Repository navigation
Conversation
Contributor
|
Warning Review limit reachedYou've used all free OSS reviews for now. Wait for the free limit to reset to keep reviewing this public repository. Next included review available in 19 minutes. View limit details
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
After this merges, Fullsend can pick up work straight from the LCORE Jira board and act on it in this repository, with a human in control of every handoff. JIRA -> Fullsend workflow: Tickets opt into Fullsend assistance by adding the label `repo:lightspeed-core/lightspeed-stack`. A cron workflow can be enabled to poll the LCORE board every five minutes, considering only non-done issues with that label; tickets without that label are invisible to Fullsend. Scheduled polling is turned on by setting the GitHub Actions repository variable `FULLSEND_JIRA_POLL_ENABLED=true` (repo Settings -> Secrets and variables -> Actions -> Variables). Until then the schedule is a no-op, but the workflow can be run manually at any time (Run workflow / workflow_dispatch), so the integration can be validated before scheduled polling is turned on. Polling by itself never dispatches an agent. To ask for triage, a human reviewer adds the `ready-to-triage` label or comments `/fs-triage` on the issue; on the next poll the triage agent reads the issue and posts its assessment back to Jira. Triage stops there on purpose: automatic triage-to-code handoff is disabled, so a human decides whether the work should proceed. To move an issue into implementation, a reviewer adds the `ready-to-code` label (the normal, reviewable handoff) or comments `/fs-code`; the next poll dispatches the code agent, which does the work and opens a GitHub pull request. Ordinary Jira edits do nothing, and an already-present label does not re-fire -- remove and re-add it to retry. Under the hood, agents authenticate to Vertex AI inference through the repository's UIE WIF identity (the `FULLSEND_GCP_WIF_PROVIDER` repo secret, also recorded in .fullsend/config.yaml) and run on the same tested Fullsend release (v0.51.0) as the installed shim workflow. This PR adds the triage and code routing rules as pinned harness overlays. Signed-off-by: Anik Bhattacharjee <anbhatta@redhat.com>
anik120
force-pushed
the
fullsend-JIRA-poller
branch
from
October 30, 2026 21:02
4b3046d to
997692d
Compare
This branch has not been deployed
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.
Description
After this merges, Fullsend can pick up work straight from the LCORE Jira
board and act on it in this repository, with a human in control of every
handoff.
JIRA -> Fullsend workflow:
Tickets opt into Fullsend assistance by adding the label
repo:lightspeed-core/lightspeed-stack.A cron workflow can be enabled to poll the LCORE board every five minutes,
considering only non-done issues with that label; tickets that do not have that label on
the board is invisible to Fullsend.
Scheduled polling is turned on by setting the GitHub Actions repository
variable
FULLSEND_JIRA_POLL_ENABLED=true(repo Settings -> Secrets andvariables -> Actions -> Variables). Until then the schedule is a no-op, but
the workflow can be run manually at any time (Run workflow / workflow_dispatch),
so the integration can be validated before scheduled polling is turned on.
Polling by itself never dispatches an agent. To ask for triage, a human reviewer
adds the
ready-to-triagelabel or comments/fs-triageon the issue; on thenext poll the triage agent reads the issue and posts its assessment back to
Jira. Triage stops there on purpose: automatic triage-to-code handoff is
disabled, so a human decides whether the work should proceed.
To move an issue into implementation, a reviewer adds the
ready-to-codelabel(the normal, reviewable handoff) or comments
/fs-code; the next polldispatches the code agent, which does the work and opens a GitHub pull
request. Ordinary Jira edits do nothing, and an already-present label does not
re-fire -- remove and re-add it to retry.
Under the hood, agents authenticate to Vertex AI inference through the
repository's UIE WIF identity (the
FULLSEND_GCP_WIF_PROVIDERrepo secret, alsorecorded in .fullsend/config.yaml) and run on the same tested Fullsend release
(v0.51.0) as the installed shim workflow.
This PR adds the triage and code routing rules as pinned harness overlays.
Type of change
pyproject.toml+uv.lock]requirements.*.txtfor Konflux]Tools used to create PR
Identify any AI code assistants used in this PR (for transparency and review context)
Related Tickets & Documents
Checklist before requesting a review
Testing