Component
Agent (Python runtime)
Describe the feature
Support an explicit verify_build or verify_lint step before the first run_agent that fails the task without invoking the LLM when the repo is already broken.
steps:
- { kind: clone_repo, name: setup }
- { kind: verify_build, name: preflight, gate: strict, on_failure: fail }
- { kind: run_agent, name: implement }
- { kind: verify_build, name: build, gate: regression_only }
- { kind: ensure_pr, name: open_pr, strategy: create }
Use case
What exists today (not sufficient):
clone_repo / setup_repo already runs mise run build and mise run lint deterministically and records build_before / lint_before in RepoSetup.
- If the initial build fails, the task still proceeds to
run_agent — failure is noted in setup notes and prompts tell the agent to run build, but there is no workflow-level fail-fast gate.
- Post-agent
verify_build runs only after the agent consumes tokens.
Gap: Operators need a declarative, deterministic preflight gate — not prompt guidance — to skip LLM execution when the tree is already red.
Orchestrator pre-flight (ARCHITECTURE.md) covers GitHub reachability; this covers repo health after clone.
Proposed solution
- Validator — If a
verify_* step appears before run_agent, gate must be strict or regression_only (not informational); record baseline in workflow_state.json for post-agent regression_only compare.
- Runner — Step order already supported; add test proving preflight failure never invokes
run_agent.
- Cost —
clone_repo already runs build; consider skipping duplicate full build in clone when a preflight verify_build immediately follows, or document opt-in on workflows only.
- Docs — WORKFLOWS.md preflight pattern + cost trade-off.
- Opt-in — Enable on
coding/new-task-v1 only after cold-start cost measurement.
Other information
Acknowledgements
Component
Agent (Python runtime)
Describe the feature
Support an explicit
verify_buildorverify_lintstep before the firstrun_agentthat fails the task without invoking the LLM when the repo is already broken.Use case
What exists today (not sufficient):
clone_repo/setup_repoalready runsmise run buildandmise run lintdeterministically and recordsbuild_before/lint_beforeinRepoSetup.run_agent— failure is noted in setup notes and prompts tell the agent to run build, but there is no workflow-level fail-fast gate.verify_buildruns only after the agent consumes tokens.Gap: Operators need a declarative, deterministic preflight gate — not prompt guidance — to skip LLM execution when the tree is already red.
Orchestrator pre-flight (ARCHITECTURE.md) covers GitHub reachability; this covers repo health after clone.
Proposed solution
verify_*step appears beforerun_agent,gatemust bestrictorregression_only(notinformational); record baseline inworkflow_state.jsonfor post-agentregression_onlycompare.run_agent.clone_repoalready runs build; consider skipping duplicate full build in clone when a preflightverify_buildimmediately follows, or document opt-in on workflows only.coding/new-task-v1only after cold-start cost measurement.Other information
requires_repo: false(existing validator rule).Acknowledgements