Open
Conversation
Summary: - add a real `full_agent` runner for GitHub and GitLab projects that clones an isolated workspace, runs Codex, and posts the generated issue reply back to the tracker - fix multi-project retry behavior by stabilizing issue signatures, replacing the invalid build timeout handling, and clearing trigger labels after each run to prevent comment spam loops - document the new fork behavior and add regression coverage for the workspace, agent runner, and orchestrator helpers Rationale: - multi-project mode needed a true issue-driven Codex path instead of routing `full_agent` through the same build-only pipeline - the original build runner bug and label retry loop made GitHub issue testing noisy and hard to validate in practice - writing the final reply into `.symphony/issue_comment.md` keeps the agent run deterministic and lets Symphony own the final tracker post Tests: - cd elixir && mise exec -- mix test - cd elixir && mise exec -- mix specs.check - cd elixir && mise exec -- mix credo --strict - live-tested full_agent against #2 and verified the `todo` label was removed and a single joke comment was posted Co-authored-by: Codex <codex@openai.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Context
Multi-project mode could detect GitHub and GitLab issues, but
full_agentstill behaved likebuild_onlyand issue-triggered runs could spam comments when retries fired.TL;DR
Wire
full_agentto real Codex issue runs and harden the GitHub/GitLab trigger loop.Summary
full_agentruns.symphony/issue_comment.mdback to GitHub or GitLabAlternatives
full_agentmapped to the build pipeline, but that could not execute issue-text requestsTest Plan
make -C elixir allcd elixir && mise exec -- mix testcd elixir && mise exec -- mix specs.checkcd elixir && mise exec -- mix credo --strictfull_agentonRaistlinMuc/symphony#2and verify label cleanup + single issue comment