| """Canned, language-matched refusals for the guardrail layer. |
| |
| Centralized so the three refusal sites — the `out_of_scope` router branch, the |
| input-guard block, and the content-filter fallback — speak with one voice. |
| |
| Deterministic on purpose (no LLM): the refusal must not call the same model that |
| just refused or failed. Language is picked with a tiny marker check (EN default, |
| ID when Indonesian markers are present), mirroring the lightweight detector in |
| `handlers/help.py` — enough for a one-line reply without an LLM round-trip. |
| """ |
|
|
| from __future__ import annotations |
|
|
| import re |
|
|
| |
| |
| |
| _ID_MARKERS = frozenset({ |
| "yang", "dan", "apa", "gimana", "bagaimana", "kenapa", "mengapa", "aku", "saya", |
| "tolong", "ini", "itu", "untuk", "dengan", "tidak", "nggak", "enggak", "bisa", |
| "mau", "buat", "dari", "kamu", "berapa", "kapan", "siapa", "dimana", "adalah", |
| "akan", "sudah", "belum", "lupakan", "abaikan", "kredensial", "tunjukkan", |
| }) |
|
|
|
|
| def _is_indonesian(message: str) -> bool: |
| tokens = re.findall(r"[a-z']+", (message or "").lower()) |
| return any(t in _ID_MARKERS for t in tokens) |
|
|
|
|
| |
| _OUT_OF_SCOPE = { |
| "en": ( |
| "That's outside what I can help with — I'm a data assistant, so I can only work " |
| "with the sources you've connected to Data Eyond. Ask me a question about your " |
| "data, or type /help to see what I can do." |
| ), |
| "id": ( |
| "Itu di luar yang bisa saya bantu — saya asisten data, jadi saya hanya bisa " |
| "bekerja dengan sumber data yang Anda hubungkan ke Data Eyond. Ajukan pertanyaan " |
| "tentang data Anda, atau ketik /help untuk melihat yang bisa saya lakukan." |
| ), |
| } |
|
|
| |
| _BLOCKED = { |
| "en": ( |
| "I can't help with that request. I'm here to analyze the data you've connected — " |
| "ask me a question about your data and I'll take it from there." |
| ), |
| "id": ( |
| "Saya tidak bisa membantu permintaan tersebut. Saya di sini untuk menganalisis " |
| "data yang Anda hubungkan — ajukan pertanyaan tentang data Anda dan saya bantu." |
| ), |
| } |
|
|
|
|
| |
| |
| |
| |
| |
| _DATA_GAP = { |
| "en": ( |
| "I can't answer that from the data sources connected to this analysis. " |
| "{reason}You can bind a source that holds this data, or ask me what's " |
| "available (try /help or \"what data do I have?\")." |
| ), |
| "id": ( |
| "Saya tidak bisa menjawab itu dari sumber data yang terhubung ke " |
| "analisis ini. {reason}Anda bisa menambahkan sumber yang memuat data " |
| "tersebut, atau tanyakan data apa yang tersedia (coba /help atau " |
| "\"data apa yang saya punya?\")." |
| ), |
| } |
|
|
|
|
| |
| |
| |
| _RUN_FAILURE = { |
| "en": ( |
| "I ran the analysis, but every step failed, so I don't have a result I can " |
| "stand behind. {reason}You can try rephrasing the question, or check that " |
| "the connected data source is reachable." |
| ), |
| "id": ( |
| "Saya sudah menjalankan analisisnya, tetapi semua langkah gagal, jadi belum " |
| "ada hasil yang bisa saya laporkan. {reason}Coba ubah pertanyaannya, atau " |
| "periksa apakah sumber data yang terhubung dapat diakses." |
| ), |
| } |
|
|
|
|
| |
| |
| |
| _RAW_ERROR_MARKERS = ("[SQL:", "[parameters:", "psycopg", "sqlalche.me", "Traceback", "LINE ") |
| _MAX_REASON_CHARS = 200 |
|
|
|
|
| def _presentable(reason: str | None) -> str: |
| """The failure detail if it reads as a sentence for a user, else ''.""" |
| detail = (reason or "").strip() |
| if ( |
| not detail |
| or "\n" in detail |
| or len(detail) > _MAX_REASON_CHARS |
| or any(m in detail for m in _RAW_ERROR_MARKERS) |
| ): |
| return "" |
| return detail |
|
|
|
|
| def run_failure_message(reason: str | None, reply_language: str | None = None) -> str: |
| """Answer for an all-steps-failed run (S1a CK1). `reason` is the most specific |
| failure detail available (may be None); `reply_language` as in data_gap_message.""" |
| detail = _presentable(reason) |
| if detail and not detail.endswith((".", "!", "?")): |
| detail += "." |
| lang = "id" if reply_language == "Indonesian" else "en" |
| return _RUN_FAILURE[lang].format(reason=f"{detail} " if detail else "") |
|
|
|
|
| _DATA_GAP_LEAD = { |
| "en": "I can't answer that from the data sources connected to this analysis. ", |
| "id": "Saya tidak bisa menjawab itu dari sumber data yang terhubung ke analisis ini. ", |
| } |
|
|
|
|
| def data_gap_message(reason: str | None, reply_language: str | None = None) -> str: |
| """Answer for an infeasible analysis: the bound sources lack the asked-for data. |
| |
| `reason` is the planner's `infeasible_reason` (may be None/empty); |
| `reply_language` is the pipeline's detected language ("Indonesian"/"English"). |
| |
| The planner's reason is written FOR the user (planner.md: what is missing and the |
| nearest data that is available), so it is not held to the 200-char cap meant for |
| raw execution errors: that cap dropped all 18 of 18 reasons in the 2026-10-28 eval |
| runs (246–502 chars) and left only the generic "add a source" advice (2026-10-29). |
| Raw driver text is still never quoted. The generic advice is shown only when there |
| is no reason to show. |
| """ |
| detail = (reason or "").strip() |
| if any(m in detail for m in _RAW_ERROR_MARKERS): |
| detail = "" |
| lang = "id" if reply_language == "Indonesian" else "en" |
| if not detail: |
| return _DATA_GAP[lang].format(reason="") |
| if not detail.endswith((".", "!", "?")): |
| detail += "." |
| return _DATA_GAP_LEAD[lang] + detail |
|
|
|
|
| def out_of_scope_message(message: str) -> str: |
| """Refusal for a benign but out-of-scope request (the `out_of_scope` intent).""" |
| return _OUT_OF_SCOPE["id" if _is_indonesian(message) else "en"] |
|
|
|
|
| def blocked_message(message: str) -> str: |
| """Refusal for a blocked request (injection / secrets / abuse / content-filter).""" |
| return _BLOCKED["id" if _is_indonesian(message) else "en"] |
|
|
