Release v2.3.0 (#3436)

🐛 Bugfix: Guard memory_user_config against None in store/search memory tools (#3359)

🐛 Bugfix: Guard memory_user_config against None in store/search memory tools


Add None checks before accessing memory_user_config attributes in
StoreMemoryTool and SearchMemoryTool. When config is unavailable,
apply conservative default (agent_share_option=’never’) to prevent
unintended cross-agent memory sharing.

fix(memory): restore hidden tabs and hide Tenant Shared in speed mode


Fix nested array syntax bug that hid Tenant Shared and Agent Shared tabs
Conditionally hide Tenant Shared tab when isSpeedMode=true (no tenant concept)
All 5 tabs now properly visible in non-speed mode
4 tabs visible in speed mode (Tenant Shared hidden)


test: add coverage for memory None guard, duplicate cleanup, and system tool filtering


test_store_memory_tool: add None config, _run_coroutine tests
test_search_memory_tool: add None config, _run_coroutine tests
test_memory_config_service: add duplicate record cleanup tests
test_tool_configuration_service: add SYSTEM_MANAGED_TOOL_NAMES filter test


✨Feat:Integrate openjiuwen’s intelligent agent evaluation function close#3188 (#3356)

✨Feat：add prompt optimization

🐛Bugfix: dockerbuild failed when running pipefail in python3_11

🔨Optimize： Optimize prompt optimization display page and interaction methods

✨Feat:add agent evaluator

🐛Bugfix: fix fronted and report download

🐛 Bugfix: Add xlrd dependency and improve openjiuwen SDK adapter to handle circular imports more effectively. Update import paths in frontend components for consistency.

♻️Refactor: frontend style refact

🔨Rename evaluator sql

♻️ Refactor: Optimize the frontend page for agent evaluation

♻️Refactor: update modal mask properties for consistency

♻️ Refactor: Simplify locale handling and clean up imports in OAuthCompletePage and UserManageComp

✨ Feature: Enhance agent evaluation with Chinese output directive and new database migrations

🔧 Update: Change button variant from “outline” to “outlined” in EvaluationConfigCard and EvaluationReportCard components; enhance datetime handling in test_client.py to ensure correct timezone representation.

🧪Test: Add unit tests for the jiuwen_sdk_adapter to verify module-level behavior and side effects.

🔧 Update: Refactor the mock invocation in test_jiuwen_sdk_adapter to use an async function for better compatibility with asynchronous tests.

🧪 Test: Add comprehensive unit tests for evaluation set functionality, including CRUD operations and Excel parsing, to ensure robust behavior and error handling.

🧪 Test: Add extensive unit tests for Jiuwen SDK adapter and evaluation services, covering lazy imports, log envelope parsing, and case validation to enhance error handling and ensure robust functionality.

🔧 Update: Consolidate judge_model_id addition into agent_evaluation_t migration, removing the separate migration file for improved installation simplicity and ensuring idempotency in existing environments.

🔧 Update: Introduce a consolidated migration file for agent evaluation, combining previous separate migrations into a single idempotent script for improved installation simplicity and clarity. This includes the addition of evaluation tables and the pass_status column, ensuring all necessary structures are created in one step.

fix：Fix share link copy fallback (#3340)

feat: add conversation share

add ut test

add conversation share db tests

Fix share link copy fallback

🐛 Bugfix: Update homepage redirect link (#3376)

Bugfix:add crypto.randomUUID() fallback in http

Bugfix: Update homepage redirect link

🐛 Bugfix: Tool debugging bug fixes. (#3371)


[Specification Details]

Standardizing the styling of debugging pop-ups in frontend tools.
Tool debugging configuration parameters are retrieved from the store rather than from the API each time.


🐛 Bugfix: W11 capacity suggestion for batch gear modals + model add/edit fixes (#3355)

fix(model): stop sending hidden form.provider as modelFactory on single-add


Single-add mode has no provider dropdown — form.provider stays at its
hidden default ‘modelengine’, which was forwarded as modelFactory to
the backend, overriding the Pydantic default ‘OpenAI-API-Compatible’.
Introduced in 4becd6992 which added modelFactory: form.provider to both
save paths but missed the isBatchImport guard already present on the
suggest-capacity path in the same commit.
STT/TTS paths are unaffected — they set modelFactory from
form.sttProvider/ttsProvider downstream. Embedding is unaffected —
backend _infer_model_factory overrides from base_url.

refactor: move generate_backfill_sql.py to deploy/sql/migrations/

The script’s sole purpose is generating SQL migration files that live
in deploy/sql/migrations/. Keeping the generator alongside its output
is more natural than a standalone top-level scripts/ directory.

Updated _project_root path (three levels up instead of one)
Updated docstring usage path and generated SQL self-reference
Removed empty scripts/ directory


fix: preserve embedding legacy inference, extend VLM only


Embedding/multi_embedding keeps old logic (only dashscope recognized)
VLM uses extended inference so tokenpony URLs can trigger catalog healthcheck
Prevents unintended behavior change for embedding models


fix(ui): reorganize agent config layout - maxSteps+provideSummary on row1, outputReserve+verification on row2

test(W11): add normalize_model_name, _fuzzy_catalog_match, and Pydantic constructor-audit tests


Spec ‘Tests and Release Evidence’ explicitly requires these three test
groups. Previously they were only exercised indirectly through
suggest_capacity integration paths.
normalize_model_name (14 parametrized cases + convergence test):

Case folding, separator collapsing (dash/underscore/dot/slash/space)
Whitespace trimming, empty string, mixed separators
Catalog entry convergence: full-name variants (GPT-4o/gpt-4o) and
final-segment variants (Kimi-K2.6 vs Pro/moonshotai/Kimi-K2.6)

_fuzzy_catalog_match (6 cases):

Normalized name match, unique final-segment fallback
Ambiguous final-segment rejection (two entries same final segment)
Empty catalog, wrong provider, unrelated name

Pydantic constructor-audit (7 tests, skip when SDK deps unavailable):

CapacitySuggestionFields: model_dump shape pin, all-optional defaults
ModelCapacitySuggestionResponse: catalog_exact shape pin, none shape
pin, invalid match_kind rejection
CapacityCoverageBareModel: model_dump shape pin
CapacityCoverageResponse: model_dump shape pin

Results: 37 passed, 7 skipped (Pydantic tests skip when consts.model
import chain is unavailable due to missing SDK deps).

feat(W11): add capacity suggestion to batch gear modals

Add manual check-button capacity suggestion to the two batch per-row
gear modals, matching the single-model Add/Edit pattern:
ModelAddDialog.tsx (batch-add per-row gear):

Add gear-scoped suggestion state (enabled, checking, suggestion,
accepted, request ref for race-condition guard)
Add handleGearSuggestCapacity with monotonic token stale guard
Add applyGearCapacitySuggestion using capacityFormFromSuggestion
Render Switch + Check button toolbar above ModelCapacityFields
Pass suggestion/suggestionLoading/onUseSuggestion/acceptedSuggestion
props to ModelCapacityFields
handleSettingsSave writes accepted_suggestion_match_kind and
accepted_capability_profile_version audit fields onto the row
Clear suggestion state on gear modal open

ModelEditDialog.tsx (ProviderConfigEditDialog per-row gear):

Add modelName/baseUrl props to interface
Add suggestion state, handleSuggestCapacity, applyCapacitySuggestion
Render Switch + Check button in supportsCapacityFields mode only
(NOT in bulk-apply / hideCapacityFields mode)
Pass suggestion props to ModelCapacityFields
handleSave spreads accept-signal fields into onSave payload
Add acceptedSuggestionMatchKind/acceptedCapabilityProfileVersion
to onSave callback type

ModelDeleteDialog.tsx:

Pass modelName and baseUrl from selectedSingleModel to per-model
gear ProviderConfigEditDialog (NOT to provider-level invocation)
Forward accepted_suggestion_match_kind and
accepted_capability_profile_version in updateBatchModel payload

No auto-suggest — manual check button only, per spec.

chore(i18n): remove dead agent.modelSelector.bareCapacity.subtitle key

Spec ‘Agent-Edit Model Selector Warning’ explicitly states V1 dropdown
does not render a persistent subtitle. Code only uses .tooltip. Dead key.

fix(W11): pass correct modelName/baseUrl to batch-edit gear suggestion

providerModel uses ‘id’ as model name (not model_name/name), and
base_url is provider-level (not on individual model objects). The
Check button was always disabled because both resolved to empty string.
Fix:

modelName: add selectedSingleModel?.id as fallback
baseUrl: use getProviderBaseUrlByType(deletingModelType) directly


fix(W11): remove emptyHint Alert and i18n keys

The ‘provider list has no capacity info’ Alert is misleading in all
contexts: batch-add unchecked models, batch-edit gear with check button,
and single-edit with suggestion. Delete the component and both locale keys.

fix(W11): reset suggestion state when switching models in batch-edit gear

ProviderConfigEditDialog’s useEffect already resets capacityForm on
prop change but missed the suggestion state. Adding modelName/baseUrl
to deps and resetting capacitySuggestion/acceptedCapacitySuggestion/
enabled/checking on every prop change prevents stale suggestion from
the previous model leaking into the next gear dialog.

fix: preserve saved model capacity in batch edit

fix: persist batch gear model config edits

fix: pass provider hint for batch capacity suggestions

refactor: extract useCapacitySuggestion hook to deduplicate suggestion lifecycle


Consolidate the /suggest-capacity API call state machine (loading flag,
race-condition token, suggestion result, accepted suggestion) that was
duplicated across four call sites into a single reusable hook.
Call sites refactored:

ModelEditDialog (top-level edit form)
ProviderConfigEditDialog (per-row gear config edit)
ModelAddDialog (top-level add form)
ModelAddDialog (batch gear modal)

Net reduction: ~49 lines. No behavioral changes — the monotonic request
token, error handling, and state cleanup logic are preserved identically.

refactor: simplify capacity suggestion UI — remove noise tags and localize

Remove four low-value elements from the suggestion result panel:

matchExplanation (unlocalized backend English)
matchConfidence tag (high/medium/low)
suggestedProvider tag (internal backend concept)
noExplanation fallback text

Keep only what the operator needs:

canonical model name (bold, first position)
match kind (exact/fuzzy, without redundant ‘catalog’ prefix)
‘Use suggestion’ button
fuzzy-match warning when canonical name not accepted

When no suggestion is found, show a localized description instead of
the generic ‘no additional details’ fallback.

♻️ Refactor: Auto-create conversation when conversation_id is empty in agent/run (#3380)

Bugfix:add crypto.randomUUID() fallback in http

Bugfix: Update homepage redirect link

Refactor: Auto-create conversation when conversation_id is empty in agent/run

Bugfix: skip conversation auto-create in debug mode

修复单元测试

新增UT

新增UT测试

修改单元测试

Feat/opt agent context refactor v2 (#3383)

fix(context): use ContextManager uncompressed baseline for save% metric


Previously _last_uncompressed_est was set from input_messages which are
already compressed by prepare_step, making est_raw_i always equal est_i
and save% structurally ~0%. Now pull the truly-uncompressed token count
from ContextManager.get_token_counts()[‘last_uncompressed’], recorded in
compress_if_needed from the raw memory before compression.
Co-Authored-By: Claude noreply@anthropic.com

chore: expose temp_scripts test harness for cross-machine sync

Add test scripts and fixtures used during context-manager refactor
development. Only .py and .md files are tracked; .out run artifacts
remain ignored via .git/info/exclude.
Co-Authored-By: Claude noreply@anthropic.com

chore: add .gitignore in temp_scripts to suppress .out/.log artifacts

Co-Authored-By: Claude noreply@anthropic.com

chore: allow common ops by default, keep rm/mv/git push as ask

Co-Authored-By: Claude noreply@anthropic.com

refactor: extract SummaryTaskStep and ManagedRunContext into summary_step.py

Co-Authored-By: Claude Haiku 4.5 noreply@anthropic.com

refactor: extract pure budget/cache/fingerprint helpers into budget.py

Co-Authored-By: Claude Haiku 4.5 noreply@anthropic.com

refactor: extract LLMSummary class into llm_summary.py

Co-Authored-By: Claude Haiku 4.5 noreply@anthropic.com

refactor: extract StepRenderer and compress_history_offline into step_renderer.py

Co-Authored-By: Claude Haiku 4.5 noreply@anthropic.com

refactor: extract PreviousCompressor into previous_compression.py

Co-Authored-By: Claude Haiku 4.5 noreply@anthropic.com

refactor: extract CurrentCompressor into current_compression.py

Co-Authored-By: Claude Haiku 4.5 noreply@anthropic.com

refactor: extract compression stats functions into stats_export.py

Co-Authored-By: Claude Haiku 4.5 noreply@anthropic.com

refactor: extract ContextManager orchestrator into manager.py

Co-Authored-By: Claude Haiku 4.5 noreply@anthropic.com

fix: correct relative import depth for utils.token_estimation

The token_estimation module lives at core/utils/, not agents/utils/.
From agent_context/ sub-package, three dots (…utils) are needed
instead of two (..utils).
Co-Authored-By: Claude Haiku 4.5 noreply@anthropic.com

refactor: wire agent_context package with init.py re-exports and remove monolith

Co-Authored-By: Claude Haiku 4.5 noreply@anthropic.com

refactor: update test loader for agent_context package structure

Co-Authored-By: Claude Haiku 4.5 noreply@anthropic.com

refactor: update tests to use standalone functions from decomposed agent_context package

Co-Authored-By: Claude Haiku 4.5 noreply@anthropic.com

fix: align extra compression tests with v2 compressor behavior

The v2 PreviousCompressor and CurrentCompressor do not fall through
from incremental to fresh when LLM returns None - they return
PreviousCompressResult/CurrentCompressResult(summary_text=None)
immediately. Updated tests P3, C4 to match this behavior.
Updated P4 and C6_asymmetry to patch _summarize_pairs with
PreviousCompressResult instead of raw tuples.
Co-Authored-By: Claude Haiku 4.5 noreply@anthropic.com

fix: correct relative import depth for context_runtime.contracts

The context_runtime package lives at core/context_runtime/, not
agents/context_runtime/. From agent_context/ sub-package, three dots
(…context_runtime) are needed instead of two (..context_runtime).
Co-Authored-By: Claude Haiku 4.5 noreply@anthropic.com

chore: untrack temp_scripts and settings.local before PR

Co-Authored-By: Claude noreply@anthropic.com

chore: restore .claude/settings.local.json to match upstream

Co-Authored-By: Claude noreply@anthropic.com

test: add coverage for stats_export, step_renderer, and budget modules


New test_stats_export.py: 21 tests covering all pure functions (100%)
New test_step_renderer.py: 24 tests covering truncation, rendering,
compress_history_offline with mock LLM (49%→86%)
Extended test_pure_functions.py: tests for _is_context_length_error,
has_invoked_tools, message_role, trim_pairs_to_budget (92%→97%)

Overall agent_context package coverage: 71% → 81%
Co-Authored-By: Claude noreply@anthropic.com

test: add llm_summary error-handling and output-format coverage (72%→100%)

Co-Authored-By: Claude noreply@anthropic.com

test: cover _step_stream uncompressed estimation path in core_agent

Adds two tests:

test_step_stream_uses_context_manager_for_uncompressed_est: verifies
_last_uncompressed_est is pulled from ContextManager.get_token_counts()
test_step_stream_falls_back_without_context_manager: verifies fallback
to msg_token_count when context_manager is None

Co-Authored-By: Claude noreply@anthropic.com

test: add fingerprint, change detection, and manager utility tests

Cover the largest untested blocks in manager.py:

_normalize_for_fingerprint, _fingerprint
_change_reasons, _stable_component_fingerprints
_purpose_messages, _messages_from_memory
_without_leading_stable_messages, _canonical_tools
_estimate_tools_tokens, build_compressed_snapshot
init keep_recent_steps cap, token estimation delegates

Manager.py coverage: 69% → 91%, overall: 82% → 92%
Co-Authored-By: Claude Haiku 4.5 noreply@anthropic.com

chore: fix SonarCloud issues in test and llm_summary files


test_pure_functions.py: use ValueError instead of generic Exception (S112)
test_step_renderer.py: remove separator comments flagged as code (S125)
llm_summary.py: use logger.exception() in except blocks (S8572)
test_manager_fingerprint.py: replace unused variable with _ (S1481)

Co-Authored-By: Claude noreply@anthropic.com

refactor: reduce duplication in step_renderer and fix Sonar warnings in compression and test files


Extract _build_offline_user_prompt and _call_model_for_summary helpers from compress_history_offline
Rename unused cache parameter to _cache with alias in current/previous compression (Sonar S1172)
Replace unused idx variables with _ in test_cache_valid (Sonar S1481)
Rename test methods to lowercase convention in test_compress_with_cache_extra (Sonar S100)

Co-Authored-By: Claude Haiku 4.5 noreply@anthropic.com

Co-authored-by: Claude noreply@anthropic.com
Co-authored-by: liudongfei liudongfei4@huawei.com

Enhance image builds and monitoring with no-cache and cleanup (#3344)

Use CCS tag for mainland pushes

Add no-cache support to image builds

Revamp rollout checksums for env and image changes

Add root build wrapper for image and package builds

Sync monitoring defaults and env generation

Harden monitoring deploy and uninstall cleanup

Unify monitoring provider handling in deploy scripts

Clean up stale monitoring services during deployment

Restrict monitoring dashboard to superusers

Restrict monitoring dashboard to superusers

Relocate monitoring env files to deploy/env

Unify monitoring env handling for deploys

Show image tag examples in deployment source selector

同步修改文档

Refactor agent generation workflow

Add interactive deploy config mode

Enable default config mode in offline deploy wrapper

Stop persisting appVersion in deployment config

Add defaults mode to deploy wrappers



Co-authored-by: root root@DESKTOP-UARO3HF.localdomain
Co-authored-by: hhhhsc 

feat(ragflow): add RAGFlow search tool (#3378)

Release/v2.2.1 (#3269)

add_greeting_fields_to_agent-develop

feat(knowledge-base): add preserve_source_file and post-index source cleanup


Let knowledge bases opt out of keeping uploaded MinIO copies after indexing
while retaining Elasticsearch chunks for retrieval. Default behavior remains
preserve_source_file=true for backward compatibility.

Add preserve_source_file column (init.sql + v2.2.0_0601 migration)
Accept preserve_source_file on create/update and northbound/vector APIs
Support document DELETE scope=source_only and source_available in listings
Run cleanup_source Celery task when preserve_source_file is false
UI: create-KB toggle, list tag, knowledge-base preview when copy is missing
Update vector-database SDK docs and backend tests


test(data_process): stub knowledge_db, redis_service, and redis in test_worker

Align setup_mocks_for_worker with test_tasks so importing
backend.data_process.worker loads package init without real DB/redis deps.

test(data_process): shim cleanup_source for submit_process_forward_chain tests

remove duplicate import

fix: update unit tests for greeting_message and example_questions fields

add init.sql to sonar.properites

♻️ Improvement: API to MCP conversion service supports configuring headers. (#3194)

♻️ Improvement: API to MCP conversion service supports configuring headers.
[Specification Details]



Front-end and back-end modifications


♻️ Improvement: API to MCP conversion service supports configuring headers.
[Specification Details]


Modify the frontend, after adding, set the HTTP headers to empty.
Modify test cases.


♻️ Improvement: Enhance processing of ES index names in memory banks. (#3196)

[Specification Details]

Replace all symbols in the index name that do not meet the rules with “_”.
Modify test cases.


feat: add active memory tools (StoreMemoryTool, SearchMemoryTool) (#3197)


Implement StoreMemoryTool for explicit memory storage during agent reasoning
Implement SearchMemoryTool for on-demand memory retrieval during conversations
Integrate tools into agent creation flow (create_agent_info.py)
Register tools in nexent_agent.py and tools/init.py
Add MEMORY_OPERATION tool sign for proper categorization
Fix memory_core.py cache key to include event loop ID (prevents cross-loop conflicts)
Add comprehensive test coverage for both tools
Add procedural memory verification documentation

Tools follow existing patterns: lazy imports, observer integration, error handling,
and respect user memory preferences (agent_share_option, disabled_agent_ids).
Co-authored-by: Dallas98 40557804+Dallas98@users.noreply.github.com

🐛 Bugfix: skill names and descriptions never load to context (#3205)

🐛 Bugfix: skill names and descriptions never load to context

🐛 Bugfix: skill names and descriptions never load to context

🐛 Bugfix: skill names and descriptions never load to context

🐛 Bugfix: official skills not copied to target directory

🐛 Bugfix: official skills not copied to target directory

Feat: add selected count badges to tool/skill pool labels (#3206)


Co-authored-by: chase byzhangxin11@126.com

🐛 Bugfix: Fix attribution error when tool calling error (#3208)

✨ Feat: Add support for Word document generation, preview, and download (#3191)

Feat: Add support for Word document generation, preview, and download

Potential fix for pull request finding


Co-authored-by: Copilot Autofix powered by AI 175728472+Copilot@users.noreply.github.com

Potential fix for pull request finding

Co-authored-by: Copilot Autofix powered by AI 175728472+Copilot@users.noreply.github.com

Restrict uploads to a known safe workspace/output directory

修改单元测试

修复单元测试

Bugfix: Store uploaded files in Minio for conversation messages to enable file visibility in history



Co-authored-by: Copilot Autofix powered by AI 175728472+Copilot@users.noreply.github.com

✨Feat:Enhance prompt optimization by integrating openjiuwen and fix related bugs (#3190)

✨Feat：add prompt optimization

🐛Bugfix: dockerbuild failed when running pipefail in python3_11

🔨Optimize： Optimize prompt optimization display page and interaction methods

🐛Bugfix: fix dependencies replication

🎨:Optimize frontend prompts and loading interface

🔧 Refactor: Update imports and remove redundant ENABLE_JIUWEN_SDK import in prompt_service.py

🔧 Refactor: Correct import path for NexentCapabilityError and enhance test coverage for prompt optimization service

🔧 Refactor: Update import paths for exception handling and improve logging formatting in prompt_service.py

🔧 Refactor: Simplify lazy imports in jiuwen_sdk_adapter.py and update import paths in prompt_service.py

🔧 Refactor: Enhance Jiuwen SDK adapter handling and improve test stubs in prompt_service.py and related test files

🧪test:Pydantic model for PromptTemplateRequest in test_prompt_template_app.py

🔧 Refactor: Remove unnecessary dependency exclusions from pyproject.toml

🔧 Update: Upgrade huggingface_hub dependency version in pyproject.toml

🔧 Update: Exclude unnecessary transitive dependencies and adjust huggingface_hub version in pyproject.toml

🔧 Test: Add mock modules for unstructured inference and set up package paths in test files

🔧 Test: Enhance test setup by adding optional SDK mocks and cleaning up module imports in data processing tests

🔧 Test: Consolidate mock module setup for unstructured inference across multiple test files

🔧 Test: Remove unused optional SDK mocks from test configuration

🔧 Refactor: Clean up imports and enhance dynamic loading of fastmcp components in Docker client

📦update:sdk dependence update

Add CAS SSO integration and improve logout handling (#3072)

feat: add CAS SSO integration

Skip CAS logout when CAS_LOGOUT_URL is unset

取消转义

Improve CAS logout handling and confirm user logout

Disable account deletion for CAS users

Add CAS session init SQL and k8s config

clean code

Remove agent guardrails design doc from tracking

补充文档



Co-authored-by: hhhhsc 

🐛Bugfix: Remove unnecessary dependency exclusions and upgrade huggingface_hub version in pyproject.toml (#3211)

refactor: move current time from system prompt to user message for prompt cache stability (#3203)


Remove {{time}} from all 4 prompt YAML templates (manager/managed × en/zh)
and strip time_str from the context_utils pipeline (_format_app_context,
build_skeleton_header_component, build_context_components,
build_app_context_string). Also remove time from create_agent_info render
kwargs and build_context_components call.
In CoreAgent.run, prepend [Current time: …] to self.task so the timestamp
travels with the user message instead of being baked into the system prompt.
This makes the rendered system prompt fully deterministic per (agent_id,
tenant_id, version_no, language) — enabling prompt/KV cache hits across
requests for the same agent config.
Sync test_context_utils.py: drop time_str= from 3 test cases.
Remove unused datetime imports from context_utils.py and create_agent_info.py.

🐛 Bugfix: Fixed the issue of being unable to add MCP services via containerization. (#3213)

[Specification Details]

Modify the DEFAULT_NETWORK_NAME when starting the MCP service in the container to match the name in docker-compose.
Modify the parameters passed to the add_mcp_service method; custom_headers defaults to None.


🐛 Bugfix: Fixed the issue where uploaded text files could not be parsed during a session. (#3219)

🐛 Bugfix: Fixed the issue where uploaded text files could not be parsed during a session.
[Specification Details]



The return parameter of the file_process method has changed and needs to be unpacked.


🐛 Bugfix: Fixed the issue where uploaded text files could not be parsed during a session.
[Specification Details]


Modify test case.


🐛 Bugfix: Fixed an issue where the MCP service could not be added correctly after updating the FastMCP version. (#3222)

[Specification Details]

Add kwargs to the create_httpx_client function to accept all additional parameters.


🐛 Bugfix: Fix incomplete display of tenant resources page after window resize (#3215)

Move non-shadcn ui component to other folder

Bugfix: Fix incomplete display of tenant resources page after window resize

Bugfix: Fix incomplete display of tenant resources page after window resize

Add agent marketplace repository and version pinning for sub-agents (#3239)

feat: add agent marketplace repository and pin sub-agent versions at publish


Introduce ag_agent_repository_t with list/status/publish/import APIs for
frozen agent snapshots. Pin selected_agent_version_no on agent relations when
publishing so sub-agents resolve to a fixed version at runtime. Extend agent
export/import to bundle skills in ZIP payloads and add embedding model fallback
when no model name is provided.

feat: add agent marketplace repository and pin sub-agent versions at publish

Introduce ag_agent_repository_t with list/status/publish/import APIs for
frozen agent snapshots. Pin selected_agent_version_no on agent relations when
publishing so sub-agents resolve to a fixed version at runtime. Extend agent
export/import to bundle skills in ZIP payloads and add embedding model fallback
when no model name is provided.

feat: add agent marketplace repository and pin sub-agent versions at publish

Introduce ag_agent_repository_t with list/status/publish/import APIs for
frozen agent snapshots. Pin selected_agent_version_no on agent relations when
publishing so sub-agents resolve to a fixed version at runtime. Extend agent
export/import to bundle skills in ZIP payloads and add embedding model fallback
when no model name is provided.

feat: add agent marketplace repository and pin sub-agent versions at publish

Introduce ag_agent_repository_t with list/status/publish/import APIs for
frozen agent snapshots. Pin selected_agent_version_no on agent relations when
publishing so sub-agents resolve to a fixed version at runtime. Extend agent
export/import to bundle skills in ZIP payloads and add embedding model fallback
when no model name is provided.

feat(agent): add verification configuration for agents and update related components (#3174)

feat(agent): add verification configuration for agents and update related components

feat(model): update model type labels and add monitoring dashboard translations

🐛 Bugfix: Fix inability to select agent from agent space to edit (#3240)

Move non-shadcn ui component to other folder

Bugfix: Fix incomplete display of tenant resources page after window resize

Bugfix: Fix incomplete display of tenant resources page after window resize

Bugfix: Fix inability to select agent from agent space to edit

Bugfix: Display correct version info when viewing agent details

Update data agent and ME CAS integration documentation (#3242)

补充dataagent对接文档

补充ME cas对接文档

补充ME cas对接文档



Co-authored-by: hhhhsc 

✨ Add several northbound apis (#3223)

✨ Add several northbound apis

✨ Add several northbound apis

✨ Add several northbound apis

✨ Add several northbound apis

✨ Add several northbound apis

refactor: simplify deployment script by removing unused variables and functions (#3245)

feat(agent): add verification configuration for agents and update related components

feat(model): update model type labels and add monitoring dashboard translations

refactor(build_offline_package): simplify deployment script by removing unused variables and functions

🐛 Bugfix: Adjust agent detail UI layout to accommodate newly added “self-verification” field (#3246)

Move non-shadcn ui component to other folder

Bugfix: Fix incomplete display of tenant resources page after window resize

Bugfix: Fix incomplete display of tenant resources page after window resize

Bugfix: Fix inability to select agent from agent space to edit

Bugfix: Display correct version info when viewing agent details

Bugfix: Adjust agent detail UI layout to accommodate newly added “self-verification” field

补充sql (#3248)

补充sql

扩大limit限制

🐛 Bugfix: Fixed an issue where the MCP service failed to start in a Kubernetes container. (#3254)


[Specification Details]

Modify the pod naming logic to convert all non-compliant characters to -.
Modify test cases.


🐛 Bugfix: knowledge_base_search_tool called with TypeError: argument of type ‘FieldInfo’ is not iterable (#3259)

🐛 Bugfix: Fixed an issue where the one-click rename function failed after importing an agent. (#3258)


[Specification Details]

The frontend does not pass agent_id when calling the regenerate_name API.


Bugfix: Exclude attachments from assistant when saving conversation history (#3261)

Bump APP_VERSION from v2.2.0 to v2.2.1 (#3268)


The default setting for client-side self-validation is “False”.

Co-authored-by: chase byzhangxin11@126.com
Co-authored-by: Chenlifeng 174292121+Lifeng-Chen@users.noreply.github.com
Co-authored-by: Dallas98 40557804+Dallas98@users.noreply.github.com
Co-authored-by: Jason Wang 56037774+JasonW404@users.noreply.github.com
Co-authored-by: Xia Yichen iamjasonxia@126.com
Co-authored-by: JeffWu 45140512+jeffwu-1999@users.noreply.github.com
Co-authored-by: WMC001 46217886+WMC001@users.noreply.github.com
Co-authored-by: xuyaqi xuyaqist@gmail.com
Co-authored-by: Copilot Autofix powered by AI 175728472+Copilot@users.noreply.github.com
Co-authored-by: DongJiBao2001 120021235+DongJiBao2001@users.noreply.github.com
Co-authored-by: hhhhsc701 56435672+hhhhsc701@users.noreply.github.com
Co-authored-by: Dallas98 990259227@qq.com
Co-authored-by: frr 64584192+wuyuanfr@users.noreply.github.com

Revert “Release/v2.2.1 (#3269)” (#3272)

This reverts commit 9ff420ecce6b2ca21a67ce51053205860a76e41a.

feat(ragflow): add RAGFlow search tool


Add RAGFlowSearchTool SDK with list/str compatibility for dataset_ids and doc_id
Add backend ragflow_service and ragflow_app endpoints
Add frontend KB selector support for ragflow in ToolConfigModal and ToolTestPanel
Fix KB selection clearing when switching between tools
Fix missing inputs field in searchAgentInfo tool mapping
Clean up incorrect configParams fallback in ToolTestPanel


test(ragflow): add unit tests for RAGFlow search tool and service

Add 90 tests across 4 files covering ragflow_search_tool, ragflow_service,
nexent_agent RAGFlowSearchTool branch, and tool_configuration_service
ragflow_search validation.
Co-Authored-By: Claude noreply@anthropic.com

test(ragflow): fix SonarCloud issues


Add docstring to _MockTool.init
Replace float == with pytest.approx()
Remove type hint from mock_observer fixture
Remove commented code
Add type: ignore for _validate_ragflow_config edge cases

Co-Authored-By: Claude noreply@anthropic.com

Co-authored-by: panyehong 91180085+YehongPan@users.noreply.github.com
Co-authored-by: chase byzhangxin11@126.com
Co-authored-by: Chenlifeng 174292121+Lifeng-Chen@users.noreply.github.com
Co-authored-by: Dallas98 40557804+Dallas98@users.noreply.github.com
Co-authored-by: Jason Wang 56037774+JasonW404@users.noreply.github.com
Co-authored-by: Xia Yichen iamjasonxia@126.com
Co-authored-by: JeffWu 45140512+jeffwu-1999@users.noreply.github.com
Co-authored-by: WMC001 46217886+WMC001@users.noreply.github.com
Co-authored-by: xuyaqi xuyaqist@gmail.com
Co-authored-by: Copilot Autofix powered by AI 175728472+Copilot@users.noreply.github.com
Co-authored-by: DongJiBao2001 120021235+DongJiBao2001@users.noreply.github.com
Co-authored-by: hhhhsc701 56435672+hhhhsc701@users.noreply.github.com
Co-authored-by: Dallas98 990259227@qq.com
Co-authored-by: frr 64584192+wuyuanfr@users.noreply.github.com
Co-authored-by: Claude noreply@anthropic.com

♻️ Skill now can read files directly with relative path (#3384)

🐛 Bugfix: remove irrational fallback index logic when accurate retrieved results not appeared in semantic retrieved results
♻️ Skill now can read files directly with relative path

🐛 Bugfix: remove irrational fallback index logic when accurate retrieved results not appeared in semantic retrieved results
♻️ Skill now can read files directly with relative path

🐛 Bugfix: remove irrational fallback index logic when accurate retrieved results not appeared in semantic retrieved results
♻️ Skill now can read files directly with relative path

🧪 Add unit test

Add image registry prefix support and optimize offline deployment (#3388)

Add image registry prefix support to offline deployment

Add image registry prefix support to offline deployment

优化构建包

Support source-suffixed offline packages and configurable init image

k8s部分参数落盘

clean code



Co-authored-by: hhhhsc 

feat(agent-repository): remove categories and allow custom emoji icons (#3367)

Release/v2.2.1 (#3269)

add_greeting_fields_to_agent-develop

feat(knowledge-base): add preserve_source_file and post-index source cleanup


Let knowledge bases opt out of keeping uploaded MinIO copies after indexing
while retaining Elasticsearch chunks for retrieval. Default behavior remains
preserve_source_file=true for backward compatibility.

Add preserve_source_file column (init.sql + v2.2.0_0601 migration)
Accept preserve_source_file on create/update and northbound/vector APIs
Support document DELETE scope=source_only and source_available in listings
Run cleanup_source Celery task when preserve_source_file is false
UI: create-KB toggle, list tag, knowledge-base preview when copy is missing
Update vector-database SDK docs and backend tests


test(data_process): stub knowledge_db, redis_service, and redis in test_worker

Align setup_mocks_for_worker with test_tasks so importing
backend.data_process.worker loads package init without real DB/redis deps.

test(data_process): shim cleanup_source for submit_process_forward_chain tests

remove duplicate import

fix: update unit tests for greeting_message and example_questions fields

add init.sql to sonar.properites

♻️ Improvement: API to MCP conversion service supports configuring headers. (#3194)

♻️ Improvement: API to MCP conversion service supports configuring headers.
[Specification Details]



Front-end and back-end modifications


♻️ Improvement: API to MCP conversion service supports configuring headers.
[Specification Details]


Modify the frontend, after adding, set the HTTP headers to empty.
Modify test cases.


♻️ Improvement: Enhance processing of ES index names in memory banks. (#3196)

[Specification Details]

Replace all symbols in the index name that do not meet the rules with “_”.
Modify test cases.


feat: add active memory tools (StoreMemoryTool, SearchMemoryTool) (#3197)


Implement StoreMemoryTool for explicit memory storage during agent reasoning
Implement SearchMemoryTool for on-demand memory retrieval during conversations
Integrate tools into agent creation flow (create_agent_info.py)
Register tools in nexent_agent.py and tools/init.py
Add MEMORY_OPERATION tool sign for proper categorization
Fix memory_core.py cache key to include event loop ID (prevents cross-loop conflicts)
Add comprehensive test coverage for both tools
Add procedural memory verification documentation

Tools follow existing patterns: lazy imports, observer integration, error handling,
and respect user memory preferences (agent_share_option, disabled_agent_ids).
Co-authored-by: Dallas98 40557804+Dallas98@users.noreply.github.com

🐛 Bugfix: skill names and descriptions never load to context (#3205)

🐛 Bugfix: skill names and descriptions never load to context

🐛 Bugfix: skill names and descriptions never load to context

🐛 Bugfix: skill names and descriptions never load to context

🐛 Bugfix: official skills not copied to target directory

🐛 Bugfix: official skills not copied to target directory

Feat: add selected count badges to tool/skill pool labels (#3206)


Co-authored-by: chase byzhangxin11@126.com

🐛 Bugfix: Fix attribution error when tool calling error (#3208)

✨ Feat: Add support for Word document generation, preview, and download (#3191)

Feat: Add support for Word document generation, preview, and download

Potential fix for pull request finding


Co-authored-by: Copilot Autofix powered by AI 175728472+Copilot@users.noreply.github.com

Potential fix for pull request finding

Co-authored-by: Copilot Autofix powered by AI 175728472+Copilot@users.noreply.github.com

Restrict uploads to a known safe workspace/output directory

修改单元测试

修复单元测试

Bugfix: Store uploaded files in Minio for conversation messages to enable file visibility in history



Co-authored-by: Copilot Autofix powered by AI 175728472+Copilot@users.noreply.github.com

✨Feat:Enhance prompt optimization by integrating openjiuwen and fix related bugs (#3190)

✨Feat：add prompt optimization

🐛Bugfix: dockerbuild failed when running pipefail in python3_11

🔨Optimize： Optimize prompt optimization display page and interaction methods

🐛Bugfix: fix dependencies replication

🎨:Optimize frontend prompts and loading interface

🔧 Refactor: Update imports and remove redundant ENABLE_JIUWEN_SDK import in prompt_service.py

🔧 Refactor: Correct import path for NexentCapabilityError and enhance test coverage for prompt optimization service

🔧 Refactor: Update import paths for exception handling and improve logging formatting in prompt_service.py

🔧 Refactor: Simplify lazy imports in jiuwen_sdk_adapter.py and update import paths in prompt_service.py

🔧 Refactor: Enhance Jiuwen SDK adapter handling and improve test stubs in prompt_service.py and related test files

🧪test:Pydantic model for PromptTemplateRequest in test_prompt_template_app.py

🔧 Refactor: Remove unnecessary dependency exclusions from pyproject.toml

🔧 Update: Upgrade huggingface_hub dependency version in pyproject.toml

🔧 Update: Exclude unnecessary transitive dependencies and adjust huggingface_hub version in pyproject.toml

🔧 Test: Add mock modules for unstructured inference and set up package paths in test files

🔧 Test: Enhance test setup by adding optional SDK mocks and cleaning up module imports in data processing tests

🔧 Test: Consolidate mock module setup for unstructured inference across multiple test files

🔧 Test: Remove unused optional SDK mocks from test configuration

🔧 Refactor: Clean up imports and enhance dynamic loading of fastmcp components in Docker client

📦update:sdk dependence update

Add CAS SSO integration and improve logout handling (#3072)

feat: add CAS SSO integration

Skip CAS logout when CAS_LOGOUT_URL is unset

取消转义

Improve CAS logout handling and confirm user logout

Disable account deletion for CAS users

Add CAS session init SQL and k8s config

clean code

Remove agent guardrails design doc from tracking

补充文档



Co-authored-by: hhhhsc 

🐛Bugfix: Remove unnecessary dependency exclusions and upgrade huggingface_hub version in pyproject.toml (#3211)

refactor: move current time from system prompt to user message for prompt cache stability (#3203)


Remove {{time}} from all 4 prompt YAML templates (manager/managed × en/zh)
and strip time_str from the context_utils pipeline (_format_app_context,
build_skeleton_header_component, build_context_components,
build_app_context_string). Also remove time from create_agent_info render
kwargs and build_context_components call.
In CoreAgent.run, prepend [Current time: …] to self.task so the timestamp
travels with the user message instead of being baked into the system prompt.
This makes the rendered system prompt fully deterministic per (agent_id,
tenant_id, version_no, language) — enabling prompt/KV cache hits across
requests for the same agent config.
Sync test_context_utils.py: drop time_str= from 3 test cases.
Remove unused datetime imports from context_utils.py and create_agent_info.py.

🐛 Bugfix: Fixed the issue of being unable to add MCP services via containerization. (#3213)

[Specification Details]

Modify the DEFAULT_NETWORK_NAME when starting the MCP service in the container to match the name in docker-compose.
Modify the parameters passed to the add_mcp_service method; custom_headers defaults to None.


🐛 Bugfix: Fixed the issue where uploaded text files could not be parsed during a session. (#3219)

🐛 Bugfix: Fixed the issue where uploaded text files could not be parsed during a session.
[Specification Details]



The return parameter of the file_process method has changed and needs to be unpacked.


🐛 Bugfix: Fixed the issue where uploaded text files could not be parsed during a session.
[Specification Details]


Modify test case.


🐛 Bugfix: Fixed an issue where the MCP service could not be added correctly after updating the FastMCP version. (#3222)

[Specification Details]

Add kwargs to the create_httpx_client function to accept all additional parameters.


🐛 Bugfix: Fix incomplete display of tenant resources page after window resize (#3215)

Move non-shadcn ui component to other folder

Bugfix: Fix incomplete display of tenant resources page after window resize

Bugfix: Fix incomplete display of tenant resources page after window resize

Add agent marketplace repository and version pinning for sub-agents (#3239)

feat: add agent marketplace repository and pin sub-agent versions at publish


Introduce ag_agent_repository_t with list/status/publish/import APIs for
frozen agent snapshots. Pin selected_agent_version_no on agent relations when
publishing so sub-agents resolve to a fixed version at runtime. Extend agent
export/import to bundle skills in ZIP payloads and add embedding model fallback
when no model name is provided.

feat: add agent marketplace repository and pin sub-agent versions at publish

Introduce ag_agent_repository_t with list/status/publish/import APIs for
frozen agent snapshots. Pin selected_agent_version_no on agent relations when
publishing so sub-agents resolve to a fixed version at runtime. Extend agent
export/import to bundle skills in ZIP payloads and add embedding model fallback
when no model name is provided.

feat: add agent marketplace repository and pin sub-agent versions at publish

Introduce ag_agent_repository_t with list/status/publish/import APIs for
frozen agent snapshots. Pin selected_agent_version_no on agent relations when
publishing so sub-agents resolve to a fixed version at runtime. Extend agent
export/import to bundle skills in ZIP payloads and add embedding model fallback
when no model name is provided.

feat: add agent marketplace repository and pin sub-agent versions at publish

Introduce ag_agent_repository_t with list/status/publish/import APIs for
frozen agent snapshots. Pin selected_agent_version_no on agent relations when
publishing so sub-agents resolve to a fixed version at runtime. Extend agent
export/import to bundle skills in ZIP payloads and add embedding model fallback
when no model name is provided.

feat(agent): add verification configuration for agents and update related components (#3174)

feat(agent): add verification configuration for agents and update related components

feat(model): update model type labels and add monitoring dashboard translations

🐛 Bugfix: Fix inability to select agent from agent space to edit (#3240)

Move non-shadcn ui component to other folder

Bugfix: Fix incomplete display of tenant resources page after window resize

Bugfix: Fix incomplete display of tenant resources page after window resize

Bugfix: Fix inability to select agent from agent space to edit

Bugfix: Display correct version info when viewing agent details

Update data agent and ME CAS integration documentation (#3242)

补充dataagent对接文档

补充ME cas对接文档

补充ME cas对接文档



Co-authored-by: hhhhsc 

✨ Add several northbound apis (#3223)

✨ Add several northbound apis

✨ Add several northbound apis

✨ Add several northbound apis

✨ Add several northbound apis

✨ Add several northbound apis

refactor: simplify deployment script by removing unused variables and functions (#3245)

feat(agent): add verification configuration for agents and update related components

feat(model): update model type labels and add monitoring dashboard translations

refactor(build_offline_package): simplify deployment script by removing unused variables and functions

🐛 Bugfix: Adjust agent detail UI layout to accommodate newly added “self-verification” field (#3246)

Move non-shadcn ui component to other folder

Bugfix: Fix incomplete display of tenant resources page after window resize

Bugfix: Fix incomplete display of tenant resources page after window resize

Bugfix: Fix inability to select agent from agent space to edit

Bugfix: Display correct version info when viewing agent details

Bugfix: Adjust agent detail UI layout to accommodate newly added “self-verification” field

补充sql (#3248)

补充sql

扩大limit限制

🐛 Bugfix: Fixed an issue where the MCP service failed to start in a Kubernetes container. (#3254)


[Specification Details]

Modify the pod naming logic to convert all non-compliant characters to -.
Modify test cases.


🐛 Bugfix: knowledge_base_search_tool called with TypeError: argument of type ‘FieldInfo’ is not iterable (#3259)

🐛 Bugfix: Fixed an issue where the one-click rename function failed after importing an agent. (#3258)


[Specification Details]

The frontend does not pass agent_id when calling the regenerate_name API.


Bugfix: Exclude attachments from assistant when saving conversation history (#3261)

Bump APP_VERSION from v2.2.0 to v2.2.1 (#3268)


The default setting for client-side self-validation is “False”.

Co-authored-by: chase byzhangxin11@126.com
Co-authored-by: Chenlifeng 174292121+Lifeng-Chen@users.noreply.github.com
Co-authored-by: Dallas98 40557804+Dallas98@users.noreply.github.com
Co-authored-by: Jason Wang 56037774+JasonW404@users.noreply.github.com
Co-authored-by: Xia Yichen iamjasonxia@126.com
Co-authored-by: JeffWu 45140512+jeffwu-1999@users.noreply.github.com
Co-authored-by: WMC001 46217886+WMC001@users.noreply.github.com
Co-authored-by: xuyaqi xuyaqist@gmail.com
Co-authored-by: Copilot Autofix powered by AI 175728472+Copilot@users.noreply.github.com
Co-authored-by: DongJiBao2001 120021235+DongJiBao2001@users.noreply.github.com
Co-authored-by: hhhhsc701 56435672+hhhhsc701@users.noreply.github.com
Co-authored-by: Dallas98 990259227@qq.com
Co-authored-by: frr 64584192+wuyuanfr@users.noreply.github.com

Revert “Release/v2.2.1 (#3269)” (#3272)

This reverts commit 9ff420ecce6b2ca21a67ce51053205860a76e41a.

feat(agent-repository): remove categories and allow custom emoji icons

feat(agent-space): improve mine tab UX with delete, navigation, and author display



Add delete action for agents in mine tab with confirmation modal
Navigate back to agent repository when editing from agent-space
Persist agent-space tab state via URL query params (?tab=mine)
Display author in repository detail modal and map author field
Auto-fill agent author from user email on create
Adjust agents page header layout to accommodate back button


fix conflict

fix conflict

fix: delete test ts file



Co-authored-by: panyehong 91180085+YehongPan@users.noreply.github.com
Co-authored-by: chase byzhangxin11@126.com
Co-authored-by: Dallas98 40557804+Dallas98@users.noreply.github.com
Co-authored-by: Jason Wang 56037774+JasonW404@users.noreply.github.com
Co-authored-by: Xia Yichen iamjasonxia@126.com
Co-authored-by: JeffWu 45140512+jeffwu-1999@users.noreply.github.com
Co-authored-by: WMC001 46217886+WMC001@users.noreply.github.com
Co-authored-by: xuyaqi xuyaqist@gmail.com
Co-authored-by: Copilot Autofix powered by AI 175728472+Copilot@users.noreply.github.com
Co-authored-by: DongJiBao2001 120021235+DongJiBao2001@users.noreply.github.com
Co-authored-by: hhhhsc701 56435672+hhhhsc701@users.noreply.github.com
Co-authored-by: Dallas98 990259227@qq.com
Co-authored-by: frr 64584192+wuyuanfr@users.noreply.github.com

🐛Bugfix: Fix responsive layout issues on knowledge base page (#3381)

🐛 BugFix: show name conflict error inline in knowledge base input (#3251)


Show error message inline below input when KB name already exists, instead of relying on input status alone. Closes #3251.

Add nameStatus state + AlertCircle icon + error text
Change title bar alignment from items-center to items-start
Pass nameStatus from UploadArea to DocumentList via prop


🐛 BugFix: Improve responsive layout of knowledge base creation page (#3251)

fix: improve responsive layout and prevent overflow in knowledge base components

🐛 Bugfix: Fixed an issue with tools relying on large models: previously, if a model was selected and subsequently deleted, the agent would encounter runtime errors without any corresponding notification on the frontend. (#3397)

🐛 Bugfix: Fixed an issue where deleted models could still be selected during debugging. + Internationalization loading description of tools.

🐛 Bugfix: Fixed an issue with tools relying on large models: previously, if a model was selected and subsequently deleted, the agent would encounter runtime errors without any corresponding notification on the frontend.

Disable context component budget pruning (#3394)

🐛Bugfix: Persist conversation agent and verify jwt expiry (#3392)

fix: persist conversation agent and verify jwt expiry

test: cover conversation agent and jwt expiry changes

fix: refresh published agents after deletion

11

♻️ Refactor: Remove the limit on the maximum number of execution steps for the agent. (#3400)

♻️ Refactor: Remove the limit on the maximum number of execution steps for the agent.

♻️ Refactor: Remove the limit on the maximum number of execution steps for the agent.

♻️ Refactor: Remove the limit on the maximum number of execution steps for the agent.

fix context manager builtin tool context (#3401)

支持web config runtime northbound多副本 (#3390)

feat: 支持web config runtime northbound多副本

Use ReadWriteMany for Kubernetes persistence defaults

Normalize PR diff line endings

fix: 修复单测

Fix agent service unit test mocks

feat: 默认单实例

feat: 补充单测

feat: 补充单测

feat: enhance deployment options persistence and loading mechanism

feat: remove multi-replica mode references and improve error logging in northbound service



Co-authored-by: root root@DESKTOP-UARO3HF.localdomain

✨ Feature: add skill repository lifecycle and management UI (#3393)

Add skill repository backend APIs

Add skill repository frontend flow

Refine skill repository build UI

feat: add skill edit modal state

feat: improve skill repository copy, edit, and review flows

feat: refine agent config skill management

test: add skill repository coverage and remove dead code

fix: harden skill editing and repository workflow

fix: address skill repository quality gates

fix: correct skill path validation

fix: stabilize skill path test setup

test: cover skill update by id workflow

fix: resolve skill repository quality gate issues

fix: test



Co-authored-by: sumi2234 sumi2234@noreply.atomgit.com

Add OAuth login mode config and forced redirect handling (#3414)

Co-authored-by: root root@DESKTOP-UARO3HF.localdomain

✨ Feature: MCP market restructure — Repository, My MCPs, Review Center (#3396)

mcp web

mcp web

mcp web

mcp web

mcp web

mcp web

delete version

delete version

local mirror

修复工具验证问题以及工具数量显示问题

增加自定义外部市场mcp名称功能；
增加mcp重复命名检查；

增加工具数量更新功能

增加工具数量更新功能

修复仓库的工具数量显示问题；
修复mcp删除bug

“我的”mcp“申请上架”逻辑问题

修复“我的”mcp开发者显示问题；
修复mcp删除后没有同步到智能体开发mcp列表问题；

修复删除mcp未初始化mcp启用状态的问题

修复市场下载的mcp作者显示问题

外部市场mcp连通性校验

添加MCP服务按钮修改

修复仓库下载的mcp不显示hub的问题

删除smithery mcp市场

修复通过镜像上传mcp不显示工具数量问题

修复mcp来源显示错误

修复审核中心标签数字显示问题

mcp市场“仓库”页面和“我的”页面权限调整：仓库页面为租户内共享，我的页面为用户个人使用；
增加表格迁移；

Update settings.local.json

Delete MCP_MARKET_FRONTEND_BACKEND_MAPPING.md

更新测试用例

fix test case

Quality Gate

Quality Gate

test case

前端修改

审核机制及表设计按照agent仓库修改

审核机制及表设计按照agent仓库修改

test cases

test cases

test cases

test cases

🐛 Bugfix: Fix skill count display error when delete a skill has been selected (#3415)

feat: move /owner-manage left-nav from ASSET_OWNER to SU, add index chunks listing and hybrid search endpoints(#3416)

feat: move /owner-manage left-nav from ASSET_OWNER to SU, add index chunks listing and hybrid search endpoints

feat: move /owner-manage left-nav from ASSET_OWNER to SU, add index chunks listing and hybrid search endpoints

feat: move /owner-manage left-nav from ASSET_OWNER to SU, add index chunks listing and hybrid search endpoints

Bump version from v2.2.2 to v2.3.0

🐛 Bugfix: update skill repository action wording (#3418)

fix: update skill repository action wording

fix: update skill repository action wording

fix: internationalize skill repository UI

fix: remove duplicate skill locale keys (#3423)

fix: Clean up leftover file (#3421)

mcp web

mcp web

mcp web

mcp web

mcp web

mcp web

delete version

delete version

local mirror

修复工具验证问题以及工具数量显示问题

增加自定义外部市场mcp名称功能；
增加mcp重复命名检查；

增加工具数量更新功能

增加工具数量更新功能

修复仓库的工具数量显示问题；
修复mcp删除bug

“我的”mcp“申请上架”逻辑问题

修复“我的”mcp开发者显示问题；
修复mcp删除后没有同步到智能体开发mcp列表问题；

修复删除mcp未初始化mcp启用状态的问题

修复市场下载的mcp作者显示问题

外部市场mcp连通性校验

添加MCP服务按钮修改

修复仓库下载的mcp不显示hub的问题

删除smithery mcp市场

修复通过镜像上传mcp不显示工具数量问题

修复mcp来源显示错误

修复审核中心标签数字显示问题

mcp市场“仓库”页面和“我的”页面权限调整：仓库页面为租户内共享，我的页面为用户个人使用；
增加表格迁移；

Update settings.local.json

Delete MCP_MARKET_FRONTEND_BACKEND_MAPPING.md

更新测试用例

fix test case

Quality Gate

Quality Gate

test case

前端修改

审核机制及表设计按照agent仓库修改

审核机制及表设计按照agent仓库修改

test cases

test cases

test cases

test cases

bug fix

Delete k8s/helm/nexent/charts/nexent-common/files/init.sql

Bugfix: Disable Supabase auto refrsh token, restrict token refresh requests to frontend only (#3422)

Bugfix:add crypto.randomUUID() fallback in http

Bugfix: Update homepage redirect link

Refactor: Auto-create conversation when conversation_id is empty in agent/run

Bugfix: skip conversation auto-create in debug mode

修复单元测试

新增UT

新增UT测试

修改单元测试

Bugfix: Disable Supabase auto refrsh token, restrict token refresh requests to frontend only

Revert “Bugfix: Disable Supabase auto refrsh token, restrict token refresh requests to frontend only”


This reverts commit fb7a2934a5bd6cce111f6b349b8190f52b177e04.

Bugfix: Disable Supabase auto refrsh token, restrict token refresh requests to frontend only

🐛 Fix sequence OWNED BY before table creation in migration v2.3.0_0709 (#3424)

Fix agent skill unselect persistence (#3426)

fix: MCP space - api and frontend bug fixes (#3427)

Fix: remove mcp version number (#3429)

feat: remove version number field from MCP edit modal


Co-Authored-By: Claude Opus 4.7 noreply@anthropic.com

🐛 Fix: remove version badge from review center detail modal

Co-Authored-By: Claude Opus 4.7 noreply@anthropic.com

🐛 Fix: add missing English translations for MCP page

Co-Authored-By: Claude Opus 4.7 noreply@anthropic.com

Co-authored-by: Claude Opus 4.7 noreply@anthropic.com

fix: skill summary  (#3430)

fix skill creation stream parsing

fix copied skill repository publish

test skill stream and export edge cases

test remaining skill stream parser branches



Co-authored-by: Jason Wang 56037774+JasonW404@users.noreply.github.com
Co-authored-by: DongJiBao2001 120021235+DongJiBao2001@users.noreply.github.com
Co-authored-by: gjc199 97944442+gjc199@users.noreply.github.com
Co-authored-by: xuyaqi xuyaqist@gmail.com
Co-authored-by: panyehong 91180085+YehongPan@users.noreply.github.com
Co-authored-by: frr 64584192+wuyuanfr@users.noreply.github.com
Co-authored-by: liudfgoo 49781630+liudfgoo@users.noreply.github.com
Co-authored-by: Claude noreply@anthropic.com
Co-authored-by: liudongfei liudongfei4@huawei.com
Co-authored-by: hhhhsc701 56435672+hhhhsc701@users.noreply.github.com
Co-authored-by: root root@DESKTOP-UARO3HF.localdomain
Co-authored-by: jxl jixiaolongcom@sina.cn
Co-authored-by: chase byzhangxin11@126.com
Co-authored-by: Chenlifeng 174292121+Lifeng-Chen@users.noreply.github.com
Co-authored-by: Xia Yichen iamjasonxia@126.com
Co-authored-by: JeffWu 45140512+jeffwu-1999@users.noreply.github.com
Co-authored-by: WMC001 46217886+WMC001@users.noreply.github.com
Co-authored-by: Copilot Autofix powered by AI 175728472+Copilot@users.noreply.github.com
Co-authored-by: Jinyu Z 1012871848@qq.com
Co-authored-by: Summer-Si 140902149+Summer-Si@users.noreply.github.com
Co-authored-by: sumi2234 sumi2234@noreply.atomgit.com
Co-authored-by: Hankin 837833609@qq.com