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.
Tighten model prompt so retrieval questions stay topic-bound and self-contained,
reserve knowledge slots in hybrid mode, and carry suggestion KB IDs into the next send.
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.
Improve follow-up question quality by feeding the model structured context
(evidence, capabilities, complete turns) instead of raw RAG content, and
rank knowledge candidates by current-topic relevance.
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.
Implement a comprehensive API for managing storage backends, including endpoints for listing, creating, updating, and deleting storage instances. Enhance the UI to support multi-instance configurations, allowing users to manage multiple storage types effectively. Update localization files for new storage backend features and improve error handling for connectivity tests. This update also includes detailed documentation for the storage backend API.
Enhance error messaging for storage connectivity issues by sanitizing raw errors to prevent leaking sensitive information. Introduce a new utility function for consistent error handling across storage backend operations. Additionally, implement logic to support multi-instance storage backends, allowing for more flexible workspace configurations and improved reporting of active storage providers.
Update the image source protection logic to include support for storage backend images. Introduce new regex patterns for identifying storage URLs and refactor the image tag building process to ensure proper handling of both provider and storage backend images. Add corresponding tests to validate the new functionality.
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.
Extract storage allowlist into internal/storageallowlist so KB creation
uses FirstAllowed when tenant default_provider is empty or disallowed.
Share pickUsableStorageProvider via editorResources for consistent UI
selection, and add regression tests for OBS status and allow-list defaults.
Prevent in-chat navigation from replacing the active conversation by
opening knowledge-base and citation links in a new tab with
noopener/noreferrer, and apply the same policy to sanitized markdown links.
Stop failing distributed-mode knowledge rows on startup; let housekeeping
decide using span activity and Asynq queue state. In Lite mode, resume
wiki work from durable task_pending_ops and surface SERVER_RESTART errors
in the processing timeline with i18n support.
Move follow-up loading into the answer toolbar so the card only appears when suggestions are ready, and delay toolbar actions until the typewriter finishes revealing the answer.
Replace offset-based page numbers with opaque Redis-backed cursors so
scheduled/retry tasks sort by next run time and live lists stay stable
when queue state changes between requests.
Refactor the error handling logic in the GetKnowledgeSpans function to utilize a new helper function, knowledgeSpansLastError, which consolidates the logic for determining the last error from span failures and knowledge row failures. This improves clarity and maintainability of the code. Additionally, update test cases to cover new scenarios for last error handling.
Latest attempt tabs and header now trust parse_status over a closed root span, surface recovery failures via last_error, and keep attempt hover styles from washing out the active tab.
Align product copy, API docs, Swagger descriptions, and i18n strings
with workspace terminology while keeping internal tenant identifiers
and headers unchanged for API compatibility.
Allow platform system administrators to update builtin model parameters
and credentials from the management UI while keeping secrets masked in API
responses. UI edits clear YAML ownership so startup reconciliation no
longer overwrites runtime overrides.
Added new translations and improved existing ones for English, Korean, Russian, and Chinese. Introduced short weight labels, refined failed task notices, and updated queue names and descriptions for better clarity and consistency across languages.
The '全部状态' (All Statuses) filter dropdown on the knowledge base documents page was missing the 'cancelled', 'finalizing', and 'draft' status options, even though documents can reach these states (e.g. cancelled via the '停止解析' button). Added all three status options and their i18n translations for zh-CN, en-US, ru-RU, and ko-KR.
Enable agents to configure starter prompts and async follow-up questions after completed answers, with durable caching, analytics events, and chat/embed UI integration.
Let system administrators reset another user's local password from the settings UI, revoke all active sessions, and record the action in the audit log.
Group global settings by product area (access, tenant, runtime, security),
add overview summary badges and inline save feedback, surface high-risk
keys, and collapse config-priority docs into a disclosure panel.
Drop the standalone OIDC_AUTH_DEFAULT_TENANT_MODE / oidc_auth.default_tenant_mode
knob so OIDC auto-provisioning and local password registration share the single
auth.default_tenant_mode policy (resolved by the callback handler). Repair
tenantless sessions by falling back to the first active membership on the login
happy path and stale-preference paths, allow tenantless PUT /auth/me/preferences,
clear the tenant snapshot on /auth/me responses without a tenant, and default the
frontend canCreateTenant capability to fail-closed until /auth/me confirms it.
Allow deployments to register users without auto-creating a personal tenant, expose creation policy via /auth/me, and guide tenantless accounts through a workspace onboarding flow.
Requesty is an OpenAI-compatible LLM gateway that uses the same provider/model
naming convention as OpenRouter, so this mirrors the existing OpenRouter provider.
- internal/models/provider/requesty.go: RequestyProvider mirroring openrouter.go
(base URL https://router.requesty.ai/v1, REQUESTY_API_KEY, RequiresAuth)
- provider.go: ProviderRequesty const + AllProviders() entry + DetectProvider case
- internal/types/model.go + client/model.go: ModelSourceRequesty
- provider_test.go: TestRequestyProviderValidation + DetectProvider case
- frontend model editor + i18n (en/zh/ko/ru) + docs/BUILTIN_MODELS.md provider list
- docs/swagger.{json,yaml} + docs.go: requesty enum value (hand-edited to match; these
are normally swag-generated)
Verified: go build/vet/test pass; live call to https://router.requesty.ai/v1 succeeds.
Signed-off-by: Thibault Jaigu <thibault.jaigu@gmail.com>
Split the monolithic upstream worker budget into explicit core, post-process,
enrichment, maintenance, and shared elastic pools, expose live cluster capacity
on the runtime dashboard, and retire the legacy asynq.concurrency setting.
Org-shared and agent-visible knowledge bases store images under the owner
tenant's storage path, which the tenant-scoped /files route rejects for
borrowing tenants. Add GET /api/v1/knowledge-bases/:id/files gated by
RequireKBAccess and route frontend image hydration through it when kbId
is known.
Surface per-model active/waiting/limit from the background task limiter so admins can distinguish task scheduling from model-service throttling, with full i18n coverage.
Updated the RuntimeQueues component to improve the layout and styling of the task queue display. Changes include a new grid layout for pool items, updated class names for better semantic structure, and adjustments to font sizes and spacing for improved readability. Additionally, added a note section with enhanced styling for clarity.
Route summary/sync/maintenance tasks to dedicated queues and servers so parsing, enrichment, and batch work no longer share one concurrency budget, while extending the runtime dashboard and settings validation to reflect the new topology.
Expose live asynq queue depths and worker-pool concurrency via a new SystemAdmin API and settings UI, so operators can monitor parsing/wiki backlog without Redis CLI access.
Add a new `max_concurrency` setting to the model configuration, allowing for fine-tuned control over the maximum number of concurrent background tasks (ingestion/enrichment) per model. This update includes localization support across multiple languages and integrates the setting into the system's concurrency governor, enabling immediate application of changes without requiring a service restart.
Introduce a new `max_concurrency` parameter to the model configuration, allowing control over the maximum number of concurrent background tasks (ingestion/enrichment) per model. This feature is applicable to chat, embedding, and VLM models, with a value of 0 or undefined falling back to the global default. Update UI components and localization files to support this new setting, ensuring a seamless user experience.
Drop client-supplied target_id, generate IDs server-side, localize duplicate
names from request language, document the endpoint, and expand handler/client tests.