Bump OpenClaw to 2026.3.13-1 and move Maestro agents to gpt-5-mini#31
Merged
Merged
Conversation
There was a problem hiding this comment.
Pull request overview
Updates the repository’s tracked inventories and supporting docs to align with a newer OpenClaw container image, and adjusts default agent model selections for the Maestro inventory.
Changes:
- Bump
ghcr.io/openclaw/openclawimage references from2026.2.22to2026.3.13-1across inventories and build/runbook docs. - Switch several agents in
inventory/instances.yamlto useopenai/gpt-5-mini. - Simplify the
core-humancustom Dockerfile by removing the runtime patch/build steps and only layering ingws.
Reviewed changes
Copilot reviewed 6 out of 6 changed files in this pull request and generated 4 comments.
Show a summary per file
| File | Description |
|---|---|
| inventory/org.instances.example.yaml | Updates example org inventory Docker image tag. |
| inventory/instances.yaml | Updates Docker image tag and changes default agent models to openai/gpt-5-mini. |
| inventory/instances.example.yaml | Updates template inventory Docker image tag. |
| instances/core-human/config/Dockerfile.custom | Updates base image and removes runtime patch + pnpm build, leaving only gws layer. |
| docs/GOOGLE_CALENDAR_GWS_ROLLOUT.md | Updates example custom image tag used in the build command. |
| docs/BOT_ACCESS_SETUP.md | Updates guidance around telegram-group-allowlist-guard behavior for blocking group sends. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
You can also share your feedback on Copilot code review. Take the survey.
Comment on lines
97
to
+101
| - id: vbarsegyan | ||
| role: human | ||
| workspace: vbarsegyan | ||
| agent_dir: agents/vbarsegyan | ||
| model: openai/gpt-5.1 | ||
| model: openai/gpt-5-mini |
Comment on lines
72
to
76
| - ../templates/openclaw/profiles/human.base.json5 | ||
| - ../instances/core-human/config/instance.overrides.example.json5 | ||
| docker: | ||
| image: ghcr.io/openclaw/openclaw:2026.2.22 | ||
| image: ghcr.io/openclaw/openclaw:2026.3.13-1 | ||
| container_name: openclaw-core-human |
Comment on lines
47
to
51
| - ../templates/openclaw/profiles/human.base.json5 | ||
| - ../orgs/example-org/instances/core-human/config/instance.overrides.example.json5 | ||
| docker: | ||
| image: ghcr.io/openclaw/openclaw:2026.2.22 | ||
| image: ghcr.io/openclaw/openclaw:2026.3.13-1 | ||
| container_name: openclaw-example-org-core-human |
|
|
||
| FROM ghcr.io/openclaw/openclaw:2026.2.22 | ||
| FROM ghcr.io/openclaw/openclaw:2026.3.13-1 | ||
|
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
2026.3.13-1in the shared and example inventoriescore-humancustom image to build from the latest upstream base and remove the obsolete runtime patch build stepinventory/instances.yamltoopenai/gpt-5-miniVerification
docker build -f instances/core-human/config/Dockerfile.custom -t openclaw-core-human-custom:2026.3.13-1-r1 .bash -lc "set -a; source .env; set +a; export INVENTORY_PATH=inventory/instances.local.yaml; ./scripts/deploy-instance.sh core-human"bash -lc "set -a; source .env; set +a; export INVENTORY_PATH=inventory/instances.yaml; ./scripts/deploy-instance.sh maestro-discord-knowledge"bash -lc "set -a; source .env; set +a; export INVENTORY_PATH=inventory/instances.yaml; ./scripts/deploy-instance.sh maestro-discord-systems"bash -lc "set -a; source .env; set +a; export INVENTORY_PATH=inventory/instances.yaml; ./scripts/deploy-instance.sh maestro-discord-infra"openclaw.mjs doctorcompleted forcore-human,maestro-discord-knowledge,maestro-discord-systems, andmaestro-discord-infradrichardson,brain-qa,github-manager, andinfra-triageall returnedokFollow-up
unhealthyafter rollout even though doctor passes and the smoke tests succeed