odysseus-dev/odysseus · error · HTTPException

No available model endpoint for auto-sort

Error message

No available model endpoint for auto-sort

What it means

Error "No available model endpoint for auto-sort" thrown in odysseus-dev/odysseus.

Source

Thrown at routes/session_routes.py:1204

        if len(session_list) < 2:
            if deleted_empty or deleted_throwaway:
                return {
                    "status": "ok",
                    "updated": 0,
                    "folders": [],
                    "deleted_empty": deleted_empty,
                    "deleted_throwaway": deleted_throwaway,
                    "unfiled_remaining": unfiled_total,
                }
            return {"status": "skipped", "reason": "No unfiled sessions to sort"}

        # Pick an endpoint — prefer admin-configured task endpoint
        from src.task_endpoint import resolve_task_endpoint
        url, model, headers = resolve_task_endpoint(owner=user)
        if not url:
            url, model, headers = _pick_endpoint_for_sort(owner=user)
        if not url:
            raise HTTPException(503, "No available model endpoint for auto-sort")

        # Build prompt
        names_text = "\n".join(f'  "{s["id"][:8]}": "{s["name"]}"' for s in session_list)
        prompt = (
            "You are a session organizer. Group these chat sessions into folders by topic.\n\n"
            "Rules:\n"
            "- Be aggressive about grouping — put EVERY session in a folder\n"
            "- Use short folder names (2-4 words max)\n"
            "- Use the 8-char ID prefixes exactly as given\n"
            "- Output ONLY raw JSON, no markdown fences, no explanation\n\n"
            "Required JSON format:\n"
            '{"folders": {"Folder Name": ["id_prefix1", "id_prefix2"], "Other Folder": ["id_prefix3"]}}\n\n'
            f"Sessions (id_prefix: name):\n{{\n{names_text}\n}}"
        )

        try:
            logger.info(f"Auto-sort: using model={model} at {url}")
            # 16384 (was 4096): with many chats the folder JSON is large, and a

View on GitHub (pinned to f9235ebbf1)

Solutions

1. Configure a utility model for auto-sort in Settings.
2. Add and enable a model endpoint that auto-sort can use.

When it happens

Trigger: Triggered when the corresponding server-side validation or runtime check at the recorded location rejects the request or operation and returns this error message to the caller.

Common situations: See trigger scenarios.

AI-assisted analysis of odysseus-dev/odysseus@f9235ebbf1 (2026-08-14). Data as JSON: /api/errors/9edbd7c04c3c71c9. Report an issue: GitHub.