WeKnora/internal/types
lyingbug ba253bcbac
feat(agent): unified agent permission model with grants and run modes (#4490)
* refactor(agent): route approval decisions through a single policy

Operations, assistant write tools, MCP tool approval, delegated-child
approval and the child tool guard each compared access levels on their
own. They now ask policy.Decide, which maps an action's risk and the
run's rules to allow or ask. Behaviour is unchanged: MCP tools still
follow only the workspace per-tool flag and delegation, and a write that
reaches a read-only run still asks.

Add design docs for the agent permission model and scheduled automation.

* refactor(agent): replace interactive flags with a run mode

Runs are attended, deferred or unattended. Unattended runs refuse every
approval, including MCP approvals that used to wait out the timeout;
deferred runs suspend at once.

* feat(agent): apply access levels to MCP tools and every agent

MCP tools get a risk: the workspace's explicit setting, else the service's
readOnlyHint, never lower than a risk the service declared before. The
run's access level now decides MCP calls as it does operations; read-only
runs neither see nor run tools that change data. Ordinary agents get a
configurable ceiling that defaults to auto_write, and delegated children
take the lower of their parent's level and their own ceiling instead of
asking for every MCP call.

* feat(agent): persist approval grants with session/automation scopes

Remembered "allow for this conversation" approvals move from prompt history
into an agent_grants table keyed by root session (or automation binding), so
delegated children share the root grant and unattended runs honour it.
MCP write tools now offer the grant, keyed by service, tool and input schema.
Users can list and revoke their grants from the chat header.

* feat(agent): acting-via identity, decision logs and grant lapse reasons

Principal gains ActingVia so work done on a user's behalf (automations) is
told apart in audit details and policy decision logs. Every non-read policy
decision is logged with its action, risk, level, mode and verdict.
Automation grants bind to a hash of the agent setup, owner role and access
ceiling; a grant that no longer applies asks again and the card says why.

* docs(agent): record permission model implementation status

* chore(handler): check c.Error in agent grant handlers

* chore(handler): check c.Error in MCP tool policy handler

* fix(agent): raise MCP observed risk atomically and scope worker access

- Compare observed_risk inside the upsert so a stale lower observation
  cannot overwrite a higher one recorded concurrently.
- Delegated workers use the same conditional level as attach: the
  assistant ceiling applies only under an assistant parent.
- Mock @/api/assistant in useModalShell tests; gofmt internal/mcp/client.go.

* docs(agent): allow destructive pre-grants only in automation scope

Decide against a level that skips every prompt: Always stays
unwaivable and destructive actions may only be pre-approved per resource
when an automation is set up. Note that automation runs must look up
both automation and session grants.

* feat(agent): standing grant scope and risk-bounded grants

Grants record the risk they were approved for and never cover a riskier
call. Destructive calls are now named for matching, so an automation's
standing grant can cover one, but the card still offers to remember only
writes. The gate looks up the run's own scope and then its standing
scope; approvals during a run are written only to the run's scope.
2026-10-19 20:52:15 +08:00
..
interfaces feat(agent): unified agent permission model with grants and run modes (#4490) 2026-10-19 20:52:15 +08:00
agent.go feat(assistant): add durable multi-agent collaboration and live task views (#4438) 2026-10-19 12:14:15 +08:00
agent_grant.go feat(agent): unified agent permission model with grants and run modes (#4490) 2026-10-19 20:52:15 +08:00
agent_grant_test.go feat(agent): unified agent permission model with grants and run modes (#4490) 2026-10-19 20:52:15 +08:00
agent_operation.go feat(agent): unified agent permission model with grants and run modes (#4490) 2026-10-19 20:52:15 +08:00
agent_operation_acting_via_test.go feat(agent): unified agent permission model with grants and run modes (#4490) 2026-10-19 20:52:15 +08:00
agent_prompt.go feat(agent): unified agent permission model with grants and run modes (#4490) 2026-10-19 20:52:15 +08:00
agent_share_source.go fix: harden shared agent source selector validation 2026-07-30 12:28:23 +08:00
agent_share_source_test.go fix: harden shared agent source selector validation 2026-07-30 12:28:23 +08:00
agent_test.go feat(agent): keep long sandbox turns from truncating, overflowing, or rewriting files 2026-09-02 22:09:09 +08:00
agent_type_preset.go feat: Introduce agent type presets for smart-reasoning mode 2026-04-22 21:18:20 +08:00
artifact_versions.go feat(agent): unify sandbox tools and drop host preloaded skills (#3033) 2026-09-05 16:45:59 +08:00
artifact_versions_test.go feat(agent): unify sandbox tools and drop host preloaded skills (#3033) 2026-09-05 16:45:59 +08:00
ask_user.go feat(agent): persist human-in-the-loop prompts with a shared broker (#4250) 2026-10-14 20:37:28 +08:00
ask_user_test.go feat(agent): persist human-in-the-loop prompts with a shared broker (#4250) 2026-10-14 20:37:28 +08:00
assistant.go feat(agent): unified agent permission model with grants and run modes (#4490) 2026-10-19 20:52:15 +08:00
assistant_test.go feat(assistant): side panel, access levels and role-aware operations (#4342) 2026-10-15 18:18:22 +08:00
audit_log.go feat(agent): add the built-in WeKnora assistant with an operation catalog (#4302) 2026-10-15 12:18:30 +08:00
audit_log_test.go feat(system-admin): add endpoint for creating users (#2722) 2026-08-20 19:51:10 +08:00
browser_search.go feat(browser): polish connection settings, open tasks in a new window, and streamline prompts (#3193) 2026-09-11 21:28:58 +08:00
builtin_agent_config.go fix(i18n): 修复内置智能体名称与描述不随界面语言切换的问题 (#2828) 2026-08-27 11:53:45 +08:00
builtin_agent_localization_test.go fix(i18n): 修复内置智能体名称与描述不随界面语言切换的问题 (#2828) 2026-08-27 11:53:45 +08:00
builtin_models_config.go refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
builtin_models_config_test.go feat(models): let system admins edit builtin model config 2026-07-14 15:56:02 +08:00
caller.go refactor(resource-access): unify scoped authorization and transfer recovery (#3097) 2026-09-08 15:36:33 +08:00
chat.go feat(assistant): add durable multi-agent collaboration and live task views (#4438) 2026-10-19 12:14:15 +08:00
chat_history_config.go feat: implement chat history and retrieval settings 2026-03-09 11:46:56 +08:00
chat_manage.go fix(retrieval): skip KB retrieval for summarize intent 2026-10-10 20:51:04 +08:00
chat_manage_test.go fix(retrieval): skip KB retrieval for summarize intent 2026-10-10 20:51:04 +08:00
chunk.go feat(assistant): expand management operations and polish interaction UI (#4427) 2026-10-17 14:35:58 +08:00
chunk_contextheader_test.go test(types): regression test that ContextHeader is hidden from JSON 2026-05-06 17:17:07 +08:00
cleanup.go init commit 2025-08-05 15:08:07 +08:00
config_redaction.go feat(docparser): support MinerU 4.0 V1 API for self-hosted MinerU 2026-09-24 20:40:52 +08:00
config_redaction_sandbox_test.go feat(sandbox): add a graphical desktop to session sandboxes (#3245) 2026-09-14 20:37:37 +08:00
config_redaction_test.go feat(docparser): support MinerU 4.0 V1 API for self-hosted MinerU 2026-09-24 20:40:52 +08:00
const.go feat(agent): unified agent permission model with grants and run modes (#4490) 2026-10-19 20:52:15 +08:00
context_checkpoint.go feat(agent): size agent history by the window and calibrate token estimates (#3413) 2026-09-18 22:51:31 +08:00
context_clone.go feat(agent): unified agent permission model with grants and run modes (#4490) 2026-10-19 20:52:15 +08:00
context_clone_coverage_test.go refactor(context): replace middleware.EmbedChannelContextKey with types.EmbedChannelContextKey 2026-08-13 18:00:02 +08:00
context_helpers.go feat(agent): unified agent permission model with grants and run modes (#4490) 2026-10-19 20:52:15 +08:00
context_helpers_test.go fix: retry document summaries before fallback 2026-08-05 19:29:32 +08:00
custom_agent.go feat(agent): unified agent permission model with grants and run modes (#4490) 2026-10-19 20:52:15 +08:00
custom_agent_allowed_tools_test.go fix(agent): make agent tool selection match the tools the runtime registers (#4211) 2026-10-13 11:29:24 +08:00
custom_agent_reasoning_effort_test.go refactor(models): rebuild vendor integration on protocol + catalog + vendor layers (#3470) 2026-09-20 21:28:23 +08:00
custom_agent_test.go feat(agent): keep long sandbox turns from truncating, overflowing, or rewriting files 2026-09-02 22:09:09 +08:00
dataset.go init commit 2025-08-05 15:08:07 +08:00
datasource.go feat(assistant): expand management operations and polish interaction UI (#4427) 2026-10-17 14:35:58 +08:00
datasource_test.go feat(feishu): sync docx via blocks API with per-type downdrill (#2087) 2026-07-27 16:04:56 +08:00
docparser.go feat(assistant): expand management operations and polish interaction UI (#4427) 2026-10-17 14:35:58 +08:00
embed_channel.go docs(swagger): document the real request and response types (#4304) 2026-10-15 01:41:42 +08:00
embed_channel_test.go feat(memory): add cross-session long-term memory 2026-08-13 18:00:02 +08:00
embedding.go feat: index and recall images with multimodal embedding models (#3683) 2026-10-08 18:19:53 +08:00
errors.go init commit 2025-08-05 15:08:07 +08:00
evaluation.go fix: support custom jieba dictionary directory 2026-06-08 20:10:37 +08:00
event_bus.go refactor: Implement event-driven streaming and enhance session management 2025-11-07 22:41:41 +08:00
extract_graph.go fix(graph): preserve relationship direction and document provenance (#3950) 2026-10-08 00:48:51 +08:00
extract_graph_test.go fix(graph): preserve relationship direction and document provenance (#3950) 2026-10-08 00:48:51 +08:00
faq.go feat(agent): let the assistant manage FAQ entries (#4327) 2026-10-15 16:14:21 +08:00
faq_sync.go feat(knowledge): enhance FAQ export functionality 2026-07-23 10:50:32 +08:00
faq_sync_test.go feat(knowledge): enhance FAQ export functionality 2026-07-23 10:50:32 +08:00
faq_test.go feat(memory): add cross-session long-term memory 2026-08-13 18:00:02 +08:00
file_reference.go refactor(resource-access): unify scoped authorization and transfer recovery (#3097) 2026-09-08 15:36:33 +08:00
file_reference_test.go refactor(resource-access): unify scoped authorization and transfer recovery (#3097) 2026-09-08 15:36:33 +08:00
gallery_attr_source.go feat(gallery): add an image gallery tab with schema-driven filters (#3694) 2026-09-25 12:33:59 +08:00
gallery_builtin_source.go feat(gallery): add an image gallery tab with schema-driven filters (#3694) 2026-09-25 12:33:59 +08:00
gallery_policy.go feat(gallery): add an image gallery tab with schema-driven filters (#3694) 2026-09-25 12:33:59 +08:00
generated_question_revision_test.go fix(chunks): retain questions across content edits 2026-07-28 20:23:48 +08:00
generated_question_source_id_test.go fix(knowledge): bound generated question source IDs 2026-07-28 20:23:48 +08:00
graph.go feat: implement preview of user level memory graph 2026-02-25 14:29:54 +08:00
graph_search.go feat(graph): add standalone JSON graph search API (#4395) 2026-10-17 23:00:55 +08:00
graph_search_test.go feat(graph): add standalone JSON graph search API (#4395) 2026-10-17 23:00:55 +08:00
image_actions.go refactor(image): turn the hard-coded image flow into configurable pipelines (#3746) 2026-10-16 16:18:57 +08:00
image_attrs.go feat(gallery): add an image gallery tab with schema-driven filters (#3694) 2026-09-25 12:33:59 +08:00
image_attrs_gallery.go feat(gallery): add an image gallery tab with schema-driven filters (#3694) 2026-09-25 12:33:59 +08:00
image_attrs_test.go feat(gallery): add an image gallery tab with schema-driven filters (#3694) 2026-09-25 12:33:59 +08:00
image_gallery.go feat(gallery): filter images by source document (#4159) 2026-10-12 15:43:28 +08:00
image_read.go fix(agent): clarify attachment image paths and chart readings (#4283) 2026-10-14 14:23:28 +08:00
indexing_strategy.go feat(agent): add the built-in WeKnora assistant with an operation catalog (#4302) 2026-10-15 12:18:30 +08:00
json.go test(types): add unit test for JSON unmarshalling and validation 2026-04-22 21:17:36 +08:00
json_map.go refactor(knowledge): replace flat stage table with langfuse-style span tree 2026-05-28 15:14:45 +08:00
json_test.go test(types): add unit test for JSON unmarshalling and validation 2026-04-22 21:17:36 +08:00
knowledge.go feat(assistant): trial runs, session grants, page links, and MCP/model/skill management (#4375) 2026-10-16 23:36:01 +08:00
knowledge_custom_metadata_test.go feat(knowledge): support editable chunks and metadata 2026-07-28 20:23:48 +08:00
knowledge_folder.go feat(agent): open more workspace operations to the WeKnora assistant (#4318) 2026-10-15 15:19:23 +08:00
knowledge_folder_test.go fix(knowledge): keep long non-ASCII folder names valid UTF-8 2026-09-07 11:50:32 +08:00
knowledge_process.go refactor(image): turn the hard-coded image flow into configurable pipelines (#3746) 2026-10-16 16:18:57 +08:00
knowledge_process_test.go feat(docreader): support forcing PDF scanned-page OCR parsing 2026-06-25 17:30:22 +08:00
knowledge_profile.go feat(knowledge): derive knowledge base descriptions from document profiles (#3370) 2026-09-17 22:21:55 +08:00
knowledge_profile_test.go feat(knowledge): derive knowledge base descriptions from document profiles (#3370) 2026-09-17 22:21:55 +08:00
knowledge_span.go fix(spans): expand knowledge span name column and truncate long wiki names 2026-07-13 10:35:44 +08:00
knowledgebase.go feat(assistant): expand management operations and polish interaction UI (#4427) 2026-10-17 14:35:58 +08:00
knowledgebase_auto_tag_test.go fix(knowledge): harden auto-tagging and let it respect manual tags 2026-08-07 15:35:58 +08:00
knowledgebase_profile.go feat(assistant): let the assistant manage knowledge bases (#4353) 2026-10-15 23:54:14 +08:00
knowledgebase_test.go feat: index and recall images with multimodal embedding models (#3683) 2026-10-08 18:19:53 +08:00
legacy_persisted_json_test.go refactor(models): rebuild vendor integration on protocol + catalog + vendor layers (#3470) 2026-09-20 21:28:23 +08:00
locale.go feat(i18n): add Traditional Chinese (zh-TW) locale support (#3916) 2026-10-08 16:18:17 +08:00
locale_test.go feat(i18n): add Traditional Chinese (zh-TW) locale support (#3916) 2026-10-08 16:18:17 +08:00
mcp.go feat(agent): unified agent permission model with grants and run modes (#4490) 2026-10-19 20:52:15 +08:00
mcp_endpoint.go feat(mcp): add built-in MCP server with per-workspace endpoints (#3371) 2026-09-17 22:40:05 +08:00
mcp_endpoint_tools.go feat(mcp): add built-in MCP server with per-workspace endpoints (#3371) 2026-09-17 22:40:05 +08:00
mcp_endpoint_tools_test.go feat(mcp): add built-in MCP server with per-workspace endpoints (#3371) 2026-09-17 22:40:05 +08:00
mcp_metadata.go feat(assistant): expand management operations and polish interaction UI (#4427) 2026-10-17 14:35:58 +08:00
mcp_oauth.go fix(mcp): coordinate OAuth token refresh and authorization polling 2026-07-23 15:35:24 +08:00
mcp_test.go feat(mcp): let callers without a browser obtain MCP OAuth tokens (#4229) 2026-10-13 16:37:24 +08:00
memory.go fix(memory): rank memories by the query, not by importance 2026-09-13 11:43:17 +08:00
memory_extraction.go fix(memory): preserve extraction progress and atomic memory updates (#3224) 2026-09-13 00:04:16 +08:00
memory_test.go feat(browser): polish connection settings, open tasks in a new window, and streamline prompts (#3193) 2026-09-11 21:28:58 +08:00
message.go feat(assistant): add durable multi-agent collaboration and live task views (#4438) 2026-10-19 12:14:15 +08:00
message_agent_attachment_test.go feat(agent): read chat attachments on demand (#4203) 2026-10-13 14:37:17 +08:00
message_artifact.go feat(artifacts): let users delete generated files (#3447) 2026-09-20 13:01:46 +08:00
message_attachment_test.go feat(im): process file attachments in QA 2026-08-12 16:08:51 +08:00
message_suggestion.go feat(agent): add question suggestions with after-answer follow-ups 2026-07-14 11:17:25 +08:00
message_test.go feat(session): fork conversations from a historical user message (#3304) 2026-09-17 14:20:18 +08:00
model.go fix(frontend): 修复复制模型时模型名称被改写的问题 (#3830) 2026-09-29 19:32:08 +08:00
model_catalog_config.go feat(models): add system admin model catalog console (#3662) 2026-09-24 16:31:45 +08:00
organization.go fix(security): close the low-severity shared-space findings (#3416) 2026-09-18 22:58:46 +08:00
page_action.go feat(assistant): trial runs, session grants, page links, and MCP/model/skill management (#4375) 2026-10-16 23:36:01 +08:00
page_action_test.go feat(assistant): trial runs, session grants, page links, and MCP/model/skill management (#4375) 2026-10-16 23:36:01 +08:00
parser_engine_config_test.go fix(parser): default ppt/pptx to markitdown when no engine rules (#2882) 2026-08-31 14:58:15 +08:00
placeholder.go feat(chat): keep prompt prefixes stable and send provider cache markers 2026-09-03 00:45:52 +08:00
placeholder_time_test.go feat(chat): keep prompt prefixes stable and send provider cache markers 2026-09-03 00:45:52 +08:00
principal.go feat(agent): unified agent permission model with grants and run modes (#4490) 2026-10-19 20:52:15 +08:00
principal_test.go test(api-keys): add unit tests for tenant API key validation 2026-07-07 12:00:13 +08:00
prompt_instructions.go feat(knowledge): derive knowledge base descriptions from document profiles (#3370) 2026-09-17 22:21:55 +08:00
prompt_instructions_test.go Enhance knowledge base configuration by normalizing and validating custom instruction fields. Implemented length checks for prompt instructions and added tests for validation logic. Updated GraphSettings to retain custom instructions when extraction is disabled. 2026-07-13 12:16:19 +08:00
qa_request.go feat(agent): unified agent permission model with grants and run modes (#4490) 2026-10-19 20:52:15 +08:00
qa_request_test.go fix(chat): preserve steering continuity and composer focus 2026-09-09 20:15:23 +08:00
question_suggestion_test.go feat(agent): add question suggestions with after-answer follow-ups 2026-07-14 11:17:25 +08:00
rerank.go feat: judge image hits by their image in rerank and show them to vision models (#4013) 2026-10-09 13:01:48 +08:00
resource.go refactor(resource-access): unify scoped authorization and transfer recovery (#3097) 2026-09-08 15:36:33 +08:00
resource_test.go feat(agent): preview skill artifacts and verify installs without running them (#2823) 2026-08-27 10:30:32 +08:00
retrieval_config.go fix(retrieval): fix recall correctness, score scales, cost and agent tools (#3687) 2026-09-25 10:48:18 +08:00
retriever.go feat: judge image hits by their image in rerank and show them to vision models (#4013) 2026-10-09 13:01:48 +08:00
run_mode.go feat(agent): unified agent permission model with grants and run modes (#4490) 2026-10-19 20:52:15 +08:00
runtime_task.go feat(assistant): expand management operations and polish interaction UI (#4427) 2026-10-17 14:35:58 +08:00
sandbox_network_policy.go fix(sandbox): always require inbound credentials 2026-09-03 13:34:40 +08:00
sandbox_network_policy_test.go feat(sandbox): add tenant-configurable network policy (#2995) 2026-09-03 10:49:46 +08:00
sandbox_tenant_context_test.go feat(sandbox) (#2301) 2026-08-10 21:28:20 +08:00
search.go feat(assistant): trial runs, session grants, page links, and MCP/model/skill management (#4375) 2026-10-16 23:36:01 +08:00
search_scope_test.go refactor(agent): introduce modelcontext registry and fix handle-codec bugs 2026-07-27 11:05:43 +08:00
secret.go fix(security): harden secret redaction follow-ups for PR #1884 2026-07-02 14:41:42 +08:00
secret_test.go fix(security): harden secret redaction follow-ups for PR #1884 2026-07-02 14:41:42 +08:00
session.go feat(assistant): add durable multi-agent collaboration and live task views (#4438) 2026-10-19 12:14:15 +08:00
session_access_test.go feat(sandbox): expose tenant skill management over HTTP and in the console (#2789) 2026-08-25 11:28:12 +08:00
session_fork.go feat(session): fork conversations from a historical user message (#3304) 2026-09-17 14:20:18 +08:00
session_fork_test.go feat(session): fork conversations from a historical user message (#3304) 2026-09-17 14:20:18 +08:00
session_kind_test.go feat(assistant): manage agents and skills, separate history, refresh pages (#4344) 2026-10-15 21:43:20 +08:00
shared_agent_access.go refactor(resource-access): unify scoped authorization and transfer recovery (#3097) 2026-09-08 15:36:33 +08:00
shared_agent_access_test.go refactor(resource-access): unify scoped authorization and transfer recovery (#3097) 2026-09-08 15:36:33 +08:00
source_locator.go fix(citations): 修复原文定位、高亮范围与 DocReader 启动失败 (#3794) 2026-09-27 20:32:26 +08:00
storagebackend.go feat(storage): add multi-instance storage backends per workspace 2026-07-15 14:54:39 +08:00
storagebackend_test.go feat(storage): add multi-instance storage backends per workspace 2026-07-15 14:54:39 +08:00
sync_item_error_test.go fix(feishu): resilient large-wiki sync — retry, streaming resume, failure visibility 2026-07-21 16:14:22 +08:00
system_setting.go refactor(terminology): rename user-facing tenant labels to workspace 2026-07-14 16:14:43 +08:00
system_setting_summary.go feat(assistant): expand management operations and polish interaction UI (#4427) 2026-10-17 14:35:58 +08:00
tag.go feat(agent): let the assistant manage FAQ entries (#4327) 2026-10-15 16:14:21 +08:00
task.go feat(assistant): expand management operations and polish interaction UI (#4427) 2026-10-17 14:35:58 +08:00
task_dead_letter.go perf(wiki-ingest): scale to 4w-doc KBs + generic task queue / dead-letter 2026-05-10 00:01:06 +08:00
task_initiator_test.go feat(audit): 知识库活动记录对 API Key 操作额外显示 Key 名称 (#3405) 2026-09-18 19:39:34 +08:00
task_pending_op.go fix(queue): order ClaimBatch by fail_count so retries cannot starve new work (#3444) 2026-09-21 13:00:29 +08:00
task_queue_test.go feat(knowledge): derive knowledge base descriptions from document profiles (#3370) 2026-09-17 22:21:55 +08:00
temporary_document.go docs(swagger): document the real request and response types (#4304) 2026-10-15 01:41:42 +08:00
temporary_document_test.go feat(agent): read chat attachments on demand (#4203) 2026-10-13 14:37:17 +08:00
tenant.go feat(assistant): side panel, access levels and role-aware operations (#4342) 2026-10-15 18:18:22 +08:00
tenant_api_key.go feat(audit): 知识库活动记录对 API Key 操作额外显示 Key 名称 (#3405) 2026-09-18 19:39:34 +08:00
tenant_api_key_scope_test.go Add API key member and space capabilities 2026-07-07 12:00:13 +08:00
tenant_api_key_test.go Refine scoped API key capabilities 2026-07-07 12:00:13 +08:00
tenant_env_vars.go fix(sandbox): make skill env capture fill blanks only 2026-08-27 14:32:00 +08:00
tenant_env_vars_test.go fix(sandbox): make skill env capture fill blanks only 2026-08-27 14:32:00 +08:00
tenant_invitation.go feat(rbac): add multi-use share-link invitations for invite_only mode (#1504) 2026-05-27 19:42:01 +08:00
tenant_member.go feat(assistant): expand management operations and polish interaction UI (#4427) 2026-10-17 14:35:58 +08:00
tenant_sandbox_config_entity.go feat(sandbox): 沙箱后端改为按空间配置,并补齐 E2B 模板与检测诊断 2026-08-11 15:42:02 +08:00
tenant_sandbox_config_entity_test.go feat(sandbox) (#2301) 2026-08-10 21:28:20 +08:00
tenant_sandbox_config_test.go feat(sandbox) (#2301) 2026-08-10 21:28:20 +08:00
tenant_skill.go fix(skills): upgrade outdated sandbox skills without rolling back the catalog or taking them offline (#3406) 2026-09-18 20:27:43 +08:00
tenant_test.go fix: preserve MinerU automatic PDF parsing 2026-08-03 15:37:07 +08:00
token_usage_test.go feat(agent): report and attribute per-turn LLM token usage 2026-08-24 10:36:19 +08:00
tracing.go feat(tracing): migrate langfuse client to OTLP/OTel wire protocol 2026-07-17 16:30:45 +08:00
user.go feat(assistant): expand management operations and polish interaction UI (#4427) 2026-10-17 14:35:58 +08:00
user_resource_favorite.go feat(favorites): implement user favorites and recents functionality 2026-05-18 17:28:58 +08:00
vectorstore.go fix: use consistent qdrant env settings (#3960) 2026-10-07 23:59:56 +08:00
vectorstore_opensearch_test.go feat(retriever): activate OpenSearch k-NN driver (PR 3 of 3) 2026-05-29 16:32:27 +08:00
vectorstore_test.go fix: use consistent qdrant env settings (#3960) 2026-10-07 23:59:56 +08:00
web_search.go fix(agent): improve web search and persistent page reading (#3086) 2026-09-07 23:09:27 +08:00
web_search_filters.go fix(agent): improve web search and persistent page reading (#3086) 2026-09-07 23:09:27 +08:00
web_search_filters_test.go fix(agent): improve web search and persistent page reading (#3086) 2026-09-07 23:09:27 +08:00
web_search_provider.go feat(assistant): expand management operations and polish interaction UI (#4427) 2026-10-17 14:35:58 +08:00
web_search_provider_test.go feat(web-search): add Serply provider 2026-09-17 12:25:09 +08:00
web_search_test.go fix(web-search): normalize default tenant web search config at runtime 2026-04-30 15:28:35 +08:00
weknoracloud.go refactor(weknoracloud): update credential handling and configuration 2026-04-15 11:37:24 +08:00
wiki_page.go feat(assistant): let the assistant manage knowledge bases (#4353) 2026-10-15 23:54:14 +08:00
wiki_page_test.go refactor(modelcontext): consolidate source_refs parsing, fixed data_analysis table, and identifier leak report (#3372) 2026-09-17 22:08:16 +08:00