Let users upload documents in chat without ingesting them into a knowledge base: files are parsed in the background, referenced by ID on send, and expire after a configurable TTL.
When retrieved context or tool results contain Markdown images, dynamically
append output requirements to system prompts and final-answer instructions.
Also normalize fullwidth image parentheses in the frontend renderer so
localized model output still renders correctly.
Chat and agent tool context now emits answer-ready Markdown images instead
of internal <image> XML so copied content renders safely. The frontend also
normalizes legacy XML blocks in persisted conversations during streaming.
Refactor tests and registry to use the new 'res://' syntax for resource aliases, ensuring consistency across the codebase. This change addresses alias handling in various test cases, including stream processing and registry encoding, to prevent data loss and improve resource reference management.
Add functionality to detect unresolvable resource aliases emitted by the model during chat completion and streaming. Introduce logging for these orphan aliases to aid in debugging and improve the handling of resource references. Update the stream processing to ensure held aliases are flushed upon cancellation, preventing data loss. Include tests to verify the correct reporting of orphan aliases.
Introduce resource://<handle> as the stable application identity for stored
objects, decoupling API responses, persisted rich text, and LLM prompts from
physical storage paths. Adds a resource catalog service (register/resolve/bind,
revocable expiring access grants), a request-local alias registry that compacts
resource references while in the LLM context and restores them (including across
streaming chunks), plus router, IM, chat-pipeline, and multimodal integration.
Includes schema migrations (resources, resource_bindings, resource_access_grants)
for sqlite, and hardens URL/output security handling.
Introduce tenant-scoped storage backend registry so workspaces can register
multiple storage instances and bind each knowledge base to a specific backend,
with migration from legacy tenant-level storage config and new settings UI.
Align product copy, API docs, Swagger descriptions, and i18n strings
with workspace terminology while keeping internal tenant identifiers
and headers unchanged for API compatibility.
Wiki ingest prompts previously encouraged inline [cNNN] citations that
leak internal chunk metadata into reader-facing Markdown. Strip legacy
aliases on read/write paths and update the modify prompt to keep prose
clean while source links remain in ChunkRefs.
Drop client-supplied target_id, generate IDs server-side, localize duplicate
names from request language, document the endpoint, and expand handler/client tests.
Add a side panel for web and knowledge-base citations with citation-badge
highlighting, refine collapsed RAG pipeline summary layout, and emit
knowledge_base_id from agent knowledge_search results.
OAuth authorization was only handled in MCPTool.Execute, so unauthenticated
services failed silently during RegisterMCPTools before any tool reached the
agent. Wire EventBus/session metadata into registration and reuse the same
getOrCreateMCPClientWithOAuthRetry path used at execution time.
Extract MCP OAuth session/wait/connect logic into mcp_oauth.go and remove the
duplicate waitForOAuthAndRetry + RegisterMCPContext layering in mcp_tool.go.
When an agent invokes an OAuth-enabled MCP service that the current user has
not authorized yet, the tool call now pauses and surfaces an "Authorize" card
in the chat instead of failing with an opaque error. After the user completes
the per-user OAuth popup, the backend verifies a token exists and resumes the
paused tool call automatically.
Backend:
- Add mcp_oauth_required / mcp_oauth_resolved events and response types.
- Add OAuthPendingRequest + Gate.RequestOAuthAndWait, reusing the existing
approval waiter, Resolve, Redis cross-instance fan-out and timeout.
- MCPTool.Execute pauses on an authorization-required error for OAuth services
and retries once (with a fresh ctx and recycled connection) after the user
authorizes.
- Forward the new events to the SSE stream.
- Add ResolveMCPOAuth handler + route; it verifies authorization before
unblocking so a premature resolve cannot resume into another failure.
Frontend:
- Add McpOAuthCard with an Authorize button reusing the popup + status-poll
flow, then resolve the paused run.
- Handle the new stream events (dedup multiple pending cards per service).
- Add resolveMCPOAuth API client and i18n keys (zh/en/ko/ru).
- Introduced tests for buildMustUseBlock to validate multi-word service prefix handling and name sanitization.
- Ensured that service names are correctly sanitized to prevent newline injection in must_use blocks.
- Verified that the generated block includes the correct tool name prefixes and does not contain unwanted characters.
- Fix grep_chunks dropping the full-KB scope when a turn mixes @KB with
@tag/@file: extract scopeClause and OR knowledge-ID and (kb,tenant)
predicates together, matching knowledge_search's fan-out.
- Consolidate the three scattered per-request @Skill/@MCP scope blocks in
buildAgentConfig into applyPerRequestSkillScope / applyPerRequestMCPScope,
each narrowing the whitelist and computing the must_use pin in one place.
- Dedupe the two identical selection-mode normalizers in Input-field.vue.
- Fix knowledge_create_test passing "" for the tagIDs []string parameter,
which made the whole service test package fail to compile.
- Add unit tests for scopeClause and the per-request scope helpers.
Tighten per-turn @MCP/@Skill/@tag handling after review: enforce agent
MCP/Skill whitelist, ignore mentions when selection mode is none, tag-scope
grep_chunks, and simplified English must_use lines without tool dumps.
Skip persisting scope envelopes to history rendered_content.
Wire per-turn @mentions for skills, MCP services, tags, and files through
QA handlers into agent config, runtime_context/must_use user blocks, and
tool registration. Fix tag-only scopes dropping KB tools, refresh suggested
questions on mention changes, and strengthen MCP must_use so @selected
services are invoked before local KB search.
Support connecting to MCP servers that require OAuth2, with a Cursor-like
zero-config flow: the user provides only a URL and the system performs
metadata discovery, dynamic client registration (DCR), and the
authorization code flow with PKCE on first connect.
- Persist per-user access/refresh tokens and per-service DCR client
credentials, encrypted at rest (AES-256-GCM)
- Store the PKCE verifier/state during the flow via Redis with an
in-memory fallback for Lite mode
- Cache MCP clients per (service, user) so tokens stay user-isolated
- Add endpoints for authorize-url, callback, status, and token revoke;
the callback is allowlisted for unauthenticated access
- Surface a structured "authorization required" hint when a tool call
hits an unauthorized MCP service
- Frontend: add an auth-type selector with OAuth config, inline
authorization status/actions, and render the connection test result
inline in the editor drawer instead of a stacked centered dialog
Enhance the internationalization support by adding optional descriptions for the embedding model in English, Korean, Russian, and Chinese. Update the UI to reflect these changes, ensuring users are informed about the optional nature of the embedding model when configuring knowledge base settings.
Revamp the wiki taxonomy planning process to assign coherent directory paths to entity/concept pages in a single pass, ensuring consistent reuse of existing folders. This change eliminates the need for per-page category assignments during the reduce phase, preserving user-curated categories.
Consolidate category path parsing and deduplication into a shared utility, improving consistency across the service and repository layers. Update related functions and tests to reflect these changes, ensuring efficient handling of category paths in the wiki ingestion process.
Persist category and hierarchy metadata on wiki pages (new migration), expose
category-path retrieval and related repository/service/handler/router APIs, and
update wiki ingestion (batch, cite, taxonomy) plus agent wiki prompts to build
and consume the taxonomy. Regenerate swagger docs for the new endpoints.
WikiChunkCitationPrompt placed the per-batch <chunks> block before the
static rules, output schema and the per-document-stable <candidate_slugs>.
Within one document only ChunksXML changes between batches, so the stable
content trailing the chunks could not form a long common prefix and
providers re-billed the static rules on every citation batch (issue #1687
measured ~6.4% prefix-cache hit rate on wiki synthesis).
Reorder to [rules | output schema | candidate_slugs | chunks] so every
batch after the first shares the long [rules | candidate_slugs] prefix.
No instruction text was dropped; only block order and the inline
above/below directional references changed. Verified the cacheable prefix
grows from 281 to 2366 bytes and is byte-identical across batches.
Addresses #1687
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Wiki summary/entity/concept/page-modify prompts instructed the LLM to
reproduce  verbatim, so high-entropy image URLs passed
through generation and got corrupted (dropped UUID segments, duplicated
or mangled path prefixes, even CJK chars inserted into the bucket name),
producing object keys that don't exist -> 404.
Mask all image URLs to opaque placeholders at the generateWithTemplate
chokepoint and deterministically rehydrate after generation; drop
corrupted/hallucinated placeholders so broken links never reach storage.
- Removed dependency on utils for schema generation, replacing it with a hardcoded JSON schema for GetDocumentInfoInput.
- Updated the input struct to use omitempty for JSON fields, clarifying that either knowledge_ids or faq_ids may be provided, but both are optional.
- Enhanced documentation for GetDocumentInfoInput to specify the usage of knowledge_ids and faq_ids.
- Updated the agent system prompt to clarify mandatory deep read requirements for FAQ entries, ensuring accurate retrieval and response generation.
- Added new localization strings for FAQ-related labels in English and Chinese, improving user experience and consistency across the application.
- Refactored the document and grep results components to support distinct FAQ identification, enhancing clarity in the output.
- Introduced new tests for FAQ metadata handling, ensuring robust functionality and correctness in the FAQ processing logic.
- Increased the default worker pool size for the asynq server from 16 to 32 to improve performance during concurrent uploads.
- Updated the .env.example and docker-compose.yml files to reflect the new default concurrency setting.
- Enhanced the handling of FAQ entries in the tool results, ensuring distinct identification through standard questions, improving user experience and clarity in the output.
- Refactored related components to utilize the new FAQ attributes, ensuring consistent display and interaction across the application.
- Eliminated all instances of the final_answer tool from the agent's configuration and logic, transitioning to a model where the agent concludes responses with plain text instead.
- Updated event handling and response analysis to reflect this change, ensuring that the agent's output is now directly delivered as text without relying on a dedicated final answer tool.
- Adjusted localization strings across multiple languages to remove references to final_answer, enhancing clarity and consistency in user-facing messages.
- Improved the overall structure of the agent's response handling to streamline the process and reduce potential confusion regarding tool usage.
refactor(agent): streamline answer handling and preamble logic
- Updated the agent's response handling to treat any text streamed before a tool call as a preamble, ensuring it is not included in the final answer.
- Removed the superseded marker logic from the event emission process, simplifying the flow of answer content and enhancing clarity in the UI.
- Adjusted the event handling to ensure that preamble segments are correctly retracted and relocated into the steps tree, improving the overall user experience.
- Enhanced the agent's internal logic to better manage answer segments and their states during streaming, leading to a more coherent response structure.
- Added logic to suppress whitespace-only content emitted before the actual answer starts, addressing issues with spurious empty events interleaved with tool call events.
- Enhanced the event emission process to ensure that only meaningful content is routed to the final answer area, improving the clarity and relevance of streamed responses.
- Introduced new tests to ensure correct routing of reasoning and answer content during streaming, addressing UX issues where answers appeared under the Thinking phase before transitioning.
- Implemented a ThinkStreamSplitter to separate inline reasoning from answer text, allowing for real-time updates to the UI without duplication.
- Updated the event emission logic to prevent re-emission of answers that were already streamed live, ensuring a seamless user experience.
- Enhanced the ChatResponse struct to include flags for streamed answers, improving the handling of final answer events.
- Added comprehensive unit tests for the ThinkStreamSplitter to validate its functionality across various scenarios.
- Redesigned SVG assets for screenshots to improve visual consistency and clarity, including updates to gradients, titles, and layout.
- Added a new screenshot asset to showcase the Wiki Knowledge Base feature.
- Enhanced localization strings across multiple languages to reflect updated terminology and descriptions for the knowledge framework, including agentic reasoning and hybrid search strategies.
- Improved the user interface in the login view to include new tags for agent and wiki features, enhancing user awareness of available functionalities.
- Introduced `started_at` and `uptime_seconds` fields to the `SystemInfo` structure for tracking server boot time and uptime.
- Updated the `GetSystemInfo` handler to populate these new fields based on server runtime.
- Enhanced the frontend to display server startup time and uptime in the system information view, improving visibility for users.
- Added localization support for new labels and descriptions related to server uptime and startup time in multiple languages.
- Added detailed communication and final answer instructions to the runtime context block, guiding the model on user-facing text and tool usage.
- Updated the XML structure to reflect these changes, ensuring clarity on metadata and instructions for each turn.
- Improved the overall safety and clarity of the model's output by preventing the exposure of internal tool names and IDs.
Cloning a knowledge base previously copied only the storage path strings
(knowledge.FilePath and chunk.ImageInfo.URL), so the source and the clone
shared the same physical objects in the storage backend. Once the original
file and extracted images are deleted on source removal, the clone is left
with dangling references and its document and images become unreadable —
data loss that occurs even for same-store clones.
Add a CopyFile primitive to the FileService interface and implement it in
every backend: server-side CopyObject on the object stores
(s3/obs/cos/oss/tos/ks3/minio), io.Copy on local, and a no-op on dummy.
Destinations use the knowledge-owned layout and reuse the existing
path/object-key guards; a sentinel ErrCrossBackendCopy is returned when the
source scheme does not match the backend.
Use CopyFile to deep-copy the document file in cloneKnowledge and the
extracted images in CloneChunk and cloneFAQKnowledgeBase via a shared
cloneChunkImageInfo helper that deduplicates identical image URLs per clone
and rewrites them to the new objects. Copied objects are cleaned up
best-effort if a clone fails partway through. A clone-time preflight rejects
cloning into a target bound to a different storage backend when the tenant
pins providers via StorageEngineConfig.
Adds unit tests for local CopyFile (independent copy survives source
deletion, traversal rejection, cross-backend rejection), cloneChunkImageInfo
(empty/multi/dedup/parse-failure/OriginalURL handling), and the storage
provider preflight.
`ToolRegistry.GetFunctionDefinitions` and `ListTools` previously ranged
over the internal map directly. Go map iteration is intentionally
randomized, so the resulting `tools` array reshuffled on every request.
That reshuffling silently breaks provider-side prompt caches that key on
a byte-level prefix match — most visibly Qwen explicit caching, which
requires the messages (system + tools + history) to be byte-identical up
to the `cache_control` marker. With random ordering the serialized tools
block changes every call, so the cache prefix never matches and the
hit rate stays at 0%.
Sort by tool name in both functions. Output is now byte-stable across
calls and `cache_control: ephemeral` can actually take effect.
Tests in registry_test.go cover:
- Deterministic ordering across 50 iterations
- JSON byte-stability across 20 iterations (the real motivation)
- Field projection (Name / Description / Parameters)
- Empty registry returns `[]` not `null`
- ListTools sorting
- First-wins duplicate registration policy (GHSA-67q9-58vj-32qx)
The grep_chunks tool previously accepted an array of regex queries (1-5)
and an optional knowledge_base_ids filter and limit. In practice the LLM
either fired multiple near-duplicate calls or split synonyms across
entries instead of using POSIX alternation, and KB scoping plus result
limit are server-side concerns the model should not control.
Reshape the contract to match `grep -E -i` semantics:
- Schema accepts a single required `query` string. Combine concepts with
`|` alternation in one regex instead of multiple calls.
- Drop `knowledge_base_ids` and `limit` from the schema; the tool now
always searches the full agent scope and uses a fixed internal cap.
- Legacy `pattern`, `queries`, `patterns`, `max_results` keys are still
accepted and joined into a single alternation regex so older callers
and in-flight model outputs keep working.
- Update the agent system prompt template to document the new single
`query` field.
- Frontend tool title now reads `query`/`queries`/`pattern`/`patterns`
in that order so the search text is shown again under the new schema.
- Add a dedicated `grepSearch` / `grepSearchFailed` tool status (zh-CN,
en-US, ko-KR, ru-RU) and rename the zh-CN tool label to "搜索关键词"
so the UI no longer prefixes the call with a generic "调用 ..." label.
The Tenant.ConversationConfig field was marked deprecated when
CustomAgent (builtin-quick-answer) replaced the per-tenant defaults
path, but the JSONB column, GET/PUT KV handlers, write helpers and
read fall-throughs all stayed wired. This had two concrete failure
modes:
- Input-field.vue silently PUT-ed per-user model picks back into
/tenants/kv/conversation-config, which requires Admin+ — Viewers
and Contributors got a 403 every time they switched chat models.
- The same write also overwrote the tenant-shared default for every
other user, turning a per-user UX into a per-tenant footgun.
Remove the field, the struct, the validate helper, the PUT case and
the two dead Summary helpers in session/helpers.go. KnowledgeSearch
loses its tenant-conversation fallback (one chunk-tool reader); the
global config + hardcoded defaults still cover it. session_agent_qa
already required agents to declare their own rerank_model_id, so no
behaviour change there.
Frontend follows:
- Input-field.vue: per-user 'last selected chat model' moves to
localStorage, no API call.
- AgentEditorModal: defaults for builtin-quick-answer creation now
come from prompt-templates (system/context/rewrite/fallback) and
retrieval-config (top_k / threshold), the two endpoints that
actually own those settings now.
- AgentSettings.vue: orphan settings page with no router/import
referencing it; deleted.
- api/system: getConversationConfig / updateConversationConfig and
the ConversationConfig interface go away.
Net: 137 insertions, 2761 deletions.
MiMo and DeepSeek V3.2/V4 reject multi-turn requests in thinking mode
when the prior assistant message lacks reasoning_content with HTTP 400:
"The reasoning_content in the thinking mode must be passed back to the API."
Agent's ReAct loop is the worst-case scenario — every round produces tool
calls, exactly the case DeepSeek's docs specify reasoning_content MUST
participate in subsequent context.
Plumb reasoning_content through the full assistant-message round-trip:
- chat.Message / types.ChatResponse / types.AgentStep gain a
reasoning_content field (AgentStep persists via the existing
Message.AgentSteps jsonb column, no migration needed).
- streamLLMToEventBus accumulates reasoning chunks into
result.ReasoningContent and surfaces it on the round's ChatResponse.
- engine.runReActIteration writes it onto AgentStep so cross-turn replay
preserves it.
- observe.appendToolResults attaches it to the same-turn assistant
message; agent_history.buildAssistantHistoryMessages does the same on
cross-turn replay.
- RemoteAPIChat.ConvertMessages forwards it on assistant turns to
openai.ChatCompletionMessage.ReasoningContent (already supported by
go-openai); providers that don't recognize the field ignore it.
Tests cover the three boundaries: ConvertMessages serializes it for
upstream, appendToolResults preserves it within the same turn, and
buildAssistantHistoryMessages replays it across turns.
Scope is intentionally limited to Agent mode — KnowledgeQA's chat
pipeline and Anthropic's signed thinking_blocks are separate fixes that
require schema changes (rendered_content / thinking_blocks columns).
Fixes#1302
Quick-answer agent mode retrieves purely through vector/keyword chunk
search and ships with no `allowed_tools`, so the existing capability
filter (which only reads from `allowed_tools`) let wiki-only KBs through
in every entry point. End result: users could @-mention, select, and
receive suggested questions from wiki-only KBs in quick-answer mode,
but the underlying retrieval always returned empty.
Treat "RAG-only" as an implicit property of `agent_mode = quick-answer`
and union it with the tool-derived filter. The same predicate is now
used everywhere the user can pick or be steered toward a KB:
Backend
- `tools.DeriveKBFilterForAgent` / `KBSatisfiesAgentRequirements`
layer the implicit quick-answer requirement on top of tool derivation.
- `ListKnowledgeBases`, `SearchKnowledge` (shared-agent `@file`),
`resolveKnowledgeBasesFromAgent` (chat runtime), `/search` IM command,
and `GetSuggestedQuestions` now all use the agent-mode-aware variant.
- `GetSuggestedQuestions` also skips the wiki-page fallback for
quick-answer agents to cover the `selected` / explicit-kb-ids paths
where a wiki-only KB could still slip through.
Frontend
- `deriveKbFilterForAgent` / `kbSatisfiesAgentRequirements` mirror the
Go helpers.
- `@` mention dropdown (`Input-field.vue`) uses the new helper.
- Agent editor's "specified KB" picker (`AgentEditorModal.vue`) grays
out wiki-only KBs for quick-answer agents with a tooltip, and the
pre-save warning fires for quick-answer mode too.
- i18n: add `agentEditor.agentType.kbMismatch.quickAnswer` across all
four locales.