Astron Agent v1.1.1

What's Changed

Based on PRs merged into main since v1.1.0.

New Features

• feat(console): Integrate workflow functionality into the Agent (#1487)
• feat(mcp): add Streamable HTTP with SSE fallback (#1552)

Fixes

• fix(knowledge): load platform config from persistent storage (#1558)
• fix(workflow): allow zero LLM temperature (#1562)
• fix(console): include space context in debug SSE requests (#1569)
• fix(console): prevent blank workflow history poisoning (#1579)
• fix(agent): harden CoT parsing and avoid duplicate LLM calls (#1589)

Improvements

• docs: add agent guidance files (#1534)
• chore: Update README with CNCF Landscape details (#1543)
• docs: add Japanese README (#1109)
• docs(faq): 补齐 FAQ 缺失条目（社区问答 + 维护版 FAQ 文档同步，含截图） (#1553)
• docs: fix translated README license links (#1546)
• docs: register ja locale in VitePress config (#1550)

Astron Agent v1.1.0

This release expands the standalone Agent into a more capable execution surface: Agents can now use configured Workflows, Link plugins, and Mem0-backed memory directly from the standard Agent experience. It also includes security hardening for tool-debug URLs, CI/test stabilization, and documentation cleanup for the v1.1 line.

Highlights

Agent Capabilities

• Workflow invocation inside Agents. Standard Agents can persist workflow capabilities, expose workflows as runtime tool callbacks, and use them from both chat and debug paths. The implementation includes ownership and space-membership validation, workflow runtime service support, response extraction handling, and test coverage for key runtime branches. (#1487)
• Plugin capability for Standard Agents. The Agent ability page can import Link plugins from the plugin store, persist selected tools, reload them in bot details, and pass them into debug/chat requests for runtime invocation. Official/admin-owned plugins are handled as trusted import sources. (#1448)
• Mem0 Agent memory. Added configurable Mem0 memory support for Agents, including scoped memory settings, improved retrieval, app-level memory isolation, non-blocking memory writes, Chinese memory preservation, and related CI/test fixes. (#1479)

Security and Stability

• Hardened official tool debug URL validation and trusted-owner handling to reduce unsafe redirect/debug invocation risk. (#1453)
• Addressed GitHub code-scanning alert no. 54 for server-side request forgery. (#1459)
• Stabilized Superteam CI and remote test checks, including S3 client integration-test setup and remaining remote test failures. (#1429, #1431, #1432, #1433)

Documentation and Maintenance

• Added the v1.0.9 release-notes PDF to homepage resources. (#1442)
• Cleaned up unrelated documentation/files and ignored local agent instruction files in git. (#1438, #1435)

Upgrade Notes

• To use Agent workflow invocation, deploy the Console/Toolkit changes together so configured workflows can be resolved and executed through the new runtime path.
• Review Agent capability settings after upgrade if you plan to enable plugins, workflow tools, or Mem0 memory for existing Agents.

Change Scope

• 154 files changed: 6,489 insertions and 6,559 deletions.
• Full comparison: v1.0.9...v1.1.0

Astron Agent v1.0.9

This release centers on a major overhaul of the standalone Agent (agents created directly in the Console): its chat runtime was rebuilt on Spring AI and gained MCP and Skill capabilities. It also adds team publish approval, an agent workbench redesign, and a round of documentation, examples, and security improvements.

Highlights

Standalone Agent

• Runtime rebuilt on Spring AI. The standalone agent's chat runtime was migrated from a hand-rolled OpenAI-compatible implementation to Spring AI (spring-ai-openai), using OpenAiChatModel and ToolCallback / ToolCallingManager for model calls, streaming, and framework-managed tool execution. Legacy runtime paths were removed. (#1418, #1425)
• MCP (Model Context Protocol) support. Standalone agents can now connect external MCP tools by configuring MCP Server URLs on the capability page; the runtime fetches and invokes those tools and lets the model choose them by description. (#1418, #1426)
• Skill module. A new Skill block on the capability page reuses the resource-management importable-skill list (search / multi-select / remove, up to 30). At runtime each skill exposes read_skill_* (reads SKILL.md and referenced resources) and run_skill_* (executes commands in the E2B script sandbox via a new core/agent endpoint). (#1424, #1427)

Collaboration & Workbench

• Added a team publish approval flow for shared spaces, with OWNER/ADMIN review of workflow/agent publishing. (#1383)
• Redesigned the agent workbench with refined settings and interactions. (#1397)
• Added agent debug conversation history and improved web-search tool orchestration.

Docs, Examples & i18n

• Standardized the VitePress docs site with an i18n layout, edit links, and a contribution guide. (#1406)
• Added a community workflow examples gallery (scaffold, seeds, lint, docs page) and a submission issue template. (#1407, #1408)
• Supplemented the FAQ with community-sourced Q&A (#1413) and refreshed MiniMax M-series model examples (#1373).

Security & Stability

• Hardened code-scanning security checks. (#1398, #1402)
• Tightened agent tool-calling boundaries and stabilized order-dependent toolkit tests. (#1403)

Upgrade Notes

• Standalone agent model selection: the two built-in default Spark models were removed from agent creation — choose a model explicitly (e.g., one configured in Model Management).
• Database migration: Flyway V1.38 adds the chat_bot_base.skills column and runs automatically on startup.
• Skill execution (run_skill): requires an E2B script sandbox configured in resource management. The Console backend reaches core/agent via the AGENT_URL env (defaults to http://core-agent:${CORE_AGENT_PORT} in Docker). read_skill works without a sandbox.

Change Scope

• 248 files changed: 18,358 insertions and 6,136 deletions.
• Full comparison: v1.0.8...v1.0.9

Astron Agent v1.0.8

This release focuses on production readiness across observability, credential management, workflow execution security, and deployment operations. It adds health checks, gateway authentication, platform account management, and several security hardening fixes.

Highlights

Core Capabilities

• Added health check endpoints for core services, including Agent, Workflow, Knowledge, and Memory, making container orchestration, operational checks, and incident diagnosis easier (#1358).
• Added platform account management to centralize platform-level runtime credentials and connect the Console, Knowledge, AI Tools, and plugin invocation paths (#1348).
• Added Workflow gateway authentication based on tenant application credentials (#1352).
• Added script sandbox execution for Workflow code nodes, with related node debugging and sandbox configuration support (#1333).
• Added Astron Agent website deployment support for GitHub Pages and Vercel (#1344).

Security and Stability

• Strengthened tool-debug redirect validation to reduce SSRF risk (#1338).
• Hardened database DML execution checks to prevent SQL injection (#1340).
• Fixed bot list sort direction handling to avoid invalid query parameters affecting query stability (#1342).
• Fixed credential loading across AI Tools, Knowledge document upload, voice, and model invocation paths by moving them to platform account configuration (#1348).
• Removed an unused Agent service database dependency to simplify service startup requirements (#1358).

Deployment and Documentation

• Updated Docker Compose, Helm, Nginx, and authenticated deployment guides with platform account, gateway authentication, and core service configuration notes (#1348, #1352).
• Aligned core router and workflow documentation to reduce integration and troubleshooting overhead (#1335).

Upgrade Notes

• Before upgrading, review the Docker, Helm, and env example changes for platform account, AI Tools, Knowledge, and Workflow configuration.
• If your deployment relies on health checks or gateway authentication, update the related gateway, tenant, and service configuration together.

Change Scope

• 155 files changed: 6,629 insertions and 2,304 deletions.
• Full comparison: v1.0.7...v1.0.8

Astron Agent v1.0.7

Astron Agent v1.0.7

This release focuses on workflow reliability, automation capabilities, Skill script sandbox execution, team-space data isolation, and operational polish across the Astron Agent platform.

Highlights

• Added Skill script sandbox execution support for Agent nodes, with E2B as the first third-party sandbox provider.
• Added workflow artifact collection for Skill script outputs, allowing generated files to be uploaded to OSS and managed from the workflow file view.
• Added workflow automation scheduling support, enabling workflows to be triggered and managed by schedule.
• Added workflow loop node capability for iterative orchestration scenarios.
• Persisted Ragflow dataset IDs and routed knowledge requests by dataset ID for more stable RAG integration.
• Improved team-space data sharing behavior and strengthened ownership validation for space update/delete APIs.

New Features

• Support Skill script execution in a third-party sandbox from Agent nodes.
  • Resource management now includes a script sandbox configuration entry.
  • E2B is supported as the first sandbox provider through the official SDK.
  • Agent nodes can expose default run_skill_xxx tools and let the model decide when to invoke Skill scripts.
  • Standard SKILL.md format is preserved; no runtime field is required.
• Support workflow file artifacts generated by sandboxed Skill scripts.
  • Script outputs are collected from the sandbox workspace, uploaded to OSS, and associated with the workflow.
  • The workflow UI includes a file entry for viewing, downloading, and deleting generated artifacts.
• Persist Ragflow dataset ID and route by ID (#1250).
• Add workflow automation scheduling and workflow loop node (#1264).

Fixes

• Fixed direct chat execution for workflow Agent nodes using Skills by refreshing Skill OSS presigned URLs before runtime execution, preventing expired SKILL.md download links from causing 403 failures.
• Fixed workflow dialog display issues (#1294).
• Fixed team-space data sharing issues (#1300).
• Added ownership validation for space delete and update endpoints (#1302).
• Fixed CI-related issues (#1309).

Improvements

• Added a script sandbox provider card layout in resource management, leaving room for future sandbox providers beyond E2B.
• Added a clear fallback message when no script sandbox is configured, so models can explain that administrators must configure a sandbox before Skill scripts can run.
• Keep traceback information when sending errors, improving troubleshooting visibility (#1183).
• Added governance documents (#1280).
• Updated RPA configuration for deployment/runtime consistency (#1289).

Upgrade Notes

• No breaking changes are expected for existing deployments.
• To run Skill scripts, administrators must configure a script sandbox provider in resource management. E2B is supported in this release.
• Teams using Skill scripts should verify sandbox configuration, artifact upload settings, and workflow file visibility after upgrade.
• Teams using workflow automation or loop nodes should verify workflow execution behavior after upgrade.
• Operators should pull the latest images and restart the deployment stack to apply this release.

Full Changelog

Changes are based on PRs merged into main since v1.0.6, plus the Skill sandbox execution and artifact-management work included in this release line.

Astron Agent v1.0.6

What's Changed

Based on PRs merged into main since v1.0.5.

New Features

• feat(knowledge): expose optional RAGFlow retrieval parameters (#1231)
• feat: Added skill system，you can now manage skills in the resource management interface and use skills in the plugins of the workflow’s Agent nodes (#1239)
• feat(knowledge): route RAGFlow ops by per-repo datasets (#1242)
• feat: add workflow export to SKILL feature (#1249)

Fixes

• fix(knowledge): forward documentId in /document/split for Ragflow upsert (#1206)
• fix(knowledge): paginate RAGFlow chunks and use id filter for lookups (#1211)
• fix(knowledge): propagate RAGFlow failures instead of swallowing to empty results (#1222)
• fix(ragflow): honor explicit dataset id during upload (#1240)

Improvements

• refactor(knowledge): unify RAGFLOW_DEFAULT_GROUP fallback loader (#1208)

Astron Agent v1.0.5

What's Changed

Based on PRs merged into main since v1.0.4.

New Features

• feat(engine): add parallel execution support for iteration nodes (#1131)
• feat: 新增迭代节点并行模式 (#1134)
• feat: Add agent removal function (#1147)
• feat: Add workflow export as template feature (#1201)

Fixes

• fix: Modify the release workflow (#1136)
• fix: chat_bot_list Data synchronization (#1154)
• fix: Fix HTTPS protocol verification issue (#1156)
• fix: Fix the invalid session ID issue (#1159)
• fix: Extend model to add form field length (#1163)
• fix:Fix the issue of missing link logs during API calls (#1166)
• fix:Fix the issue of the MCP tool displaying blank (#1170)
• fix:fix hub ci (#1176)
• fix(core-link): mock create_engine in database initialization unit tests (#1184)
• fix: resolve Python CI formatting failures and fix workflow unittest (#1185)
• fix(knowledge): RAGFlow RAG重新切片时出现重复的RAGFlow文档 (#1193)

Improvements

• chore: add GitHub-reward form, scripts & actions (#1152)
• chore: fix some nits for make check-python (#1169)
• chore: fix some nits for make check-typescript (#1172)
• chore: fix some nits for make check-java (#1179)
• Delete irrelevant content (#1093)
• refactor(console-backend): improve code quality and make test-java passes (#1182)

Astron Agent v1.0.4

What's Changed

Based on PRs merged into main since v1.0.3.

New Features

• feature: Push localization image (#1128)
• feat: improve MySQL compatibility and streamline model provider configuration (#1135)

Fixes

• No bug fixes in this release

Improvements

• Bugfix/superteam (#1055)
• Remove duplicate event entry from README (#1063)
• Remove duplicate entry for 合肥城市行 (#1064)
• add workflow trace panel (#1078)
• Remove duplicate hackathon entry from README (#1125)
• Update README-zh.md (#1126)
• docs: add tutorial link to README (#1127)
• docs: add open source workflows link to Chinese and English READMEs (#1130)

Astron Agent v1.0.3

What's Changed

✨ New Features

• Add memory nodes and asynchronous task support to workflow engine
• Add node detail template for variable aggregation node
• Add isThink field support for custom models
• Add Variable Aggregation Node
• Add Variable Aggregation Node
• add knowledge expert node support
  feat(link):complete alembic migration for link service
  feat(aitools):Add hot-reload, aio kafka, and new tests
• add x-display response visibility filtering
  feat(aitools):Add Polaris hot loading and asynchronous Kafka features
• Agent link logs pushed to ES
  feat(aitools):add headers param
  feat(link):add alembic
• add stdout support for loguru
• 新增知识库节点智能匹配模式

🐛 Fixes

• add TTL to event lock to prevent permanent locks on service crashes
• Fix online search
• Fix online search
• Fix online search
• Fix online search
• Fix online search
• Fix online search
• delete error test
• correct typo in string literal
• improve string concatenation syntax in test file
• replace Java text block syntax with traditional string concatenation
• replace nonexistent USER_NOT_LOGIN enum with UNAUTHORIZED
• Fix online search
• resolve model validation failure during chat debugging
• resolve model validation issue in bot-debug interface
• Update nginx configuration to properly route workflow API endpoints
• set uid when copying agent in space
• Add reasons why you cannot talk to the agent (#1010)
• fix x-display response visibility filtering
• Avoid displaying the upload button incorrectly on the chat page 🐛 (#987)
  fix(docker):fix I_ABILITY_CHAT_BASE_URL (#979)
• error url (#978)
• show third party model name (#965)
• update_sensitive_sql_info
  fix(link):Modify the unique key constraint for the Tools table.
  fix array-of-objects value extraction returning only first element
• fix error handling and add more logs
• change the parameter for updating the audit result (#939)
• Adjust the rpa test cases
• resolve prompt-based agent creation bug (#889)

🔧 Improvements

• remove unused error code ENG_PROTOCOL_VALIDATE_ERROR
• optimize implementation with reduced cyclomatic complexity
• Update deployment documentation
• add Astron Industrial Intelligence Hackathon to ongoing activities (#1016)
• add codex and cc md
• add .claude documentation and skills
• add codex and cc md
• update github workflow
• update training camp credits and add MWC 2026 news
• database project add dangerous function detection
• improve quick start wording and cloud access sentence
• fix quick-start grammar in README
  chore(aitools):Convert path blacklist to whitelist
  refactor(link):optimize kafka send
• database project alembic add create db
• database project remove sensitive information
• database project fix the check issue
• database project add alembic database version record
• database project add alembic database version record
• database project fixed sql injection vulnerability related to system keywords
• common project modify set extend method
• common project add the set extend method to redis

What's Changed

• fix: resolve prompt-based agent creation bug by @likes1234-bro in #889
• bugfix(plugin): fix JSON import issue by @wq457 in #931
• feat(knowledge): 新增知识库节点智能匹配模式 by @cumthxy in #932
• feat: add stdout support for loguru by @hygao1024 in #934
• feat(link):add alembic by @Alex-Smith-1234 in #936
• feat(aitools):add headers param by @zijian2 in #937
• feat: Agent link logs pushed to ES by @lyj715824 in #938
• fix: change the parameter for updating the audit result by @vsxd in #939
• chore: common project add the set extend method to redis by @sharphu in #940
• add: Add Claude code capability by @lyj715824 in #945
• add: Add Claude code capability by @lyj715824 in #948
• add: Add Claude code capability by @lyj715824 in #949
• chore: database project add alembic database version record by @sharphu in #951
• add: Add Claude code capability by @lyj715824 in #953
• chore: database project alembic add create db by @sharphu in #955
• fix(aitools): fix error handling and add more logs by @zijian2 in #956
• refactor(link):optimize kafka send by @Alex-Smith-1234 in #957
• chore(aitools):Convert path blacklist to whitelist by @zijian2 in #958
• fix array-of-objects value extraction returning only first element by @cumthxy in #959
• Refactor/replace optimize model by @mikasa-code in #962
• add: database model Add redis config by @lyj715824 in #963
• fix(link):Modify the unique key constraint for the Tools table. by @Alex-Smith-1234 in #970
• fix: update_sensitive_sql_info by @BillorBear in #971
• feat(aitools):Add Polaris hot loading and asynchronous Kafka features by @zijian2 in #976
• fix: show third party model name by @slqcode in #965
• feat(link): add x-display response visibility filtering by @pxc1130 in #973
• docs: update training camp credits and add MWC Barcelona 2026 news by @FenjuFu in #977
• fix: error url by @mikasa-code in #978
• fix(docker):fix I_ABILITY_CHAT_BASE_URL by @mikasa-code in #979
• feat(aitools):Add hot-reload, aio kafka, and new tests by @zijian2 in #981
• docs: update github workflow by @lyj715824 in #982
• docs: add codex and cc md by @lyj715824 in #984
• docs: fix README grammar in quick-start and cloud sections by @haosenwang1018 in #966
• docs: improve quick-start wording and Astron Cloud sentence by @haosenwang1018 in #967
• Fixes #972 Avoid displaying the upload button incorrectly on the chat page 🐛 by @lantianhemao in #987
• Add Astron Agent & RPA Hefei Meetup to ongoing activities; restructure News section into Ongoing/Past by @Copilot in #990
• docs(console): add .claude documentation and skills by @zhuxinghan01 in #991
• add: Support other model providers by @lyj715824 in #993
• add: Support other model providers by @lyj715824 in #994
• add: Support other model providers by @lyj715824 in #995
• add: Support other model providers by @lyj715824 in #997
• add: Support other model providers by @lyj715824 in #998
• feat(link):complete alembic migration for link service by @ggfgtonyquan in #992
• add: Support other model providers by @lyj715824 in #1002
• add: Support other model providers by @lyj715824 in #1003
• add: Support other model providers by @lyj715824 in #1004
• add: Support other model providers by @lyj715824 in #1005
• add: Support other model providers by @lyj715824 in #1006
• Bugfix/superteam by @lyj715824 in #1007
• add: Support other model providers by @lyj715824 in #1008
• add: Support other model providers by @lyj715824 in #1009
• fix: Add reasons why you cannot talk to the agent 🐛 by @lantianhemao in #1010
• feat: Add Variable Aggregation Node by @lyj715824 in #1012
• feat(workflow): add knowledge expert node support by @cumthxy in #1001
• feat: Add Variable Aggregation Node by @lyj715824 in #1015
• docs: add Astron Industrial Intelligence Hackathon to ongoing activities by @Copilot in #1016
• feat: Add Variable Aggregation Node by @lyj715824 in #1018
• Bugfix/superteam by @zhuxinghan01 in #1017
• fix(link): fix x-display response visibility filtering by @pxc1130 in #1011
• fix: set uid when copying agent in space by @zhuxinghan01 in #1014
• feat: Add isThink field support for custom models by @Kexinist in #1019
• feat: Add isThink field support for custom models by @Kexinist in #1020
• docs: Update deployment docum...

Astron Agent v1.0.2

What's Changed

✨ New Features

• remove auth check from import/export endpoints
• enhance RPA setup with new services and configurations (#921)
• add auto database creation and improve migration lock mechanism

🐛 Fixes

• restore mypy ignore-missing-imports flag
• code quality and aiohtpp client bug fix

🔧 Improvements

• introduce DatabaseConfig for DB config
• optimize packet guiding exceptions
• exclude enterprise watchdog feature from mypy checks

What's Changed

• fix(aitools): code quality and aiohtpp client bug fix by @zijian2 in #911
• chore: exclude enterprise watchdog feature from mypy checks by @hygao1024 in #912
• 添加插件导入导出功能 by @Xxbys752521 in #913
• feat: add auto database creation and improve migration lock mechanism by @cumthxy in #910
• fix(ci): restore mypy ignore-missing-imports flag by @cumthxy in #924
• feat(docker): enhance RPA setup with new services and configurations by @doctorbruce in #921
• feat(toolkit): remove auth check from import/export endpoints by @Xxbys752521 in #926

Full Changelog: v1.0.1...v1.0.2