Skip to content

Commit 0ac090a

Browse files
Darragh-McGonigleerifsxAlex HaynesNimsha V BNarayanan-V-Eswar
authored andcommitted
chore(release): Release of 2.3.0 (#2549)
* release candidate of 2.2.0a0 * feat(runtime): Adds custom agent creation preview (#2281) This PR adds support to the ADK for uploading custom agents and adding connections to them. Addresses WatsonOrchestrate/wxo-agent-experiments#56 Testing Checkout the following branches: https://github.ibm.com/WatsonOrchestrate/wxo-server/tree/alexh/langgraph-style https://github.ibm.com/WatsonOrchestrate/tools-runtime-manager/tree/alexh/langgraph-style https://github.ibm.com/WatsonOrchestrate/wxo-clients/tree/alexh/langgraph-style Running an Agent To run an agent in TRM, you need to have the following prerequisites: Checkout this branch of wxo-server Checkout this branch of wxo-clients Create the connection orchestrate connections add -a openai_api orchestrate connections configure --app-id openai_api --environment draft -t team -k api_key orchestrate connections set-credentials --app-id openai_api --api-key your-api-key --env draft Import the Agent Run the following command to import the agent: orchestrate agents create --style custom --experimental-package-root examples/agents/langgraph/met_agent Connect the Agent to the Connection orchestrate agents connect -n met_agent_openai_v3 -c openai_api Importing your own agent To import your own agent, you need to follow these steps: Create a config.yaml based on this config.yaml Create a function like create_agent in agent.py (this API may change in the future) Create a zip file containing your agent code Run the agents create command pointing at your zip * build * Security issue fix glob (#2418) * builder-ui security fix * 49379 - command updated for builder-ui * chore: update docker image tags to 18-12-2025-c9bad1b * update agent runtime tag * update builder-ui image tag and added feature flag for EPIC-39988 * Update Docproc images for January release (#2439) Co-authored-by: Darragh McGonigle <Darragh.McGonigle@ibm.com> * Feat (channels): auto generate genesys audio connector cred (#2438) * generate secrets * Update .secrets.baseline --------- Co-authored-by: Darragh McGonigle <Darragh.McGonigle@ibm.com> * feat (channel): Add MS Teams and FB Messenger Channels (#2414) * add teams and fb messenger * for create command * teams example * fixing examples contributes to WatsonOrchestrate/wo-tracker#50762 * Instruction for GAC credentials More detailed instructions for GAC credentials contributes to WatsonOrchestrate/wo-tracker#50733 * new examples + fix old examples * add unit tests * add readme for examples * Update .secrets.baseline * update instruction for slack * Contributes to WatsonOrchestrate/wo-tracker#51032 * chore(secrets): Detect Secrets Update * add teams and fb messenger * teams example * new examples + fix old examples --------- Co-authored-by: Darragh McGonigle <darragh.mcgonigle@ibm.com> * chore: adding code and tests for feature wsl, lima when -d is used it checks and increases memory to 24GB (#2412) * chore: adding code and tests for feature wsl, lima whenever it tries to start with <24GB it will start it with 24GB * chore: deleting the warning for native system * chore: deleting the logging for native os * chore: fixing minor bug for when wsl2 didnt exist * chore: update edit_wsl funciton to not deleted infromation from wsl configs * chore: skipped false positive secret detection * chore: make WSLConfigLinesManager to edit the configuration lines of wsl --------- Co-authored-by: Darragh McGonigle <Darragh.McGonigle@ibm.com> * chore: update docker image tags to 06-01-2026-67e4835 * feat/enhance-langflow-commands (#2200) * command controller client * controller logic * completed controller logic * update outdated description * tests for langflow commands * add langflow version/image to --version command * remove top level langflow command * update new clients to use BaseWXOClient * remove broken 'FetchConfigAuthTypes' import --------- Co-authored-by: Darragh McGonigle <Darragh.McGonigle@ibm.com> * Update default.env (#2463) updated default.env Co-authored-by: Darragh McGonigle <Darragh.McGonigle@ibm.com> * chore: fix to not break when the stderr isn't byte (#2476) * Fix circular references openapi (#2464) * chore: adding functionality for circular refs, resolving all objects to plain python types recursively * Update openapi_tool, deleting comment about not supporting ref --------- Co-authored-by: Darragh McGonigle <Darragh.McGonigle@ibm.com> * Feat (channels): Update phone MCP (#2448) * SIP MCP * show generated creds * update description texts * Update .secrets.baseline --------- Co-authored-by: Darragh McGonigle <Darragh.McGonigle@ibm.com> * add OAUTH_REDIRECT_URI env var (#2467) Co-authored-by: Darragh McGonigle <Darragh.McGonigle@ibm.com> * chore(warnings): Cleanup test warnings (#2468) * new image (#2482) * update: ui tag (#2483) * update llm to watsonx/meta-llama/llama-3-2-11b-vision-instruct for all docproc examples (#2497) * chore(secrets): Update detect secrets * [51890] - ADK not resolving tool ids in guidelines (#2475) * fix tool names not showing up in guidelines * remove print --------- Co-authored-by: Darragh McGonigle <Darragh.McGonigle@ibm.com> * unhide aoutdiscover command (#2500) Co-authored-by: Darragh McGonigle <Darragh.McGonigle@ibm.com> * Add chat ask Feature (#2481) * build * Update Docproc images for January release (#2439) Co-authored-by: Darragh McGonigle <Darragh.McGonigle@ibm.com> * Update samples use gpt (#2436) * chore: changed soon withdrawn llama models to groq model * chore: reverting import script * chore: documenting the need to add the groq key * chore: flagging secret false positive * feat (channel): Add MS Teams and FB Messenger Channels (#2414) * add teams and fb messenger * for create command * teams example * fixing examples contributes to WatsonOrchestrate/wo-tracker#50762 * Instruction for GAC credentials More detailed instructions for GAC credentials contributes to WatsonOrchestrate/wo-tracker#50733 * new examples + fix old examples * add unit tests * add readme for examples * Update .secrets.baseline * update instruction for slack * Contributes to WatsonOrchestrate/wo-tracker#51032 * chore(secrets): Detect Secrets Update * add teams and fb messenger * teams example * new examples + fix old examples --------- Co-authored-by: Darragh McGonigle <darragh.mcgonigle@ibm.com> * chore: adding code and tests for feature wsl, lima when -d is used it checks and increases memory to 24GB (#2412) * chore: adding code and tests for feature wsl, lima whenever it tries to start with <24GB it will start it with 24GB * chore: deleting the warning for native system * chore: deleting the logging for native os * chore: fixing minor bug for when wsl2 didnt exist * chore: update edit_wsl funciton to not deleted infromation from wsl configs * chore: skipped false positive secret detection * chore: make WSLConfigLinesManager to edit the configuration lines of wsl --------- Co-authored-by: Darragh McGonigle <Darragh.McGonigle@ibm.com> * chore: update docker image tags to 06-01-2026-67e4835 * chore: adding chat interface to talk to agent - Needs Improvement * chore: added the cli ask chat capability and changed the orchestrate_client to run_client logic to go according to adk guidelines * chore: formatting changes * chore: adding the tests and some small changes in the other files * chore: formatting changes * chore: delete experimental-runs command, add ask in commands file, add agent name instead of id and mapper function to map them * chore: fix tests and renaming of functions create client * chore: add to ask a single utternace question and related test * chore: created the function _execute_agent_interaction so that both interactive and single message mode use it to eliminate code duplication * chore: deleted the single message feature, added the option to ask a question and then it opens the chat * chore: adding more messages when running orchestrate chat --help * chore: delete run_agent function, change ask flag to -n * chore: print actual assistant name instead of assistant * chore(merge): Remove merge artifact --------- Co-authored-by: Eric Marcoux <eric.marcoux@ibm.com> Co-authored-by: Dhaval Sonawane <Dhaval.Sonawane1@ibm.com> Co-authored-by: Darragh McGonigle <Darragh.McGonigle@ibm.com> Co-authored-by: John Hwang <jhhwang21c@ibm.com> Co-authored-by: Narayanan V Eswar <Narayanan.V.Eswar@ibm.com> * 2.3.0: Update Wxo-server & TRM (#2498) * build * feat (channel): Add MS Teams and FB Messenger Channels (#2414) * add teams and fb messenger * for create command * teams example * fixing examples contributes to WatsonOrchestrate/wo-tracker#50762 * Instruction for GAC credentials More detailed instructions for GAC credentials contributes to WatsonOrchestrate/wo-tracker#50733 * new examples + fix old examples * add unit tests * add readme for examples * Update .secrets.baseline * update instruction for slack * Contributes to WatsonOrchestrate/wo-tracker#51032 * chore(secrets): Detect Secrets Update * add teams and fb messenger * teams example * new examples + fix old examples --------- Co-authored-by: Darragh McGonigle <darragh.mcgonigle@ibm.com> * chore: adding code and tests for feature wsl, lima when -d is used it checks and increases memory to 24GB (#2412) * chore: adding code and tests for feature wsl, lima whenever it tries to start with <24GB it will start it with 24GB * chore: deleting the warning for native system * chore: deleting the logging for native os * chore: fixing minor bug for when wsl2 didnt exist * chore: update edit_wsl funciton to not deleted infromation from wsl configs * chore: skipped false positive secret detection * chore: make WSLConfigLinesManager to edit the configuration lines of wsl --------- Co-authored-by: Darragh McGonigle <Darragh.McGonigle@ibm.com> * 2.30: Update Wxo-server & TRM * chore(tags): Update server tag to match worker --------- Co-authored-by: Eric Marcoux <eric.marcoux@ibm.com> Co-authored-by: John Hwang <jhhwang21c@ibm.com> Co-authored-by: Darragh McGonigle <darragh.mcgonigle@ibm.com> Co-authored-by: Panagiotis Christodoulou <Panagiotis.Christodoulou@ibm.com> * feat(flows) - Update flow runtime image for ADK 2.3.0 and onboard flow tracing to agent analytics (#2484) * build * Update samples use gpt (#2436) * chore: changed soon withdrawn llama models to groq model * chore: reverting import script * chore: documenting the need to add the groq key * chore: flagging secret false positive * feat (channel): Add MS Teams and FB Messenger Channels (#2414) * add teams and fb messenger * for create command * teams example * fixing examples contributes to WatsonOrchestrate/wo-tracker#50762 * Instruction for GAC credentials More detailed instructions for GAC credentials contributes to WatsonOrchestrate/wo-tracker#50733 * new examples + fix old examples * add unit tests * add readme for examples * Update .secrets.baseline * update instruction for slack * Contributes to WatsonOrchestrate/wo-tracker#51032 * chore(secrets): Detect Secrets Update * add teams and fb messenger * teams example * new examples + fix old examples --------- Co-authored-by: Darragh McGonigle <darragh.mcgonigle@ibm.com> * chore: adding code and tests for feature wsl, lima when -d is used it checks and increases memory to 24GB (#2412) * chore: adding code and tests for feature wsl, lima whenever it tries to start with <24GB it will start it with 24GB * chore: deleting the warning for native system * chore: deleting the logging for native os * chore: fixing minor bug for when wsl2 didnt exist * chore: update edit_wsl funciton to not deleted infromation from wsl configs * chore: skipped false positive secret detection * chore: make WSLConfigLinesManager to edit the configuration lines of wsl --------- Co-authored-by: Darragh McGonigle <Darragh.McGonigle@ibm.com> * feat(flows) - Update flow runtime image for ADK 2.3.0 * feat(flows) - Onboard flow tracing to agent analytics * feat(flows) - Update flow runtime image for ADK 2.3.0 --------- Co-authored-by: Eric Marcoux <eric.marcoux@ibm.com> Co-authored-by: Panagiotis Christodoulou <Panagiotis.Christodoulou@ibm.com> Co-authored-by: John Hwang <jhhwang21c@ibm.com> Co-authored-by: Darragh McGonigle <darragh.mcgonigle@ibm.com> * [DocProc] Updates the docproc images for end of Jan (#2489) * build * Update samples use gpt (#2436) * chore: changed soon withdrawn llama models to groq model * chore: reverting import script * chore: documenting the need to add the groq key * chore: flagging secret false positive * feat (channel): Add MS Teams and FB Messenger Channels (#2414) * add teams and fb messenger * for create command * teams example * fixing examples contributes to WatsonOrchestrate/wo-tracker#50762 * Instruction for GAC credentials More detailed instructions for GAC credentials contributes to WatsonOrchestrate/wo-tracker#50733 * new examples + fix old examples * add unit tests * add readme for examples * Update .secrets.baseline * update instruction for slack * Contributes to WatsonOrchestrate/wo-tracker#51032 * chore(secrets): Detect Secrets Update * add teams and fb messenger * teams example * new examples + fix old examples --------- Co-authored-by: Darragh McGonigle <darragh.mcgonigle@ibm.com> * chore: adding code and tests for feature wsl, lima when -d is used it checks and increases memory to 24GB (#2412) * chore: adding code and tests for feature wsl, lima whenever it tries to start with <24GB it will start it with 24GB * chore: deleting the warning for native system * chore: deleting the logging for native os * chore: fixing minor bug for when wsl2 didnt exist * chore: update edit_wsl funciton to not deleted infromation from wsl configs * chore: skipped false positive secret detection * chore: make WSLConfigLinesManager to edit the configuration lines of wsl --------- Co-authored-by: Darragh McGonigle <Darragh.McGonigle@ibm.com> * Update DocProc Images for End Jan Release --------- Co-authored-by: Eric Marcoux <eric.marcoux@ibm.com> Co-authored-by: Panagiotis Christodoulou <Panagiotis.Christodoulou@ibm.com> Co-authored-by: John Hwang <jhhwang21c@ibm.com> Co-authored-by: Darragh McGonigle <darragh.mcgonigle@ibm.com> * (fix) WO-52360 add default to multi-choice (#2492) * build * Update samples use gpt (#2436) * chore: changed soon withdrawn llama models to groq model * chore: reverting import script * chore: documenting the need to add the groq key * chore: flagging secret false positive * feat (channel): Add MS Teams and FB Messenger Channels (#2414) * add teams and fb messenger * for create command * teams example * fixing examples contributes to WatsonOrchestrate/wo-tracker#50762 * Instruction for GAC credentials More detailed instructions for GAC credentials contributes to WatsonOrchestrate/wo-tracker#50733 * new examples + fix old examples * add unit tests * add readme for examples * Update .secrets.baseline * update instruction for slack * Contributes to WatsonOrchestrate/wo-tracker#51032 * chore(secrets): Detect Secrets Update * add teams and fb messenger * teams example * new examples + fix old examples --------- Co-authored-by: Darragh McGonigle <darragh.mcgonigle@ibm.com> * chore: adding code and tests for feature wsl, lima when -d is used it checks and increases memory to 24GB (#2412) * chore: adding code and tests for feature wsl, lima whenever it tries to start with <24GB it will start it with 24GB * chore: deleting the warning for native system * chore: deleting the logging for native os * chore: fixing minor bug for when wsl2 didnt exist * chore: update edit_wsl funciton to not deleted infromation from wsl configs * chore: skipped false positive secret detection * chore: make WSLConfigLinesManager to edit the configuration lines of wsl --------- Co-authored-by: Darragh McGonigle <Darragh.McGonigle@ibm.com> * WO-52360 add default to muclti-choice Signed-off-by: Alina Rotarescu <alinayr@ca.ibm.com> --------- Signed-off-by: Alina Rotarescu <alinayr@ca.ibm.com> Co-authored-by: Eric Marcoux <eric.marcoux@ibm.com> Co-authored-by: Panagiotis Christodoulou <Panagiotis.Christodoulou@ibm.com> Co-authored-by: John Hwang <jhhwang21c@ibm.com> Co-authored-by: Darragh McGonigle <darragh.mcgonigle@ibm.com> * clearer create_schema failure reason (#2495) * build * feat (channel): Add MS Teams and FB Messenger Channels (#2414) * add teams and fb messenger * for create command * teams example * fixing examples contributes to WatsonOrchestrate/wo-tracker#50762 * Instruction for GAC credentials More detailed instructions for GAC credentials contributes to WatsonOrchestrate/wo-tracker#50733 * new examples + fix old examples * add unit tests * add readme for examples * Update .secrets.baseline * update instruction for slack * Contributes to WatsonOrchestrate/wo-tracker#51032 * chore(secrets): Detect Secrets Update * add teams and fb messenger * teams example * new examples + fix old examples --------- Co-authored-by: Darragh McGonigle <darragh.mcgonigle@ibm.com> * chore: adding code and tests for feature wsl, lima when -d is used it checks and increases memory to 24GB (#2412) * chore: adding code and tests for feature wsl, lima whenever it tries to start with <24GB it will start it with 24GB * chore: deleting the warning for native system * chore: deleting the logging for native os * chore: fixing minor bug for when wsl2 didnt exist * chore: update edit_wsl funciton to not deleted infromation from wsl configs * chore: skipped false positive secret detection * chore: make WSLConfigLinesManager to edit the configuration lines of wsl --------- Co-authored-by: Darragh McGonigle <Darragh.McGonigle@ibm.com> * clearer create_schema failure reason --------- Co-authored-by: Eric Marcoux <eric.marcoux@ibm.com> Co-authored-by: John Hwang <jhhwang21c@ibm.com> Co-authored-by: Darragh McGonigle <darragh.mcgonigle@ibm.com> Co-authored-by: Panagiotis Christodoulou <Panagiotis.Christodoulou@ibm.com> * feat/modify-context (#2487) * RequestContext object * tool response & __call__ changes * test updates and additions * BuilderUI release bug fixes (#2503) Signed-off-by: Alina Rotarescu <alinayr@ca.ibm.com> * chore: change base endpoint, delete unused libraries (#2502) Co-authored-by: Darragh McGonigle <Darragh.McGonigle@ibm.com> * feat(export): Add export functionality to models and model policies (#2410) * feat(runtime): Adds custom agent creation preview (#2281) This PR adds support to the ADK for uploading custom agents and adding connections to them. Addresses WatsonOrchestrate/wxo-agent-experiments#56 Testing Checkout the following branches: https://github.ibm.com/WatsonOrchestrate/wxo-server/tree/alexh/langgraph-style https://github.ibm.com/WatsonOrchestrate/tools-runtime-manager/tree/alexh/langgraph-style https://github.ibm.com/WatsonOrchestrate/wxo-clients/tree/alexh/langgraph-style Running an Agent To run an agent in TRM, you need to have the following prerequisites: Checkout this branch of wxo-server Checkout this branch of wxo-clients Create the connection orchestrate connections add -a openai_api orchestrate connections configure --app-id openai_api --environment draft -t team -k api_key orchestrate connections set-credentials --app-id openai_api --api-key your-api-key --env draft Import the Agent Run the following command to import the agent: orchestrate agents create --style custom --experimental-package-root examples/agents/langgraph/met_agent Connect the Agent to the Connection orchestrate agents connect -n met_agent_openai_v3 -c openai_api Importing your own agent To import your own agent, you need to follow these steps: Create a config.yaml based on this config.yaml Create a function like create_agent in agent.py (this API may change in the future) Create a zip file containing your agent code Run the agents create command pointing at your zip * build * feat (channel): Add MS Teams and FB Messenger Channels (#2414) * add teams and fb messenger * for create command * teams example * fixing examples contributes to WatsonOrchestrate/wo-tracker#50762 * Instruction for GAC credentials More detailed instructions for GAC credentials contributes to WatsonOrchestrate/wo-tracker#50733 * new examples + fix old examples * add unit tests * add readme for examples * Update .secrets.baseline * update instruction for slack * Contributes to WatsonOrchestrate/wo-tracker#51032 * chore(secrets): Detect Secrets Update * add teams and fb messenger * teams example * new examples + fix old examples --------- Co-authored-by: Darragh McGonigle <darragh.mcgonigle@ibm.com> * chore: adding code and tests for feature wsl, lima when -d is used it checks and increases memory to 24GB (#2412) * chore: adding code and tests for feature wsl, lima whenever it tries to start with <24GB it will start it with 24GB * chore: deleting the warning for native system * chore: deleting the logging for native os * chore: fixing minor bug for when wsl2 didnt exist * chore: update edit_wsl funciton to not deleted infromation from wsl configs * chore: skipped false positive secret detection * chore: make WSLConfigLinesManager to edit the configuration lines of wsl --------- Co-authored-by: Darragh McGonigle <Darragh.McGonigle@ibm.com> * feat(export): Add export functionality to models and model policies Enable exporting models and model policies. Model Export: ``` orchestrate models export -n virtual-model/openai/o4-mini -o examples/local/test2.zip ``` Model Policy Export: ``` orchestrate models policy export -n virtual-policy/openai-load-balance -o examples/local/test4.zip ``` Closes https://github.ibm.com/WatsonOrchestrate/wo-tracker/issues/43633 * Added agents and models. Also includes tests * Update return statement * Update agents controller and export model policy * Export connections for Models * Updated tests for agents controller and models controller * Fix connections export * Update connections export * Add app_id if it exists * chore: update rebase --------- Co-authored-by: Alex Haynes <alex.haynes@ibm.com> Co-authored-by: Eric Marcoux <eric.marcoux@ibm.com> Co-authored-by: John Hwang <jhhwang21c@ibm.com> Co-authored-by: Darragh McGonigle <darragh.mcgonigle@ibm.com> Co-authored-by: Panagiotis Christodoulou <Panagiotis.Christodoulou@ibm.com> * fix(knowledge): Default to dynamic mode, and include migration for older KBs without dynamic mode setting in DB (#2510) Signed-off-by: Zander Bobronnikov <Zander.Bobronnikov@ibm.com> * fix(agent): issue 52856 - latest (#2516) * Fix flow tool issue and stop flows from attaching forms, documents (#2513) * chore: adding pool to wait for flow completion * chore: added hadling of flows that need to attach a file to show message that they cant do so and close the chat * chore: delete info messages, added flow started message as in ui, made the pools not stop after 30 tries but run forever until they get an answer, fixed widgets keyword detection * chore: delete info messages, added flow started message as in ui, fixed widgets keyword detection * build * chore: deleting print and let only logging for errors --------- Co-authored-by: Darragh McGonigle <darragh.mcgonigle@ibm.com> * Fix serialization issue and handle toolresponse in TRM (#2520) * fix/tool-response-mcp-response-format (#2514) * rename ToolResponse result var to content * update tests * move tool response into _internal --------- Co-authored-by: Darragh McGonigle <Darragh.McGonigle@ibm.com> * update builder image * fix/langflow check pod label change (#2519) * change the expected label for the langflow pod * add LANGFLOW_SKIP_AUTH_AUTO_LOGIN=true --------- Co-authored-by: Darragh McGonigle <Darragh.McGonigle@ibm.com> * fix: role issue and a example on context base evaluation (#2511) Co-authored-by: Darragh McGonigle <Darragh.McGonigle@ibm.com> * [52465] - AI builder Collaborator Issue (#2507) * update code and fix tests * remove agent value from yaml --------- Co-authored-by: Darragh McGonigle <Darragh.McGonigle@ibm.com> * Add websockets chat ask (#2525) * chore: trying to add cover for async agent responses- not fully done * chore: add warning message after 30 seconds for user to exit the chat in cli and fix the fetching of reasoning trace in the end for async * fix(flows) - Update flow runtime image for ADK 2.3.0 (#2524) Co-authored-by: Allen Chan <avchan@ca.ibm.com> * bug(builder-ui) - Update builder-ui image for ADK 2.3.0 (#2529) * Builder UI fixes - release Signed-off-by: Alina Rotarescu <alinayr@ca.ibm.com> * Update builder UI tag ADK Release 2.0 Signed-off-by: Alina Rotarescu <alinayr@ca.ibm.com> --------- Signed-off-by: Alina Rotarescu <alinayr@ca.ibm.com> Co-authored-by: Suzette Samoojh <ssamoojh@ca.ibm.com> * MCP Gateway (#2494) * inital pitstop * fixes for mcp gateway * added mcpgateway database * updated for mcp * adding the server db and context forge images * pitstop-image-testing * updated the mcp image with proper pipeline built image * updated pg connection strgin * remove platform for mcp-gateway * fix images * build * feat (channel): Add MS Teams and FB Messenger Channels (#2414) * add teams and fb messenger * for create command * teams example * fixing examples contributes to WatsonOrchestrate/wo-tracker#50762 * Instruction for GAC credentials More detailed instructions for GAC credentials contributes to WatsonOrchestrate/wo-tracker#50733 * new examples + fix old examples * add unit tests * add readme for examples * Update .secrets.baseline * update instruction for slack * Contributes to WatsonOrchestrate/wo-tracker#51032 * chore(secrets): Detect Secrets Update * add teams and fb messenger * teams example * new examples + fix old examples --------- Co-authored-by: Darragh McGonigle <darragh.mcgonigle@ibm.com> * chore: adding code and tests for feature wsl, lima when -d is used it checks and increases memory to 24GB (#2412) * chore: adding code and tests for feature wsl, lima whenever it tries to start with <24GB it will start it with 24GB * chore: deleting the warning for native system * chore: deleting the logging for native os * chore: fixing minor bug for when wsl2 didnt exist * chore: update edit_wsl funciton to not deleted infromation from wsl configs * chore: skipped false positive secret detection * chore: make WSLConfigLinesManager to edit the configuration lines of wsl --------- Co-authored-by: Darragh McGonigle <Darragh.McGonigle@ibm.com> * test mcp gateway * secrets audit * make credentials configurable and fix description/kind mix up when listing toolkits * make credentials configurable and fix description/kind mix up when listing toolkits * update mcp-gateway to new image --------- Co-authored-by: Benjamin Nechicattu <benjamin@ibm.com> Co-authored-by: ramcysiddique <ramcy.siddique@ibm.com> Co-authored-by: Eric Marcoux <eric.marcoux@ibm.com> Co-authored-by: John Hwang <jhhwang21c@ibm.com> Co-authored-by: Darragh McGonigle <darragh.mcgonigle@ibm.com> Co-authored-by: Panagiotis Christodoulou <Panagiotis.Christodoulou@ibm.com> * [53713] - Add comments around Secret Values (#2533) * default and server command file. Adding new comment * comment added to compose file --------- Co-authored-by: Darragh McGonigle <Darragh.McGonigle@ibm.com> * custom agents (#2509) * release candidate of 2.2.0a0 * WIP * WIP * add Dockerfile * mcp working * TRM working * agent runtime * WIP connections * prepare for PR, langgraph style -> custom agent style * clean up for PR * dont base64 encode * separate upload call for agents * fix agent upload * fix agent upload, unique placeholder name * rename agent connect to agent experimental-connect * add experimental-package-root and experimental-config, do zipping for the user, add export * update docker compose * fix agent runtime docker compose * update agent runtime tag * WIP * prefix with experimental, add check that its custom agent * revert compose and default env * add newlines * address comments * only allow in local env * address comments * block run with logs in non local * fix agent upload response parsing * update image tags, fix agent runtime port * fix tests * clean up * fix response parsing on agent updates * clean up * make --capture-logs a flag on an experimental-run command * fix orchestrate client * fix capture logs * fix captured logs log_id lookup location * remove orchestrate client and use run client * allow custom agents in deployed environments * update image tags * fix tools runtime tag * update images to include tool call bug fix --------- Co-authored-by: Eric Marcoux <eric.marcoux@ibm.com> Co-authored-by: Darragh McGonigle <Darragh.McGonigle@ibm.com> * fix/migration manager 2.3.0 (#2537) * fix: mistral supervisor+gpt oss collab not working (#2531) * migration files && MigrationManager class * move migrations & utilize migrations manager for server start * fix bash command warnings * unlink env file * refactor MigrationsManager & VmAccessibleFile for migration and env files * fix tests * (lima) run_docker_command handle **kwargs * minor refactoring * clearer cache sub-directory var name * update tests to reflect incorporation of get_compose_file inside of MigrationsManager * fixes for wsl * remove server worker root --------- Co-authored-by: Cheng Qian <Cheng.Qian@ibm.com> * fix(mcpgateway): Add back migrations (#2540) * fix(tools): Temporarily unnest bytes from the ToolReponse object (#2541) * move env vars to top of file (#2535) Co-authored-by: Darragh McGonigle <Darragh.McGonigle@ibm.com> * ADK UI image update (#2545) Co-authored-by: Darragh McGonigle <Darragh.McGonigle@ibm.com> * Update default.env (#2542) Co-authored-by: Darragh McGonigle <Darragh.McGonigle@ibm.com> * chore(sps): Add agent runtime and mcpgateway --------- Signed-off-by: Alina Rotarescu <alinayr@ca.ibm.com> Signed-off-by: Zander Bobronnikov <Zander.Bobronnikov@ibm.com> Co-authored-by: Eric Marcoux <eric.marcoux@ibm.com> Co-authored-by: Alex Haynes <alex.haynes@ibm.com> Co-authored-by: Nimsha V B <Nimsha.V.B@ibm.com> Co-authored-by: Narayanan V Eswar <Narayanan.V.Eswar@ibm.com> Co-authored-by: shafeen-kn <shafeen.kn@ibm.com> Co-authored-by: Dhaval Sonawane <Dhaval.Sonawane1@ibm.com> Co-authored-by: John Hwang <jhhwang21c@ibm.com> Co-authored-by: Panagiotis Christodoulou <Panagiotis.Christodoulou@ibm.com> Co-authored-by: Benen Bruen <benenbruen@ibm.com> Co-authored-by: Vishnu A <vishnuvinod1@ibm.com> Co-authored-by: Vikram Melkote <Vikram.Melkote@ibm.com> Co-authored-by: Minsa Aji <minsa-aji@ibm.com> Co-authored-by: Nino Joy <nino.joy@ibm.com> Co-authored-by: Phuong Ngo <Phuong.Ngo1@ibm.com> Co-authored-by: Eric Grehan <Eric.Grehan@ibm.com> Co-authored-by: Gokul Krishna R <gok@ibm.com> Co-authored-by: Jiajin Lin <Jiajin.Lin@ibm.com> Co-authored-by: Wenjing Jiang <Wenjing.Jiang@ibm.com> Co-authored-by: Alina Rotarescu <alinayr@ca.ibm.com> Co-authored-by: Juan Zapata Gomez <juangomez@ibm.com> Co-authored-by: Zander Bobronnikov <Zander.Bobronnikov@ibm.com> Co-authored-by: Adhil Salim <adhil@ibm.com> Co-authored-by: Haode Qi <Haode.Qi@ibm.com> Co-authored-by: Allen Chan <avchan@ca.ibm.com> Co-authored-by: Suzette Samoojh <ssamoojh@ca.ibm.com> Co-authored-by: Benjamin Nechicattu <benjamin@ibm.com> Co-authored-by: ramcysiddique <ramcy.siddique@ibm.com> Co-authored-by: Cheng Qian <Cheng.Qian@ibm.com> Co-authored-by: Aishwarya Ravi <Aishwarya.Ravi4@ibm.com> Co-authored-by: Keshav Raj <Keshav.Raj1@ibm.com>
1 parent d5e3cc6 commit 0ac090a

File tree

75 files changed

+4757
-577
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

75 files changed

+4757
-577
lines changed

.secrets.baseline

Lines changed: 39 additions & 31 deletions
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@
33
"files": "package-lock.json|^.secrets.baseline$",
44
"lines": null
55
},
6-
"generated_at": "2026-01-05T11:18:16Z",
6+
"generated_at": "2026-01-19T11:01:11Z",
77
"plugins_used": [
88
{
99
"name": "AWSKeyDetector"
@@ -344,15 +344,15 @@
344344
"hashed_secret": "11fa7c37d697f30e6aee828b4426a10f83ab2380",
345345
"is_secret": false,
346346
"is_verified": false,
347-
"line_number": 76,
347+
"line_number": 92,
348348
"type": "Secret Keyword",
349349
"verified_result": null
350350
},
351351
{
352-
"hashed_secret": "c303df00cd0a72b21c62900b758b06fc541664ce",
352+
"hashed_secret": "29c32f233d04598b3181c0e27ea0ec7a5c949297",
353353
"is_secret": false,
354354
"is_verified": false,
355-
"line_number": 77,
355+
"line_number": 93,
356356
"type": "Secret Keyword",
357357
"verified_result": null
358358
}
@@ -362,7 +362,7 @@
362362
"hashed_secret": "6eae3a5b062c6d0d79f070c26e6d62486b40cb46",
363363
"is_secret": false,
364364
"is_verified": false,
365-
"line_number": 43,
365+
"line_number": 45,
366366
"type": "Secret Keyword",
367367
"verified_result": null
368368
}
@@ -406,7 +406,7 @@
406406
"hashed_secret": "50f013532a9770a2c2cfdc38b7581dd01df69b70",
407407
"is_secret": false,
408408
"is_verified": false,
409-
"line_number": 143,
409+
"line_number": 151,
410410
"type": "Secret Keyword",
411411
"verified_result": null
412412
}
@@ -452,131 +452,139 @@
452452
}
453453
],
454454
"src/ibm_watsonx_orchestrate/developer_edition/resources/docker/compose-lite.yml": [
455+
{
456+
"hashed_secret": "d982fbbf213882e6b45e4b0143d74839eccf03a1",
457+
"is_secret": false,
458+
"is_verified": false,
459+
"line_number": 100,
460+
"type": "Secret Keyword",
461+
"verified_result": null
462+
},
455463
{
456464
"hashed_secret": "ecf77930223e0c677ad818c431c904fea177c6a9",
457465
"is_secret": false,
458466
"is_verified": false,
459-
"line_number": 342,
467+
"line_number": 343,
460468
"type": "Secret Keyword",
461469
"verified_result": null
462470
},
463471
{
464472
"hashed_secret": "e6f1e9eba4122e87c1fac3540d6dd0d984f3400f",
465473
"is_secret": false,
466474
"is_verified": false,
467-
"line_number": 477,
475+
"line_number": 478,
468476
"type": "Secret Keyword",
469477
"verified_result": null
470478
},
471479
{
472480
"hashed_secret": "afd84dd061397dc95c97dfc6423b4d9f6498fb18",
473481
"is_secret": false,
474482
"is_verified": false,
475-
"line_number": 651,
483+
"line_number": 652,
476484
"type": "Secret Keyword",
477485
"verified_result": null
478486
},
479487
{
480488
"hashed_secret": "8053a326b998dd67bbe61e3786afcfd74c696e09",
481489
"is_secret": false,
482490
"is_verified": false,
483-
"line_number": 669,
491+
"line_number": 670,
484492
"type": "Secret Keyword",
485493
"verified_result": null
486494
},
487495
{
488496
"hashed_secret": "fa9beb99e4029ad5a6615399e7bbae21356086b3",
489497
"is_secret": false,
490498
"is_verified": false,
491-
"line_number": 902,
499+
"line_number": 903,
492500
"type": "Secret Keyword",
493501
"verified_result": null
494502
},
495503
{
496504
"hashed_secret": "86db9d41639d6b37c1dd9f8425ccb43c8e5cdc1e",
497505
"is_secret": false,
498506
"is_verified": false,
499-
"line_number": 945,
507+
"line_number": 946,
500508
"type": "Secret Keyword",
501509
"verified_result": null
502510
},
503511
{
504512
"hashed_secret": "a4e59d8ec0a2fc63fb4044f4a287b78c0ded6a1a",
505513
"is_secret": false,
506514
"is_verified": false,
507-
"line_number": 946,
515+
"line_number": 947,
508516
"type": "Secret Keyword",
509517
"verified_result": null
510518
},
511519
{
512520
"hashed_secret": "0a39f2b70b172ce11f8d91a3741fafa6dfc83d90",
513521
"is_secret": false,
514522
"is_verified": false,
515-
"line_number": 948,
523+
"line_number": 949,
516524
"type": "Hex High Entropy String",
517525
"verified_result": null
518526
},
519527
{
520528
"hashed_secret": "e9fe51f94eadabf54dbf2fbbd57188b9abee436e",
521529
"is_secret": false,
522530
"is_verified": false,
523-
"line_number": 994,
531+
"line_number": 995,
524532
"type": "Secret Keyword",
525533
"verified_result": null
526534
},
527535
{
528536
"hashed_secret": "ce66b7447d6f80746f10f53783d1e6c5612cfda5",
529537
"is_secret": false,
530538
"is_verified": false,
531-
"line_number": 1006,
539+
"line_number": 1007,
532540
"type": "Secret Keyword",
533541
"verified_result": null
534542
},
535543
{
536544
"hashed_secret": "b6340f437f9d48d53ec1440e7b1224b09d085891",
537545
"is_secret": false,
538546
"is_verified": false,
539-
"line_number": 1057,
547+
"line_number": 1058,
540548
"type": "Secret Keyword",
541549
"verified_result": null
542550
},
543551
{
544552
"hashed_secret": "79c8ba0e2b683559db1fa1204b0a947a2fe8d3bc",
545553
"is_secret": false,
546554
"is_verified": false,
547-
"line_number": 1257,
555+
"line_number": 1258,
548556
"type": "Secret Keyword",
549557
"verified_result": null
550558
},
551559
{
552560
"hashed_secret": "05be325f77bba3fb3fad73f1d838d835ef00e503",
553561
"is_secret": false,
554562
"is_verified": false,
555-
"line_number": 1322,
563+
"line_number": 1323,
556564
"type": "Secret Keyword",
557565
"verified_result": null
558566
},
559567
{
560568
"hashed_secret": "f39d24020236552be2c31c096706de5bcd5ea3bb",
561569
"is_secret": false,
562570
"is_verified": false,
563-
"line_number": 1354,
571+
"line_number": 1355,
564572
"type": "Secret Keyword",
565573
"verified_result": null
566574
},
567575
{
568576
"hashed_secret": "536eab60de9d1c1046f9b18b08bc10a9dce2f627",
569577
"is_secret": false,
570578
"is_verified": false,
571-
"line_number": 1384,
579+
"line_number": 1385,
572580
"type": "Secret Keyword",
573581
"verified_result": null
574582
},
575583
{
576584
"hashed_secret": "de96274b7fa87252a1201b65325c1fc245b7d822",
577585
"is_secret": false,
578586
"is_verified": false,
579-
"line_number": 1409,
587+
"line_number": 1410,
580588
"type": "Secret Keyword",
581589
"verified_result": null
582590
}
@@ -634,55 +642,55 @@
634642
"hashed_secret": "07596f183f5e91b1778d5e47b2752b8d42aa763d",
635643
"is_secret": false,
636644
"is_verified": false,
637-
"line_number": 132,
645+
"line_number": 130,
638646
"type": "Secret Keyword",
639647
"verified_result": null
640648
},
641649
{
642650
"hashed_secret": "a3751173f4b1d25e5f01e1addea614b18ee2abe2",
643651
"is_secret": false,
644652
"is_verified": false,
645-
"line_number": 152,
653+
"line_number": 151,
646654
"type": "Secret Keyword",
647655
"verified_result": null
648656
},
649657
{
650658
"hashed_secret": "1357b590996d4cecb94c84fffedc250d6ef4961b",
651659
"is_secret": false,
652660
"is_verified": false,
653-
"line_number": 155,
661+
"line_number": 154,
654662
"type": "Secret Keyword",
655663
"verified_result": null
656664
},
657665
{
658666
"hashed_secret": "7e6a3680012346b94b54731e13d8a9ffa3790645",
659667
"is_secret": false,
660668
"is_verified": false,
661-
"line_number": 177,
669+
"line_number": 176,
662670
"type": "Secret Keyword",
663671
"verified_result": null
664672
},
665673
{
666674
"hashed_secret": "fa9beb99e4029ad5a6615399e7bbae21356086b3",
667675
"is_secret": false,
668676
"is_verified": false,
669-
"line_number": 186,
677+
"line_number": 185,
670678
"type": "Secret Keyword",
671679
"verified_result": null
672680
},
673681
{
674682
"hashed_secret": "b0399d2029f64d445bd131ffaa399a42d2f8e7dc",
675683
"is_secret": false,
676684
"is_verified": false,
677-
"line_number": 227,
685+
"line_number": 228,
678686
"type": "Secret Keyword",
679687
"verified_result": null
680688
},
681689
{
682690
"hashed_secret": "c3499c2729730a7f807efb8676a92dcb6f8a3f8f",
683691
"is_secret": false,
684692
"is_verified": false,
685-
"line_number": 230,
693+
"line_number": 231,
686694
"type": "Secret Keyword",
687695
"verified_result": null
688696
}
@@ -720,15 +728,15 @@
720728
"hashed_secret": "3b653202eb692574a8ad22357ba20b12d83f7ada",
721729
"is_secret": false,
722730
"is_verified": false,
723-
"line_number": 243,
731+
"line_number": 244,
724732
"type": "Secret Keyword",
725733
"verified_result": null
726734
},
727735
{
728736
"hashed_secret": "2b6af625779f6ddc57b191c1557c4e652cdb5d47",
729737
"is_secret": false,
730738
"is_verified": false,
731-
"line_number": 244,
739+
"line_number": 245,
732740
"type": "Secret Keyword",
733741
"verified_result": null
734742
}

.sps/utils/release-to-cp-registry.sh

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -35,6 +35,8 @@ document-processing/wo_doc_processing_rag:${DOCPROC_LLMSERVICE_TAG}
3535
document-processing/wo_doc_processing_cache:${DOCPROC_CACHE_TAG}
3636
document-processing/wo_doc_processing_cache_rds_init:${DOCPROC_CACHE_TAG}
3737
wxo-agent-architect-server:${AGENT_ARCHITECT_TAG}
38+
wxo-agent-runtime:${AR_TAG}
39+
mcp-gateway:${MCP_GATEWAY_TAG}
3840
EOF)
3941
4042
for image in $images; do
Lines changed: 44 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,44 @@
1+
### How to run evaluation with context variables
2+
3+
This example demonstrates how to evaluate an agent that uses **context variables**. Context variables allow the agent to receive runtime information (such as the logged-in user's identity) without requiring the user to explicitly provide it.
4+
5+
#### Key Differences from Standard Evaluation
6+
7+
1. **Agent Definition**: The agent includes `context_access_enabled: true` and a `context_variables` list specifying which variables it expects (e.g., `sap_username`).
8+
9+
2. **Test Data**: Each test case includes a `runtime_context` field that provides the context variable values for that test scenario.
10+
11+
#### Setup
12+
13+
1. Run `import-all.sh` to import the tools and agent:
14+
```bash
15+
./examples/evaluations/evaluate_with_context_variable/import-all.sh
16+
```
17+
18+
2. Run the evaluation:
19+
```bash
20+
orchestrate evaluations evaluate -p ./examples/evaluations/evaluate_with_context_variable/ -o ./debug -e .env_file
21+
```
22+
23+
Note: We expect `WATSONX_APIKEY, WATSONX_SPACE_ID` or `WO_INSTANCE, WO_API_KEY` to be part of the environment variables or specified in .env_file.
24+
25+
#### Context Variables in Test Data
26+
27+
The test data files (`data_simple.json`, `data_complex.json`) include a `runtime_context` field:
28+
29+
```json
30+
{
31+
"agent": "hr_agent_context",
32+
"runtime_context": {
33+
"sap_username": "nwaters"
34+
},
35+
...
36+
}
37+
```
38+
39+
This simulates a scenario where the user "nwaters" is already authenticated, and the agent can use this context to automatically look up the user's information without asking for their username.
40+
41+
#### Test Scenarios
42+
43+
- **data_simple.json**: A single user querying their own timeoff schedule using context variables
44+
- **data_complex.json**: A manager querying the timeoff schedules of their direct reports using context variables
Lines changed: 20 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,20 @@
1+
{
2+
"spec_version": "v1",
3+
"kind": "native",
4+
"style": "default",
5+
"name": "hr_agent_context",
6+
"display_name": "HR Agent with Context Variables",
7+
"llm": "groq/openai/gpt-oss-120b",
8+
"description": "An HR Agent that leverages context variables to provide personalized assistance with timeoff, schedules, and direct reports without requiring users to identify themselves.",
9+
"instructions": "You are an HR assistant with access to the following context information:\n - SAP Username: {sap_username}\n\n**Important Guidelines:**\n\n1. **Use Context Variables First**: You already know the user's SAP identity from the context variable above.\n Use {sap_username} to look up the user's assignment_id automatically - do NOT ask the user for their username.\n\n2. **Proactive Assistance**: Since you know who the user is, you can immediately help them with:\n - Looking up their assignment ID using their SAP username\n - Retrieving their timeoff schedule\n - Finding their direct reports (if they are a manager)\n\n3. **Tool Usage Flow**:\n - To get the user's assignment ID: Use get_assignment_id_hr_context with {sap_username}\n - To get timeoff schedule: First get assignment_id, then use get_timeoff_schedule_hr_context\n - To get direct reports: Use get_direct_reports_hr_context with username\n\n4. **Personalization**: Address the user by their SAP username when confirming actions.\n\n5. **If context variables are not available**: Fall back to asking the user for the required information.",
10+
"collaborators": [],
11+
"tools": [
12+
"get_assignment_id_hr_context",
13+
"get_timeoff_schedule_hr_context",
14+
"get_direct_reports_hr_context"
15+
],
16+
"context_access_enabled": true,
17+
"context_variables": [
18+
"sap_username"
19+
]
20+
}

0 commit comments

Comments
 (0)