab in zh-CN and en-US
The previous private-repo support inlined the access token into the
clone URL and then logged that URL on success — leaking the token to
log files, container stdout, and any IOException thrown when the clone
failed. The token also appeared in the process command line, visible
to anyone with shell access via `ps`.
Switch to git's GIT_CONFIG_COUNT/KEY/VALUE environment variables, which
inject `http.extraHeader: Authorization: Bearer <token>` into the child
process without ever touching argv or the repo URL. The URL stays
pristine, so the existing INFO log and error message are safe.
Other changes:
- Resolve token from `mateclaw.skill.github-token` property first, then
fall back to GITHUB_TOKEN env var. Keeps the original deployment
contract while letting admins manage the credential via configuration.
- Tighten the host check (prefix match on `https://github.com/` etc.)
so a crafted URL like `https://evil.com/?u=github.com/...` cannot
trick the fetcher into forwarding the token to a third party.
- Set GIT_TERMINAL_PROMPT=0 so a bad token fails fast instead of
blocking on an interactive password prompt.
stopWebSocket() only nullified the wsClient reference without calling
disconnect() on the SDK client. This left the old WebSocket connection's
pingLoop thread and ExecutorService running, leaking file descriptors
and threads on each reconnect. Over time, accumulated leaks prevented
new connections from being established, causing the Feishu channel to
silently stop receiving messages.
Fix: use reflection to access the SDK's protected `conn` field and call
close(1000) on the OkHttp WebSocket, triggering the SDK's onClosed →
disconnect() cleanup chain.
Note: oapi-sdk 2.7.1 adds a public close() method that would make this
reflection unnecessary. Consider upgrading as a follow-up.
Closes#220
IM channels (Feishu, DingTalk, WeCom, etc.) and the WebChat widget were
calling saveMessage without token usage parameters, causing promptTokens
and completionTokens to default to 0. This made the Token Statistics
module report significantly lower numbers than actual usage.
Root cause: the _usage_final event (containing promptTokens /
completionTokens) emitted by the agent graph at stream end was not being
captured in these paths, unlike ChatController's StreamAccumulator which
already handles it correctly.
Fix: capture _usage_final events in doOnNext handlers for:
- ChannelMessageRouter sync path (non-streaming IM adapters)
- ChannelMessageRouter streaming path (DingTalk, etc.)
- WebChatController SSE stream
Refs #214 (remaining String-API paths covered by follow-up).
Some OpenAI-compatible providers (LM Studio's built-in server, certain
strict-mode vLLM / SGLang deployments) reject 400 "System message must
be at the beginning" when SystemMessages appear after user / assistant
/ tool messages. The reasoning loop currently emits four SystemMessage
segments — main prompt at index 0, skill catalog inserted at index 1,
progress-ledger snapshot and stale-reminder appended at the end of
nonHistoryPrefix after the runtime-context UserMessage. The latter two
violate the strict shape, so conversations on LM Studio 400 on the
first turn (reported in #218).
Add MessageNormalizer: collects every SystemMessage in the outbound
prompt regardless of position, joins their text with a blank-line
separator, and emits a single SystemMessage at index 0. Non-system
messages keep their relative order, so AssistantMessage(tool_calls) ↔
ToolResponseMessage adjacency is preserved verbatim (required by strict
pair validators).
Wire it into doStreamCall as the first pre-egress step so every node
(reasoning, step-execution, summarizing, plan-generation, limit-exceeded)
inherits the fix without per-node changes, and any future node that
emits multiple SystemMessages stays compliant.
The transformation is semantically equivalent on permissive providers
(OpenAI, DashScope, Ollama, DeepSeek, Kimi, Doubao, GLM) — the merged
token sequence matches what they would have seen across N SystemMessages
— and safe on non-OpenAI protocols (Anthropic, Vertex / Gemini), whose
adapters already extract SystemMessages into a top-level system field
and receive an identical payload.
Kill switch: -Dmateclaw.llm.message-normalizer.enabled=false reverts to
the prior behavior for emergency rollback.
Tests: 11 unit tests on MessageNormalizer cover empty / no-system /
canonical / mid-list / tail / blanks / tool-pair preservation / Prompt
option-reference preservation / kill switch. 1 wiring test pins the
call site in doStreamCall. Full vip.mate.agent.** suite (504 tests)
stays green.
Closes#218.
1. Relative parent traversal in shell commands (HIGH)
validateShellCommand only scanned absolute path tokens, so commands
like `cat ../mateclaw/CLAUDE.md`, `cd .. && cat foo`, or
`ln -sf ../bar breakout` had no absolute path to trip the check.
From a workspace cwd that's a real escape — `..` segments resolve
against the JVM cwd at file-tool time and reach anywhere the user
can read.
Add a second pass: any token containing `..` as a path segment is
resolved against the workspace root via root.resolve(token).
normalize(); reject when the result falls outside. In-workspace
traversal like `subdir/../sibling` normalizes back inside and
passes. Identifiers without slashes (e.g. version strings with
`1.2..3`) are not treated as paths.
2. Shell validation and process working directory used different
context sources (MEDIUM)
execute_shell_command validated with the explicit ToolContext, but
buildShellProcess called WorkspacePathGuard.getWorkingDirectory()
(no-arg), which only sees the ThreadLocal fallback. Today the
ToolExecutionExecutor sets both so the discrepancy is latent, but
a future direct Spring AI invocation passing only ToolContext would
validate against one basePath and exec against another. Thread ctx
through buildShellProcess and call getWorkingDirectory(ctx) so
validation and execution agree on a single source of truth.
3. Absolute agent override could disable workspace scoping (MEDIUM)
resolveAgentBasePath accepted an absolute override verbatim, even
when it pointed outside the workspace root. An admin (or any
account with agent-edit permission) could set workspaceBasePath="/"
or another team's repo and bypass workspace boundaries entirely.
When a workspace has its own basePath, require absolute overrides
to sit underneath it. The caller in build() catches the rejection,
logs WARN, and falls back to the workspace basePath so chat stays
available rather than crashing agent construction. When the
workspace has no basePath there's no boundary to enforce, so legacy
behavior is preserved.
Test coverage: WorkspacePathGuardShellTest grows from 17 to 23 (six
new cases for `cd ..`, relative parent traversal, relative symlink
escape, deeper traversal, in-workspace normalization, and the
identifier false-positive guard). AgentGraphBuilderBasePathResolutionTest
grows from 7 to 10 (three new cases for in-workspace absolute,
outside-workspace absolute rejection, and no-workspace legacy
behavior). All 45 sandbox-area tests pass with no regressions.
* feat(agent): optional agent-level workspace basePath override
Add workspaceBasePath field to AgentEntity that optionally overrides
the workspace-level basePath. When set, the agent uses its own directory;
when null, it inherits the workspace's basePath (existing behavior).
- AgentEntity: new workspaceBasePath field with ALWAYS update strategy
- AgentGraphBuilder: agent-level override takes priority over workspace
- Flyway migration V121 for H2 and MySQL
- UI: form input in basic tab with i18n (zh-CN, en-US)
* fix(agent): rename migration V121→V125 to avoid Flyway conflict with upstream
Upstream already has V121__tool_disclosure_tier.sql. Rename our
migration to V125 (next available after V124).
* fix(agent): make MySQL V125 migration idempotent
Use INFORMATION_SCHEMA check before ADD COLUMN to avoid
"Duplicate column name" error on re-deploy.
* feat(tool): add send_file tool for sending existing server files as IM attachments
Adds a new built-in tool that reads a file from the server and stashes it
in GeneratedFileCache so the channel adapter (Feishu, DingTalk, etc.)
automatically sends it as a native attachment. This fills the gap where
agents had no way to send existing server files to users — ReadFileTool
only reads text, and render tools only generate new files.
- New SendFileTool with path validation, MIME detection, 20MB limit
- Added "send_file" to tool allowlist in AgentBindingService
- Added i18n error messages (zh-CN + en-US)
* fix(tool): send_file returns URL in scrubber-detectable format
The previous JSON return format caused the LLM to reply with just
"status: sent" without echoing the /api/v1/files/generated/{id} URL.
GeneratedFileScrubber only scans the LLM's final text output, so the
file was never delivered as a native attachment.
Changed to match GeneratedFileLink's format: returns a markdown link
with explicit instructions for the LLM to echo the URL verbatim.
The Lark SDK throws HandlerNotFoundException for any event type without
a registered handler. This exception is caught internally by the SDK's
WebSocket client, which then sends a 500 response to the Feishu server.
The server may close the connection as a result, and the exception is
swallowed — never reaching the application layer.
Added empty handlers for all remaining IM event types:
- P2MessageReadV1 (read receipts)
- P2MessageRecalledV1 (message recall)
- P2ChatMemberBotDeletedV1 (bot removed from chat)
- P2ChatMemberUserAddedV1 / UserDeletedV1 / UserWithdrawnV1
- P2ChatUpdatedV1 (chat info update)
- P2ChatDisbandedV1 (chat disbanded)
- P2ChatAccessEventBotP2pChatEnteredV1 (bot entered p2p chat)
Also added explicit logback config for com.lark.oapi at WARN level
to ensure SDK internal errors are not silently filtered.
Refs: larksuite/oapi-sdk-java#185
Some providers (notably SiliconFlow) return "network connection error" in the response body when their backend is overloaded or the upstream model connection is disrupted. classifyError() had no pattern for this string, so it fell through to UNKNOWN (non-retryable), surfacing the raw error to the user on the first failure instead of running the exponential-backoff recovery. Adds the pattern to the SERVER_ERROR classifier and a friendly message mapping in extractUserFriendlyError(); bumps MAX_RETRIES from 5 to 10 so sustained wiki batch load can ride out provider flaps without surfacing an error to the channel user.
Closes#178
Closes#174
Model identifiers like 'Qwen/Qwen3-Embedding-8B' or
'Pro/deepseek-ai/DeepSeek-V3' carry forward slashes that Spring MVC
decodes from %2F before path matching, so even with the frontend's
encodeURIComponent the request never reaches the handler and 404s out.
The two affected endpoints take modelId as a request param instead:
DELETE /{providerId}/models/{modelId} -> DELETE /{providerId}/models?modelId=...
POST /{providerId}/models/{modelId}/test -> POST /{providerId}/models/test?modelId=...
modelApi.removeProviderModel / testModel in the UI follow suit, passing
the id via axios params so axios handles the URL encoding consistently.
providerId stays as a path variable — provider ids are kebab-case and
never contain slashes.
Closes#175
ModelConfigController.testEmbedding() previously caught and stringified
the exception's getMessage() into the response body without writing
anything to the server log. Operators investigating an Embedding test
failure saw only the truncated client-side message — root causes like
the DashScope-native vs OpenAI-compat routing bug (#166) or the
requireApiKey gap (#167) were invisible server-side.
Add @Slf4j to the controller and log.error the full stack trace
alongside the failing modelId, so future Embedding test regressions are
diagnosable from the server log without redeploying with debug
breakpoints.
