glm-result-handling

GLM Result Handling

When the helper returns GLM output:

• Preserve the helper's verdict, summary, findings, and next steps structure.
• For review output, present findings first and keep them ordered by severity.
• Use the file paths and line numbers exactly as the helper reports them.
• Preserve evidence boundaries. If GLM marked something as an inference, uncertainty, or follow-up question, keep that distinction.
• If there are no findings, say that explicitly and keep the residual-risk note brief.
• If GLM made edits, say so explicitly and list the touched files when the helper provides them.
• For glm:glm-rescue, do not turn a failed or incomplete GLM run into a Claude-side implementation attempt. Report the failure and stop.
• For glm:glm-rescue, if GLM was never successfully invoked, do not generate a substitute answer at all.
• CRITICAL: After presenting review findings, STOP. Do not make any code changes. Do not fix any issues. You MUST explicitly ask the user which issues, if any, they want fixed before touching a single file. Auto-applying fixes from a review is strictly forbidden.
• If the helper reports malformed output or a failed GLM run, include the most actionable stderr lines and stop there instead of guessing.
• If the helper reports that setup or authentication is required, direct the user to /glm:setup and do not improvise alternate auth flows.