Add the user-facing and API-reference docs that explain how an employee
can declare a primary knowledge base, what the runtime fallback chain
looks like, and how the binding is driven from the API.
agents.md (zh + en)
- New section "Knowledge base binding (per-agent primary KB)" right after
the tool-binding section, with a 1.5.0 New In badge
- Lays out the design intent explicitly: KBs stay workspace-shared, the
binding only chooses a default target, multiple agents may pick the
same KB as primary
- Documents the runtime resolution order used by wiki tools: explicit
kbName/kbId, agent.primaryKbId, most-recently-updated workspace KB
- Migration note about the legacy kb.agent_id to agent.primary_kb_id
backfill and the visibility change for anyone who relied on the old
one-to-one isolation
api.md (zh + en)
- Under Agents: document the primaryKbId field with the three-state PUT
semantics (omit / null / value) and example curl calls
- Under LLM Wiki: document GET /api/v1/wiki/knowledge-bases/bindable and
the explicit warning that PUT /api/v1/wiki/knowledge-bases/{id} no
longer processes the agentId field
PR #237 introduced V129__agent_primary_kb.sql while dev also has
V129__wiki_page_broken_links.sql shipped from the broken-link lint work.
Flyway rejects duplicate version numbers at startup, so the agent
primary_kb migration moves to V130 across both H2 and MySQL dialects.
No content change beyond the rename — the column add, index, and
backfill SQL are identical to the V129 originals from #237.
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.
Closes#169
ModelConfigService.validateModel() flagged a duplicate when re-adding a
manually-typed (provider, modelName) pair that happened to match a row
with deleted=1 in mate_model_config. The user-visible symptom: adding
'dashscope/qwen3-plus' fails with 'model identifier already exists',
yet the management page shows no such model.
The project itself runs hard-delete via deleteById(), so the user-facing
delete path doesn't create deleted=1 rows. The stale rows come from
schema migrations (V44, V81) that intentionally tombstone bogus catalog
entries — for instance V81 sets deleted=1 on the non-existent
'qwen3-plus' (id=1000000172) so it stays out of routing but preserves
the id for audit. ModelConfigEntity has no @TableLogic, and the project
has no global logic-delete-field config, so LambdaQueryWrapper queries
do not auto-append the deleted filter; the migration tombstones leak
into the validate-model query.
Add an explicit .eq(getDeleted, 0) to the uniqueness check so migration
tombstones don't block legitimate re-adds.
Follow-up: several other queries in ModelConfigService share the same
oversight (list/get methods), and a future migration could drop the
tombstones entirely to align with the V20 hard-delete posture.
Closes#168
The native DashScope provider exposes both chat and embedding models, but
DASHSCOPE_NATIVE_ALLOW_PREFIXES only listed chat families
(qwen-/qwen2-/qwen3-/deepseek-/baichuan/yi-/llama). When a user manually
added text-embedding-v1/v2/v3/v4 to the dashscope provider,
assertModelIdAcceptable() rejected the id because no allow prefix matched.
Add 'text-embedding-' to the allow-list and broaden the doc comment from
"native chat protocol" to "native protocol (chat or embedding)" so the
intent is clear.
Discovery probing is chat-based and will still mark embedding entries
probeOk=false; surfacing them as discoverable embedding suggestions is a
separate follow-up.
Closes#167
EmbeddingModelFactory.buildOpenAi() hard-failed on any provider whose API
key was empty or unusable, so keyless providers like Ollama and OpenCode
(declared with requireApiKey=false) could pass the chat connectivity test
but bounce when the same provider's embedding model was tested.
Mirror the chat path in OpenAiCompatibleChatModelBuilder.buildOpenAiApi:
- If requireApiKey is not explicitly false, an unusable key still throws.
- If requireApiKey == false, the key check is skipped and an empty string
is passed to OpenAiApi.builder() so no Authorization: Bearer header is
attached to the outgoing request.
Closes#166
EmbeddingModelFactory used EmbeddingProtocol.fromProviderId() to pick the
embedding protocol, which substring-matches 'dashscope' / 'qwen' / 'aliyun'
in the providerId. The dashscope-compat provider carries 'dashscope' in its
id but runs in OpenAI compatible mode (chatModel='OpenAIChatModel',
baseUrl='https://dashscope.aliyuncs.com/compatible-mode/v1'). Routing it to
DASHSCOPE_EMBEDDING made DashScopeApi build its native path against the
compat base, producing 404s on every embedding call.
Switch to the chatModel column instead — the same signal ModelProtocol
.fromChatModel() uses for the chat path. chatModel='DashScopeChatModel'
takes the native protocol; everything else (including dashscope-compat)
takes OpenAI-compatible.
EmbeddingProtocol.fromProviderId() is retained for reference but is no
longer called; future callers should follow the chatModel pattern.
Closes#162
require_mention=true previously degraded to a no-op when botPrefix was unset:
shouldProcess() returned true for all messages and checkAccess() fell through
unconditionally, so any group message would be answered — including ones where
the @mention targeted another user.
FeishuChannelAdapter now consults the Feishu SDK's mentions field directly:
- WebSocket: read EventMessage.getMentions(); webhook: read mentions[] from the
JSON payload. In both paths each mention's id.open_id is compared against the
bot's own open_id.
- Bot open_id is fetched lazily via /open-apis/bot/v3/info and cached on the
adapter instance. If the call fails the message is allowed through, matching
the previous behaviour.
- The require_mention gate is applied at the top of handleFeishuMessage so 1:1
chats are unaffected.
Tests: 15 unit cases covering null/empty inputs, bot mentioned, only-other
mentioned, bot among multiple mentions, and malformed payloads.
Register a no-op handler for the bot-added-to-chat event on the Feishu WebSocket EventDispatcher. Without it, adding the bot to a group chat raises HandlerNotFoundException and drops the long connection. Mirrors the existing reaction-event handlers. Fixes#153.
The Feishu SDK EventDispatcher had no handler registered for im.message.reaction.created_v1 / deleted_v1, so adding or removing an emoji reaction raised HandlerNotFoundException and logged an ERROR stack trace. Register no-op handlers to silently ignore these events.
The PRIVATE_ITEMS list contained the bare 'test' entry, which rsync
interprets as 'any directory named test at any depth' — so it caught
the root-level /test/ scratch directory (intended) AND every src/test/
under each module (not intended).
Pattern is already anchored to /test (root-only). This commit rsyncs
the accumulated src/test/ tree forward so opensource has the unit tests
that have been written / updated against existing src/main/ code since
the pattern regression. Going forward each per-commit sync will carry
src/test/ files along with the main change.
OAuth token save now promotes the first available chat model when no usable default exists. Default-model resolution and provider availability checks require Provider.enabled=true alongside credentials, so disabled Providers no longer return stale defaults. /models/enabled drops the single-Provider hard-code so OpenAI OAuth and other enabled chat models surface in selectors. Docker exposes the 1455 PKCE callback via MATECLAW_OAUTH_OPENAI_CALLBACK_BIND_HOST (default 127.0.0.1) and a port mapping; deployment mode stays Host-driven.
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.
Group-chat reply slot fallback:
- The platform blocks proactive sends in group chats; outbound paths
(cron summaries, async-task completions, generated image/music/3D
delivery, TTS audio) silently failed because they fell through to
the proactive-send command. New bounded LRU maps each group chat
to its most recent inbound frame id; the dispatcher prefers that
reply slot and falls through to proactive only for single chats.
- Centralised text and media dispatch through a single helper so the
group rule never has to be re-implemented per outbound path.
Upload size pre-check + auto-downgrade:
- Without client-side limits, oversized uploads streamed for ~1 minute
before the server rejected at the finish step — users saw nothing
arrive in their chat. The new decision layer mirrors the platform's
hard limits and produces three outcomes: rejected with a friendly
reason, downgraded to a generic file delivery with an inline note,
or pass-through unchanged.
- Files over 20MB reject. Images / videos over their 10MB limit
downgrade to file. Voice content that isn't AMR or exceeds 2MB
downgrades. AMR voice within 2MB stays native.
appmsg inbound parsing:
- Forwarded complex messages (document transfers, article links,
miniprogram cards) used to fall into the inbound switch's default
branch and silently drop. The new branch flattens four sub-types
into a text marker the agent reads plus any media that needs to
reach downstream tools — document forwards reuse the same magic-
byte sniff and per-conversation upload layout as native file
inbound, so extension recovery and chat-uploads serving work
identically.
- Article links produce "[链接] title\ndescription\nurl" so the agent
can summarize without round-tripping. Miniprograms surface their
title. Unknown sub-types still emit a generic marker so the agent
is never blind.
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.
Inbound (WeCom):
- Save uploaded media under data/chat-uploads/{conversationId}/ with full
fileName/path/fileUrl/storedName/fileSize on the content part. Web mirrors
of an IM conversation now show real thumbnails instead of "未命名".
- Magic-byte sniff (PDF / PNG / JPEG / GIF / Office / ODF / archives /
audio / video) recovers a real extension when the platform omits filename
for forwarded files — no more PDFs labelled "file.bin".
- ZIP container peek distinguishes DOCX / XLSX / PPTX / VSDX / ODT / ODS /
ODP / EPUB / JAR from a plain zip via discriminator paths and the OASIS
mimetype entry.
Outbound (WeCom):
- Chunk upload field name corrected so server-side actually stores the
bytes — file messages used to arrive with correct filename/size but
empty content, breaking every PDF / DOCX / PPTX recipient.
- Scan agent text for served-file URLs in both the text-reply and
content-parts paths; fetch bytes from the in-memory generated-file
cache and dispatch through the native chunk upload + media message
protocol so users receive a tappable file card instead of an
unopenable markdown link. Cache miss surfaces a clear retry hint.
Async tool result forwarding:
- New AsyncTaskMediaDispatcher routes generation completions (image,
video, music, 3D model) to whichever IM channel the conversation is
bound to via ChannelSessionStore + ChannelManager. Web / webchat
conversations are intentionally skipped — their SSE stream already
renders the result.
- Wired into all four generation services so IM users actually receive
generated media as native attachments. Each part now carries an
absolute disk path so adapters read bytes locally instead of round-
tripping through an authenticated served URL.
Slack native file upload:
- SlackChannelAdapter overrides the content-parts dispatch. Image /
audio / video / file / model3d parts ride filesUploadV2 so users see a
file card with preview thumbnail bound to the same thread as the
originating message. Text parts continue through chat.postMessage.
- Resolves bytes from the part's local path, falls back to an HTTP fetch
of fully-qualified URLs.
IM approval hint visibility:
- IM-driven approve / deny / auto-cancel / replay-error hints now go
through saveMessage + tracker broadcast in addition to the channel
adapter, so a Web mirror viewing the same conversationId sees the
resolution. Previously hints reached only the IM channel; the Web
admin console had no record of the outcome.
Adaptive paste-merge debounce:
- WeCom and other IM clients silently split long pasted prompts into
fragments that arrive 0.5-2 seconds apart, missing the existing 500ms
merge window. The agent then saw torn context and emitted multiple
conflicting replies.
- When the merged buffer crosses a content-length threshold, extend the
debounce window so subsequent fragments arrive in time. Default
500ms unchanged for normal short messages.
Resolve ${user.home} and other JVM system properties in MCP server env, headers, and cwd — previously only OS env vars were expanded, causing the filesystem MCP server to fail on Windows where $HOME isn't set.
Temporarily restore McpClientManager.java to its pre-#60 state so the
contributor's PR can squash-merge cleanly with their authorship preserved.
The args-expansion follow-up will land as a separate commit right after.
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.
When a user-installed skill (e.g. RedisOps) was bound to an agent, the
model frequently called the skill name directly as a tool, hit
"Tool not found: RedisOps", and either gave up or fell back to shell
guessing. Two compounding causes:
1. The system prompt block injected by SkillRuntimeService listed each
skill as `- **RedisOps** — desc`, which is the same format used for
tool catalogs and primed the model to call the names directly. The
"how to use" instructions referenced `read_skill_file` /
`run_skill_script` — names that don't exist in the tool registry,
so even a compliant LLM couldn't follow them.
2. ToolExecutionExecutor's `callback == null` branches returned a bare
"Tool not found: <name>" string. The model had no recovery signal
and no hint that the name it called was actually a skill.
Fix is two-layered:
- Prompt rewrite (SkillRuntimeService.buildSkillPromptEnhancement): lead
with an explicit warning that skills are NOT directly callable, use the
correct camelCase tool names (readSkillFile / runSkillScript), include
a concrete worked example anchored to the first enabled skill, and
render the listing as a markdown table so it stops looking like a
callable tool list. listAvailableSkills tool description and output
follow the same pattern.
- Runtime safety net (ToolExecutionExecutor): when toolCallbackMap.get
misses, check if the requested name (case-insensitive) matches an
active skill. If so, return a precise hint telling the LLM the right
invocation pattern instead of the bare error. Wired through both the
main execute path and the pre-approved replay path. SkillRuntimeService
is attached via a setter from AgentGraphBuilder so the executor's many
legacy constructors stay untouched, and it's nullable so isolated
tests still work.
Adds 5 unit tests covering: skill match -> hint, case-insensitive match,
no-match -> bare error, no SkillRuntimeService wired -> bare error,
pre-approved replay path -> hint.
Reported and reproduced by @pipima9950-glitch in issue #46.
SkillPackageResolver.persistScanOutcome built a fresh SkillEntity with only
id + scan fields, then called updateById. SkillEntity declares six columns
with @TableField(updateStrategy = FieldStrategy.ALWAYS) — name_zh, name_en,
config_json, source_code, skill_content, security_scan_result — so the
ALWAYS strategy emits UPDATE statements that write NULL to every one of
those columns not set on the partial entity.
Effect: every security re-scan that produced a status/findings change
silently wiped skill_content, config_json, source_code, name_zh, name_en
on the row. After importing a custom skill, the first scan tick destroyed
the imported content.
Fix: switch to LambdaUpdateWrapper so the UPDATE only touches the three
scan columns we actually want to change. Other skillMapper.updateById
call sites (SkillService, BuiltinSkillSeedService) pass DB-hydrated
existing entities and are unaffected.
Reported and diagnosed by @pipima9950-glitch in issue #45.
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.
Add a callout above the existing intro to make the wedge explicit:
multi-user workspaces, approval-gated sensitive actions, full audit trail,
production-grade health monitoring, per-channel error isolation.
One JAR on your own machine, zero data egress.
Chat attachments with non-ASCII filenames (e.g. Chinese) get sanitized
at upload time — `人人有虾.docx` is stored as `1777391026594_____.docx`.
Tools then receive only the original filename via '[Attachment] foo.docx'
and fail with 'file not found'.
- renderMessageContent now appends the actual server-side path so any
tool the LLM picks (read_file / extract_document_text /
detect_file_type) gets a path that resolves directly.
- New ChatUploadResolver helper performs basename-suffix matching inside
the conversation's chat-upload directory; ReadFileTool, DocumentExtractTool
and FileTypeDetectorTool fall through to it when the literal path does
not exist (defense in depth for cases where the LLM ignores the path
hint).
Refs https://github.com/matevip/mateclaw/issues/29
Replace the per-startup admin reconciliation in
WorkspaceSchemaMigration.ensureDefaultWorkspaceMembership() with a
one-shot bootstrap. Once the default workspace has any owner, the
method returns immediately, so an operator's deliberate removal of an
admin from the default workspace persists across restarts. If no owner
exists yet, pick the lowest-id active admin and add them as owner; if
no admin exists at all, log a warning and skip rather than failing
startup.
Refs https://github.com/matevip/mateclaw/issues/29
Restart-time backfill in WorkspaceSchemaMigration was inserting every
existing user into the default workspace and copying mate_user.role
('user'/'admin') into mate_workspace_member.role, whose valid domain is
{owner, admin, member, viewer}. Result: non-admin users assigned to
other workspaces were silently re-attached to the default workspace
with role='user', failing roleLevel() lookup and 403'ing on Agents.
- Filter the INSERT on u.role = 'admin' and hard-code the membership
role to 'owner', removing the role-domain mismatch and the
workspace-isolation violation in one change.
- Add V60__fix_invalid_workspace_member_roles.sql (h2 + mysql) to
drop already-corrupted default-workspace rows for users who have a
valid membership elsewhere, and downgrade the orphan rows to
'member' so those users aren't locked out entirely.
Refs https://github.com/matevip/mateclaw/issues/29
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
