ollama-result-handling

Ollama Result Handling

When the helper returns Ollama 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 Ollama marked something as an inference, uncertainty, or follow-up question, keep that distinction.
• Preserve output sections when the prompt asked for them, such as observed facts, inferences, open questions, touched files, or next steps.
• If there are no findings, say that explicitly and keep the residual-risk note brief.
• If Ollama made edits, say so explicitly and list the touched files when the helper provides them.
• For ollama:ollama-rescue, do not turn a failed or incomplete Ollama run into a Claude-side implementation attempt. Report the failure and stop.
• For ollama:ollama-rescue, if Ollama 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, even if the fix is obvious.
• If the helper reports malformed output or a failed Ollama run, include the most actionable stderr lines and stop there instead of guessing.
• If Ollama returns malformed JSON despite JSON-mode being enabled, surface the raw response verbatim with a clear error label ("Ollama returned malformed JSON:") rather than trying to extract or infer fields from it. Prompt the user to retry with a stronger model or to run /ollama:review --wait manually.
• If the helper reports that setup or authentication is required, direct the user to /ollama:setup and do not improvise alternate auth flows.