GitLab Issue To Mr

GitLab Issue to MR Automation

Create a cron automation that watches one or more GitLab projects for issues with a trigger label, starts an OpenHands conversation once per label event with the project's default branch already checked out, and opens a merge request with whatever the agent produced.

The automation script is deterministic: issue discovery, label-event tracking, state persistence, the clone, the branch, the commit, the push, the merge request, the issue comments, and the clone's removal are all handled in Python. The LLM is invoked only to write the code.

The agent is told which issue to implement, not what it says. It fetches the description, the discussion, and whatever they link to itself, so nothing in the prompt goes stale between dispatch and the moment the agent reads it.

That needs read access, so the conversation is handed one secret, GITLAB_TOKEN. AGENT_SECRET_NAMES stays an allow-list: the rest of the deployment's secret store is not reachable from a conversation whose instructions came from an issue.

The deployment's MCP servers are forwarded whole, matching github-pr-reviewer, so a connected GitLab server gives the agent typed tools rather than curl. What those servers reach is reachable from an issue-authored prompt, so connect only servers that may be driven by untrusted text.

The agent also finishes the job: it commits, pushes its branch, and opens the merge request, so the merge request appears when the agent stops rather than on the next poll. The script does not trust that it happened - when the conversation ends it asks GitLab whether the merge request exists, and opens it itself when it does not. origin still carries no credential, so every GitLab command the agent runs has to name GITLAB_TOKEN; the SDK only puts a secret in the environment of a command that mentions it, and masks it in the output.

Prerequisites

Required secret

Verify that the following secret is set in OpenHands Settings -> Secrets:

The api scope is what GitLab grants read and write on issues, notes, branches, and merge requests through one scope; read_api polls happily and then fails at the point of pushing. Developer is the lowest role that can push a branch and open a merge request.

Two things the role does not cover, and which fail the push rather than the poll:

• Protected branches. The default branch is usually protected, but the automation never pushes to it. Protect the branch prefix as well and the push is rejected; leave openhands/issue-* unprotected.
• CI/CD files. An issue asking for a pipeline change makes the agent touch .gitlab-ci.yml. That needs no extra scope, but a project with a protected CI/CD configuration path rejects the push.

When several projects are monitored, the token must cover all of them.

Check with:

curl -s "https://gitlab.com/api/v4/user" \
  -H "PRIVATE-TOKEN: $GITLAB_TOKEN" \
  | python3 -c "import json,sys; d=json.load(sys.stdin); print(d.get('username') or d.get('message'))"

If the token is missing or invalid, inform the user and stop.

Setup Workflow

Follow these steps in order.

Step 1 - Verify GITLAB_TOKEN

Run the curl check above, against the user's instance if it is not gitlab.com.

• If absent: "GITLAB_TOKEN is not set. Please add it in OpenHands Settings -> Secrets." Stop.
• If the API returns {"message": "401 Unauthorized"}: tell the user the token is invalid and ask them to update it. Stop.

Step 2 - Collect the GitLab API URL

Ask: "Which GitLab instance? (Press Enter for gitlab.com. For a self-managed instance give its API root, e.g. https://gitlab.example.com/api/v4.)"

Record as GITLAB_API_URL. Default: https://gitlab.com/api/v4. Use this URL in every check below.

Step 3 - Collect projects

Ask: "Which GitLab projects should be watched? (Format: group/project, e.g. myorg/backend. Subgroups are fine - myorg/team/service. List several separated by commas to serve them all from one automation.)"

Validate access to each project, and confirm the token's role:

PROJECT_ID=$(python3 -c "import urllib.parse,sys; print(urllib.parse.quote(sys.argv[1], safe=''))" "{group}/{project}")
curl -s "${GITLAB_API_URL}/projects/${PROJECT_ID}" \
  -H "PRIVATE-TOKEN: $GITLAB_TOKEN" \
  | python3 -c "
import json, sys
d = json.load(sys.stdin)
if 'message' in d or 'error' in d:
    print('ERROR:', d.get('message') or d.get('error'))
else:
    perms = d.get('permissions') or {}
    levels = [(perms.get(k) or {}).get('access_level') for k in ('project_access', 'group_access')]
    levels = [n for n in levels if isinstance(n, int)]
    role = max(levels) if levels else 'unknown'
    print(f\"Accessible. Default branch: {d.get('default_branch')}. Access level: {role}\")
"

Record every accepted project into PROJECTS = ["{group}/{project}", ...]. If one project fails the check, say which and ask whether to continue without it. An access level below 30 (Developer) means the automation cannot open merge requests there; ask for a token with a higher role.

Each project is polled independently and keeps its own state, so issue numbers never collide between them. The trigger label, branch prefix, and schedule are shared; a project needing different settings wants its own automation.

Step 4 - Collect trigger label

Ask: "Which issue label should trigger an implementation? (Press Enter for the default: openhands.)"

Record the answer as TRIGGER_LABEL. If the label does not exist yet, tell the user that GitLab will still record the event once the label is created and applied to an issue.

The automation works an issue when it sees the latest matching label event for that label. To ask for another attempt later, remove and re-apply the label - that opens a second branch and a second merge request rather than overwriting the first.

Step 5 - Collect the merge request mode

Ask: *"Should the merge requests be opened as drafts?

1. Draft (default) - title prefixed Draft:, ready for a human to mark ready
2. Ready for review - opened as a normal merge request (Press Enter for Draft)"*

Map the choice to DRAFT_MERGE_REQUEST (True or False). GitLab has no draft flag on the merge request API; a draft is a title carrying the Draft: prefix, which the script adds.

Step 6 - Collect the branch prefix

Ask: "What branch prefix should the automation use? (Press Enter for the default: openhands/issue, which produces openhands/issue-42.)"

Record as BRANCH_PREFIX. Keep it free of spaces and of characters git rejects in a ref name, and make sure the prefix is not covered by a protected-branch rule.

Step 7 - Collect cron schedule

Ask: "How often should the automation poll for labelled issues? (Press Enter for the default: every 5 minutes. Use a cron expression for a different interval, e.g. 0 * * * * = hourly)"

Default: */5 * * * *.

Record as CRON_SCHEDULE.

Step 8 - Confirm the secret scope

The agent is handed GITLAB_TOKEN, because it reads the issue and its discussion itself. Ask: "Beyond the GitLab token, does the project's build need a secret of its own - a package registry token, for example? (Press Enter for none.)"

Record the answers appended to the default, as AGENT_SECRET_NAMES = ["GITLAB_TOKEN", "NAME", ...].

Keep it an allow-list. Forwarding the whole secret store would put every credential in the deployment behind a prompt written by whoever opened the issue. If the projects are public and you would rather the conversation held no credential at all, set the list to [] - the agent can still read a public issue unauthenticated, and private projects then stop working.

The deployment's MCP servers are a separate matter: they are forwarded whole, so the conversation can reach everything they expose. Say so, and check the user is willing to have those servers driven by text written by whoever opened an issue. Removing a server from the deployment's MCP settings is the only way to keep it out of these conversations.

Step 9 - Generate the automation script

Read scripts/main.py from this skill's directory. Apply exactly six constant substitutions near the top of the file:

The script also reads a config.json shipped beside it, if there is one, over these constants. That is how the catalog entry (automations/catalog/gitlab-issue-to-mr/) configures an unmodified copy, since a declarative host cannot rewrite Python. This setup path substitutes the constants and ships no config.json, so the two never collide.

Leave MAX_NEW_PER_RUN and DEFAULT_OPENHANDS_URL alone unless the user asks for a different cap or a non-default OpenHands URL.

A project may be given as group/project, as a clone URL, or as an SSH remote; the script normalizes each one at startup and names the value it could not read rather than blaming the token. Subgroups are preserved.

Use a safe string writer such as json.dumps(value) when inserting user-provided project paths, labels, or prefixes into Python string literals. json.dumps(list_of_projects) produces the whole PROJECTS list safely in one step.

Write the customized script to a temporary build directory:

mkdir -p /tmp/issue-to-mr-build
# write the customized main.py to /tmp/issue-to-mr-build/main.py

Validate syntax before packaging:

python3 -m py_compile /tmp/issue-to-mr-build/main.py && echo "Syntax OK"

Fix any syntax errors before proceeding.

Step 10 - Package and upload

Set OPENHANDS_HOST and AUTH_HEADER for the commands below:

• OpenHands Cloud or Enterprise - a <HOST> value is in your system prompt: use it as OPENHANDS_HOST, with AUTH_HEADER="Authorization: Bearer $OPENHANDS_API_KEY"
• Local Agent Canvas - an Automation backend is listed in the <RUNTIME_SERVICES> block of your system context: use its url_from_agent as OPENHANDS_HOST, with AUTH_HEADER="X-Session-API-Key: $OPENHANDS_AUTOMATION_API_KEY"

On OpenHands Cloud or Enterprise each run starts in a fresh sandbox, so the automation keeps its state in the KV store: check that kvStore is listed under features in GET ${OPENHANDS_HOST}/api/automation/v1/capabilities before deploying.

tar -czf /tmp/issue-to-mr.tar.gz -C /tmp/issue-to-mr-build .

TARBALL_PATH=$(curl -s -X POST \
  "${OPENHANDS_HOST}/api/automation/v1/uploads?name=gitlab-issue-to-mr" \
  -H "$AUTH_HEADER" \
  -H "Content-Type: application/gzip" \
  --data-binary @/tmp/issue-to-mr.tar.gz \
  | python3 -c "import json,sys; print(json.load(sys.stdin)['tarball_path'])")

echo "Uploaded: $TARBALL_PATH"

Step 11 - Register the automation

curl -s -X POST "${OPENHANDS_HOST}/api/automation/v1" \
  -H "$AUTH_HEADER" \
  -H "Content-Type: application/json" \
  -d "{
    \"name\": \"GitLab Issue to MR: {project_summary} label {trigger_label}\",
    \"trigger\": {\"type\": \"cron\", \"schedule\": \"{cron_schedule}\"},
    \"tarball_path\": \"$TARBALL_PATH\",
    \"entrypoint\": \"python3 main.py\",
    \"timeout\": 900
  }" | python3 -m json.tool

Use the single project as {project_summary} when there is one, and something like 3 projects when there are several. A poll clones a project per queued issue and pushes finished branches, so the timeout allows for that; a run never waits for an agent to finish, only for it to be started.

Record the returned id.